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.

AdaColmap		97.23 124	96.80 133	98.51 126	99.99 1	95.60 192	99.09 284	98.84 62	93.32 192	96.74 201	99.72 88	86.04 252	100.00 1	98.01 144	99.43 122	99.94 80

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 18	98.69 75	98.20 9	99.93 1	99.98 2	96.82 24	100.00 1	99.75 36	100.00 1	99.99 23

MCST-MVS		99.32 3	99.14 4	99.86 5	99.97 3	99.59 5	99.97 36	98.64 84	98.47 3	99.13 100	99.92 13	96.38 34	100.00 1	99.74 38	100.00 1	100.00 1

mPP-MVS		98.39 52	98.20 50	98.97 86	99.97 3	96.92 131	99.95 65	98.38 177	95.04 116	98.61 130	99.80 54	93.39 114	100.00 1	98.64 108	100.00 1	99.98 51

CPTT-MVS		97.64 104	97.32 108	98.58 115	99.97 3	95.77 181	99.96 46	98.35 183	89.90 311	98.36 145	99.79 58	91.18 173	99.99 36	98.37 124	99.99 21	99.99 23

DP-MVS Recon		98.41 49	98.02 64	99.56 25	99.97 3	98.70 48	99.92 92	98.44 141	92.06 248	98.40 144	99.84 44	95.68 44	100.00 1	98.19 133	99.71 88	99.97 61

PAPR		98.52 39	98.16 54	99.58 24	99.97 3	98.77 42	99.95 65	98.43 149	95.35 110	98.03 159	99.75 75	94.03 99	99.98 47	98.11 138	99.83 77	99.99 23

HFP-MVS		98.56 36	98.37 40	99.14 66	99.96 8	97.43 107	99.95 65	98.61 92	94.77 126	99.31 89	99.85 33	94.22 92	100.00 1	98.70 103	99.98 32	99.98 51

region2R		98.54 37	98.37 40	99.05 76	99.96 8	97.18 117	99.96 46	98.55 112	94.87 123	99.45 76	99.85 33	94.07 98	100.00 1	98.67 105	100.00 1	99.98 51

ACMMPR		98.50 40	98.32 44	99.05 76	99.96 8	97.18 117	99.95 65	98.60 94	94.77 126	99.31 89	99.84 44	93.73 108	100.00 1	98.70 103	99.98 32	99.98 51

NCCC		99.37 2	99.25 2	99.71 15	99.96 8	99.15 22	99.97 36	98.62 91	98.02 19	99.90 4	99.95 3	97.33 17	100.00 1	99.54 52	100.00 1	100.00 1

CP-MVS		98.45 44	98.32 44	98.87 91	99.96 8	96.62 144	99.97 36	98.39 173	94.43 142	98.90 112	99.87 27	94.30 89	100.00 1	99.04 78	99.99 21	99.99 23

test_one_0601					99.94 13	99.30 12		98.41 166	96.63 70	99.75 37	99.93 11	97.49 10

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 65	98.43 149					100.00 1	99.99 5	100.00 1	100.00 1

XVS		98.70 29	98.55 28	99.15 64	99.94 13	97.50 103	99.94 82	98.42 161	96.22 87	99.41 81	99.78 62	94.34 86	99.96 70	98.92 88	99.95 50	99.99 23

X-MVStestdata		93.83 248	92.06 283	99.15 64	99.94 13	97.50 103	99.94 82	98.42 161	96.22 87	99.41 81	41.37 455	94.34 86	99.96 70	98.92 88	99.95 50	99.99 23

test_prior				99.43 35	99.94 13	98.49 60		98.65 81					99.80 135			99.99 23

MSLP-MVS++		99.13 8	99.01 11	99.49 32	99.94 13	98.46 61	99.98 18	98.86 56	97.10 50	99.80 23	99.94 4	95.92 40	100.00 1	99.51 53	100.00 1	100.00 1

APDe-MVS		99.06 11	98.91 14	99.51 29	99.94 13	98.76 45	99.91 100	98.39 173	97.20 48	99.46 75	99.85 33	95.53 48	99.79 137	99.86 22	100.00 1	99.99 23
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MP-MVS		98.23 66	97.97 68	99.03 78	99.94 13	97.17 120	99.95 65	98.39 173	94.70 130	98.26 151	99.81 53	91.84 164	100.00 1	98.85 94	99.97 42	99.93 81
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CDPH-MVS		98.65 32	98.36 42	99.49 32	99.94 13	98.73 46	99.87 122	98.33 188	93.97 167	99.76 36	99.87 27	94.99 64	99.75 146	98.55 112	100.00 1	99.98 51

PAPM_NR		98.12 70	97.93 74	98.70 102	99.94 13	96.13 170	99.82 151	98.43 149	94.56 134	97.52 176	99.70 94	94.40 81	99.98 47	97.00 178	99.98 32	99.99 23

MG-MVS		98.91 19	98.65 24	99.68 16	99.94 13	99.07 24	99.64 205	99.44 19	97.33 41	99.00 108	99.72 88	94.03 99	99.98 47	98.73 102	100.00 1	100.00 1

SED-MVS		99.28 5	99.11 7	99.77 8	99.93 24	99.30 12	99.96 46	98.43 149	97.27 44	99.80 23	99.94 4	96.71 27	100.00 1	100.00 1	100.00 1	100.00 1

IU-MVS					99.93 24	99.31 10		98.41 166	97.71 28	99.84 18				100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 24	99.30 12		98.43 149	97.26 46	99.80 23	99.88 24	96.71 27	100.00 1

DVP-MVS		99.30 4	99.16 3	99.73 12	99.93 24	99.29 15	99.95 65	98.32 190	97.28 42	99.83 19	99.91 14	97.22 19	100.00 1	99.99 5	100.00 1	99.89 90
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					99.93 24	99.29 15	99.96 46	98.42 161	97.28 42	99.86 12	99.94 4	97.22 19

MSP-MVS		99.09 9	99.12 5	98.98 85	99.93 24	97.24 114	99.95 65	98.42 161	97.50 35	99.52 71	99.88 24	97.43 16	99.71 152	99.50 55	99.98 32	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
agg_prior					99.93 24	98.77 42		98.43 149		99.63 54			99.85 122

FOURS1					99.92 31	97.66 97	99.95 65	98.36 181	95.58 104	99.52 71

ZD-MVS					99.92 31	98.57 56		98.52 121	92.34 238	99.31 89	99.83 46	95.06 59	99.80 135	99.70 43	99.97 42

GST-MVS		98.27 59	97.97 68	99.17 59	99.92 31	97.57 99	99.93 89	98.39 173	94.04 165	98.80 117	99.74 82	92.98 130	100.00 1	98.16 135	99.76 85	99.93 81

TEST9					99.92 31	98.92 29	99.96 46	98.43 149	93.90 173	99.71 44	99.86 29	95.88 41	99.85 122

train_agg		98.88 20	98.65 24	99.59 23	99.92 31	98.92 29	99.96 46	98.43 149	94.35 147	99.71 44	99.86 29	95.94 38	99.85 122	99.69 44	99.98 32	99.99 23

test_8					99.92 31	98.88 32	99.96 46	98.43 149	94.35 147	99.69 46	99.85 33	95.94 38	99.85 122

PGM-MVS		98.34 54	98.13 56	98.99 83	99.92 31	97.00 127	99.75 172	99.50 17	93.90 173	99.37 86	99.76 67	93.24 123	100.00 1	97.75 163	99.96 46	99.98 51

ACMMP		97.74 97	97.44 101	98.66 106	99.92 31	96.13 170	99.18 277	99.45 18	94.84 124	96.41 211	99.71 91	91.40 167	99.99 36	97.99 146	98.03 182	99.87 93
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
DVP-MVS++		99.26 6	99.09 9	99.77 8	99.91 39	99.31 10	99.95 65	98.43 149	96.48 75	99.80 23	99.93 11	97.44 14	100.00 1	99.92 13	99.98 32	100.00 1

MSC_two_6792asdad				99.93 2	99.91 39	99.80 2		98.41 166					100.00 1	99.96 9	100.00 1	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 166					100.00 1	99.96 9	100.00 1	100.00 1

HPM-MVS++		99.07 10	98.88 16	99.63 17	99.90 42	99.02 25	99.95 65	98.56 106	97.56 34	99.44 77	99.85 33	95.38 52	100.00 1	99.31 65	99.99 21	99.87 93

APD-MVS		98.62 33	98.35 43	99.41 38	99.90 42	98.51 59	99.87 122	98.36 181	94.08 160	99.74 40	99.73 85	94.08 97	99.74 148	99.42 61	99.99 21	99.99 23
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DeepC-MVS_fast	96.59 1	98.81 23	98.54 29	99.62 20	99.90 42	98.85 35	99.24 272	98.47 133	98.14 14	99.08 103	99.91 14	93.09 127	100.00 1	99.04 78	99.99 21	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
OPU-MVS				99.93 2	99.89 45	99.80 2	99.96 46				99.80 54	97.44 14	100.00 1	100.00 1	99.98 32	100.00 1

DPE-MVS		99.26 6	99.10 8	99.74 11	99.89 45	99.24 19	99.87 122	98.44 141	97.48 36	99.64 53	99.94 4	96.68 29	99.99 36	99.99 5	100.00 1	99.99 23
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_part2					99.89 45	99.25 18				99.49 74

CSCG		97.10 130	97.04 120	97.27 212	99.89 45	91.92 298	99.90 106	99.07 37	88.67 335	95.26 238	99.82 49	93.17 126	99.98 47	98.15 136	99.47 117	99.90 89

ZNCC-MVS		98.31 56	98.03 63	99.17 59	99.88 49	97.59 98	99.94 82	98.44 141	94.31 150	98.50 137	99.82 49	93.06 128	99.99 36	98.30 128	99.99 21	99.93 81

SR-MVS		98.46 43	98.30 47	98.93 89	99.88 49	97.04 126	99.84 141	98.35 183	94.92 120	99.32 88	99.80 54	93.35 116	99.78 139	99.30 66	99.95 50	99.96 69

9.14			98.38 38		99.87 51		99.91 100	98.33 188	93.22 195	99.78 34	99.89 22	94.57 77	99.85 122	99.84 24	99.97 42

SMA-MVS		98.76 26	98.48 32	99.62 20	99.87 51	98.87 33	99.86 133	98.38 177	93.19 196	99.77 35	99.94 4	95.54 46	100.00 1	99.74 38	99.99 21	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
NormalMVS		97.90 79	97.85 79	98.04 158	99.86 53	95.39 201	99.61 210	97.78 257	96.52 73	98.61 130	99.31 148	92.73 138	99.67 160	96.77 187	99.48 114	99.06 224

lecture		98.67 30	98.46 33	99.28 47	99.86 53	97.88 86	99.97 36	99.25 30	96.07 91	99.79 32	99.70 94	92.53 146	99.98 47	99.51 53	99.48 114	99.97 61

PHI-MVS		98.41 49	98.21 49	99.03 78	99.86 53	97.10 124	99.98 18	98.80 68	90.78 293	99.62 57	99.78 62	95.30 53	100.00 1	99.80 27	99.93 61	99.99 23

MTAPA		98.29 58	97.96 71	99.30 46	99.85 56	97.93 84	99.39 250	98.28 197	95.76 98	97.18 189	99.88 24	92.74 137	100.00 1	98.67 105	99.88 73	99.99 23

LS3D		95.84 188	95.11 200	98.02 159	99.85 56	95.10 216	98.74 332	98.50 130	87.22 357	93.66 256	99.86 29	87.45 230	99.95 79	90.94 294	99.81 83	99.02 228

HPM-MVS		97.96 74	97.72 84	98.68 103	99.84 58	96.39 156	99.90 106	98.17 212	92.61 224	98.62 129	99.57 123	91.87 163	99.67 160	98.87 93	99.99 21	99.99 23
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EI-MVSNet-Vis-set		98.27 59	98.11 58	98.75 99	99.83 59	96.59 148	99.40 246	98.51 124	95.29 112	98.51 136	99.76 67	93.60 112	99.71 152	98.53 115	99.52 107	99.95 76

save fliter					99.82 60	98.79 40	99.96 46	98.40 170	97.66 30

PLC	95.54 3	97.93 77	97.89 77	98.05 157	99.82 60	94.77 226	99.92 92	98.46 135	93.93 170	97.20 187	99.27 153	95.44 51	99.97 58	97.41 168	99.51 110	99.41 181
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
APD-MVS_3200maxsize		98.25 64	98.08 60	98.78 96	99.81 62	96.60 146	99.82 151	98.30 195	93.95 169	99.37 86	99.77 65	92.84 134	99.76 145	98.95 84	99.92 64	99.97 61

EI-MVSNet-UG-set		98.14 69	97.99 66	98.60 111	99.80 63	96.27 159	99.36 256	98.50 130	95.21 114	98.30 148	99.75 75	93.29 120	99.73 151	98.37 124	99.30 131	99.81 102

SR-MVS-dyc-post		98.31 56	98.17 53	98.71 101	99.79 64	96.37 157	99.76 168	98.31 192	94.43 142	99.40 83	99.75 75	93.28 121	99.78 139	98.90 91	99.92 64	99.97 61

RE-MVS-def			98.13 56		99.79 64	96.37 157	99.76 168	98.31 192	94.43 142	99.40 83	99.75 75	92.95 131		98.90 91	99.92 64	99.97 61

HPM-MVS_fast		97.80 91	97.50 97	98.68 103	99.79 64	96.42 152	99.88 119	98.16 217	91.75 259	98.94 110	99.54 126	91.82 165	99.65 164	97.62 166	99.99 21	99.99 23

SF-MVS		98.67 30	98.40 36	99.50 30	99.77 67	98.67 49	99.90 106	98.21 207	93.53 184	99.81 21	99.89 22	94.70 73	99.86 121	99.84 24	99.93 61	99.96 69

MVS_0304		99.06 11	98.84 17	99.72 13	99.76 68	99.21 21	99.99 5	99.34 25	98.70 2	99.44 77	99.75 75	93.24 123	99.99 36	99.94 11	99.41 124	99.95 76

旧先验1					99.76 68	97.52 101		98.64 84			99.85 33	95.63 45			99.94 55	99.99 23

OMC-MVS		97.28 120	97.23 112	97.41 203	99.76 68	93.36 266	99.65 201	97.95 238	96.03 92	97.41 181	99.70 94	89.61 199	99.51 170	96.73 189	98.25 172	99.38 183

新几何1				99.42 37	99.75 71	98.27 65		98.63 90	92.69 219	99.55 66	99.82 49	94.40 81	100.00 1	91.21 286	99.94 55	99.99 23

MP-MVS-pluss		98.07 73	97.64 90	99.38 43	99.74 72	98.41 63	99.74 175	98.18 211	93.35 190	96.45 208	99.85 33	92.64 141	99.97 58	98.91 90	99.89 70	99.77 109
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
TSAR-MVS + MP.		98.93 17	98.77 19	99.41 38	99.74 72	98.67 49	99.77 163	98.38 177	96.73 66	99.88 9	99.74 82	94.89 66	99.59 166	99.80 27	99.98 32	99.97 61
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test12				99.43 35	99.74 72	98.56 57		98.40 170		99.65 50		94.76 69	99.75 146		99.98 32	99.99 23

原ACMM1				98.96 87	99.73 75	96.99 128		98.51 124	94.06 163	99.62 57	99.85 33	94.97 65	99.96 70	95.11 211	99.95 50	99.92 86

TSAR-MVS + GP.		98.60 34	98.51 31	98.86 92	99.73 75	96.63 143	99.97 36	97.92 243	98.07 16	98.76 122	99.55 124	95.00 63	99.94 87	99.91 16	97.68 189	99.99 23

CANet		98.27 59	97.82 81	99.63 17	99.72 77	99.10 23	99.98 18	98.51 124	97.00 56	98.52 134	99.71 91	87.80 222	99.95 79	99.75 36	99.38 126	99.83 98

reproduce_model		98.75 27	98.66 23	99.03 78	99.71 78	97.10 124	99.73 182	98.23 205	97.02 55	99.18 98	99.90 18	94.54 78	99.99 36	99.77 32	99.90 69	99.99 23

F-COLMAP		96.93 142	96.95 123	96.87 223	99.71 78	91.74 303	99.85 136	97.95 238	93.11 202	95.72 229	99.16 164	92.35 152	99.94 87	95.32 208	99.35 129	98.92 232

reproduce-ours		98.78 24	98.67 21	99.09 73	99.70 80	97.30 111	99.74 175	98.25 201	97.10 50	99.10 101	99.90 18	94.59 74	99.99 36	99.77 32	99.91 67	99.99 23

our_new_method		98.78 24	98.67 21	99.09 73	99.70 80	97.30 111	99.74 175	98.25 201	97.10 50	99.10 101	99.90 18	94.59 74	99.99 36	99.77 32	99.91 67	99.99 23

SD-MVS		98.92 18	98.70 20	99.56 25	99.70 80	98.73 46	99.94 82	98.34 187	96.38 81	99.81 21	99.76 67	94.59 74	99.98 47	99.84 24	99.96 46	99.97 61
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
patch_mono-2		98.24 65	99.12 5	95.59 261	99.67 83	86.91 382	99.95 65	98.89 52	97.60 31	99.90 4	99.76 67	96.54 32	99.98 47	99.94 11	99.82 81	99.88 91

ACMMP_NAP		98.49 41	98.14 55	99.54 27	99.66 84	98.62 55	99.85 136	98.37 180	94.68 131	99.53 69	99.83 46	92.87 133	100.00 1	98.66 107	99.84 76	99.99 23

DeepPCF-MVS	95.94 2	97.71 101	98.98 12	93.92 325	99.63 85	81.76 416	99.96 46	98.56 106	99.47 1	99.19 97	99.99 1	94.16 96	100.00 1	99.92 13	99.93 61	100.00 1

EPNet		98.49 41	98.40 36	98.77 98	99.62 86	96.80 137	99.90 106	99.51 16	97.60 31	99.20 95	99.36 144	93.71 109	99.91 103	97.99 146	98.71 157	99.61 140
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MM		98.83 21	98.53 30	99.76 10	99.59 87	99.33 8	99.99 5	99.76 6	98.39 4	99.39 85	99.80 54	90.49 188	99.96 70	99.89 18	99.43 122	99.98 51

PVSNet_BlendedMVS		96.05 181	95.82 177	96.72 228	99.59 87	96.99 128	99.95 65	99.10 34	94.06 163	98.27 149	95.80 330	89.00 210	99.95 79	99.12 72	87.53 322	93.24 384

PVSNet_Blended		97.94 76	97.64 90	98.83 93	99.59 87	96.99 128	100.00 1	99.10 34	95.38 109	98.27 149	99.08 167	89.00 210	99.95 79	99.12 72	99.25 133	99.57 151

PatchMatch-RL		96.04 182	95.40 187	97.95 161	99.59 87	95.22 211	99.52 228	99.07 37	93.96 168	96.49 207	98.35 245	82.28 285	99.82 134	90.15 310	99.22 136	98.81 239

dcpmvs_2		97.42 115	98.09 59	95.42 266	99.58 91	87.24 378	99.23 273	96.95 357	94.28 153	98.93 111	99.73 85	94.39 84	99.16 198	99.89 18	99.82 81	99.86 95

test222					99.55 92	97.41 109	99.34 258	98.55 112	91.86 254	99.27 93	99.83 46	93.84 106			99.95 50	99.99 23

CNLPA		97.76 95	97.38 104	98.92 90	99.53 93	96.84 133	99.87 122	98.14 221	93.78 177	96.55 206	99.69 98	92.28 154	99.98 47	97.13 174	99.44 121	99.93 81

API-MVS		97.86 82	97.66 88	98.47 128	99.52 94	95.41 199	99.47 238	98.87 55	91.68 260	98.84 114	99.85 33	92.34 153	99.99 36	98.44 120	99.96 46	100.00 1

PVSNet	91.05 13	97.13 129	96.69 139	98.45 130	99.52 94	95.81 179	99.95 65	99.65 12	94.73 128	99.04 106	99.21 160	84.48 270	99.95 79	94.92 217	98.74 156	99.58 149

114514_t		97.41 116	96.83 130	99.14 66	99.51 96	97.83 87	99.89 116	98.27 199	88.48 339	99.06 105	99.66 108	90.30 191	99.64 165	96.32 193	99.97 42	99.96 69

cl22		93.77 253	93.25 257	95.33 270	99.49 97	94.43 231	99.61 210	98.09 224	90.38 299	89.16 326	95.61 338	90.56 186	97.34 314	91.93 277	84.45 343	94.21 329

testdata				98.42 134	99.47 98	95.33 205		98.56 106	93.78 177	99.79 32	99.85 33	93.64 111	99.94 87	94.97 215	99.94 55	100.00 1

MAR-MVS		97.43 111	97.19 114	98.15 150	99.47 98	94.79 225	99.05 295	98.76 69	92.65 222	98.66 127	99.82 49	88.52 216	99.98 47	98.12 137	99.63 94	99.67 123
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
DP-MVS		94.54 227	93.42 247	97.91 167	99.46 100	94.04 244	98.93 312	97.48 294	81.15 410	90.04 297	99.55 124	87.02 238	99.95 79	88.97 322	98.11 178	99.73 113

MVS_111021_LR		98.42 48	98.38 38	98.53 123	99.39 101	95.79 180	99.87 122	99.86 2	96.70 67	98.78 118	99.79 58	92.03 160	99.90 105	99.17 71	99.86 75	99.88 91

CHOSEN 280x420		99.01 14	99.03 10	98.95 88	99.38 102	98.87 33	98.46 350	99.42 21	97.03 54	99.02 107	99.09 166	99.35 2	98.21 276	99.73 40	99.78 84	99.77 109

MVS_111021_HR		98.72 28	98.62 26	99.01 82	99.36 103	97.18 117	99.93 89	99.90 1	96.81 64	98.67 126	99.77 65	93.92 101	99.89 110	99.27 67	99.94 55	99.96 69

DPM-MVS		98.83 21	98.46 33	99.97 1	99.33 104	99.92 1	99.96 46	98.44 141	97.96 20	99.55 66	99.94 4	97.18 21	100.00 1	93.81 246	99.94 55	99.98 51

TAPA-MVS	92.12 8	94.42 235	93.60 239	96.90 222	99.33 104	91.78 302	99.78 160	98.00 232	89.89 312	94.52 244	99.47 130	91.97 161	99.18 195	69.90 428	99.52 107	99.73 113
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
reproduce_monomvs		95.38 203	95.07 202	96.32 242	99.32 106	96.60 146	99.76 168	98.85 59	96.65 69	87.83 348	96.05 327	99.52 1	98.11 281	96.58 190	81.07 372	94.25 324

fmvsm_s_conf0.5_n_9		98.15 68	98.02 64	98.55 117	99.28 107	95.84 178	99.99 5	98.57 100	98.17 11	99.93 1	99.74 82	87.04 237	99.97 58	99.86 22	99.59 102	99.83 98

SPE-MVS-test		97.88 80	97.94 73	97.70 183	99.28 107	95.20 212	99.98 18	97.15 332	95.53 106	99.62 57	99.79 58	92.08 159	98.38 259	98.75 101	99.28 132	99.52 163

test_fmvsm_n_1920		98.44 45	98.61 27	97.92 165	99.27 109	95.18 213	100.00 1	98.90 50	98.05 17	99.80 23	99.73 85	92.64 141	99.99 36	99.58 51	99.51 110	98.59 249

fmvsm_l_conf0.5_n_a		99.00 15	98.91 14	99.28 47	99.21 110	97.91 85	99.98 18	98.85 59	98.25 5	99.92 3	99.75 75	94.72 71	99.97 58	99.87 20	99.64 92	99.95 76

fmvsm_s_conf0.5_n_8		98.38 53	98.05 62	99.35 44	99.20 111	98.12 71	99.98 18	98.81 64	98.22 7	99.80 23	99.71 91	87.37 232	99.97 58	99.91 16	99.48 114	99.97 61

test_yl		97.83 86	97.37 105	99.21 53	99.18 112	97.98 80	99.64 205	99.27 27	91.43 269	97.88 166	98.99 176	95.84 42	99.84 130	98.82 95	95.32 251	99.79 105

DCV-MVSNet		97.83 86	97.37 105	99.21 53	99.18 112	97.98 80	99.64 205	99.27 27	91.43 269	97.88 166	98.99 176	95.84 42	99.84 130	98.82 95	95.32 251	99.79 105

fmvsm_l_conf0.5_n		98.94 16	98.84 17	99.25 49	99.17 114	97.81 89	99.98 18	98.86 56	98.25 5	99.90 4	99.76 67	94.21 94	99.97 58	99.87 20	99.52 107	99.98 51

DeepC-MVS	94.51 4	96.92 143	96.40 151	98.45 130	99.16 115	95.90 176	99.66 200	98.06 227	96.37 84	94.37 247	99.49 129	83.29 280	99.90 105	97.63 165	99.61 99	99.55 153
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DELS-MVS		98.54 37	98.22 48	99.50 30	99.15 116	98.65 53	100.00 1	98.58 98	97.70 29	98.21 154	99.24 158	92.58 144	99.94 87	98.63 110	99.94 55	99.92 86
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
fmvsm_l_conf0.5_n_3		98.41 49	98.08 60	99.39 40	99.12 117	98.29 64	99.98 18	98.64 84	98.14 14	99.86 12	99.76 67	87.99 221	99.97 58	99.72 41	99.54 105	99.91 88

CS-MVS		97.79 93	97.91 75	97.43 201	99.10 118	94.42 232	99.99 5	97.10 339	95.07 115	99.68 47	99.75 75	92.95 131	98.34 263	98.38 122	99.14 138	99.54 157

Anonymous202405211		93.10 271	91.99 284	96.40 238	99.10 118	89.65 350	98.88 318	97.93 240	83.71 395	94.00 253	98.75 209	68.79 389	99.88 116	95.08 212	91.71 284	99.68 121

fmvsm_s_conf0.5_n		97.80 91	97.85 79	97.67 184	99.06 120	94.41 233	99.98 18	98.97 43	97.34 39	99.63 54	99.69 98	87.27 233	99.97 58	99.62 49	99.06 143	98.62 248

HyFIR lowres test		96.66 157	96.43 150	97.36 208	99.05 121	93.91 249	99.70 194	99.80 3	90.54 297	96.26 214	98.08 258	92.15 157	98.23 275	96.84 186	95.46 246	99.93 81

LFMVS		94.75 221	93.56 242	98.30 140	99.03 122	95.70 186	98.74 332	97.98 235	87.81 350	98.47 138	99.39 141	67.43 398	99.53 167	98.01 144	95.20 254	99.67 123

fmvsm_s_conf0.5_n_4		97.75 96	97.86 78	97.42 202	99.01 123	94.69 227	99.97 36	98.76 69	97.91 22	99.87 10	99.76 67	86.70 243	99.93 96	99.67 46	99.12 141	97.64 275

fmvsm_s_conf0.5_n_2		97.59 106	97.28 109	98.53 123	99.01 123	98.15 66	99.98 18	98.59 96	98.17 11	99.75 37	99.63 114	81.83 291	99.94 87	99.78 30	98.79 154	97.51 283

AllTest		92.48 286	91.64 289	95.00 279	99.01 123	88.43 366	98.94 310	96.82 371	86.50 366	88.71 331	98.47 240	74.73 364	99.88 116	85.39 362	96.18 223	96.71 289

TestCases				95.00 279	99.01 123	88.43 366		96.82 371	86.50 366	88.71 331	98.47 240	74.73 364	99.88 116	85.39 362	96.18 223	96.71 289

COLMAP_ROB	90.47 14	92.18 293	91.49 295	94.25 313	99.00 127	88.04 372	98.42 356	96.70 378	82.30 406	88.43 340	99.01 173	76.97 339	99.85 122	86.11 358	96.50 215	94.86 300
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
fmvsm_s_conf0.5_n_3		97.95 75	97.66 88	98.81 94	98.99 128	98.07 74	99.98 18	98.81 64	98.18 10	99.89 7	99.70 94	84.15 273	99.97 58	99.76 35	99.50 112	98.39 254

test_fmvs1		95.35 204	95.68 182	94.36 309	98.99 128	84.98 393	99.96 46	96.65 380	97.60 31	99.73 42	98.96 182	71.58 379	99.93 96	98.31 127	99.37 127	98.17 259

HY-MVS	92.50 7	97.79 93	97.17 116	99.63 17	98.98 130	99.32 9	97.49 383	99.52 14	95.69 101	98.32 147	97.41 278	93.32 118	99.77 142	98.08 141	95.75 238	99.81 102

VNet		97.21 125	96.57 144	99.13 70	98.97 131	97.82 88	99.03 298	99.21 32	94.31 150	99.18 98	98.88 194	86.26 250	99.89 110	98.93 86	94.32 264	99.69 120

thres200		96.96 139	96.21 157	99.22 52	98.97 131	98.84 36	99.85 136	99.71 7	93.17 197	96.26 214	98.88 194	89.87 196	99.51 170	94.26 236	94.91 256	99.31 198

tfpn200view9		96.79 147	95.99 163	99.19 55	98.94 133	98.82 37	99.78 160	99.71 7	92.86 208	96.02 221	98.87 199	89.33 203	99.50 172	93.84 243	94.57 260	99.27 205

thres400		96.78 149	95.99 163	99.16 62	98.94 133	98.82 37	99.78 160	99.71 7	92.86 208	96.02 221	98.87 199	89.33 203	99.50 172	93.84 243	94.57 260	99.16 213

sasdasda		97.09 132	96.32 152	99.39 40	98.93 135	98.95 27	99.72 186	97.35 307	94.45 138	97.88 166	99.42 134	86.71 241	99.52 168	98.48 117	93.97 270	99.72 115

Anonymous20231211		89.86 343	88.44 351	94.13 316	98.93 135	90.68 328	98.54 347	98.26 200	76.28 422	86.73 362	95.54 342	70.60 385	97.56 307	90.82 297	80.27 381	94.15 337

canonicalmvs		97.09 132	96.32 152	99.39 40	98.93 135	98.95 27	99.72 186	97.35 307	94.45 138	97.88 166	99.42 134	86.71 241	99.52 168	98.48 117	93.97 270	99.72 115

SDMVSNet		94.80 217	93.96 231	97.33 210	98.92 138	95.42 198	99.59 214	98.99 40	92.41 235	92.55 271	97.85 269	75.81 354	98.93 213	97.90 152	91.62 285	97.64 275

sd_testset		93.55 260	92.83 264	95.74 259	98.92 138	90.89 324	98.24 363	98.85 59	92.41 235	92.55 271	97.85 269	71.07 384	98.68 234	93.93 240	91.62 285	97.64 275

EPNet_dtu		95.71 193	95.39 188	96.66 230	98.92 138	93.41 263	99.57 219	98.90 50	96.19 89	97.52 176	98.56 230	92.65 140	97.36 312	77.89 409	98.33 167	99.20 211
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WTY-MVS		98.10 71	97.60 92	99.60 22	98.92 138	99.28 17	99.89 116	99.52 14	95.58 104	98.24 153	99.39 141	93.33 117	99.74 148	97.98 148	95.58 245	99.78 108

CHOSEN 1792x2688		96.81 146	96.53 145	97.64 186	98.91 142	93.07 268	99.65 201	99.80 3	95.64 102	95.39 234	98.86 201	84.35 272	99.90 105	96.98 180	99.16 137	99.95 76

thres100view900		96.74 152	95.92 173	99.18 56	98.90 143	98.77 42	99.74 175	99.71 7	92.59 226	95.84 225	98.86 201	89.25 205	99.50 172	93.84 243	94.57 260	99.27 205

thres600view7		96.69 155	95.87 176	99.14 66	98.90 143	98.78 41	99.74 175	99.71 7	92.59 226	95.84 225	98.86 201	89.25 205	99.50 172	93.44 256	94.50 263	99.16 213

MSDG		94.37 237	93.36 254	97.40 204	98.88 145	93.95 248	99.37 254	97.38 303	85.75 377	90.80 290	99.17 163	84.11 275	99.88 116	86.35 354	98.43 165	98.36 256

MGCFI-Net		97.00 137	96.22 156	99.34 45	98.86 146	98.80 39	99.67 199	97.30 314	94.31 150	97.77 172	99.41 138	86.36 248	99.50 172	98.38 122	93.90 272	99.72 115

h-mvs33		94.92 214	94.36 219	96.59 232	98.85 147	91.29 316	98.93 312	98.94 44	95.90 94	98.77 119	98.42 243	90.89 181	99.77 142	97.80 156	70.76 420	98.72 245

Anonymous20240529		92.10 294	90.65 306	96.47 234	98.82 148	90.61 330	98.72 334	98.67 80	75.54 426	93.90 255	98.58 228	66.23 402	99.90 105	94.70 226	90.67 288	98.90 235

PVSNet_Blended_VisFu		97.27 121	96.81 132	98.66 106	98.81 149	96.67 142	99.92 92	98.64 84	94.51 136	96.38 212	98.49 236	89.05 209	99.88 116	97.10 176	98.34 166	99.43 179

PS-MVSNAJ		98.44 45	98.20 50	99.16 62	98.80 150	98.92 29	99.54 226	98.17 212	97.34 39	99.85 15	99.85 33	91.20 170	99.89 110	99.41 62	99.67 90	98.69 246

CANet_DTU		96.76 150	96.15 159	98.60 111	98.78 151	97.53 100	99.84 141	97.63 272	97.25 47	99.20 95	99.64 111	81.36 297	99.98 47	92.77 267	98.89 148	98.28 258

mvsany_test1		97.82 89	97.90 76	97.55 192	98.77 152	93.04 271	99.80 157	97.93 240	96.95 58	99.61 64	99.68 105	90.92 178	99.83 132	99.18 70	98.29 171	99.80 104

alignmvs		97.81 90	97.33 107	99.25 49	98.77 152	98.66 51	99.99 5	98.44 141	94.40 146	98.41 142	99.47 130	93.65 110	99.42 182	98.57 111	94.26 266	99.67 123

SymmetryMVS		97.64 104	97.46 98	98.17 146	98.74 154	95.39 201	99.61 210	99.26 29	96.52 73	98.61 130	99.31 148	92.73 138	99.67 160	96.77 187	95.63 243	99.45 175

SteuartSystems-ACMMP		99.02 13	98.97 13	99.18 56	98.72 155	97.71 92	99.98 18	98.44 141	96.85 59	99.80 23	99.91 14	97.57 8	99.85 122	99.44 60	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
xiu_mvs_v2_base		98.23 66	97.97 68	99.02 81	98.69 156	98.66 51	99.52 228	98.08 226	97.05 53	99.86 12	99.86 29	90.65 183	99.71 152	99.39 64	98.63 158	98.69 246

miper_enhance_ethall		94.36 239	93.98 230	95.49 262	98.68 157	95.24 209	99.73 182	97.29 317	93.28 194	89.86 302	95.97 328	94.37 85	97.05 335	92.20 271	84.45 343	94.19 330

fmvsm_s_conf0.5_n_5		98.08 72	97.71 86	99.17 59	98.67 158	97.69 96	99.99 5	98.57 100	97.40 37	99.89 7	99.69 98	85.99 253	99.96 70	99.80 27	99.40 125	99.85 96

ETVMVS		97.03 136	96.64 140	98.20 145	98.67 158	97.12 121	99.89 116	98.57 100	91.10 280	98.17 155	98.59 225	93.86 105	98.19 277	95.64 205	95.24 253	99.28 204

test2506		97.53 108	97.19 114	98.58 115	98.66 160	96.90 132	98.81 327	99.77 5	94.93 118	97.95 161	98.96 182	92.51 147	99.20 193	94.93 216	98.15 175	99.64 129

ECVR-MVS		95.66 196	95.05 203	97.51 196	98.66 160	93.71 253	98.85 324	98.45 136	94.93 118	96.86 197	98.96 182	75.22 360	99.20 193	95.34 207	98.15 175	99.64 129

mamv4		95.24 207	96.90 125	90.25 387	98.65 162	72.11 434	98.28 361	97.64 271	89.99 310	95.93 223	98.25 253	94.74 70	99.11 199	99.01 83	99.64 92	99.53 161

balanced_conf03		98.27 59	97.99 66	99.11 71	98.64 163	98.43 62	99.47 238	97.79 255	94.56 134	99.74 40	98.35 245	94.33 88	99.25 187	99.12 72	99.96 46	99.64 129

fmvsm_s_conf0.5_n_a		97.73 99	97.72 84	97.77 178	98.63 164	94.26 239	99.96 46	98.92 49	97.18 49	99.75 37	99.69 98	87.00 239	99.97 58	99.46 58	98.89 148	99.08 222

MVSMamba_PlusPlus		97.83 86	97.45 100	98.99 83	98.60 165	98.15 66	99.58 216	97.74 262	90.34 302	99.26 94	98.32 248	94.29 90	99.23 188	99.03 81	99.89 70	99.58 149

testing222		97.08 135	96.75 135	98.06 156	98.56 166	96.82 134	99.85 136	98.61 92	92.53 230	98.84 114	98.84 205	93.36 115	98.30 267	95.84 201	94.30 265	99.05 226

test1111		95.57 198	94.98 206	97.37 206	98.56 166	93.37 265	98.86 322	98.45 136	94.95 117	96.63 203	98.95 187	75.21 361	99.11 199	95.02 213	98.14 177	99.64 129

MVSTER		95.53 199	95.22 195	96.45 236	98.56 166	97.72 91	99.91 100	97.67 267	92.38 237	91.39 281	97.14 285	97.24 18	97.30 319	94.80 222	87.85 317	94.34 319

testing3-2		97.72 100	97.43 103	98.60 111	98.55 169	97.11 123	100.00 1	99.23 31	93.78 177	97.90 163	98.73 211	95.50 49	99.69 156	98.53 115	94.63 258	98.99 230

VDD-MVS		93.77 253	92.94 262	96.27 243	98.55 169	90.22 339	98.77 331	97.79 255	90.85 286	96.82 199	99.42 134	61.18 422	99.77 142	98.95 84	94.13 267	98.82 238

tpmvs		94.28 241	93.57 241	96.40 238	98.55 169	91.50 314	95.70 420	98.55 112	87.47 352	92.15 274	94.26 393	91.42 166	98.95 212	88.15 333	95.85 234	98.76 241

UGNet		95.33 205	94.57 215	97.62 189	98.55 169	94.85 221	98.67 340	99.32 26	95.75 99	96.80 200	96.27 317	72.18 376	99.96 70	94.58 229	99.05 144	98.04 264
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
PCF-MVS	94.20 5	95.18 208	94.10 226	98.43 132	98.55 169	95.99 174	97.91 376	97.31 313	90.35 301	89.48 315	99.22 159	85.19 262	99.89 110	90.40 307	98.47 164	99.41 181
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS-28		95.95 184	96.49 146	94.34 310	98.51 174	89.99 344	99.39 250	98.57 100	93.14 199	97.33 183	98.31 250	93.44 113	94.68 410	93.69 253	95.98 228	98.34 257

UWE-MVS		96.79 147	96.72 137	97.00 217	98.51 174	93.70 254	99.71 189	98.60 94	92.96 204	97.09 190	98.34 247	96.67 31	98.85 216	92.11 275	96.50 215	98.44 252

myMVS_eth3d28		97.86 82	97.59 94	98.68 103	98.50 176	97.26 113	99.92 92	98.55 112	93.79 176	98.26 151	98.75 209	95.20 54	99.48 178	98.93 86	96.40 218	99.29 202

test_vis1_n_1920		95.44 201	95.31 191	95.82 256	98.50 176	88.74 360	99.98 18	97.30 314	97.84 25	99.85 15	99.19 161	66.82 400	99.97 58	98.82 95	99.46 119	98.76 241

BH-w/o		95.71 193	95.38 189	96.68 229	98.49 178	92.28 289	99.84 141	97.50 292	92.12 245	92.06 277	98.79 207	84.69 268	98.67 235	95.29 209	99.66 91	99.09 220

baseline1		95.78 189	94.86 208	98.54 121	98.47 179	98.07 74	99.06 291	97.99 233	92.68 220	94.13 252	98.62 224	93.28 121	98.69 233	93.79 248	85.76 330	98.84 237

fmvsm_s_conf0.5_n_7		97.70 102	97.74 83	97.59 191	98.44 180	95.16 215	99.97 36	98.65 81	97.95 21	99.62 57	99.78 62	86.09 251	99.94 87	99.69 44	99.50 112	97.66 274

EPMVS		96.53 163	96.01 162	98.09 154	98.43 181	96.12 172	96.36 407	99.43 20	93.53 184	97.64 174	95.04 370	94.41 80	98.38 259	91.13 288	98.11 178	99.75 111

kuosan		93.17 268	92.60 270	94.86 286	98.40 182	89.54 352	98.44 352	98.53 119	84.46 390	88.49 336	97.92 266	90.57 185	97.05 335	83.10 379	93.49 275	97.99 265

WBMVS		94.52 230	94.03 228	95.98 249	98.38 183	96.68 141	99.92 92	97.63 272	90.75 294	89.64 310	95.25 363	96.77 25	96.90 347	94.35 234	83.57 350	94.35 317

UBG		97.84 85	97.69 87	98.29 141	98.38 183	96.59 148	99.90 106	98.53 119	93.91 172	98.52 134	98.42 243	96.77 25	99.17 196	98.54 113	96.20 222	99.11 219

sss		97.57 107	97.03 121	99.18 56	98.37 185	98.04 77	99.73 182	99.38 22	93.46 187	98.76 122	99.06 169	91.21 169	99.89 110	96.33 192	97.01 207	99.62 136

testing11		97.48 110	97.27 110	98.10 153	98.36 186	96.02 173	99.92 92	98.45 136	93.45 189	98.15 156	98.70 214	95.48 50	99.22 189	97.85 154	95.05 255	99.07 223

BH-untuned		95.18 208	94.83 209	96.22 244	98.36 186	91.22 317	99.80 157	97.32 312	90.91 284	91.08 284	98.67 216	83.51 277	98.54 242	94.23 237	99.61 99	98.92 232

testing91		97.16 127	96.90 125	97.97 160	98.35 188	95.67 189	99.91 100	98.42 161	92.91 207	97.33 183	98.72 212	94.81 68	99.21 190	96.98 180	94.63 258	99.03 227

testing99		97.17 126	96.91 124	97.95 161	98.35 188	95.70 186	99.91 100	98.43 149	92.94 205	97.36 182	98.72 212	94.83 67	99.21 190	97.00 178	94.64 257	98.95 231

ET-MVSNet_ETH3D		94.37 237	93.28 256	97.64 186	98.30 190	97.99 79	99.99 5	97.61 278	94.35 147	71.57 432	99.45 133	96.23 35	95.34 400	96.91 185	85.14 337	99.59 143

AUN-MVS		93.28 265	92.60 270	95.34 269	98.29 191	90.09 342	99.31 262	98.56 106	91.80 258	96.35 213	98.00 261	89.38 202	98.28 270	92.46 268	69.22 425	97.64 275

FMVSNet3		92.69 281	91.58 291	95.99 248	98.29 191	97.42 108	99.26 271	97.62 275	89.80 313	89.68 306	95.32 357	81.62 295	96.27 377	87.01 350	85.65 331	94.29 321

PMMVS		96.76 150	96.76 134	96.76 226	98.28 193	92.10 293	99.91 100	97.98 235	94.12 158	99.53 69	99.39 141	86.93 240	98.73 227	96.95 183	97.73 186	99.45 175

hse-mvs2		94.38 236	94.08 227	95.31 271	98.27 194	90.02 343	99.29 267	98.56 106	95.90 94	98.77 119	98.00 261	90.89 181	98.26 274	97.80 156	69.20 426	97.64 275

PVSNet_0	88.03 19	91.80 301	90.27 315	96.38 240	98.27 194	90.46 334	99.94 82	99.61 13	93.99 166	86.26 372	97.39 280	71.13 383	99.89 110	98.77 99	67.05 431	98.79 240

UA-Net		96.54 162	95.96 169	98.27 142	98.23 196	95.71 185	98.00 374	98.45 136	93.72 181	98.41 142	99.27 153	88.71 215	99.66 163	91.19 287	97.69 187	99.44 178

test_cas_vis1_n_1920		96.59 160	96.23 155	97.65 185	98.22 197	94.23 240	99.99 5	97.25 321	97.77 26	99.58 65	99.08 167	77.10 336	99.97 58	97.64 164	99.45 120	98.74 243

FE-MVS		95.70 195	95.01 205	97.79 175	98.21 198	94.57 228	95.03 421	98.69 75	88.90 329	97.50 178	96.19 319	92.60 143	99.49 177	89.99 312	97.94 184	99.31 198

GG-mvs-BLEND				98.54 121	98.21 198	98.01 78	93.87 426	98.52 121		97.92 162	97.92 266	99.02 3	97.94 294	98.17 134	99.58 103	99.67 123

mvs_anonymous		95.65 197	95.03 204	97.53 194	98.19 200	95.74 183	99.33 259	97.49 293	90.87 285	90.47 293	97.10 287	88.23 218	97.16 326	95.92 199	97.66 190	99.68 121

MVS_Test		96.46 165	95.74 178	98.61 110	98.18 201	97.23 115	99.31 262	97.15 332	91.07 281	98.84 114	97.05 291	88.17 219	98.97 209	94.39 231	97.50 192	99.61 140

BH-RMVSNet		95.18 208	94.31 222	97.80 173	98.17 202	95.23 210	99.76 168	97.53 288	92.52 231	94.27 250	99.25 157	76.84 341	98.80 219	90.89 296	99.54 105	99.35 191

dongtai		91.55 307	91.13 300	92.82 355	98.16 203	86.35 383	99.47 238	98.51 124	83.24 398	85.07 382	97.56 274	90.33 190	94.94 406	76.09 417	91.73 283	97.18 286

RPSCF		91.80 301	92.79 266	88.83 398	98.15 204	69.87 436	98.11 370	96.60 382	83.93 393	94.33 248	99.27 153	79.60 319	99.46 181	91.99 276	93.16 280	97.18 286

ETV-MVS		97.92 78	97.80 82	98.25 143	98.14 205	96.48 150	99.98 18	97.63 272	95.61 103	99.29 92	99.46 132	92.55 145	98.82 217	99.02 82	98.54 162	99.46 173

IS-MVSNet		96.29 175	95.90 174	97.45 199	98.13 206	94.80 224	99.08 286	97.61 278	92.02 250	95.54 232	98.96 182	90.64 184	98.08 283	93.73 251	97.41 196	99.47 172

test_fmvsmconf_n		98.43 47	98.32 44	98.78 96	98.12 207	96.41 153	99.99 5	98.83 63	98.22 7	99.67 48	99.64 111	91.11 174	99.94 87	99.67 46	99.62 95	99.98 51

fmvsm_s_conf0.1_n_2		97.25 122	96.85 129	98.43 132	98.08 208	98.08 73	99.92 92	97.76 261	98.05 17	99.65 50	99.58 120	80.88 304	99.93 96	99.59 50	98.17 173	97.29 284

ab-mvs		94.69 222	93.42 247	98.51 126	98.07 209	96.26 160	96.49 405	98.68 77	90.31 303	94.54 243	97.00 293	76.30 349	99.71 152	95.98 198	93.38 278	99.56 152

XVG-OURS-SEG-HR		94.79 218	94.70 214	95.08 276	98.05 210	89.19 354	99.08 286	97.54 286	93.66 182	94.87 241	99.58 120	78.78 327	99.79 137	97.31 170	93.40 277	96.25 293

EIA-MVS		97.53 108	97.46 98	97.76 180	98.04 211	94.84 222	99.98 18	97.61 278	94.41 145	97.90 163	99.59 117	92.40 151	98.87 214	98.04 143	99.13 139	99.59 143

XVG-OURS		94.82 215	94.74 213	95.06 277	98.00 212	89.19 354	99.08 286	97.55 284	94.10 159	94.71 242	99.62 115	80.51 310	99.74 148	96.04 197	93.06 282	96.25 293

mvsmamba		96.94 140	96.73 136	97.55 192	97.99 213	94.37 236	99.62 208	97.70 264	93.13 200	98.42 141	97.92 266	88.02 220	98.75 226	98.78 98	99.01 145	99.52 163

dp		95.05 211	94.43 217	96.91 220	97.99 213	92.73 278	96.29 410	97.98 235	89.70 314	95.93 223	94.67 383	93.83 107	98.45 248	86.91 353	96.53 214	99.54 157

tpmrst		96.27 177	95.98 165	97.13 214	97.96 215	93.15 267	96.34 408	98.17 212	92.07 246	98.71 125	95.12 367	93.91 102	98.73 227	94.91 219	96.62 212	99.50 169

TR-MVS		94.54 227	93.56 242	97.49 198	97.96 215	94.34 237	98.71 335	97.51 291	90.30 304	94.51 245	98.69 215	75.56 355	98.77 223	92.82 266	95.99 227	99.35 191

Vis-MVSNet (Re-imp)		96.32 172	95.98 165	97.35 209	97.93 217	94.82 223	99.47 238	98.15 220	91.83 255	95.09 239	99.11 165	91.37 168	97.47 310	93.47 255	97.43 193	99.74 112

MDTV_nov1_ep13			95.69 180		97.90 218	94.15 242	95.98 416	98.44 141	93.12 201	97.98 160	95.74 332	95.10 57	98.58 239	90.02 311	96.92 209

Fast-Effi-MVS+		95.02 212	94.19 224	97.52 195	97.88 219	94.55 229	99.97 36	97.08 343	88.85 331	94.47 246	97.96 265	84.59 269	98.41 251	89.84 314	97.10 202	99.59 143

ADS-MVSNet2		93.80 252	93.88 234	93.55 338	97.87 220	85.94 387	94.24 422	96.84 368	90.07 307	96.43 209	94.48 388	90.29 192	95.37 399	87.44 340	97.23 199	99.36 187

ADS-MVSNet		94.79 218	94.02 229	97.11 216	97.87 220	93.79 250	94.24 422	98.16 217	90.07 307	96.43 209	94.48 388	90.29 192	98.19 277	87.44 340	97.23 199	99.36 187

Effi-MVS+		96.30 174	95.69 180	98.16 147	97.85 222	96.26 160	97.41 385	97.21 324	90.37 300	98.65 128	98.58 228	86.61 245	98.70 232	97.11 175	97.37 197	99.52 163

PatchmatchNet		95.94 185	95.45 186	97.39 205	97.83 223	94.41 233	96.05 414	98.40 170	92.86 208	97.09 190	95.28 362	94.21 94	98.07 285	89.26 320	98.11 178	99.70 118
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
cascas		94.64 225	93.61 237	97.74 182	97.82 224	96.26 160	99.96 46	97.78 257	85.76 375	94.00 253	97.54 275	76.95 340	99.21 190	97.23 172	95.43 248	97.76 273

1112_ss		96.01 183	95.20 196	98.42 134	97.80 225	96.41 153	99.65 201	96.66 379	92.71 217	92.88 267	99.40 139	92.16 156	99.30 185	91.92 278	93.66 273	99.55 153

Test_1112_low_res		95.72 191	94.83 209	98.42 134	97.79 226	96.41 153	99.65 201	96.65 380	92.70 218	92.86 268	96.13 323	92.15 157	99.30 185	91.88 279	93.64 274	99.55 153

Effi-MVS+-dtu		94.53 229	95.30 192	92.22 363	97.77 227	82.54 409	99.59 214	97.06 345	94.92 120	95.29 236	95.37 355	85.81 254	97.89 295	94.80 222	97.07 203	96.23 295

tpm cat1		93.51 261	92.52 276	96.47 234	97.77 227	91.47 315	96.13 412	98.06 227	80.98 411	92.91 266	93.78 397	89.66 197	98.87 214	87.03 349	96.39 219	99.09 220

FA-MVS(test-final)		95.86 186	95.09 201	98.15 150	97.74 229	95.62 191	96.31 409	98.17 212	91.42 271	96.26 214	96.13 323	90.56 186	99.47 180	92.18 272	97.07 203	99.35 191

xiu_mvs_v1_base_debu		97.43 111	97.06 117	98.55 117	97.74 229	98.14 68	99.31 262	97.86 249	96.43 78	99.62 57	99.69 98	85.56 257	99.68 157	99.05 75	98.31 168	97.83 269

xiu_mvs_v1_base		97.43 111	97.06 117	98.55 117	97.74 229	98.14 68	99.31 262	97.86 249	96.43 78	99.62 57	99.69 98	85.56 257	99.68 157	99.05 75	98.31 168	97.83 269

xiu_mvs_v1_base_debi		97.43 111	97.06 117	98.55 117	97.74 229	98.14 68	99.31 262	97.86 249	96.43 78	99.62 57	99.69 98	85.56 257	99.68 157	99.05 75	98.31 168	97.83 269

EPP-MVSNet		96.69 155	96.60 142	96.96 219	97.74 229	93.05 270	99.37 254	98.56 106	88.75 333	95.83 227	99.01 173	96.01 36	98.56 240	96.92 184	97.20 201	99.25 207

gg-mvs-nofinetune		93.51 261	91.86 288	98.47 128	97.72 234	97.96 83	92.62 430	98.51 124	74.70 429	97.33 183	69.59 446	98.91 4	97.79 298	97.77 161	99.56 104	99.67 123

IB-MVS	92.85 6	94.99 213	93.94 232	98.16 147	97.72 234	95.69 188	99.99 5	98.81 64	94.28 153	92.70 269	96.90 295	95.08 58	99.17 196	96.07 196	73.88 413	99.60 142
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
thisisatest0515		97.41 116	97.02 122	98.59 114	97.71 236	97.52 101	99.97 36	98.54 116	91.83 255	97.45 179	99.04 170	97.50 9	99.10 201	94.75 224	96.37 220	99.16 213

VortexMVS		94.11 243	93.50 244	95.94 251	97.70 237	96.61 145	99.35 257	97.18 327	93.52 186	89.57 313	95.74 332	87.55 227	96.97 343	95.76 204	85.13 338	94.23 326

Syy-MVS		90.00 341	90.63 307	88.11 405	97.68 238	74.66 432	99.71 189	98.35 183	90.79 291	92.10 275	98.67 216	79.10 325	93.09 425	63.35 439	95.95 231	96.59 291

myMVS_eth3d		94.46 234	94.76 212	93.55 338	97.68 238	90.97 319	99.71 189	98.35 183	90.79 291	92.10 275	98.67 216	92.46 150	93.09 425	87.13 346	95.95 231	96.59 291

test_fmvs1_n		94.25 242	94.36 219	93.92 325	97.68 238	83.70 400	99.90 106	96.57 383	97.40 37	99.67 48	98.88 194	61.82 419	99.92 102	98.23 132	99.13 139	98.14 262

fmvsm_s_conf0.5_n_6		98.27 59	97.96 71	99.23 51	97.66 241	98.11 72	99.98 18	98.64 84	97.85 24	99.87 10	99.72 88	88.86 212	99.93 96	99.64 48	99.36 128	99.63 135

RRT-MVS		96.24 178	95.68 182	97.94 164	97.65 242	94.92 220	99.27 270	97.10 339	92.79 214	97.43 180	97.99 263	81.85 290	99.37 184	98.46 119	98.57 159	99.53 161

diffmvs		97.00 137	96.64 140	98.09 154	97.64 243	96.17 169	99.81 153	97.19 325	94.67 132	98.95 109	99.28 150	86.43 246	98.76 224	98.37 124	97.42 195	99.33 194
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		95.72 191	95.15 199	97.45 199	97.62 244	94.28 238	99.28 268	98.24 203	94.27 155	96.84 198	98.94 189	79.39 320	98.76 224	93.25 257	98.49 163	99.30 200
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
thisisatest0530		97.10 130	96.72 137	98.22 144	97.60 245	96.70 138	99.92 92	98.54 116	91.11 279	97.07 192	98.97 180	97.47 12	99.03 204	93.73 251	96.09 225	98.92 232

GDP-MVS		97.88 80	97.59 94	98.75 99	97.59 246	97.81 89	99.95 65	97.37 306	94.44 141	99.08 103	99.58 120	97.13 23	99.08 202	94.99 214	98.17 173	99.37 185

miper_ehance_all_eth		93.16 269	92.60 270	94.82 287	97.57 247	93.56 258	99.50 232	97.07 344	88.75 333	88.85 330	95.52 344	90.97 177	96.74 357	90.77 298	84.45 343	94.17 331

guyue		97.15 128	96.82 131	98.15 150	97.56 248	96.25 164	99.71 189	97.84 252	95.75 99	98.13 157	98.65 219	87.58 226	98.82 217	98.29 129	97.91 185	99.36 187

testing3		93.92 246	94.23 223	92.99 352	97.54 249	90.23 338	99.99 5	99.16 33	90.57 296	91.33 283	98.63 223	92.99 129	92.52 429	82.46 383	95.39 249	96.22 296

mamba_0404		95.75 190	95.16 198	97.50 197	97.53 250	95.39 201	99.11 282	97.25 321	90.81 288	95.27 237	98.83 206	84.74 266	98.67 235	95.24 210	97.69 187	98.45 251

LCM-MVSNet-Re		92.31 290	92.60 270	91.43 372	97.53 250	79.27 426	99.02 300	91.83 442	92.07 246	80.31 406	94.38 391	83.50 278	95.48 396	97.22 173	97.58 191	99.54 157

GBi-Net		90.88 318	89.82 324	94.08 317	97.53 250	91.97 294	98.43 353	96.95 357	87.05 358	89.68 306	94.72 379	71.34 380	96.11 382	87.01 350	85.65 331	94.17 331

test1		90.88 318	89.82 324	94.08 317	97.53 250	91.97 294	98.43 353	96.95 357	87.05 358	89.68 306	94.72 379	71.34 380	96.11 382	87.01 350	85.65 331	94.17 331

FMVSNet2		91.02 315	89.56 329	95.41 267	97.53 250	95.74 183	98.98 302	97.41 301	87.05 358	88.43 340	95.00 373	71.34 380	96.24 379	85.12 365	85.21 336	94.25 324

tttt0517		96.85 144	96.49 146	97.92 165	97.48 255	95.89 177	99.85 136	98.54 116	90.72 295	96.63 203	98.93 192	97.47 12	99.02 205	93.03 264	95.76 237	98.85 236

BP-MVS1		98.33 55	98.18 52	98.81 94	97.44 256	97.98 80	99.96 46	98.17 212	94.88 122	98.77 119	99.59 117	97.59 7	99.08 202	98.24 131	98.93 147	99.36 187

casdiffmvs_mvg		96.43 166	95.94 171	97.89 169	97.44 256	95.47 195	99.86 133	97.29 317	93.35 190	96.03 220	99.19 161	85.39 260	98.72 229	97.89 153	97.04 205	99.49 171
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EC-MVSNet		97.38 118	97.24 111	97.80 173	97.41 258	95.64 190	99.99 5	97.06 345	94.59 133	99.63 54	99.32 146	89.20 208	98.14 279	98.76 100	99.23 135	99.62 136

c3_l		92.53 285	91.87 287	94.52 299	97.40 259	92.99 272	99.40 246	96.93 362	87.86 348	88.69 333	95.44 349	89.95 195	96.44 369	90.45 304	80.69 377	94.14 340

fmvsm_s_conf0.1_n		97.30 119	97.21 113	97.60 190	97.38 260	94.40 235	99.90 106	98.64 84	96.47 77	99.51 73	99.65 110	84.99 265	99.93 96	99.22 69	99.09 142	98.46 250

CDS-MVSNet		96.34 171	96.07 160	97.13 214	97.37 261	94.96 218	99.53 227	97.91 244	91.55 263	95.37 235	98.32 248	95.05 60	97.13 329	93.80 247	95.75 238	99.30 200
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TESTMET0.1,1		96.74 152	96.26 154	98.16 147	97.36 262	96.48 150	99.96 46	98.29 196	91.93 251	95.77 228	98.07 259	95.54 46	98.29 268	90.55 302	98.89 148	99.70 118

miper_lstm_enhance		91.81 298	91.39 297	93.06 351	97.34 263	89.18 356	99.38 252	96.79 373	86.70 365	87.47 354	95.22 364	90.00 194	95.86 391	88.26 331	81.37 366	94.15 337

baseline		96.43 166	95.98 165	97.76 180	97.34 263	95.17 214	99.51 230	97.17 329	93.92 171	96.90 196	99.28 150	85.37 261	98.64 237	97.50 167	96.86 211	99.46 173

cl____		92.31 290	91.58 291	94.52 299	97.33 265	92.77 274	99.57 219	96.78 374	86.97 362	87.56 352	95.51 345	89.43 201	96.62 362	88.60 325	82.44 358	94.16 336

SD_0403		92.63 284	93.38 251	90.40 386	97.32 266	77.91 428	97.75 381	98.03 231	91.89 252	90.83 289	98.29 252	82.00 287	93.79 419	88.51 329	95.75 238	99.52 163

DIV-MVS_self_test		92.32 289	91.60 290	94.47 303	97.31 267	92.74 276	99.58 216	96.75 375	86.99 361	87.64 350	95.54 342	89.55 200	96.50 366	88.58 326	82.44 358	94.17 331

casdiffmvs		96.42 168	95.97 168	97.77 178	97.30 268	94.98 217	99.84 141	97.09 342	93.75 180	96.58 205	99.26 156	85.07 263	98.78 222	97.77 161	97.04 205	99.54 157
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GeoE		94.36 239	93.48 245	96.99 218	97.29 269	93.54 259	99.96 46	96.72 377	88.35 342	93.43 257	98.94 189	82.05 286	98.05 286	88.12 335	96.48 217	99.37 185

eth_miper_zixun_eth		92.41 288	91.93 285	93.84 329	97.28 270	90.68 328	98.83 325	96.97 356	88.57 338	89.19 325	95.73 335	89.24 207	96.69 360	89.97 313	81.55 364	94.15 337

MVSFormer		96.94 140	96.60 142	97.95 161	97.28 270	97.70 94	99.55 224	97.27 319	91.17 276	99.43 79	99.54 126	90.92 178	96.89 348	94.67 227	99.62 95	99.25 207

lupinMVS		97.85 84	97.60 92	98.62 109	97.28 270	97.70 94	99.99 5	97.55 284	95.50 108	99.43 79	99.67 106	90.92 178	98.71 230	98.40 121	99.62 95	99.45 175

SCA		94.69 222	93.81 236	97.33 210	97.10 273	94.44 230	98.86 322	98.32 190	93.30 193	96.17 219	95.59 340	76.48 347	97.95 292	91.06 290	97.43 193	99.59 143

KinetiMVS		96.10 179	95.29 193	98.53 123	97.08 274	97.12 121	99.56 221	98.12 223	94.78 125	98.44 139	98.94 189	80.30 314	99.39 183	91.56 283	98.79 154	99.06 224

TAMVS		95.85 187	95.58 184	96.65 231	97.07 275	93.50 260	99.17 278	97.82 254	91.39 273	95.02 240	98.01 260	92.20 155	97.30 319	93.75 250	95.83 235	99.14 216

Fast-Effi-MVS+-dtu		93.72 256	93.86 235	93.29 343	97.06 276	86.16 384	99.80 157	96.83 369	92.66 221	92.58 270	97.83 271	81.39 296	97.67 303	89.75 315	96.87 210	96.05 298

CostFormer		96.10 179	95.88 175	96.78 225	97.03 277	92.55 284	97.08 394	97.83 253	90.04 309	98.72 124	94.89 377	95.01 62	98.29 268	96.54 191	95.77 236	99.50 169

test_fmvsmvis_n_1920		97.67 103	97.59 94	97.91 167	97.02 278	95.34 204	99.95 65	98.45 136	97.87 23	97.02 193	99.59 117	89.64 198	99.98 47	99.41 62	99.34 130	98.42 253

test-LLR		96.47 164	96.04 161	97.78 176	97.02 278	95.44 196	99.96 46	98.21 207	94.07 161	95.55 230	96.38 312	93.90 103	98.27 272	90.42 305	98.83 152	99.64 129

test-mter		96.39 169	95.93 172	97.78 176	97.02 278	95.44 196	99.96 46	98.21 207	91.81 257	95.55 230	96.38 312	95.17 55	98.27 272	90.42 305	98.83 152	99.64 129

ICG_test_0404		93.83 248	93.17 258	95.80 257	96.97 281	91.64 309	97.78 380	97.12 335	92.33 239	90.87 288	98.88 194	76.78 342	96.43 370	92.12 273	95.70 241	99.32 196

icg_test_0403		95.25 206	94.81 211	96.58 233	96.97 281	91.64 309	98.97 307	97.12 335	92.33 239	95.43 233	98.88 194	85.78 255	98.79 220	92.12 273	95.70 241	99.32 196

gm-plane-assit					96.97 281	93.76 252			91.47 267		98.96 182		98.79 220	94.92 217

WB-MVSnew		92.90 275	92.77 267	93.26 345	96.95 284	93.63 256	99.71 189	98.16 217	91.49 264	94.28 249	98.14 256	81.33 298	96.48 367	79.47 400	95.46 246	89.68 426

QAPM		95.40 202	94.17 225	99.10 72	96.92 285	97.71 92	99.40 246	98.68 77	89.31 317	88.94 329	98.89 193	82.48 284	99.96 70	93.12 263	99.83 77	99.62 136

KD-MVS_2432*1600		88.00 363	86.10 367	93.70 334	96.91 286	94.04 244	97.17 391	97.12 335	84.93 385	81.96 396	92.41 410	92.48 148	94.51 412	79.23 401	52.68 445	92.56 396

miper_refine_blended		88.00 363	86.10 367	93.70 334	96.91 286	94.04 244	97.17 391	97.12 335	84.93 385	81.96 396	92.41 410	92.48 148	94.51 412	79.23 401	52.68 445	92.56 396

tpm2		95.47 200	95.18 197	96.35 241	96.91 286	91.70 307	96.96 397	97.93 240	88.04 346	98.44 139	95.40 351	93.32 118	97.97 289	94.00 239	95.61 244	99.38 183

FMVSNet5		88.32 359	87.47 361	90.88 375	96.90 289	88.39 368	97.28 388	95.68 404	82.60 405	84.67 384	92.40 412	79.83 317	91.16 434	76.39 416	81.51 365	93.09 387

3Dnovator+	91.53 11	96.31 173	95.24 194	99.52 28	96.88 290	98.64 54	99.72 186	98.24 203	95.27 113	88.42 342	98.98 178	82.76 283	99.94 87	97.10 176	99.83 77	99.96 69

Patchmatch-test		92.65 283	91.50 294	96.10 247	96.85 291	90.49 333	91.50 435	97.19 325	82.76 404	90.23 294	95.59 340	95.02 61	98.00 288	77.41 411	96.98 208	99.82 100

MVS		96.60 159	95.56 185	99.72 13	96.85 291	99.22 20	98.31 359	98.94 44	91.57 262	90.90 287	99.61 116	86.66 244	99.96 70	97.36 169	99.88 73	99.99 23

3Dnovator	91.47 12	96.28 176	95.34 190	99.08 75	96.82 293	97.47 106	99.45 243	98.81 64	95.52 107	89.39 316	99.00 175	81.97 288	99.95 79	97.27 171	99.83 77	99.84 97

EI-MVSNet		93.73 255	93.40 250	94.74 288	96.80 294	92.69 279	99.06 291	97.67 267	88.96 326	91.39 281	99.02 171	88.75 214	97.30 319	91.07 289	87.85 317	94.22 327

CVMVSNet		94.68 224	94.94 207	93.89 328	96.80 294	86.92 381	99.06 291	98.98 41	94.45 138	94.23 251	99.02 171	85.60 256	95.31 401	90.91 295	95.39 249	99.43 179

IterMVS-LS		92.69 281	92.11 281	94.43 307	96.80 294	92.74 276	99.45 243	96.89 365	88.98 324	89.65 309	95.38 354	88.77 213	96.34 374	90.98 293	82.04 361	94.22 327
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
AstraMVS		96.57 161	96.46 149	96.91 220	96.79 297	92.50 285	99.90 106	97.38 303	96.02 93	97.79 171	99.32 146	86.36 248	98.99 206	98.26 130	96.33 221	99.23 210

IterMVS		90.91 317	90.17 319	93.12 348	96.78 298	90.42 336	98.89 316	97.05 348	89.03 321	86.49 367	95.42 350	76.59 345	95.02 403	87.22 345	84.09 346	93.93 358
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
1314		96.84 145	95.96 169	99.48 34	96.74 299	98.52 58	98.31 359	98.86 56	95.82 96	89.91 300	98.98 178	87.49 229	99.96 70	97.80 156	99.73 87	99.96 69

IterMVS-SCA-FT		90.85 320	90.16 320	92.93 353	96.72 300	89.96 345	98.89 316	96.99 352	88.95 327	86.63 364	95.67 336	76.48 347	95.00 404	87.04 348	84.04 349	93.84 365

MVS-HIRNet		86.22 370	83.19 383	95.31 271	96.71 301	90.29 337	92.12 432	97.33 311	62.85 440	86.82 361	70.37 445	69.37 388	97.49 309	75.12 419	97.99 183	98.15 260

VDDNet		93.12 270	91.91 286	96.76 226	96.67 302	92.65 282	98.69 338	98.21 207	82.81 403	97.75 173	99.28 150	61.57 420	99.48 178	98.09 140	94.09 268	98.15 260

dmvs_re		93.20 267	93.15 259	93.34 341	96.54 303	83.81 399	98.71 335	98.51 124	91.39 273	92.37 273	98.56 230	78.66 329	97.83 297	93.89 241	89.74 289	98.38 255

Elysia		94.50 231	93.38 251	97.85 171	96.49 304	96.70 138	98.98 302	97.78 257	90.81 288	96.19 217	98.55 232	73.63 371	98.98 207	89.41 316	98.56 160	97.88 267

StellarMVS		94.50 231	93.38 251	97.85 171	96.49 304	96.70 138	98.98 302	97.78 257	90.81 288	96.19 217	98.55 232	73.63 371	98.98 207	89.41 316	98.56 160	97.88 267

MIMVSNet		90.30 333	88.67 347	95.17 275	96.45 306	91.64 309	92.39 431	97.15 332	85.99 372	90.50 292	93.19 405	66.95 399	94.86 408	82.01 387	93.43 276	99.01 229

CR-MVSNet		93.45 264	92.62 269	95.94 251	96.29 307	92.66 280	92.01 433	96.23 391	92.62 223	96.94 194	93.31 403	91.04 175	96.03 387	79.23 401	95.96 229	99.13 217

RPMNet		89.76 345	87.28 362	97.19 213	96.29 307	92.66 280	92.01 433	98.31 192	70.19 436	96.94 194	85.87 438	87.25 234	99.78 139	62.69 440	95.96 229	99.13 217

tt0805		91.28 310	90.18 318	94.60 294	96.26 309	87.55 374	98.39 357	98.72 72	89.00 323	89.22 322	98.47 240	62.98 415	98.96 211	90.57 301	88.00 316	97.28 285

Patchmtry		89.70 346	88.49 350	93.33 342	96.24 310	89.94 348	91.37 436	96.23 391	78.22 419	87.69 349	93.31 403	91.04 175	96.03 387	80.18 399	82.10 360	94.02 348

test_vis1_rt		86.87 368	86.05 370	89.34 394	96.12 311	78.07 427	99.87 122	83.54 453	92.03 249	78.21 417	89.51 424	45.80 439	99.91 103	96.25 194	93.11 281	90.03 423

JIA-IIPM		91.76 304	90.70 305	94.94 281	96.11 312	87.51 375	93.16 429	98.13 222	75.79 425	97.58 175	77.68 443	92.84 134	97.97 289	88.47 330	96.54 213	99.33 194

OpenMVS	90.15 15	94.77 220	93.59 240	98.33 138	96.07 313	97.48 105	99.56 221	98.57 100	90.46 298	86.51 366	98.95 187	78.57 330	99.94 87	93.86 242	99.74 86	97.57 280

PAPM		98.60 34	98.42 35	99.14 66	96.05 314	98.96 26	99.90 106	99.35 24	96.68 68	98.35 146	99.66 108	96.45 33	98.51 243	99.45 59	99.89 70	99.96 69

CLD-MVS		94.06 245	93.90 233	94.55 298	96.02 315	90.69 327	99.98 18	97.72 263	96.62 72	91.05 286	98.85 204	77.21 335	98.47 244	98.11 138	89.51 295	94.48 305
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PatchT		90.38 330	88.75 346	95.25 273	95.99 316	90.16 340	91.22 437	97.54 286	76.80 421	97.26 186	86.01 437	91.88 162	96.07 386	66.16 436	95.91 233	99.51 167

ACMH+	89.98 16	90.35 331	89.54 330	92.78 357	95.99 316	86.12 385	98.81 327	97.18 327	89.38 316	83.14 392	97.76 272	68.42 393	98.43 249	89.11 321	86.05 329	93.78 368

DeepMVS_CX				82.92 415	95.98 318	58.66 446		96.01 396	92.72 216	78.34 416	95.51 345	58.29 425	98.08 283	82.57 382	85.29 334	92.03 404

ACMP	92.05 9	92.74 279	92.42 278	93.73 330	95.91 319	88.72 361	99.81 153	97.53 288	94.13 157	87.00 360	98.23 254	74.07 368	98.47 244	96.22 195	88.86 302	93.99 353
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n		93.61 259	93.03 261	95.35 268	95.86 320	86.94 380	99.87 122	96.36 389	96.85 59	99.54 68	98.79 207	52.41 433	99.83 132	98.64 108	98.97 146	99.29 202

HQP-NCC					95.78 321		99.87 122		96.82 61	93.37 258

ACMP_Plane					95.78 321		99.87 122		96.82 61	93.37 258

HQP-MVS		94.61 226	94.50 216	94.92 282	95.78 321	91.85 299	99.87 122	97.89 245	96.82 61	93.37 258	98.65 219	80.65 308	98.39 255	97.92 150	89.60 290	94.53 301

NP-MVS					95.77 324	91.79 301					98.65 219

test_fmvsmconf0.1_n		97.74 97	97.44 101	98.64 108	95.76 325	96.20 166	99.94 82	98.05 229	98.17 11	98.89 113	99.42 134	87.65 224	99.90 105	99.50 55	99.60 101	99.82 100

plane_prior6					95.76 325	91.72 306						80.47 312

ACMM	91.95 10	92.88 276	92.52 276	93.98 324	95.75 327	89.08 358	99.77 163	97.52 290	93.00 203	89.95 299	97.99 263	76.17 351	98.46 247	93.63 254	88.87 301	94.39 313
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GA-MVS		93.83 248	92.84 263	96.80 224	95.73 328	93.57 257	99.88 119	97.24 323	92.57 228	92.92 265	96.66 304	78.73 328	97.67 303	87.75 338	94.06 269	99.17 212

plane_prior1					95.73 328

jason		97.24 123	96.86 128	98.38 137	95.73 328	97.32 110	99.97 36	97.40 302	95.34 111	98.60 133	99.54 126	87.70 223	98.56 240	97.94 149	99.47 117	99.25 207
jason: jason.
mmtdpeth		88.52 357	87.75 359	90.85 377	95.71 331	83.47 404	98.94 310	94.85 419	88.78 332	97.19 188	89.58 423	63.29 413	98.97 209	98.54 113	62.86 439	90.10 422

HQP_MVS		94.49 233	94.36 219	94.87 283	95.71 331	91.74 303	99.84 141	97.87 247	96.38 81	93.01 263	98.59 225	80.47 312	98.37 261	97.79 159	89.55 293	94.52 303

plane_prior7					95.71 331	91.59 313

ITE_SJBPF				92.38 360	95.69 334	85.14 391		95.71 403	92.81 211	89.33 319	98.11 257	70.23 386	98.42 250	85.91 360	88.16 314	93.59 376

fmvsm_s_conf0.1_n_a		97.09 132	96.90 125	97.63 188	95.65 335	94.21 241	99.83 148	98.50 130	96.27 86	99.65 50	99.64 111	84.72 267	99.93 96	99.04 78	98.84 151	98.74 243

ACMH	89.72 17	90.64 324	89.63 327	93.66 336	95.64 336	88.64 364	98.55 345	97.45 295	89.03 321	81.62 399	97.61 273	69.75 387	98.41 251	89.37 318	87.62 321	93.92 359
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline2		96.71 154	96.49 146	97.37 206	95.63 337	95.96 175	99.74 175	98.88 54	92.94 205	91.61 279	98.97 180	97.72 6	98.62 238	94.83 221	98.08 181	97.53 282

FMVSNet1		88.50 358	86.64 365	94.08 317	95.62 338	91.97 294	98.43 353	96.95 357	83.00 401	86.08 374	94.72 379	59.09 424	96.11 382	81.82 389	84.07 347	94.17 331

LuminaMVS		96.63 158	96.21 157	97.87 170	95.58 339	96.82 134	99.12 280	97.67 267	94.47 137	97.88 166	98.31 250	87.50 228	98.71 230	98.07 142	97.29 198	98.10 263

LPG-MVS_test		92.96 273	92.71 268	93.71 332	95.43 340	88.67 362	99.75 172	97.62 275	92.81 211	90.05 295	98.49 236	75.24 358	98.40 253	95.84 201	89.12 297	94.07 345

LGP-MVS_train				93.71 332	95.43 340	88.67 362		97.62 275	92.81 211	90.05 295	98.49 236	75.24 358	98.40 253	95.84 201	89.12 297	94.07 345

tpm		93.70 257	93.41 249	94.58 296	95.36 342	87.41 376	97.01 395	96.90 364	90.85 286	96.72 202	94.14 394	90.40 189	96.84 352	90.75 299	88.54 309	99.51 167

D2MVS		92.76 278	92.59 274	93.27 344	95.13 343	89.54 352	99.69 195	99.38 22	92.26 242	87.59 351	94.61 385	85.05 264	97.79 298	91.59 282	88.01 315	92.47 399

VPA-MVSNet		92.70 280	91.55 293	96.16 245	95.09 344	96.20 166	98.88 318	99.00 39	91.02 283	91.82 278	95.29 361	76.05 353	97.96 291	95.62 206	81.19 367	94.30 320

LTVRE_ROB	88.28 18	90.29 334	89.05 341	94.02 320	95.08 345	90.15 341	97.19 390	97.43 297	84.91 387	83.99 388	97.06 290	74.00 369	98.28 270	84.08 371	87.71 319	93.62 375
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
TinyColmap		87.87 365	86.51 366	91.94 366	95.05 346	85.57 389	97.65 382	94.08 429	84.40 391	81.82 398	96.85 299	62.14 418	98.33 264	80.25 398	86.37 328	91.91 406

test0.0.03 1		93.86 247	93.61 237	94.64 292	95.02 347	92.18 292	99.93 89	98.58 98	94.07 161	87.96 346	98.50 235	93.90 103	94.96 405	81.33 390	93.17 279	96.78 288

UniMVSNet (Re)		93.07 272	92.13 280	95.88 253	94.84 348	96.24 165	99.88 119	98.98 41	92.49 233	89.25 320	95.40 351	87.09 236	97.14 328	93.13 262	78.16 391	94.26 322

USDC		90.00 341	88.96 342	93.10 350	94.81 349	88.16 370	98.71 335	95.54 408	93.66 182	83.75 390	97.20 284	65.58 404	98.31 266	83.96 374	87.49 323	92.85 393

VPNet		91.81 298	90.46 309	95.85 255	94.74 350	95.54 194	98.98 302	98.59 96	92.14 244	90.77 291	97.44 277	68.73 391	97.54 308	94.89 220	77.89 393	94.46 306

FIs		94.10 244	93.43 246	96.11 246	94.70 351	96.82 134	99.58 216	98.93 48	92.54 229	89.34 318	97.31 281	87.62 225	97.10 332	94.22 238	86.58 326	94.40 312

UniMVSNet_ETH3D		90.06 340	88.58 349	94.49 302	94.67 352	88.09 371	97.81 379	97.57 283	83.91 394	88.44 338	97.41 278	57.44 426	97.62 305	91.41 284	88.59 308	97.77 272

UniMVSNet_NR-MVSNet		92.95 274	92.11 281	95.49 262	94.61 353	95.28 207	99.83 148	99.08 36	91.49 264	89.21 323	96.86 298	87.14 235	96.73 358	93.20 258	77.52 396	94.46 306

test_fmvs2		89.47 350	89.70 326	88.77 401	94.54 354	75.74 429	99.83 148	94.70 425	94.71 129	91.08 284	96.82 303	54.46 429	97.78 300	92.87 265	88.27 312	92.80 394

MonoMVSNet		94.82 215	94.43 217	95.98 249	94.54 354	90.73 326	99.03 298	97.06 345	93.16 198	93.15 262	95.47 348	88.29 217	97.57 306	97.85 154	91.33 287	99.62 136

WR-MVS		92.31 290	91.25 298	95.48 265	94.45 356	95.29 206	99.60 213	98.68 77	90.10 306	88.07 345	96.89 296	80.68 307	96.80 356	93.14 261	79.67 384	94.36 314

nrg030		93.51 261	92.53 275	96.45 236	94.36 357	97.20 116	99.81 153	97.16 331	91.60 261	89.86 302	97.46 276	86.37 247	97.68 302	95.88 200	80.31 380	94.46 306

tfpnnormal		89.29 353	87.61 360	94.34 310	94.35 358	94.13 243	98.95 309	98.94 44	83.94 392	84.47 385	95.51 345	74.84 363	97.39 311	77.05 414	80.41 378	91.48 409

FC-MVSNet-test		93.81 251	93.15 259	95.80 257	94.30 359	96.20 166	99.42 245	98.89 52	92.33 239	89.03 328	97.27 283	87.39 231	96.83 354	93.20 258	86.48 327	94.36 314

SSC-MVS3.2		89.59 348	88.66 348	92.38 360	94.29 360	86.12 385	99.49 234	97.66 270	90.28 305	88.63 335	95.18 365	64.46 409	96.88 350	85.30 364	82.66 355	94.14 340

MS-PatchMatch		90.65 323	90.30 314	91.71 371	94.22 361	85.50 390	98.24 363	97.70 264	88.67 335	86.42 369	96.37 314	67.82 396	98.03 287	83.62 376	99.62 95	91.60 407

WR-MVS_H		91.30 308	90.35 312	94.15 314	94.17 362	92.62 283	99.17 278	98.94 44	88.87 330	86.48 368	94.46 390	84.36 271	96.61 363	88.19 332	78.51 389	93.21 385

DU-MVS		92.46 287	91.45 296	95.49 262	94.05 363	95.28 207	99.81 153	98.74 71	92.25 243	89.21 323	96.64 306	81.66 293	96.73 358	93.20 258	77.52 396	94.46 306

NR-MVSNet		91.56 306	90.22 316	95.60 260	94.05 363	95.76 182	98.25 362	98.70 74	91.16 278	80.78 405	96.64 306	83.23 281	96.57 364	91.41 284	77.73 395	94.46 306

CP-MVSNet		91.23 312	90.22 316	94.26 312	93.96 365	92.39 288	99.09 284	98.57 100	88.95 327	86.42 369	96.57 309	79.19 323	96.37 372	90.29 308	78.95 386	94.02 348

XXY-MVS		91.82 297	90.46 309	95.88 253	93.91 366	95.40 200	98.87 321	97.69 266	88.63 337	87.87 347	97.08 288	74.38 367	97.89 295	91.66 281	84.07 347	94.35 317

PS-CasMVS		90.63 325	89.51 332	93.99 323	93.83 367	91.70 307	98.98 302	98.52 121	88.48 339	86.15 373	96.53 311	75.46 356	96.31 376	88.83 323	78.86 388	93.95 356

test_0402		85.58 372	83.94 377	90.50 383	93.81 368	85.04 392	98.55 345	95.20 416	76.01 423	79.72 411	95.13 366	64.15 411	96.26 378	66.04 437	86.88 325	90.21 420

XVG-ACMP-BASELINE		91.22 313	90.75 304	92.63 359	93.73 369	85.61 388	98.52 349	97.44 296	92.77 215	89.90 301	96.85 299	66.64 401	98.39 255	92.29 270	88.61 306	93.89 361

TranMVSNet+NR-MVSNet		91.68 305	90.61 308	94.87 283	93.69 370	93.98 247	99.69 195	98.65 81	91.03 282	88.44 338	96.83 302	80.05 316	96.18 380	90.26 309	76.89 404	94.45 311

TransMVSNet (Re)		87.25 366	85.28 373	93.16 347	93.56 371	91.03 318	98.54 347	94.05 431	83.69 396	81.09 403	96.16 320	75.32 357	96.40 371	76.69 415	68.41 427	92.06 403

v10		90.25 335	88.82 344	94.57 297	93.53 372	93.43 262	99.08 286	96.87 367	85.00 384	87.34 358	94.51 386	80.93 303	97.02 342	82.85 381	79.23 385	93.26 383

testgi		89.01 355	88.04 356	91.90 367	93.49 373	84.89 394	99.73 182	95.66 405	93.89 175	85.14 380	98.17 255	59.68 423	94.66 411	77.73 410	88.88 300	96.16 297

v8		90.54 327	89.17 337	94.66 291	93.43 374	93.40 264	99.20 275	96.94 361	85.76 375	87.56 352	94.51 386	81.96 289	97.19 325	84.94 367	78.25 390	93.38 381

V42		91.28 310	90.12 321	94.74 288	93.42 375	93.46 261	99.68 197	97.02 349	87.36 354	89.85 304	95.05 369	81.31 299	97.34 314	87.34 343	80.07 382	93.40 379

pm-mvs1		89.36 352	87.81 358	94.01 321	93.40 376	91.93 297	98.62 343	96.48 387	86.25 370	83.86 389	96.14 322	73.68 370	97.04 338	86.16 357	75.73 409	93.04 389

v1144		91.09 314	89.83 323	94.87 283	93.25 377	93.69 255	99.62 208	96.98 354	86.83 364	89.64 310	94.99 374	80.94 302	97.05 335	85.08 366	81.16 368	93.87 363

v1192		90.62 326	89.25 336	94.72 290	93.13 378	93.07 268	99.50 232	97.02 349	86.33 369	89.56 314	95.01 371	79.22 322	97.09 334	82.34 385	81.16 368	94.01 350

v2v482		91.30 308	90.07 322	95.01 278	93.13 378	93.79 250	99.77 163	97.02 349	88.05 345	89.25 320	95.37 355	80.73 306	97.15 327	87.28 344	80.04 383	94.09 344

OPM-MVS		93.21 266	92.80 265	94.44 305	93.12 380	90.85 325	99.77 163	97.61 278	96.19 89	91.56 280	98.65 219	75.16 362	98.47 244	93.78 249	89.39 296	93.99 353
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v144192		90.79 321	89.52 331	94.59 295	93.11 381	92.77 274	99.56 221	96.99 352	86.38 368	89.82 305	94.95 376	80.50 311	97.10 332	83.98 373	80.41 378	93.90 360

PEN-MVS		90.19 337	89.06 340	93.57 337	93.06 382	90.90 323	99.06 291	98.47 133	88.11 344	85.91 375	96.30 316	76.67 343	95.94 390	87.07 347	76.91 403	93.89 361

v1240		90.20 336	88.79 345	94.44 305	93.05 383	92.27 290	99.38 252	96.92 363	85.89 373	89.36 317	94.87 378	77.89 334	97.03 340	80.66 394	81.08 371	94.01 350

v148		90.70 322	89.63 327	93.92 325	92.97 384	90.97 319	99.75 172	96.89 365	87.51 351	88.27 343	95.01 371	81.67 292	97.04 338	87.40 342	77.17 401	93.75 369

v1921920		90.46 328	89.12 338	94.50 301	92.96 385	92.46 286	99.49 234	96.98 354	86.10 371	89.61 312	95.30 358	78.55 331	97.03 340	82.17 386	80.89 376	94.01 350

MVStest1		85.03 378	82.76 387	91.83 368	92.95 386	89.16 357	98.57 344	94.82 420	71.68 434	68.54 437	95.11 368	83.17 282	95.66 394	74.69 420	65.32 434	90.65 416

tt0320-xc		82.94 392	80.35 399	90.72 381	92.90 387	83.54 402	96.85 400	94.73 423	63.12 439	79.85 410	93.77 398	49.43 437	95.46 397	80.98 393	71.54 418	93.16 386

Baseline_NR-MVSNet		90.33 332	89.51 332	92.81 356	92.84 388	89.95 346	99.77 163	93.94 432	84.69 389	89.04 327	95.66 337	81.66 293	96.52 365	90.99 292	76.98 402	91.97 405

test_method		80.79 397	79.70 401	84.08 412	92.83 389	67.06 438	99.51 230	95.42 410	54.34 444	81.07 404	93.53 400	44.48 440	92.22 431	78.90 405	77.23 400	92.94 391

pmmvs4		92.10 294	91.07 302	95.18 274	92.82 390	94.96 218	99.48 237	96.83 369	87.45 353	88.66 334	96.56 310	83.78 276	96.83 354	89.29 319	84.77 341	93.75 369

LF4IMVS		89.25 354	88.85 343	90.45 385	92.81 391	81.19 419	98.12 369	94.79 421	91.44 268	86.29 371	97.11 286	65.30 407	98.11 281	88.53 328	85.25 335	92.07 402

tt0320		83.56 391	81.15 394	90.77 379	92.77 392	83.58 401	96.83 401	95.52 409	63.26 438	81.36 401	92.54 408	53.26 431	95.77 392	80.45 395	74.38 412	92.96 390

DTE-MVSNet		89.40 351	88.24 354	92.88 354	92.66 393	89.95 346	99.10 283	98.22 206	87.29 355	85.12 381	96.22 318	76.27 350	95.30 402	83.56 377	75.74 408	93.41 378

EU-MVSNet		90.14 339	90.34 313	89.54 393	92.55 394	81.06 420	98.69 338	98.04 230	91.41 272	86.59 365	96.84 301	80.83 305	93.31 424	86.20 356	81.91 362	94.26 322

APD_test1		81.15 396	80.92 396	81.86 416	92.45 395	59.76 445	96.04 415	93.61 435	73.29 432	77.06 420	96.64 306	44.28 441	96.16 381	72.35 424	82.52 356	89.67 427

sc_t1		85.01 379	82.46 389	92.67 358	92.44 396	83.09 405	97.39 386	95.72 402	65.06 437	85.64 378	96.16 320	49.50 436	97.34 314	84.86 368	75.39 410	97.57 280

our_test_3		90.39 329	89.48 334	93.12 348	92.40 397	89.57 351	99.33 259	96.35 390	87.84 349	85.30 379	94.99 374	84.14 274	96.09 385	80.38 396	84.56 342	93.71 374

ppachtmachnet_test		89.58 349	88.35 352	93.25 346	92.40 397	90.44 335	99.33 259	96.73 376	85.49 380	85.90 376	95.77 331	81.09 301	96.00 389	76.00 418	82.49 357	93.30 382

v7n		89.65 347	88.29 353	93.72 331	92.22 399	90.56 332	99.07 290	97.10 339	85.42 382	86.73 362	94.72 379	80.06 315	97.13 329	81.14 391	78.12 392	93.49 377

dmvs_testset		83.79 388	86.07 369	76.94 420	92.14 400	48.60 455	96.75 402	90.27 445	89.48 315	78.65 414	98.55 232	79.25 321	86.65 443	66.85 434	82.69 354	95.57 299

PS-MVSNAJss		93.64 258	93.31 255	94.61 293	92.11 401	92.19 291	99.12 280	97.38 303	92.51 232	88.45 337	96.99 294	91.20 170	97.29 322	94.36 232	87.71 319	94.36 314

pmmvs5		90.17 338	89.09 339	93.40 340	92.10 402	89.77 349	99.74 175	95.58 407	85.88 374	87.24 359	95.74 332	73.41 373	96.48 367	88.54 327	83.56 351	93.95 356

N_pmnet		80.06 400	80.78 397	77.89 419	91.94 403	45.28 457	98.80 329	56.82 459	78.10 420	80.08 408	93.33 401	77.03 337	95.76 393	68.14 432	82.81 353	92.64 395

test_djsdf		92.83 277	92.29 279	94.47 303	91.90 404	92.46 286	99.55 224	97.27 319	91.17 276	89.96 298	96.07 326	81.10 300	96.89 348	94.67 227	88.91 299	94.05 347

SixPastTwentyTwo		88.73 356	88.01 357	90.88 375	91.85 405	82.24 411	98.22 366	95.18 417	88.97 325	82.26 395	96.89 296	71.75 378	96.67 361	84.00 372	82.98 352	93.72 373

K. test v3		88.05 362	87.24 363	90.47 384	91.82 406	82.23 412	98.96 308	97.42 299	89.05 320	76.93 422	95.60 339	68.49 392	95.42 398	85.87 361	81.01 374	93.75 369

OurMVSNet-221017-0		89.81 344	89.48 334	90.83 378	91.64 407	81.21 418	98.17 368	95.38 412	91.48 266	85.65 377	97.31 281	72.66 374	97.29 322	88.15 333	84.83 340	93.97 355

mvs_tets		91.81 298	91.08 301	94.00 322	91.63 408	90.58 331	98.67 340	97.43 297	92.43 234	87.37 357	97.05 291	71.76 377	97.32 317	94.75 224	88.68 305	94.11 343

Gipuma		66.95 413	65.00 413	72.79 425	91.52 409	67.96 437	66.16 448	95.15 418	47.89 446	58.54 443	67.99 448	29.74 445	87.54 442	50.20 447	77.83 394	62.87 448
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_fmvsmconf0.01_n		96.39 169	95.74 178	98.32 139	91.47 410	95.56 193	99.84 141	97.30 314	97.74 27	97.89 165	99.35 145	79.62 318	99.85 122	99.25 68	99.24 134	99.55 153

jajsoiax		91.92 296	91.18 299	94.15 314	91.35 411	90.95 322	99.00 301	97.42 299	92.61 224	87.38 356	97.08 288	72.46 375	97.36 312	94.53 230	88.77 303	94.13 342

MDA-MVSNet-bldmvs		84.09 386	81.52 393	91.81 369	91.32 412	88.00 373	98.67 340	95.92 398	80.22 414	55.60 446	93.32 402	68.29 394	93.60 422	73.76 421	76.61 405	93.82 367

MVP-Stereo		90.93 316	90.45 311	92.37 362	91.25 413	88.76 359	98.05 373	96.17 393	87.27 356	84.04 386	95.30 358	78.46 332	97.27 324	83.78 375	99.70 89	91.09 410
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MDA-MVSNet_test_wron		85.51 374	83.32 382	92.10 364	90.96 414	88.58 365	99.20 275	96.52 385	79.70 416	57.12 445	92.69 407	79.11 324	93.86 418	77.10 413	77.46 398	93.86 364

YYNet1		85.50 375	83.33 381	92.00 365	90.89 415	88.38 369	99.22 274	96.55 384	79.60 417	57.26 444	92.72 406	79.09 326	93.78 420	77.25 412	77.37 399	93.84 365

anonymousdsp		91.79 303	90.92 303	94.41 308	90.76 416	92.93 273	98.93 312	97.17 329	89.08 319	87.46 355	95.30 358	78.43 333	96.92 346	92.38 269	88.73 304	93.39 380

lessismore_v0				90.53 382	90.58 417	80.90 421		95.80 399		77.01 421	95.84 329	66.15 403	96.95 344	83.03 380	75.05 411	93.74 372

EG-PatchMatch MVS		85.35 376	83.81 379	89.99 391	90.39 418	81.89 414	98.21 367	96.09 395	81.78 408	74.73 428	93.72 399	51.56 435	97.12 331	79.16 404	88.61 306	90.96 413

EGC-MVSNET		69.38 406	63.76 416	86.26 409	90.32 419	81.66 417	96.24 411	93.85 433	0.99 456	3.22 457	92.33 413	52.44 432	92.92 427	59.53 443	84.90 339	84.21 437

CMPMVS	61.59 21	84.75 382	85.14 374	83.57 413	90.32 419	62.54 441	96.98 396	97.59 282	74.33 430	69.95 434	96.66 304	64.17 410	98.32 265	87.88 337	88.41 311	89.84 425
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
new_pmnet		84.49 385	82.92 385	89.21 395	90.03 421	82.60 408	96.89 399	95.62 406	80.59 412	75.77 427	89.17 425	65.04 408	94.79 409	72.12 425	81.02 373	90.23 419

pmmvs6		85.69 371	83.84 378	91.26 374	90.00 422	84.41 397	97.82 378	96.15 394	75.86 424	81.29 402	95.39 353	61.21 421	96.87 351	83.52 378	73.29 414	92.50 398

ttmdpeth		88.23 361	87.06 364	91.75 370	89.91 423	87.35 377	98.92 315	95.73 401	87.92 347	84.02 387	96.31 315	68.23 395	96.84 352	86.33 355	76.12 406	91.06 411

DSMNet-mixed		88.28 360	88.24 354	88.42 403	89.64 424	75.38 431	98.06 372	89.86 446	85.59 379	88.20 344	92.14 414	76.15 352	91.95 432	78.46 407	96.05 226	97.92 266

UnsupCasMVSNet_eth		85.52 373	83.99 375	90.10 389	89.36 425	83.51 403	96.65 403	97.99 233	89.14 318	75.89 426	93.83 396	63.25 414	93.92 416	81.92 388	67.90 430	92.88 392

Anonymous20231206		86.32 369	85.42 372	89.02 397	89.11 426	80.53 424	99.05 295	95.28 413	85.43 381	82.82 393	93.92 395	74.40 366	93.44 423	66.99 433	81.83 363	93.08 388

Anonymous20240521		85.15 377	83.81 379	89.16 396	88.32 427	82.69 407	98.80 329	95.74 400	79.72 415	81.53 400	90.99 417	65.38 406	94.16 414	72.69 423	81.11 370	90.63 417

OpenMVS_ROB	79.82 20	83.77 389	81.68 392	90.03 390	88.30 428	82.82 406	98.46 350	95.22 415	73.92 431	76.00 425	91.29 416	55.00 428	96.94 345	68.40 431	88.51 310	90.34 418

test20.03		84.72 383	83.99 375	86.91 407	88.19 429	80.62 423	98.88 318	95.94 397	88.36 341	78.87 412	94.62 384	68.75 390	89.11 438	66.52 435	75.82 407	91.00 412

KD-MVS_self_test		83.59 390	82.06 390	88.20 404	86.93 430	80.70 422	97.21 389	96.38 388	82.87 402	82.49 394	88.97 426	67.63 397	92.32 430	73.75 422	62.30 441	91.58 408

MIMVSNet1		82.58 393	80.51 398	88.78 399	86.68 431	84.20 398	96.65 403	95.41 411	78.75 418	78.59 415	92.44 409	51.88 434	89.76 437	65.26 438	78.95 386	92.38 401

CL-MVSNet_self_test		84.50 384	83.15 384	88.53 402	86.00 432	81.79 415	98.82 326	97.35 307	85.12 383	83.62 391	90.91 419	76.66 344	91.40 433	69.53 429	60.36 442	92.40 400

UnsupCasMVSNet_bld		79.97 402	77.03 407	88.78 399	85.62 433	81.98 413	93.66 427	97.35 307	75.51 427	70.79 433	83.05 440	48.70 438	94.91 407	78.31 408	60.29 443	89.46 430

mvs5depth		84.87 380	82.90 386	90.77 379	85.59 434	84.84 395	91.10 438	93.29 437	83.14 399	85.07 382	94.33 392	62.17 417	97.32 317	78.83 406	72.59 417	90.14 421

Patchmatch-RL test		86.90 367	85.98 371	89.67 392	84.45 435	75.59 430	89.71 441	92.43 439	86.89 363	77.83 419	90.94 418	94.22 92	93.63 421	87.75 338	69.61 422	99.79 105

pmmvs-eth3d		84.03 387	81.97 391	90.20 388	84.15 436	87.09 379	98.10 371	94.73 423	83.05 400	74.10 430	87.77 432	65.56 405	94.01 415	81.08 392	69.24 424	89.49 429

test_fmvs3		79.99 401	80.17 400	79.45 418	84.02 437	62.83 439	99.05 295	93.49 436	88.29 343	80.06 409	86.65 435	28.09 447	88.00 439	88.63 324	73.27 415	87.54 435

PM-MVS		80.47 398	78.88 403	85.26 410	83.79 438	72.22 433	95.89 418	91.08 443	85.71 378	76.56 424	88.30 428	36.64 443	93.90 417	82.39 384	69.57 423	89.66 428

new-patchmatchnet		81.19 395	79.34 402	86.76 408	82.86 439	80.36 425	97.92 375	95.27 414	82.09 407	72.02 431	86.87 434	62.81 416	90.74 436	71.10 426	63.08 438	89.19 432

mvsany_test3		82.12 394	81.14 395	85.06 411	81.87 440	70.41 435	97.09 393	92.14 440	91.27 275	77.84 418	88.73 427	39.31 442	95.49 395	90.75 299	71.24 419	89.29 431

WB-MVS		76.28 404	77.28 406	73.29 424	81.18 441	54.68 449	97.87 377	94.19 428	81.30 409	69.43 435	90.70 420	77.02 338	82.06 447	35.71 452	68.11 429	83.13 438

test_f		78.40 403	77.59 405	80.81 417	80.82 442	62.48 442	96.96 397	93.08 438	83.44 397	74.57 429	84.57 439	27.95 448	92.63 428	84.15 370	72.79 416	87.32 436

SSC-MVS		75.42 405	76.40 408	72.49 428	80.68 443	53.62 450	97.42 384	94.06 430	80.42 413	68.75 436	90.14 422	76.54 346	81.66 448	33.25 453	66.34 433	82.19 439

pmmvs3		80.27 399	77.77 404	87.76 406	80.32 444	82.43 410	98.23 365	91.97 441	72.74 433	78.75 413	87.97 431	57.30 427	90.99 435	70.31 427	62.37 440	89.87 424

testf1		68.38 409	66.92 410	72.78 426	78.80 445	50.36 452	90.95 439	87.35 451	55.47 442	58.95 441	88.14 429	20.64 452	87.60 440	57.28 444	64.69 435	80.39 441

APD_test2		68.38 409	66.92 410	72.78 426	78.80 445	50.36 452	90.95 439	87.35 451	55.47 442	58.95 441	88.14 429	20.64 452	87.60 440	57.28 444	64.69 435	80.39 441

ambc				83.23 414	77.17 447	62.61 440	87.38 443	94.55 427		76.72 423	86.65 435	30.16 444	96.36 373	84.85 369	69.86 421	90.73 415

test_vis3_rt		68.82 407	66.69 412	75.21 423	76.24 448	60.41 444	96.44 406	68.71 458	75.13 428	50.54 449	69.52 447	16.42 457	96.32 375	80.27 397	66.92 432	68.89 445

TDRefinement		84.76 381	82.56 388	91.38 373	74.58 449	84.80 396	97.36 387	94.56 426	84.73 388	80.21 407	96.12 325	63.56 412	98.39 255	87.92 336	63.97 437	90.95 414

E-PMN		52.30 417	52.18 419	52.67 434	71.51 450	45.40 456	93.62 428	76.60 456	36.01 450	43.50 451	64.13 450	27.11 449	67.31 453	31.06 454	26.06 449	45.30 452

EMVS		51.44 419	51.22 421	52.11 435	70.71 451	44.97 458	94.04 424	75.66 457	35.34 452	42.40 452	61.56 453	28.93 446	65.87 454	27.64 455	24.73 450	45.49 451

PMMVS2		67.15 412	64.15 415	76.14 422	70.56 452	62.07 443	93.89 425	87.52 450	58.09 441	60.02 440	78.32 442	22.38 451	84.54 445	59.56 442	47.03 447	81.80 440

FPMVS		68.72 408	68.72 409	68.71 430	65.95 453	44.27 459	95.97 417	94.74 422	51.13 445	53.26 447	90.50 421	25.11 450	83.00 446	60.80 441	80.97 375	78.87 443

wuyk23d		20.37 423	20.84 426	18.99 438	65.34 454	27.73 461	50.43 449	7.67 462	9.50 455	8.01 456	6.34 456	6.13 460	26.24 455	23.40 456	10.69 454	2.99 453

LCM-MVSNet		67.77 411	64.73 414	76.87 421	62.95 455	56.25 448	89.37 442	93.74 434	44.53 447	61.99 439	80.74 441	20.42 454	86.53 444	69.37 430	59.50 444	87.84 433

MVE	53.74 22	51.54 418	47.86 422	62.60 432	59.56 456	50.93 451	79.41 446	77.69 455	35.69 451	36.27 453	61.76 452	5.79 461	69.63 451	37.97 451	36.61 448	67.24 446
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		56.10 415	52.24 418	67.66 431	49.27 457	56.82 447	83.94 444	82.02 454	70.47 435	33.28 454	64.54 449	17.23 456	69.16 452	45.59 449	23.85 451	77.02 444

tmp_tt		65.23 414	62.94 417	72.13 429	44.90 458	50.03 454	81.05 445	89.42 449	38.45 448	48.51 450	99.90 18	54.09 430	78.70 450	91.84 280	18.26 452	87.64 434

PMVS	49.05 23	53.75 416	51.34 420	60.97 433	40.80 459	34.68 460	74.82 447	89.62 448	37.55 449	28.67 455	72.12 444	7.09 459	81.63 449	43.17 450	68.21 428	66.59 447
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test123		37.68 421	39.14 424	33.31 436	19.94 460	24.83 462	98.36 358	9.75 461	15.53 454	51.31 448	87.14 433	19.62 455	17.74 456	47.10 448	3.47 455	57.36 449

testmvs		40.60 420	44.45 423	29.05 437	19.49 461	14.11 463	99.68 197	18.47 460	20.74 453	64.59 438	98.48 239	10.95 458	17.09 457	56.66 446	11.01 453	55.94 450

mmdepth		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 458	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

monomultidepth		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 458	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

test_blank		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.02 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

eth-test2					0.00 462

eth-test					0.00 462

uanet_test		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 458	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

DCPMVS		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 458	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

cdsmvs_eth3d_5k		23.43 422	31.24 425	0.00 439	0.00 462	0.00 464	0.00 450	98.09 224	0.00 457	0.00 458	99.67 106	83.37 279	0.00 458	0.00 457	0.00 456	0.00 454

pcd_1.5k_mvsjas		7.60 425	10.13 428	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 458	91.20 170	0.00 458	0.00 457	0.00 456	0.00 454

sosnet-low-res		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 458	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

sosnet		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 458	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

uncertanet		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 458	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

Regformer		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 458	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

ab-mvs-re		8.28 424	11.04 427	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	99.40 139	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

uanet		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 458	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

WAC-MVS						90.97 319								86.10 359

PC_three_1452									96.96 57	99.80 23	99.79 58	97.49 10	100.00 1	99.99 5	99.98 32	100.00 1

test_241102_TWO								98.43 149	97.27 44	99.80 23	99.94 4	97.18 21	100.00 1	100.00 1	100.00 1	100.00 1

test_0728_THIRD									96.48 75	99.83 19	99.91 14	97.87 5	100.00 1	99.92 13	100.00 1	100.00 1

GSMVS																99.59 143

sam_mvs1												94.72 71				99.59 143

sam_mvs												94.25 91

MTGPA								98.28 197

test_post1							95.78 419				59.23 454	93.20 125	97.74 301	91.06 290

test_post											63.35 451	94.43 79	98.13 280

patchmatchnet-post											91.70 415	95.12 56	97.95 292

MTMP							99.87 122	96.49 386

test9_res														99.71 42	99.99 21	100.00 1

agg_prior2														99.48 57	100.00 1	100.00 1

test_prior4						98.05 76	99.94 82

test_prior2							99.95 65		95.78 97	99.73 42	99.76 67	96.00 37		99.78 30	100.00 1

旧先验2							99.46 242		94.21 156	99.85 15			99.95 79	96.96 182

新几何2							99.40 246

无先验							99.49 234	98.71 73	93.46 187				100.00 1	94.36 232		99.99 23

原ACMM2							99.90 106

testdata2													99.99 36	90.54 303

segment_acmp												96.68 29

testdata1							99.28 268		96.35 85

plane_prior5								97.87 247					98.37 261	97.79 159	89.55 293	94.52 303

plane_prior4											98.59 225

plane_prior3						91.64 309			96.63 70	93.01 263

plane_prior2							99.84 141		96.38 81

plane_prior						91.74 303	99.86 133		96.76 65						89.59 292

n2								0.00 463

nn								0.00 463

door-mid								89.69 447

test11								98.44 141

door								90.31 444

HQP5-MVS						91.85 299

BP-MVS														97.92 150

HQP4-MVS										93.37 258			98.39 255			94.53 301

HQP3-MVS								97.89 245							89.60 290

HQP2-MVS												80.65 308

MDTV_nov1_ep13_2view						96.26 160	96.11 413		91.89 252	98.06 158		94.40 81		94.30 235		99.67 123

ACMMP++_ref															87.04 324

ACMMP++															88.23 313

Test By Simon												92.82 136

High-resolution multi-view benchmark