High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

RA-MVS			99.37 1		99.96 9	98.86 39	99.98 24	98.73 78	97.97 24	99.92 6	99.94 5	97.85 7	100.00 1	99.98 9	100.00 1

test-260524					99.95 18	99.33 10		98.42 171		99.04 118		96.44 37	100.00 1	99.98 9	99.98 33

aaatest				99.60 25	99.96 9	98.79 45	99.97 44	98.88 55	96.36 92	99.07 115	99.93 13		100.00 1	99.98 9	99.96 49	99.99 27

MED-MVS		99.24 8	99.12 6	99.60 25	99.96 9	98.79 45	99.97 44	98.88 55	96.91 64	99.07 115	99.92 17	97.36 19	100.00 1	99.98 9	99.98 33	100.00 1

TestfortrainingZip				99.90 5	99.97 3	99.70 5	99.97 44	98.89 52	96.02 101	99.99 1	99.96 3	97.97 5	100.00 1		99.65 99	100.00 1

DVP-MVS++		99.26 6	99.09 11	99.77 10	99.91 46	99.31 13	99.95 77	98.43 159	96.48 82	99.80 30	99.93 13	97.44 16	100.00 1	99.92 18	99.98 33	100.00 1

MSC_two_6792asdad				99.93 2	99.91 46	99.80 2		98.41 177					100.00 1	99.96 14	100.00 1	100.00 1

PC_three_1452									96.96 62	99.80 30	99.79 64	97.49 12	100.00 1	99.99 5	99.98 33	100.00 1

No_MVS				99.93 2	99.91 46	99.80 2		98.41 177					100.00 1	99.96 14	100.00 1	100.00 1

SED-MVS		99.28 5	99.11 9	99.77 10	99.93 30	99.30 15	99.96 58	98.43 159	97.27 49	99.80 30	99.94 5	96.71 30	100.00 1	100.00 1	100.00 1	100.00 1

OPU-MVS				99.93 2	99.89 52	99.80 2	99.96 58				99.80 60	97.44 16	100.00 1	100.00 1	99.98 33	100.00 1

test_241102_TWO								98.43 159	97.27 49	99.80 30	99.94 5	97.18 24	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 30	99.30 15		98.43 159	97.26 51	99.80 30	99.88 30	96.71 30	100.00 1

DVP-MVS		99.30 4	99.16 4	99.73 14	99.93 30	99.29 18	99.95 77	98.32 201	97.28 47	99.83 26	99.91 20	97.22 22	100.00 1	99.99 5	100.00 1	99.89 99
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_THIRD									96.48 82	99.83 26	99.91 20	97.87 6	100.00 1	99.92 18	100.00 1	100.00 1

test_0728_SECOND				99.82 8	99.94 19	99.47 9	99.95 77	98.43 159					100.00 1	99.99 5	100.00 1	100.00 1

DPM-MVS		98.83 25	98.46 38	99.97 1	99.33 112	99.92 1	99.96 58	98.44 151	97.96 25	99.55 74	99.94 5	97.18 24	100.00 1	93.81 291	99.94 60	99.98 58

GST-MVS		98.27 64	97.97 74	99.17 67	99.92 38	97.57 111	99.93 102	98.39 184	94.04 180	98.80 131	99.74 90	92.98 139	100.00 1	98.16 149	99.76 90	99.93 89

SMA-MVS		98.76 30	98.48 37	99.62 23	99.87 58	98.87 37	99.86 149	98.38 188	93.19 220	99.77 42	99.94 5	95.54 53	100.00 1	99.74 46	99.99 22	100.00 1
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
ACMMP_NAP		98.49 46	98.14 61	99.54 33	99.66 91	98.62 63	99.85 152	98.37 191	94.68 142	99.53 77	99.83 52	92.87 142	100.00 1	98.66 118	99.84 81	99.99 27

MTAPA		98.29 63	97.96 77	99.30 53	99.85 63	97.93 93	99.39 298	98.28 208	95.76 109	97.18 211	99.88 30	92.74 146	100.00 1	98.67 116	99.88 78	99.99 27

HFP-MVS		98.56 40	98.37 45	99.14 74	99.96 9	97.43 119	99.95 77	98.61 102	94.77 137	99.31 98	99.85 39	94.22 99	100.00 1	98.70 114	99.98 33	99.98 58

region2R		98.54 42	98.37 45	99.05 84	99.96 9	97.18 129	99.96 58	98.55 122	94.87 134	99.45 84	99.85 39	94.07 105	100.00 1	98.67 116	100.00 1	99.98 58

HPM-MVS++		99.07 12	98.88 20	99.63 20	99.90 49	99.02 29	99.95 77	98.56 116	97.56 39	99.44 85	99.85 39	95.38 59	100.00 1	99.31 74	99.99 22	99.87 102

新几何1				99.42 44	99.75 78	98.27 74		98.63 99	92.69 251	99.55 74	99.82 55	94.40 88	100.00 1	91.21 334	99.94 60	99.99 27

无先验							99.49 281	98.71 80	93.46 205				100.00 1	94.36 275		99.99 27

MSLP-MVS++		99.13 10	99.01 13	99.49 38	99.94 19	98.46 70	99.98 24	98.86 59	97.10 55	99.80 30	99.94 5	95.92 46	100.00 1	99.51 62	100.00 1	100.00 1

ACMMPR		98.50 45	98.32 49	99.05 84	99.96 9	97.18 129	99.95 77	98.60 104	94.77 137	99.31 98	99.84 50	93.73 115	100.00 1	98.70 114	99.98 33	99.98 58

MP-MVS		98.23 72	97.97 74	99.03 86	99.94 19	97.17 133	99.95 77	98.39 184	94.70 141	98.26 168	99.81 59	91.84 177	100.00 1	98.85 104	99.97 45	99.93 89
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PGM-MVS		98.34 59	98.13 62	98.99 91	99.92 38	97.00 140	99.75 205	99.50 17	93.90 188	99.37 95	99.76 75	93.24 132	100.00 1	97.75 179	99.96 49	99.98 58

MCST-MVS		99.32 3	99.14 5	99.86 6	99.97 3	99.59 6	99.97 44	98.64 92	98.47 3	99.13 110	99.92 17	96.38 38	100.00 1	99.74 46	100.00 1	100.00 1

mPP-MVS		98.39 57	98.20 56	98.97 94	99.97 3	96.92 144	99.95 77	98.38 188	95.04 127	98.61 146	99.80 60	93.39 122	100.00 1	98.64 119	100.00 1	99.98 58

CNVR-MVS		99.40 1	99.26 2	99.84 7	99.98 2	99.51 8	99.98 24	98.69 83	98.20 10	99.93 4	99.98 2	96.82 27	100.00 1	99.75 44	100.00 1	99.99 27

NCCC		99.37 2	99.25 3	99.71 17	99.96 9	99.15 25	99.97 44	98.62 100	98.02 23	99.90 9	99.95 4	97.33 20	100.00 1	99.54 61	100.00 1	100.00 1

CP-MVS		98.45 49	98.32 49	98.87 100	99.96 9	96.62 159	99.97 44	98.39 184	94.43 155	98.90 125	99.87 33	94.30 96	100.00 1	99.04 89	99.99 22	99.99 27

DP-MVS Recon		98.41 54	98.02 70	99.56 31	99.97 3	98.70 56	99.92 105	98.44 151	92.06 287	98.40 161	99.84 50	95.68 51	100.00 1	98.19 147	99.71 94	99.97 68

PHI-MVS		98.41 54	98.21 55	99.03 86	99.86 60	97.10 137	99.98 24	98.80 71	90.78 338	99.62 64	99.78 68	95.30 60	100.00 1	99.80 35	99.93 66	99.99 27

DeepPCF-MVS	95.94 2	97.71 110	98.98 14	93.92 383	99.63 92	81.76 479	99.96 58	98.56 116	99.47 1	99.19 107	99.99 1	94.16 103	100.00 1	99.92 18	99.93 66	100.00 1

DeepC-MVS_fast	96.59 1	98.81 27	98.54 34	99.62 23	99.90 49	98.85 40	99.24 325	98.47 143	98.14 17	99.08 113	99.91 20	93.09 136	100.00 1	99.04 89	99.99 22	100.00 1
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
AdaColmap		97.23 133	96.80 143	98.51 135	99.99 1	95.60 207	99.09 338	98.84 65	93.32 214	96.74 230	99.72 97	86.04 271	100.00 1	98.01 158	99.43 132	99.94 88

TestfortrainingZip a		99.01 17	98.78 23	99.69 18	99.96 9	99.09 27	99.97 44	98.74 76	96.91 64	99.86 18	99.92 17	96.29 39	99.99 41	98.32 139	99.09 152	100.00 1

reproduce_model		98.75 31	98.66 28	99.03 86	99.71 85	97.10 137	99.73 216	98.23 216	97.02 60	99.18 108	99.90 24	94.54 85	99.99 41	99.77 40	99.90 74	99.99 27

reproduce-ours		98.78 28	98.67 26	99.09 81	99.70 87	97.30 123	99.74 209	98.25 212	97.10 55	99.10 111	99.90 24	94.59 81	99.99 41	99.77 40	99.91 72	99.99 27

our_new_method		98.78 28	98.67 26	99.09 81	99.70 87	97.30 123	99.74 209	98.25 212	97.10 55	99.10 111	99.90 24	94.59 81	99.99 41	99.77 40	99.91 72	99.99 27

test_fmvsm_n_1920		98.44 50	98.61 32	97.92 177	99.27 117	95.18 233	100.00 1	98.90 50	98.05 21	99.80 30	99.73 94	92.64 151	99.99 41	99.58 60	99.51 120	98.59 293

ZNCC-MVS		98.31 61	98.03 69	99.17 67	99.88 56	97.59 110	99.94 95	98.44 151	94.31 163	98.50 154	99.82 55	93.06 137	99.99 41	98.30 141	99.99 22	99.93 89

DPE-MVS		99.26 6	99.10 10	99.74 13	99.89 52	99.24 22	99.87 136	98.44 151	97.48 41	99.64 60	99.94 5	96.68 32	99.99 41	99.99 5	100.00 1	99.99 27
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MGCNet		99.06 14	98.84 21	99.72 15	99.76 75	99.21 24	99.99 8	99.34 25	98.70 2	99.44 85	99.75 83	93.24 132	99.99 41	99.94 16	99.41 134	99.95 84

testdata2													99.99 41	90.54 351

CPTT-MVS		97.64 113	97.32 118	98.58 124	99.97 3	95.77 196	99.96 58	98.35 194	89.90 361	98.36 162	99.79 64	91.18 186	99.99 41	98.37 136	99.99 22	99.99 27

API-MVS		97.86 89	97.66 96	98.47 137	99.52 101	95.41 215	99.47 285	98.87 58	91.68 302	98.84 127	99.85 39	92.34 163	99.99 41	98.44 131	99.96 49	100.00 1

ACMMP		97.74 105	97.44 111	98.66 115	99.92 38	96.13 185	99.18 330	99.45 18	94.84 135	96.41 249	99.71 100	91.40 180	99.99 41	97.99 160	98.03 194	99.87 102
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
fmvsm_l_conf0.5_n_9		98.55 41	98.23 53	99.49 38	99.10 127	98.50 68	99.99 8	98.70 81	98.14 17	99.94 2	99.68 114	89.02 223	99.98 53	99.89 23	99.61 107	99.99 27

aaEdge-Enhanced		99.07 12	98.89 19	99.59 28	99.93 30	98.79 45	99.95 77	98.80 71	95.89 106	99.28 102	99.93 13	96.28 40	99.98 53	99.98 9	99.96 49	99.99 27

lecture		98.67 34	98.46 38	99.28 54	99.86 60	97.88 95	99.97 44	99.25 30	96.07 99	99.79 39	99.70 103	92.53 156	99.98 53	99.51 62	99.48 124	99.97 68

test_fmvsmvis_n_1920		97.67 112	97.59 102	97.91 179	97.02 317	95.34 220	99.95 77	98.45 146	97.87 28	97.02 216	99.59 127	89.64 211	99.98 53	99.41 71	99.34 140	98.42 299

patch_mono-2		98.24 70	99.12 6	95.59 310	99.67 90	86.91 443	99.95 77	98.89 52	97.60 36	99.90 9	99.76 75	96.54 35	99.98 53	99.94 16	99.82 86	99.88 100

CANet_DTU		96.76 161	96.15 176	98.60 120	98.78 162	97.53 112	99.84 157	97.63 290	97.25 52	99.20 105	99.64 121	81.36 345	99.98 53	92.77 313	98.89 159	98.28 304

SD-MVS		98.92 22	98.70 25	99.56 31	99.70 87	98.73 54	99.94 95	98.34 198	96.38 88	99.81 28	99.76 75	94.59 81	99.98 53	99.84 31	99.96 49	99.97 68
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
PAPM_NR		98.12 76	97.93 80	98.70 111	99.94 19	96.13 185	99.82 172	98.43 159	94.56 145	97.52 196	99.70 103	94.40 88	99.98 53	97.00 202	99.98 33	99.99 27

PAPR		98.52 44	98.16 60	99.58 30	99.97 3	98.77 50	99.95 77	98.43 159	95.35 121	98.03 177	99.75 83	94.03 106	99.98 53	98.11 152	99.83 82	99.99 27

CSCG		97.10 140	97.04 130	97.27 247	99.89 52	91.92 346	99.90 119	99.07 37	88.67 385	95.26 282	99.82 55	93.17 135	99.98 53	98.15 150	99.47 127	99.90 98

CNLPA		97.76 103	97.38 114	98.92 98	99.53 100	96.84 146	99.87 136	98.14 235	93.78 192	96.55 238	99.69 107	92.28 164	99.98 53	97.13 197	99.44 131	99.93 89

MG-MVS		98.91 23	98.65 29	99.68 19	99.94 19	99.07 28	99.64 246	99.44 19	97.33 46	99.00 121	99.72 97	94.03 106	99.98 53	98.73 112	100.00 1	100.00 1

MAR-MVS		97.43 120	97.19 124	98.15 160	99.47 105	94.79 249	99.05 349	98.76 73	92.65 254	98.66 142	99.82 55	88.52 231	99.98 53	98.12 151	99.63 101	99.67 135
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
fmvsm_l_mol_unc0.5_1		99.14 9	98.92 16	99.81 9	99.03 132	99.54 7	99.98 24	97.90 261	98.36 5	99.94 2	99.78 68	95.70 50	99.97 66	99.83 34	99.75 91	99.92 94

fmvsm_s_conf0.5_n_9		98.15 74	98.02 70	98.55 126	99.28 115	95.84 193	99.99 8	98.57 110	98.17 14	99.93 4	99.74 90	87.04 253	99.97 66	99.86 29	99.59 111	99.83 107

fmvsm_s_conf0.5_n_8		98.38 58	98.05 68	99.35 51	99.20 120	98.12 80	99.98 24	98.81 67	98.22 8	99.80 30	99.71 100	87.37 248	99.97 66	99.91 21	99.48 124	99.97 68

fmvsm_l_conf0.5_n_3		98.41 54	98.08 66	99.39 47	99.12 126	98.29 73	99.98 24	98.64 92	98.14 17	99.86 18	99.76 75	87.99 236	99.97 66	99.72 49	99.54 114	99.91 97

fmvsm_s_conf0.5_n_3		97.95 82	97.66 96	98.81 103	98.99 139	98.07 83	99.98 24	98.81 67	98.18 13	99.89 13	99.70 103	84.15 312	99.97 66	99.76 43	99.50 122	98.39 300

fmvsm_l_conf0.5_n_a		99.00 19	98.91 17	99.28 54	99.21 119	97.91 94	99.98 24	98.85 62	98.25 6	99.92 6	99.75 83	94.72 77	99.97 66	99.87 27	99.64 100	99.95 84

fmvsm_l_conf0.5_n		98.94 20	98.84 21	99.25 57	99.17 123	97.81 99	99.98 24	98.86 59	98.25 6	99.90 9	99.76 75	94.21 101	99.97 66	99.87 27	99.52 117	99.98 58

fmvsm_s_conf0.5_n_a		97.73 107	97.72 92	97.77 192	98.63 174	94.26 273	99.96 58	98.92 49	97.18 54	99.75 44	99.69 107	87.00 255	99.97 66	99.46 67	98.89 159	99.08 257

fmvsm_s_conf0.5_n		97.80 99	97.85 87	97.67 201	99.06 130	94.41 265	99.98 24	98.97 43	97.34 44	99.63 61	99.69 107	87.27 249	99.97 66	99.62 58	99.06 154	98.62 292

test_cas_vis1_n_1920		96.59 175	96.23 170	97.65 204	98.22 211	94.23 275	99.99 8	97.25 354	97.77 31	99.58 73	99.08 194	77.10 391	99.97 66	97.64 181	99.45 130	98.74 287

test_vis1_n_1920		95.44 237	95.31 226	95.82 305	98.50 187	88.74 420	99.98 24	97.30 340	97.84 30	99.85 22	99.19 184	66.82 459	99.97 66	98.82 105	99.46 129	98.76 285

MP-MVS-pluss		98.07 79	97.64 98	99.38 50	99.74 79	98.41 72	99.74 209	98.18 225	93.35 211	96.45 242	99.85 39	92.64 151	99.97 66	98.91 100	99.89 75	99.77 118
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
PLC	95.54 3	97.93 84	97.89 84	98.05 168	99.82 67	94.77 250	99.92 105	98.46 145	93.93 185	97.20 209	99.27 168	95.44 58	99.97 66	97.41 186	99.51 120	99.41 202
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
fmvsm_s_conf0.5_n_5		98.08 78	97.71 94	99.17 67	98.67 169	97.69 107	99.99 8	98.57 110	97.40 42	99.89 13	99.69 107	85.99 272	99.96 79	99.80 35	99.40 135	99.85 105

MM		98.83 25	98.53 35	99.76 12	99.59 94	99.33 10	99.99 8	99.76 6	98.39 4	99.39 94	99.80 60	90.49 201	99.96 79	99.89 23	99.43 132	99.98 58

XVS		98.70 33	98.55 33	99.15 72	99.94 19	97.50 115	99.94 95	98.42 171	96.22 95	99.41 90	99.78 68	94.34 93	99.96 79	98.92 98	99.95 55	99.99 27

X-MVStestdata		93.83 294	92.06 330	99.15 72	99.94 19	97.50 115	99.94 95	98.42 171	96.22 95	99.41 90	41.37 557	94.34 93	99.96 79	98.92 98	99.95 55	99.99 27

原ACMM1				98.96 95	99.73 82	96.99 141		98.51 134	94.06 178	99.62 64	99.85 39	94.97 72	99.96 79	95.11 254	99.95 55	99.92 94

1314		96.84 156	95.96 189	99.48 41	96.74 343	98.52 66	98.31 418	98.86 59	95.82 107	89.91 352	98.98 213	87.49 245	99.96 79	97.80 172	99.73 93	99.96 76

MVS		96.60 174	95.56 211	99.72 15	96.85 335	99.22 23	98.31 418	98.94 44	91.57 304	90.90 337	99.61 126	86.66 261	99.96 79	97.36 188	99.88 78	99.99 27

UGNet		95.33 241	94.57 253	97.62 209	98.55 180	94.85 244	98.67 397	99.32 26	95.75 110	96.80 229	96.27 367	72.18 434	99.96 79	94.58 272	99.05 155	98.04 311
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
QAPM		95.40 238	94.17 264	99.10 80	96.92 329	97.71 103	99.40 294	98.68 85	89.31 367	88.94 381	98.89 229	82.48 332	99.96 79	93.12 309	99.83 82	99.62 150

fmvsm_s_conf0.5_n_11		98.03 80	97.89 84	98.46 139	99.35 111	97.76 101	99.99 8	98.04 245	98.20 10	99.90 9	99.78 68	86.21 269	99.95 88	99.89 23	99.68 96	97.65 322

CANet		98.27 64	97.82 89	99.63 20	99.72 84	99.10 26	99.98 24	98.51 134	97.00 61	98.52 151	99.71 100	87.80 237	99.95 88	99.75 44	99.38 136	99.83 107

旧先验2							99.46 289		94.21 169	99.85 22			99.95 88	96.96 206

PVSNet_BlendedMVS		96.05 207	95.82 200	96.72 271	99.59 94	96.99 141	99.95 77	99.10 34	94.06 178	98.27 166	95.80 380	89.00 224	99.95 88	99.12 82	87.53 369	93.24 441

PVSNet_Blended		97.94 83	97.64 98	98.83 102	99.59 94	96.99 141	100.00 1	99.10 34	95.38 120	98.27 166	99.08 194	89.00 224	99.95 88	99.12 82	99.25 143	99.57 165

DP-MVS		94.54 267	93.42 290	97.91 179	99.46 107	94.04 282	98.93 368	97.48 313	81.15 467	90.04 349	99.55 134	87.02 254	99.95 88	88.97 373	98.11 190	99.73 122

PVSNet	91.05 13	97.13 138	96.69 149	98.45 140	99.52 101	95.81 194	99.95 77	99.65 12	94.73 139	99.04 118	99.21 181	84.48 308	99.95 88	94.92 260	98.74 168	99.58 163

3Dnovator	91.47 12	96.28 197	95.34 225	99.08 83	96.82 337	97.47 118	99.45 290	98.81 67	95.52 118	89.39 368	99.00 208	81.97 336	99.95 88	97.27 190	99.83 82	99.84 106

LS3D		95.84 217	95.11 235	98.02 170	99.85 63	95.10 237	98.74 389	98.50 140	87.22 410	93.66 306	99.86 35	87.45 246	99.95 88	90.94 342	99.81 88	99.02 267

fmvsm_s_conf0.5_n_10		98.24 70	97.90 82	99.26 56	99.24 118	97.88 95	99.99 8	98.76 73	98.20 10	99.92 6	99.74 90	85.97 273	99.94 97	99.72 49	99.53 116	99.96 76

fmvsm_s_conf0.5_n_7		97.70 111	97.74 91	97.59 214	98.44 191	95.16 235	99.97 44	98.65 89	97.95 26	99.62 64	99.78 68	86.09 270	99.94 97	99.69 53	99.50 122	97.66 321

fmvsm_s_conf0.5_n_2		97.59 115	97.28 119	98.53 132	99.01 134	98.15 75	99.98 24	98.59 106	98.17 14	99.75 44	99.63 124	81.83 339	99.94 97	99.78 38	98.79 166	97.51 331

test_fmvsmconf_n		98.43 52	98.32 49	98.78 105	98.12 221	96.41 168	99.99 8	98.83 66	98.22 8	99.67 55	99.64 121	91.11 187	99.94 97	99.67 55	99.62 102	99.98 58

testdata				98.42 144	99.47 105	95.33 221		98.56 116	93.78 192	99.79 39	99.85 39	93.64 119	99.94 97	94.97 258	99.94 60	100.00 1

TSAR-MVS + GP.		98.60 38	98.51 36	98.86 101	99.73 82	96.63 158	99.97 44	97.92 259	98.07 20	98.76 137	99.55 134	95.00 70	99.94 97	99.91 21	97.68 201	99.99 27

DELS-MVS		98.54 42	98.22 54	99.50 36	99.15 125	98.65 61	100.00 1	98.58 108	97.70 34	98.21 172	99.24 177	92.58 154	99.94 97	98.63 121	99.94 60	99.92 94
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
F-COLMAP		96.93 152	96.95 133	96.87 265	99.71 85	91.74 356	99.85 152	97.95 254	93.11 228	95.72 271	99.16 189	92.35 162	99.94 97	95.32 250	99.35 139	98.92 275

3Dnovator+	91.53 11	96.31 194	95.24 229	99.52 34	96.88 334	98.64 62	99.72 220	98.24 214	95.27 124	88.42 397	98.98 213	82.76 330	99.94 97	97.10 199	99.83 82	99.96 76

OpenMVS	90.15 15	94.77 259	93.59 283	98.33 148	96.07 359	97.48 117	99.56 268	98.57 110	90.46 348	86.51 425	98.95 222	78.57 380	99.94 97	93.86 287	99.74 92	97.57 328

fmvsm_s_conf0.5_n_6		98.27 64	97.96 77	99.23 59	97.66 257	98.11 81	99.98 24	98.64 92	97.85 29	99.87 16	99.72 97	88.86 227	99.93 107	99.64 57	99.36 138	99.63 149

fmvsm_s_conf0.5_n_4		97.75 104	97.86 86	97.42 233	99.01 134	94.69 253	99.97 44	98.76 73	97.91 27	99.87 16	99.76 75	86.70 260	99.93 107	99.67 55	99.12 151	97.64 323

fmvsm_s_conf0.1_n_2		97.25 131	96.85 139	98.43 142	98.08 222	98.08 82	99.92 105	97.76 280	98.05 21	99.65 57	99.58 130	80.88 353	99.93 107	99.59 59	98.17 185	97.29 332

fmvsm_s_conf0.1_n_a		97.09 142	96.90 136	97.63 208	95.65 381	94.21 277	99.83 165	98.50 140	96.27 94	99.65 57	99.64 121	84.72 302	99.93 107	99.04 89	98.84 163	98.74 287

fmvsm_s_conf0.1_n		97.30 128	97.21 123	97.60 211	97.38 285	94.40 267	99.90 119	98.64 92	96.47 84	99.51 81	99.65 120	84.99 294	99.93 107	99.22 79	99.09 152	98.46 296

test_fmvs1		95.35 240	95.68 207	94.36 360	98.99 139	84.98 455	99.96 58	96.65 437	97.60 36	99.73 49	98.96 217	71.58 437	99.93 107	98.31 140	99.37 137	98.17 306

test_fmvs1_n		94.25 282	94.36 257	93.92 383	97.68 254	83.70 462	99.90 119	96.57 440	97.40 42	99.67 55	98.88 230	61.82 478	99.92 113	98.23 146	99.13 149	98.14 309

test_vis1_rt		86.87 422	86.05 420	89.34 452	96.12 357	78.07 491	99.87 136	83.54 525	92.03 288	78.21 480	89.51 491	45.80 502	99.91 114	96.25 234	93.11 326	90.03 486

EPNet		98.49 46	98.40 41	98.77 107	99.62 93	96.80 152	99.90 119	99.51 16	97.60 36	99.20 105	99.36 155	93.71 116	99.91 114	97.99 160	98.71 169	99.61 154
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvsmconf0.1_n		97.74 105	97.44 111	98.64 117	95.76 371	96.20 181	99.94 95	98.05 244	98.17 14	98.89 126	99.42 144	87.65 240	99.90 116	99.50 64	99.60 110	99.82 109

Anonymous20240529		92.10 342	90.65 355	96.47 278	98.82 159	90.61 388	98.72 391	98.67 88	75.54 490	93.90 305	98.58 272	66.23 461	99.90 116	94.70 269	90.67 333	98.90 278

CHOSEN 1792x2688		96.81 157	96.53 155	97.64 205	98.91 153	93.07 314	99.65 242	99.80 3	95.64 113	95.39 278	98.86 239	84.35 310	99.90 116	96.98 204	99.16 147	99.95 84

MVS_111021_LR		98.42 53	98.38 43	98.53 132	99.39 108	95.79 195	99.87 136	99.86 2	96.70 74	98.78 132	99.79 64	92.03 173	99.90 116	99.17 81	99.86 80	99.88 100

DeepC-MVS	94.51 4	96.92 153	96.40 165	98.45 140	99.16 124	95.90 191	99.66 241	98.06 242	96.37 91	94.37 297	99.49 139	83.29 326	99.90 116	97.63 182	99.61 107	99.55 167
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PS-MVSNAJ		98.44 50	98.20 56	99.16 70	98.80 161	98.92 33	99.54 273	98.17 226	97.34 44	99.85 22	99.85 39	91.20 183	99.89 121	99.41 71	99.67 97	98.69 290

VNet		97.21 134	96.57 154	99.13 78	98.97 142	97.82 98	99.03 352	99.21 32	94.31 163	99.18 108	98.88 230	86.26 268	99.89 121	98.93 96	94.32 309	99.69 132

sss		97.57 116	97.03 131	99.18 64	98.37 197	98.04 86	99.73 216	99.38 22	93.46 205	98.76 137	99.06 198	91.21 182	99.89 121	96.33 232	97.01 239	99.62 150

MVS_111021_HR		98.72 32	98.62 31	99.01 90	99.36 110	97.18 129	99.93 102	99.90 1	96.81 71	98.67 141	99.77 73	93.92 108	99.89 121	99.27 77	99.94 60	99.96 76

PVSNet_0	88.03 19	91.80 349	90.27 364	96.38 285	98.27 208	90.46 392	99.94 95	99.61 13	93.99 181	86.26 431	97.39 326	71.13 441	99.89 121	98.77 109	67.05 491	98.79 284

PCF-MVS	94.20 5	95.18 244	94.10 265	98.43 142	98.55 180	95.99 189	97.91 437	97.31 339	90.35 351	89.48 367	99.22 178	85.19 290	99.89 121	90.40 355	98.47 176	99.41 202
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Anonymous202405211		93.10 317	91.99 331	96.40 283	99.10 127	89.65 408	98.88 374	97.93 256	83.71 450	94.00 303	98.75 249	68.79 447	99.88 127	95.08 255	91.71 329	99.68 133

AllTest		92.48 334	91.64 338	95.00 330	99.01 134	88.43 426	98.94 365	96.82 428	86.50 420	88.71 383	98.47 284	74.73 421	99.88 127	85.39 420	96.18 263	96.71 337

TestCases				95.00 330	99.01 134	88.43 426		96.82 428	86.50 420	88.71 383	98.47 284	74.73 421	99.88 127	85.39 420	96.18 263	96.71 337

PVSNet_Blended_VisFu		97.27 130	96.81 142	98.66 115	98.81 160	96.67 157	99.92 105	98.64 92	94.51 147	96.38 250	98.49 280	89.05 222	99.88 127	97.10 199	98.34 178	99.43 198

MSDG		94.37 277	93.36 297	97.40 237	98.88 156	93.95 287	99.37 302	97.38 323	85.75 431	90.80 340	99.17 186	84.11 314	99.88 127	86.35 412	98.43 177	98.36 302

SF-MVS		98.67 34	98.40 41	99.50 36	99.77 74	98.67 57	99.90 119	98.21 221	93.53 200	99.81 28	99.89 28	94.70 79	99.86 132	99.84 31	99.93 66	99.96 76

test_fmvsmconf0.01_n		96.39 188	95.74 203	98.32 150	91.47 465	95.56 208	99.84 157	97.30 340	97.74 32	97.89 184	99.35 156	79.62 368	99.85 133	99.25 78	99.24 144	99.55 167

9.14			98.38 43		99.87 58		99.91 113	98.33 199	93.22 218	99.78 41	99.89 28	94.57 84	99.85 133	99.84 31	99.97 45

TEST9					99.92 38	98.92 33	99.96 58	98.43 159	93.90 188	99.71 51	99.86 35	95.88 47	99.85 133

train_agg		98.88 24	98.65 29	99.59 28	99.92 38	98.92 33	99.96 58	98.43 159	94.35 160	99.71 51	99.86 35	95.94 44	99.85 133	99.69 53	99.98 33	99.99 27

test_8					99.92 38	98.88 36	99.96 58	98.43 159	94.35 160	99.69 53	99.85 39	95.94 44	99.85 133

agg_prior					99.93 30	98.77 50		98.43 159		99.63 61			99.85 133

SteuartSystems-ACMMP		99.02 16	98.97 15	99.18 64	98.72 166	97.71 103	99.98 24	98.44 151	96.85 66	99.80 30	99.91 20	97.57 10	99.85 133	99.44 69	99.99 22	99.99 27
Skip Steuart: Steuart Systems R&D Blog.
COLMAP_ROB	90.47 14	92.18 341	91.49 344	94.25 364	99.00 138	88.04 432	98.42 414	96.70 435	82.30 462	88.43 395	99.01 204	76.97 396	99.85 133	86.11 416	96.50 253	94.86 348
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_yl		97.83 93	97.37 115	99.21 61	99.18 121	97.98 89	99.64 246	99.27 27	91.43 311	97.88 186	98.99 211	95.84 48	99.84 141	98.82 105	95.32 296	99.79 114

DCV-MVSNet		97.83 93	97.37 115	99.21 61	99.18 121	97.98 89	99.64 246	99.27 27	91.43 311	97.88 186	98.99 211	95.84 48	99.84 141	98.82 105	95.32 296	99.79 114

test_vis1_n		93.61 305	93.03 306	95.35 319	95.86 366	86.94 441	99.87 136	96.36 447	96.85 66	99.54 76	98.79 247	52.41 494	99.83 143	98.64 119	98.97 157	99.29 228

mvsany_test1		97.82 97	97.90 82	97.55 216	98.77 163	93.04 317	99.80 180	97.93 256	96.95 63	99.61 72	99.68 114	90.92 191	99.83 143	99.18 80	98.29 183	99.80 113

PatchMatch-RL		96.04 208	95.40 218	97.95 173	99.59 94	95.22 231	99.52 275	99.07 37	93.96 183	96.49 240	98.35 290	82.28 333	99.82 145	90.15 358	99.22 146	98.81 283

ZD-MVS					99.92 38	98.57 64		98.52 131	92.34 275	99.31 98	99.83 52	95.06 66	99.80 146	99.70 52	99.97 45

test_prior				99.43 42	99.94 19	98.49 69		98.65 89					99.80 146			99.99 27

APDe-MVS		99.06 14	98.91 17	99.51 35	99.94 19	98.76 53	99.91 113	98.39 184	97.20 53	99.46 83	99.85 39	95.53 55	99.79 148	99.86 29	100.00 1	99.99 27
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
XVG-OURS-SEG-HR		94.79 257	94.70 252	95.08 327	98.05 224	89.19 412	99.08 340	97.54 305	93.66 197	94.87 285	99.58 130	78.78 377	99.79 148	97.31 189	93.40 322	96.25 341

SR-MVS-dyc-post		98.31 61	98.17 59	98.71 110	99.79 71	96.37 172	99.76 198	98.31 203	94.43 155	99.40 92	99.75 83	93.28 130	99.78 150	98.90 101	99.92 69	99.97 68

SR-MVS		98.46 48	98.30 52	98.93 97	99.88 56	97.04 139	99.84 157	98.35 194	94.92 131	99.32 97	99.80 60	93.35 124	99.78 150	99.30 75	99.95 55	99.96 76

RPMNet		89.76 394	87.28 412	97.19 248	96.29 353	92.66 327	92.01 503	98.31 203	70.19 501	96.94 220	85.87 512	87.25 250	99.78 150	62.69 512	95.96 269	99.13 250

h-mvs33		94.92 253	94.36 257	96.59 276	98.85 158	91.29 374	98.93 368	98.94 44	95.90 104	98.77 134	98.42 287	90.89 194	99.77 153	97.80 172	70.76 477	98.72 289

VDD-MVS		93.77 299	92.94 309	96.27 288	98.55 180	90.22 397	98.77 388	97.79 272	90.85 330	96.82 227	99.42 144	61.18 481	99.77 153	98.95 94	94.13 312	98.82 282

HY-MVS	92.50 7	97.79 101	97.17 126	99.63 20	98.98 141	99.32 12	97.49 444	99.52 14	95.69 112	98.32 164	97.41 324	93.32 126	99.77 153	98.08 155	95.75 280	99.81 111

APD-MVS_3200maxsize		98.25 69	98.08 66	98.78 105	99.81 69	96.60 161	99.82 172	98.30 206	93.95 184	99.37 95	99.77 73	92.84 143	99.76 156	98.95 94	99.92 69	99.97 68

CDPH-MVS		98.65 36	98.36 47	99.49 38	99.94 19	98.73 54	99.87 136	98.33 199	93.97 182	99.76 43	99.87 33	94.99 71	99.75 157	98.55 123	100.00 1	99.98 58

test12				99.43 42	99.74 79	98.56 65		98.40 181		99.65 57		94.76 76	99.75 157		99.98 33	99.99 27

XVG-OURS		94.82 254	94.74 251	95.06 328	98.00 226	89.19 412	99.08 340	97.55 303	94.10 174	94.71 287	99.62 125	80.51 360	99.74 159	96.04 238	93.06 327	96.25 341

APD-MVS		98.62 37	98.35 48	99.41 45	99.90 49	98.51 67	99.87 136	98.36 192	94.08 175	99.74 47	99.73 94	94.08 104	99.74 159	99.42 70	99.99 22	99.99 27
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
WTY-MVS		98.10 77	97.60 100	99.60 25	98.92 149	99.28 20	99.89 130	99.52 14	95.58 115	98.24 170	99.39 152	93.33 125	99.74 159	97.98 162	95.58 289	99.78 117

EI-MVSNet-UG-set		98.14 75	97.99 72	98.60 120	99.80 70	96.27 174	99.36 304	98.50 140	95.21 125	98.30 165	99.75 83	93.29 129	99.73 162	98.37 136	99.30 141	99.81 111

MSP-MVS		99.09 11	99.12 6	98.98 93	99.93 30	97.24 126	99.95 77	98.42 171	97.50 40	99.52 79	99.88 30	97.43 18	99.71 163	99.50 64	99.98 33	100.00 1
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
xiu_mvs_v2_base		98.23 72	97.97 74	99.02 89	98.69 167	98.66 59	99.52 275	98.08 241	97.05 58	99.86 18	99.86 35	90.65 196	99.71 163	99.39 73	98.63 170	98.69 290

EI-MVSNet-Vis-set		98.27 64	98.11 64	98.75 108	99.83 66	96.59 163	99.40 294	98.51 134	95.29 123	98.51 153	99.76 75	93.60 120	99.71 163	98.53 126	99.52 117	99.95 84

ab-mvs		94.69 262	93.42 290	98.51 135	98.07 223	96.26 175	96.49 468	98.68 85	90.31 353	94.54 290	97.00 340	76.30 406	99.71 163	95.98 239	93.38 323	99.56 166

testing3-2		97.72 108	97.43 113	98.60 120	98.55 180	97.11 136	100.00 1	99.23 31	93.78 192	97.90 182	98.73 251	95.50 56	99.69 167	98.53 126	94.63 303	98.99 269

xiu_mvs_v1_base_debu		97.43 120	97.06 127	98.55 126	97.74 244	98.14 77	99.31 312	97.86 266	96.43 85	99.62 64	99.69 107	85.56 282	99.68 168	99.05 86	98.31 180	97.83 316

xiu_mvs_v1_base		97.43 120	97.06 127	98.55 126	97.74 244	98.14 77	99.31 312	97.86 266	96.43 85	99.62 64	99.69 107	85.56 282	99.68 168	99.05 86	98.31 180	97.83 316

xiu_mvs_v1_base_debi		97.43 120	97.06 127	98.55 126	97.74 244	98.14 77	99.31 312	97.86 266	96.43 85	99.62 64	99.69 107	85.56 282	99.68 168	99.05 86	98.31 180	97.83 316

NormalMVS		97.90 86	97.85 87	98.04 169	99.86 60	95.39 217	99.61 253	97.78 276	96.52 80	98.61 146	99.31 160	92.73 147	99.67 171	96.77 218	99.48 124	99.06 259

SymmetryMVS		97.64 113	97.46 108	98.17 157	98.74 165	95.39 217	99.61 253	99.26 29	96.52 80	98.61 146	99.31 160	92.73 147	99.67 171	96.77 218	95.63 287	99.45 194

HPM-MVS		97.96 81	97.72 92	98.68 112	99.84 65	96.39 171	99.90 119	98.17 226	92.61 256	98.62 145	99.57 133	91.87 176	99.67 171	98.87 103	99.99 22	99.99 27
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
UA-Net		96.54 179	95.96 189	98.27 153	98.23 210	95.71 200	98.00 434	98.45 146	93.72 196	98.41 159	99.27 168	88.71 230	99.66 174	91.19 335	97.69 199	99.44 197

HPM-MVS_fast		97.80 99	97.50 106	98.68 112	99.79 71	96.42 167	99.88 133	98.16 231	91.75 299	98.94 123	99.54 136	91.82 178	99.65 175	97.62 183	99.99 22	99.99 27

114514_t		97.41 125	96.83 140	99.14 74	99.51 103	97.83 97	99.89 130	98.27 210	88.48 390	99.06 117	99.66 118	90.30 204	99.64 176	96.32 233	99.97 45	99.96 76

TSAR-MVS + MP.		98.93 21	98.77 24	99.41 45	99.74 79	98.67 57	99.77 192	98.38 188	96.73 73	99.88 15	99.74 90	94.89 73	99.59 177	99.80 35	99.98 33	99.97 68
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
LFMVS		94.75 261	93.56 285	98.30 151	99.03 132	95.70 201	98.74 389	97.98 251	87.81 403	98.47 155	99.39 152	67.43 456	99.53 178	98.01 158	95.20 299	99.67 135

sasdasda		97.09 142	96.32 167	99.39 47	98.93 146	98.95 31	99.72 220	97.35 328	94.45 151	97.88 186	99.42 144	86.71 258	99.52 179	98.48 128	93.97 315	99.72 124

canonicalmvs		97.09 142	96.32 167	99.39 47	98.93 146	98.95 31	99.72 220	97.35 328	94.45 151	97.88 186	99.42 144	86.71 258	99.52 179	98.48 128	93.97 315	99.72 124

thres200		96.96 149	96.21 173	99.22 60	98.97 142	98.84 41	99.85 152	99.71 7	93.17 222	96.26 252	98.88 230	89.87 209	99.51 181	94.26 279	94.91 301	99.31 223

OMC-MVS		97.28 129	97.23 122	97.41 236	99.76 75	93.36 311	99.65 242	97.95 254	96.03 100	97.41 202	99.70 103	89.61 212	99.51 181	96.73 221	98.25 184	99.38 205

MGCFI-Net		97.00 147	96.22 172	99.34 52	98.86 157	98.80 44	99.67 240	97.30 340	94.31 163	97.77 192	99.41 149	86.36 266	99.50 183	98.38 134	93.90 317	99.72 124

thres100view900		96.74 166	95.92 195	99.18 64	98.90 154	98.77 50	99.74 209	99.71 7	92.59 258	95.84 265	98.86 239	89.25 218	99.50 183	93.84 288	94.57 305	99.27 233

tfpn200view9		96.79 158	95.99 183	99.19 63	98.94 144	98.82 42	99.78 186	99.71 7	92.86 238	96.02 262	98.87 237	89.33 216	99.50 183	93.84 288	94.57 305	99.27 233

thres600view7		96.69 169	95.87 199	99.14 74	98.90 154	98.78 49	99.74 209	99.71 7	92.59 258	95.84 265	98.86 239	89.25 218	99.50 183	93.44 301	94.50 308	99.16 246

thres400		96.78 160	95.99 183	99.16 70	98.94 144	98.82 42	99.78 186	99.71 7	92.86 238	96.02 262	98.87 237	89.33 216	99.50 183	93.84 288	94.57 305	99.16 246

FE-MVS		95.70 230	95.01 240	97.79 188	98.21 212	94.57 255	95.03 484	98.69 83	88.90 379	97.50 198	96.19 369	92.60 153	99.49 188	89.99 360	97.94 196	99.31 223

myMVS_eth3d28		97.86 89	97.59 102	98.68 112	98.50 187	97.26 125	99.92 105	98.55 122	93.79 191	98.26 168	98.75 249	95.20 61	99.48 189	98.93 96	96.40 256	99.29 228

VDDNet		93.12 316	91.91 333	96.76 269	96.67 348	92.65 329	98.69 395	98.21 221	82.81 459	97.75 193	99.28 164	61.57 479	99.48 189	98.09 154	94.09 313	98.15 307

FA-MVS(test-final)		95.86 215	95.09 236	98.15 160	97.74 244	95.62 206	96.31 472	98.17 226	91.42 313	96.26 252	96.13 373	90.56 199	99.47 191	92.18 318	97.07 230	99.35 213

RPSCF		91.80 349	92.79 313	88.83 456	98.15 218	69.87 503	98.11 430	96.60 439	83.93 448	94.33 298	99.27 168	79.60 369	99.46 192	91.99 324	93.16 325	97.18 334

alignmvs		97.81 98	97.33 117	99.25 57	98.77 163	98.66 59	99.99 8	98.44 151	94.40 159	98.41 159	99.47 140	93.65 118	99.42 193	98.57 122	94.26 311	99.67 135

KinetiMVS		96.10 204	95.29 228	98.53 132	97.08 310	97.12 134	99.56 268	98.12 237	94.78 136	98.44 156	98.94 224	80.30 364	99.39 194	91.56 331	98.79 166	99.06 259

RRT-MVS		96.24 200	95.68 207	97.94 176	97.65 258	94.92 243	99.27 322	97.10 386	92.79 244	97.43 201	97.99 307	81.85 338	99.37 195	98.46 130	98.57 171	99.53 175

balanced_ft_v1		96.88 154	96.52 156	97.96 172	98.60 175	94.94 242	99.41 293	97.56 302	93.53 200	99.42 89	97.89 313	83.33 325	99.31 196	99.29 76	99.62 102	99.64 141

Test_1112_low_res		95.72 226	94.83 245	98.42 144	97.79 240	96.41 168	99.65 242	96.65 437	92.70 250	92.86 318	96.13 373	92.15 170	99.30 197	91.88 327	93.64 319	99.55 167

1112_ss		96.01 209	95.20 231	98.42 144	97.80 239	96.41 168	99.65 242	96.66 436	92.71 249	92.88 317	99.40 150	92.16 169	99.30 197	91.92 326	93.66 318	99.55 167

BridgeMVS		98.27 64	97.99 72	99.11 79	98.64 173	98.43 71	99.47 285	97.79 272	94.56 145	99.74 47	98.35 290	94.33 95	99.25 199	99.12 82	99.96 49	99.64 141

MVSMamba_PlusPlus		97.83 93	97.45 110	98.99 91	98.60 175	98.15 75	99.58 260	97.74 281	90.34 352	99.26 104	98.32 293	94.29 97	99.23 200	99.03 92	99.89 75	99.58 163

testing11		97.48 119	97.27 120	98.10 164	98.36 198	96.02 188	99.92 105	98.45 146	93.45 207	98.15 174	98.70 255	95.48 57	99.22 201	97.85 169	95.05 300	99.07 258

testing91		97.16 136	96.90 136	97.97 171	98.35 200	95.67 204	99.91 113	98.42 171	92.91 236	97.33 205	98.72 252	94.81 75	99.21 202	96.98 204	94.63 303	99.03 266

testing99		97.17 135	96.91 135	97.95 173	98.35 200	95.70 201	99.91 113	98.43 159	92.94 234	97.36 203	98.72 252	94.83 74	99.21 202	97.00 202	94.64 302	98.95 271

cascas		94.64 265	93.61 280	97.74 196	97.82 238	96.26 175	99.96 58	97.78 276	85.76 429	94.00 303	97.54 320	76.95 397	99.21 202	97.23 194	95.43 293	97.76 320

test2506		97.53 117	97.19 124	98.58 124	98.66 171	96.90 145	98.81 383	99.77 5	94.93 129	97.95 180	98.96 217	92.51 157	99.20 205	94.93 259	98.15 187	99.64 141

ECVR-MVS		95.66 231	95.05 238	97.51 221	98.66 171	93.71 292	98.85 380	98.45 146	94.93 129	96.86 223	98.96 217	75.22 417	99.20 205	95.34 249	98.15 187	99.64 141

TAPA-MVS	92.12 8	94.42 275	93.60 282	96.90 264	99.33 112	91.78 355	99.78 186	98.00 248	89.89 362	94.52 291	99.47 140	91.97 174	99.18 207	69.90 491	99.52 117	99.73 122
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
UBG		97.84 92	97.69 95	98.29 152	98.38 195	96.59 163	99.90 119	98.53 129	93.91 187	98.52 151	98.42 287	96.77 28	99.17 208	98.54 124	96.20 262	99.11 253

IB-MVS	92.85 6	94.99 251	93.94 273	98.16 158	97.72 249	95.69 203	99.99 8	98.81 67	94.28 166	92.70 319	96.90 344	95.08 65	99.17 208	96.07 237	73.88 465	99.60 156
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
dcpmvs_2		97.42 124	98.09 65	95.42 317	99.58 98	87.24 439	99.23 326	96.95 413	94.28 166	98.93 124	99.73 94	94.39 91	99.16 210	99.89 23	99.82 86	99.86 104

test1111		95.57 234	94.98 241	97.37 239	98.56 177	93.37 310	98.86 378	98.45 146	94.95 128	96.63 232	98.95 222	75.21 418	99.11 211	95.02 256	98.14 189	99.64 141

thisisatest0515		97.41 125	97.02 132	98.59 123	97.71 251	97.52 113	99.97 44	98.54 126	91.83 294	97.45 200	99.04 200	97.50 11	99.10 212	94.75 267	96.37 258	99.16 246

GDP-MVS		97.88 87	97.59 102	98.75 108	97.59 265	97.81 99	99.95 77	97.37 326	94.44 154	99.08 113	99.58 130	97.13 26	99.08 213	94.99 257	98.17 185	99.37 207

BP-MVS1		98.33 60	98.18 58	98.81 103	97.44 278	97.98 89	99.96 58	98.17 226	94.88 133	98.77 134	99.59 127	97.59 9	99.08 213	98.24 145	98.93 158	99.36 209

thisisatest0530		97.10 140	96.72 147	98.22 155	97.60 264	96.70 153	99.92 105	98.54 126	91.11 323	97.07 215	98.97 215	97.47 14	99.03 215	93.73 296	96.09 265	98.92 275

tttt0517		96.85 155	96.49 157	97.92 177	97.48 275	95.89 192	99.85 152	98.54 126	90.72 340	96.63 232	98.93 227	97.47 14	99.02 216	93.03 310	95.76 279	98.85 280

AstraMVS		96.57 177	96.46 160	96.91 262	96.79 341	92.50 332	99.90 119	97.38 323	96.02 101	97.79 191	99.32 157	86.36 266	98.99 217	98.26 144	96.33 259	99.23 240

Elysia		94.50 271	93.38 294	97.85 183	96.49 350	96.70 153	98.98 357	97.78 276	90.81 332	96.19 255	98.55 276	73.63 429	98.98 218	89.41 364	98.56 172	97.88 314

StellarMVS		94.50 271	93.38 294	97.85 183	96.49 350	96.70 153	98.98 357	97.78 276	90.81 332	96.19 255	98.55 276	73.63 429	98.98 218	89.41 364	98.56 172	97.88 314

testing915		97.83 93	97.48 107	98.88 99	98.41 193	97.68 108	99.87 136	98.64 92	93.35 211	98.82 130	98.62 265	94.60 80	98.97 220	98.72 113	96.25 261	100.00 1

mmtdpeth		88.52 406	87.75 409	90.85 435	95.71 377	83.47 467	98.94 365	94.85 481	88.78 382	97.19 210	89.58 489	63.29 472	98.97 220	98.54 124	62.86 500	90.10 485

MVS_Test		96.46 183	95.74 203	98.61 119	98.18 215	97.23 127	99.31 312	97.15 372	91.07 325	98.84 127	97.05 337	88.17 234	98.97 220	94.38 274	97.50 204	99.61 154

FBQ-MVS		97.12 139	96.92 134	97.72 197	98.35 200	94.55 256	99.87 136	98.62 100	93.23 217	98.60 149	98.39 289	93.66 117	98.96 223	95.76 245	95.82 276	99.64 141

tt0805		91.28 358	90.18 367	94.60 345	96.26 355	87.55 435	98.39 416	98.72 79	89.00 373	89.22 374	98.47 284	62.98 474	98.96 223	90.57 349	88.00 361	97.28 333

tpmvs		94.28 281	93.57 284	96.40 283	98.55 180	91.50 372	95.70 483	98.55 122	87.47 405	92.15 324	94.26 447	91.42 179	98.95 225	88.15 390	95.85 274	98.76 285

viewdifsd2359ckpt07		95.83 218	95.42 216	97.07 256	97.40 282	93.04 317	99.60 256	97.24 357	92.39 273	96.09 259	99.14 191	83.07 329	98.93 226	97.02 201	96.87 242	99.23 240

SDMVSNet		94.80 256	93.96 272	97.33 244	98.92 149	95.42 214	99.59 258	98.99 40	92.41 271	92.55 321	97.85 314	75.81 411	98.93 226	97.90 167	91.62 330	97.64 323

viewmsd2359difaftdt		94.09 287	93.64 278	95.46 315	96.68 346	88.92 417	99.62 249	97.13 377	93.07 229	95.73 269	99.22 178	77.05 392	98.89 228	96.52 228	87.70 366	98.58 294

viewdifsd2359ckpt11		94.09 287	93.63 279	95.46 315	96.68 346	88.92 417	99.62 249	97.12 378	93.07 229	95.73 269	99.22 178	77.05 392	98.88 229	96.52 228	87.69 367	98.58 294

Casviewmamba		96.25 199	95.89 197	97.32 246	97.45 277	93.68 295	99.80 180	97.22 361	93.38 209	96.86 223	99.28 164	84.64 304	98.87 230	97.18 196	97.19 219	99.41 202

EIA-MVS		97.53 117	97.46 108	97.76 194	98.04 225	94.84 245	99.98 24	97.61 296	94.41 158	97.90 182	99.59 127	92.40 161	98.87 230	98.04 157	99.13 149	99.59 157

tpm cat1		93.51 307	92.52 323	96.47 278	97.77 242	91.47 373	96.13 475	98.06 242	80.98 468	92.91 316	93.78 452	89.66 210	98.87 230	87.03 407	96.39 257	99.09 255

UWE-MVS		96.79 158	96.72 147	97.00 258	98.51 185	93.70 293	99.71 225	98.60 104	92.96 233	97.09 213	98.34 292	96.67 34	98.85 233	92.11 323	96.50 253	98.44 298

E4		96.01 209	95.53 213	97.44 231	97.05 313	94.23 275	99.57 264	97.30 340	92.72 247	96.47 241	99.02 201	83.98 315	98.83 234	96.92 208	96.77 245	99.27 233

E3new		96.75 163	96.43 162	97.71 198	97.79 240	94.83 246	99.80 180	97.33 332	93.52 203	97.49 199	99.31 160	87.73 238	98.83 234	97.52 184	97.40 209	99.48 186

viewcassd2359sk11		96.59 175	96.23 170	97.66 203	97.63 261	94.70 251	99.77 192	97.33 332	93.41 208	97.34 204	99.17 186	86.72 257	98.83 234	97.40 187	97.32 213	99.46 189

E2		96.36 190	95.95 191	97.60 211	97.41 280	94.52 258	99.71 225	97.33 332	93.20 219	97.02 216	99.07 196	85.37 287	98.82 237	97.27 190	97.14 226	99.46 189

E3		96.36 190	95.95 191	97.60 211	97.37 287	94.52 258	99.71 225	97.33 332	93.18 221	97.02 216	99.07 196	85.45 285	98.82 237	97.27 190	97.14 226	99.46 189

guyue		97.15 137	96.82 141	98.15 160	97.56 267	96.25 179	99.71 225	97.84 269	95.75 110	98.13 175	98.65 260	87.58 242	98.82 237	98.29 142	97.91 197	99.36 209

ETV-MVS		97.92 85	97.80 90	98.25 154	98.14 219	96.48 165	99.98 24	97.63 290	95.61 114	99.29 101	99.46 142	92.55 155	98.82 237	99.02 93	98.54 174	99.46 189

onestephybrid01		96.75 163	96.44 161	97.71 198	97.47 276	95.03 238	99.83 165	97.27 350	94.15 171	98.66 142	99.25 175	85.72 276	98.81 241	98.42 132	97.17 224	99.28 230

E5new		95.83 218	95.39 219	97.15 249	97.03 314	93.59 297	99.32 310	97.30 340	92.58 260	96.45 242	99.00 208	83.37 322	98.81 241	96.81 214	96.65 248	99.04 262

E6new		95.83 218	95.39 219	97.14 251	97.00 321	93.58 299	99.31 312	97.30 340	92.57 262	96.45 242	99.01 204	83.44 320	98.81 241	96.80 216	96.66 246	99.04 262

E6		95.83 218	95.39 219	97.14 251	97.00 321	93.58 299	99.31 312	97.30 340	92.57 262	96.45 242	99.01 204	83.44 320	98.81 241	96.80 216	96.66 246	99.04 262

E5		95.83 218	95.39 219	97.15 249	97.03 314	93.59 297	99.32 310	97.30 340	92.58 260	96.45 242	99.00 208	83.37 322	98.81 241	96.81 214	96.65 248	99.04 262

hybridnocas07		96.57 177	96.16 175	97.81 185	97.36 290	95.32 222	99.81 174	97.12 378	94.17 170	98.02 178	98.90 228	85.05 292	98.80 246	97.85 169	97.18 220	99.32 218

BH-RMVSNet		95.18 244	94.31 260	97.80 186	98.17 216	95.23 230	99.76 198	97.53 307	92.52 267	94.27 300	99.25 175	76.84 398	98.80 246	90.89 344	99.54 114	99.35 213

IMVS_0403		95.25 242	94.81 247	96.58 277	96.97 323	91.64 364	98.97 362	97.12 378	92.33 276	95.43 277	98.88 230	85.78 275	98.79 248	92.12 319	95.70 283	99.32 218

gm-plane-assit					96.97 323	93.76 291			91.47 309		98.96 217		98.79 248	94.92 260

casdiffmvs		96.42 187	95.97 188	97.77 192	97.30 297	94.98 239	99.84 157	97.09 389	93.75 195	96.58 235	99.26 172	85.07 291	98.78 250	97.77 177	97.04 234	99.54 171
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
diffmvs_AUTHOR		96.75 163	96.41 164	97.79 188	97.20 304	95.46 211	99.69 235	97.15 372	94.46 150	98.78 132	99.21 181	85.64 279	98.77 251	98.27 143	97.31 214	99.13 250

TR-MVS		94.54 267	93.56 285	97.49 226	97.96 229	94.34 271	98.71 392	97.51 310	90.30 354	94.51 292	98.69 256	75.56 412	98.77 251	92.82 312	95.99 267	99.35 213

diffmvs		97.00 147	96.64 150	98.09 165	97.64 259	96.17 184	99.81 174	97.19 363	94.67 143	98.95 122	99.28 164	86.43 263	98.76 253	98.37 136	97.42 207	99.33 216
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Vis-MVSNet		95.72 226	95.15 234	97.45 228	97.62 262	94.28 272	99.28 320	98.24 214	94.27 168	96.84 225	98.94 224	79.39 370	98.76 253	93.25 303	98.49 175	99.30 226
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
viewmambaseed2359dif		95.92 214	95.55 212	97.04 257	97.38 285	93.41 307	99.78 186	96.97 411	91.14 322	96.58 235	99.27 168	84.85 296	98.75 255	96.87 211	97.12 228	98.97 270

mvsmamba		96.94 150	96.73 146	97.55 216	97.99 227	94.37 269	99.62 249	97.70 283	93.13 226	98.42 158	97.92 310	88.02 235	98.75 255	98.78 108	99.01 156	99.52 176

dtuplus		95.79 223	95.42 216	96.93 261	97.24 303	93.16 312	99.78 186	96.93 418	91.69 301	96.18 257	99.29 163	83.80 316	98.73 257	96.83 213	97.02 237	98.89 279

tpmrst		96.27 198	95.98 185	97.13 253	97.96 229	93.15 313	96.34 471	98.17 226	92.07 285	98.71 140	95.12 418	93.91 109	98.73 257	94.91 262	96.62 250	99.50 183

PMMVS		96.76 161	96.76 144	96.76 269	98.28 207	92.10 341	99.91 113	97.98 251	94.12 173	99.53 77	99.39 152	86.93 256	98.73 257	96.95 207	97.73 198	99.45 194

casdiffmvs_mvg		96.43 185	95.94 193	97.89 181	97.44 278	95.47 210	99.86 149	97.29 348	93.35 211	96.03 260	99.19 184	85.39 286	98.72 260	97.89 168	97.04 234	99.49 185
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewmanbaseed2359cas		96.45 184	96.07 179	97.59 214	97.55 268	94.59 254	99.70 232	97.33 332	93.62 199	97.00 219	99.32 157	85.57 281	98.71 261	97.26 193	97.33 212	99.47 187

LuminaMVS		96.63 172	96.21 173	97.87 182	95.58 385	96.82 147	99.12 334	97.67 286	94.47 149	97.88 186	98.31 295	87.50 244	98.71 261	98.07 156	97.29 215	98.10 310

lupinMVS		97.85 91	97.60 100	98.62 118	97.28 299	97.70 105	99.99 8	97.55 303	95.50 119	99.43 87	99.67 116	90.92 191	98.71 261	98.40 133	99.62 102	99.45 194

hybrid		96.53 180	96.15 176	97.67 201	97.39 284	95.12 236	99.80 180	97.15 372	93.38 209	98.23 171	99.16 189	85.20 289	98.70 264	97.92 164	97.15 225	99.20 243

Effi-MVS+		96.30 195	95.69 205	98.16 158	97.85 236	96.26 175	97.41 447	97.21 362	90.37 350	98.65 144	98.58 272	86.61 262	98.70 264	97.11 198	97.37 210	99.52 176

baseline1		95.78 224	94.86 244	98.54 130	98.47 190	98.07 83	99.06 345	97.99 249	92.68 252	94.13 302	98.62 265	93.28 130	98.69 266	93.79 293	85.76 379	98.84 281

viewmacassd2359aftdt		95.93 213	95.45 214	97.36 241	97.09 309	94.12 281	99.57 264	97.26 353	93.05 231	96.50 239	99.17 186	82.76 330	98.68 267	96.61 223	97.04 234	99.28 230

sd_testset		93.55 306	92.83 311	95.74 308	98.92 149	90.89 382	98.24 422	98.85 62	92.41 271	92.55 321	97.85 314	71.07 442	98.68 267	93.93 285	91.62 330	97.64 323

mamba_0408		94.98 252	94.09 266	97.64 205	97.14 305	95.31 223	93.48 495	97.08 390	90.48 346	94.40 294	98.62 265	84.49 306	98.67 269	93.99 283	97.18 220	98.93 272

SSM_0404		95.75 225	95.16 233	97.50 223	97.53 270	95.39 217	99.11 336	97.25 354	90.81 332	95.27 281	98.83 244	84.74 300	98.67 269	95.24 252	97.69 199	98.45 297

BH-w/o		95.71 228	95.38 224	96.68 272	98.49 189	92.28 337	99.84 157	97.50 311	92.12 284	92.06 327	98.79 247	84.69 303	98.67 269	95.29 251	99.66 98	99.09 255

viewmamba		96.61 173	96.34 166	97.42 233	97.26 302	94.37 269	99.83 165	97.16 369	94.51 147	97.89 184	99.26 172	86.38 264	98.66 272	97.70 180	97.06 233	99.23 240

viewdifsd2359ckpt09		96.21 202	95.77 201	97.53 218	97.69 253	94.50 260	99.78 186	97.23 359	92.88 237	96.58 235	99.26 172	84.85 296	98.66 272	96.61 223	97.02 237	99.43 198

hybridcas		96.09 206	95.62 209	97.50 223	97.37 287	94.44 261	99.84 157	97.16 369	93.16 223	96.03 260	99.21 181	84.19 311	98.65 274	96.53 227	97.07 230	99.42 201

viewdifsd2359ckpt13		96.19 203	95.77 201	97.45 228	97.62 262	94.40 267	99.70 232	97.23 359	92.76 246	96.63 232	99.05 199	84.96 295	98.64 275	96.65 222	97.35 211	99.31 223

baseline		96.43 185	95.98 185	97.76 194	97.34 292	95.17 234	99.51 277	97.17 367	93.92 186	96.90 222	99.28 164	85.37 287	98.64 275	97.50 185	96.86 244	99.46 189

baseline2		96.71 168	96.49 157	97.37 239	95.63 383	95.96 190	99.74 209	98.88 55	92.94 234	91.61 329	98.97 215	97.72 8	98.62 277	94.83 264	98.08 193	97.53 330

0.3-1-1-0.015		94.22 283	93.13 305	97.49 226	95.49 386	94.17 278	100.00 1	98.22 217	88.44 392	97.14 212	97.04 339	92.73 147	98.59 278	96.45 230	72.65 471	99.70 127

SSM_0407		95.62 233	94.95 242	97.61 210	97.14 305	95.31 223	99.00 355	97.25 354	90.81 332	94.40 294	98.83 244	84.74 300	98.58 279	95.24 252	97.18 220	98.93 272

MDTV_nov1_ep13			95.69 205		97.90 232	94.15 279	95.98 479	98.44 151	93.12 227	97.98 179	95.74 382	95.10 64	98.58 279	90.02 359	96.92 241

0.4-1-1-0.2		94.14 284	93.02 307	97.51 221	95.45 387	94.25 274	100.00 1	98.22 217	88.53 389	96.83 226	96.95 342	92.25 166	98.57 281	96.34 231	72.65 471	99.70 127

0.4-1-1-0.1		94.07 289	92.95 308	97.42 233	95.24 391	94.00 285	100.00 1	98.22 217	88.27 396	96.81 228	96.93 343	92.27 165	98.56 282	96.21 236	72.63 473	99.70 127

jason		97.24 132	96.86 138	98.38 147	95.73 374	97.32 122	99.97 44	97.40 322	95.34 122	98.60 149	99.54 136	87.70 239	98.56 282	97.94 163	99.47 127	99.25 237
jason: jason.
EPP-MVSNet		96.69 169	96.60 152	96.96 260	97.74 244	93.05 316	99.37 302	98.56 116	88.75 383	95.83 267	99.01 204	96.01 42	98.56 282	96.92 208	97.20 218	99.25 237

casdiffseed414692147		95.07 247	94.26 261	97.50 223	97.01 320	94.70 251	99.58 260	97.02 403	91.27 317	94.66 288	98.82 246	80.79 355	98.55 285	93.39 302	95.79 277	99.27 233

BH-untuned		95.18 244	94.83 245	96.22 289	98.36 198	91.22 375	99.80 180	97.32 338	90.91 328	91.08 334	98.67 257	83.51 318	98.54 286	94.23 280	99.61 107	98.92 275

PAPM		98.60 38	98.42 40	99.14 74	96.05 360	98.96 30	99.90 119	99.35 24	96.68 75	98.35 163	99.66 118	96.45 36	98.51 287	99.45 68	99.89 75	99.96 76

OPM-MVS		93.21 312	92.80 312	94.44 356	93.12 430	90.85 383	99.77 192	97.61 296	96.19 97	91.56 330	98.65 260	75.16 419	98.47 288	93.78 294	89.39 341	93.99 410
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMP	92.05 9	92.74 327	92.42 325	93.73 388	95.91 365	88.72 421	99.81 174	97.53 307	94.13 172	87.00 419	98.23 298	74.07 425	98.47 288	96.22 235	88.86 347	93.99 410
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
CLD-MVS		94.06 290	93.90 274	94.55 349	96.02 361	90.69 385	99.98 24	97.72 282	96.62 79	91.05 336	98.85 242	77.21 390	98.47 288	98.11 152	89.51 340	94.48 353
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
ACMM	91.95 10	92.88 322	92.52 323	93.98 382	95.75 373	89.08 416	99.77 192	97.52 309	93.00 232	89.95 351	97.99 307	76.17 408	98.46 291	93.63 299	88.87 346	94.39 361
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
nomal-1		96.23 201	96.10 178	96.64 275	97.64 259	92.37 336	99.76 198	98.09 238	91.73 300	94.59 289	97.47 321	93.31 128	98.45 292	96.77 218	95.52 290	99.10 254

dp		95.05 248	94.43 255	96.91 262	97.99 227	92.73 325	96.29 473	97.98 251	89.70 364	95.93 264	94.67 436	93.83 114	98.45 292	86.91 411	96.53 252	99.54 171

ACMH+	89.98 16	90.35 379	89.54 379	92.78 415	95.99 362	86.12 447	98.81 383	97.18 365	89.38 366	83.14 453	97.76 317	68.42 451	98.43 294	89.11 372	86.05 378	93.78 425

IMVS_0407		95.21 243	94.80 248	96.46 280	96.97 323	91.64 364	98.81 383	97.12 378	92.33 276	95.60 272	98.88 230	85.65 277	98.42 295	92.12 319	95.70 283	99.32 218

ITE_SJBPF				92.38 418	95.69 380	85.14 453		95.71 462	92.81 241	89.33 371	98.11 301	70.23 444	98.42 295	85.91 418	88.16 359	93.59 433

Fast-Effi-MVS+		95.02 250	94.19 263	97.52 220	97.88 233	94.55 256	99.97 44	97.08 390	88.85 381	94.47 293	97.96 309	84.59 305	98.41 297	89.84 362	97.10 229	99.59 157

ACMH	89.72 17	90.64 372	89.63 376	93.66 394	95.64 382	88.64 424	98.55 403	97.45 315	89.03 371	81.62 460	97.61 318	69.75 445	98.41 297	89.37 366	87.62 368	93.92 416
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LPG-MVS_test		92.96 319	92.71 315	93.71 390	95.43 388	88.67 422	99.75 205	97.62 293	92.81 241	90.05 347	98.49 280	75.24 415	98.40 299	95.84 242	89.12 342	94.07 401

LGP-MVS_train				93.71 390	95.43 388	88.67 422		97.62 293	92.81 241	90.05 347	98.49 280	75.24 415	98.40 299	95.84 242	89.12 342	94.07 401

XVG-ACMP-BASELINE		91.22 361	90.75 353	92.63 417	93.73 419	85.61 450	98.52 407	97.44 316	92.77 245	89.90 353	96.85 348	66.64 460	98.39 301	92.29 316	88.61 351	93.89 418

HQP4-MVS										93.37 308			98.39 301			94.53 349

HQP-MVS		94.61 266	94.50 254	94.92 333	95.78 367	91.85 349	99.87 136	97.89 262	96.82 68	93.37 308	98.65 260	80.65 358	98.39 301	97.92 164	89.60 335	94.53 349

TDRefinement		84.76 439	82.56 447	91.38 431	74.58 530	84.80 458	97.36 449	94.56 489	84.73 443	80.21 469	96.12 375	63.56 471	98.39 301	87.92 393	63.97 498	90.95 475

SPE-MVS-test		97.88 87	97.94 79	97.70 200	99.28 115	95.20 232	99.98 24	97.15 372	95.53 117	99.62 64	99.79 64	92.08 172	98.38 305	98.75 111	99.28 142	99.52 176

EPMVS		96.53 180	96.01 182	98.09 165	98.43 192	96.12 187	96.36 470	99.43 20	93.53 200	97.64 194	95.04 421	94.41 87	98.38 305	91.13 336	98.11 190	99.75 120

HQP_MVS		94.49 273	94.36 257	94.87 334	95.71 377	91.74 356	99.84 157	97.87 264	96.38 88	93.01 313	98.59 269	80.47 362	98.37 307	97.79 175	89.55 338	94.52 351

plane_prior5								97.87 264					98.37 307	97.79 175	89.55 338	94.52 351

CS-MVS		97.79 101	97.91 81	97.43 232	99.10 127	94.42 264	99.99 8	97.10 386	95.07 126	99.68 54	99.75 83	92.95 140	98.34 309	98.38 134	99.14 148	99.54 171

TinyColmap		87.87 414	86.51 416	91.94 424	95.05 395	85.57 451	97.65 443	94.08 493	84.40 446	81.82 459	96.85 348	62.14 477	98.33 310	80.25 459	86.37 375	91.91 467

CMPMVS	61.59 21	84.75 440	85.14 430	83.57 477	90.32 475	62.54 512	96.98 458	97.59 300	74.33 494	69.95 500	96.66 354	64.17 469	98.32 311	87.88 394	88.41 356	89.84 488
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
dtuonly		93.89 292	93.16 302	96.08 293	94.37 406	91.67 363	99.15 333	95.04 479	91.79 298	94.74 286	98.72 252	81.01 350	98.31 312	87.29 401	96.33 259	98.27 305

USDC		90.00 390	88.96 391	93.10 408	94.81 398	88.16 430	98.71 392	95.54 467	93.66 197	83.75 451	97.20 330	65.58 463	98.31 312	83.96 432	87.49 370	92.85 450

testing222		97.08 145	96.75 145	98.06 167	98.56 177	96.82 147	99.85 152	98.61 102	92.53 266	98.84 127	98.84 243	93.36 123	98.30 314	95.84 242	94.30 310	99.05 261

TESTMET0.1,1		96.74 166	96.26 169	98.15 160	97.36 290	96.48 165	99.96 58	98.29 207	91.93 290	95.77 268	98.07 303	95.54 53	98.29 315	90.55 350	98.89 159	99.70 127

CostFormer		96.10 204	95.88 198	96.78 268	97.03 314	92.55 331	97.08 456	97.83 270	90.04 359	98.72 139	94.89 430	95.01 69	98.29 315	96.54 226	95.77 278	99.50 183

PRO-TEST		97.72 108	97.51 105	98.33 148	98.30 203	97.18 129	99.90 119	97.46 314	95.98 103	99.62 64	99.42 144	88.95 226	98.28 317	99.12 82	98.88 162	99.52 176

AUN-MVS		93.28 311	92.60 317	95.34 320	98.29 205	90.09 400	99.31 312	98.56 116	91.80 297	96.35 251	98.00 305	89.38 215	98.28 317	92.46 314	69.22 484	97.64 323

LTVRE_ROB	88.28 18	90.29 382	89.05 390	94.02 377	95.08 394	90.15 399	97.19 452	97.43 317	84.91 442	83.99 449	97.06 336	74.00 426	98.28 317	84.08 429	87.71 364	93.62 432
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
test-LLR		96.47 182	96.04 181	97.78 190	97.02 317	95.44 212	99.96 58	98.21 221	94.07 176	95.55 274	96.38 362	93.90 110	98.27 320	90.42 353	98.83 164	99.64 141

test-mter		96.39 188	95.93 194	97.78 190	97.02 317	95.44 212	99.96 58	98.21 221	91.81 296	95.55 274	96.38 362	95.17 62	98.27 320	90.42 353	98.83 164	99.64 141

hse-mvs2		94.38 276	94.08 268	95.31 322	98.27 208	90.02 401	99.29 319	98.56 116	95.90 104	98.77 134	98.00 305	90.89 194	98.26 322	97.80 172	69.20 485	97.64 323

HyFIR lowres test		96.66 171	96.43 162	97.36 241	99.05 131	93.91 288	99.70 232	99.80 3	90.54 344	96.26 252	98.08 302	92.15 170	98.23 323	96.84 212	95.46 291	99.93 89

CHOSEN 280x420		99.01 17	99.03 12	98.95 96	99.38 109	98.87 37	98.46 408	99.42 21	97.03 59	99.02 120	99.09 193	99.35 2	98.21 324	99.73 48	99.78 89	99.77 118

ETVMVS		97.03 146	96.64 150	98.20 156	98.67 169	97.12 134	99.89 130	98.57 110	91.10 324	98.17 173	98.59 269	93.86 112	98.19 325	95.64 247	95.24 298	99.28 230

ADS-MVSNet		94.79 257	94.02 270	97.11 255	97.87 234	93.79 289	94.24 485	98.16 231	90.07 357	96.43 247	94.48 441	90.29 205	98.19 325	87.44 397	97.23 216	99.36 209

EC-MVSNet		97.38 127	97.24 121	97.80 186	97.41 280	95.64 205	99.99 8	97.06 399	94.59 144	99.63 61	99.32 157	89.20 221	98.14 327	98.76 110	99.23 145	99.62 150

test_post											63.35 541	94.43 86	98.13 328

reproduce_monomvs		95.38 239	95.07 237	96.32 287	99.32 114	96.60 161	99.76 198	98.85 62	96.65 76	87.83 407	96.05 377	99.52 1	98.11 329	96.58 225	81.07 422	94.25 372

LF4IMVS		89.25 403	88.85 392	90.45 443	92.81 445	81.19 482	98.12 429	94.79 483	91.44 310	86.29 430	97.11 332	65.30 466	98.11 329	88.53 379	85.25 384	92.07 463

IS-MVSNet		96.29 196	95.90 196	97.45 228	98.13 220	94.80 248	99.08 340	97.61 296	92.02 289	95.54 276	98.96 217	90.64 197	98.08 331	93.73 296	97.41 208	99.47 187

DeepMVS_CX				82.92 481	95.98 364	58.66 519		96.01 455	92.72 247	78.34 479	95.51 396	58.29 486	98.08 331	82.57 440	85.29 383	92.03 465

PatchmatchNet		95.94 212	95.45 214	97.39 238	97.83 237	94.41 265	96.05 477	98.40 181	92.86 238	97.09 213	95.28 413	94.21 101	98.07 333	89.26 371	98.11 190	99.70 127
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
GeoE		94.36 279	93.48 288	96.99 259	97.29 298	93.54 303	99.96 58	96.72 434	88.35 394	93.43 307	98.94 224	82.05 334	98.05 334	88.12 392	96.48 255	99.37 207

MS-PatchMatch		90.65 371	90.30 363	91.71 429	94.22 411	85.50 452	98.24 422	97.70 283	88.67 385	86.42 428	96.37 364	67.82 454	98.03 335	83.62 434	99.62 102	91.60 468

Patchmatch-test		92.65 331	91.50 343	96.10 292	96.85 335	90.49 391	91.50 506	97.19 363	82.76 460	90.23 344	95.59 391	95.02 68	98.00 336	77.41 474	96.98 240	99.82 109

tpm2		95.47 236	95.18 232	96.35 286	96.91 330	91.70 361	96.96 459	97.93 256	88.04 399	98.44 156	95.40 402	93.32 126	97.97 337	94.00 282	95.61 288	99.38 205

JIA-IIPM		91.76 352	90.70 354	94.94 332	96.11 358	87.51 436	93.16 498	98.13 236	75.79 489	97.58 195	77.68 522	92.84 143	97.97 337	88.47 382	96.54 251	99.33 216

VPA-MVSNet		92.70 328	91.55 342	96.16 290	95.09 393	96.20 181	98.88 374	99.00 39	91.02 327	91.82 328	95.29 412	76.05 410	97.96 339	95.62 248	81.19 417	94.30 368

patchmatchnet-post											91.70 478	95.12 63	97.95 340

SCA		94.69 262	93.81 277	97.33 244	97.10 308	94.44 261	98.86 378	98.32 201	93.30 215	96.17 258	95.59 391	76.48 404	97.95 340	91.06 338	97.43 205	99.59 157

GG-mvs-BLEND				98.54 130	98.21 212	98.01 87	93.87 489	98.52 131		97.92 181	97.92 310	99.02 3	97.94 342	98.17 148	99.58 112	99.67 135

Effi-MVS+-dtu		94.53 269	95.30 227	92.22 421	97.77 242	82.54 472	99.59 258	97.06 399	94.92 131	95.29 280	95.37 406	85.81 274	97.89 343	94.80 265	97.07 230	96.23 343

XXY-MVS		91.82 345	90.46 358	95.88 301	93.91 416	95.40 216	98.87 377	97.69 285	88.63 387	87.87 406	97.08 334	74.38 424	97.89 343	91.66 329	84.07 396	94.35 365

dmvs_re		93.20 313	93.15 303	93.34 399	96.54 349	83.81 461	98.71 392	98.51 134	91.39 315	92.37 323	98.56 274	78.66 379	97.83 345	93.89 286	89.74 334	98.38 301

D2MVS		92.76 326	92.59 321	93.27 402	95.13 392	89.54 410	99.69 235	99.38 22	92.26 281	87.59 410	94.61 438	85.05 292	97.79 346	91.59 330	88.01 360	92.47 458

gg-mvs-nofinetune		93.51 307	91.86 335	98.47 137	97.72 249	97.96 92	92.62 500	98.51 134	74.70 493	97.33 205	69.59 529	98.91 4	97.79 346	97.77 177	99.56 113	99.67 135

test_fmvs2		89.47 399	89.70 375	88.77 459	94.54 403	75.74 495	99.83 165	94.70 487	94.71 140	91.08 334	96.82 352	54.46 490	97.78 348	92.87 311	88.27 357	92.80 451

test_post1							95.78 482				59.23 545	93.20 134	97.74 349	91.06 338

nrg030		93.51 307	92.53 322	96.45 281	94.36 407	97.20 128	99.81 174	97.16 369	91.60 303	89.86 354	97.46 322	86.37 265	97.68 350	95.88 241	80.31 430	94.46 354

Fast-Effi-MVS+-dtu		93.72 302	93.86 276	93.29 401	97.06 312	86.16 446	99.80 180	96.83 426	92.66 253	92.58 320	97.83 316	81.39 344	97.67 351	89.75 363	96.87 242	96.05 346

GA-MVS		93.83 294	92.84 310	96.80 267	95.73 374	93.57 301	99.88 133	97.24 357	92.57 262	92.92 315	96.66 354	78.73 378	97.67 351	87.75 395	94.06 314	99.17 245

UniMVSNet_ETH3D		90.06 389	88.58 399	94.49 353	94.67 401	88.09 431	97.81 440	97.57 301	83.91 449	88.44 392	97.41 324	57.44 487	97.62 353	91.41 332	88.59 353	97.77 319

MonoMVSNet		94.82 254	94.43 255	95.98 295	94.54 403	90.73 384	99.03 352	97.06 399	93.16 223	93.15 312	95.47 399	88.29 232	97.57 354	97.85 169	91.33 332	99.62 150

Anonymous20231211		89.86 392	88.44 401	94.13 372	98.93 146	90.68 386	98.54 405	98.26 211	76.28 486	86.73 421	95.54 393	70.60 443	97.56 355	90.82 345	80.27 431	94.15 388

VPNet		91.81 346	90.46 358	95.85 303	94.74 399	95.54 209	98.98 357	98.59 106	92.14 283	90.77 341	97.44 323	68.73 449	97.54 356	94.89 263	77.89 444	94.46 354

MVS-HIRNet		86.22 425	83.19 442	95.31 322	96.71 345	90.29 395	92.12 502	97.33 332	62.85 510	86.82 420	70.37 527	69.37 446	97.49 357	75.12 482	97.99 195	98.15 307

Vis-MVSNet (Re-imp)		96.32 193	95.98 185	97.35 243	97.93 231	94.82 247	99.47 285	98.15 234	91.83 294	95.09 283	99.11 192	91.37 181	97.47 358	93.47 300	97.43 205	99.74 121

tfpnnormal		89.29 402	87.61 410	94.34 361	94.35 408	94.13 280	98.95 364	98.94 44	83.94 447	84.47 445	95.51 396	74.84 420	97.39 359	77.05 477	80.41 428	91.48 470

jajsoiax		91.92 344	91.18 348	94.15 368	91.35 466	90.95 380	99.00 355	97.42 319	92.61 256	87.38 415	97.08 334	72.46 433	97.36 360	94.53 273	88.77 348	94.13 397

EPNet_dtu		95.71 228	95.39 219	96.66 273	98.92 149	93.41 307	99.57 264	98.90 50	96.19 97	97.52 196	98.56 274	92.65 150	97.36 360	77.89 472	98.33 179	99.20 243
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
sc_t1		85.01 437	82.46 448	92.67 416	92.44 450	83.09 468	97.39 448	95.72 461	65.06 506	85.64 437	96.16 370	49.50 499	97.34 362	84.86 426	75.39 461	97.57 328

cl22		93.77 299	93.25 300	95.33 321	99.49 104	94.43 263	99.61 253	98.09 238	90.38 349	89.16 378	95.61 389	90.56 199	97.34 362	91.93 325	84.45 392	94.21 379

V42		91.28 358	90.12 370	94.74 339	93.42 425	93.46 305	99.68 238	97.02 403	87.36 407	89.85 356	95.05 420	81.31 347	97.34 362	87.34 400	80.07 432	93.40 436

mvs5depth		84.87 438	82.90 445	90.77 437	85.59 505	84.84 457	91.10 509	93.29 502	83.14 455	85.07 442	94.33 446	62.17 476	97.32 365	78.83 469	72.59 474	90.14 484

mvs_tets		91.81 346	91.08 350	94.00 379	91.63 463	90.58 389	98.67 397	97.43 317	92.43 270	87.37 416	97.05 337	71.76 435	97.32 365	94.75 267	88.68 350	94.11 399

EI-MVSNet		93.73 301	93.40 293	94.74 339	96.80 338	92.69 326	99.06 345	97.67 286	88.96 376	91.39 331	99.02 201	88.75 229	97.30 367	91.07 337	87.85 362	94.22 377

MVSTER		95.53 235	95.22 230	96.45 281	98.56 177	97.72 102	99.91 113	97.67 286	92.38 274	91.39 331	97.14 331	97.24 21	97.30 367	94.80 265	87.85 362	94.34 367

TAMVS		95.85 216	95.58 210	96.65 274	97.07 311	93.50 304	99.17 331	97.82 271	91.39 315	95.02 284	98.01 304	92.20 168	97.30 367	93.75 295	95.83 275	99.14 249

PS-MVSNAJss		93.64 304	93.31 298	94.61 344	92.11 455	92.19 339	99.12 334	97.38 323	92.51 268	88.45 391	96.99 341	91.20 183	97.29 370	94.36 275	87.71 364	94.36 362

OurMVSNet-221017-0		89.81 393	89.48 383	90.83 436	91.64 462	81.21 481	98.17 428	95.38 471	91.48 308	85.65 436	97.31 327	72.66 432	97.29 370	88.15 390	84.83 389	93.97 412

MVP-Stereo		90.93 364	90.45 360	92.37 420	91.25 468	88.76 419	98.05 433	96.17 451	87.27 409	84.04 447	95.30 409	78.46 382	97.27 372	83.78 433	99.70 95	91.09 471
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v8		90.54 375	89.17 386	94.66 342	93.43 424	93.40 309	99.20 328	96.94 417	85.76 429	87.56 411	94.51 439	81.96 337	97.19 373	84.94 425	78.25 441	93.38 438

mvs_anonymous		95.65 232	95.03 239	97.53 218	98.19 214	95.74 198	99.33 307	97.49 312	90.87 329	90.47 343	97.10 333	88.23 233	97.16 374	95.92 240	97.66 202	99.68 133

v2v482		91.30 356	90.07 371	95.01 329	93.13 428	93.79 289	99.77 192	97.02 403	88.05 398	89.25 372	95.37 406	80.73 356	97.15 375	87.28 402	80.04 433	94.09 400

UniMVSNet (Re)		93.07 318	92.13 327	95.88 301	94.84 397	96.24 180	99.88 133	98.98 41	92.49 269	89.25 372	95.40 402	87.09 252	97.14 376	93.13 308	78.16 442	94.26 370

v7n		89.65 396	88.29 403	93.72 389	92.22 453	90.56 390	99.07 344	97.10 386	85.42 436	86.73 421	94.72 432	80.06 365	97.13 377	81.14 450	78.12 443	93.49 434

CDS-MVSNet		96.34 192	96.07 179	97.13 253	97.37 287	94.96 240	99.53 274	97.91 260	91.55 305	95.37 279	98.32 293	95.05 67	97.13 377	93.80 292	95.75 280	99.30 226
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EG-PatchMatch MVS		85.35 433	83.81 438	89.99 449	90.39 474	81.89 477	98.21 427	96.09 453	81.78 464	74.73 491	93.72 454	51.56 496	97.12 379	79.16 466	88.61 351	90.96 474

v144192		90.79 369	89.52 380	94.59 346	93.11 431	92.77 321	99.56 268	96.99 407	86.38 422	89.82 357	94.95 429	80.50 361	97.10 380	83.98 431	80.41 428	93.90 417

FIs		94.10 286	93.43 289	96.11 291	94.70 400	96.82 147	99.58 260	98.93 48	92.54 265	89.34 370	97.31 327	87.62 241	97.10 380	94.22 281	86.58 373	94.40 360

v1192		90.62 374	89.25 385	94.72 341	93.13 428	93.07 314	99.50 279	97.02 403	86.33 423	89.56 366	95.01 424	79.22 372	97.09 382	82.34 444	81.16 418	94.01 407

kuosan		93.17 314	92.60 317	94.86 337	98.40 194	89.54 410	98.44 410	98.53 129	84.46 445	88.49 390	97.92 310	90.57 198	97.05 383	83.10 437	93.49 320	97.99 312

miper_enhance_ethall		94.36 279	93.98 271	95.49 311	98.68 168	95.24 229	99.73 216	97.29 348	93.28 216	89.86 354	95.97 378	94.37 92	97.05 383	92.20 317	84.45 392	94.19 380

v1144		91.09 362	89.83 372	94.87 334	93.25 427	93.69 294	99.62 249	96.98 409	86.83 417	89.64 362	94.99 427	80.94 351	97.05 383	85.08 424	81.16 418	93.87 420

v148		90.70 370	89.63 376	93.92 383	92.97 437	90.97 377	99.75 205	96.89 422	87.51 404	88.27 401	95.01 424	81.67 340	97.04 386	87.40 399	77.17 452	93.75 426

pm-mvs1		89.36 401	87.81 408	94.01 378	93.40 426	91.93 345	98.62 401	96.48 445	86.25 424	83.86 450	96.14 372	73.68 428	97.04 386	86.16 415	75.73 460	93.04 446

v1921920		90.46 376	89.12 387	94.50 352	92.96 438	92.46 333	99.49 281	96.98 409	86.10 425	89.61 364	95.30 409	78.55 381	97.03 388	82.17 445	80.88 426	94.01 407

v1240		90.20 384	88.79 394	94.44 356	93.05 433	92.27 338	99.38 300	96.92 420	85.89 427	89.36 369	94.87 431	77.89 387	97.03 388	80.66 454	81.08 421	94.01 407

v10		90.25 383	88.82 393	94.57 348	93.53 422	93.43 306	99.08 340	96.87 424	85.00 439	87.34 417	94.51 439	80.93 352	97.02 390	82.85 439	79.23 435	93.26 440

VortexMVS		94.11 285	93.50 287	95.94 297	97.70 252	96.61 160	99.35 305	97.18 365	93.52 203	89.57 365	95.74 382	87.55 243	96.97 391	95.76 245	85.13 387	94.23 374

lessismore_v0				90.53 440	90.58 473	80.90 484		95.80 458		77.01 484	95.84 379	66.15 462	96.95 392	83.03 438	75.05 462	93.74 429

OpenMVS_ROB	79.82 20	83.77 447	81.68 451	90.03 448	88.30 487	82.82 469	98.46 408	95.22 475	73.92 495	76.00 488	91.29 479	55.00 489	96.94 393	68.40 494	88.51 355	90.34 479

LoFTR		74.41 470	70.88 474	84.99 475	86.56 499	67.85 505	93.74 490	89.63 515	69.46 503	54.95 521	87.39 504	30.76 509	96.92 394	61.37 515	64.06 497	90.19 483

anonymousdsp		91.79 351	90.92 352	94.41 359	90.76 472	92.93 320	98.93 368	97.17 367	89.08 369	87.46 414	95.30 409	78.43 383	96.92 394	92.38 315	88.73 349	93.39 437

WBMVS		94.52 270	94.03 269	95.98 295	98.38 195	96.68 156	99.92 105	97.63 290	90.75 339	89.64 362	95.25 414	96.77 28	96.90 396	94.35 277	83.57 399	94.35 365

MVSFormer		96.94 150	96.60 152	97.95 173	97.28 299	97.70 105	99.55 271	97.27 350	91.17 319	99.43 87	99.54 136	90.92 191	96.89 397	94.67 270	99.62 102	99.25 237

test_djsdf		92.83 323	92.29 326	94.47 354	91.90 458	92.46 333	99.55 271	97.27 350	91.17 319	89.96 350	96.07 376	81.10 348	96.89 397	94.67 270	88.91 344	94.05 404

SSC-MVS3.2		89.59 397	88.66 398	92.38 418	94.29 410	86.12 447	99.49 281	97.66 289	90.28 355	88.63 388	95.18 416	64.46 468	96.88 399	85.30 422	82.66 405	94.14 392

pmmvs6		85.69 428	83.84 437	91.26 432	90.00 479	84.41 459	97.82 439	96.15 452	75.86 488	81.29 463	95.39 404	61.21 480	96.87 400	83.52 436	73.29 467	92.50 457

ttmdpeth		88.23 410	87.06 414	91.75 428	89.91 480	87.35 438	98.92 371	95.73 460	87.92 400	84.02 448	96.31 365	68.23 453	96.84 401	86.33 413	76.12 457	91.06 472

tpm		93.70 303	93.41 292	94.58 347	95.36 390	87.41 437	97.01 457	96.90 421	90.85 330	96.72 231	94.14 449	90.40 202	96.84 401	90.75 347	88.54 354	99.51 181

FC-MVSNet-test		93.81 297	93.15 303	95.80 306	94.30 409	96.20 181	99.42 292	98.89 52	92.33 276	89.03 380	97.27 329	87.39 247	96.83 403	93.20 304	86.48 374	94.36 362

pmmvs4		92.10 342	91.07 351	95.18 325	92.82 444	94.96 240	99.48 284	96.83 426	87.45 406	88.66 387	96.56 360	83.78 317	96.83 403	89.29 369	84.77 390	93.75 426

WR-MVS		92.31 338	91.25 347	95.48 314	94.45 405	95.29 226	99.60 256	98.68 85	90.10 356	88.07 404	96.89 345	80.68 357	96.80 405	93.14 307	79.67 434	94.36 362

MatchFormer		70.84 472	66.72 480	83.19 480	85.99 503	64.61 509	93.58 493	88.62 519	59.32 515	50.64 524	82.31 519	28.00 516	96.79 406	52.52 526	59.50 513	88.18 500

miper_ehance_all_eth		93.16 315	92.60 317	94.82 338	97.57 266	93.56 302	99.50 279	97.07 398	88.75 383	88.85 382	95.52 395	90.97 190	96.74 407	90.77 346	84.45 392	94.17 382

UniMVSNet_NR-MVSNet		92.95 320	92.11 328	95.49 311	94.61 402	95.28 227	99.83 165	99.08 36	91.49 306	89.21 375	96.86 347	87.14 251	96.73 408	93.20 304	77.52 447	94.46 354

DU-MVS		92.46 335	91.45 345	95.49 311	94.05 413	95.28 227	99.81 174	98.74 76	92.25 282	89.21 375	96.64 356	81.66 341	96.73 408	93.20 304	77.52 447	94.46 354

usedtu_dtu_shiyan1		92.78 324	91.73 336	95.92 299	93.03 434	96.82 147	99.83 165	97.79 272	90.58 341	90.09 345	95.04 421	84.75 298	96.72 410	88.19 388	86.23 376	94.23 374

FE-MVSNET3		92.78 324	91.73 336	95.92 299	93.03 434	96.82 147	99.83 165	97.79 272	90.58 341	90.09 345	95.04 421	84.75 298	96.72 410	88.20 387	86.23 376	94.23 374

eth_miper_zixun_eth		92.41 336	91.93 332	93.84 387	97.28 299	90.68 386	98.83 381	96.97 411	88.57 388	89.19 377	95.73 385	89.24 220	96.69 412	89.97 361	81.55 414	94.15 388

SixPastTwentyTwo		88.73 405	88.01 407	90.88 433	91.85 459	82.24 474	98.22 426	95.18 477	88.97 375	82.26 456	96.89 345	71.75 436	96.67 413	84.00 430	82.98 401	93.72 430

cl____		92.31 338	91.58 340	94.52 350	97.33 294	92.77 321	99.57 264	96.78 431	86.97 415	87.56 411	95.51 396	89.43 214	96.62 414	88.60 376	82.44 408	94.16 387

WR-MVS_H		91.30 356	90.35 361	94.15 368	94.17 412	92.62 330	99.17 331	98.94 44	88.87 380	86.48 427	94.46 443	84.36 309	96.61 415	88.19 388	78.51 439	93.21 442

NR-MVSNet		91.56 354	90.22 365	95.60 309	94.05 413	95.76 197	98.25 421	98.70 81	91.16 321	80.78 467	96.64 356	83.23 327	96.57 416	91.41 332	77.73 446	94.46 354

blended_shiyan8		87.82 415	85.71 423	94.16 366	86.54 500	91.79 353	99.72 220	97.08 390	79.32 478	88.44 392	92.35 474	77.88 388	96.56 417	88.53 379	61.51 504	94.15 388

icg_test_0407_2		95.04 249	94.78 249	95.84 304	96.97 323	91.64 364	98.63 400	97.12 378	92.33 276	95.60 272	98.88 230	85.65 277	96.56 417	92.12 319	95.70 283	99.32 218

Baseline_NR-MVSNet		90.33 380	89.51 381	92.81 414	92.84 441	89.95 404	99.77 192	93.94 496	84.69 444	89.04 379	95.66 387	81.66 341	96.52 419	90.99 340	76.98 453	91.97 466

usedtu_blend_shiyan5		86.75 423	84.29 432	94.16 366	86.66 495	91.83 351	97.42 445	95.23 474	69.94 502	88.37 398	92.36 471	78.01 384	96.50 420	89.35 367	61.26 505	94.14 392

blend_shiyan4		90.13 388	88.79 394	94.17 365	87.12 491	91.83 351	99.75 205	97.08 390	79.27 480	88.69 385	92.53 466	92.25 166	96.50 420	89.35 367	73.04 469	94.18 381

DIV-MVS_self_test		92.32 337	91.60 339	94.47 354	97.31 296	92.74 323	99.58 260	96.75 432	86.99 414	87.64 409	95.54 393	89.55 213	96.50 420	88.58 377	82.44 408	94.17 382

WB-MVSnew		92.90 321	92.77 314	93.26 403	96.95 328	93.63 296	99.71 225	98.16 231	91.49 306	94.28 299	98.14 300	81.33 346	96.48 423	79.47 461	95.46 291	89.68 490

pmmvs5		90.17 386	89.09 388	93.40 398	92.10 456	89.77 407	99.74 209	95.58 466	85.88 428	87.24 418	95.74 382	73.41 431	96.48 423	88.54 378	83.56 400	93.95 413

c3_l		92.53 333	91.87 334	94.52 350	97.40 282	92.99 319	99.40 294	96.93 418	87.86 401	88.69 385	95.44 400	89.95 208	96.44 425	90.45 352	80.69 427	94.14 392

wanda-best-256-512		87.82 415	85.71 423	94.15 368	86.66 495	91.88 347	99.76 198	97.08 390	79.46 476	88.37 398	92.36 471	78.01 384	96.43 426	88.39 383	61.26 505	94.14 392

FE-blended-shiyan7		87.82 415	85.71 423	94.15 368	86.66 495	91.88 347	99.76 198	97.08 390	79.46 476	88.37 398	92.36 471	78.01 384	96.43 426	88.39 383	61.26 505	94.14 392

blended_shiyan6		87.74 418	85.62 426	94.09 373	86.53 501	91.73 359	99.72 220	97.08 390	79.32 478	88.22 402	92.31 476	77.82 389	96.43 426	88.31 385	61.26 505	94.13 397

IMVS_0404		93.83 294	93.17 301	95.80 306	96.97 323	91.64 364	97.78 441	97.12 378	92.33 276	90.87 338	98.88 230	76.78 399	96.43 426	92.12 319	95.70 283	99.32 218

TransMVSNet (Re)		87.25 420	85.28 429	93.16 405	93.56 421	91.03 376	98.54 405	94.05 495	83.69 451	81.09 464	96.16 370	75.32 414	96.40 430	76.69 478	68.41 487	92.06 464

CP-MVSNet		91.23 360	90.22 365	94.26 363	93.96 415	92.39 335	99.09 338	98.57 110	88.95 377	86.42 428	96.57 359	79.19 373	96.37 431	90.29 356	78.95 436	94.02 405

ambc				83.23 479	77.17 526	62.61 511	87.38 516	94.55 490		76.72 486	86.65 508	30.16 512	96.36 432	84.85 427	69.86 480	90.73 476

gbinet_0.2-2-1-0.02		87.63 419	85.51 427	93.99 380	87.22 490	91.56 371	99.81 174	97.36 327	79.54 475	88.60 389	93.29 460	73.76 427	96.34 433	89.27 370	60.78 510	94.06 403

IterMVS-LS		92.69 329	92.11 328	94.43 358	96.80 338	92.74 323	99.45 290	96.89 422	88.98 374	89.65 361	95.38 405	88.77 228	96.34 433	90.98 341	82.04 411	94.22 377
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test_vis3_rt		68.82 476	66.69 481	75.21 495	76.24 527	60.41 516	96.44 469	68.71 534	75.13 492	50.54 525	69.52 530	16.42 542	96.32 435	80.27 458	66.92 492	68.89 530

PS-CasMVS		90.63 373	89.51 381	93.99 380	93.83 417	91.70 361	98.98 357	98.52 131	88.48 390	86.15 432	96.53 361	75.46 413	96.31 436	88.83 374	78.86 438	93.95 413

FMVSNet3		92.69 329	91.58 340	95.99 294	98.29 205	97.42 120	99.26 324	97.62 293	89.80 363	89.68 358	95.32 408	81.62 343	96.27 437	87.01 408	85.65 380	94.29 369

test_0402		85.58 429	83.94 436	90.50 441	93.81 418	85.04 454	98.55 403	95.20 476	76.01 487	79.72 473	95.13 417	64.15 470	96.26 438	66.04 505	86.88 372	90.21 482

FMVSNet2		91.02 363	89.56 378	95.41 318	97.53 270	95.74 198	98.98 357	97.41 321	87.05 411	88.43 395	95.00 426	71.34 438	96.24 439	85.12 423	85.21 385	94.25 372

SSM_04072		94.77 259	94.09 266	96.82 266	97.14 305	95.31 223	93.48 495	97.08 390	90.48 346	94.40 294	98.62 265	84.49 306	96.21 440	93.99 283	97.18 220	98.93 272

TranMVSNet+NR-MVSNet		91.68 353	90.61 357	94.87 334	93.69 420	93.98 286	99.69 235	98.65 89	91.03 326	88.44 392	96.83 351	80.05 366	96.18 441	90.26 357	76.89 455	94.45 359

APD_test1		81.15 455	80.92 456	81.86 482	92.45 449	59.76 518	96.04 478	93.61 500	73.29 496	77.06 483	96.64 356	44.28 504	96.16 442	72.35 487	82.52 406	89.67 491

GBi-Net		90.88 366	89.82 373	94.08 374	97.53 270	91.97 342	98.43 411	96.95 413	87.05 411	89.68 358	94.72 432	71.34 438	96.11 443	87.01 408	85.65 380	94.17 382

test1		90.88 366	89.82 373	94.08 374	97.53 270	91.97 342	98.43 411	96.95 413	87.05 411	89.68 358	94.72 432	71.34 438	96.11 443	87.01 408	85.65 380	94.17 382

FMVSNet1		88.50 407	86.64 415	94.08 374	95.62 384	91.97 342	98.43 411	96.95 413	82.99 457	86.08 433	94.72 432	59.09 485	96.11 443	81.82 448	84.07 396	94.17 382

our_test_3		90.39 377	89.48 383	93.12 406	92.40 451	89.57 409	99.33 307	96.35 448	87.84 402	85.30 438	94.99 427	84.14 313	96.09 446	80.38 457	84.56 391	93.71 431

PatchT		90.38 378	88.75 396	95.25 324	95.99 362	90.16 398	91.22 508	97.54 305	76.80 485	97.26 208	86.01 511	91.88 175	96.07 447	66.16 503	95.91 273	99.51 181

CR-MVSNet		93.45 310	92.62 316	95.94 297	96.29 353	92.66 327	92.01 503	96.23 449	92.62 255	96.94 220	93.31 458	91.04 188	96.03 448	79.23 463	95.96 269	99.13 250

Patchmtry		89.70 395	88.49 400	93.33 400	96.24 356	89.94 406	91.37 507	96.23 449	78.22 483	87.69 408	93.31 458	91.04 188	96.03 448	80.18 460	82.10 410	94.02 405

ppachtmachnet_test		89.58 398	88.35 402	93.25 404	92.40 451	90.44 393	99.33 307	96.73 433	85.49 434	85.90 435	95.77 381	81.09 349	96.00 450	76.00 481	82.49 407	93.30 439

PEN-MVS		90.19 385	89.06 389	93.57 395	93.06 432	90.90 381	99.06 345	98.47 143	88.11 397	85.91 434	96.30 366	76.67 400	95.94 451	87.07 405	76.91 454	93.89 418

miper_lstm_enhance		91.81 346	91.39 346	93.06 409	97.34 292	89.18 414	99.38 300	96.79 430	86.70 419	87.47 413	95.22 415	90.00 207	95.86 452	88.26 386	81.37 416	94.15 388

ArgMatch-SfM		85.25 434	84.17 433	88.48 461	92.99 436	77.23 494	97.92 435	94.24 491	90.50 345	85.08 441	95.65 388	49.84 498	95.83 453	81.06 452	70.22 478	92.39 460

PatchmatchNet3													95.80 454
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
tt0320		83.56 450	81.15 454	90.77 437	92.77 446	83.58 464	96.83 463	95.52 468	63.26 508	81.36 462	92.54 465	53.26 492	95.77 455	80.45 455	74.38 464	92.96 447

N_pmnet		80.06 460	80.78 457	77.89 487	91.94 457	45.28 537	98.80 386	56.82 540	78.10 484	80.08 470	93.33 456	77.03 394	95.76 456	68.14 497	82.81 403	92.64 453

MVStest1		85.03 436	82.76 446	91.83 426	92.95 439	89.16 415	98.57 402	94.82 482	71.68 498	68.54 503	95.11 419	83.17 328	95.66 457	74.69 483	65.32 494	90.65 477

mvsany_test3		82.12 453	81.14 455	85.06 474	81.87 519	70.41 502	97.09 455	92.14 506	91.27 317	77.84 481	88.73 494	39.31 505	95.49 458	90.75 347	71.24 476	89.29 495

LCM-MVSNet-Re		92.31 338	92.60 317	91.43 430	97.53 270	79.27 490	99.02 354	91.83 508	92.07 285	80.31 468	94.38 445	83.50 319	95.48 459	97.22 195	97.58 203	99.54 171

tt0320-xc		82.94 451	80.35 459	90.72 439	92.90 440	83.54 465	96.85 462	94.73 485	63.12 509	79.85 472	93.77 453	49.43 500	95.46 460	80.98 453	71.54 475	93.16 443

K. test v3		88.05 411	87.24 413	90.47 442	91.82 461	82.23 475	98.96 363	97.42 319	89.05 370	76.93 485	95.60 390	68.49 450	95.42 461	85.87 419	81.01 424	93.75 426

ADS-MVSNet2		93.80 298	93.88 275	93.55 396	97.87 234	85.94 449	94.24 485	96.84 425	90.07 357	96.43 247	94.48 441	90.29 205	95.37 462	87.44 397	97.23 216	99.36 209

ET-MVSNet_ETH3D		94.37 277	93.28 299	97.64 205	98.30 203	97.99 88	99.99 8	97.61 296	94.35 160	71.57 498	99.45 143	96.23 41	95.34 463	96.91 210	85.14 386	99.59 157

CVMVSNet		94.68 264	94.94 243	93.89 386	96.80 338	86.92 442	99.06 345	98.98 41	94.45 151	94.23 301	99.02 201	85.60 280	95.31 464	90.91 343	95.39 294	99.43 198

DTE-MVSNet		89.40 400	88.24 404	92.88 412	92.66 447	89.95 404	99.10 337	98.22 217	87.29 408	85.12 440	96.22 368	76.27 407	95.30 465	83.56 435	75.74 459	93.41 435

IterMVS		90.91 365	90.17 368	93.12 406	96.78 342	90.42 394	98.89 372	97.05 402	89.03 371	86.49 426	95.42 401	76.59 402	95.02 466	87.22 403	84.09 395	93.93 415
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		90.85 368	90.16 369	92.93 411	96.72 344	89.96 403	98.89 372	96.99 407	88.95 377	86.63 423	95.67 386	76.48 404	95.00 467	87.04 406	84.04 398	93.84 422

test0.0.03 1		93.86 293	93.61 280	94.64 343	95.02 396	92.18 340	99.93 102	98.58 108	94.07 176	87.96 405	98.50 279	93.90 110	94.96 468	81.33 449	93.17 324	96.78 336

dongtai		91.55 355	91.13 349	92.82 413	98.16 217	86.35 444	99.47 285	98.51 134	83.24 453	85.07 442	97.56 319	90.33 203	94.94 469	76.09 480	91.73 328	97.18 334

UnsupCasMVSNet_bld		79.97 462	77.03 469	88.78 457	85.62 504	81.98 476	93.66 491	97.35 328	75.51 491	70.79 499	83.05 515	48.70 501	94.91 470	78.31 471	60.29 512	89.46 494

ArgMatch-Sym		85.85 427	85.07 431	88.21 463	92.84 441	77.63 493	98.42 414	94.70 487	89.91 360	84.33 446	96.72 353	51.42 497	94.89 471	82.48 441	74.80 463	92.10 462

MIMVSNet		90.30 381	88.67 397	95.17 326	96.45 352	91.64 364	92.39 501	97.15 372	85.99 426	90.50 342	93.19 461	66.95 457	94.86 472	82.01 446	93.43 321	99.01 268

new_pmnet		84.49 443	82.92 444	89.21 453	90.03 478	82.60 471	96.89 461	95.62 465	80.59 469	75.77 490	89.17 492	65.04 467	94.79 473	72.12 488	81.02 423	90.23 481

UWE-MVS-28		95.95 211	96.49 157	94.34 361	98.51 185	89.99 402	99.39 298	98.57 110	93.14 225	97.33 205	98.31 295	93.44 121	94.68 474	93.69 298	95.98 268	98.34 303

testgi		89.01 404	88.04 406	91.90 425	93.49 423	84.89 456	99.73 216	95.66 464	93.89 190	85.14 439	98.17 299	59.68 483	94.66 475	77.73 473	88.88 345	96.16 345

KD-MVS_2432*1600		88.00 412	86.10 417	93.70 392	96.91 330	94.04 282	97.17 453	97.12 378	84.93 440	81.96 457	92.41 468	92.48 158	94.51 476	79.23 463	52.68 522	92.56 454

miper_refine_blended		88.00 412	86.10 417	93.70 392	96.91 330	94.04 282	97.17 453	97.12 378	84.93 440	81.96 457	92.41 468	92.48 158	94.51 476	79.23 463	52.68 522	92.56 454

Anonymous20240521		85.15 435	83.81 438	89.16 454	88.32 486	82.69 470	98.80 386	95.74 459	79.72 472	81.53 461	90.99 480	65.38 465	94.16 478	72.69 486	81.11 420	90.63 478

pmmvs-eth3d		84.03 445	81.97 450	90.20 445	84.15 511	87.09 440	98.10 431	94.73 485	83.05 456	74.10 495	87.77 500	65.56 464	94.01 479	81.08 451	69.24 483	89.49 493

UnsupCasMVSNet_eth		85.52 430	83.99 434	90.10 447	89.36 483	83.51 466	96.65 465	97.99 249	89.14 368	75.89 489	93.83 451	63.25 473	93.92 480	81.92 447	67.90 490	92.88 449

PM-MVS		80.47 458	78.88 464	85.26 473	83.79 514	72.22 500	95.89 481	91.08 510	85.71 432	76.56 487	88.30 496	36.64 508	93.90 481	82.39 443	69.57 482	89.66 492

MDA-MVSNet_test_wron		85.51 431	83.32 441	92.10 422	90.96 469	88.58 425	99.20 328	96.52 442	79.70 473	57.12 518	92.69 464	79.11 374	93.86 482	77.10 476	77.46 449	93.86 421

SD_0403		92.63 332	93.38 294	90.40 444	97.32 295	77.91 492	97.75 442	98.03 247	91.89 291	90.83 339	98.29 297	82.00 335	93.79 483	88.51 381	95.75 280	99.52 176

YYNet1		85.50 432	83.33 440	92.00 423	90.89 470	88.38 429	99.22 327	96.55 441	79.60 474	57.26 517	92.72 463	79.09 376	93.78 484	77.25 475	77.37 450	93.84 422

Patchmatch-RL test		86.90 421	85.98 421	89.67 450	84.45 509	75.59 496	89.71 514	92.43 504	86.89 416	77.83 482	90.94 481	94.22 99	93.63 485	87.75 395	69.61 481	99.79 114

MDA-MVSNet-bldmvs		84.09 444	81.52 452	91.81 427	91.32 467	88.00 433	98.67 397	95.92 457	80.22 471	55.60 520	93.32 457	68.29 452	93.60 486	73.76 484	76.61 456	93.82 424

Anonymous20231206		86.32 424	85.42 428	89.02 455	89.11 484	80.53 487	99.05 349	95.28 472	85.43 435	82.82 454	93.92 450	74.40 423	93.44 487	66.99 499	81.83 413	93.08 445

EU-MVSNet		90.14 387	90.34 362	89.54 451	92.55 448	81.06 483	98.69 395	98.04 245	91.41 314	86.59 424	96.84 350	80.83 354	93.31 488	86.20 414	81.91 412	94.26 370

FE-MVSNET2		83.57 449	81.36 453	90.20 445	82.83 517	87.59 434	98.28 420	96.04 454	85.33 437	74.13 494	87.45 502	59.16 484	93.26 489	79.12 467	69.91 479	89.77 489

Syy-MVS		90.00 390	90.63 356	88.11 465	97.68 254	74.66 499	99.71 225	98.35 194	90.79 336	92.10 325	98.67 257	79.10 375	93.09 490	63.35 509	95.95 271	96.59 339

myMVS_eth3d		94.46 274	94.76 250	93.55 396	97.68 254	90.97 377	99.71 225	98.35 194	90.79 336	92.10 325	98.67 257	92.46 160	93.09 490	87.13 404	95.95 271	96.59 339

EGC-MVSNET		69.38 473	63.76 486	86.26 472	90.32 475	81.66 480	96.24 474	93.85 497	0.99 562	3.22 563	92.33 475	52.44 493	92.92 492	59.53 520	84.90 388	84.21 511

test_f		78.40 464	77.59 467	80.81 484	80.82 521	62.48 513	96.96 459	93.08 503	83.44 452	74.57 492	84.57 514	27.95 517	92.63 493	84.15 428	72.79 470	87.32 506

testing3		93.92 291	94.23 262	92.99 410	97.54 269	90.23 396	99.99 8	99.16 33	90.57 343	91.33 333	98.63 264	92.99 138	92.52 494	82.46 442	95.39 294	96.22 344

KD-MVS_self_test		83.59 448	82.06 449	88.20 464	86.93 492	80.70 485	97.21 451	96.38 446	82.87 458	82.49 455	88.97 493	67.63 455	92.32 495	73.75 485	62.30 503	91.58 469

MASt3R-SfM		78.94 463	79.57 462	77.07 488	84.15 511	50.74 528	91.56 505	92.34 505	83.22 454	80.84 466	94.16 448	36.67 507	92.30 496	79.45 462	73.71 466	88.16 501

test_method		80.79 457	79.70 461	84.08 476	92.83 443	67.06 507	99.51 277	95.42 469	54.34 520	81.07 465	93.53 455	44.48 503	92.22 497	78.90 468	77.23 451	92.94 448

DSMNet-mixed		88.28 409	88.24 404	88.42 462	89.64 481	75.38 498	98.06 432	89.86 513	85.59 433	88.20 403	92.14 477	76.15 409	91.95 498	78.46 470	96.05 266	97.92 313

CL-MVSNet_self_test		84.50 442	83.15 443	88.53 460	86.00 502	81.79 478	98.82 382	97.35 328	85.12 438	83.62 452	90.91 482	76.66 401	91.40 499	69.53 492	60.36 511	92.40 459

FMVSNet5		88.32 408	87.47 411	90.88 433	96.90 333	88.39 428	97.28 450	95.68 463	82.60 461	84.67 444	92.40 470	79.83 367	91.16 500	76.39 479	81.51 415	93.09 444

usedtu_dtu_shiyan2		75.87 467	72.37 473	86.39 471	76.18 528	75.49 497	96.53 467	93.82 498	64.74 507	72.53 496	88.48 495	37.67 506	91.12 501	64.13 508	57.22 515	92.56 454

pmmvs3		80.27 459	77.77 466	87.76 467	80.32 523	82.43 473	98.23 424	91.97 507	72.74 497	78.75 476	87.97 499	57.30 488	90.99 502	70.31 490	62.37 502	89.87 487

dtuonlycased		86.10 426	85.82 422	86.95 468	91.84 460	79.57 489	99.27 322	94.89 480	86.79 418	79.46 474	94.46 443	66.85 458	90.93 503	80.41 456	78.44 440	90.34 479

new-patchmatchnet		81.19 454	79.34 463	86.76 470	82.86 516	80.36 488	97.92 435	95.27 473	82.09 463	72.02 497	86.87 507	62.81 475	90.74 504	71.10 489	63.08 499	89.19 496

FE-MVSNET		81.05 456	78.81 465	87.79 466	81.98 518	83.70 462	98.23 424	91.78 509	81.27 466	74.29 493	87.44 503	60.92 482	90.67 505	64.92 507	68.43 486	89.01 498

MIMVSNet1		82.58 452	80.51 458	88.78 457	86.68 494	84.20 460	96.65 465	95.41 470	78.75 481	78.59 478	92.44 467	51.88 495	89.76 506	65.26 506	78.95 436	92.38 461

DenseAffine		75.91 466	73.39 471	83.47 478	89.52 482	71.86 501	93.39 497	89.29 518	71.44 499	66.83 504	90.32 486	30.65 510	89.67 507	68.20 496	60.88 509	88.88 499

ELoFTR		64.32 484	60.56 488	75.60 494	73.46 533	53.20 525	86.50 521	80.09 527	60.74 513	45.95 530	82.48 518	16.05 543	89.20 508	56.48 525	43.34 532	84.38 510

test20.03		84.72 441	83.99 434	86.91 469	88.19 488	80.62 486	98.88 374	95.94 456	88.36 393	78.87 475	94.62 437	68.75 448	89.11 509	66.52 502	75.82 458	91.00 473

test_fmvs3		79.99 461	80.17 460	79.45 485	84.02 513	62.83 510	99.05 349	93.49 501	88.29 395	80.06 471	86.65 508	28.09 515	88.00 510	88.63 375	73.27 468	87.54 505

RoMa-SfM		74.91 469	72.77 472	81.35 483	88.00 489	67.35 506	93.55 494	86.23 523	68.27 504	66.79 505	92.92 462	30.40 511	87.68 511	66.14 504	62.62 501	89.02 497

testf1		68.38 478	66.92 478	72.78 498	78.80 524	50.36 529	90.95 510	87.35 521	55.47 518	58.95 513	88.14 497	20.64 535	87.60 512	57.28 521	64.69 495	80.39 522

APD_test2		68.38 478	66.92 478	72.78 498	78.80 524	50.36 529	90.95 510	87.35 521	55.47 518	58.95 513	88.14 497	20.64 535	87.60 512	57.28 521	64.69 495	80.39 522

Gipuma		66.95 482	65.00 483	72.79 497	91.52 464	67.96 504	66.16 538	95.15 478	47.89 523	58.54 516	67.99 535	29.74 513	87.54 514	50.20 527	77.83 445	62.87 533
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
dmvs_testset		83.79 446	86.07 419	76.94 489	92.14 454	48.60 532	96.75 464	90.27 512	89.48 365	78.65 477	98.55 276	79.25 371	86.65 515	66.85 501	82.69 404	95.57 347

LCM-MVSNet		67.77 480	64.73 484	76.87 490	62.95 547	56.25 522	89.37 515	93.74 499	44.53 524	61.99 509	80.74 520	20.42 537	86.53 516	69.37 493	59.50 513	87.84 502

DKM		72.18 471	69.80 475	79.34 486	86.79 493	65.15 508	92.70 499	84.00 524	67.67 505	61.97 510	89.63 488	23.69 528	85.17 517	67.39 498	54.35 520	87.70 503

PMMVS2		67.15 481	64.15 485	76.14 492	70.56 536	62.07 514	93.89 488	87.52 520	58.09 516	60.02 512	78.32 521	22.38 530	84.54 518	59.56 519	47.03 530	81.80 516

RoMa-HiRes		69.18 474	67.02 477	75.65 493	83.52 515	60.31 517	90.80 512	76.82 530	62.46 511	62.85 508	90.44 485	24.75 525	83.07 519	60.58 517	50.97 527	83.58 512

FPMVS		68.72 477	68.72 476	68.71 504	65.95 541	44.27 540	95.97 480	94.74 484	51.13 522	53.26 522	90.50 484	25.11 523	83.00 520	60.80 516	80.97 425	78.87 524

DKM-HiRes		68.91 475	66.34 482	76.62 491	84.17 510	60.69 515	90.78 513	78.55 528	62.17 512	58.82 515	87.54 501	20.94 532	82.56 521	63.05 510	51.00 526	86.61 507

WB-MVS		76.28 465	77.28 468	73.29 496	81.18 520	54.68 523	97.87 438	94.19 492	81.30 465	69.43 501	90.70 483	77.02 395	82.06 522	35.71 534	68.11 489	83.13 513

SSC-MVS		75.42 468	76.40 470	72.49 501	80.68 522	53.62 524	97.42 445	94.06 494	80.42 470	68.75 502	90.14 487	76.54 403	81.66 523	33.25 535	66.34 493	82.19 514

PMVS	49.05 23	53.75 496	51.34 503	60.97 509	40.80 564	34.68 547	74.82 533	89.62 516	37.55 527	28.67 546	72.12 524	7.09 560	81.63 524	43.17 531	68.21 488	66.59 532
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PMatch-SfM		62.12 485	58.57 489	72.76 500	74.34 531	52.97 526	84.95 523	65.57 535	56.89 517	46.61 529	85.70 513	9.51 553	80.54 525	60.53 518	43.03 533	84.77 508

GLUNet-SfM		51.10 503	46.61 508	64.56 507	61.54 551	39.88 542	79.38 532	65.13 536	36.09 528	33.36 544	69.94 528	14.50 545	78.76 526	42.46 532	17.10 553	75.02 527

tmp_tt		65.23 483	62.94 487	72.13 502	44.90 562	50.03 531	81.05 530	89.42 517	38.45 526	48.51 528	99.90 24	54.09 491	78.70 527	91.84 328	18.26 552	87.64 504

PMatch-Up-SfM		57.92 487	53.93 492	69.90 503	69.97 537	46.69 533	81.36 528	55.29 546	51.90 521	43.17 536	82.54 517	7.86 558	78.44 528	57.13 523	36.17 537	84.58 509

PDCNetPlus		59.83 486	57.26 490	67.55 506	76.18 528	56.71 521	87.01 517	45.27 550	59.54 514	48.80 527	83.01 516	26.63 519	76.54 529	62.12 514	26.78 543	69.40 529

ALIKED-MNN		52.51 498	50.15 506	59.60 517	90.05 477	44.33 539	81.60 527	54.93 547	32.36 535	40.96 539	68.77 531	20.90 533	75.30 530	20.00 546	41.78 534	59.18 536

ALIKED-LG		54.29 494	52.28 499	60.32 511	88.90 485	45.51 534	81.66 526	56.33 541	38.60 525	42.62 537	70.81 526	25.00 524	75.20 531	19.87 547	46.76 531	60.24 534

ALIKED-NN		54.48 493	52.67 498	59.89 515	90.79 471	45.45 535	81.25 529	55.75 544	34.99 532	44.87 531	71.98 525	25.50 522	74.36 532	21.88 545	47.04 529	59.85 535

MVE	53.74 22	51.54 501	47.86 507	62.60 508	59.56 554	50.93 527	79.41 531	77.69 529	35.69 530	36.27 542	61.76 543	5.79 564	69.63 533	37.97 533	36.61 536	67.24 531
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		56.10 489	52.24 500	67.66 505	49.27 560	56.82 520	83.94 524	82.02 526	70.47 500	33.28 545	64.54 539	17.23 541	69.16 534	45.59 530	23.85 547	77.02 526

E-PMN		52.30 499	52.18 501	52.67 518	71.51 534	45.40 536	93.62 492	76.60 531	36.01 529	43.50 535	64.13 540	27.11 518	67.31 535	31.06 536	26.06 544	45.30 543

EMVS		51.44 502	51.22 504	52.11 519	70.71 535	44.97 538	94.04 487	75.66 532	35.34 531	42.40 538	61.56 544	28.93 514	65.87 536	27.64 542	24.73 545	45.49 540

SP-NN		55.28 492	53.59 495	60.34 510	86.63 498	39.01 544	86.70 519	56.31 542	31.08 537	43.77 534	68.45 533	23.39 529	60.24 537	29.19 540	56.76 517	81.77 517

SP-MNN		53.97 495	52.04 502	59.73 516	84.72 508	38.63 546	86.51 520	55.94 543	29.25 538	40.20 540	67.48 537	22.18 531	59.59 538	27.79 541	54.33 521	80.98 520

SP-SuperGlue		55.29 490	53.71 493	60.00 514	85.11 507	38.86 545	86.96 518	57.95 538	32.77 534	44.54 532	68.00 534	23.90 527	59.51 539	29.61 539	54.59 519	81.63 518

SP-LightGlue		55.29 490	53.65 494	60.20 512	85.58 506	39.12 543	86.36 522	57.52 539	32.34 536	44.34 533	67.75 536	24.36 526	59.32 540	29.62 538	54.98 518	82.17 515

SP-DiffGlue		56.84 488	55.72 491	60.19 513	65.70 542	40.86 541	81.89 525	60.28 537	34.62 533	50.39 526	76.88 523	26.61 520	58.81 541	48.21 528	56.94 516	80.90 521

VLMVS_CLIP		52.57 497	53.54 496	49.65 520	41.84 563	19.27 565	69.54 535	70.45 533	22.22 541	56.57 519	86.16 510	15.89 544	54.77 542	66.88 500	52.29 524	74.91 528

XFeat-MNN		41.51 506	41.24 511	42.32 523	55.40 558	28.19 551	69.39 537	46.53 548	23.57 540	34.47 543	63.21 542	20.04 538	52.41 543	27.43 543	31.08 542	46.37 539

XFeat-NN		42.54 505	42.87 510	41.54 524	59.73 553	27.86 552	69.53 536	45.34 549	24.36 539	37.16 541	64.79 538	20.84 534	51.40 544	30.01 537	34.12 539	45.36 542

SIFT-NN		35.94 509	36.54 513	34.16 525	73.93 532	29.52 548	62.74 539	37.28 551	19.65 544	27.91 547	49.19 546	11.66 546	46.35 545	9.19 549	37.30 535	26.61 544

SIFT-MNN		34.10 510	34.41 514	33.17 527	68.99 538	28.51 549	60.22 541	36.81 552	19.08 547	24.04 550	47.28 549	10.06 550	45.04 546	8.72 550	34.47 538	25.97 547

SIFT-NN-NCMNet		33.88 511	34.14 515	33.10 528	66.88 540	28.42 550	60.42 540	36.72 553	19.15 545	24.06 549	47.14 550	10.24 548	44.77 547	8.72 550	33.94 540	26.10 546

VLMVS		51.63 500	52.90 497	47.80 521	47.64 561	20.83 564	69.98 534	55.61 545	20.15 543	63.34 507	87.24 505	19.48 540	43.90 548	62.94 511	49.76 528	78.65 525

SIFT-NCM-Cal		31.73 512	31.67 516	31.91 530	67.18 539	27.55 555	58.36 544	33.09 556	18.38 551	14.93 557	45.16 555	8.60 554	43.82 549	7.62 559	31.68 541	24.36 550

SIFT-NN-UMatch		31.23 514	31.05 519	31.79 531	60.08 552	27.23 557	58.49 543	33.65 554	19.13 546	17.30 554	47.31 548	10.12 549	42.88 550	8.67 553	24.67 546	25.27 548

SIFT-NN-CMatch		31.71 513	31.56 517	32.16 529	62.58 548	27.53 556	56.45 545	33.28 555	19.00 548	23.65 551	47.34 547	10.05 551	42.72 551	8.71 552	22.96 548	26.24 545

SIFT-UMatch		29.40 517	28.87 522	30.98 533	62.08 550	26.57 558	56.09 546	29.45 559	18.31 552	15.86 556	46.00 551	8.23 556	42.54 552	7.99 556	15.81 554	23.85 551

SIFT-ConvMatch		30.09 515	29.76 520	31.09 532	65.16 544	27.56 554	54.13 548	31.17 557	18.55 550	17.88 553	45.89 552	8.40 555	42.26 553	8.11 555	18.51 551	23.46 552

SIFT-CM-Cal		28.34 518	27.90 523	29.63 534	63.75 546	25.98 559	50.66 551	26.18 561	18.12 554	16.88 555	44.64 556	8.08 557	39.70 554	7.65 558	15.19 556	23.22 553

SIFT-UM-Cal		27.47 519	27.02 524	28.83 537	62.12 549	24.58 561	53.60 549	23.46 562	18.14 553	12.85 559	45.56 553	7.49 559	39.45 555	7.68 557	12.30 557	22.45 554

SIFT-NN-PointCN		29.63 516	29.72 521	29.36 535	57.55 555	23.55 562	56.07 547	30.57 558	17.99 555	20.99 552	45.21 554	9.94 552	39.33 556	8.40 554	20.81 549	25.20 549

SIFT-PCN-Cal		24.67 521	24.81 526	24.24 539	56.13 557	18.04 567	49.05 553	23.39 563	16.07 557	12.99 558	40.17 558	6.97 561	34.68 557	6.71 560	11.81 558	19.99 556

SIFT-PointCN		25.49 520	25.71 525	24.84 538	56.17 556	18.65 566	51.37 550	26.53 560	16.31 556	12.78 560	39.87 559	6.41 562	34.09 558	6.51 561	15.42 555	21.77 555

SIFT-NCMNet		21.21 523	21.22 527	21.17 540	52.99 559	16.41 568	42.12 554	14.05 566	15.89 558	10.70 561	35.85 560	5.14 565	29.82 559	5.80 562	8.44 561	17.28 557

MVS_clip		48.84 504	50.24 505	44.65 522	64.05 545	23.54 563	58.84 542	20.46 564	18.73 549	60.84 511	89.57 490	25.96 521	29.22 560	62.25 513	51.44 525	81.19 519

wuyk23d		20.37 524	20.84 528	18.99 541	65.34 543	27.73 553	50.43 552	7.67 568	9.50 560	8.01 562	6.34 561	6.13 563	26.24 561	23.40 544	10.69 560	2.99 558

test123		37.68 508	39.14 512	33.31 526	19.94 566	24.83 560	98.36 417	9.75 567	15.53 559	51.31 523	87.14 506	19.62 539	17.74 562	47.10 529	3.47 562	57.36 537

testmvs		40.60 507	44.45 509	29.05 536	19.49 567	14.11 569	99.68 238	18.47 565	20.74 542	64.59 506	98.48 283	10.95 547	17.09 563	56.66 524	11.01 559	55.94 538

MVS_baseline		18.28 525	19.10 529	15.85 542	22.71 565	1.80 570	10.32 555	3.08 569	1.00 561	27.16 548	68.73 532	2.83 566	0.36 564	17.05 548	18.98 550	45.38 541

Meshroom													0.00 565
: In preparation.
AliceVision / Meshro													0.00 565
: In preparation.
AliceVision_Meshroom													0.00 565
: In preparation.
mmdepth		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 563	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

monomultidepth		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 563	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

test_blank		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.02 562	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

uanet_test		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 563	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

DCPMVS		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 563	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

cdsmvs_eth3d_5k		23.43 522	31.24 518	0.00 543	0.00 568	0.00 571	0.00 556	98.09 238	0.00 563	0.00 564	99.67 116	83.37 322	0.00 565	0.00 563	0.00 563	0.00 559

pcd_1.5k_mvsjas		7.60 527	10.13 531	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 563	91.20 183	0.00 565	0.00 563	0.00 563	0.00 559

sosnet-low-res		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 563	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

sosnet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 563	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

uncertanet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 563	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

Regformer		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 563	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

ab-mvs-re		8.28 526	11.04 530	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	99.40 150	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

uanet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 563	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

PatchmatchNet2					0.00 568	86.19 445	98.94 365	96.51 443	78.40 482
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1														68.29 495	82.87 402	92.70 452
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						90.97 377								86.10 417

FOURS1					99.92 38	97.66 109	99.95 77	98.36 192	95.58 115	99.52 79

test_one_0601					99.94 19	99.30 15		98.41 177	96.63 77	99.75 44	99.93 13	97.49 12

eth-test2					0.00 568

eth-test					0.00 568

RE-MVS-def			98.13 62		99.79 71	96.37 172	99.76 198	98.31 203	94.43 155	99.40 92	99.75 83	92.95 140		98.90 101	99.92 69	99.97 68

IU-MVS					99.93 30	99.31 13		98.41 177	97.71 33	99.84 25				100.00 1	100.00 1	100.00 1

save fliter					99.82 67	98.79 45	99.96 58	98.40 181	97.66 35

test0726					99.93 30	99.29 18	99.96 58	98.42 171	97.28 47	99.86 18	99.94 5	97.22 22

GSMVS																99.59 157

test_part2					99.89 52	99.25 21				99.49 82

sam_mvs1												94.72 77				99.59 157

sam_mvs												94.25 98

MTGPA								98.28 208

MTMP							99.87 136	96.49 444

test9_res														99.71 51	99.99 22	100.00 1

agg_prior2														99.48 66	100.00 1	100.00 1

test_prior4						98.05 85	99.94 95

test_prior2							99.95 77		95.78 108	99.73 49	99.76 75	96.00 43		99.78 38	100.00 1

新几何2							99.40 294

旧先验1					99.76 75	97.52 113		98.64 92			99.85 39	95.63 52			99.94 60	99.99 27

原ACMM2							99.90 119

test222					99.55 99	97.41 121	99.34 306	98.55 122	91.86 293	99.27 103	99.83 52	93.84 113			99.95 55	99.99 27

segment_acmp												96.68 32

testdata1							99.28 320		96.35 93

plane_prior7					95.71 377	91.59 370

plane_prior6					95.76 371	91.72 360						80.47 362

plane_prior4											98.59 269

plane_prior3						91.64 364			96.63 77	93.01 313

plane_prior2							99.84 157		96.38 88

plane_prior1					95.73 374

plane_prior						91.74 356	99.86 149		96.76 72						89.59 337

n2								0.00 570

nn								0.00 570

door-mid								89.69 514

test11								98.44 151

door								90.31 511

HQP5-MVS						91.85 349

HQP-NCC					95.78 367		99.87 136		96.82 68	93.37 308

ACMP_Plane					95.78 367		99.87 136		96.82 68	93.37 308

BP-MVS														97.92 164

HQP3-MVS								97.89 262							89.60 335

HQP2-MVS												80.65 358

NP-MVS					95.77 370	91.79 353					98.65 260

MDTV_nov1_ep13_2view						96.26 175	96.11 476		91.89 291	98.06 176		94.40 88		94.30 278		99.67 135

ACMMP++_ref															87.04 371

ACMMP++															88.23 358

Test By Simon												92.82 145

High-resolution multi-view benchmark