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		97.23 111	96.80 119	98.51 116	99.99 1	95.60 177	99.09 263	98.84 59	93.32 174	96.74 183	99.72 84	86.04 236	100.00 1	98.01 130	99.43 115	99.94 78

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 15	98.69 69	98.20 8	99.93 1	99.98 2	96.82 24	100.00 1	99.75 32	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 29	98.64 77	98.47 3	99.13 91	99.92 13	96.38 34	100.00 1	99.74 34	100.00 1	100.00 1

mPP-MVS		98.39 50	98.20 49	98.97 81	99.97 3	96.92 122	99.95 55	98.38 164	95.04 103	98.61 121	99.80 54	93.39 111	100.00 1	98.64 98	100.00 1	99.98 51

CPTT-MVS		97.64 92	97.32 95	98.58 107	99.97 3	95.77 166	99.96 36	98.35 170	89.90 285	98.36 133	99.79 58	91.18 167	99.99 36	98.37 113	99.99 21	99.99 23

DP-MVS Recon		98.41 48	98.02 61	99.56 25	99.97 3	98.70 48	99.92 82	98.44 128	92.06 227	98.40 132	99.84 44	95.68 44	100.00 1	98.19 120	99.71 88	99.97 61

PAPR		98.52 38	98.16 53	99.58 24	99.97 3	98.77 42	99.95 55	98.43 136	95.35 97	98.03 145	99.75 72	94.03 97	99.98 47	98.11 125	99.83 77	99.99 23

HFP-MVS		98.56 35	98.37 39	99.14 61	99.96 8	97.43 101	99.95 55	98.61 83	94.77 112	99.31 80	99.85 33	94.22 90	100.00 1	98.70 93	99.98 32	99.98 51

region2R		98.54 36	98.37 39	99.05 71	99.96 8	97.18 110	99.96 36	98.55 100	94.87 110	99.45 67	99.85 33	94.07 96	100.00 1	98.67 95	100.00 1	99.98 51

ACMMPR		98.50 39	98.32 43	99.05 71	99.96 8	97.18 110	99.95 55	98.60 85	94.77 112	99.31 80	99.84 44	93.73 106	100.00 1	98.70 93	99.98 32	99.98 51

NCCC		99.37 2	99.25 2	99.71 15	99.96 8	99.15 22	99.97 29	98.62 82	98.02 15	99.90 3	99.95 3	97.33 17	100.00 1	99.54 44	100.00 1	100.00 1

CP-MVS		98.45 43	98.32 43	98.87 86	99.96 8	96.62 132	99.97 29	98.39 160	94.43 127	98.90 103	99.87 27	94.30 87	100.00 1	99.04 69	99.99 21	99.99 23

test_one_0601					99.94 13	99.30 12		98.41 153	96.63 62	99.75 29	99.93 11	97.49 10

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 55	98.43 136					100.00 1	99.99 5	100.00 1	100.00 1

XVS		98.70 29	98.55 28	99.15 59	99.94 13	97.50 97	99.94 72	98.42 148	96.22 77	99.41 72	99.78 62	94.34 84	99.96 65	98.92 78	99.95 50	99.99 23

X-MVStestdata		93.83 225	92.06 258	99.15 59	99.94 13	97.50 97	99.94 72	98.42 148	96.22 77	99.41 72	41.37 426	94.34 84	99.96 65	98.92 78	99.95 50	99.99 23

test_prior				99.43 35	99.94 13	98.49 60		98.65 75					99.80 126			99.99 23

MSLP-MVS++		99.13 8	99.01 11	99.49 32	99.94 13	98.46 61	99.98 15	98.86 53	97.10 42	99.80 17	99.94 4	95.92 40	100.00 1	99.51 45	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 89	98.39 160	97.20 40	99.46 66	99.85 33	95.53 48	99.79 128	99.86 21	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 62	97.97 64	99.03 73	99.94 13	97.17 113	99.95 55	98.39 160	94.70 116	98.26 139	99.81 53	91.84 158	100.00 1	98.85 84	99.97 42	99.93 79
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CDPH-MVS		98.65 31	98.36 41	99.49 32	99.94 13	98.73 46	99.87 110	98.33 175	93.97 152	99.76 28	99.87 27	94.99 62	99.75 137	98.55 102	100.00 1	99.98 51

PAPM_NR		98.12 65	97.93 69	98.70 96	99.94 13	96.13 156	99.82 139	98.43 136	94.56 120	97.52 159	99.70 88	94.40 79	99.98 47	97.00 164	99.98 32	99.99 23

MG-MVS		98.91 19	98.65 24	99.68 16	99.94 13	99.07 24	99.64 192	99.44 19	97.33 33	99.00 99	99.72 84	94.03 97	99.98 47	98.73 92	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 36	98.43 136	97.27 36	99.80 17	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		98.41 153	97.71 21	99.84 12				100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 24	99.30 12		98.43 136	97.26 38	99.80 17	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 55	98.32 177	97.28 34	99.83 13	99.91 14	97.22 19	100.00 1	99.99 5	100.00 1	99.89 87
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 36	98.42 148	97.28 34	99.86 7	99.94 4	97.22 19

MSP-MVS		99.09 9	99.12 5	98.98 80	99.93 24	97.24 107	99.95 55	98.42 148	97.50 28	99.52 62	99.88 24	97.43 16	99.71 143	99.50 46	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		98.43 136		99.63 46			99.85 113

FOURS1					99.92 31	97.66 91	99.95 55	98.36 168	95.58 91	99.52 62

ZD-MVS					99.92 31	98.57 56		98.52 108	92.34 219	99.31 80	99.83 46	95.06 57	99.80 126	99.70 38	99.97 42

GST-MVS		98.27 56	97.97 64	99.17 55	99.92 31	97.57 93	99.93 79	98.39 160	94.04 150	98.80 108	99.74 79	92.98 127	100.00 1	98.16 122	99.76 85	99.93 79

TEST9					99.92 31	98.92 29	99.96 36	98.43 136	93.90 158	99.71 36	99.86 29	95.88 41	99.85 113

train_agg		98.88 20	98.65 24	99.59 23	99.92 31	98.92 29	99.96 36	98.43 136	94.35 132	99.71 36	99.86 29	95.94 38	99.85 113	99.69 39	99.98 32	99.99 23

test_8					99.92 31	98.88 32	99.96 36	98.43 136	94.35 132	99.69 38	99.85 33	95.94 38	99.85 113

PGM-MVS		98.34 51	98.13 55	98.99 78	99.92 31	97.00 118	99.75 160	99.50 17	93.90 158	99.37 77	99.76 66	93.24 120	100.00 1	97.75 149	99.96 46	99.98 51

ACMMP		97.74 87	97.44 89	98.66 99	99.92 31	96.13 156	99.18 258	99.45 18	94.84 111	96.41 193	99.71 86	91.40 161	99.99 36	97.99 132	98.03 169	99.87 90
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 55	98.43 136	96.48 65	99.80 17	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		98.41 153					100.00 1	99.96 9	100.00 1	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 153					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 55	98.56 94	97.56 27	99.44 68	99.85 33	95.38 51	100.00 1	99.31 56	99.99 21	99.87 90

APD-MVS		98.62 32	98.35 42	99.41 38	99.90 42	98.51 59	99.87 110	98.36 168	94.08 145	99.74 32	99.73 81	94.08 95	99.74 139	99.42 52	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	99.24 253	98.47 120	98.14 11	99.08 94	99.91 14	93.09 124	100.00 1	99.04 69	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 36				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	99.87 110	98.44 128	97.48 29	99.64 45	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 65

CSCG		97.10 116	97.04 107	97.27 193	99.89 45	91.92 277	99.90 95	99.07 34	88.67 309	95.26 216	99.82 49	93.17 123	99.98 47	98.15 123	99.47 110	99.90 86

ZNCC-MVS		98.31 53	98.03 60	99.17 55	99.88 49	97.59 92	99.94 72	98.44 128	94.31 135	98.50 126	99.82 49	93.06 125	99.99 36	98.30 117	99.99 21	99.93 79

SR-MVS		98.46 42	98.30 46	98.93 84	99.88 49	97.04 117	99.84 129	98.35 170	94.92 107	99.32 79	99.80 54	93.35 113	99.78 130	99.30 57	99.95 50	99.96 67

9.14			98.38 37		99.87 51		99.91 89	98.33 175	93.22 177	99.78 26	99.89 22	94.57 75	99.85 113	99.84 22	99.97 42

SMA-MVS		98.76 26	98.48 32	99.62 20	99.87 51	98.87 33	99.86 121	98.38 164	93.19 178	99.77 27	99.94 4	95.54 46	100.00 1	99.74 34	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
PHI-MVS		98.41 48	98.21 48	99.03 73	99.86 53	97.10 115	99.98 15	98.80 63	90.78 268	99.62 49	99.78 62	95.30 52	100.00 1	99.80 25	99.93 61	99.99 23

MTAPA		98.29 55	97.96 67	99.30 44	99.85 54	97.93 80	99.39 233	98.28 184	95.76 86	97.18 171	99.88 24	92.74 134	100.00 1	98.67 95	99.88 73	99.99 23

LS3D		95.84 170	95.11 181	98.02 146	99.85 54	95.10 197	98.74 308	98.50 117	87.22 331	93.66 234	99.86 29	87.45 219	99.95 73	90.94 272	99.81 83	99.02 213

HPM-MVS		97.96 68	97.72 76	98.68 97	99.84 56	96.39 143	99.90 95	98.17 199	92.61 205	98.62 120	99.57 114	91.87 157	99.67 150	98.87 83	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 56	98.11 57	98.75 93	99.83 57	96.59 135	99.40 229	98.51 111	95.29 99	98.51 125	99.76 66	93.60 110	99.71 143	98.53 105	99.52 105	99.95 74

save fliter					99.82 58	98.79 40	99.96 36	98.40 157	97.66 23

PLC	95.54 3	97.93 70	97.89 72	98.05 145	99.82 58	94.77 207	99.92 82	98.46 122	93.93 155	97.20 169	99.27 141	95.44 50	99.97 57	97.41 154	99.51 108	99.41 173
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
APD-MVS_3200maxsize		98.25 60	98.08 59	98.78 90	99.81 60	96.60 133	99.82 139	98.30 182	93.95 154	99.37 77	99.77 64	92.84 131	99.76 136	98.95 75	99.92 64	99.97 61

EI-MVSNet-UG-set		98.14 64	97.99 62	98.60 104	99.80 61	96.27 146	99.36 238	98.50 117	95.21 101	98.30 136	99.75 72	93.29 117	99.73 142	98.37 113	99.30 122	99.81 97

SR-MVS-dyc-post		98.31 53	98.17 52	98.71 95	99.79 62	96.37 144	99.76 156	98.31 179	94.43 127	99.40 74	99.75 72	93.28 118	99.78 130	98.90 81	99.92 64	99.97 61

RE-MVS-def			98.13 55		99.79 62	96.37 144	99.76 156	98.31 179	94.43 127	99.40 74	99.75 72	92.95 128		98.90 81	99.92 64	99.97 61

HPM-MVS_fast		97.80 82	97.50 86	98.68 97	99.79 62	96.42 139	99.88 107	98.16 204	91.75 237	98.94 101	99.54 117	91.82 159	99.65 152	97.62 152	99.99 21	99.99 23

SF-MVS		98.67 30	98.40 35	99.50 30	99.77 65	98.67 49	99.90 95	98.21 194	93.53 167	99.81 15	99.89 22	94.70 71	99.86 112	99.84 22	99.93 61	99.96 67

MVS_0304		99.06 11	98.84 17	99.72 13	99.76 66	99.21 21	99.99 4	99.34 25	98.70 2	99.44 68	99.75 72	93.24 120	99.99 36	99.94 11	99.41 117	99.95 74

旧先验1					99.76 66	97.52 95		98.64 77			99.85 33	95.63 45			99.94 55	99.99 23

OMC-MVS		97.28 107	97.23 99	97.41 184	99.76 66	93.36 246	99.65 188	97.95 223	96.03 81	97.41 164	99.70 88	89.61 193	99.51 158	96.73 173	98.25 159	99.38 175

新几何1				99.42 37	99.75 69	98.27 64		98.63 81	92.69 200	99.55 57	99.82 49	94.40 79	100.00 1	91.21 264	99.94 55	99.99 23

MP-MVS-pluss		98.07 67	97.64 80	99.38 42	99.74 70	98.41 63	99.74 163	98.18 198	93.35 172	96.45 190	99.85 33	92.64 136	99.97 57	98.91 80	99.89 70	99.77 104
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
TSAR-MVS + MP.		98.93 17	98.77 19	99.41 38	99.74 70	98.67 49	99.77 151	98.38 164	96.73 58	99.88 6	99.74 79	94.89 64	99.59 154	99.80 25	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 70	98.56 57		98.40 157		99.65 42		94.76 67	99.75 137		99.98 32	99.99 23

原ACMM1				98.96 82	99.73 73	96.99 119		98.51 111	94.06 148	99.62 49	99.85 33	94.97 63	99.96 65	95.11 193	99.95 50	99.92 84

TSAR-MVS + GP.		98.60 33	98.51 31	98.86 87	99.73 73	96.63 131	99.97 29	97.92 228	98.07 12	98.76 113	99.55 115	95.00 61	99.94 81	99.91 16	97.68 174	99.99 23

CANet		98.27 56	97.82 74	99.63 17	99.72 75	99.10 23	99.98 15	98.51 111	97.00 48	98.52 123	99.71 86	87.80 214	99.95 73	99.75 32	99.38 118	99.83 94

reproduce_model		98.75 27	98.66 23	99.03 73	99.71 76	97.10 115	99.73 170	98.23 192	97.02 47	99.18 89	99.90 18	94.54 76	99.99 36	99.77 29	99.90 69	99.99 23

F-COLMAP		96.93 128	96.95 110	96.87 203	99.71 76	91.74 282	99.85 124	97.95 223	93.11 183	95.72 209	99.16 152	92.35 146	99.94 81	95.32 191	99.35 120	98.92 216

reproduce-ours		98.78 24	98.67 21	99.09 68	99.70 78	97.30 105	99.74 163	98.25 188	97.10 42	99.10 92	99.90 18	94.59 72	99.99 36	99.77 29	99.91 67	99.99 23

our_new_method		98.78 24	98.67 21	99.09 68	99.70 78	97.30 105	99.74 163	98.25 188	97.10 42	99.10 92	99.90 18	94.59 72	99.99 36	99.77 29	99.91 67	99.99 23

SD-MVS		98.92 18	98.70 20	99.56 25	99.70 78	98.73 46	99.94 72	98.34 174	96.38 71	99.81 15	99.76 66	94.59 72	99.98 47	99.84 22	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 61	99.12 5	95.59 238	99.67 81	86.91 358	99.95 55	98.89 49	97.60 24	99.90 3	99.76 66	96.54 32	99.98 47	99.94 11	99.82 81	99.88 88

ACMMP_NAP		98.49 40	98.14 54	99.54 27	99.66 82	98.62 55	99.85 124	98.37 167	94.68 117	99.53 60	99.83 46	92.87 130	100.00 1	98.66 97	99.84 76	99.99 23

DeepPCF-MVS	95.94 2	97.71 90	98.98 12	93.92 301	99.63 83	81.76 388	99.96 36	98.56 94	99.47 1	99.19 88	99.99 1	94.16 94	100.00 1	99.92 13	99.93 61	100.00 1

EPNet		98.49 40	98.40 35	98.77 92	99.62 84	96.80 127	99.90 95	99.51 16	97.60 24	99.20 86	99.36 135	93.71 107	99.91 94	97.99 132	98.71 146	99.61 134
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 85	99.33 8	99.99 4	99.76 6	98.39 4	99.39 76	99.80 54	90.49 182	99.96 65	99.89 17	99.43 115	99.98 51

PVSNet_BlendedMVS		96.05 164	95.82 160	96.72 208	99.59 85	96.99 119	99.95 55	99.10 31	94.06 148	98.27 137	95.80 305	89.00 204	99.95 73	99.12 63	87.53 298	93.24 357

PVSNet_Blended		97.94 69	97.64 80	98.83 88	99.59 85	96.99 119	100.00 1	99.10 31	95.38 96	98.27 137	99.08 155	89.00 204	99.95 73	99.12 63	99.25 124	99.57 145

PatchMatch-RL		96.04 165	95.40 170	97.95 148	99.59 85	95.22 193	99.52 212	99.07 34	93.96 153	96.49 189	98.35 224	82.28 265	99.82 125	90.15 288	99.22 127	98.81 223

dcpmvs_2		97.42 102	98.09 58	95.42 243	99.58 89	87.24 354	99.23 254	96.95 331	94.28 138	98.93 102	99.73 81	94.39 82	99.16 184	99.89 17	99.82 81	99.86 92

test222					99.55 90	97.41 103	99.34 239	98.55 100	91.86 232	99.27 84	99.83 46	93.84 104			99.95 50	99.99 23

CNLPA		97.76 86	97.38 91	98.92 85	99.53 91	96.84 124	99.87 110	98.14 208	93.78 161	96.55 188	99.69 90	92.28 148	99.98 47	97.13 160	99.44 114	99.93 79

API-MVS		97.86 74	97.66 79	98.47 118	99.52 92	95.41 184	99.47 221	98.87 52	91.68 238	98.84 105	99.85 33	92.34 147	99.99 36	98.44 109	99.96 46	100.00 1

PVSNet	91.05 13	97.13 115	96.69 125	98.45 120	99.52 92	95.81 164	99.95 55	99.65 12	94.73 114	99.04 97	99.21 148	84.48 251	99.95 73	94.92 199	98.74 145	99.58 143

114514_t		97.41 103	96.83 117	99.14 61	99.51 94	97.83 82	99.89 104	98.27 186	88.48 313	99.06 96	99.66 99	90.30 185	99.64 153	96.32 177	99.97 42	99.96 67

cl22		93.77 229	93.25 233	95.33 247	99.49 95	94.43 211	99.61 197	98.09 210	90.38 274	89.16 301	95.61 312	90.56 180	97.34 293	91.93 256	84.45 318	94.21 303

testdata				98.42 124	99.47 96	95.33 187		98.56 94	93.78 161	99.79 25	99.85 33	93.64 109	99.94 81	94.97 197	99.94 55	100.00 1

MAR-MVS		97.43 98	97.19 101	98.15 139	99.47 96	94.79 206	99.05 274	98.76 64	92.65 203	98.66 118	99.82 49	88.52 209	99.98 47	98.12 124	99.63 94	99.67 118
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		94.54 207	93.42 226	97.91 154	99.46 98	94.04 224	98.93 288	97.48 273	81.15 384	90.04 273	99.55 115	87.02 225	99.95 73	88.97 298	98.11 165	99.73 108

MVS_111021_LR		98.42 47	98.38 37	98.53 114	99.39 99	95.79 165	99.87 110	99.86 2	96.70 59	98.78 109	99.79 58	92.03 154	99.90 96	99.17 62	99.86 75	99.88 88

CHOSEN 280x420		99.01 14	99.03 10	98.95 83	99.38 100	98.87 33	98.46 326	99.42 21	97.03 46	99.02 98	99.09 154	99.35 2	98.21 255	99.73 36	99.78 84	99.77 104

MVS_111021_HR		98.72 28	98.62 26	99.01 77	99.36 101	97.18 110	99.93 79	99.90 1	96.81 56	98.67 117	99.77 64	93.92 99	99.89 101	99.27 58	99.94 55	99.96 67

DPM-MVS		98.83 21	98.46 33	99.97 1	99.33 102	99.92 1	99.96 36	98.44 128	97.96 16	99.55 57	99.94 4	97.18 21	100.00 1	93.81 228	99.94 55	99.98 51

TAPA-MVS	92.12 8	94.42 213	93.60 219	96.90 202	99.33 102	91.78 281	99.78 148	98.00 217	89.89 286	94.52 222	99.47 121	91.97 155	99.18 181	69.90 399	99.52 105	99.73 108
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
reproduce_monomvs		95.38 184	95.07 183	96.32 221	99.32 104	96.60 133	99.76 156	98.85 56	96.65 61	87.83 322	96.05 302	99.52 1	98.11 260	96.58 174	81.07 346	94.25 299

SPE-MVS-test		97.88 72	97.94 68	97.70 167	99.28 105	95.20 194	99.98 15	97.15 308	95.53 93	99.62 49	99.79 58	92.08 153	98.38 238	98.75 91	99.28 123	99.52 157

test_fmvsm_n_1920		98.44 44	98.61 27	97.92 152	99.27 106	95.18 195	100.00 1	98.90 47	98.05 13	99.80 17	99.73 81	92.64 136	99.99 36	99.58 43	99.51 108	98.59 233

fmvsm_l_conf0.5_n_a		99.00 15	98.91 14	99.28 45	99.21 107	97.91 81	99.98 15	98.85 56	98.25 5	99.92 2	99.75 72	94.72 69	99.97 57	99.87 19	99.64 92	99.95 74

test_yl		97.83 77	97.37 92	99.21 49	99.18 108	97.98 76	99.64 192	99.27 27	91.43 247	97.88 151	98.99 164	95.84 42	99.84 121	98.82 85	95.32 228	99.79 100

DCV-MVSNet		97.83 77	97.37 92	99.21 49	99.18 108	97.98 76	99.64 192	99.27 27	91.43 247	97.88 151	98.99 164	95.84 42	99.84 121	98.82 85	95.32 228	99.79 100

fmvsm_l_conf0.5_n		98.94 16	98.84 17	99.25 46	99.17 110	97.81 84	99.98 15	98.86 53	98.25 5	99.90 3	99.76 66	94.21 92	99.97 57	99.87 19	99.52 105	99.98 51

DeepC-MVS	94.51 4	96.92 129	96.40 135	98.45 120	99.16 111	95.90 162	99.66 187	98.06 213	96.37 74	94.37 225	99.49 120	83.29 260	99.90 96	97.63 151	99.61 99	99.55 147
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 36	98.22 47	99.50 30	99.15 112	98.65 53	100.00 1	98.58 89	97.70 22	98.21 141	99.24 146	92.58 139	99.94 81	98.63 100	99.94 55	99.92 84
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
CS-MVS		97.79 84	97.91 70	97.43 183	99.10 113	94.42 212	99.99 4	97.10 313	95.07 102	99.68 39	99.75 72	92.95 128	98.34 242	98.38 111	99.14 129	99.54 151

Anonymous202405211		93.10 247	91.99 259	96.40 217	99.10 113	89.65 326	98.88 294	97.93 225	83.71 369	94.00 231	98.75 193	68.79 364	99.88 107	95.08 194	91.71 260	99.68 116

fmvsm_s_conf0.5_n		97.80 82	97.85 73	97.67 168	99.06 115	94.41 213	99.98 15	98.97 40	97.34 31	99.63 46	99.69 90	87.27 221	99.97 57	99.62 41	99.06 133	98.62 232

HyFIR lowres test		96.66 143	96.43 134	97.36 189	99.05 116	93.91 229	99.70 181	99.80 3	90.54 272	96.26 196	98.08 234	92.15 151	98.23 254	96.84 172	95.46 223	99.93 79

LFMVS		94.75 201	93.56 222	98.30 130	99.03 117	95.70 171	98.74 308	97.98 220	87.81 324	98.47 127	99.39 132	67.43 373	99.53 155	98.01 130	95.20 231	99.67 118

fmvsm_s_conf0.5_n_2		97.59 93	97.28 96	98.53 114	99.01 118	98.15 65	99.98 15	98.59 87	98.17 9	99.75 29	99.63 105	81.83 270	99.94 81	99.78 27	98.79 144	97.51 258

AllTest		92.48 261	91.64 264	95.00 256	99.01 118	88.43 342	98.94 286	96.82 345	86.50 340	88.71 306	98.47 219	74.73 341	99.88 107	85.39 337	96.18 205	96.71 264

TestCases				95.00 256	99.01 118	88.43 342		96.82 345	86.50 340	88.71 306	98.47 219	74.73 341	99.88 107	85.39 337	96.18 205	96.71 264

COLMAP_ROB	90.47 14	92.18 268	91.49 270	94.25 289	99.00 121	88.04 348	98.42 332	96.70 352	82.30 380	88.43 314	99.01 161	76.97 317	99.85 113	86.11 333	96.50 199	94.86 275
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvs1		95.35 185	95.68 165	94.36 286	98.99 122	84.98 368	99.96 36	96.65 354	97.60 24	99.73 34	98.96 170	71.58 354	99.93 89	98.31 116	99.37 119	98.17 240

HY-MVS	92.50 7	97.79 84	97.17 103	99.63 17	98.98 123	99.32 9	97.49 357	99.52 14	95.69 88	98.32 135	97.41 254	93.32 115	99.77 133	98.08 128	95.75 219	99.81 97

VNet		97.21 112	96.57 130	99.13 65	98.97 124	97.82 83	99.03 277	99.21 29	94.31 135	99.18 89	98.88 181	86.26 235	99.89 101	98.93 77	94.32 240	99.69 115

thres200		96.96 125	96.21 141	99.22 48	98.97 124	98.84 36	99.85 124	99.71 7	93.17 179	96.26 196	98.88 181	89.87 190	99.51 158	94.26 218	94.91 233	99.31 187

tfpn200view9		96.79 133	95.99 146	99.19 51	98.94 126	98.82 37	99.78 148	99.71 7	92.86 189	96.02 201	98.87 184	89.33 197	99.50 160	93.84 225	94.57 236	99.27 193

thres400		96.78 135	95.99 146	99.16 57	98.94 126	98.82 37	99.78 148	99.71 7	92.86 189	96.02 201	98.87 184	89.33 197	99.50 160	93.84 225	94.57 236	99.16 200

sasdasda		97.09 118	96.32 136	99.39 40	98.93 128	98.95 27	99.72 174	97.35 285	94.45 123	97.88 151	99.42 125	86.71 228	99.52 156	98.48 106	93.97 246	99.72 110

Anonymous20231211		89.86 318	88.44 325	94.13 292	98.93 128	90.68 305	98.54 323	98.26 187	76.28 396	86.73 336	95.54 316	70.60 360	97.56 286	90.82 275	80.27 355	94.15 311

canonicalmvs		97.09 118	96.32 136	99.39 40	98.93 128	98.95 27	99.72 174	97.35 285	94.45 123	97.88 151	99.42 125	86.71 228	99.52 156	98.48 106	93.97 246	99.72 110

SDMVSNet		94.80 197	93.96 211	97.33 191	98.92 131	95.42 183	99.59 199	98.99 37	92.41 216	92.55 249	97.85 245	75.81 331	98.93 196	97.90 138	91.62 261	97.64 252

sd_testset		93.55 236	92.83 239	95.74 236	98.92 131	90.89 301	98.24 339	98.85 56	92.41 216	92.55 249	97.85 245	71.07 359	98.68 214	93.93 222	91.62 261	97.64 252

EPNet_dtu		95.71 174	95.39 171	96.66 210	98.92 131	93.41 243	99.57 204	98.90 47	96.19 79	97.52 159	98.56 211	92.65 135	97.36 291	77.89 380	98.33 154	99.20 198
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WTY-MVS		98.10 66	97.60 82	99.60 22	98.92 131	99.28 17	99.89 104	99.52 14	95.58 91	98.24 140	99.39 132	93.33 114	99.74 139	97.98 134	95.58 222	99.78 103

CHOSEN 1792x2688		96.81 132	96.53 131	97.64 170	98.91 135	93.07 248	99.65 188	99.80 3	95.64 89	95.39 213	98.86 186	84.35 253	99.90 96	96.98 166	99.16 128	99.95 74

thres100view900		96.74 138	95.92 156	99.18 52	98.90 136	98.77 42	99.74 163	99.71 7	92.59 207	95.84 205	98.86 186	89.25 199	99.50 160	93.84 225	94.57 236	99.27 193

thres600view7		96.69 141	95.87 159	99.14 61	98.90 136	98.78 41	99.74 163	99.71 7	92.59 207	95.84 205	98.86 186	89.25 199	99.50 160	93.44 237	94.50 239	99.16 200

MSDG		94.37 215	93.36 230	97.40 185	98.88 138	93.95 228	99.37 236	97.38 282	85.75 351	90.80 266	99.17 151	84.11 255	99.88 107	86.35 329	98.43 152	98.36 238

MGCFI-Net		97.00 123	96.22 140	99.34 43	98.86 139	98.80 39	99.67 186	97.30 292	94.31 135	97.77 155	99.41 129	86.36 234	99.50 160	98.38 111	93.90 248	99.72 110

h-mvs33		94.92 194	94.36 199	96.59 212	98.85 140	91.29 293	98.93 288	98.94 41	95.90 82	98.77 110	98.42 222	90.89 175	99.77 133	97.80 142	70.76 391	98.72 229

Anonymous20240529		92.10 269	90.65 281	96.47 213	98.82 141	90.61 307	98.72 310	98.67 74	75.54 400	93.90 233	98.58 209	66.23 377	99.90 96	94.70 208	90.67 264	98.90 219

PVSNet_Blended_VisFu		97.27 108	96.81 118	98.66 99	98.81 142	96.67 130	99.92 82	98.64 77	94.51 122	96.38 194	98.49 215	89.05 203	99.88 107	97.10 162	98.34 153	99.43 171

PS-MVSNAJ		98.44 44	98.20 49	99.16 57	98.80 143	98.92 29	99.54 210	98.17 199	97.34 31	99.85 9	99.85 33	91.20 164	99.89 101	99.41 53	99.67 90	98.69 230

CANet_DTU		96.76 136	96.15 142	98.60 104	98.78 144	97.53 94	99.84 129	97.63 251	97.25 39	99.20 86	99.64 102	81.36 276	99.98 47	92.77 248	98.89 138	98.28 239

mvsany_test1		97.82 80	97.90 71	97.55 175	98.77 145	93.04 251	99.80 145	97.93 225	96.95 50	99.61 55	99.68 96	90.92 172	99.83 123	99.18 61	98.29 158	99.80 99

alignmvs		97.81 81	97.33 94	99.25 46	98.77 145	98.66 51	99.99 4	98.44 128	94.40 131	98.41 130	99.47 121	93.65 108	99.42 169	98.57 101	94.26 242	99.67 118

SteuartSystems-ACMMP		99.02 13	98.97 13	99.18 52	98.72 147	97.71 87	99.98 15	98.44 128	96.85 51	99.80 17	99.91 14	97.57 8	99.85 113	99.44 51	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
xiu_mvs_v2_base		98.23 62	97.97 64	99.02 76	98.69 148	98.66 51	99.52 212	98.08 212	97.05 45	99.86 7	99.86 29	90.65 177	99.71 143	99.39 55	98.63 147	98.69 230

miper_enhance_ethall		94.36 217	93.98 210	95.49 239	98.68 149	95.24 191	99.73 170	97.29 295	93.28 176	89.86 278	95.97 303	94.37 83	97.05 313	92.20 252	84.45 318	94.19 304

ETVMVS		97.03 122	96.64 126	98.20 135	98.67 150	97.12 114	99.89 104	98.57 91	91.10 258	98.17 142	98.59 206	93.86 103	98.19 256	95.64 188	95.24 230	99.28 192

test2506		97.53 95	97.19 101	98.58 107	98.66 151	96.90 123	98.81 303	99.77 5	94.93 105	97.95 147	98.96 170	92.51 141	99.20 179	94.93 198	98.15 162	99.64 124

ECVR-MVS		95.66 177	95.05 184	97.51 179	98.66 151	93.71 233	98.85 300	98.45 123	94.93 105	96.86 179	98.96 170	75.22 337	99.20 179	95.34 190	98.15 162	99.64 124

mamv4		95.24 187	96.90 112	90.25 358	98.65 153	72.11 405	98.28 337	97.64 250	89.99 284	95.93 203	98.25 229	94.74 68	99.11 185	99.01 74	99.64 92	99.53 155

balanced_conf03		98.27 56	97.99 62	99.11 66	98.64 154	98.43 62	99.47 221	97.79 239	94.56 120	99.74 32	98.35 224	94.33 86	99.25 173	99.12 63	99.96 46	99.64 124

fmvsm_s_conf0.5_n_a		97.73 89	97.72 76	97.77 162	98.63 155	94.26 219	99.96 36	98.92 46	97.18 41	99.75 29	99.69 90	87.00 226	99.97 57	99.46 49	98.89 138	99.08 209

MVSMamba_PlusPlus		97.83 77	97.45 88	98.99 78	98.60 156	98.15 65	99.58 201	97.74 243	90.34 277	99.26 85	98.32 227	94.29 88	99.23 174	99.03 72	99.89 70	99.58 143

testing222		97.08 121	96.75 121	98.06 144	98.56 157	96.82 125	99.85 124	98.61 83	92.53 211	98.84 105	98.84 190	93.36 112	98.30 246	95.84 185	94.30 241	99.05 211

test1111		95.57 179	94.98 187	97.37 187	98.56 157	93.37 245	98.86 298	98.45 123	94.95 104	96.63 185	98.95 175	75.21 338	99.11 185	95.02 195	98.14 164	99.64 124

MVSTER		95.53 180	95.22 177	96.45 215	98.56 157	97.72 86	99.91 89	97.67 248	92.38 218	91.39 259	97.14 261	97.24 18	97.30 297	94.80 204	87.85 293	94.34 294

VDD-MVS		93.77 229	92.94 237	96.27 222	98.55 160	90.22 316	98.77 307	97.79 239	90.85 264	96.82 181	99.42 125	61.18 396	99.77 133	98.95 75	94.13 243	98.82 222

tpmvs		94.28 219	93.57 221	96.40 217	98.55 160	91.50 291	95.70 391	98.55 100	87.47 326	92.15 252	94.26 366	91.42 160	98.95 195	88.15 308	95.85 215	98.76 225

UGNet		95.33 186	94.57 195	97.62 173	98.55 160	94.85 202	98.67 316	99.32 26	95.75 87	96.80 182	96.27 293	72.18 351	99.96 65	94.58 211	99.05 134	98.04 244
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	95.18 188	94.10 206	98.43 122	98.55 160	95.99 160	97.91 352	97.31 291	90.35 276	89.48 290	99.22 147	85.19 244	99.89 101	90.40 285	98.47 151	99.41 173
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS		96.79 133	96.72 123	97.00 198	98.51 164	93.70 234	99.71 177	98.60 85	92.96 185	97.09 172	98.34 226	96.67 31	98.85 199	92.11 254	96.50 199	98.44 235

test_vis1_n_1920		95.44 182	95.31 174	95.82 234	98.50 165	88.74 336	99.98 15	97.30 292	97.84 18	99.85 9	99.19 149	66.82 375	99.97 57	98.82 85	99.46 112	98.76 225

BH-w/o		95.71 174	95.38 172	96.68 209	98.49 166	92.28 268	99.84 129	97.50 271	92.12 224	92.06 255	98.79 191	84.69 249	98.67 215	95.29 192	99.66 91	99.09 207

baseline1		95.78 171	94.86 189	98.54 112	98.47 167	98.07 71	99.06 270	97.99 218	92.68 201	94.13 230	98.62 205	93.28 118	98.69 213	93.79 230	85.76 306	98.84 221

EPMVS		96.53 147	96.01 145	98.09 142	98.43 168	96.12 158	96.36 378	99.43 20	93.53 167	97.64 157	95.04 343	94.41 78	98.38 238	91.13 266	98.11 165	99.75 106

kuosan		93.17 244	92.60 245	94.86 263	98.40 169	89.54 328	98.44 328	98.53 106	84.46 364	88.49 310	97.92 242	90.57 179	97.05 313	83.10 352	93.49 251	97.99 245

WBMVS		94.52 210	94.03 208	95.98 228	98.38 170	96.68 129	99.92 82	97.63 251	90.75 269	89.64 286	95.25 337	96.77 25	96.90 324	94.35 216	83.57 325	94.35 292

UBG		97.84 76	97.69 78	98.29 131	98.38 170	96.59 135	99.90 95	98.53 106	93.91 157	98.52 123	98.42 222	96.77 25	99.17 182	98.54 103	96.20 204	99.11 206

sss		97.57 94	97.03 108	99.18 52	98.37 172	98.04 73	99.73 170	99.38 22	93.46 169	98.76 113	99.06 157	91.21 163	99.89 101	96.33 176	97.01 191	99.62 130

testing11		97.48 97	97.27 97	98.10 141	98.36 173	96.02 159	99.92 82	98.45 123	93.45 171	98.15 143	98.70 196	95.48 49	99.22 175	97.85 140	95.05 232	99.07 210

BH-untuned		95.18 188	94.83 190	96.22 223	98.36 173	91.22 294	99.80 145	97.32 290	90.91 262	91.08 262	98.67 198	83.51 257	98.54 221	94.23 219	99.61 99	98.92 216

testing91		97.16 114	96.90 112	97.97 147	98.35 175	95.67 174	99.91 89	98.42 148	92.91 188	97.33 166	98.72 194	94.81 66	99.21 176	96.98 166	94.63 235	99.03 212

testing99		97.17 113	96.91 111	97.95 148	98.35 175	95.70 171	99.91 89	98.43 136	92.94 186	97.36 165	98.72 194	94.83 65	99.21 176	97.00 164	94.64 234	98.95 215

ET-MVSNet_ETH3D		94.37 215	93.28 232	97.64 170	98.30 177	97.99 75	99.99 4	97.61 257	94.35 132	71.57 403	99.45 124	96.23 35	95.34 373	96.91 171	85.14 313	99.59 137

AUN-MVS		93.28 241	92.60 245	95.34 246	98.29 178	90.09 319	99.31 243	98.56 94	91.80 236	96.35 195	98.00 237	89.38 196	98.28 249	92.46 249	69.22 396	97.64 252

FMVSNet3		92.69 257	91.58 266	95.99 227	98.29 178	97.42 102	99.26 252	97.62 254	89.80 287	89.68 282	95.32 331	81.62 274	96.27 352	87.01 325	85.65 307	94.29 296

PMMVS		96.76 136	96.76 120	96.76 206	98.28 180	92.10 272	99.91 89	97.98 220	94.12 143	99.53 60	99.39 132	86.93 227	98.73 208	96.95 169	97.73 172	99.45 168

hse-mvs2		94.38 214	94.08 207	95.31 248	98.27 181	90.02 320	99.29 248	98.56 94	95.90 82	98.77 110	98.00 237	90.89 175	98.26 253	97.80 142	69.20 397	97.64 252

PVSNet_0	88.03 19	91.80 276	90.27 290	96.38 219	98.27 181	90.46 311	99.94 72	99.61 13	93.99 151	86.26 346	97.39 256	71.13 358	99.89 101	98.77 89	67.05 402	98.79 224

UA-Net		96.54 146	95.96 152	98.27 132	98.23 183	95.71 170	98.00 350	98.45 123	93.72 164	98.41 130	99.27 141	88.71 208	99.66 151	91.19 265	97.69 173	99.44 170

test_cas_vis1_n_1920		96.59 145	96.23 139	97.65 169	98.22 184	94.23 220	99.99 4	97.25 299	97.77 19	99.58 56	99.08 155	77.10 314	99.97 57	97.64 150	99.45 113	98.74 227

FE-MVS		95.70 176	95.01 186	97.79 159	98.21 185	94.57 208	95.03 392	98.69 69	88.90 303	97.50 161	96.19 295	92.60 138	99.49 165	89.99 290	97.94 171	99.31 187

GG-mvs-BLEND				98.54 112	98.21 185	98.01 74	93.87 397	98.52 108		97.92 148	97.92 242	99.02 3	97.94 273	98.17 121	99.58 102	99.67 118

mvs_anonymous		95.65 178	95.03 185	97.53 177	98.19 187	95.74 168	99.33 240	97.49 272	90.87 263	90.47 269	97.10 263	88.23 211	97.16 304	95.92 183	97.66 175	99.68 116

MVS_Test		96.46 149	95.74 161	98.61 103	98.18 188	97.23 108	99.31 243	97.15 308	91.07 259	98.84 105	97.05 267	88.17 212	98.97 192	94.39 213	97.50 177	99.61 134

BH-RMVSNet		95.18 188	94.31 202	97.80 157	98.17 189	95.23 192	99.76 156	97.53 267	92.52 212	94.27 228	99.25 145	76.84 319	98.80 201	90.89 274	99.54 104	99.35 182

dongtai		91.55 282	91.13 275	92.82 331	98.16 190	86.35 359	99.47 221	98.51 111	83.24 372	85.07 355	97.56 250	90.33 184	94.94 379	76.09 388	91.73 259	97.18 261

RPSCF		91.80 276	92.79 241	88.83 369	98.15 191	69.87 407	98.11 346	96.60 356	83.93 367	94.33 226	99.27 141	79.60 297	99.46 168	91.99 255	93.16 256	97.18 261

ETV-MVS		97.92 71	97.80 75	98.25 133	98.14 192	96.48 137	99.98 15	97.63 251	95.61 90	99.29 83	99.46 123	92.55 140	98.82 200	99.02 73	98.54 149	99.46 166

IS-MVSNet		96.29 159	95.90 157	97.45 181	98.13 193	94.80 205	99.08 265	97.61 257	92.02 229	95.54 212	98.96 170	90.64 178	98.08 262	93.73 233	97.41 181	99.47 165

test_fmvsmconf_n		98.43 46	98.32 43	98.78 90	98.12 194	96.41 140	99.99 4	98.83 60	98.22 7	99.67 40	99.64 102	91.11 168	99.94 81	99.67 40	99.62 95	99.98 51

fmvsm_s_conf0.1_n_2		97.25 109	96.85 116	98.43 122	98.08 195	98.08 70	99.92 82	97.76 242	98.05 13	99.65 42	99.58 111	80.88 283	99.93 89	99.59 42	98.17 160	97.29 259

ab-mvs		94.69 202	93.42 226	98.51 116	98.07 196	96.26 147	96.49 376	98.68 71	90.31 278	94.54 221	97.00 269	76.30 326	99.71 143	95.98 182	93.38 254	99.56 146

XVG-OURS-SEG-HR		94.79 198	94.70 194	95.08 253	98.05 197	89.19 330	99.08 265	97.54 265	93.66 165	94.87 219	99.58 111	78.78 305	99.79 128	97.31 156	93.40 253	96.25 268

EIA-MVS		97.53 95	97.46 87	97.76 164	98.04 198	94.84 203	99.98 15	97.61 257	94.41 130	97.90 149	99.59 108	92.40 145	98.87 197	98.04 129	99.13 130	99.59 137

XVG-OURS		94.82 195	94.74 193	95.06 254	98.00 199	89.19 330	99.08 265	97.55 263	94.10 144	94.71 220	99.62 106	80.51 289	99.74 139	96.04 181	93.06 258	96.25 268

mvsmamba		96.94 126	96.73 122	97.55 175	97.99 200	94.37 216	99.62 195	97.70 245	93.13 181	98.42 129	97.92 242	88.02 213	98.75 207	98.78 88	99.01 135	99.52 157

dp		95.05 191	94.43 197	96.91 201	97.99 200	92.73 258	96.29 381	97.98 220	89.70 288	95.93 203	94.67 356	93.83 105	98.45 227	86.91 328	96.53 198	99.54 151

tpmrst		96.27 161	95.98 148	97.13 195	97.96 202	93.15 247	96.34 379	98.17 199	92.07 225	98.71 116	95.12 340	93.91 100	98.73 208	94.91 201	96.62 196	99.50 162

TR-MVS		94.54 207	93.56 222	97.49 180	97.96 202	94.34 217	98.71 311	97.51 270	90.30 279	94.51 223	98.69 197	75.56 332	98.77 204	92.82 247	95.99 209	99.35 182

Vis-MVSNet (Re-imp)		96.32 156	95.98 148	97.35 190	97.93 204	94.82 204	99.47 221	98.15 207	91.83 233	95.09 217	99.11 153	91.37 162	97.47 289	93.47 236	97.43 178	99.74 107

MDTV_nov1_ep13			95.69 163		97.90 205	94.15 222	95.98 387	98.44 128	93.12 182	97.98 146	95.74 307	95.10 55	98.58 218	90.02 289	96.92 193

Fast-Effi-MVS+		95.02 192	94.19 204	97.52 178	97.88 206	94.55 209	99.97 29	97.08 317	88.85 305	94.47 224	97.96 241	84.59 250	98.41 230	89.84 292	97.10 186	99.59 137

ADS-MVSNet2		93.80 228	93.88 214	93.55 314	97.87 207	85.94 362	94.24 393	96.84 342	90.07 281	96.43 191	94.48 361	90.29 186	95.37 372	87.44 315	97.23 183	99.36 179

ADS-MVSNet		94.79 198	94.02 209	97.11 197	97.87 207	93.79 230	94.24 393	98.16 204	90.07 281	96.43 191	94.48 361	90.29 186	98.19 256	87.44 315	97.23 183	99.36 179

Effi-MVS+		96.30 158	95.69 163	98.16 136	97.85 209	96.26 147	97.41 359	97.21 301	90.37 275	98.65 119	98.58 209	86.61 231	98.70 212	97.11 161	97.37 182	99.52 157

PatchmatchNet		95.94 167	95.45 169	97.39 186	97.83 210	94.41 213	96.05 385	98.40 157	92.86 189	97.09 172	95.28 336	94.21 92	98.07 264	89.26 296	98.11 165	99.70 113
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
cascas		94.64 205	93.61 217	97.74 166	97.82 211	96.26 147	99.96 36	97.78 241	85.76 349	94.00 231	97.54 251	76.95 318	99.21 176	97.23 158	95.43 225	97.76 251

1112_ss		96.01 166	95.20 178	98.42 124	97.80 212	96.41 140	99.65 188	96.66 353	92.71 198	92.88 245	99.40 130	92.16 150	99.30 171	91.92 257	93.66 249	99.55 147

Test_1112_low_res		95.72 172	94.83 190	98.42 124	97.79 213	96.41 140	99.65 188	96.65 354	92.70 199	92.86 246	96.13 298	92.15 151	99.30 171	91.88 258	93.64 250	99.55 147

Effi-MVS+-dtu		94.53 209	95.30 175	92.22 337	97.77 214	82.54 381	99.59 199	97.06 319	94.92 107	95.29 215	95.37 329	85.81 237	97.89 274	94.80 204	97.07 187	96.23 270

tpm cat1		93.51 237	92.52 251	96.47 213	97.77 214	91.47 292	96.13 383	98.06 213	80.98 385	92.91 244	93.78 370	89.66 191	98.87 197	87.03 324	96.39 202	99.09 207

FA-MVS(test-final)		95.86 168	95.09 182	98.15 139	97.74 216	95.62 176	96.31 380	98.17 199	91.42 249	96.26 196	96.13 298	90.56 180	99.47 167	92.18 253	97.07 187	99.35 182

xiu_mvs_v1_base_debu		97.43 98	97.06 104	98.55 109	97.74 216	98.14 67	99.31 243	97.86 234	96.43 68	99.62 49	99.69 90	85.56 239	99.68 147	99.05 66	98.31 155	97.83 247

xiu_mvs_v1_base		97.43 98	97.06 104	98.55 109	97.74 216	98.14 67	99.31 243	97.86 234	96.43 68	99.62 49	99.69 90	85.56 239	99.68 147	99.05 66	98.31 155	97.83 247

xiu_mvs_v1_base_debi		97.43 98	97.06 104	98.55 109	97.74 216	98.14 67	99.31 243	97.86 234	96.43 68	99.62 49	99.69 90	85.56 239	99.68 147	99.05 66	98.31 155	97.83 247

EPP-MVSNet		96.69 141	96.60 128	96.96 200	97.74 216	93.05 250	99.37 236	98.56 94	88.75 307	95.83 207	99.01 161	96.01 36	98.56 219	96.92 170	97.20 185	99.25 195

gg-mvs-nofinetune		93.51 237	91.86 263	98.47 118	97.72 221	97.96 79	92.62 401	98.51 111	74.70 403	97.33 166	69.59 417	98.91 4	97.79 277	97.77 147	99.56 103	99.67 118

IB-MVS	92.85 6	94.99 193	93.94 212	98.16 136	97.72 221	95.69 173	99.99 4	98.81 61	94.28 138	92.70 247	96.90 271	95.08 56	99.17 182	96.07 180	73.88 385	99.60 136
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		97.41 103	97.02 109	98.59 106	97.71 223	97.52 95	99.97 29	98.54 103	91.83 233	97.45 162	99.04 158	97.50 9	99.10 187	94.75 206	96.37 203	99.16 200

Syy-MVS		90.00 316	90.63 282	88.11 376	97.68 224	74.66 403	99.71 177	98.35 170	90.79 266	92.10 253	98.67 198	79.10 303	93.09 396	63.35 410	95.95 212	96.59 266

myMVS_eth3d		94.46 212	94.76 192	93.55 314	97.68 224	90.97 296	99.71 177	98.35 170	90.79 266	92.10 253	98.67 198	92.46 144	93.09 396	87.13 321	95.95 212	96.59 266

test_fmvs1_n		94.25 220	94.36 199	93.92 301	97.68 224	83.70 375	99.90 95	96.57 357	97.40 30	99.67 40	98.88 181	61.82 393	99.92 93	98.23 119	99.13 130	98.14 243

RRT-MVS		96.24 162	95.68 165	97.94 151	97.65 227	94.92 201	99.27 251	97.10 313	92.79 195	97.43 163	97.99 239	81.85 269	99.37 170	98.46 108	98.57 148	99.53 155

diffmvs		97.00 123	96.64 126	98.09 142	97.64 228	96.17 155	99.81 141	97.19 302	94.67 118	98.95 100	99.28 138	86.43 232	98.76 205	98.37 113	97.42 180	99.33 185
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Vis-MVSNet		95.72 172	95.15 180	97.45 181	97.62 229	94.28 218	99.28 249	98.24 190	94.27 140	96.84 180	98.94 177	79.39 298	98.76 205	93.25 238	98.49 150	99.30 189
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
thisisatest0530		97.10 116	96.72 123	98.22 134	97.60 230	96.70 128	99.92 82	98.54 103	91.11 257	97.07 174	98.97 168	97.47 12	99.03 190	93.73 233	96.09 207	98.92 216

GDP-MVS		97.88 72	97.59 84	98.75 93	97.59 231	97.81 84	99.95 55	97.37 284	94.44 126	99.08 94	99.58 111	97.13 23	99.08 188	94.99 196	98.17 160	99.37 177

miper_ehance_all_eth		93.16 245	92.60 245	94.82 264	97.57 232	93.56 238	99.50 216	97.07 318	88.75 307	88.85 305	95.52 318	90.97 171	96.74 333	90.77 276	84.45 318	94.17 305

testing3		93.92 223	94.23 203	92.99 328	97.54 233	90.23 315	99.99 4	99.16 30	90.57 271	91.33 261	98.63 204	92.99 126	92.52 400	82.46 356	95.39 226	96.22 271

LCM-MVSNet-Re		92.31 265	92.60 245	91.43 346	97.53 234	79.27 398	99.02 279	91.83 413	92.07 225	80.31 378	94.38 364	83.50 258	95.48 370	97.22 159	97.58 176	99.54 151

GBi-Net		90.88 293	89.82 299	94.08 293	97.53 234	91.97 273	98.43 329	96.95 331	87.05 332	89.68 282	94.72 352	71.34 355	96.11 357	87.01 325	85.65 307	94.17 305

test1		90.88 293	89.82 299	94.08 293	97.53 234	91.97 273	98.43 329	96.95 331	87.05 332	89.68 282	94.72 352	71.34 355	96.11 357	87.01 325	85.65 307	94.17 305

FMVSNet2		91.02 290	89.56 304	95.41 244	97.53 234	95.74 168	98.98 281	97.41 280	87.05 332	88.43 314	95.00 346	71.34 355	96.24 354	85.12 339	85.21 312	94.25 299

tttt0517		96.85 130	96.49 132	97.92 152	97.48 238	95.89 163	99.85 124	98.54 103	90.72 270	96.63 185	98.93 179	97.47 12	99.02 191	93.03 245	95.76 218	98.85 220

BP-MVS1		98.33 52	98.18 51	98.81 89	97.44 239	97.98 76	99.96 36	98.17 199	94.88 109	98.77 110	99.59 108	97.59 7	99.08 188	98.24 118	98.93 137	99.36 179

casdiffmvs_mvg		96.43 150	95.94 154	97.89 156	97.44 239	95.47 180	99.86 121	97.29 295	93.35 172	96.03 200	99.19 149	85.39 242	98.72 210	97.89 139	97.04 189	99.49 164
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		97.38 105	97.24 98	97.80 157	97.41 241	95.64 175	99.99 4	97.06 319	94.59 119	99.63 46	99.32 137	89.20 202	98.14 258	98.76 90	99.23 126	99.62 130

c3_l		92.53 260	91.87 262	94.52 276	97.40 242	92.99 252	99.40 229	96.93 336	87.86 322	88.69 308	95.44 323	89.95 189	96.44 345	90.45 282	80.69 351	94.14 314

fmvsm_s_conf0.1_n		97.30 106	97.21 100	97.60 174	97.38 243	94.40 215	99.90 95	98.64 77	96.47 67	99.51 64	99.65 101	84.99 247	99.93 89	99.22 60	99.09 132	98.46 234

CDS-MVSNet		96.34 155	96.07 143	97.13 195	97.37 244	94.96 199	99.53 211	97.91 229	91.55 241	95.37 214	98.32 227	95.05 58	97.13 307	93.80 229	95.75 219	99.30 189
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TESTMET0.1,1		96.74 138	96.26 138	98.16 136	97.36 245	96.48 137	99.96 36	98.29 183	91.93 230	95.77 208	98.07 235	95.54 46	98.29 247	90.55 280	98.89 138	99.70 113

miper_lstm_enhance		91.81 273	91.39 272	93.06 327	97.34 246	89.18 332	99.38 234	96.79 347	86.70 339	87.47 328	95.22 338	90.00 188	95.86 366	88.26 306	81.37 340	94.15 311

baseline		96.43 150	95.98 148	97.76 164	97.34 246	95.17 196	99.51 214	97.17 305	93.92 156	96.90 178	99.28 138	85.37 243	98.64 216	97.50 153	96.86 195	99.46 166

cl____		92.31 265	91.58 266	94.52 276	97.33 248	92.77 254	99.57 204	96.78 348	86.97 336	87.56 326	95.51 319	89.43 195	96.62 338	88.60 301	82.44 332	94.16 310

DIV-MVS_self_test		92.32 264	91.60 265	94.47 280	97.31 249	92.74 256	99.58 201	96.75 349	86.99 335	87.64 324	95.54 316	89.55 194	96.50 342	88.58 302	82.44 332	94.17 305

casdiffmvs		96.42 152	95.97 151	97.77 162	97.30 250	94.98 198	99.84 129	97.09 316	93.75 163	96.58 187	99.26 144	85.07 245	98.78 203	97.77 147	97.04 189	99.54 151
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		94.36 217	93.48 224	96.99 199	97.29 251	93.54 239	99.96 36	96.72 351	88.35 316	93.43 235	98.94 177	82.05 266	98.05 265	88.12 310	96.48 201	99.37 177

eth_miper_zixun_eth		92.41 263	91.93 260	93.84 305	97.28 252	90.68 305	98.83 301	96.97 330	88.57 312	89.19 300	95.73 309	89.24 201	96.69 336	89.97 291	81.55 338	94.15 311

MVSFormer		96.94 126	96.60 128	97.95 148	97.28 252	97.70 89	99.55 208	97.27 297	91.17 254	99.43 70	99.54 117	90.92 172	96.89 325	94.67 209	99.62 95	99.25 195

lupinMVS		97.85 75	97.60 82	98.62 102	97.28 252	97.70 89	99.99 4	97.55 263	95.50 95	99.43 70	99.67 97	90.92 172	98.71 211	98.40 110	99.62 95	99.45 168

SCA		94.69 202	93.81 216	97.33 191	97.10 255	94.44 210	98.86 298	98.32 177	93.30 175	96.17 199	95.59 314	76.48 324	97.95 271	91.06 268	97.43 178	99.59 137

TAMVS		95.85 169	95.58 167	96.65 211	97.07 256	93.50 240	99.17 259	97.82 238	91.39 251	95.02 218	98.01 236	92.20 149	97.30 297	93.75 232	95.83 216	99.14 203

Fast-Effi-MVS+-dtu		93.72 232	93.86 215	93.29 319	97.06 257	86.16 360	99.80 145	96.83 343	92.66 202	92.58 248	97.83 247	81.39 275	97.67 282	89.75 293	96.87 194	96.05 273

CostFormer		96.10 163	95.88 158	96.78 205	97.03 258	92.55 264	97.08 367	97.83 237	90.04 283	98.72 115	94.89 350	95.01 60	98.29 247	96.54 175	95.77 217	99.50 162

test_fmvsmvis_n_1920		97.67 91	97.59 84	97.91 154	97.02 259	95.34 186	99.95 55	98.45 123	97.87 17	97.02 175	99.59 108	89.64 192	99.98 47	99.41 53	99.34 121	98.42 236

test-LLR		96.47 148	96.04 144	97.78 160	97.02 259	95.44 181	99.96 36	98.21 194	94.07 146	95.55 210	96.38 288	93.90 101	98.27 251	90.42 283	98.83 142	99.64 124

test-mter		96.39 153	95.93 155	97.78 160	97.02 259	95.44 181	99.96 36	98.21 194	91.81 235	95.55 210	96.38 288	95.17 53	98.27 251	90.42 283	98.83 142	99.64 124

gm-plane-assit					96.97 262	93.76 232			91.47 245		98.96 170		98.79 202	94.92 199

WB-MVSnew		92.90 251	92.77 242	93.26 321	96.95 263	93.63 236	99.71 177	98.16 204	91.49 242	94.28 227	98.14 232	81.33 277	96.48 343	79.47 371	95.46 223	89.68 397

QAPM		95.40 183	94.17 205	99.10 67	96.92 264	97.71 87	99.40 229	98.68 71	89.31 291	88.94 304	98.89 180	82.48 264	99.96 65	93.12 244	99.83 77	99.62 130

KD-MVS_2432*1600		88.00 337	86.10 341	93.70 310	96.91 265	94.04 224	97.17 364	97.12 311	84.93 359	81.96 369	92.41 381	92.48 142	94.51 384	79.23 372	52.68 416	92.56 367

miper_refine_blended		88.00 337	86.10 341	93.70 310	96.91 265	94.04 224	97.17 364	97.12 311	84.93 359	81.96 369	92.41 381	92.48 142	94.51 384	79.23 372	52.68 416	92.56 367

tpm2		95.47 181	95.18 179	96.35 220	96.91 265	91.70 286	96.96 370	97.93 225	88.04 320	98.44 128	95.40 325	93.32 115	97.97 268	94.00 221	95.61 221	99.38 175

FMVSNet5		88.32 333	87.47 335	90.88 349	96.90 268	88.39 344	97.28 361	95.68 377	82.60 379	84.67 357	92.40 383	79.83 295	91.16 405	76.39 387	81.51 339	93.09 359

3Dnovator+	91.53 11	96.31 157	95.24 176	99.52 28	96.88 269	98.64 54	99.72 174	98.24 190	95.27 100	88.42 316	98.98 166	82.76 263	99.94 81	97.10 162	99.83 77	99.96 67

Patchmatch-test		92.65 259	91.50 269	96.10 226	96.85 270	90.49 310	91.50 406	97.19 302	82.76 378	90.23 270	95.59 314	95.02 59	98.00 267	77.41 382	96.98 192	99.82 95

MVS		96.60 144	95.56 168	99.72 13	96.85 270	99.22 20	98.31 335	98.94 41	91.57 240	90.90 265	99.61 107	86.66 230	99.96 65	97.36 155	99.88 73	99.99 23

3Dnovator	91.47 12	96.28 160	95.34 173	99.08 70	96.82 272	97.47 100	99.45 226	98.81 61	95.52 94	89.39 291	99.00 163	81.97 267	99.95 73	97.27 157	99.83 77	99.84 93

EI-MVSNet		93.73 231	93.40 229	94.74 265	96.80 273	92.69 259	99.06 270	97.67 248	88.96 300	91.39 259	99.02 159	88.75 207	97.30 297	91.07 267	87.85 293	94.22 301

CVMVSNet		94.68 204	94.94 188	93.89 304	96.80 273	86.92 357	99.06 270	98.98 38	94.45 123	94.23 229	99.02 159	85.60 238	95.31 374	90.91 273	95.39 226	99.43 171

IterMVS-LS		92.69 257	92.11 256	94.43 284	96.80 273	92.74 256	99.45 226	96.89 339	88.98 298	89.65 285	95.38 328	88.77 206	96.34 349	90.98 271	82.04 335	94.22 301
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS		90.91 292	90.17 294	93.12 324	96.78 276	90.42 313	98.89 292	97.05 322	89.03 295	86.49 341	95.42 324	76.59 322	95.02 376	87.22 320	84.09 321	93.93 331
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
1314		96.84 131	95.96 152	99.48 34	96.74 277	98.52 58	98.31 335	98.86 53	95.82 84	89.91 276	98.98 166	87.49 218	99.96 65	97.80 142	99.73 87	99.96 67

IterMVS-SCA-FT		90.85 295	90.16 295	92.93 329	96.72 278	89.96 321	98.89 292	96.99 326	88.95 301	86.63 338	95.67 310	76.48 324	95.00 377	87.04 323	84.04 324	93.84 338

MVS-HIRNet		86.22 344	83.19 357	95.31 248	96.71 279	90.29 314	92.12 403	97.33 289	62.85 411	86.82 335	70.37 416	69.37 363	97.49 288	75.12 390	97.99 170	98.15 241

VDDNet		93.12 246	91.91 261	96.76 206	96.67 280	92.65 262	98.69 314	98.21 194	82.81 377	97.75 156	99.28 138	61.57 394	99.48 166	98.09 127	94.09 244	98.15 241

dmvs_re		93.20 243	93.15 234	93.34 317	96.54 281	83.81 374	98.71 311	98.51 111	91.39 251	92.37 251	98.56 211	78.66 307	97.83 276	93.89 223	89.74 265	98.38 237

MIMVSNet		90.30 308	88.67 322	95.17 252	96.45 282	91.64 288	92.39 402	97.15 308	85.99 346	90.50 268	93.19 377	66.95 374	94.86 381	82.01 360	93.43 252	99.01 214

CR-MVSNet		93.45 240	92.62 244	95.94 230	96.29 283	92.66 260	92.01 404	96.23 365	92.62 204	96.94 176	93.31 375	91.04 169	96.03 362	79.23 372	95.96 210	99.13 204

RPMNet		89.76 320	87.28 336	97.19 194	96.29 283	92.66 260	92.01 404	98.31 179	70.19 410	96.94 176	85.87 409	87.25 222	99.78 130	62.69 411	95.96 210	99.13 204

tt0805		91.28 285	90.18 293	94.60 271	96.26 285	87.55 350	98.39 333	98.72 66	89.00 297	89.22 297	98.47 219	62.98 389	98.96 194	90.57 279	88.00 292	97.28 260

Patchmtry		89.70 321	88.49 324	93.33 318	96.24 286	89.94 324	91.37 407	96.23 365	78.22 393	87.69 323	93.31 375	91.04 169	96.03 362	80.18 370	82.10 334	94.02 321

test_vis1_rt		86.87 342	86.05 344	89.34 365	96.12 287	78.07 399	99.87 110	83.54 424	92.03 228	78.21 388	89.51 395	45.80 410	99.91 94	96.25 178	93.11 257	90.03 394

JIA-IIPM		91.76 279	90.70 280	94.94 258	96.11 288	87.51 351	93.16 400	98.13 209	75.79 399	97.58 158	77.68 414	92.84 131	97.97 268	88.47 305	96.54 197	99.33 185

OpenMVS	90.15 15	94.77 200	93.59 220	98.33 128	96.07 289	97.48 99	99.56 206	98.57 91	90.46 273	86.51 340	98.95 175	78.57 308	99.94 81	93.86 224	99.74 86	97.57 256

PAPM		98.60 33	98.42 34	99.14 61	96.05 290	98.96 26	99.90 95	99.35 24	96.68 60	98.35 134	99.66 99	96.45 33	98.51 222	99.45 50	99.89 70	99.96 67

CLD-MVS		94.06 222	93.90 213	94.55 275	96.02 291	90.69 304	99.98 15	97.72 244	96.62 64	91.05 264	98.85 189	77.21 313	98.47 223	98.11 125	89.51 271	94.48 280
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PatchT		90.38 305	88.75 321	95.25 250	95.99 292	90.16 317	91.22 408	97.54 265	76.80 395	97.26 168	86.01 408	91.88 156	96.07 361	66.16 407	95.91 214	99.51 160

ACMH+	89.98 16	90.35 306	89.54 305	92.78 333	95.99 292	86.12 361	98.81 303	97.18 304	89.38 290	83.14 365	97.76 248	68.42 368	98.43 228	89.11 297	86.05 305	93.78 341

DeepMVS_CX				82.92 386	95.98 294	58.66 417		96.01 370	92.72 197	78.34 387	95.51 319	58.29 399	98.08 262	82.57 355	85.29 310	92.03 375

ACMP	92.05 9	92.74 255	92.42 253	93.73 306	95.91 295	88.72 337	99.81 141	97.53 267	94.13 142	87.00 334	98.23 230	74.07 345	98.47 223	96.22 179	88.86 278	93.99 326
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n		93.61 235	93.03 236	95.35 245	95.86 296	86.94 356	99.87 110	96.36 363	96.85 51	99.54 59	98.79 191	52.41 406	99.83 123	98.64 98	98.97 136	99.29 191

HQP-NCC					95.78 297		99.87 110		96.82 53	93.37 236

ACMP_Plane					95.78 297		99.87 110		96.82 53	93.37 236

HQP-MVS		94.61 206	94.50 196	94.92 259	95.78 297	91.85 278	99.87 110	97.89 230	96.82 53	93.37 236	98.65 201	80.65 287	98.39 234	97.92 136	89.60 266	94.53 276

NP-MVS					95.77 300	91.79 280					98.65 201

test_fmvsmconf0.1_n		97.74 87	97.44 89	98.64 101	95.76 301	96.20 152	99.94 72	98.05 215	98.17 9	98.89 104	99.42 125	87.65 216	99.90 96	99.50 46	99.60 101	99.82 95

plane_prior6					95.76 301	91.72 285						80.47 291

ACMM	91.95 10	92.88 252	92.52 251	93.98 300	95.75 303	89.08 334	99.77 151	97.52 269	93.00 184	89.95 275	97.99 239	76.17 328	98.46 226	93.63 235	88.87 277	94.39 288
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GA-MVS		93.83 225	92.84 238	96.80 204	95.73 304	93.57 237	99.88 107	97.24 300	92.57 209	92.92 243	96.66 280	78.73 306	97.67 282	87.75 313	94.06 245	99.17 199

plane_prior1					95.73 304

jason		97.24 110	96.86 115	98.38 127	95.73 304	97.32 104	99.97 29	97.40 281	95.34 98	98.60 122	99.54 117	87.70 215	98.56 219	97.94 135	99.47 110	99.25 195
jason: jason.
mmtdpeth		88.52 331	87.75 333	90.85 351	95.71 307	83.47 377	98.94 286	94.85 391	88.78 306	97.19 170	89.58 394	63.29 387	98.97 192	98.54 103	62.86 410	90.10 393

HQP_MVS		94.49 211	94.36 199	94.87 260	95.71 307	91.74 282	99.84 129	97.87 232	96.38 71	93.01 241	98.59 206	80.47 291	98.37 240	97.79 145	89.55 269	94.52 278

plane_prior7					95.71 307	91.59 290

ITE_SJBPF				92.38 335	95.69 310	85.14 366		95.71 376	92.81 192	89.33 294	98.11 233	70.23 361	98.42 229	85.91 335	88.16 290	93.59 349

fmvsm_s_conf0.1_n_a		97.09 118	96.90 112	97.63 172	95.65 311	94.21 221	99.83 136	98.50 117	96.27 76	99.65 42	99.64 102	84.72 248	99.93 89	99.04 69	98.84 141	98.74 227

ACMH	89.72 17	90.64 299	89.63 302	93.66 312	95.64 312	88.64 340	98.55 321	97.45 274	89.03 295	81.62 372	97.61 249	69.75 362	98.41 230	89.37 294	87.62 297	93.92 332
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline2		96.71 140	96.49 132	97.37 187	95.63 313	95.96 161	99.74 163	98.88 51	92.94 186	91.61 257	98.97 168	97.72 6	98.62 217	94.83 203	98.08 168	97.53 257

FMVSNet1		88.50 332	86.64 339	94.08 293	95.62 314	91.97 273	98.43 329	96.95 331	83.00 375	86.08 348	94.72 352	59.09 398	96.11 357	81.82 362	84.07 322	94.17 305

LPG-MVS_test		92.96 249	92.71 243	93.71 308	95.43 315	88.67 338	99.75 160	97.62 254	92.81 192	90.05 271	98.49 215	75.24 335	98.40 232	95.84 185	89.12 273	94.07 318

LGP-MVS_train				93.71 308	95.43 315	88.67 338		97.62 254	92.81 192	90.05 271	98.49 215	75.24 335	98.40 232	95.84 185	89.12 273	94.07 318

tpm		93.70 233	93.41 228	94.58 273	95.36 317	87.41 352	97.01 368	96.90 338	90.85 264	96.72 184	94.14 367	90.40 183	96.84 328	90.75 277	88.54 285	99.51 160

D2MVS		92.76 254	92.59 249	93.27 320	95.13 318	89.54 328	99.69 182	99.38 22	92.26 221	87.59 325	94.61 358	85.05 246	97.79 277	91.59 261	88.01 291	92.47 370

VPA-MVSNet		92.70 256	91.55 268	96.16 224	95.09 319	96.20 152	98.88 294	99.00 36	91.02 261	91.82 256	95.29 335	76.05 330	97.96 270	95.62 189	81.19 341	94.30 295

LTVRE_ROB	88.28 18	90.29 309	89.05 316	94.02 296	95.08 320	90.15 318	97.19 363	97.43 276	84.91 361	83.99 361	97.06 266	74.00 346	98.28 249	84.08 344	87.71 295	93.62 348
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		87.87 339	86.51 340	91.94 340	95.05 321	85.57 364	97.65 356	94.08 400	84.40 365	81.82 371	96.85 275	62.14 392	98.33 243	80.25 369	86.37 304	91.91 377

test0.0.03 1		93.86 224	93.61 217	94.64 269	95.02 322	92.18 271	99.93 79	98.58 89	94.07 146	87.96 320	98.50 214	93.90 101	94.96 378	81.33 363	93.17 255	96.78 263

UniMVSNet (Re)		93.07 248	92.13 255	95.88 231	94.84 323	96.24 151	99.88 107	98.98 38	92.49 214	89.25 295	95.40 325	87.09 224	97.14 306	93.13 243	78.16 365	94.26 297

USDC		90.00 316	88.96 317	93.10 326	94.81 324	88.16 346	98.71 311	95.54 381	93.66 165	83.75 363	97.20 260	65.58 379	98.31 245	83.96 347	87.49 299	92.85 364

VPNet		91.81 273	90.46 284	95.85 233	94.74 325	95.54 179	98.98 281	98.59 87	92.14 223	90.77 267	97.44 253	68.73 366	97.54 287	94.89 202	77.89 367	94.46 281

FIs		94.10 221	93.43 225	96.11 225	94.70 326	96.82 125	99.58 201	98.93 45	92.54 210	89.34 293	97.31 257	87.62 217	97.10 310	94.22 220	86.58 302	94.40 287

UniMVSNet_ETH3D		90.06 315	88.58 323	94.49 279	94.67 327	88.09 347	97.81 355	97.57 262	83.91 368	88.44 312	97.41 254	57.44 400	97.62 284	91.41 262	88.59 284	97.77 250

UniMVSNet_NR-MVSNet		92.95 250	92.11 256	95.49 239	94.61 328	95.28 189	99.83 136	99.08 33	91.49 242	89.21 298	96.86 274	87.14 223	96.73 334	93.20 239	77.52 370	94.46 281

test_fmvs2		89.47 324	89.70 301	88.77 372	94.54 329	75.74 400	99.83 136	94.70 396	94.71 115	91.08 262	96.82 279	54.46 403	97.78 279	92.87 246	88.27 288	92.80 365

MonoMVSNet		94.82 195	94.43 197	95.98 228	94.54 329	90.73 303	99.03 277	97.06 319	93.16 180	93.15 240	95.47 322	88.29 210	97.57 285	97.85 140	91.33 263	99.62 130

WR-MVS		92.31 265	91.25 273	95.48 242	94.45 331	95.29 188	99.60 198	98.68 71	90.10 280	88.07 319	96.89 272	80.68 286	96.80 332	93.14 242	79.67 358	94.36 289

nrg030		93.51 237	92.53 250	96.45 215	94.36 332	97.20 109	99.81 141	97.16 307	91.60 239	89.86 278	97.46 252	86.37 233	97.68 281	95.88 184	80.31 354	94.46 281

tfpnnormal		89.29 327	87.61 334	94.34 287	94.35 333	94.13 223	98.95 285	98.94 41	83.94 366	84.47 358	95.51 319	74.84 340	97.39 290	77.05 385	80.41 352	91.48 380

FC-MVSNet-test		93.81 227	93.15 234	95.80 235	94.30 334	96.20 152	99.42 228	98.89 49	92.33 220	89.03 303	97.27 259	87.39 220	96.83 330	93.20 239	86.48 303	94.36 289

MS-PatchMatch		90.65 298	90.30 289	91.71 345	94.22 335	85.50 365	98.24 339	97.70 245	88.67 309	86.42 343	96.37 290	67.82 371	98.03 266	83.62 349	99.62 95	91.60 378

WR-MVS_H		91.30 283	90.35 287	94.15 290	94.17 336	92.62 263	99.17 259	98.94 41	88.87 304	86.48 342	94.46 363	84.36 252	96.61 339	88.19 307	78.51 363	93.21 358

DU-MVS		92.46 262	91.45 271	95.49 239	94.05 337	95.28 189	99.81 141	98.74 65	92.25 222	89.21 298	96.64 282	81.66 272	96.73 334	93.20 239	77.52 370	94.46 281

NR-MVSNet		91.56 281	90.22 291	95.60 237	94.05 337	95.76 167	98.25 338	98.70 68	91.16 256	80.78 377	96.64 282	83.23 261	96.57 340	91.41 262	77.73 369	94.46 281

CP-MVSNet		91.23 287	90.22 291	94.26 288	93.96 339	92.39 267	99.09 263	98.57 91	88.95 301	86.42 343	96.57 285	79.19 301	96.37 347	90.29 286	78.95 360	94.02 321

XXY-MVS		91.82 272	90.46 284	95.88 231	93.91 340	95.40 185	98.87 297	97.69 247	88.63 311	87.87 321	97.08 264	74.38 344	97.89 274	91.66 260	84.07 322	94.35 292

PS-CasMVS		90.63 300	89.51 307	93.99 299	93.83 341	91.70 286	98.98 281	98.52 108	88.48 313	86.15 347	96.53 287	75.46 333	96.31 351	88.83 299	78.86 362	93.95 329

test_0402		85.58 346	83.94 351	90.50 355	93.81 342	85.04 367	98.55 321	95.20 388	76.01 397	79.72 382	95.13 339	64.15 385	96.26 353	66.04 408	86.88 301	90.21 391

XVG-ACMP-BASELINE		91.22 288	90.75 279	92.63 334	93.73 343	85.61 363	98.52 325	97.44 275	92.77 196	89.90 277	96.85 275	66.64 376	98.39 234	92.29 251	88.61 282	93.89 334

TranMVSNet+NR-MVSNet		91.68 280	90.61 283	94.87 260	93.69 344	93.98 227	99.69 182	98.65 75	91.03 260	88.44 312	96.83 278	80.05 294	96.18 355	90.26 287	76.89 378	94.45 286

TransMVSNet (Re)		87.25 340	85.28 347	93.16 323	93.56 345	91.03 295	98.54 323	94.05 402	83.69 370	81.09 375	96.16 296	75.32 334	96.40 346	76.69 386	68.41 398	92.06 374

v10		90.25 310	88.82 319	94.57 274	93.53 346	93.43 242	99.08 265	96.87 341	85.00 358	87.34 332	94.51 359	80.93 282	97.02 320	82.85 354	79.23 359	93.26 356

testgi		89.01 329	88.04 330	91.90 341	93.49 347	84.89 369	99.73 170	95.66 378	93.89 160	85.14 353	98.17 231	59.68 397	94.66 383	77.73 381	88.88 276	96.16 272

v8		90.54 302	89.17 312	94.66 268	93.43 348	93.40 244	99.20 256	96.94 335	85.76 349	87.56 326	94.51 359	81.96 268	97.19 303	84.94 341	78.25 364	93.38 354

V42		91.28 285	90.12 296	94.74 265	93.42 349	93.46 241	99.68 184	97.02 323	87.36 328	89.85 280	95.05 342	81.31 278	97.34 293	87.34 318	80.07 356	93.40 352

pm-mvs1		89.36 326	87.81 332	94.01 297	93.40 350	91.93 276	98.62 319	96.48 361	86.25 344	83.86 362	96.14 297	73.68 347	97.04 316	86.16 332	75.73 383	93.04 361

v1144		91.09 289	89.83 298	94.87 260	93.25 351	93.69 235	99.62 195	96.98 328	86.83 338	89.64 286	94.99 347	80.94 281	97.05 313	85.08 340	81.16 342	93.87 336

v1192		90.62 301	89.25 311	94.72 267	93.13 352	93.07 248	99.50 216	97.02 323	86.33 343	89.56 289	95.01 344	79.22 300	97.09 312	82.34 358	81.16 342	94.01 323

v2v482		91.30 283	90.07 297	95.01 255	93.13 352	93.79 230	99.77 151	97.02 323	88.05 319	89.25 295	95.37 329	80.73 285	97.15 305	87.28 319	80.04 357	94.09 317

OPM-MVS		93.21 242	92.80 240	94.44 282	93.12 354	90.85 302	99.77 151	97.61 257	96.19 79	91.56 258	98.65 201	75.16 339	98.47 223	93.78 231	89.39 272	93.99 326
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v144192		90.79 296	89.52 306	94.59 272	93.11 355	92.77 254	99.56 206	96.99 326	86.38 342	89.82 281	94.95 349	80.50 290	97.10 310	83.98 346	80.41 352	93.90 333

PEN-MVS		90.19 312	89.06 315	93.57 313	93.06 356	90.90 300	99.06 270	98.47 120	88.11 318	85.91 349	96.30 292	76.67 320	95.94 365	87.07 322	76.91 377	93.89 334

v1240		90.20 311	88.79 320	94.44 282	93.05 357	92.27 269	99.38 234	96.92 337	85.89 347	89.36 292	94.87 351	77.89 312	97.03 318	80.66 366	81.08 345	94.01 323

v148		90.70 297	89.63 302	93.92 301	92.97 358	90.97 296	99.75 160	96.89 339	87.51 325	88.27 317	95.01 344	81.67 271	97.04 316	87.40 317	77.17 375	93.75 342

v1921920		90.46 303	89.12 313	94.50 278	92.96 359	92.46 265	99.49 218	96.98 328	86.10 345	89.61 288	95.30 332	78.55 309	97.03 318	82.17 359	80.89 350	94.01 323

MVStest1		85.03 352	82.76 361	91.83 342	92.95 360	89.16 333	98.57 320	94.82 392	71.68 408	68.54 408	95.11 341	83.17 262	95.66 368	74.69 391	65.32 405	90.65 387

Baseline_NR-MVSNet		90.33 307	89.51 307	92.81 332	92.84 361	89.95 322	99.77 151	93.94 403	84.69 363	89.04 302	95.66 311	81.66 272	96.52 341	90.99 270	76.98 376	91.97 376

test_method		80.79 368	79.70 372	84.08 383	92.83 362	67.06 409	99.51 214	95.42 382	54.34 415	81.07 376	93.53 372	44.48 411	92.22 402	78.90 376	77.23 374	92.94 362

pmmvs4		92.10 269	91.07 277	95.18 251	92.82 363	94.96 199	99.48 220	96.83 343	87.45 327	88.66 309	96.56 286	83.78 256	96.83 330	89.29 295	84.77 316	93.75 342

LF4IMVS		89.25 328	88.85 318	90.45 357	92.81 364	81.19 391	98.12 345	94.79 393	91.44 246	86.29 345	97.11 262	65.30 382	98.11 260	88.53 304	85.25 311	92.07 373

DTE-MVSNet		89.40 325	88.24 328	92.88 330	92.66 365	89.95 322	99.10 262	98.22 193	87.29 329	85.12 354	96.22 294	76.27 327	95.30 375	83.56 350	75.74 382	93.41 351

EU-MVSNet		90.14 314	90.34 288	89.54 364	92.55 366	81.06 392	98.69 314	98.04 216	91.41 250	86.59 339	96.84 277	80.83 284	93.31 395	86.20 331	81.91 336	94.26 297

APD_test1		81.15 367	80.92 368	81.86 387	92.45 367	59.76 416	96.04 386	93.61 406	73.29 406	77.06 391	96.64 282	44.28 412	96.16 356	72.35 395	82.52 330	89.67 398

our_test_3		90.39 304	89.48 309	93.12 324	92.40 368	89.57 327	99.33 240	96.35 364	87.84 323	85.30 352	94.99 347	84.14 254	96.09 360	80.38 367	84.56 317	93.71 347

ppachtmachnet_test		89.58 323	88.35 326	93.25 322	92.40 368	90.44 312	99.33 240	96.73 350	85.49 354	85.90 350	95.77 306	81.09 280	96.00 364	76.00 389	82.49 331	93.30 355

v7n		89.65 322	88.29 327	93.72 307	92.22 370	90.56 309	99.07 269	97.10 313	85.42 356	86.73 336	94.72 352	80.06 293	97.13 307	81.14 364	78.12 366	93.49 350

dmvs_testset		83.79 361	86.07 343	76.94 391	92.14 371	48.60 426	96.75 373	90.27 416	89.48 289	78.65 385	98.55 213	79.25 299	86.65 414	66.85 405	82.69 329	95.57 274

PS-MVSNAJss		93.64 234	93.31 231	94.61 270	92.11 372	92.19 270	99.12 261	97.38 282	92.51 213	88.45 311	96.99 270	91.20 164	97.29 300	94.36 214	87.71 295	94.36 289

pmmvs5		90.17 313	89.09 314	93.40 316	92.10 373	89.77 325	99.74 163	95.58 380	85.88 348	87.24 333	95.74 307	73.41 348	96.48 343	88.54 303	83.56 326	93.95 329

N_pmnet		80.06 371	80.78 369	77.89 390	91.94 374	45.28 428	98.80 305	56.82 430	78.10 394	80.08 380	93.33 373	77.03 315	95.76 367	68.14 403	82.81 328	92.64 366

test_djsdf		92.83 253	92.29 254	94.47 280	91.90 375	92.46 265	99.55 208	97.27 297	91.17 254	89.96 274	96.07 301	81.10 279	96.89 325	94.67 209	88.91 275	94.05 320

SixPastTwentyTwo		88.73 330	88.01 331	90.88 349	91.85 376	82.24 383	98.22 342	95.18 389	88.97 299	82.26 368	96.89 272	71.75 353	96.67 337	84.00 345	82.98 327	93.72 346

K. test v3		88.05 336	87.24 337	90.47 356	91.82 377	82.23 384	98.96 284	97.42 278	89.05 294	76.93 393	95.60 313	68.49 367	95.42 371	85.87 336	81.01 348	93.75 342

OurMVSNet-221017-0		89.81 319	89.48 309	90.83 352	91.64 378	81.21 390	98.17 344	95.38 384	91.48 244	85.65 351	97.31 257	72.66 349	97.29 300	88.15 308	84.83 315	93.97 328

mvs_tets		91.81 273	91.08 276	94.00 298	91.63 379	90.58 308	98.67 316	97.43 276	92.43 215	87.37 331	97.05 267	71.76 352	97.32 295	94.75 206	88.68 281	94.11 316

Gipuma		66.95 384	65.00 384	72.79 396	91.52 380	67.96 408	66.16 419	95.15 390	47.89 417	58.54 414	67.99 419	29.74 416	87.54 413	50.20 418	77.83 368	62.87 419
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_fmvsmconf0.01_n		96.39 153	95.74 161	98.32 129	91.47 381	95.56 178	99.84 129	97.30 292	97.74 20	97.89 150	99.35 136	79.62 296	99.85 113	99.25 59	99.24 125	99.55 147

jajsoiax		91.92 271	91.18 274	94.15 290	91.35 382	90.95 299	99.00 280	97.42 278	92.61 205	87.38 330	97.08 264	72.46 350	97.36 291	94.53 212	88.77 279	94.13 315

MDA-MVSNet-bldmvs		84.09 359	81.52 366	91.81 343	91.32 383	88.00 349	98.67 316	95.92 372	80.22 388	55.60 417	93.32 374	68.29 369	93.60 393	73.76 392	76.61 379	93.82 340

MVP-Stereo		90.93 291	90.45 286	92.37 336	91.25 384	88.76 335	98.05 349	96.17 367	87.27 330	84.04 359	95.30 332	78.46 310	97.27 302	83.78 348	99.70 89	91.09 381
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MDA-MVSNet_test_wron		85.51 348	83.32 356	92.10 338	90.96 385	88.58 341	99.20 256	96.52 359	79.70 390	57.12 416	92.69 379	79.11 302	93.86 390	77.10 384	77.46 372	93.86 337

YYNet1		85.50 349	83.33 355	92.00 339	90.89 386	88.38 345	99.22 255	96.55 358	79.60 391	57.26 415	92.72 378	79.09 304	93.78 391	77.25 383	77.37 373	93.84 338

anonymousdsp		91.79 278	90.92 278	94.41 285	90.76 387	92.93 253	98.93 288	97.17 305	89.08 293	87.46 329	95.30 332	78.43 311	96.92 323	92.38 250	88.73 280	93.39 353

lessismore_v0				90.53 354	90.58 388	80.90 393		95.80 373		77.01 392	95.84 304	66.15 378	96.95 321	83.03 353	75.05 384	93.74 345

EG-PatchMatch MVS		85.35 350	83.81 353	89.99 362	90.39 389	81.89 386	98.21 343	96.09 369	81.78 382	74.73 399	93.72 371	51.56 408	97.12 309	79.16 375	88.61 282	90.96 384

EGC-MVSNET		69.38 377	63.76 387	86.26 380	90.32 390	81.66 389	96.24 382	93.85 404	0.99 427	3.22 428	92.33 384	52.44 405	92.92 398	59.53 414	84.90 314	84.21 408

CMPMVS	61.59 21	84.75 355	85.14 348	83.57 384	90.32 390	62.54 412	96.98 369	97.59 261	74.33 404	69.95 405	96.66 280	64.17 384	98.32 244	87.88 312	88.41 287	89.84 396
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
new_pmnet		84.49 358	82.92 359	89.21 366	90.03 392	82.60 380	96.89 372	95.62 379	80.59 386	75.77 398	89.17 396	65.04 383	94.79 382	72.12 396	81.02 347	90.23 390

pmmvs6		85.69 345	83.84 352	91.26 348	90.00 393	84.41 372	97.82 354	96.15 368	75.86 398	81.29 374	95.39 327	61.21 395	96.87 327	83.52 351	73.29 386	92.50 369

ttmdpeth		88.23 335	87.06 338	91.75 344	89.91 394	87.35 353	98.92 291	95.73 375	87.92 321	84.02 360	96.31 291	68.23 370	96.84 328	86.33 330	76.12 380	91.06 382

DSMNet-mixed		88.28 334	88.24 328	88.42 374	89.64 395	75.38 402	98.06 348	89.86 417	85.59 353	88.20 318	92.14 385	76.15 329	91.95 403	78.46 378	96.05 208	97.92 246

UnsupCasMVSNet_eth		85.52 347	83.99 349	90.10 360	89.36 396	83.51 376	96.65 374	97.99 218	89.14 292	75.89 397	93.83 369	63.25 388	93.92 388	81.92 361	67.90 401	92.88 363

Anonymous20231206		86.32 343	85.42 346	89.02 368	89.11 397	80.53 396	99.05 274	95.28 385	85.43 355	82.82 366	93.92 368	74.40 343	93.44 394	66.99 404	81.83 337	93.08 360

Anonymous20240521		85.15 351	83.81 353	89.16 367	88.32 398	82.69 379	98.80 305	95.74 374	79.72 389	81.53 373	90.99 388	65.38 381	94.16 386	72.69 394	81.11 344	90.63 388

OpenMVS_ROB	79.82 20	83.77 362	81.68 365	90.03 361	88.30 399	82.82 378	98.46 326	95.22 387	73.92 405	76.00 396	91.29 387	55.00 402	96.94 322	68.40 402	88.51 286	90.34 389

test20.03		84.72 356	83.99 349	86.91 378	88.19 400	80.62 395	98.88 294	95.94 371	88.36 315	78.87 383	94.62 357	68.75 365	89.11 409	66.52 406	75.82 381	91.00 383

KD-MVS_self_test		83.59 363	82.06 363	88.20 375	86.93 401	80.70 394	97.21 362	96.38 362	82.87 376	82.49 367	88.97 397	67.63 372	92.32 401	73.75 393	62.30 412	91.58 379

MIMVSNet1		82.58 364	80.51 370	88.78 370	86.68 402	84.20 373	96.65 374	95.41 383	78.75 392	78.59 386	92.44 380	51.88 407	89.76 408	65.26 409	78.95 360	92.38 372

CL-MVSNet_self_test		84.50 357	83.15 358	88.53 373	86.00 403	81.79 387	98.82 302	97.35 285	85.12 357	83.62 364	90.91 390	76.66 321	91.40 404	69.53 400	60.36 413	92.40 371

UnsupCasMVSNet_bld		79.97 373	77.03 378	88.78 370	85.62 404	81.98 385	93.66 398	97.35 285	75.51 401	70.79 404	83.05 411	48.70 409	94.91 380	78.31 379	60.29 414	89.46 401

mvs5depth		84.87 353	82.90 360	90.77 353	85.59 405	84.84 370	91.10 409	93.29 408	83.14 373	85.07 355	94.33 365	62.17 391	97.32 295	78.83 377	72.59 389	90.14 392

Patchmatch-RL test		86.90 341	85.98 345	89.67 363	84.45 406	75.59 401	89.71 412	92.43 410	86.89 337	77.83 390	90.94 389	94.22 90	93.63 392	87.75 313	69.61 393	99.79 100

pmmvs-eth3d		84.03 360	81.97 364	90.20 359	84.15 407	87.09 355	98.10 347	94.73 395	83.05 374	74.10 401	87.77 403	65.56 380	94.01 387	81.08 365	69.24 395	89.49 400

test_fmvs3		79.99 372	80.17 371	79.45 389	84.02 408	62.83 410	99.05 274	93.49 407	88.29 317	80.06 381	86.65 406	28.09 418	88.00 410	88.63 300	73.27 387	87.54 406

PM-MVS		80.47 369	78.88 374	85.26 381	83.79 409	72.22 404	95.89 389	91.08 414	85.71 352	76.56 395	88.30 399	36.64 414	93.90 389	82.39 357	69.57 394	89.66 399

new-patchmatchnet		81.19 366	79.34 373	86.76 379	82.86 410	80.36 397	97.92 351	95.27 386	82.09 381	72.02 402	86.87 405	62.81 390	90.74 407	71.10 397	63.08 409	89.19 403

mvsany_test3		82.12 365	81.14 367	85.06 382	81.87 411	70.41 406	97.09 366	92.14 411	91.27 253	77.84 389	88.73 398	39.31 413	95.49 369	90.75 277	71.24 390	89.29 402

WB-MVS		76.28 375	77.28 377	73.29 395	81.18 412	54.68 420	97.87 353	94.19 399	81.30 383	69.43 406	90.70 391	77.02 316	82.06 418	35.71 423	68.11 400	83.13 409

test_f		78.40 374	77.59 376	80.81 388	80.82 413	62.48 413	96.96 370	93.08 409	83.44 371	74.57 400	84.57 410	27.95 419	92.63 399	84.15 343	72.79 388	87.32 407

SSC-MVS		75.42 376	76.40 379	72.49 399	80.68 414	53.62 421	97.42 358	94.06 401	80.42 387	68.75 407	90.14 393	76.54 323	81.66 419	33.25 424	66.34 404	82.19 410

pmmvs3		80.27 370	77.77 375	87.76 377	80.32 415	82.43 382	98.23 341	91.97 412	72.74 407	78.75 384	87.97 402	57.30 401	90.99 406	70.31 398	62.37 411	89.87 395

testf1		68.38 380	66.92 381	72.78 397	78.80 416	50.36 423	90.95 410	87.35 422	55.47 413	58.95 412	88.14 400	20.64 423	87.60 411	57.28 415	64.69 406	80.39 412

APD_test2		68.38 380	66.92 381	72.78 397	78.80 416	50.36 423	90.95 410	87.35 422	55.47 413	58.95 412	88.14 400	20.64 423	87.60 411	57.28 415	64.69 406	80.39 412

ambc				83.23 385	77.17 418	62.61 411	87.38 414	94.55 398		76.72 394	86.65 406	30.16 415	96.36 348	84.85 342	69.86 392	90.73 386

test_vis3_rt		68.82 378	66.69 383	75.21 394	76.24 419	60.41 415	96.44 377	68.71 429	75.13 402	50.54 420	69.52 418	16.42 428	96.32 350	80.27 368	66.92 403	68.89 416

TDRefinement		84.76 354	82.56 362	91.38 347	74.58 420	84.80 371	97.36 360	94.56 397	84.73 362	80.21 379	96.12 300	63.56 386	98.39 234	87.92 311	63.97 408	90.95 385

E-PMN		52.30 388	52.18 390	52.67 405	71.51 421	45.40 427	93.62 399	76.60 427	36.01 421	43.50 422	64.13 421	27.11 420	67.31 424	31.06 425	26.06 420	45.30 423

EMVS		51.44 390	51.22 392	52.11 406	70.71 422	44.97 429	94.04 395	75.66 428	35.34 423	42.40 423	61.56 424	28.93 417	65.87 425	27.64 426	24.73 421	45.49 422

PMMVS2		67.15 383	64.15 386	76.14 393	70.56 423	62.07 414	93.89 396	87.52 421	58.09 412	60.02 411	78.32 413	22.38 422	84.54 416	59.56 413	47.03 418	81.80 411

FPMVS		68.72 379	68.72 380	68.71 401	65.95 424	44.27 430	95.97 388	94.74 394	51.13 416	53.26 418	90.50 392	25.11 421	83.00 417	60.80 412	80.97 349	78.87 414

wuyk23d		20.37 394	20.84 397	18.99 409	65.34 425	27.73 432	50.43 420	7.67 433	9.50 426	8.01 427	6.34 427	6.13 431	26.24 426	23.40 427	10.69 425	2.99 424

LCM-MVSNet		67.77 382	64.73 385	76.87 392	62.95 426	56.25 419	89.37 413	93.74 405	44.53 418	61.99 410	80.74 412	20.42 425	86.53 415	69.37 401	59.50 415	87.84 404

MVE	53.74 22	51.54 389	47.86 393	62.60 403	59.56 427	50.93 422	79.41 417	77.69 426	35.69 422	36.27 424	61.76 423	5.79 432	69.63 422	37.97 422	36.61 419	67.24 417
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		56.10 386	52.24 389	67.66 402	49.27 428	56.82 418	83.94 415	82.02 425	70.47 409	33.28 425	64.54 420	17.23 427	69.16 423	45.59 420	23.85 422	77.02 415

tmp_tt		65.23 385	62.94 388	72.13 400	44.90 429	50.03 425	81.05 416	89.42 420	38.45 419	48.51 421	99.90 18	54.09 404	78.70 421	91.84 259	18.26 423	87.64 405

PMVS	49.05 23	53.75 387	51.34 391	60.97 404	40.80 430	34.68 431	74.82 418	89.62 419	37.55 420	28.67 426	72.12 415	7.09 430	81.63 420	43.17 421	68.21 399	66.59 418
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test123		37.68 392	39.14 395	33.31 407	19.94 431	24.83 433	98.36 334	9.75 432	15.53 425	51.31 419	87.14 404	19.62 426	17.74 427	47.10 419	3.47 426	57.36 420

testmvs		40.60 391	44.45 394	29.05 408	19.49 432	14.11 434	99.68 184	18.47 431	20.74 424	64.59 409	98.48 218	10.95 429	17.09 428	56.66 417	11.01 424	55.94 421

mmdepth		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 429	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

monomultidepth		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 429	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

test_blank		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.02 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

eth-test2					0.00 433

eth-test					0.00 433

uanet_test		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 429	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

DCPMVS		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 429	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

cdsmvs_eth3d_5k		23.43 393	31.24 396	0.00 410	0.00 433	0.00 435	0.00 421	98.09 210	0.00 428	0.00 429	99.67 97	83.37 259	0.00 429	0.00 428	0.00 427	0.00 425

pcd_1.5k_mvsjas		7.60 396	10.13 399	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 429	91.20 164	0.00 429	0.00 428	0.00 427	0.00 425

sosnet-low-res		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 429	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

sosnet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 429	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

uncertanet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 429	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

Regformer		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 429	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

ab-mvs-re		8.28 395	11.04 398	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	99.40 130	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

uanet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 429	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

WAC-MVS						90.97 296								86.10 334

PC_three_1452									96.96 49	99.80 17	99.79 58	97.49 10	100.00 1	99.99 5	99.98 32	100.00 1

test_241102_TWO								98.43 136	97.27 36	99.80 17	99.94 4	97.18 21	100.00 1	100.00 1	100.00 1	100.00 1

test_0728_THIRD									96.48 65	99.83 13	99.91 14	97.87 5	100.00 1	99.92 13	100.00 1	100.00 1

GSMVS																99.59 137

sam_mvs1												94.72 69				99.59 137

sam_mvs												94.25 89

MTGPA								98.28 184

test_post1							95.78 390				59.23 425	93.20 122	97.74 280	91.06 268

test_post											63.35 422	94.43 77	98.13 259

patchmatchnet-post											91.70 386	95.12 54	97.95 271

MTMP							99.87 110	96.49 360

test9_res														99.71 37	99.99 21	100.00 1

agg_prior2														99.48 48	100.00 1	100.00 1

test_prior4						98.05 72	99.94 72

test_prior2							99.95 55		95.78 85	99.73 34	99.76 66	96.00 37		99.78 27	100.00 1

旧先验2							99.46 225		94.21 141	99.85 9			99.95 73	96.96 168

新几何2							99.40 229

无先验							99.49 218	98.71 67	93.46 169				100.00 1	94.36 214		99.99 23

原ACMM2							99.90 95

testdata2													99.99 36	90.54 281

segment_acmp												96.68 29

testdata1							99.28 249		96.35 75

plane_prior5								97.87 232					98.37 240	97.79 145	89.55 269	94.52 278

plane_prior4											98.59 206

plane_prior3						91.64 288			96.63 62	93.01 241

plane_prior2							99.84 129		96.38 71

plane_prior						91.74 282	99.86 121		96.76 57						89.59 268

n2								0.00 434

nn								0.00 434

door-mid								89.69 418

test11								98.44 128

door								90.31 415

HQP5-MVS						91.85 278

BP-MVS														97.92 136

HQP4-MVS										93.37 236			98.39 234			94.53 276

HQP3-MVS								97.89 230							89.60 266

HQP2-MVS												80.65 287

MDTV_nov1_ep13_2view						96.26 147	96.11 384		91.89 231	98.06 144		94.40 79		94.30 217		99.67 118

ACMMP++_ref															87.04 300

ACMMP++															88.23 289

Test By Simon												92.82 133

High-resolution multi-view benchmark