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.

MM		98.51 44	98.24 60	99.33 31	99.12 114	98.14 61	98.93 106	97.02 388	98.96 1	99.17 57	99.47 33	91.97 144	99.94 13	99.85 5	99.69 67	99.91 4

fmvsm_s_conf0.5_n_9		98.63 25	98.66 19	98.54 103	99.40 62	95.83 190	98.79 158	99.17 34	98.94 2	99.92 1	99.61 4	92.49 121	99.93 32	99.86 1	99.76 43	99.86 10

fmvsm_s_conf0.5_n_8		98.73 20	98.62 20	99.05 62	99.35 64	97.27 101	98.80 150	99.23 25	98.93 3	99.79 13	99.59 12	92.34 126	99.95 9	99.82 6	99.71 64	99.92 2

fmvsm_l_conf0.5_n_9		98.90 13	98.79 11	99.24 41	99.34 65	97.83 74	98.70 182	99.26 16	98.85 4	99.92 1	99.51 24	93.91 103	99.95 9	99.86 1	99.79 30	99.92 2

fmvsm_s_conf0.5_n_3		98.53 41	98.45 34	98.79 80	99.23 98	97.32 94	98.80 150	99.26 16	98.82 5	99.87 4	99.60 9	90.95 184	99.93 32	99.76 9	99.73 57	99.12 182

fmvsm_s_conf0.5_n_2		98.30 70	98.21 64	98.57 98	99.25 90	97.11 114	98.66 194	99.20 30	98.82 5	99.79 13	99.60 9	89.38 220	99.92 41	99.80 7	99.38 128	98.69 238

fmvsm_s_conf0.1_n_2		98.14 76	98.02 77	98.53 106	98.88 141	97.07 116	98.69 185	98.82 95	98.78 7	99.77 16	99.61 4	88.83 240	99.91 51	99.71 13	99.07 144	98.61 248

fmvsm_l_conf0.5_n_3		98.90 13	98.74 16	99.37 23	99.36 63	98.25 51	98.89 115	99.24 20	98.77 8	99.89 3	99.59 12	93.39 109	99.96 4	99.78 8	99.76 43	99.89 6

test_fmvsmconf0.1_n		98.58 32	98.44 35	98.99 65	97.73 279	97.15 112	98.84 137	98.97 53	98.75 9	99.43 39	99.54 18	93.29 111	99.93 32	99.64 18	99.79 30	99.89 6

test_fmvsmconf_n		98.92 11	98.87 6	99.04 63	98.88 141	97.25 107	98.82 141	99.34 11	98.75 9	99.80 12	99.61 4	95.16 74	99.95 9	99.70 15	99.80 24	99.93 1

test_fmvsm_n_1920		98.87 16	99.01 3	98.45 117	99.42 60	96.43 149	98.96 96	99.36 10	98.63 11	99.86 7	99.51 24	95.91 43	99.97 1	99.72 12	99.75 50	98.94 210

test_fmvsmconf0.01_n		97.86 87	97.54 98	98.83 78	95.48 408	96.83 126	98.95 97	98.60 159	98.58 12	98.93 75	99.55 16	88.57 245	99.91 51	99.54 22	99.61 86	99.77 35

MVS_0304		98.23 71	97.91 82	99.21 45	98.06 242	97.96 68	98.58 208	95.51 426	98.58 12	98.87 79	99.26 72	92.99 115	99.95 9	99.62 20	99.67 70	99.73 50

test_fmvsmvis_n_1920		98.44 52	98.51 27	98.23 138	98.33 205	96.15 163	98.97 91	99.15 38	98.55 14	98.45 115	99.55 16	94.26 97	99.97 1	99.65 16	99.66 73	98.57 255

fmvsm_l_conf0.5_n		99.07 4	99.05 2	99.14 53	99.41 61	97.54 83	98.89 115	99.31 13	98.49 15	99.86 7	99.42 42	96.45 24	99.96 4	99.86 1	99.74 54	99.90 5

fmvsm_l_conf0.5_n_a		99.09 1	99.08 1	99.11 57	99.43 59	97.48 85	98.88 122	99.30 14	98.47 16	99.85 10	99.43 41	96.71 17	99.96 4	99.86 1	99.80 24	99.89 6

fmvsm_s_conf0.5_n_4		98.35 63	98.50 29	97.90 170	99.16 109	95.08 226	98.75 163	99.24 20	98.39 17	99.81 11	99.52 21	92.35 125	99.90 59	99.74 11	99.51 110	98.71 236

fmvsm_s_conf0.5_n_7		98.23 71	98.35 43	97.89 172	98.86 145	94.99 232	98.58 208	99.00 49	98.29 18	99.73 20	99.60 9	91.70 149	99.92 41	99.63 19	99.73 57	98.76 230

EPNet		97.28 134	96.87 141	98.51 108	94.98 417	96.14 164	98.90 111	97.02 388	98.28 19	95.99 248	99.11 102	91.36 163	99.89 62	96.98 146	99.19 141	99.50 101
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepPCF-MVS	96.37 2	97.93 85	98.48 33	96.30 307	99.00 128	89.54 392	97.43 354	98.87 80	98.16 20	99.26 52	99.38 51	96.12 35	99.64 150	98.30 72	99.77 37	99.72 54

fmvsm_s_conf0.5_n_6		98.65 22	98.55 25	98.95 72	98.50 181	97.30 97	98.79 158	99.16 36	98.14 21	99.86 7	99.41 44	93.71 106	99.91 51	99.71 13	99.64 81	99.65 78

test_vis1_n_1920		96.71 167	96.84 143	96.31 306	99.11 116	89.74 385	99.05 70	98.58 171	98.08 22	99.87 4	99.37 52	78.48 389	99.93 32	99.29 25	99.69 67	99.27 150

reproduce_model		98.94 8	98.81 10	99.34 27	99.52 41	98.26 50	98.94 100	98.84 90	98.06 23	99.35 44	99.61 4	96.39 27	99.94 13	98.77 40	99.82 14	99.83 16

reproduce-ours		98.93 9	98.78 12	99.38 19	99.49 48	98.38 36	98.86 129	98.83 92	98.06 23	99.29 48	99.58 14	96.40 25	99.94 13	98.68 43	99.81 15	99.81 22

our_new_method		98.93 9	98.78 12	99.38 19	99.49 48	98.38 36	98.86 129	98.83 92	98.06 23	99.29 48	99.58 14	96.40 25	99.94 13	98.68 43	99.81 15	99.81 22

save fliter					99.46 54	98.38 36	98.21 265	98.71 131	97.95 26

fmvsm_s_conf0.5_n		98.42 55	98.51 27	98.13 149	99.30 77	95.25 217	98.85 133	99.39 7	97.94 27	99.74 19	99.62 3	92.59 120	99.91 51	99.65 16	99.52 108	99.25 159

patch_mono-2		98.36 61	98.87 6	96.82 254	99.53 38	90.68 365	98.64 198	99.29 15	97.88 28	99.19 56	99.52 21	96.80 15	99.97 1	99.11 29	99.86 2	99.82 20

NormalMVS		98.07 79	97.90 83	98.59 97	99.75 3	96.60 137	98.94 100	98.60 159	97.86 29	98.71 95	99.08 114	91.22 171	99.80 103	97.40 132	99.57 94	99.37 128

SymmetryMVS		97.84 90	97.58 92	98.62 94	99.01 126	96.60 137	98.94 100	98.44 205	97.86 29	98.71 95	99.08 114	91.22 171	99.80 103	97.40 132	97.53 231	99.47 110

NCCC		98.61 27	98.35 43	99.38 19	99.28 86	98.61 27	98.45 232	98.76 119	97.82 31	98.45 115	98.93 138	96.65 19	99.83 84	97.38 135	99.41 123	99.71 58

CNVR-MVS		98.78 17	98.56 24	99.45 15	99.32 71	98.87 19	98.47 230	98.81 101	97.72 32	98.76 89	99.16 93	97.05 13	99.78 118	98.06 83	99.66 73	99.69 65

DeepC-MVS_fast	96.70 1	98.55 39	98.34 49	99.18 48	99.25 90	98.04 64	98.50 227	98.78 115	97.72 32	98.92 77	99.28 68	95.27 67	99.82 91	97.55 122	99.77 37	99.69 65
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DELS-MVS		98.40 57	98.20 66	98.99 65	99.00 128	97.66 76	97.75 332	98.89 70	97.71 34	98.33 123	98.97 129	94.97 81	99.88 71	98.42 67	99.76 43	99.42 123
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
test_cas_vis1_n_1920		97.38 129	97.36 112	97.45 209	98.95 136	93.25 312	99.00 84	98.53 182	97.70 35	99.77 16	99.35 58	84.71 328	99.85 78	98.57 50	99.66 73	99.26 157

fmvsm_s_conf0.5_n_a		98.38 58	98.42 36	98.27 132	99.09 118	95.41 207	98.86 129	99.37 9	97.69 36	99.78 15	99.61 4	92.38 124	99.91 51	99.58 21	99.43 121	99.49 106

SED-MVS		99.09 1	98.91 4	99.63 4	99.71 21	99.24 5	99.02 80	98.87 80	97.65 37	99.73 20	99.48 31	97.53 7	99.94 13	98.43 65	99.81 15	99.70 62

test_241102_TWO								98.87 80	97.65 37	99.53 35	99.48 31	97.34 11	99.94 13	98.43 65	99.80 24	99.83 16

test_241102_ONE					99.71 21	99.24 5		98.87 80	97.62 39	99.73 20	99.39 46	97.53 7	99.74 128

DVP-MVS		99.03 5	98.83 9	99.63 4	99.72 14	99.25 2	98.97 91	98.58 171	97.62 39	99.45 37	99.46 38	97.42 9	99.94 13	98.47 61	99.81 15	99.69 65
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
test0726					99.72 14	99.25 2	99.06 68	98.88 73	97.62 39	99.56 32	99.50 27	97.42 9

lecture		98.95 7	98.78 12	99.45 15	99.75 3	98.63 26	99.43 10	99.38 8	97.60 42	99.58 31	99.47 33	95.36 61	99.93 32	98.87 36	99.57 94	99.78 28

DPE-MVS		98.92 11	98.67 18	99.65 2	99.58 34	99.20 9	98.42 242	98.91 67	97.58 43	99.54 34	99.46 38	97.10 12	99.94 13	97.64 113	99.84 11	99.83 16
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
reproduce_monomvs		94.77 279	94.67 254	95.08 357	98.40 192	89.48 393	98.80 150	98.64 153	97.57 44	93.21 346	97.65 284	80.57 375	98.83 291	97.72 104	89.47 376	96.93 315

test_one_0601					99.66 28	99.25 2		98.86 86	97.55 45	99.20 54	99.47 33	97.57 6

MSP-MVS		98.74 19	98.55 25	99.29 34	99.75 3	98.23 52	99.26 28	98.88 73	97.52 46	99.41 40	98.78 165	96.00 39	99.79 115	97.79 100	99.59 90	99.85 13
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
HPM-MVS++		98.58 32	98.25 58	99.55 9	99.50 44	99.08 11	98.72 177	98.66 148	97.51 47	98.15 126	98.83 156	95.70 49	99.92 41	97.53 124	99.67 70	99.66 77

fmvsm_s_conf0.5_n_5		98.53 41	98.35 43	99.08 59	99.07 120	97.46 89	98.68 187	99.20 30	97.50 48	99.87 4	99.50 27	91.96 145	99.96 4	99.76 9	99.65 76	99.82 20

fmvsm_s_conf0.1_n		98.18 75	98.21 64	98.11 153	98.54 179	95.24 218	98.87 125	99.24 20	97.50 48	99.70 24	99.67 1	91.33 165	99.89 62	99.47 23	99.54 105	99.21 165

h-mvs33		96.17 193	95.62 207	97.81 178	99.03 123	94.45 259	98.64 198	98.75 121	97.48 50	98.67 98	98.72 178	89.76 205	99.86 77	97.95 88	81.59 431	99.11 185

hse-mvs2		95.71 217	95.30 224	96.93 246	98.50 181	93.53 297	98.36 244	98.10 288	97.48 50	98.67 98	97.99 249	89.76 205	99.02 261	97.95 88	80.91 436	98.22 272

AstraMVS		97.34 132	97.24 119	97.65 199	98.13 235	94.15 275	98.94 100	96.25 417	97.47 52	98.60 106	99.28 68	89.67 209	99.41 199	98.73 41	98.07 206	99.38 127

FOURS1					99.82 1	98.66 24	99.69 1	98.95 57	97.46 53	99.39 42

SPE-MVS-test		98.49 46	98.50 29	98.46 116	99.20 103	97.05 117	99.64 4	98.50 193	97.45 54	98.88 78	99.14 97	95.25 69	99.15 236	98.83 38	99.56 102	99.20 166

XVS		98.70 21	98.49 31	99.34 27	99.70 24	98.35 45	99.29 23	98.88 73	97.40 55	98.46 112	99.20 83	95.90 45	99.89 62	97.85 96	99.74 54	99.78 28

X-MVStestdata		94.06 335	92.30 361	99.34 27	99.70 24	98.35 45	99.29 23	98.88 73	97.40 55	98.46 112	43.50 460	95.90 45	99.89 62	97.85 96	99.74 54	99.78 28

UGNet		96.78 163	96.30 174	98.19 144	98.24 215	95.89 186	98.88 122	98.93 61	97.39 57	96.81 212	97.84 265	82.60 357	99.90 59	96.53 173	99.49 113	98.79 222
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
APDe-MVS		99.02 6	98.84 8	99.55 9	99.57 35	98.96 16	99.39 11	98.93 61	97.38 58	99.41 40	99.54 18	96.66 18	99.84 82	98.86 37	99.85 6	99.87 9
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SteuartSystems-ACMMP		98.90 13	98.75 15	99.36 25	99.22 100	98.43 34	99.10 64	98.87 80	97.38 58	99.35 44	99.40 45	97.78 5	99.87 73	97.77 101	99.85 6	99.78 28
Skip Steuart: Steuart Systems R&D Blog.
CANet		98.05 80	97.76 86	98.90 76	98.73 155	97.27 101	98.35 245	98.78 115	97.37 60	97.72 166	98.96 134	91.53 158	99.92 41	98.79 39	99.65 76	99.51 99

DVP-MVS++		99.08 3	98.89 5	99.64 3	99.17 105	99.23 7	99.69 1	98.88 73	97.32 61	99.53 35	99.47 33	97.81 3	99.94 13	98.47 61	99.72 62	99.74 45

test_0728_THIRD									97.32 61	99.45 37	99.46 38	97.88 1	99.94 13	98.47 61	99.86 2	99.85 13

guyue		97.57 112	97.37 111	98.20 141	98.50 181	95.86 188	98.89 115	97.03 385	97.29 63	98.73 92	98.90 144	89.41 219	99.32 209	98.68 43	98.86 159	99.42 123

PS-MVSNAJ		97.73 95	97.77 85	97.62 201	98.68 165	95.58 197	97.34 363	98.51 188	97.29 63	98.66 102	97.88 261	94.51 88	99.90 59	97.87 95	99.17 142	97.39 298

SD-MVS		98.64 24	98.68 17	98.53 106	99.33 68	98.36 44	98.90 111	98.85 89	97.28 65	99.72 23	99.39 46	96.63 20	97.60 402	98.17 78	99.85 6	99.64 81
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
MSLP-MVS++		98.56 38	98.57 23	98.55 101	99.26 89	96.80 127	98.71 178	99.05 46	97.28 65	98.84 81	99.28 68	96.47 23	99.40 200	98.52 59	99.70 66	99.47 110

HQP_MVS		96.14 195	95.90 191	96.85 252	97.42 308	94.60 255	98.80 150	98.56 176	97.28 65	95.34 259	98.28 223	87.09 280	99.03 258	96.07 186	94.27 295	96.92 316

plane_prior2							98.80 150		97.28 65

MTAPA		98.58 32	98.29 56	99.46 14	99.76 2	98.64 25	98.90 111	98.74 123	97.27 69	98.02 139	99.39 46	94.81 84	99.96 4	97.91 92	99.79 30	99.77 35

fmvsm_s_conf0.1_n_a		98.08 77	98.04 76	98.21 139	97.66 285	95.39 208	98.89 115	99.17 34	97.24 70	99.76 18	99.67 1	91.13 175	99.88 71	99.39 24	99.41 123	99.35 132

CANet_DTU		96.96 154	96.55 162	98.21 139	98.17 232	96.07 166	97.98 302	98.21 262	97.24 70	97.13 193	98.93 138	86.88 285	99.91 51	95.00 230	99.37 130	98.66 244

EI-MVSNet-Vis-set		98.47 49	98.39 38	98.69 88	99.46 54	96.49 146	98.30 255	98.69 137	97.21 72	98.84 81	99.36 56	95.41 57	99.78 118	98.62 47	99.65 76	99.80 25

MVS_111021_HR		98.47 49	98.34 49	98.88 77	99.22 100	97.32 94	97.91 311	99.58 3	97.20 73	98.33 123	99.00 127	95.99 40	99.64 150	98.05 85	99.76 43	99.69 65

TSAR-MVS + GP.		98.38 58	98.24 60	98.81 79	99.22 100	97.25 107	98.11 286	98.29 248	97.19 74	98.99 69	99.02 121	96.22 30	99.67 143	98.52 59	98.56 177	99.51 99

KinetiMVS		97.48 118	97.05 131	98.78 81	98.37 195	97.30 97	98.99 87	98.70 135	97.18 75	99.02 64	99.01 125	87.50 274	99.67 143	95.33 217	99.33 134	99.37 128

CS-MVS		98.44 52	98.49 31	98.31 130	99.08 119	96.73 131	99.67 3	98.47 200	97.17 76	98.94 71	99.10 104	95.73 48	99.13 240	98.71 42	99.49 113	99.09 190

EI-MVSNet-UG-set		98.41 56	98.34 49	98.61 95	99.45 57	96.32 156	98.28 258	98.68 140	97.17 76	98.74 90	99.37 52	95.25 69	99.79 115	98.57 50	99.54 105	99.73 50

xiu_mvs_v2_base		97.66 102	97.70 88	97.56 205	98.61 174	95.46 205	97.44 352	98.46 201	97.15 78	98.65 103	98.15 236	94.33 94	99.80 103	97.84 98	98.66 171	97.41 296

MVS_111021_LR		98.34 65	98.23 62	98.67 90	99.27 87	96.90 123	97.95 304	99.58 3	97.14 79	98.44 117	99.01 125	95.03 80	99.62 157	97.91 92	99.75 50	99.50 101

xiu_mvs_v1_base_debu		97.60 107	97.56 95	97.72 187	98.35 197	95.98 168	97.86 321	98.51 188	97.13 80	99.01 66	98.40 208	91.56 154	99.80 103	98.53 53	98.68 167	97.37 300

xiu_mvs_v1_base		97.60 107	97.56 95	97.72 187	98.35 197	95.98 168	97.86 321	98.51 188	97.13 80	99.01 66	98.40 208	91.56 154	99.80 103	98.53 53	98.68 167	97.37 300

xiu_mvs_v1_base_debi		97.60 107	97.56 95	97.72 187	98.35 197	95.98 168	97.86 321	98.51 188	97.13 80	99.01 66	98.40 208	91.56 154	99.80 103	98.53 53	98.68 167	97.37 300

3Dnovator+	94.38 6	97.43 125	96.78 148	99.38 19	97.83 270	98.52 29	99.37 13	98.71 131	97.09 83	92.99 355	99.13 98	89.36 221	99.89 62	96.97 147	99.57 94	99.71 58

MCST-MVS		98.65 22	98.37 40	99.48 13	99.60 33	98.87 19	98.41 243	98.68 140	97.04 84	98.52 110	98.80 159	96.78 16	99.83 84	97.93 90	99.61 86	99.74 45

plane_prior3						94.61 253			97.02 85	95.34 259

3Dnovator	94.51 5	97.46 120	96.93 138	99.07 60	97.78 273	97.64 77	99.35 16	99.06 44	97.02 85	93.75 325	99.16 93	89.25 224	99.92 41	97.22 140	99.75 50	99.64 81

test1111		95.94 204	95.78 195	96.41 299	98.99 131	90.12 379	99.04 74	92.45 451	96.99 87	98.03 137	99.27 71	81.40 362	99.48 189	96.87 159	99.04 146	99.63 83

test2506		94.44 306	93.91 304	96.04 316	99.02 124	88.99 403	99.06 68	79.47 465	96.96 88	98.36 120	99.26 72	77.21 404	99.52 179	96.78 166	99.04 146	99.59 89

ECVR-MVS		95.95 201	95.71 201	96.65 266	99.02 124	90.86 360	99.03 77	91.80 452	96.96 88	98.10 130	99.26 72	81.31 363	99.51 180	96.90 153	99.04 146	99.59 89

DeepC-MVS	95.98 3	97.88 86	97.58 92	98.77 82	99.25 90	96.93 121	98.83 139	98.75 121	96.96 88	96.89 208	99.50 27	90.46 193	99.87 73	97.84 98	99.76 43	99.52 96
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MG-MVS		97.81 92	97.60 91	98.44 119	99.12 114	95.97 173	97.75 332	98.78 115	96.89 91	98.46 112	99.22 80	93.90 104	99.68 142	94.81 236	99.52 108	99.67 74

ETV-MVS		97.96 82	97.81 84	98.40 125	98.42 188	97.27 101	98.73 173	98.55 178	96.84 92	98.38 119	97.44 303	95.39 58	99.35 205	97.62 114	98.89 155	98.58 254

TSAR-MVS + MP.		98.78 17	98.62 20	99.24 41	99.69 26	98.28 49	99.14 55	98.66 148	96.84 92	99.56 32	99.31 65	96.34 28	99.70 136	98.32 71	99.73 57	99.73 50
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
dcpmvs_2		98.08 77	98.59 22	96.56 281	99.57 35	90.34 377	99.15 52	98.38 224	96.82 94	99.29 48	99.49 30	95.78 47	99.57 163	98.94 34	99.86 2	99.77 35

EC-MVSNet		98.21 74	98.11 71	98.49 113	98.34 202	97.26 106	99.61 5	98.43 212	96.78 95	98.87 79	98.84 152	93.72 105	99.01 263	98.91 35	99.50 111	99.19 170

EPNet_dtu		95.21 251	94.95 241	95.99 318	96.17 381	90.45 372	98.16 277	97.27 367	96.77 96	93.14 351	98.33 219	90.34 195	98.42 330	85.57 412	98.81 164	99.09 190
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
sasdasda		97.67 100	97.23 120	98.98 67	98.70 160	98.38 36	99.34 17	98.39 220	96.76 97	97.67 170	97.40 307	92.26 130	99.49 184	98.28 73	96.28 272	99.08 194

canonicalmvs		97.67 100	97.23 120	98.98 67	98.70 160	98.38 36	99.34 17	98.39 220	96.76 97	97.67 170	97.40 307	92.26 130	99.49 184	98.28 73	96.28 272	99.08 194

alignmvs		97.56 114	97.07 130	99.01 64	98.66 167	98.37 43	98.83 139	98.06 300	96.74 99	98.00 143	97.65 284	90.80 186	99.48 189	98.37 69	96.56 258	99.19 170

VNet		97.79 93	97.40 109	98.96 70	98.88 141	97.55 81	98.63 201	98.93 61	96.74 99	99.02 64	98.84 152	90.33 196	99.83 84	98.53 53	96.66 254	99.50 101

plane_prior						94.60 255	98.44 237		96.74 99						94.22 297

balanced_conf03		98.45 51	98.35 43	98.74 84	98.65 170	97.55 81	99.19 45	98.60 159	96.72 102	99.35 44	98.77 168	95.06 79	99.55 173	98.95 33	99.87 1	99.12 182

BP-MVS1		97.82 91	97.51 100	98.76 83	98.25 214	97.39 91	99.15 52	97.68 320	96.69 103	98.47 111	99.10 104	90.29 197	99.51 180	98.60 48	99.35 131	99.37 128

MGCFI-Net		97.62 106	97.19 123	98.92 73	98.66 167	98.20 54	99.32 22	98.38 224	96.69 103	97.58 179	97.42 306	92.10 138	99.50 183	98.28 73	96.25 275	99.08 194

UA-Net		97.96 82	97.62 90	98.98 67	98.86 145	97.47 87	98.89 115	99.08 42	96.67 105	98.72 94	99.54 18	93.15 113	99.81 96	94.87 232	98.83 162	99.65 78

OPM-MVS		95.69 220	95.33 221	96.76 257	96.16 383	94.63 250	98.43 239	98.39 220	96.64 106	95.02 267	98.78 165	85.15 318	99.05 254	95.21 226	94.20 298	96.60 358
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Vis-MVSNet		97.42 126	97.11 127	98.34 128	98.66 167	96.23 159	99.22 37	99.00 49	96.63 107	98.04 136	99.21 81	88.05 261	99.35 205	96.01 192	99.21 139	99.45 117
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_vis1_n		95.47 229	95.13 230	96.49 289	97.77 274	90.41 374	99.27 27	98.11 285	96.58 108	99.66 26	99.18 89	67.00 440	99.62 157	99.21 27	99.40 126	99.44 118

SR-MVS		98.57 36	98.35 43	99.24 41	99.53 38	98.18 56	99.09 65	98.82 95	96.58 108	99.10 62	99.32 63	95.39 58	99.82 91	97.70 109	99.63 83	99.72 54

Effi-MVS+-dtu		96.29 188	96.56 161	95.51 341	97.89 268	90.22 378	98.80 150	98.10 288	96.57 110	96.45 234	96.66 372	90.81 185	98.91 278	95.72 204	97.99 207	97.40 297

LuminaMVS		97.49 117	97.18 124	98.42 123	97.50 300	97.15 112	98.45 232	97.68 320	96.56 111	98.68 97	98.78 165	89.84 204	99.32 209	98.60 48	98.57 176	98.79 222

SR-MVS-dyc-post		98.54 40	98.35 43	99.13 54	99.49 48	97.86 70	99.11 61	98.80 108	96.49 112	99.17 57	99.35 58	95.34 63	99.82 91	97.72 104	99.65 76	99.71 58

RE-MVS-def			98.34 49		99.49 48	97.86 70	99.11 61	98.80 108	96.49 112	99.17 57	99.35 58	95.29 66		97.72 104	99.65 76	99.71 58

HQP-NCC					97.20 323		98.05 293		96.43 114	94.45 283

ACMP_Plane					97.20 323		98.05 293		96.43 114	94.45 283

HQP-MVS		95.72 216	95.40 212	96.69 264	97.20 323	94.25 271	98.05 293	98.46 201	96.43 114	94.45 283	97.73 274	86.75 286	98.96 269	95.30 219	94.18 299	96.86 330

test_fmvs1_n		95.90 207	95.99 188	95.63 337	98.67 166	88.32 416	99.26 28	98.22 261	96.40 117	99.67 25	99.26 72	73.91 426	99.70 136	99.02 32	99.50 111	98.87 215

test_fmvs1		96.42 182	96.67 156	95.66 336	98.82 150	88.53 412	98.80 150	98.20 264	96.39 118	99.64 28	99.20 83	80.35 377	99.67 143	99.04 31	99.57 94	98.78 226

diffmvs_AUTHOR		97.59 110	97.44 106	98.01 163	98.26 213	95.47 204	98.12 283	98.36 229	96.38 119	98.84 81	99.10 104	91.13 175	99.26 218	98.24 77	98.56 177	99.30 144

casdiffmvs		97.63 105	97.41 108	98.28 131	98.33 205	96.14 164	98.82 141	98.32 235	96.38 119	97.95 146	99.21 81	91.23 170	99.23 224	98.12 80	98.37 194	99.48 108
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GDP-MVS		97.64 103	97.28 115	98.71 87	98.30 210	97.33 93	99.05 70	98.52 185	96.34 121	98.80 85	99.05 119	89.74 207	99.51 180	96.86 162	98.86 159	99.28 149

testdata1							97.32 365		96.34 121

baseline		97.64 103	97.44 106	98.25 136	98.35 197	96.20 160	99.00 84	98.32 235	96.33 123	98.03 137	99.17 90	91.35 164	99.16 233	98.10 81	98.29 200	99.39 125

APD-MVS_3200maxsize		98.53 41	98.33 53	99.15 52	99.50 44	97.92 69	99.15 52	98.81 101	96.24 124	99.20 54	99.37 52	95.30 65	99.80 103	97.73 103	99.67 70	99.72 54

mPP-MVS		98.51 44	98.26 57	99.25 40	99.75 3	98.04 64	99.28 25	98.81 101	96.24 124	98.35 122	99.23 78	95.46 55	99.94 13	97.42 130	99.81 15	99.77 35

diffmvs		97.58 111	97.40 109	98.13 149	98.32 208	95.81 192	98.06 292	98.37 226	96.20 126	98.74 90	98.89 147	91.31 167	99.25 221	98.16 79	98.52 181	99.34 134
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
casdiffmvs_mvg		97.72 96	97.48 103	98.44 119	98.42 188	96.59 141	98.92 108	98.44 205	96.20 126	97.76 160	99.20 83	91.66 152	99.23 224	98.27 76	98.41 192	99.49 106
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
region2R		98.61 27	98.38 39	99.29 34	99.74 9	98.16 58	99.23 33	98.93 61	96.15 128	98.94 71	99.17 90	95.91 43	99.94 13	97.55 122	99.79 30	99.78 28

testing3-2		95.45 232	95.34 218	95.77 332	98.69 163	88.75 407	98.87 125	97.21 372	96.13 129	97.22 190	97.68 282	77.95 397	99.65 147	97.58 117	96.77 252	98.91 213

MP-MVS		98.33 67	98.01 78	99.28 37	99.75 3	98.18 56	99.22 37	98.79 113	96.13 129	97.92 151	99.23 78	94.54 87	99.94 13	96.74 168	99.78 35	99.73 50
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test_prior2							97.80 328		96.12 131	97.89 155	98.69 180	95.96 41		96.89 154	99.60 88

HFP-MVS		98.63 25	98.40 37	99.32 33	99.72 14	98.29 48	99.23 33	98.96 56	96.10 132	98.94 71	99.17 90	96.06 36	99.92 41	97.62 114	99.78 35	99.75 43

ACMMPR		98.59 30	98.36 41	99.29 34	99.74 9	98.15 59	99.23 33	98.95 57	96.10 132	98.93 75	99.19 88	95.70 49	99.94 13	97.62 114	99.79 30	99.78 28

VortexMVS		95.95 201	95.79 194	96.42 298	98.29 211	93.96 280	98.68 187	98.31 239	96.02 134	94.29 296	97.57 293	89.47 214	98.37 344	97.51 126	91.93 339	96.94 314

ACMMP		98.23 71	97.95 80	99.09 58	99.74 9	97.62 79	99.03 77	99.41 6	95.98 135	97.60 178	99.36 56	94.45 92	99.93 32	97.14 141	98.85 161	99.70 62
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
CP-MVS		98.57 36	98.36 41	99.19 46	99.66 28	97.86 70	99.34 17	98.87 80	95.96 136	98.60 106	99.13 98	96.05 37	99.94 13	97.77 101	99.86 2	99.77 35

SDMVSNet		96.85 159	96.42 167	98.14 145	99.30 77	96.38 152	99.21 40	99.23 25	95.92 137	95.96 250	98.76 173	85.88 303	99.44 196	97.93 90	95.59 287	98.60 249

sd_testset		96.17 193	95.76 196	97.42 212	99.30 77	94.34 266	98.82 141	99.08 42	95.92 137	95.96 250	98.76 173	82.83 356	99.32 209	95.56 210	95.59 287	98.60 249

FIs		96.51 179	96.12 180	97.67 195	97.13 330	97.54 83	99.36 14	99.22 29	95.89 139	94.03 311	98.35 214	91.98 142	98.44 328	96.40 178	92.76 331	97.01 308

EIA-MVS		97.75 94	97.58 92	98.27 132	98.38 193	96.44 148	99.01 82	98.60 159	95.88 140	97.26 187	97.53 297	94.97 81	99.33 208	97.38 135	99.20 140	99.05 199

RRT-MVS		97.03 150	96.78 148	97.77 183	97.90 266	94.34 266	99.12 59	98.35 230	95.87 141	98.06 133	98.70 179	86.45 293	99.63 153	98.04 86	98.54 179	99.35 132

PS-MVSNAJss		96.43 181	96.26 176	96.92 249	95.84 397	95.08 226	99.16 51	98.50 193	95.87 141	93.84 320	98.34 218	94.51 88	98.61 310	96.88 156	93.45 320	97.06 306

FC-MVSNet-test		96.42 182	96.05 182	97.53 206	96.95 339	97.27 101	99.36 14	99.23 25	95.83 143	93.93 314	98.37 212	92.00 141	98.32 349	96.02 191	92.72 332	97.00 309

ACMMP_NAP		98.61 27	98.30 55	99.55 9	99.62 32	98.95 17	98.82 141	98.81 101	95.80 144	99.16 60	99.47 33	95.37 60	99.92 41	97.89 94	99.75 50	99.79 26

MonoMVSNet		95.51 227	95.45 211	95.68 334	95.54 404	90.87 359	98.92 108	97.37 359	95.79 145	95.53 256	97.38 309	89.58 211	97.68 398	96.40 178	92.59 333	98.49 259

ZNCC-MVS		98.49 46	98.20 66	99.35 26	99.73 13	98.39 35	99.19 45	98.86 86	95.77 146	98.31 125	99.10 104	95.46 55	99.93 32	97.57 121	99.81 15	99.74 45

test_fmvs2		93.43 345	93.58 327	92.95 408	96.97 338	83.91 434	99.19 45	97.24 369	95.74 147	95.20 264	98.27 226	69.65 432	98.72 301	96.26 182	93.73 312	96.24 391

jajsoiax		95.45 232	95.03 236	96.73 258	95.42 412	94.63 250	99.14 55	98.52 185	95.74 147	93.22 345	98.36 213	83.87 348	98.65 307	96.95 149	94.04 304	96.91 321

mvs_tets		95.41 237	95.00 237	96.65 266	95.58 403	94.42 261	99.00 84	98.55 178	95.73 149	93.21 346	98.38 211	83.45 354	98.63 308	97.09 143	94.00 306	96.91 321

GST-MVS		98.43 54	98.12 70	99.34 27	99.72 14	98.38 36	99.09 65	98.82 95	95.71 150	98.73 92	99.06 118	95.27 67	99.93 32	97.07 144	99.63 83	99.72 54

CVMVSNet		95.43 234	96.04 183	93.57 398	97.93 264	83.62 436	98.12 283	98.59 166	95.68 151	96.56 225	99.02 121	87.51 272	97.51 407	93.56 286	97.44 232	99.60 87

VPNet		94.99 265	94.19 281	97.40 215	97.16 328	96.57 142	98.71 178	98.97 53	95.67 152	94.84 270	98.24 230	80.36 376	98.67 306	96.46 175	87.32 402	96.96 311

XVG-OURS		96.55 178	96.41 168	96.99 240	98.75 154	93.76 286	97.50 351	98.52 185	95.67 152	96.83 209	99.30 66	88.95 238	99.53 176	95.88 195	96.26 274	97.69 289

testgi		93.06 358	92.45 359	94.88 365	96.43 371	89.90 381	98.75 163	97.54 340	95.60 154	91.63 387	97.91 257	74.46 424	97.02 414	86.10 408	93.67 313	97.72 288

UniMVSNet (Re)		95.78 214	95.19 228	97.58 203	96.99 337	97.47 87	98.79 158	99.18 33	95.60 154	93.92 315	97.04 342	91.68 150	98.48 321	95.80 201	87.66 397	96.79 335

Fast-Effi-MVS+-dtu		95.87 208	95.85 192	95.91 323	97.74 278	91.74 344	98.69 185	98.15 278	95.56 156	94.92 268	97.68 282	88.98 236	98.79 296	93.19 294	97.78 216	97.20 304

viewmanbaseed2359cas		97.47 119	97.25 117	98.14 145	98.41 190	95.84 189	98.57 215	98.43 212	95.55 157	97.97 144	99.12 101	91.26 169	99.15 236	97.42 130	98.53 180	99.43 120

CLD-MVS		95.62 223	95.34 218	96.46 295	97.52 299	93.75 288	97.27 369	98.46 201	95.53 158	94.42 288	98.00 248	86.21 297	98.97 265	96.25 184	94.37 293	96.66 353
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
mvsany_test1		97.69 99	97.70 88	97.66 198	98.24 215	94.18 274	97.53 348	97.53 341	95.52 159	99.66 26	99.51 24	94.30 95	99.56 166	98.38 68	98.62 172	99.23 161

OMC-MVS		97.55 115	97.34 113	98.20 141	99.33 68	95.92 180	98.28 258	98.59 166	95.52 159	97.97 144	99.10 104	93.28 112	99.49 184	95.09 227	98.88 156	99.19 170

nrg030		96.28 190	95.72 198	97.96 168	96.90 344	98.15 59	99.39 11	98.31 239	95.47 161	94.42 288	98.35 214	92.09 139	98.69 302	97.50 127	89.05 382	97.04 307

XVG-OURS-SEG-HR		96.51 179	96.34 172	97.02 239	98.77 153	93.76 286	97.79 330	98.50 193	95.45 162	96.94 203	99.09 112	87.87 266	99.55 173	96.76 167	95.83 286	97.74 286

PGM-MVS		98.49 46	98.23 62	99.27 39	99.72 14	98.08 63	98.99 87	99.49 5	95.43 163	99.03 63	99.32 63	95.56 52	99.94 13	96.80 165	99.77 37	99.78 28

DU-MVS		95.42 235	94.76 248	97.40 215	96.53 364	96.97 119	98.66 194	98.99 52	95.43 163	93.88 317	97.69 279	88.57 245	98.31 351	95.81 199	87.25 403	96.92 316

myMVS_eth3d28		95.12 256	94.62 256	96.64 270	98.17 232	92.17 333	98.02 297	97.32 361	95.41 165	96.22 239	96.05 395	78.01 395	99.13 240	95.22 225	97.16 237	98.60 249

IS-MVSNet		97.22 138	96.88 140	98.25 136	98.85 148	96.36 154	99.19 45	97.97 305	95.39 166	97.23 189	98.99 128	91.11 178	98.93 275	94.60 247	98.59 174	99.47 110

thres100view900		95.38 238	94.70 252	97.41 213	98.98 132	94.92 237	98.87 125	96.90 395	95.38 167	96.61 223	96.88 359	84.29 335	99.56 166	88.11 394	96.29 269	97.76 284

thres600view7		95.49 228	94.77 247	97.67 195	98.98 132	95.02 228	98.85 133	96.90 395	95.38 167	96.63 221	96.90 358	84.29 335	99.59 160	88.65 391	96.33 265	98.40 263

baseline1		95.84 210	95.12 232	98.01 163	98.49 185	95.98 168	98.73 173	97.03 385	95.37 169	96.22 239	98.19 233	89.96 202	99.16 233	94.60 247	87.48 398	98.90 214

tfpn200view9		95.32 245	94.62 256	97.43 211	98.94 137	94.98 233	98.68 187	96.93 393	95.33 170	96.55 227	96.53 378	84.23 339	99.56 166	88.11 394	96.29 269	97.76 284

thres400		95.38 238	94.62 256	97.65 199	98.94 137	94.98 233	98.68 187	96.93 393	95.33 170	96.55 227	96.53 378	84.23 339	99.56 166	88.11 394	96.29 269	98.40 263

CNLPA		97.45 123	97.03 132	98.73 85	99.05 121	97.44 90	98.07 291	98.53 182	95.32 172	96.80 213	98.53 196	93.32 110	99.72 130	94.31 259	99.31 135	99.02 201

OurMVSNet-221017-0		94.21 320	94.00 297	94.85 367	95.60 402	89.22 398	98.89 115	97.43 354	95.29 173	92.18 378	98.52 199	82.86 355	98.59 314	93.46 287	91.76 342	96.74 340

IU-MVS					99.71 21	99.23 7		98.64 153	95.28 174	99.63 29				98.35 70	99.81 15	99.83 16

WTY-MVS		97.37 131	96.92 139	98.72 86	98.86 145	96.89 125	98.31 252	98.71 131	95.26 175	97.67 170	98.56 195	92.21 134	99.78 118	95.89 194	96.85 248	99.48 108

CHOSEN 280x420		97.18 142	97.18 124	97.20 222	98.81 151	93.27 309	95.78 425	99.15 38	95.25 176	96.79 214	98.11 239	92.29 129	99.07 252	98.56 52	99.85 6	99.25 159

ACMM	93.85 9	95.69 220	95.38 216	96.61 274	97.61 288	93.84 284	98.91 110	98.44 205	95.25 176	94.28 297	98.47 202	86.04 302	99.12 243	95.50 213	93.95 308	96.87 328
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thres200		95.25 248	94.57 259	97.28 219	98.81 151	94.92 237	98.20 267	97.11 377	95.24 178	96.54 229	96.22 389	84.58 332	99.53 176	87.93 399	96.50 261	97.39 298

PAPM_NR		97.46 120	97.11 127	98.50 111	99.50 44	96.41 151	98.63 201	98.60 159	95.18 179	97.06 199	98.06 242	94.26 97	99.57 163	93.80 278	98.87 158	99.52 96

icg_test_0407_2		96.56 177	96.50 165	96.73 258	97.99 253	92.82 324	97.18 377	98.27 249	95.16 180	97.30 184	98.79 161	91.53 158	98.10 367	94.74 238	97.54 227	99.27 150

IMVS_0407		96.74 164	96.64 158	97.05 237	97.99 253	92.82 324	98.45 232	98.27 249	95.16 180	97.30 184	98.79 161	91.53 158	99.06 253	94.74 238	97.54 227	99.27 150

IMVS_0404		95.82 212	95.52 208	96.73 258	97.99 253	92.82 324	97.23 370	98.27 249	95.16 180	94.31 294	98.79 161	85.63 307	98.10 367	94.74 238	97.54 227	99.27 150

IMVS_0403		96.74 164	96.61 159	97.12 231	97.99 253	92.82 324	98.47 230	98.27 249	95.16 180	97.13 193	98.79 161	91.44 161	99.26 218	94.74 238	97.54 227	99.27 150

UniMVSNet_NR-MVSNet		95.71 217	95.15 229	97.40 215	96.84 347	96.97 119	98.74 167	99.24 20	95.16 180	93.88 317	97.72 276	91.68 150	98.31 351	95.81 199	87.25 403	96.92 316

VPA-MVSNet		95.75 215	95.11 233	97.69 191	97.24 319	97.27 101	98.94 100	99.23 25	95.13 185	95.51 257	97.32 313	85.73 305	98.91 278	97.33 137	89.55 373	96.89 324

SF-MVS		98.59 30	98.32 54	99.41 18	99.54 37	98.71 22	99.04 74	98.81 101	95.12 186	99.32 47	99.39 46	96.22 30	99.84 82	97.72 104	99.73 57	99.67 74

test-LLR		95.10 258	94.87 245	95.80 329	96.77 351	89.70 387	96.91 395	95.21 429	95.11 187	94.83 272	95.72 408	87.71 268	98.97 265	93.06 297	98.50 183	98.72 233

test0.0.03 1		94.08 333	93.51 331	95.80 329	95.53 406	92.89 323	97.38 357	95.97 420	95.11 187	92.51 370	96.66 372	87.71 268	96.94 416	87.03 403	93.67 313	97.57 294

LCM-MVSNet-Re		95.22 250	95.32 222	94.91 362	98.18 229	87.85 422	98.75 163	95.66 425	95.11 187	88.96 410	96.85 362	90.26 199	97.65 399	95.65 208	98.44 186	99.22 163

ITE_SJBPF				95.44 345	97.42 308	91.32 351		97.50 344	95.09 190	93.59 327	98.35 214	81.70 360	98.88 284	89.71 373	93.39 322	96.12 396

PC_three_1452									95.08 191	99.60 30	99.16 93	97.86 2	98.47 324	97.52 125	99.72 62	99.74 45

Elysia		96.64 170	96.02 185	98.51 108	98.04 246	97.30 97	98.74 167	98.60 159	95.04 192	97.91 152	98.84 152	83.59 352	99.48 189	94.20 263	99.25 137	98.75 231

StellarMVS		96.64 170	96.02 185	98.51 108	98.04 246	97.30 97	98.74 167	98.60 159	95.04 192	97.91 152	98.84 152	83.59 352	99.48 189	94.20 263	99.25 137	98.75 231

TranMVSNet+NR-MVSNet		95.14 255	94.48 264	97.11 233	96.45 370	96.36 154	99.03 77	99.03 47	95.04 192	93.58 329	97.93 255	88.27 253	98.03 375	94.13 266	86.90 408	96.95 313

mvsmamba		97.25 137	96.99 135	98.02 162	98.34 202	95.54 201	99.18 49	97.47 347	95.04 192	98.15 126	98.57 194	89.46 216	99.31 212	97.68 111	99.01 149	99.22 163

VDD-MVS		95.82 212	95.23 226	97.61 202	98.84 149	93.98 279	98.68 187	97.40 356	95.02 196	97.95 146	99.34 62	74.37 425	99.78 118	98.64 46	96.80 249	99.08 194

testing91		94.98 267	94.25 278	97.20 222	97.94 262	93.41 302	98.00 300	97.58 331	94.99 197	95.45 258	96.04 396	77.20 405	99.42 198	94.97 231	96.02 282	98.78 226

MVSFormer		97.57 112	97.49 101	97.84 174	98.07 239	95.76 193	99.47 7	98.40 217	94.98 198	98.79 86	98.83 156	92.34 126	98.41 337	96.91 150	99.59 90	99.34 134

test_djsdf		96.00 199	95.69 204	96.93 246	95.72 399	95.49 203	99.47 7	98.40 217	94.98 198	94.58 278	97.86 262	89.16 227	98.41 337	96.91 150	94.12 303	96.88 325

UBG		95.32 245	94.72 251	97.13 229	98.05 244	93.26 310	97.87 319	97.20 373	94.96 200	96.18 242	95.66 411	80.97 369	99.35 205	94.47 253	97.08 239	98.78 226

NR-MVSNet		94.98 267	94.16 284	97.44 210	96.53 364	97.22 109	98.74 167	98.95 57	94.96 200	89.25 409	97.69 279	89.32 222	98.18 361	94.59 249	87.40 400	96.92 316

XVG-ACMP-BASELINE		94.54 295	94.14 286	95.75 333	96.55 363	91.65 346	98.11 286	98.44 205	94.96 200	94.22 301	97.90 258	79.18 385	99.11 245	94.05 271	93.85 310	96.48 380

Vis-MVSNet (Re-imp)		96.87 158	96.55 162	97.83 175	98.73 155	95.46 205	99.20 43	98.30 246	94.96 200	96.60 224	98.87 149	90.05 200	98.59 314	93.67 282	98.60 173	99.46 115

testing11		95.00 263	94.28 276	97.16 227	97.96 261	93.36 307	98.09 289	97.06 383	94.94 204	95.33 262	96.15 391	76.89 410	99.40 200	95.77 203	96.30 268	98.72 233

ACMP	93.49 10	95.34 243	94.98 239	96.43 297	97.67 283	93.48 299	98.73 173	98.44 205	94.94 204	92.53 368	98.53 196	84.50 334	99.14 239	95.48 214	94.00 306	96.66 353
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
testing99		94.83 275	94.08 289	97.07 236	97.94 262	93.13 316	98.10 288	97.17 375	94.86 206	95.34 259	96.00 400	76.31 413	99.40 200	95.08 228	95.90 283	98.68 240

MVSTER		96.06 197	95.72 198	97.08 235	98.23 217	95.93 179	98.73 173	98.27 249	94.86 206	95.07 265	98.09 240	88.21 254	98.54 317	96.59 169	93.46 318	96.79 335

DPM-MVS		97.55 115	96.99 135	99.23 44	99.04 122	98.55 28	97.17 380	98.35 230	94.85 208	97.93 150	98.58 191	95.07 78	99.71 135	92.60 310	99.34 132	99.43 120

MVSMamba_PlusPlus		98.31 68	98.19 68	98.67 90	98.96 135	97.36 92	99.24 31	98.57 173	94.81 209	98.99 69	98.90 144	95.22 72	99.59 160	99.15 28	99.84 11	99.07 198

jason		97.32 133	97.08 129	98.06 159	97.45 306	95.59 196	97.87 319	97.91 311	94.79 210	98.55 109	98.83 156	91.12 177	99.23 224	97.58 117	99.60 88	99.34 134
jason: jason.
SSM_0407		97.17 143	96.87 141	98.08 156	98.19 223	95.90 182	98.52 220	98.44 205	94.77 211	96.75 215	98.93 138	91.22 171	99.22 228	96.54 171	98.43 188	99.10 187

SSM_0404		97.26 136	97.00 133	98.03 160	98.46 186	95.99 167	98.62 204	98.44 205	94.77 211	97.24 188	98.93 138	91.22 171	99.28 215	96.54 171	98.74 166	98.84 218

SD_0403		94.28 317	94.46 266	93.73 395	98.02 249	85.32 431	98.31 252	98.40 217	94.75 213	93.59 327	98.16 235	89.01 232	96.54 426	82.32 430	97.58 225	99.34 134

test_yl		97.22 138	96.78 148	98.54 103	98.73 155	96.60 137	98.45 232	98.31 239	94.70 214	98.02 139	98.42 206	90.80 186	99.70 136	96.81 163	96.79 250	99.34 134

DCV-MVSNet		97.22 138	96.78 148	98.54 103	98.73 155	96.60 137	98.45 232	98.31 239	94.70 214	98.02 139	98.42 206	90.80 186	99.70 136	96.81 163	96.79 250	99.34 134

EU-MVSNet		93.66 340	94.14 286	92.25 414	95.96 393	83.38 438	98.52 220	98.12 282	94.69 216	92.61 365	98.13 238	87.36 278	96.39 430	91.82 333	90.00 366	96.98 310

SCA		95.46 230	95.13 230	96.46 295	97.67 283	91.29 352	97.33 364	97.60 330	94.68 217	96.92 206	97.10 327	83.97 345	98.89 282	92.59 312	98.32 199	99.20 166

LPG-MVS_test		95.62 223	95.34 218	96.47 292	97.46 303	93.54 295	98.99 87	98.54 180	94.67 218	94.36 291	98.77 168	85.39 311	99.11 245	95.71 205	94.15 301	96.76 338

LGP-MVS_train				96.47 292	97.46 303	93.54 295		98.54 180	94.67 218	94.36 291	98.77 168	85.39 311	99.11 245	95.71 205	94.15 301	96.76 338

testing222		94.12 329	93.03 344	97.37 218	98.02 249	94.66 247	97.94 307	96.65 409	94.63 220	95.78 253	95.76 403	71.49 430	98.92 276	91.17 346	95.88 284	98.52 257

mamv4		97.13 146	98.11 71	94.17 391	98.97 134	83.70 435	98.66 194	98.71 131	94.63 220	97.83 156	98.90 144	96.25 29	99.55 173	99.27 26	99.76 43	99.27 150

HPM-MVS		98.36 61	98.10 73	99.13 54	99.74 9	97.82 75	99.53 6	98.80 108	94.63 220	98.61 105	98.97 129	95.13 76	99.77 123	97.65 112	99.83 13	99.79 26
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
SSC-MVS3.2		93.59 344	93.13 342	94.97 360	96.81 350	89.71 386	97.95 304	98.49 198	94.59 223	93.50 335	96.91 357	77.74 398	98.37 344	91.69 337	90.47 359	96.83 333

dmvs_re		94.48 303	94.18 283	95.37 347	97.68 282	90.11 380	98.54 219	97.08 379	94.56 224	94.42 288	97.24 319	84.25 337	97.76 396	91.02 354	92.83 330	98.24 270

BH-RMVSNet		95.92 206	95.32 222	97.69 191	98.32 208	94.64 249	98.19 270	97.45 352	94.56 224	96.03 246	98.61 186	85.02 319	99.12 243	90.68 358	99.06 145	99.30 144

ET-MVSNet_ETH3D		94.13 327	92.98 345	97.58 203	98.22 218	96.20 160	97.31 366	95.37 428	94.53 226	79.56 446	97.63 289	86.51 289	97.53 406	96.91 150	90.74 356	99.02 201

API-MVS		97.41 127	97.25 117	97.91 169	98.70 160	96.80 127	98.82 141	98.69 137	94.53 226	98.11 129	98.28 223	94.50 91	99.57 163	94.12 267	99.49 113	97.37 300

APD-MVS		98.35 63	98.00 79	99.42 17	99.51 42	98.72 21	98.80 150	98.82 95	94.52 228	99.23 53	99.25 77	95.54 54	99.80 103	96.52 174	99.77 37	99.74 45
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mamba_0408		96.81 162	96.38 170	98.09 155	98.19 223	95.90 182	95.69 426	98.32 235	94.51 229	96.75 215	98.73 175	90.99 182	99.27 217	95.83 197	98.43 188	99.10 187

SSM_04072		96.71 167	96.38 170	97.68 193	98.19 223	95.90 182	95.69 426	98.32 235	94.51 229	96.75 215	98.73 175	90.99 182	98.02 376	95.83 197	98.43 188	99.10 187

lupinMVS		97.44 124	97.22 122	98.12 152	98.07 239	95.76 193	97.68 337	97.76 317	94.50 231	98.79 86	98.61 186	92.34 126	99.30 213	97.58 117	99.59 90	99.31 141

PVSNet_Blended_VisFu		97.70 98	97.46 104	98.44 119	99.27 87	95.91 181	98.63 201	99.16 36	94.48 232	97.67 170	98.88 148	92.80 117	99.91 51	97.11 142	99.12 143	99.50 101

HPM-MVS_fast		98.38 58	98.13 69	99.12 56	99.75 3	97.86 70	99.44 9	98.82 95	94.46 233	98.94 71	99.20 83	95.16 74	99.74 128	97.58 117	99.85 6	99.77 35

UWE-MVS		94.30 313	93.89 307	95.53 340	97.83 270	88.95 404	97.52 350	93.25 445	94.44 234	96.63 221	97.07 334	78.70 387	99.28 215	91.99 329	97.56 226	98.36 266

AdaColmap		97.15 145	96.70 153	98.48 114	99.16 109	96.69 133	98.01 298	98.89 70	94.44 234	96.83 209	98.68 181	90.69 190	99.76 124	94.36 255	99.29 136	98.98 205

9.14			98.06 74		99.47 52		98.71 178	98.82 95	94.36 236	99.16 60	99.29 67	96.05 37	99.81 96	97.00 145	99.71 64

PVSNet_BlendedMVS		96.73 166	96.60 160	97.12 231	99.25 90	95.35 212	98.26 261	99.26 16	94.28 237	97.94 148	97.46 300	92.74 118	99.81 96	96.88 156	93.32 323	96.20 393

MVS_Test		97.28 134	97.00 133	98.13 149	98.33 205	95.97 173	98.74 167	98.07 295	94.27 238	98.44 117	98.07 241	92.48 122	99.26 218	96.43 177	98.19 201	99.16 176

tttt0517		96.07 196	95.51 210	97.78 180	98.41 190	94.84 240	99.28 25	94.33 439	94.26 239	97.64 175	98.64 185	84.05 343	99.47 193	95.34 216	97.60 223	99.03 200

UWE-MVS-28		92.79 361	92.51 356	93.62 397	96.46 369	86.28 428	97.93 308	92.71 450	94.17 240	94.78 275	97.16 324	81.05 368	96.43 429	81.45 433	96.86 246	98.14 276

WR-MVS		95.15 254	94.46 266	97.22 221	96.67 359	96.45 147	98.21 265	98.81 101	94.15 241	93.16 348	97.69 279	87.51 272	98.30 353	95.29 221	88.62 388	96.90 323

EPMVS		94.99 265	94.48 264	96.52 287	97.22 321	91.75 343	97.23 370	91.66 453	94.11 242	97.28 186	96.81 365	85.70 306	98.84 288	93.04 299	97.28 235	98.97 206

MP-MVS-pluss		98.31 68	97.92 81	99.49 12	99.72 14	98.88 18	98.43 239	98.78 115	94.10 243	97.69 169	99.42 42	95.25 69	99.92 41	98.09 82	99.80 24	99.67 74
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
PatchmatchNet		95.71 217	95.52 208	96.29 308	97.58 291	90.72 364	96.84 404	97.52 342	94.06 244	97.08 196	96.96 352	89.24 225	98.90 281	92.03 328	98.37 194	99.26 157
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thisisatest0530		96.01 198	95.36 217	97.97 166	98.38 193	95.52 202	98.88 122	94.19 441	94.04 245	97.64 175	98.31 221	83.82 350	99.46 194	95.29 221	97.70 220	98.93 211

K. test v3		92.55 365	91.91 368	94.48 383	95.64 401	89.24 397	99.07 67	94.88 433	94.04 245	86.78 425	97.59 291	77.64 402	97.64 400	92.08 324	89.43 377	96.57 362

mmtdpeth		93.12 357	92.61 353	94.63 377	97.60 289	89.68 389	99.21 40	97.32 361	94.02 247	97.72 166	94.42 425	77.01 409	99.44 196	99.05 30	77.18 447	94.78 425

WBMVS		94.56 293	94.04 291	96.10 315	98.03 248	93.08 320	97.82 327	98.18 269	94.02 247	93.77 324	96.82 364	81.28 364	98.34 346	95.47 215	91.00 354	96.88 325

D2MVS		95.18 253	95.08 234	95.48 342	97.10 332	92.07 337	98.30 255	99.13 40	94.02 247	92.90 356	96.73 368	89.48 213	98.73 300	94.48 252	93.60 317	95.65 407

mvs_anonymous		96.70 169	96.53 164	97.18 225	98.19 223	93.78 285	98.31 252	98.19 266	94.01 250	94.47 282	98.27 226	92.08 140	98.46 325	97.39 134	97.91 210	99.31 141

GA-MVS		94.81 276	94.03 293	97.14 228	97.15 329	93.86 283	96.76 407	97.58 331	94.00 251	94.76 276	97.04 342	80.91 370	98.48 321	91.79 334	96.25 275	99.09 190

ACMH+	92.99 14	94.30 313	93.77 316	95.88 326	97.81 272	92.04 339	98.71 178	98.37 226	93.99 252	90.60 396	98.47 202	80.86 372	99.05 254	92.75 308	92.40 335	96.55 366

sss		97.39 128	96.98 137	98.61 95	98.60 175	96.61 136	98.22 264	98.93 61	93.97 253	98.01 142	98.48 201	91.98 142	99.85 78	96.45 176	98.15 202	99.39 125

HY-MVS	93.96 8	96.82 161	96.23 178	98.57 98	98.46 186	97.00 118	98.14 280	98.21 262	93.95 254	96.72 218	97.99 249	91.58 153	99.76 124	94.51 251	96.54 259	98.95 209

TAMVS		97.02 151	96.79 147	97.70 190	98.06 242	95.31 215	98.52 220	98.31 239	93.95 254	97.05 200	98.61 186	93.49 108	98.52 319	95.33 217	97.81 214	99.29 147

testing3		93.19 354	92.48 358	95.30 350	98.07 239	92.27 331	98.64 198	97.17 375	93.94 256	93.98 313	97.04 342	67.97 437	96.01 434	88.40 392	97.14 238	97.63 291

CP-MVSNet		94.94 272	94.30 275	96.83 253	96.72 356	95.56 198	99.11 61	98.95 57	93.89 257	92.42 373	97.90 258	87.19 279	98.12 366	94.32 258	88.21 391	96.82 334

SixPastTwentyTwo		93.34 348	92.86 347	94.75 372	95.67 400	89.41 396	98.75 163	96.67 407	93.89 257	90.15 401	98.25 229	80.87 371	98.27 358	90.90 355	90.64 357	96.57 362

WR-MVS_H		95.05 261	94.46 266	96.81 255	96.86 346	95.82 191	99.24 31	99.24 20	93.87 259	92.53 368	96.84 363	90.37 194	98.24 359	93.24 292	87.93 394	96.38 385

ab-mvs		96.42 182	95.71 201	98.55 101	98.63 172	96.75 130	97.88 318	98.74 123	93.84 260	96.54 229	98.18 234	85.34 314	99.75 126	95.93 193	96.35 264	99.15 177

USDC		93.33 349	92.71 350	95.21 351	96.83 348	90.83 362	96.91 395	97.50 344	93.84 260	90.72 394	98.14 237	77.69 399	98.82 293	89.51 378	93.21 326	95.97 400

AUN-MVS		94.53 297	93.73 320	96.92 249	98.50 181	93.52 298	98.34 246	98.10 288	93.83 262	95.94 252	97.98 251	85.59 309	99.03 258	94.35 256	80.94 435	98.22 272

mvsany_test3		88.80 400	88.04 400	91.09 418	89.78 448	81.57 443	97.83 326	95.49 427	93.81 263	87.53 420	93.95 432	56.14 451	97.43 408	94.68 242	83.13 425	94.26 427

LF4IMVS		93.14 356	92.79 349	94.20 389	95.88 395	88.67 409	97.66 339	97.07 381	93.81 263	91.71 384	97.65 284	77.96 396	98.81 294	91.47 342	91.92 341	95.12 415

IterMVS-SCA-FT		94.11 330	93.87 308	94.85 367	97.98 259	90.56 371	97.18 377	98.11 285	93.75 265	92.58 366	97.48 299	83.97 345	97.41 409	92.48 319	91.30 348	96.58 360

anonymousdsp		95.42 235	94.91 242	96.94 245	95.10 416	95.90 182	99.14 55	98.41 215	93.75 265	93.16 348	97.46 300	87.50 274	98.41 337	95.63 209	94.03 305	96.50 377

MDTV_nov1_ep13			95.40 212		97.48 301	88.34 415	96.85 403	97.29 364	93.74 267	97.48 182	97.26 316	89.18 226	99.05 254	91.92 332	97.43 233

ETVMVS		94.50 300	93.44 334	97.68 193	98.18 229	95.35 212	98.19 270	97.11 377	93.73 268	96.40 235	95.39 414	74.53 422	98.84 288	91.10 347	96.31 267	98.84 218

BH-untuned		95.95 201	95.72 198	96.65 266	98.55 178	92.26 332	98.23 263	97.79 316	93.73 268	94.62 277	98.01 247	88.97 237	99.00 264	93.04 299	98.51 182	98.68 240

PatchMatch-RL		96.59 174	96.03 184	98.27 132	99.31 73	96.51 145	97.91 311	99.06 44	93.72 270	96.92 206	98.06 242	88.50 250	99.65 147	91.77 335	99.00 151	98.66 244

Effi-MVS+		97.12 147	96.69 154	98.39 126	98.19 223	96.72 132	97.37 359	98.43 212	93.71 271	97.65 174	98.02 245	92.20 135	99.25 221	96.87 159	97.79 215	99.19 170

IterMVS-LS		95.46 230	95.21 227	96.22 310	98.12 236	93.72 291	98.32 251	98.13 281	93.71 271	94.26 298	97.31 314	92.24 132	98.10 367	94.63 244	90.12 364	96.84 331
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		95.96 200	95.83 193	96.36 302	97.93 264	93.70 292	98.12 283	98.27 249	93.70 273	95.07 265	99.02 121	92.23 133	98.54 317	94.68 242	93.46 318	96.84 331

UnsupCasMVSNet_eth		90.99 382	89.92 384	94.19 390	94.08 429	89.83 382	97.13 384	98.67 145	93.69 274	85.83 431	96.19 390	75.15 419	96.74 420	89.14 384	79.41 440	96.00 399

PVSNet	91.96 18	96.35 186	96.15 179	96.96 244	99.17 105	92.05 338	96.08 418	98.68 140	93.69 274	97.75 162	97.80 271	88.86 239	99.69 141	94.26 261	99.01 149	99.15 177

PS-CasMVS		94.67 286	93.99 299	96.71 261	96.68 358	95.26 216	99.13 58	99.03 47	93.68 276	92.33 374	97.95 253	85.35 313	98.10 367	93.59 284	88.16 393	96.79 335

IterMVS		94.09 332	93.85 310	94.80 371	97.99 253	90.35 376	97.18 377	98.12 282	93.68 276	92.46 372	97.34 310	84.05 343	97.41 409	92.51 317	91.33 347	96.62 356
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tt0805		94.54 295	93.85 310	96.63 271	97.98 259	93.06 321	98.77 162	97.84 314	93.67 278	93.80 322	98.04 244	76.88 411	98.96 269	94.79 237	92.86 329	97.86 283

SMA-MVS		98.58 32	98.25 58	99.56 8	99.51 42	99.04 15	98.95 97	98.80 108	93.67 278	99.37 43	99.52 21	96.52 22	99.89 62	98.06 83	99.81 15	99.76 42
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
FMVSNet3		94.97 269	94.26 277	97.11 233	98.18 229	96.62 134	98.56 217	98.26 257	93.67 278	94.09 307	97.10 327	84.25 337	98.01 377	92.08 324	92.14 336	96.70 347

CDS-MVSNet		96.99 153	96.69 154	97.90 170	98.05 244	95.98 168	98.20 267	98.33 234	93.67 278	96.95 202	98.49 200	93.54 107	98.42 330	95.24 224	97.74 218	99.31 141
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
viewmambaseed2359dif		97.01 152	96.84 143	97.51 207	98.19 223	94.21 273	98.16 277	98.23 260	93.61 282	97.78 158	99.13 98	90.79 189	99.18 232	97.24 138	98.40 193	99.15 177

EPP-MVSNet		97.46 120	97.28 115	97.99 165	98.64 171	95.38 209	99.33 21	98.31 239	93.61 282	97.19 191	99.07 117	94.05 100	99.23 224	96.89 154	98.43 188	99.37 128

CHOSEN 1792x2688		97.12 147	96.80 145	98.08 156	99.30 77	94.56 257	98.05 293	99.71 1	93.57 284	97.09 195	98.91 143	88.17 255	99.89 62	96.87 159	99.56 102	99.81 22

PEN-MVS		94.42 307	93.73 320	96.49 289	96.28 376	94.84 240	99.17 50	99.00 49	93.51 285	92.23 376	97.83 268	86.10 299	97.90 386	92.55 315	86.92 407	96.74 340

WB-MVSnew		94.19 322	94.04 291	94.66 375	96.82 349	92.14 334	97.86 321	95.96 421	93.50 286	95.64 255	96.77 367	88.06 260	97.99 380	84.87 418	96.86 246	93.85 437

tpmrst		95.63 222	95.69 204	95.44 345	97.54 296	88.54 411	96.97 390	97.56 334	93.50 286	97.52 181	96.93 356	89.49 212	99.16 233	95.25 223	96.42 263	98.64 246

1314		96.25 192	95.73 197	97.79 179	97.13 330	95.55 200	98.19 270	98.59 166	93.47 288	92.03 381	97.82 269	91.33 165	99.49 184	94.62 246	98.44 186	98.32 269

baseline2		95.11 257	94.52 262	96.87 251	96.65 360	93.56 294	98.27 260	94.10 443	93.45 289	92.02 382	97.43 304	87.45 277	99.19 230	93.88 275	97.41 234	97.87 282

ACMH	92.88 16	94.55 294	93.95 301	96.34 304	97.63 287	93.26 310	98.81 149	98.49 198	93.43 290	89.74 403	98.53 196	81.91 359	99.08 251	93.69 279	93.30 324	96.70 347
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LFMVS		95.86 209	94.98 239	98.47 115	98.87 144	96.32 156	98.84 137	96.02 418	93.40 291	98.62 104	99.20 83	74.99 420	99.63 153	97.72 104	97.20 236	99.46 115

test20.03		90.89 383	90.38 379	92.43 410	93.48 434	88.14 419	98.33 247	97.56 334	93.40 291	87.96 418	96.71 370	80.69 374	94.13 445	79.15 440	86.17 412	95.01 421

PAPR		96.84 160	96.24 177	98.65 92	98.72 159	96.92 122	97.36 361	98.57 173	93.33 293	96.67 219	97.57 293	94.30 95	99.56 166	91.05 353	98.59 174	99.47 110

IB-MVS	91.98 17	93.27 350	91.97 365	97.19 224	97.47 302	93.41 302	97.09 385	95.99 419	93.32 294	92.47 371	95.73 406	78.06 394	99.53 176	94.59 249	82.98 426	98.62 247
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
PHI-MVS		98.34 65	98.06 74	99.18 48	99.15 112	98.12 62	99.04 74	99.09 41	93.32 294	98.83 84	99.10 104	96.54 21	99.83 84	97.70 109	99.76 43	99.59 89

test_vis1_rt		91.29 375	90.65 375	93.19 406	97.45 306	86.25 429	98.57 215	90.90 456	93.30 296	86.94 424	93.59 434	62.07 448	99.11 245	97.48 128	95.58 289	94.22 429

XXY-MVS		95.20 252	94.45 269	97.46 208	96.75 354	96.56 143	98.86 129	98.65 152	93.30 296	93.27 344	98.27 226	84.85 323	98.87 285	94.82 235	91.26 350	96.96 311

原ACMM1				98.65 92	99.32 71	96.62 134		98.67 145	93.27 298	97.81 157	98.97 129	95.18 73	99.83 84	93.84 276	99.46 119	99.50 101

FA-MVS(test-final)		96.41 185	95.94 189	97.82 177	98.21 219	95.20 220	97.80 328	97.58 331	93.21 299	97.36 183	97.70 277	89.47 214	99.56 166	94.12 267	97.99 207	98.71 236

ZD-MVS					99.46 54	98.70 23		98.79 113	93.21 299	98.67 98	98.97 129	95.70 49	99.83 84	96.07 186	99.58 93

TESTMET0.1,1		94.18 325	93.69 323	95.63 337	96.92 341	89.12 399	96.91 395	94.78 434	93.17 301	94.88 269	96.45 381	78.52 388	98.92 276	93.09 296	98.50 183	98.85 216

Syy-MVS		92.55 365	92.61 353	92.38 411	97.39 312	83.41 437	97.91 311	97.46 348	93.16 302	93.42 339	95.37 415	84.75 326	96.12 432	77.00 445	96.99 242	97.60 292

myMVS_eth3d		92.73 362	92.01 364	94.89 364	97.39 312	90.94 357	97.91 311	97.46 348	93.16 302	93.42 339	95.37 415	68.09 436	96.12 432	88.34 393	96.99 242	97.60 292

PVSNet_Blended		97.38 129	97.12 126	98.14 145	99.25 90	95.35 212	97.28 368	99.26 16	93.13 304	97.94 148	98.21 231	92.74 118	99.81 96	96.88 156	99.40 126	99.27 150

GeoE		96.58 176	96.07 181	98.10 154	98.35 197	95.89 186	99.34 17	98.12 282	93.12 305	96.09 244	98.87 149	89.71 208	98.97 265	92.95 302	98.08 205	99.43 120

dmvs_testset		87.64 404	88.93 394	83.79 430	95.25 413	63.36 462	97.20 374	91.17 454	93.07 306	85.64 433	95.98 401	85.30 317	91.52 452	69.42 451	87.33 401	96.49 378

DTE-MVSNet		93.98 337	93.26 340	96.14 312	96.06 387	94.39 263	99.20 43	98.86 86	93.06 307	91.78 383	97.81 270	85.87 304	97.58 404	90.53 359	86.17 412	96.46 382

CSCG		97.85 89	97.74 87	98.20 141	99.67 27	95.16 221	99.22 37	99.32 12	93.04 308	97.02 201	98.92 142	95.36 61	99.91 51	97.43 129	99.64 81	99.52 96

F-COLMAP		97.09 149	96.80 145	97.97 166	99.45 57	94.95 236	98.55 218	98.62 158	93.02 309	96.17 243	98.58 191	94.01 101	99.81 96	93.95 272	98.90 154	99.14 180

train_agg		97.97 81	97.52 99	99.33 31	99.31 73	98.50 30	97.92 309	98.73 126	92.98 310	97.74 163	98.68 181	96.20 32	99.80 103	96.59 169	99.57 94	99.68 70

test_8					99.29 82	98.44 32	97.89 317	98.72 128	92.98 310	97.70 168	98.66 184	96.20 32	99.80 103

thisisatest0515		95.61 226	94.89 244	97.76 184	98.15 234	95.15 223	96.77 406	94.41 437	92.95 312	97.18 192	97.43 304	84.78 325	99.45 195	94.63 244	97.73 219	98.68 240

1112_ss		96.63 172	96.00 187	98.50 111	98.56 176	96.37 153	98.18 275	98.10 288	92.92 313	94.84 270	98.43 204	92.14 136	99.58 162	94.35 256	96.51 260	99.56 95

test-mter		94.08 333	93.51 331	95.80 329	96.77 351	89.70 387	96.91 395	95.21 429	92.89 314	94.83 272	95.72 408	77.69 399	98.97 265	93.06 297	98.50 183	98.72 233

BH-w/o		95.38 238	95.08 234	96.26 309	98.34 202	91.79 341	97.70 336	97.43 354	92.87 315	94.24 300	97.22 321	88.66 243	98.84 288	91.55 341	97.70 220	98.16 275

PMMVS		96.60 173	96.33 173	97.41 213	97.90 266	93.93 281	97.35 362	98.41 215	92.84 316	97.76 160	97.45 302	91.10 179	99.20 229	96.26 182	97.91 210	99.11 185

LS3D		97.16 144	96.66 157	98.68 89	98.53 180	97.19 110	98.93 106	98.90 68	92.83 317	95.99 248	99.37 52	92.12 137	99.87 73	93.67 282	99.57 94	98.97 206

test_fmvs3		87.17 405	87.06 408	87.50 423	91.21 444	75.66 448	99.05 70	96.61 410	92.79 318	88.85 413	92.78 440	43.72 455	93.49 446	93.95 272	84.56 419	93.34 440

v2v482		94.69 281	94.03 293	96.65 266	96.17 381	94.79 245	98.67 192	98.08 293	92.72 319	94.00 312	97.16 324	87.69 271	98.45 326	92.91 303	88.87 386	96.72 343

eth_miper_zixun_eth		94.68 283	94.41 272	95.47 343	97.64 286	91.71 345	96.73 409	98.07 295	92.71 320	93.64 326	97.21 322	90.54 192	98.17 362	93.38 288	89.76 368	96.54 367

ttmdpeth		92.61 364	91.96 367	94.55 379	94.10 428	90.60 370	98.52 220	97.29 364	92.67 321	90.18 399	97.92 256	79.75 381	97.79 393	91.09 348	86.15 414	95.26 411

TEST9					99.31 73	98.50 30	97.92 309	98.73 126	92.63 322	97.74 163	98.68 181	96.20 32	99.80 103

tpm		94.13 327	93.80 313	95.12 354	96.50 366	87.91 421	97.44 352	95.89 424	92.62 323	96.37 237	96.30 384	84.13 342	98.30 353	93.24 292	91.66 345	99.14 180

DP-MVS Recon		97.86 87	97.46 104	99.06 61	99.53 38	98.35 45	98.33 247	98.89 70	92.62 323	98.05 134	98.94 137	95.34 63	99.65 147	96.04 190	99.42 122	99.19 170

v148		94.29 315	93.76 318	95.91 323	96.10 385	92.93 322	98.58 208	97.97 305	92.59 325	93.47 337	96.95 354	88.53 249	98.32 349	92.56 314	87.06 405	96.49 378

CDPH-MVS		97.94 84	97.49 101	99.28 37	99.47 52	98.44 32	97.91 311	98.67 145	92.57 326	98.77 88	98.85 151	95.93 42	99.72 130	95.56 210	99.69 67	99.68 70

CR-MVSNet		94.76 280	94.15 285	96.59 277	97.00 335	93.43 300	94.96 434	97.56 334	92.46 327	96.93 204	96.24 385	88.15 256	97.88 390	87.38 401	96.65 255	98.46 261

GBi-Net		94.49 301	93.80 313	96.56 281	98.21 219	95.00 229	98.82 141	98.18 269	92.46 327	94.09 307	97.07 334	81.16 365	97.95 382	92.08 324	92.14 336	96.72 343

test1		94.49 301	93.80 313	96.56 281	98.21 219	95.00 229	98.82 141	98.18 269	92.46 327	94.09 307	97.07 334	81.16 365	97.95 382	92.08 324	92.14 336	96.72 343

FMVSNet2		94.47 304	93.61 326	97.04 238	98.21 219	96.43 149	98.79 158	98.27 249	92.46 327	93.50 335	97.09 331	81.16 365	98.00 379	91.09 348	91.93 339	96.70 347

cl22		94.68 283	94.19 281	96.13 313	98.11 237	93.60 293	96.94 392	98.31 239	92.43 331	93.32 343	96.87 361	86.51 289	98.28 357	94.10 269	91.16 351	96.51 375

PLC	95.07 4	97.20 141	96.78 148	98.44 119	99.29 82	96.31 158	98.14 280	98.76 119	92.41 332	96.39 236	98.31 221	94.92 83	99.78 118	94.06 270	98.77 165	99.23 161
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MAR-MVS		96.91 156	96.40 169	98.45 117	98.69 163	96.90 123	98.66 194	98.68 140	92.40 333	97.07 198	97.96 252	91.54 157	99.75 126	93.68 280	98.92 153	98.69 238
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
CPTT-MVS		97.72 96	97.32 114	98.92 73	99.64 30	97.10 115	99.12 59	98.81 101	92.34 334	98.09 131	99.08 114	93.01 114	99.92 41	96.06 189	99.77 37	99.75 43

HyFIR lowres test		96.90 157	96.49 166	98.14 145	99.33 68	95.56 198	97.38 357	99.65 2	92.34 334	97.61 177	98.20 232	89.29 223	99.10 249	96.97 147	97.60 223	99.77 35

pm-mvs1		93.94 338	93.06 343	96.59 277	96.49 367	95.16 221	98.95 97	98.03 302	92.32 336	91.08 391	97.84 265	84.54 333	98.41 337	92.16 322	86.13 415	96.19 394

V42		94.78 278	94.14 286	96.70 263	96.33 375	95.22 219	98.97 91	98.09 292	92.32 336	94.31 294	97.06 338	88.39 251	98.55 316	92.90 304	88.87 386	96.34 386

TR-MVS		94.94 272	94.20 280	97.17 226	97.75 275	94.14 276	97.59 345	97.02 388	92.28 338	95.75 254	97.64 287	83.88 347	98.96 269	89.77 371	96.15 279	98.40 263

miper_ehance_all_eth		95.01 262	94.69 253	95.97 320	97.70 281	93.31 308	97.02 388	98.07 295	92.23 339	93.51 334	96.96 352	91.85 146	98.15 363	93.68 280	91.16 351	96.44 383

c3_l		94.79 277	94.43 271	95.89 325	97.75 275	93.12 318	97.16 382	98.03 302	92.23 339	93.46 338	97.05 341	91.39 162	98.01 377	93.58 285	89.21 380	96.53 369

MS-PatchMatch		93.84 339	93.63 325	94.46 385	96.18 380	89.45 394	97.76 331	98.27 249	92.23 339	92.13 379	97.49 298	79.50 382	98.69 302	89.75 372	99.38 128	95.25 412

miper_enhance_ethall		95.10 258	94.75 249	96.12 314	97.53 298	93.73 290	96.61 412	98.08 293	92.20 342	93.89 316	96.65 374	92.44 123	98.30 353	94.21 262	91.16 351	96.34 386

Test_1112_low_res		96.34 187	95.66 206	98.36 127	98.56 176	95.94 176	97.71 335	98.07 295	92.10 343	94.79 274	97.29 315	91.75 148	99.56 166	94.17 265	96.50 261	99.58 93

PVSNet_0	88.72 19	91.28 376	90.03 383	95.00 359	97.99 253	87.29 425	94.84 437	98.50 193	92.06 344	89.86 402	95.19 417	79.81 380	99.39 203	92.27 321	69.79 453	98.33 268

v7n		94.19 322	93.43 335	96.47 292	95.90 394	94.38 264	99.26 28	98.34 233	91.99 345	92.76 360	97.13 326	88.31 252	98.52 319	89.48 379	87.70 396	96.52 372

our_test_3		93.65 342	93.30 338	94.69 373	95.45 410	89.68 389	96.91 395	97.65 324	91.97 346	91.66 386	96.88 359	89.67 209	97.93 385	88.02 397	91.49 346	96.48 380

v8		94.47 304	93.77 316	96.57 280	96.36 373	94.83 242	99.05 70	98.19 266	91.92 347	93.16 348	96.97 350	88.82 242	98.48 321	91.69 337	87.79 395	96.39 384

testdata				98.26 135	99.20 103	95.36 210		98.68 140	91.89 348	98.60 106	99.10 104	94.44 93	99.82 91	94.27 260	99.44 120	99.58 93

Patchmatch-RL test		91.49 373	90.85 374	93.41 400	91.37 443	84.40 432	92.81 448	95.93 423	91.87 349	87.25 421	94.87 421	88.99 233	96.53 427	92.54 316	82.00 428	99.30 144

v1144		94.59 291	93.92 302	96.60 276	96.21 377	94.78 246	98.59 206	98.14 280	91.86 350	94.21 302	97.02 345	87.97 262	98.41 337	91.72 336	89.57 371	96.61 357

DIV-MVS_self_test		94.52 298	94.03 293	95.99 318	97.57 295	93.38 305	97.05 386	97.94 308	91.74 351	92.81 358	97.10 327	89.12 228	98.07 373	92.60 310	90.30 361	96.53 369

Fast-Effi-MVS+		96.28 190	95.70 203	98.03 160	98.29 211	95.97 173	98.58 208	98.25 258	91.74 351	95.29 263	97.23 320	91.03 181	99.15 236	92.90 304	97.96 209	98.97 206

cl____		94.51 299	94.01 296	96.02 317	97.58 291	93.40 304	97.05 386	97.96 307	91.73 353	92.76 360	97.08 333	89.06 231	98.13 365	92.61 309	90.29 362	96.52 372

LTVRE_ROB	92.95 15	94.60 289	93.90 305	96.68 265	97.41 311	94.42 261	98.52 220	98.59 166	91.69 354	91.21 389	98.35 214	84.87 322	99.04 257	91.06 351	93.44 321	96.60 358
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
miper_lstm_enhance		94.33 311	94.07 290	95.11 355	97.75 275	90.97 356	97.22 372	98.03 302	91.67 355	92.76 360	96.97 350	90.03 201	97.78 395	92.51 317	89.64 370	96.56 364

MVP-Stereo		94.28 317	93.92 302	95.35 348	94.95 418	92.60 329	97.97 303	97.65 324	91.61 356	90.68 395	97.09 331	86.32 296	98.42 330	89.70 374	99.34 132	95.02 420
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v1192		94.32 312	93.58 327	96.53 286	96.10 385	94.45 259	98.50 227	98.17 275	91.54 357	94.19 303	97.06 338	86.95 284	98.43 329	90.14 363	89.57 371	96.70 347

TDRefinement		91.06 380	89.68 385	95.21 351	85.35 458	91.49 349	98.51 226	97.07 381	91.47 358	88.83 414	97.84 265	77.31 403	99.09 250	92.79 307	77.98 445	95.04 419

v144192		94.39 309	93.70 322	96.48 291	96.06 387	94.35 265	98.58 208	98.16 277	91.45 359	94.33 293	97.02 345	87.50 274	98.45 326	91.08 350	89.11 381	96.63 355

Baseline_NR-MVSNet		94.35 310	93.81 312	95.96 321	96.20 378	94.05 278	98.61 205	96.67 407	91.44 360	93.85 319	97.60 290	88.57 245	98.14 364	94.39 254	86.93 406	95.68 406

无先验							97.58 346	98.72 128	91.38 361				99.87 73	93.36 290		99.60 87

AllTest		95.24 249	94.65 255	96.99 240	99.25 90	93.21 314	98.59 206	98.18 269	91.36 362	93.52 332	98.77 168	84.67 329	99.72 130	89.70 374	97.87 212	98.02 279

TestCases				96.99 240	99.25 90	93.21 314		98.18 269	91.36 362	93.52 332	98.77 168	84.67 329	99.72 130	89.70 374	97.87 212	98.02 279

v10		94.29 315	93.55 329	96.51 288	96.39 372	94.80 244	98.99 87	98.19 266	91.35 364	93.02 354	96.99 348	88.09 258	98.41 337	90.50 360	88.41 390	96.33 388

v1921920		94.20 321	93.47 333	96.40 301	95.98 391	94.08 277	98.52 220	98.15 278	91.33 365	94.25 299	97.20 323	86.41 294	98.42 330	90.04 368	89.39 378	96.69 352

MSDG		95.93 205	95.30 224	97.83 175	98.90 139	95.36 210	96.83 405	98.37 226	91.32 366	94.43 287	98.73 175	90.27 198	99.60 159	90.05 367	98.82 163	98.52 257

旧先验2							97.57 347		91.30 367	98.67 98			99.80 103	95.70 207

tpmvs		94.60 289	94.36 274	95.33 349	97.46 303	88.60 410	96.88 401	97.68 320	91.29 368	93.80 322	96.42 382	88.58 244	99.24 223	91.06 351	96.04 281	98.17 274

PM-MVS		87.77 403	86.55 409	91.40 417	91.03 446	83.36 439	96.92 393	95.18 431	91.28 369	86.48 429	93.42 435	53.27 452	96.74 420	89.43 380	81.97 429	94.11 431

MIMVSNet		93.26 351	92.21 362	96.41 299	97.73 279	93.13 316	95.65 428	97.03 385	91.27 370	94.04 310	96.06 394	75.33 418	97.19 412	86.56 405	96.23 277	98.92 212

PAPM		94.95 270	94.00 297	97.78 180	97.04 334	95.65 195	96.03 421	98.25 258	91.23 371	94.19 303	97.80 271	91.27 168	98.86 287	82.61 429	97.61 222	98.84 218

dp		94.15 326	93.90 305	94.90 363	97.31 316	86.82 427	96.97 390	97.19 374	91.22 372	96.02 247	96.61 377	85.51 310	99.02 261	90.00 369	94.30 294	98.85 216

UniMVSNet_ETH3D		94.24 319	93.33 337	96.97 243	97.19 326	93.38 305	98.74 167	98.57 173	91.21 373	93.81 321	98.58 191	72.85 429	98.77 298	95.05 229	93.93 309	98.77 229

v1240		94.06 335	93.29 339	96.34 304	96.03 389	93.90 282	98.44 237	98.17 275	91.18 374	94.13 306	97.01 347	86.05 300	98.42 330	89.13 385	89.50 375	96.70 347

tfpnnormal		93.66 340	92.70 351	96.55 285	96.94 340	95.94 176	98.97 91	99.19 32	91.04 375	91.38 388	97.34 310	84.94 321	98.61 310	85.45 414	89.02 384	95.11 416

MDTV_nov1_ep13_2view						84.26 433	96.89 400		90.97 376	97.90 154		89.89 203		93.91 274		99.18 175

FE-MVS		95.62 223	94.90 243	97.78 180	98.37 195	94.92 237	97.17 380	97.38 358	90.95 377	97.73 165	97.70 277	85.32 316	99.63 153	91.18 345	98.33 197	98.79 222

TransMVSNet (Re)		92.67 363	91.51 370	96.15 311	96.58 362	94.65 248	98.90 111	96.73 403	90.86 378	89.46 408	97.86 262	85.62 308	98.09 371	86.45 406	81.12 433	95.71 405

mvs5depth		91.23 377	90.17 381	94.41 387	92.09 440	89.79 383	95.26 432	96.50 411	90.73 379	91.69 385	97.06 338	76.12 415	98.62 309	88.02 397	84.11 422	94.82 422

Anonymous202405211		95.28 247	94.49 263	97.67 195	99.00 128	93.75 288	98.70 182	97.04 384	90.66 380	96.49 231	98.80 159	78.13 393	99.83 84	96.21 185	95.36 291	99.44 118

ppachtmachnet_test		93.22 352	92.63 352	94.97 360	95.45 410	90.84 361	96.88 401	97.88 312	90.60 381	92.08 380	97.26 316	88.08 259	97.86 391	85.12 417	90.33 360	96.22 392

CL-MVSNet_self_test		90.11 389	89.14 391	93.02 407	91.86 442	88.23 418	96.51 415	98.07 295	90.49 382	90.49 397	94.41 426	84.75 326	95.34 439	80.79 435	74.95 450	95.50 408

Anonymous20231206		91.66 372	91.10 372	93.33 402	94.02 432	87.35 424	98.58 208	97.26 368	90.48 383	90.16 400	96.31 383	83.83 349	96.53 427	79.36 439	89.90 367	96.12 396

VDDNet		95.36 241	94.53 261	97.86 173	98.10 238	95.13 224	98.85 133	97.75 318	90.46 384	98.36 120	99.39 46	73.27 428	99.64 150	97.98 87	96.58 257	98.81 221

TinyColmap		92.31 368	91.53 369	94.65 376	96.92 341	89.75 384	96.92 393	96.68 406	90.45 385	89.62 405	97.85 264	76.06 416	98.81 294	86.74 404	92.51 334	95.41 409

pmmvs4		94.69 281	93.99 299	96.81 255	95.74 398	95.94 176	97.40 355	97.67 323	90.42 386	93.37 341	97.59 291	89.08 230	98.20 360	92.97 301	91.67 344	96.30 389

FMVSNet1		93.19 354	92.07 363	96.56 281	97.54 296	95.00 229	98.82 141	98.18 269	90.38 387	92.27 375	97.07 334	73.68 427	97.95 382	89.36 381	91.30 348	96.72 343

KD-MVS_self_test		90.38 386	89.38 389	93.40 401	92.85 437	88.94 405	97.95 304	97.94 308	90.35 388	90.25 398	93.96 431	79.82 379	95.94 435	84.62 423	76.69 448	95.33 410

RPSCF		94.87 274	95.40 212	93.26 404	98.89 140	82.06 442	98.33 247	98.06 300	90.30 389	96.56 225	99.26 72	87.09 280	99.49 184	93.82 277	96.32 266	98.24 270

ADS-MVSNet2		94.58 292	94.40 273	95.11 355	98.00 251	88.74 408	96.04 419	97.30 363	90.15 390	96.47 232	96.64 375	87.89 264	97.56 405	90.08 365	97.06 240	99.02 201

ADS-MVSNet		95.00 263	94.45 269	96.63 271	98.00 251	91.91 340	96.04 419	97.74 319	90.15 390	96.47 232	96.64 375	87.89 264	98.96 269	90.08 365	97.06 240	99.02 201

新几何1				99.16 51	99.34 65	98.01 66		98.69 137	90.06 392	98.13 128	98.95 136	94.60 86	99.89 62	91.97 331	99.47 116	99.59 89

OpenMVS	93.04 13	95.83 211	95.00 237	98.32 129	97.18 327	97.32 94	99.21 40	98.97 53	89.96 393	91.14 390	99.05 119	86.64 288	99.92 41	93.38 288	99.47 116	97.73 287

COLMAP_ROB	93.27 12	95.33 244	94.87 245	96.71 261	99.29 82	93.24 313	98.58 208	98.11 285	89.92 394	93.57 330	99.10 104	86.37 295	99.79 115	90.78 356	98.10 204	97.09 305
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
KD-MVS_2432*1600		89.61 395	87.96 403	94.54 380	94.06 430	91.59 347	95.59 429	97.63 327	89.87 395	88.95 411	94.38 428	78.28 391	96.82 418	84.83 419	68.05 454	95.21 413

miper_refine_blended		89.61 395	87.96 403	94.54 380	94.06 430	91.59 347	95.59 429	97.63 327	89.87 395	88.95 411	94.38 428	78.28 391	96.82 418	84.83 419	68.05 454	95.21 413

QAPM		96.29 188	95.40 212	98.96 70	97.85 269	97.60 80	99.23 33	98.93 61	89.76 397	93.11 352	99.02 121	89.11 229	99.93 32	91.99 329	99.62 85	99.34 134

gm-plane-assit					95.88 395	87.47 423			89.74 398		96.94 355		99.19 230	93.32 291

pmmvs5		93.65 342	92.97 346	95.68 334	95.49 407	92.37 330	98.20 267	97.28 366	89.66 399	92.58 366	97.26 316	82.14 358	98.09 371	93.18 295	90.95 355	96.58 360

CostFormer		94.95 270	94.73 250	95.60 339	97.28 317	89.06 400	97.53 348	96.89 397	89.66 399	96.82 211	96.72 369	86.05 300	98.95 274	95.53 212	96.13 280	98.79 222

WB-MVS		84.86 410	85.33 411	83.46 431	89.48 449	69.56 457	98.19 270	96.42 414	89.55 401	81.79 440	94.67 423	84.80 324	90.12 453	52.44 457	80.64 437	90.69 444

new-patchmatchnet		88.50 401	87.45 406	91.67 416	90.31 447	85.89 430	97.16 382	97.33 360	89.47 402	83.63 438	92.77 441	76.38 412	95.06 442	82.70 428	77.29 446	94.06 434

Patchmatch-test		94.42 307	93.68 324	96.63 271	97.60 289	91.76 342	94.83 438	97.49 346	89.45 403	94.14 305	97.10 327	88.99 233	98.83 291	85.37 415	98.13 203	99.29 147

DP-MVS		96.59 174	95.93 190	98.57 98	99.34 65	96.19 162	98.70 182	98.39 220	89.45 403	94.52 280	99.35 58	91.85 146	99.85 78	92.89 306	98.88 156	99.68 70

test_f		86.07 409	85.39 410	88.10 422	89.28 450	75.57 449	97.73 334	96.33 415	89.41 405	85.35 434	91.56 446	43.31 457	95.53 437	91.32 344	84.23 421	93.21 441

FMVSNet5		91.81 370	90.92 373	94.49 382	97.21 322	92.09 336	98.00 300	97.55 339	89.31 406	90.86 393	95.61 412	74.48 423	95.32 440	85.57 412	89.70 369	96.07 398

EG-PatchMatch MVS		91.13 379	90.12 382	94.17 391	94.73 423	89.00 402	98.13 282	97.81 315	89.22 407	85.32 435	96.46 380	67.71 438	98.42 330	87.89 400	93.82 311	95.08 417

DSMNet-mixed		92.52 367	92.58 355	92.33 412	94.15 427	82.65 440	98.30 255	94.26 440	89.08 408	92.65 364	95.73 406	85.01 320	95.76 436	86.24 407	97.76 217	98.59 252

SSC-MVS		84.27 411	84.71 414	82.96 435	89.19 451	68.83 458	98.08 290	96.30 416	89.04 409	81.37 442	94.47 424	84.60 331	89.89 454	49.80 459	79.52 439	90.15 445

pmmvs-eth3d		90.36 387	89.05 392	94.32 388	91.10 445	92.12 335	97.63 344	96.95 392	88.86 410	84.91 436	93.13 439	78.32 390	96.74 420	88.70 389	81.81 430	94.09 432

test222					99.23 98	97.17 111	97.40 355	98.66 148	88.68 411	98.05 134	98.96 134	94.14 99			99.53 107	99.61 85

Anonymous20240521		91.18 378	90.44 378	93.42 399	93.70 433	88.47 413	98.94 100	97.56 334	88.46 412	89.56 407	95.08 420	77.15 407	96.97 415	83.92 424	89.55 373	94.82 422

MDA-MVSNet-bldmvs		89.97 391	88.35 397	94.83 370	95.21 414	91.34 350	97.64 341	97.51 343	88.36 413	71.17 454	96.13 392	79.22 384	96.63 425	83.65 425	86.27 411	96.52 372

MIMVSNet1		89.67 394	88.28 398	93.82 394	92.81 438	91.08 355	98.01 298	97.45 352	87.95 414	87.90 419	95.87 402	67.63 439	94.56 444	78.73 442	88.18 392	95.83 403

MDA-MVSNet_test_wron		90.71 384	89.38 389	94.68 374	94.83 420	90.78 363	97.19 376	97.46 348	87.60 415	72.41 453	95.72 408	86.51 289	96.71 423	85.92 410	86.80 409	96.56 364

YYNet1		90.70 385	89.39 387	94.62 378	94.79 422	90.65 366	97.20 374	97.46 348	87.54 416	72.54 452	95.74 404	86.51 289	96.66 424	86.00 409	86.76 410	96.54 367

Patchmtry		93.22 352	92.35 360	95.84 328	96.77 351	93.09 319	94.66 441	97.56 334	87.37 417	92.90 356	96.24 385	88.15 256	97.90 386	87.37 402	90.10 365	96.53 369

tpm2		94.19 322	93.76 318	95.46 344	97.23 320	89.04 401	97.31 366	96.85 401	87.08 418	96.21 241	96.79 366	83.75 351	98.74 299	92.43 320	96.23 277	98.59 252

PatchT		93.06 358	91.97 365	96.35 303	96.69 357	92.67 328	94.48 444	97.08 379	86.62 419	97.08 196	92.23 444	87.94 263	97.90 386	78.89 441	96.69 253	98.49 259

TAPA-MVS	93.98 7	95.35 242	94.56 260	97.74 186	99.13 113	94.83 242	98.33 247	98.64 153	86.62 419	96.29 238	98.61 186	94.00 102	99.29 214	80.00 437	99.41 123	99.09 190
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Anonymous20231211		94.10 331	93.26 340	96.61 274	99.11 116	94.28 268	99.01 82	98.88 73	86.43 421	92.81 358	97.57 293	81.66 361	98.68 305	94.83 234	89.02 384	96.88 325

new_pmnet		90.06 390	89.00 393	93.22 405	94.18 426	88.32 416	96.42 417	96.89 397	86.19 422	85.67 432	93.62 433	77.18 406	97.10 413	81.61 432	89.29 379	94.23 428

pmmvs6		91.77 371	90.63 376	95.17 353	94.69 424	91.24 353	98.67 192	97.92 310	86.14 423	89.62 405	97.56 296	75.79 417	98.34 346	90.75 357	84.56 419	95.94 401

test_0402		91.32 374	90.27 380	94.48 383	96.60 361	91.12 354	98.50 227	97.22 370	86.10 424	88.30 417	96.98 349	77.65 401	97.99 380	78.13 443	92.94 328	94.34 426

JIA-IIPM		93.35 347	92.49 357	95.92 322	96.48 368	90.65 366	95.01 433	96.96 391	85.93 425	96.08 245	87.33 450	87.70 270	98.78 297	91.35 343	95.58 289	98.34 267

N_pmnet		87.12 407	87.77 405	85.17 427	95.46 409	61.92 463	97.37 359	70.66 468	85.83 426	88.73 416	96.04 396	85.33 315	97.76 396	80.02 436	90.48 358	95.84 402

Anonymous20240529		95.10 258	94.22 279	97.75 185	99.01 126	94.26 270	98.87 125	98.83 92	85.79 427	96.64 220	98.97 129	78.73 386	99.85 78	96.27 181	94.89 292	99.12 182

cascas		94.63 288	93.86 309	96.93 246	96.91 343	94.27 269	96.00 422	98.51 188	85.55 428	94.54 279	96.23 387	84.20 341	98.87 285	95.80 201	96.98 245	97.66 290

gg-mvs-nofinetune		92.21 369	90.58 377	97.13 229	96.75 354	95.09 225	95.85 423	89.40 458	85.43 429	94.50 281	81.98 453	80.80 373	98.40 343	92.16 322	98.33 197	97.88 281

test_vis3_rt		79.22 413	77.40 420	84.67 428	86.44 456	74.85 452	97.66 339	81.43 463	84.98 430	67.12 456	81.91 454	28.09 465	97.60 402	88.96 387	80.04 438	81.55 454

114514_t		96.93 155	96.27 175	98.92 73	99.50 44	97.63 78	98.85 133	98.90 68	84.80 431	97.77 159	99.11 102	92.84 116	99.66 146	94.85 233	99.77 37	99.47 110

PCF-MVS	93.45 11	94.68 283	93.43 335	98.42 123	98.62 173	96.77 129	95.48 431	98.20 264	84.63 432	93.34 342	98.32 220	88.55 248	99.81 96	84.80 421	98.96 152	98.68 240
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UnsupCasMVSNet_bld		87.17 405	85.12 412	93.31 403	91.94 441	88.77 406	94.92 436	98.30 246	84.30 433	82.30 439	90.04 447	63.96 446	97.25 411	85.85 411	74.47 452	93.93 436

APD_test1		88.22 402	88.01 401	88.86 421	95.98 391	74.66 453	97.21 373	96.44 413	83.96 434	86.66 427	97.90 258	60.95 449	97.84 392	82.73 427	90.23 363	94.09 432

MVStest1		89.53 397	87.99 402	94.14 393	94.39 425	90.42 373	98.25 262	96.84 402	82.81 435	81.18 443	97.33 312	77.09 408	96.94 416	85.27 416	78.79 441	95.06 418

dongtai		82.47 412	81.88 415	84.22 429	95.19 415	76.03 446	94.59 443	74.14 467	82.63 436	87.19 423	96.09 393	64.10 445	87.85 457	58.91 455	84.11 422	88.78 449

ANet_high		69.08 423	65.37 427	80.22 438	65.99 466	71.96 456	90.91 452	90.09 457	82.62 437	49.93 461	78.39 456	29.36 464	81.75 458	62.49 454	38.52 460	86.95 452

RPMNet		92.81 360	91.34 371	97.24 220	97.00 335	93.43 300	94.96 434	98.80 108	82.27 438	96.93 204	92.12 445	86.98 283	99.82 91	76.32 446	96.65 255	98.46 261

tpm cat1		93.36 346	92.80 348	95.07 358	97.58 291	87.97 420	96.76 407	97.86 313	82.17 439	93.53 331	96.04 396	86.13 298	99.13 240	89.24 383	95.87 285	98.10 277

CMPMVS	66.06 21	89.70 393	89.67 386	89.78 419	93.19 435	76.56 445	97.00 389	98.35 230	80.97 440	81.57 441	97.75 273	74.75 421	98.61 310	89.85 370	93.63 315	94.17 430
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs3		86.67 408	84.86 413	92.11 415	88.16 452	87.19 426	96.63 411	94.75 435	79.88 441	87.22 422	92.75 442	66.56 441	95.20 441	81.24 434	76.56 449	93.96 435

sc_t1		91.01 381	89.39 387	95.85 327	95.99 390	90.39 375	98.43 239	97.64 326	78.79 442	92.20 377	97.94 254	66.00 442	98.60 313	91.59 340	85.94 416	98.57 255

OpenMVS_ROB	86.42 20	89.00 399	87.43 407	93.69 396	93.08 436	89.42 395	97.91 311	96.89 397	78.58 443	85.86 430	94.69 422	69.48 433	98.29 356	77.13 444	93.29 325	93.36 439

MVS		94.67 286	93.54 330	98.08 156	96.88 345	96.56 143	98.19 270	98.50 193	78.05 444	92.69 363	98.02 245	91.07 180	99.63 153	90.09 364	98.36 196	98.04 278

tt0320		90.26 388	88.73 395	94.86 366	96.12 384	90.62 368	98.17 276	97.63 327	77.46 445	89.68 404	96.04 396	69.19 434	97.79 393	88.98 386	85.29 418	96.16 395

tt0320-xc		89.79 392	88.11 399	94.84 369	96.19 379	90.61 369	98.16 277	97.22 370	77.35 446	88.75 415	96.70 371	65.94 443	97.63 401	89.31 382	83.39 424	96.28 390

kuosan		78.45 418	77.69 419	80.72 437	92.73 439	75.32 450	94.63 442	74.51 466	75.96 447	80.87 445	93.19 438	63.23 447	79.99 461	42.56 461	81.56 432	86.85 453

DeepMVS_CX				86.78 424	97.09 333	72.30 454		95.17 432	75.92 448	84.34 437	95.19 417	70.58 431	95.35 438	79.98 438	89.04 383	92.68 442

MVS-HIRNet		89.46 398	88.40 396	92.64 409	97.58 291	82.15 441	94.16 447	93.05 449	75.73 449	90.90 392	82.52 452	79.42 383	98.33 348	83.53 426	98.68 167	97.43 295

PMMVS2		77.95 420	75.44 424	85.46 426	82.54 459	74.95 451	94.23 446	93.08 448	72.80 450	74.68 448	87.38 449	36.36 460	91.56 451	73.95 447	63.94 456	89.87 446

testf1		79.02 415	77.70 417	82.99 433	88.10 453	66.90 459	94.67 439	93.11 446	71.08 451	74.02 449	93.41 436	34.15 461	93.25 447	72.25 449	78.50 443	88.82 447

APD_test2		79.02 415	77.70 417	82.99 433	88.10 453	66.90 459	94.67 439	93.11 446	71.08 451	74.02 449	93.41 436	34.15 461	93.25 447	72.25 449	78.50 443	88.82 447

FPMVS		77.62 421	77.14 421	79.05 439	79.25 462	60.97 464	95.79 424	95.94 422	65.96 453	67.93 455	94.40 427	37.73 459	88.88 456	68.83 452	88.46 389	87.29 450

Gipuma		78.40 419	76.75 422	83.38 432	95.54 404	80.43 444	79.42 457	97.40 356	64.67 454	73.46 451	80.82 455	45.65 454	93.14 449	66.32 453	87.43 399	76.56 457
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LCM-MVSNet		78.70 417	76.24 423	86.08 425	77.26 464	71.99 455	94.34 445	96.72 404	61.62 455	76.53 447	89.33 448	33.91 463	92.78 450	81.85 431	74.60 451	93.46 438

PMVS	61.03 23	65.95 425	63.57 429	73.09 442	57.90 467	51.22 469	85.05 455	93.93 444	54.45 456	44.32 462	83.57 451	13.22 466	89.15 455	58.68 456	81.00 434	78.91 456
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		64.94 426	64.25 428	67.02 443	82.28 460	59.36 466	91.83 451	85.63 460	52.69 457	60.22 458	77.28 457	41.06 458	80.12 460	46.15 460	41.14 458	61.57 459

MVE	62.14 22	63.28 428	59.38 431	74.99 440	74.33 465	65.47 461	85.55 454	80.50 464	52.02 458	51.10 460	75.00 459	10.91 469	80.50 459	51.60 458	53.40 457	78.99 455
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		64.07 427	63.26 430	66.53 444	81.73 461	58.81 467	91.85 450	84.75 461	51.93 459	59.09 459	75.13 458	43.32 456	79.09 462	42.03 462	39.47 459	61.69 458

test_method		79.03 414	78.17 416	81.63 436	86.06 457	54.40 468	82.75 456	96.89 397	39.54 460	80.98 444	95.57 413	58.37 450	94.73 443	84.74 422	78.61 442	95.75 404

tmp_tt		68.90 424	66.97 426	74.68 441	50.78 468	59.95 465	87.13 453	83.47 462	38.80 461	62.21 457	96.23 387	64.70 444	76.91 463	88.91 388	30.49 461	87.19 451

wuyk23d		30.17 429	30.18 433	30.16 445	78.61 463	43.29 470	66.79 458	14.21 469	17.31 462	14.82 465	11.93 465	11.55 468	41.43 464	37.08 463	19.30 462	5.76 462

testmvs		21.48 431	24.95 434	11.09 447	14.89 469	6.47 472	96.56 413	9.87 470	7.55 463	17.93 463	39.02 461	9.43 470	5.90 466	16.56 465	12.72 463	20.91 461

test123		20.95 432	23.72 435	12.64 446	13.54 470	8.19 471	96.55 414	6.13 471	7.48 464	16.74 464	37.98 462	12.97 467	6.05 465	16.69 464	5.43 464	23.68 460

EGC-MVSNET		75.22 422	69.54 425	92.28 413	94.81 421	89.58 391	97.64 341	96.50 411	1.82 465	5.57 466	95.74 404	68.21 435	96.26 431	73.80 448	91.71 343	90.99 443

mmdepth		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

monomultidepth		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

test_blank		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

uanet_test		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

DCPMVS		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

cdsmvs_eth3d_5k		23.98 430	31.98 432	0.00 448	0.00 471	0.00 473	0.00 459	98.59 166	0.00 466	0.00 467	98.61 186	90.60 191	0.00 467	0.00 466	0.00 465	0.00 463

pcd_1.5k_mvsjas		7.88 434	10.50 437	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	94.51 88	0.00 467	0.00 466	0.00 465	0.00 463

sosnet-low-res		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

sosnet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

uncertanet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

Regformer		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

ab-mvs-re		8.20 433	10.94 436	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	98.43 204	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

uanet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

WAC-MVS						90.94 357								88.66 390

MSC_two_6792asdad				99.62 6	99.17 105	99.08 11		98.63 156					99.94 13	98.53 53	99.80 24	99.86 10

No_MVS				99.62 6	99.17 105	99.08 11		98.63 156					99.94 13	98.53 53	99.80 24	99.86 10

eth-test2					0.00 471

eth-test					0.00 471

OPU-MVS				99.37 23	99.24 97	99.05 14	99.02 80				99.16 93	97.81 3	99.37 204	97.24 138	99.73 57	99.70 62

test_0728_SECOND				99.71 1	99.72 14	99.35 1	98.97 91	98.88 73					99.94 13	98.47 61	99.81 15	99.84 15

GSMVS																99.20 166

test_part2					99.63 31	99.18 10				99.27 51

sam_mvs1												89.45 217				99.20 166

sam_mvs												88.99 233

ambc				89.49 420	86.66 455	75.78 447	92.66 449	96.72 404		86.55 428	92.50 443	46.01 453	97.90 386	90.32 361	82.09 427	94.80 424

MTGPA								98.74 123

test_post1							96.68 410				30.43 464	87.85 267	98.69 302	92.59 312

test_post											31.83 463	88.83 240	98.91 278

patchmatchnet-post											95.10 419	89.42 218	98.89 282

GG-mvs-BLEND				96.59 277	96.34 374	94.98 233	96.51 415	88.58 459		93.10 353	94.34 430	80.34 378	98.05 374	89.53 377	96.99 242	96.74 340

MTMP							98.89 115	94.14 442

test9_res														96.39 180	99.57 94	99.69 65

agg_prior2														95.87 196	99.57 94	99.68 70

agg_prior					99.30 77	98.38 36		98.72 128		97.57 180			99.81 96

test_prior4						98.01 66	97.86 321

test_prior				99.19 46	99.31 73	98.22 53		98.84 90					99.70 136			99.65 78

新几何2							97.64 341

旧先验1					99.29 82	97.48 85		98.70 135			99.09 112	95.56 52			99.47 116	99.61 85

原ACMM2							97.67 338

testdata2													99.89 62	91.65 339

segment_acmp												96.85 14

test12				99.18 48	99.16 109	98.19 55		98.53 182		98.07 132		95.13 76	99.72 130		99.56 102	99.63 83

plane_prior7					97.42 308	94.63 250

plane_prior6					97.35 315	94.61 253						87.09 280

plane_prior5								98.56 176					99.03 258	96.07 186	94.27 295	96.92 316

plane_prior4											98.28 223

plane_prior1					97.37 314

n2								0.00 472

nn								0.00 472

door-mid								94.37 438

lessismore_v0				94.45 386	94.93 419	88.44 414		91.03 455		86.77 426	97.64 287	76.23 414	98.42 330	90.31 362	85.64 417	96.51 375

test11								98.66 148

door								94.64 436

HQP5-MVS						94.25 271

BP-MVS														95.30 219

HQP4-MVS										94.45 283			98.96 269			96.87 328

HQP3-MVS								98.46 201							94.18 299

HQP2-MVS												86.75 286

NP-MVS					97.28 317	94.51 258					97.73 274

ACMMP++_ref															92.97 327

ACMMP++															93.61 316

Test By Simon												94.64 85

High-resolution multi-view benchmark