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		97.23 130	96.80 138	98.51 133	99.99 1	95.60 202	99.09 330	98.84 65	93.32 208	96.74 222	99.72 95	86.04 263	100.00 1	98.01 152	99.43 129	99.94 87

CNVR-MVS		99.40 1	99.26 1	99.84 7	99.98 2	99.51 7	99.98 24	98.69 82	98.20 9	99.93 3	99.98 2	96.82 26	100.00 1	99.75 41	100.00 1	99.99 26

TestfortrainingZip				99.90 5	99.97 3	99.70 5	99.97 42	98.89 52	96.02 99	99.99 1	99.96 3	97.97 5	100.00 1		99.65 96	100.00 1

MCST-MVS		99.32 3	99.14 4	99.86 6	99.97 3	99.59 6	99.97 42	98.64 91	98.47 3	99.13 107	99.92 16	96.38 36	100.00 1	99.74 43	100.00 1	100.00 1

mPP-MVS		98.39 56	98.20 54	98.97 93	99.97 3	96.92 139	99.95 75	98.38 184	95.04 124	98.61 140	99.80 59	93.39 117	100.00 1	98.64 114	100.00 1	99.98 57

CPTT-MVS		97.64 110	97.32 114	98.58 122	99.97 3	95.77 191	99.96 56	98.35 190	89.90 352	98.36 155	99.79 63	91.18 180	99.99 39	98.37 130	99.99 21	99.99 26

DP-MVS Recon		98.41 53	98.02 68	99.56 30	99.97 3	98.70 53	99.92 103	98.44 148	92.06 280	98.40 154	99.84 49	95.68 48	100.00 1	98.19 141	99.71 91	99.97 67

PAPR		98.52 43	98.16 58	99.58 29	99.97 3	98.77 47	99.95 75	98.43 156	95.35 118	98.03 170	99.75 81	94.03 102	99.98 51	98.11 146	99.83 80	99.99 26

MED-MVS test				99.60 24	99.96 9	98.79 42	99.97 42	98.88 55	96.36 90	99.07 112	99.93 12		100.00 1	99.98 9	99.96 46	99.99 26

MED-MVS		99.24 8	99.11 7	99.60 24	99.96 9	98.79 42	99.97 42	98.88 55	96.91 62	99.07 112	99.92 16	97.36 18	100.00 1	99.98 9	99.96 46	100.00 1

TestfortrainingZip a		99.01 16	98.78 21	99.69 17	99.96 9	99.09 25	99.97 42	98.74 76	96.91 62	99.86 16	99.92 16	96.29 37	99.99 39	98.32 133	99.09 149	100.00 1

HFP-MVS		98.56 39	98.37 43	99.14 73	99.96 9	97.43 115	99.95 75	98.61 99	94.77 134	99.31 95	99.85 38	94.22 95	100.00 1	98.70 109	99.98 32	99.98 57

region2R		98.54 41	98.37 43	99.05 83	99.96 9	97.18 125	99.96 56	98.55 119	94.87 131	99.45 81	99.85 38	94.07 101	100.00 1	98.67 111	100.00 1	99.98 57

ACMMPR		98.50 44	98.32 47	99.05 83	99.96 9	97.18 125	99.95 75	98.60 101	94.77 134	99.31 95	99.84 49	93.73 111	100.00 1	98.70 109	99.98 32	99.98 57

NCCC		99.37 2	99.25 2	99.71 16	99.96 9	99.15 23	99.97 42	98.62 98	98.02 22	99.90 7	99.95 4	97.33 19	100.00 1	99.54 58	100.00 1	100.00 1

CP-MVS		98.45 48	98.32 47	98.87 98	99.96 9	96.62 154	99.97 42	98.39 180	94.43 151	98.90 121	99.87 32	94.30 92	100.00 1	99.04 85	99.99 21	99.99 26

test_one_0601					99.94 17	99.30 13		98.41 173	96.63 75	99.75 42	99.93 12	97.49 11

test_0728_SECOND				99.82 8	99.94 17	99.47 8	99.95 75	98.43 156					100.00 1	99.99 5	100.00 1	100.00 1

XVS		98.70 32	98.55 31	99.15 71	99.94 17	97.50 111	99.94 93	98.42 168	96.22 93	99.41 87	99.78 67	94.34 89	99.96 76	98.92 94	99.95 53	99.99 26

X-MVStestdata		93.83 287	92.06 322	99.15 71	99.94 17	97.50 111	99.94 93	98.42 168	96.22 93	99.41 87	41.37 539	94.34 89	99.96 76	98.92 94	99.95 53	99.99 26

test_prior				99.43 41	99.94 17	98.49 66		98.65 88					99.80 143			99.99 26

MSLP-MVS++		99.13 9	99.01 12	99.49 37	99.94 17	98.46 67	99.98 24	98.86 59	97.10 53	99.80 28	99.94 5	95.92 44	100.00 1	99.51 59	100.00 1	100.00 1

APDe-MVS		99.06 13	98.91 15	99.51 34	99.94 17	98.76 50	99.91 111	98.39 180	97.20 51	99.46 80	99.85 38	95.53 52	99.79 145	99.86 27	100.00 1	99.99 26
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MP-MVS		98.23 71	97.97 72	99.03 85	99.94 17	97.17 128	99.95 75	98.39 180	94.70 138	98.26 161	99.81 58	91.84 171	100.00 1	98.85 100	99.97 42	99.93 88
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CDPH-MVS		98.65 35	98.36 45	99.49 37	99.94 17	98.73 51	99.87 133	98.33 195	93.97 177	99.76 41	99.87 32	94.99 68	99.75 154	98.55 118	100.00 1	99.98 57

PAPM_NR		98.12 75	97.93 78	98.70 109	99.94 17	96.13 180	99.82 165	98.43 156	94.56 142	97.52 188	99.70 101	94.40 84	99.98 51	97.00 195	99.98 32	99.99 26

MG-MVS		98.91 22	98.65 27	99.68 18	99.94 17	99.07 26	99.64 238	99.44 19	97.33 44	99.00 117	99.72 95	94.03 102	99.98 51	98.73 108	100.00 1	100.00 1

ME-MVS		99.07 11	98.89 17	99.59 27	99.93 28	98.79 42	99.95 75	98.80 71	95.89 103	99.28 99	99.93 12	96.28 38	99.98 51	99.98 9	99.96 46	99.99 26

SED-MVS		99.28 5	99.11 7	99.77 9	99.93 28	99.30 13	99.96 56	98.43 156	97.27 47	99.80 28	99.94 5	96.71 29	100.00 1	100.00 1	100.00 1	100.00 1

IU-MVS					99.93 28	99.31 11		98.41 173	97.71 31	99.84 23				100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 28	99.30 13		98.43 156	97.26 49	99.80 28	99.88 29	96.71 29	100.00 1

DVP-MVS		99.30 4	99.16 3	99.73 13	99.93 28	99.29 16	99.95 75	98.32 197	97.28 45	99.83 24	99.91 19	97.22 21	100.00 1	99.99 5	100.00 1	99.89 97
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 28	99.29 16	99.96 56	98.42 168	97.28 45	99.86 16	99.94 5	97.22 21

MSP-MVS		99.09 10	99.12 5	98.98 92	99.93 28	97.24 122	99.95 75	98.42 168	97.50 38	99.52 76	99.88 29	97.43 17	99.71 160	99.50 61	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 28	98.77 47		98.43 156		99.63 59			99.85 130

FOURS1					99.92 36	97.66 105	99.95 75	98.36 188	95.58 112	99.52 76

ZD-MVS					99.92 36	98.57 61		98.52 128	92.34 268	99.31 95	99.83 51	95.06 63	99.80 143	99.70 49	99.97 42

GST-MVS		98.27 63	97.97 72	99.17 66	99.92 36	97.57 107	99.93 100	98.39 180	94.04 175	98.80 126	99.74 88	92.98 133	100.00 1	98.16 143	99.76 88	99.93 88

TEST9					99.92 36	98.92 31	99.96 56	98.43 156	93.90 183	99.71 49	99.86 34	95.88 45	99.85 130

train_agg		98.88 23	98.65 27	99.59 27	99.92 36	98.92 31	99.96 56	98.43 156	94.35 156	99.71 49	99.86 34	95.94 42	99.85 130	99.69 50	99.98 32	99.99 26

test_8					99.92 36	98.88 34	99.96 56	98.43 156	94.35 156	99.69 51	99.85 38	95.94 42	99.85 130

PGM-MVS		98.34 58	98.13 60	98.99 90	99.92 36	97.00 135	99.75 197	99.50 17	93.90 183	99.37 92	99.76 73	93.24 126	100.00 1	97.75 173	99.96 46	99.98 57

ACMMP		97.74 103	97.44 107	98.66 113	99.92 36	96.13 180	99.18 322	99.45 18	94.84 132	96.41 241	99.71 98	91.40 174	99.99 39	97.99 154	98.03 190	99.87 100
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 10	99.77 9	99.91 44	99.31 11	99.95 75	98.43 156	96.48 80	99.80 28	99.93 12	97.44 15	100.00 1	99.92 16	99.98 32	100.00 1

MSC_two_6792asdad				99.93 2	99.91 44	99.80 2		98.41 173					100.00 1	99.96 12	100.00 1	100.00 1

No_MVS				99.93 2	99.91 44	99.80 2		98.41 173					100.00 1	99.96 12	100.00 1	100.00 1

HPM-MVS++		99.07 11	98.88 18	99.63 19	99.90 47	99.02 27	99.95 75	98.56 113	97.56 37	99.44 82	99.85 38	95.38 56	100.00 1	99.31 71	99.99 21	99.87 100

APD-MVS		98.62 36	98.35 46	99.41 44	99.90 47	98.51 64	99.87 133	98.36 188	94.08 170	99.74 45	99.73 92	94.08 100	99.74 156	99.42 67	99.99 21	99.99 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DeepC-MVS_fast	96.59 1	98.81 26	98.54 32	99.62 22	99.90 47	98.85 37	99.24 317	98.47 140	98.14 16	99.08 110	99.91 19	93.09 130	100.00 1	99.04 85	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 50	99.80 2	99.96 56				99.80 59	97.44 15	100.00 1	100.00 1	99.98 32	100.00 1

DPE-MVS		99.26 6	99.10 9	99.74 12	99.89 50	99.24 20	99.87 133	98.44 148	97.48 39	99.64 58	99.94 5	96.68 31	99.99 39	99.99 5	100.00 1	99.99 26
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_part2					99.89 50	99.25 19				99.49 79

CSCG		97.10 136	97.04 126	97.27 241	99.89 50	91.92 337	99.90 117	99.07 37	88.67 376	95.26 274	99.82 54	93.17 129	99.98 51	98.15 144	99.47 124	99.90 96

ZNCC-MVS		98.31 60	98.03 67	99.17 66	99.88 54	97.59 106	99.94 93	98.44 148	94.31 159	98.50 147	99.82 54	93.06 131	99.99 39	98.30 135	99.99 21	99.93 88

SR-MVS		98.46 47	98.30 50	98.93 96	99.88 54	97.04 134	99.84 152	98.35 190	94.92 128	99.32 94	99.80 59	93.35 119	99.78 147	99.30 72	99.95 53	99.96 75

9.14			98.38 41		99.87 56		99.91 111	98.33 195	93.22 211	99.78 39	99.89 27	94.57 80	99.85 130	99.84 29	99.97 42

SMA-MVS		98.76 29	98.48 35	99.62 22	99.87 56	98.87 35	99.86 144	98.38 184	93.19 213	99.77 40	99.94 5	95.54 50	100.00 1	99.74 43	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 85	97.85 85	98.04 166	99.86 58	95.39 212	99.61 245	97.78 270	96.52 78	98.61 140	99.31 157	92.73 141	99.67 168	96.77 211	99.48 121	99.06 252

lecture		98.67 33	98.46 36	99.28 53	99.86 58	97.88 92	99.97 42	99.25 30	96.07 97	99.79 37	99.70 101	92.53 150	99.98 51	99.51 59	99.48 121	99.97 67

PHI-MVS		98.41 53	98.21 53	99.03 85	99.86 58	97.10 132	99.98 24	98.80 71	90.78 330	99.62 62	99.78 67	95.30 57	100.00 1	99.80 32	99.93 64	99.99 26

MTAPA		98.29 62	97.96 75	99.30 52	99.85 61	97.93 90	99.39 290	98.28 204	95.76 106	97.18 203	99.88 29	92.74 140	100.00 1	98.67 111	99.88 76	99.99 26

LS3D		95.84 210	95.11 227	98.02 167	99.85 61	95.10 232	98.74 380	98.50 137	87.22 401	93.66 297	99.86 34	87.45 239	99.95 85	90.94 333	99.81 86	99.02 260

HPM-MVS		97.96 80	97.72 90	98.68 110	99.84 63	96.39 166	99.90 117	98.17 222	92.61 249	98.62 139	99.57 131	91.87 170	99.67 168	98.87 99	99.99 21	99.99 26
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 63	98.11 62	98.75 106	99.83 64	96.59 158	99.40 286	98.51 131	95.29 120	98.51 146	99.76 73	93.60 115	99.71 160	98.53 121	99.52 114	99.95 83

save fliter					99.82 65	98.79 42	99.96 56	98.40 177	97.66 33

PLC	95.54 3	97.93 83	97.89 82	98.05 165	99.82 65	94.77 244	99.92 103	98.46 142	93.93 180	97.20 201	99.27 165	95.44 55	99.97 64	97.41 179	99.51 117	99.41 198
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
APD-MVS_3200maxsize		98.25 68	98.08 64	98.78 103	99.81 67	96.60 156	99.82 165	98.30 202	93.95 179	99.37 92	99.77 71	92.84 137	99.76 153	98.95 90	99.92 67	99.97 67

EI-MVSNet-UG-set		98.14 74	97.99 70	98.60 118	99.80 68	96.27 169	99.36 296	98.50 137	95.21 122	98.30 158	99.75 81	93.29 123	99.73 159	98.37 130	99.30 138	99.81 109

SR-MVS-dyc-post		98.31 60	98.17 57	98.71 108	99.79 69	96.37 167	99.76 191	98.31 199	94.43 151	99.40 89	99.75 81	93.28 124	99.78 147	98.90 97	99.92 67	99.97 67

RE-MVS-def			98.13 60		99.79 69	96.37 167	99.76 191	98.31 199	94.43 151	99.40 89	99.75 81	92.95 134		98.90 97	99.92 67	99.97 67

HPM-MVS_fast		97.80 97	97.50 103	98.68 110	99.79 69	96.42 162	99.88 130	98.16 227	91.75 292	98.94 119	99.54 134	91.82 172	99.65 172	97.62 176	99.99 21	99.99 26

SF-MVS		98.67 33	98.40 39	99.50 35	99.77 72	98.67 54	99.90 117	98.21 217	93.53 195	99.81 26	99.89 27	94.70 76	99.86 129	99.84 29	99.93 64	99.96 75

MGCNet		99.06 13	98.84 19	99.72 14	99.76 73	99.21 22	99.99 8	99.34 25	98.70 2	99.44 82	99.75 81	93.24 126	99.99 39	99.94 14	99.41 131	99.95 83

旧先验1					99.76 73	97.52 109		98.64 91			99.85 38	95.63 49			99.94 58	99.99 26

OMC-MVS		97.28 126	97.23 118	97.41 230	99.76 73	93.36 303	99.65 234	97.95 249	96.03 98	97.41 194	99.70 101	89.61 206	99.51 178	96.73 213	98.25 180	99.38 201

新几何1				99.42 43	99.75 76	98.27 71		98.63 97	92.69 244	99.55 71	99.82 54	94.40 84	100.00 1	91.21 325	99.94 58	99.99 26

MP-MVS-pluss		98.07 78	97.64 96	99.38 49	99.74 77	98.41 69	99.74 201	98.18 221	93.35 206	96.45 234	99.85 38	92.64 145	99.97 64	98.91 96	99.89 73	99.77 116
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
TSAR-MVS + MP.		98.93 20	98.77 22	99.41 44	99.74 77	98.67 54	99.77 185	98.38 184	96.73 71	99.88 13	99.74 88	94.89 70	99.59 174	99.80 32	99.98 32	99.97 67
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 41	99.74 77	98.56 62		98.40 177		99.65 55		94.76 73	99.75 154		99.98 32	99.99 26

原ACMM1				98.96 94	99.73 80	96.99 136		98.51 131	94.06 173	99.62 62	99.85 38	94.97 69	99.96 76	95.11 245	99.95 53	99.92 93

TSAR-MVS + GP.		98.60 37	98.51 34	98.86 99	99.73 80	96.63 153	99.97 42	97.92 254	98.07 19	98.76 132	99.55 132	95.00 67	99.94 94	99.91 19	97.68 197	99.99 26

CANet		98.27 63	97.82 87	99.63 19	99.72 82	99.10 24	99.98 24	98.51 131	97.00 59	98.52 144	99.71 98	87.80 230	99.95 85	99.75 41	99.38 133	99.83 105

reproduce_model		98.75 30	98.66 26	99.03 85	99.71 83	97.10 132	99.73 208	98.23 212	97.02 58	99.18 105	99.90 23	94.54 81	99.99 39	99.77 37	99.90 72	99.99 26

F-COLMAP		96.93 148	96.95 129	96.87 259	99.71 83	91.74 347	99.85 147	97.95 249	93.11 221	95.72 263	99.16 184	92.35 156	99.94 94	95.32 241	99.35 136	98.92 268

reproduce-ours		98.78 27	98.67 24	99.09 80	99.70 85	97.30 119	99.74 201	98.25 208	97.10 53	99.10 108	99.90 23	94.59 77	99.99 39	99.77 37	99.91 70	99.99 26

our_new_method		98.78 27	98.67 24	99.09 80	99.70 85	97.30 119	99.74 201	98.25 208	97.10 53	99.10 108	99.90 23	94.59 77	99.99 39	99.77 37	99.91 70	99.99 26

SD-MVS		98.92 21	98.70 23	99.56 30	99.70 85	98.73 51	99.94 93	98.34 194	96.38 86	99.81 26	99.76 73	94.59 77	99.98 51	99.84 29	99.96 46	99.97 67
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 69	99.12 5	95.59 303	99.67 88	86.91 434	99.95 75	98.89 52	97.60 34	99.90 7	99.76 73	96.54 34	99.98 51	99.94 14	99.82 84	99.88 98

ACMMP_NAP		98.49 45	98.14 59	99.54 32	99.66 89	98.62 60	99.85 147	98.37 187	94.68 139	99.53 74	99.83 51	92.87 136	100.00 1	98.66 113	99.84 79	99.99 26

DeepPCF-MVS	95.94 2	97.71 107	98.98 13	93.92 376	99.63 90	81.76 469	99.96 56	98.56 113	99.47 1	99.19 104	99.99 1	94.16 99	100.00 1	99.92 16	99.93 64	100.00 1

EPNet		98.49 45	98.40 39	98.77 105	99.62 91	96.80 147	99.90 117	99.51 16	97.60 34	99.20 102	99.36 152	93.71 112	99.91 111	97.99 154	98.71 165	99.61 151
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MM		98.83 24	98.53 33	99.76 11	99.59 92	99.33 9	99.99 8	99.76 6	98.39 4	99.39 91	99.80 59	90.49 195	99.96 76	99.89 21	99.43 129	99.98 57

PVSNet_BlendedMVS		96.05 200	95.82 192	96.72 265	99.59 92	96.99 136	99.95 75	99.10 34	94.06 173	98.27 159	95.80 371	89.00 218	99.95 85	99.12 79	87.53 360	93.24 434

PVSNet_Blended		97.94 82	97.64 96	98.83 100	99.59 92	96.99 136	100.00 1	99.10 34	95.38 117	98.27 159	99.08 189	89.00 218	99.95 85	99.12 79	99.25 140	99.57 162

PatchMatch-RL		96.04 201	95.40 210	97.95 170	99.59 92	95.22 226	99.52 267	99.07 37	93.96 178	96.49 232	98.35 283	82.28 324	99.82 142	90.15 349	99.22 143	98.81 276

dcpmvs_2		97.42 121	98.09 63	95.42 310	99.58 96	87.24 430	99.23 318	96.95 404	94.28 162	98.93 120	99.73 92	94.39 87	99.16 207	99.89 21	99.82 84	99.86 102

test222					99.55 97	97.41 117	99.34 298	98.55 119	91.86 286	99.27 100	99.83 51	93.84 109			99.95 53	99.99 26

CNLPA		97.76 101	97.38 110	98.92 97	99.53 98	96.84 141	99.87 133	98.14 231	93.78 187	96.55 230	99.69 105	92.28 158	99.98 51	97.13 190	99.44 128	99.93 88

API-MVS		97.86 88	97.66 94	98.47 135	99.52 99	95.41 210	99.47 277	98.87 58	91.68 294	98.84 123	99.85 38	92.34 157	99.99 39	98.44 126	99.96 46	100.00 1

PVSNet	91.05 13	97.13 135	96.69 144	98.45 138	99.52 99	95.81 189	99.95 75	99.65 12	94.73 136	99.04 115	99.21 176	84.48 299	99.95 85	94.92 251	98.74 164	99.58 160

114514_t		97.41 122	96.83 135	99.14 73	99.51 101	97.83 94	99.89 127	98.27 206	88.48 381	99.06 114	99.66 116	90.30 198	99.64 173	96.32 225	99.97 42	99.96 75

cl22		93.77 292	93.25 292	95.33 314	99.49 102	94.43 256	99.61 245	98.09 234	90.38 341	89.16 369	95.61 380	90.56 193	97.34 353	91.93 316	84.45 383	94.21 372

testdata				98.42 142	99.47 103	95.33 216		98.56 113	93.78 187	99.79 37	99.85 38	93.64 114	99.94 94	94.97 249	99.94 58	100.00 1

MAR-MVS		97.43 117	97.19 120	98.15 158	99.47 103	94.79 243	99.05 341	98.76 73	92.65 247	98.66 137	99.82 54	88.52 224	99.98 51	98.12 145	99.63 98	99.67 133
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		94.54 260	93.42 282	97.91 176	99.46 105	94.04 274	98.93 359	97.48 307	81.15 458	90.04 340	99.55 132	87.02 247	99.95 85	88.97 364	98.11 186	99.73 120

MVS_111021_LR		98.42 52	98.38 41	98.53 130	99.39 106	95.79 190	99.87 133	99.86 2	96.70 72	98.78 127	99.79 63	92.03 167	99.90 113	99.17 78	99.86 78	99.88 98

CHOSEN 280x420		99.01 16	99.03 11	98.95 95	99.38 107	98.87 35	98.46 399	99.42 21	97.03 57	99.02 116	99.09 188	99.35 2	98.21 315	99.73 45	99.78 87	99.77 116

MVS_111021_HR		98.72 31	98.62 29	99.01 89	99.36 108	97.18 125	99.93 100	99.90 1	96.81 69	98.67 136	99.77 71	93.92 104	99.89 118	99.27 74	99.94 58	99.96 75

fmvsm_s_conf0.5_n_11		98.03 79	97.89 82	98.46 137	99.35 109	97.76 98	99.99 8	98.04 240	98.20 9	99.90 7	99.78 67	86.21 261	99.95 85	99.89 21	99.68 93	97.65 315

DPM-MVS		98.83 24	98.46 36	99.97 1	99.33 110	99.92 1	99.96 56	98.44 148	97.96 23	99.55 71	99.94 5	97.18 23	100.00 1	93.81 282	99.94 58	99.98 57

TAPA-MVS	92.12 8	94.42 268	93.60 274	96.90 258	99.33 110	91.78 346	99.78 179	98.00 243	89.89 353	94.52 282	99.47 138	91.97 168	99.18 204	69.90 481	99.52 114	99.73 120
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
reproduce_monomvs		95.38 232	95.07 229	96.32 280	99.32 112	96.60 156	99.76 191	98.85 62	96.65 74	87.83 398	96.05 368	99.52 1	98.11 320	96.58 217	81.07 412	94.25 365

fmvsm_s_conf0.5_n_9		98.15 73	98.02 68	98.55 124	99.28 113	95.84 188	99.99 8	98.57 107	98.17 13	99.93 3	99.74 88	87.04 246	99.97 64	99.86 27	99.59 108	99.83 105

SPE-MVS-test		97.88 86	97.94 77	97.70 195	99.28 113	95.20 227	99.98 24	97.15 363	95.53 114	99.62 62	99.79 63	92.08 166	98.38 297	98.75 107	99.28 139	99.52 173

test_fmvsm_n_1920		98.44 49	98.61 30	97.92 174	99.27 115	95.18 228	100.00 1	98.90 50	98.05 20	99.80 28	99.73 92	92.64 145	99.99 39	99.58 57	99.51 117	98.59 286

fmvsm_s_conf0.5_n_10		98.24 69	97.90 80	99.26 55	99.24 116	97.88 92	99.99 8	98.76 73	98.20 9	99.92 5	99.74 88	85.97 265	99.94 94	99.72 46	99.53 113	99.96 75

fmvsm_l_conf0.5_n_a		99.00 18	98.91 15	99.28 53	99.21 117	97.91 91	99.98 24	98.85 62	98.25 5	99.92 5	99.75 81	94.72 74	99.97 64	99.87 25	99.64 97	99.95 83

fmvsm_s_conf0.5_n_8		98.38 57	98.05 66	99.35 50	99.20 118	98.12 77	99.98 24	98.81 67	98.22 7	99.80 28	99.71 98	87.37 241	99.97 64	99.91 19	99.48 121	99.97 67

test_yl		97.83 92	97.37 111	99.21 60	99.18 119	97.98 86	99.64 238	99.27 27	91.43 303	97.88 178	98.99 206	95.84 46	99.84 138	98.82 101	95.32 287	99.79 112

DCV-MVSNet		97.83 92	97.37 111	99.21 60	99.18 119	97.98 86	99.64 238	99.27 27	91.43 303	97.88 178	98.99 206	95.84 46	99.84 138	98.82 101	95.32 287	99.79 112

fmvsm_l_conf0.5_n		98.94 19	98.84 19	99.25 56	99.17 121	97.81 96	99.98 24	98.86 59	98.25 5	99.90 7	99.76 73	94.21 97	99.97 64	99.87 25	99.52 114	99.98 57

DeepC-MVS	94.51 4	96.92 149	96.40 159	98.45 138	99.16 122	95.90 186	99.66 233	98.06 237	96.37 89	94.37 288	99.49 137	83.29 317	99.90 113	97.63 175	99.61 104	99.55 164
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 41	98.22 52	99.50 35	99.15 123	98.65 58	100.00 1	98.58 105	97.70 32	98.21 165	99.24 172	92.58 148	99.94 94	98.63 116	99.94 58	99.92 93
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 53	98.08 64	99.39 46	99.12 124	98.29 70	99.98 24	98.64 91	98.14 16	99.86 16	99.76 73	87.99 229	99.97 64	99.72 46	99.54 111	99.91 95

fmvsm_l_conf0.5_n_9		98.55 40	98.23 51	99.49 37	99.10 125	98.50 65	99.99 8	98.70 80	98.14 16	99.94 2	99.68 112	89.02 217	99.98 51	99.89 21	99.61 104	99.99 26

CS-MVS		97.79 99	97.91 79	97.43 227	99.10 125	94.42 257	99.99 8	97.10 377	95.07 123	99.68 52	99.75 81	92.95 134	98.34 301	98.38 128	99.14 145	99.54 168

Anonymous202405211		93.10 310	91.99 323	96.40 276	99.10 125	89.65 399	98.88 365	97.93 251	83.71 441	94.00 294	98.75 244	68.79 438	99.88 124	95.08 246	91.71 320	99.68 131

fmvsm_s_conf0.5_n		97.80 97	97.85 85	97.67 196	99.06 128	94.41 258	99.98 24	98.97 43	97.34 42	99.63 59	99.69 105	87.27 242	99.97 64	99.62 55	99.06 151	98.62 285

HyFIR lowres test		96.66 166	96.43 156	97.36 235	99.05 129	93.91 280	99.70 224	99.80 3	90.54 336	96.26 244	98.08 295	92.15 164	98.23 314	96.84 205	95.46 282	99.93 88

LFMVS		94.75 254	93.56 277	98.30 148	99.03 130	95.70 196	98.74 380	97.98 246	87.81 394	98.47 148	99.39 149	67.43 447	99.53 175	98.01 152	95.20 290	99.67 133

fmvsm_s_conf0.5_n_4		97.75 102	97.86 84	97.42 228	99.01 131	94.69 247	99.97 42	98.76 73	97.91 25	99.87 14	99.76 73	86.70 253	99.93 104	99.67 52	99.12 148	97.64 316

fmvsm_s_conf0.5_n_2		97.59 112	97.28 115	98.53 130	99.01 131	98.15 72	99.98 24	98.59 103	98.17 13	99.75 42	99.63 122	81.83 330	99.94 94	99.78 35	98.79 162	97.51 324

AllTest		92.48 327	91.64 330	95.00 323	99.01 131	88.43 417	98.94 357	96.82 419	86.50 411	88.71 374	98.47 278	74.73 412	99.88 124	85.39 411	96.18 256	96.71 330

TestCases				95.00 323	99.01 131	88.43 417		96.82 419	86.50 411	88.71 374	98.47 278	74.73 412	99.88 124	85.39 411	96.18 256	96.71 330

COLMAP_ROB	90.47 14	92.18 334	91.49 336	94.25 357	99.00 135	88.04 423	98.42 405	96.70 426	82.30 453	88.43 386	99.01 199	76.97 387	99.85 130	86.11 407	96.50 247	94.86 341
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 81	97.66 94	98.81 101	98.99 136	98.07 80	99.98 24	98.81 67	98.18 12	99.89 11	99.70 101	84.15 303	99.97 64	99.76 40	99.50 119	98.39 293

test_fmvs1		95.35 233	95.68 199	94.36 353	98.99 136	84.98 445	99.96 56	96.65 428	97.60 34	99.73 47	98.96 212	71.58 428	99.93 104	98.31 134	99.37 134	98.17 299

HY-MVS	92.50 7	97.79 99	97.17 122	99.63 19	98.98 138	99.32 10	97.49 434	99.52 14	95.69 109	98.32 157	97.41 316	93.32 121	99.77 150	98.08 149	95.75 272	99.81 109

VNet		97.21 131	96.57 149	99.13 77	98.97 139	97.82 95	99.03 344	99.21 32	94.31 159	99.18 105	98.88 225	86.26 260	99.89 118	98.93 92	94.32 300	99.69 130

thres200		96.96 145	96.21 166	99.22 59	98.97 139	98.84 38	99.85 147	99.71 7	93.17 215	96.26 244	98.88 225	89.87 203	99.51 178	94.26 270	94.91 292	99.31 219

tfpn200view9		96.79 154	95.99 175	99.19 62	98.94 141	98.82 39	99.78 179	99.71 7	92.86 231	96.02 254	98.87 232	89.33 210	99.50 180	93.84 279	94.57 296	99.27 228

thres400		96.78 156	95.99 175	99.16 69	98.94 141	98.82 39	99.78 179	99.71 7	92.86 231	96.02 254	98.87 232	89.33 210	99.50 180	93.84 279	94.57 296	99.16 240

sasdasda		97.09 138	96.32 160	99.39 46	98.93 143	98.95 29	99.72 212	97.35 321	94.45 147	97.88 178	99.42 142	86.71 251	99.52 176	98.48 123	93.97 306	99.72 122

Anonymous20231211		89.86 385	88.44 393	94.13 365	98.93 143	90.68 377	98.54 396	98.26 207	76.28 476	86.73 412	95.54 384	70.60 434	97.56 346	90.82 336	80.27 421	94.15 381

canonicalmvs		97.09 138	96.32 160	99.39 46	98.93 143	98.95 29	99.72 212	97.35 321	94.45 147	97.88 178	99.42 142	86.71 251	99.52 176	98.48 123	93.97 306	99.72 122

SDMVSNet		94.80 249	93.96 264	97.33 238	98.92 146	95.42 209	99.59 250	98.99 40	92.41 264	92.55 312	97.85 307	75.81 402	98.93 221	97.90 161	91.62 321	97.64 316

sd_testset		93.55 299	92.83 303	95.74 301	98.92 146	90.89 373	98.24 412	98.85 62	92.41 264	92.55 312	97.85 307	71.07 433	98.68 261	93.93 276	91.62 321	97.64 316

EPNet_dtu		95.71 221	95.39 211	96.66 267	98.92 146	93.41 299	99.57 256	98.90 50	96.19 95	97.52 188	98.56 268	92.65 144	97.36 351	77.89 462	98.33 175	99.20 237
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WTY-MVS		98.10 76	97.60 98	99.60 24	98.92 146	99.28 18	99.89 127	99.52 14	95.58 112	98.24 163	99.39 149	93.33 120	99.74 156	97.98 156	95.58 281	99.78 115

CHOSEN 1792x2688		96.81 153	96.53 150	97.64 200	98.91 150	93.07 306	99.65 234	99.80 3	95.64 110	95.39 270	98.86 234	84.35 301	99.90 113	96.98 197	99.16 144	99.95 83

thres100view900		96.74 161	95.92 187	99.18 63	98.90 151	98.77 47	99.74 201	99.71 7	92.59 251	95.84 257	98.86 234	89.25 212	99.50 180	93.84 279	94.57 296	99.27 228

thres600view7		96.69 164	95.87 191	99.14 73	98.90 151	98.78 46	99.74 201	99.71 7	92.59 251	95.84 257	98.86 234	89.25 212	99.50 180	93.44 292	94.50 299	99.16 240

MSDG		94.37 270	93.36 289	97.40 231	98.88 153	93.95 279	99.37 294	97.38 316	85.75 422	90.80 331	99.17 181	84.11 305	99.88 124	86.35 403	98.43 173	98.36 295

MGCFI-Net		97.00 143	96.22 165	99.34 51	98.86 154	98.80 41	99.67 232	97.30 333	94.31 159	97.77 184	99.41 146	86.36 258	99.50 180	98.38 128	93.90 308	99.72 122

h-mvs33		94.92 246	94.36 249	96.59 269	98.85 155	91.29 365	98.93 359	98.94 44	95.90 101	98.77 129	98.42 281	90.89 188	99.77 150	97.80 166	70.76 466	98.72 282

Anonymous20240529		92.10 335	90.65 347	96.47 271	98.82 156	90.61 379	98.72 382	98.67 87	75.54 480	93.90 296	98.58 266	66.23 452	99.90 113	94.70 260	90.67 324	98.90 271

PVSNet_Blended_VisFu		97.27 127	96.81 137	98.66 113	98.81 157	96.67 152	99.92 103	98.64 91	94.51 144	96.38 242	98.49 274	89.05 216	99.88 124	97.10 192	98.34 174	99.43 194

PS-MVSNAJ		98.44 49	98.20 54	99.16 69	98.80 158	98.92 31	99.54 265	98.17 222	97.34 42	99.85 20	99.85 38	91.20 177	99.89 118	99.41 68	99.67 94	98.69 283

CANet_DTU		96.76 157	96.15 169	98.60 118	98.78 159	97.53 108	99.84 152	97.63 284	97.25 50	99.20 102	99.64 119	81.36 336	99.98 51	92.77 304	98.89 156	98.28 297

mvsany_test1		97.82 95	97.90 80	97.55 211	98.77 160	93.04 309	99.80 173	97.93 251	96.95 61	99.61 69	99.68 112	90.92 185	99.83 140	99.18 77	98.29 179	99.80 111

alignmvs		97.81 96	97.33 113	99.25 56	98.77 160	98.66 56	99.99 8	98.44 148	94.40 155	98.41 152	99.47 138	93.65 113	99.42 190	98.57 117	94.26 302	99.67 133

SymmetryMVS		97.64 110	97.46 104	98.17 154	98.74 162	95.39 212	99.61 245	99.26 29	96.52 78	98.61 140	99.31 157	92.73 141	99.67 168	96.77 211	95.63 279	99.45 190

SteuartSystems-ACMMP		99.02 15	98.97 14	99.18 63	98.72 163	97.71 100	99.98 24	98.44 148	96.85 64	99.80 28	99.91 19	97.57 9	99.85 130	99.44 66	99.99 21	99.99 26
Skip Steuart: Steuart Systems R&D Blog.
xiu_mvs_v2_base		98.23 71	97.97 72	99.02 88	98.69 164	98.66 56	99.52 267	98.08 236	97.05 56	99.86 16	99.86 34	90.65 190	99.71 160	99.39 70	98.63 166	98.69 283

miper_enhance_ethall		94.36 272	93.98 263	95.49 304	98.68 165	95.24 224	99.73 208	97.29 341	93.28 210	89.86 345	95.97 369	94.37 88	97.05 374	92.20 308	84.45 383	94.19 373

fmvsm_s_conf0.5_n_5		98.08 77	97.71 92	99.17 66	98.67 166	97.69 104	99.99 8	98.57 107	97.40 40	99.89 11	99.69 105	85.99 264	99.96 76	99.80 32	99.40 132	99.85 103

ETVMVS		97.03 142	96.64 145	98.20 153	98.67 166	97.12 129	99.89 127	98.57 107	91.10 316	98.17 166	98.59 263	93.86 108	98.19 316	95.64 238	95.24 289	99.28 226

test2506		97.53 114	97.19 120	98.58 122	98.66 168	96.90 140	98.81 374	99.77 5	94.93 126	97.95 173	98.96 212	92.51 151	99.20 202	94.93 250	98.15 183	99.64 139

ECVR-MVS		95.66 224	95.05 230	97.51 216	98.66 168	93.71 284	98.85 371	98.45 143	94.93 126	96.86 215	98.96 212	75.22 408	99.20 202	95.34 240	98.15 183	99.64 139

BridgeMVS		98.27 63	97.99 70	99.11 78	98.64 170	98.43 68	99.47 277	97.79 266	94.56 142	99.74 45	98.35 283	94.33 91	99.25 196	99.12 79	99.96 46	99.64 139

fmvsm_s_conf0.5_n_a		97.73 105	97.72 90	97.77 189	98.63 171	94.26 265	99.96 56	98.92 49	97.18 52	99.75 42	99.69 105	87.00 248	99.97 64	99.46 64	98.89 156	99.08 250

MVSMamba_PlusPlus		97.83 92	97.45 106	98.99 90	98.60 172	98.15 72	99.58 252	97.74 275	90.34 344	99.26 101	98.32 286	94.29 93	99.23 197	99.03 88	99.89 73	99.58 160

balanced_ft_v1		96.88 150	96.52 151	97.96 169	98.60 172	94.94 236	99.41 285	97.56 296	93.53 195	99.42 86	97.89 306	83.33 316	99.31 193	99.29 73	99.62 99	99.64 139

testing222		97.08 141	96.75 140	98.06 164	98.56 174	96.82 142	99.85 147	98.61 99	92.53 259	98.84 123	98.84 238	93.36 118	98.30 306	95.84 234	94.30 301	99.05 254

test1111		95.57 227	94.98 233	97.37 233	98.56 174	93.37 302	98.86 369	98.45 143	94.95 125	96.63 224	98.95 217	75.21 409	99.11 208	95.02 247	98.14 185	99.64 139

MVSTER		95.53 228	95.22 222	96.45 274	98.56 174	97.72 99	99.91 111	97.67 280	92.38 267	91.39 322	97.14 323	97.24 20	97.30 358	94.80 256	87.85 353	94.34 360

testing3-2		97.72 106	97.43 109	98.60 118	98.55 177	97.11 131	100.00 1	99.23 31	93.78 187	97.90 175	98.73 246	95.50 53	99.69 164	98.53 121	94.63 294	98.99 262

VDD-MVS		93.77 292	92.94 301	96.27 281	98.55 177	90.22 388	98.77 379	97.79 266	90.85 322	96.82 219	99.42 142	61.18 472	99.77 150	98.95 90	94.13 303	98.82 275

tpmvs		94.28 274	93.57 276	96.40 276	98.55 177	91.50 363	95.70 473	98.55 119	87.47 396	92.15 315	94.26 438	91.42 173	98.95 220	88.15 381	95.85 267	98.76 278

UGNet		95.33 234	94.57 245	97.62 204	98.55 177	94.85 238	98.67 388	99.32 26	95.75 107	96.80 221	96.27 358	72.18 425	99.96 76	94.58 263	99.05 152	98.04 304
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	95.18 237	94.10 257	98.43 140	98.55 177	95.99 184	97.91 427	97.31 332	90.35 343	89.48 358	99.22 173	85.19 281	99.89 118	90.40 346	98.47 172	99.41 198
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS-28		95.95 204	96.49 152	94.34 354	98.51 182	89.99 393	99.39 290	98.57 107	93.14 218	97.33 197	98.31 288	93.44 116	94.68 463	93.69 289	95.98 261	98.34 296

UWE-MVS		96.79 154	96.72 142	97.00 252	98.51 182	93.70 285	99.71 217	98.60 101	92.96 226	97.09 205	98.34 285	96.67 33	98.85 228	92.11 314	96.50 247	98.44 291

myMVS_eth3d28		97.86 88	97.59 100	98.68 110	98.50 184	97.26 121	99.92 103	98.55 119	93.79 186	98.26 161	98.75 244	95.20 58	99.48 186	98.93 92	96.40 250	99.29 224

test_vis1_n_1920		95.44 230	95.31 218	95.82 298	98.50 184	88.74 411	99.98 24	97.30 333	97.84 28	99.85 20	99.19 179	66.82 450	99.97 64	98.82 101	99.46 126	98.76 278

BH-w/o		95.71 221	95.38 216	96.68 266	98.49 186	92.28 328	99.84 152	97.50 305	92.12 277	92.06 318	98.79 242	84.69 294	98.67 263	95.29 242	99.66 95	99.09 248

baseline1		95.78 217	94.86 236	98.54 128	98.47 187	98.07 80	99.06 337	97.99 244	92.68 245	94.13 293	98.62 260	93.28 124	98.69 260	93.79 284	85.76 370	98.84 274

fmvsm_s_conf0.5_n_7		97.70 108	97.74 89	97.59 209	98.44 188	95.16 230	99.97 42	98.65 88	97.95 24	99.62 62	99.78 67	86.09 262	99.94 94	99.69 50	99.50 119	97.66 314

EPMVS		96.53 174	96.01 174	98.09 162	98.43 189	96.12 182	96.36 460	99.43 20	93.53 195	97.64 186	95.04 412	94.41 83	98.38 297	91.13 327	98.11 186	99.75 118

kuosan		93.17 307	92.60 309	94.86 330	98.40 190	89.54 401	98.44 401	98.53 126	84.46 436	88.49 381	97.92 303	90.57 192	97.05 374	83.10 428	93.49 311	97.99 305

WBMVS		94.52 263	94.03 261	95.98 288	98.38 191	96.68 151	99.92 103	97.63 284	90.75 331	89.64 353	95.25 405	96.77 27	96.90 387	94.35 268	83.57 390	94.35 358

UBG		97.84 91	97.69 93	98.29 149	98.38 191	96.59 158	99.90 117	98.53 126	93.91 182	98.52 144	98.42 281	96.77 27	99.17 205	98.54 119	96.20 255	99.11 247

sss		97.57 113	97.03 127	99.18 63	98.37 193	98.04 83	99.73 208	99.38 22	93.46 200	98.76 132	99.06 193	91.21 176	99.89 118	96.33 224	97.01 233	99.62 147

testing11		97.48 116	97.27 116	98.10 161	98.36 194	96.02 183	99.92 103	98.45 143	93.45 202	98.15 167	98.70 250	95.48 54	99.22 198	97.85 163	95.05 291	99.07 251

BH-untuned		95.18 237	94.83 237	96.22 282	98.36 194	91.22 366	99.80 173	97.32 331	90.91 320	91.08 325	98.67 252	83.51 309	98.54 279	94.23 271	99.61 104	98.92 268

testing91		97.16 133	96.90 131	97.97 168	98.35 196	95.67 199	99.91 111	98.42 168	92.91 229	97.33 197	98.72 247	94.81 72	99.21 199	96.98 197	94.63 294	99.03 259

testing99		97.17 132	96.91 130	97.95 170	98.35 196	95.70 196	99.91 111	98.43 156	92.94 227	97.36 195	98.72 247	94.83 71	99.21 199	97.00 195	94.64 293	98.95 264

ET-MVSNet_ETH3D		94.37 270	93.28 291	97.64 200	98.30 198	97.99 85	99.99 8	97.61 290	94.35 156	71.57 488	99.45 141	96.23 39	95.34 453	96.91 203	85.14 377	99.59 154

AUN-MVS		93.28 304	92.60 309	95.34 313	98.29 199	90.09 391	99.31 304	98.56 113	91.80 290	96.35 243	98.00 298	89.38 209	98.28 309	92.46 305	69.22 473	97.64 316

FMVSNet3		92.69 322	91.58 332	95.99 287	98.29 199	97.42 116	99.26 316	97.62 287	89.80 354	89.68 349	95.32 399	81.62 334	96.27 428	87.01 399	85.65 371	94.29 362

PMMVS		96.76 157	96.76 139	96.76 263	98.28 201	92.10 332	99.91 111	97.98 246	94.12 168	99.53 74	99.39 149	86.93 249	98.73 251	96.95 200	97.73 194	99.45 190

hse-mvs2		94.38 269	94.08 260	95.31 315	98.27 202	90.02 392	99.29 311	98.56 113	95.90 101	98.77 129	98.00 298	90.89 188	98.26 313	97.80 166	69.20 474	97.64 316

PVSNet_0	88.03 19	91.80 342	90.27 356	96.38 278	98.27 202	90.46 383	99.94 93	99.61 13	93.99 176	86.26 422	97.39 318	71.13 432	99.89 118	98.77 105	67.05 480	98.79 277

UA-Net		96.54 173	95.96 181	98.27 150	98.23 204	95.71 195	98.00 424	98.45 143	93.72 191	98.41 152	99.27 165	88.71 223	99.66 171	91.19 326	97.69 195	99.44 193

test_cas_vis1_n_1920		96.59 169	96.23 163	97.65 199	98.22 205	94.23 267	99.99 8	97.25 346	97.77 29	99.58 70	99.08 189	77.10 382	99.97 64	97.64 174	99.45 127	98.74 280

FE-MVS		95.70 223	95.01 232	97.79 185	98.21 206	94.57 249	95.03 474	98.69 82	88.90 370	97.50 190	96.19 360	92.60 147	99.49 185	89.99 351	97.94 192	99.31 219

GG-mvs-BLEND				98.54 128	98.21 206	98.01 84	93.87 479	98.52 128		97.92 174	97.92 303	99.02 3	97.94 333	98.17 142	99.58 109	99.67 133

mvs_anonymous		95.65 225	95.03 231	97.53 213	98.19 208	95.74 193	99.33 299	97.49 306	90.87 321	90.47 334	97.10 325	88.23 226	97.16 365	95.92 232	97.66 198	99.68 131

MVS_Test		96.46 177	95.74 195	98.61 117	98.18 209	97.23 123	99.31 304	97.15 363	91.07 317	98.84 123	97.05 329	88.17 227	98.97 217	94.39 265	97.50 200	99.61 151

BH-RMVSNet		95.18 237	94.31 252	97.80 183	98.17 210	95.23 225	99.76 191	97.53 301	92.52 260	94.27 291	99.25 171	76.84 389	98.80 240	90.89 335	99.54 111	99.35 209

dongtai		91.55 348	91.13 341	92.82 406	98.16 211	86.35 435	99.47 277	98.51 131	83.24 444	85.07 433	97.56 312	90.33 197	94.94 459	76.09 470	91.73 319	97.18 327

RPSCF		91.80 342	92.79 305	88.83 449	98.15 212	69.87 491	98.11 420	96.60 430	83.93 439	94.33 289	99.27 165	79.60 360	99.46 189	91.99 315	93.16 316	97.18 327

ETV-MVS		97.92 84	97.80 88	98.25 151	98.14 213	96.48 160	99.98 24	97.63 284	95.61 111	99.29 98	99.46 140	92.55 149	98.82 232	99.02 89	98.54 170	99.46 185

IS-MVSNet		96.29 190	95.90 188	97.45 223	98.13 214	94.80 242	99.08 332	97.61 290	92.02 282	95.54 268	98.96 212	90.64 191	98.08 322	93.73 287	97.41 204	99.47 183

test_fmvsmconf_n		98.43 51	98.32 47	98.78 103	98.12 215	96.41 163	99.99 8	98.83 66	98.22 7	99.67 53	99.64 119	91.11 181	99.94 94	99.67 52	99.62 99	99.98 57

fmvsm_s_conf0.1_n_2		97.25 128	96.85 134	98.43 140	98.08 216	98.08 79	99.92 103	97.76 274	98.05 20	99.65 55	99.58 128	80.88 344	99.93 104	99.59 56	98.17 181	97.29 325

ab-mvs		94.69 255	93.42 282	98.51 133	98.07 217	96.26 170	96.49 458	98.68 84	90.31 345	94.54 281	97.00 332	76.30 397	99.71 160	95.98 231	93.38 314	99.56 163

XVG-OURS-SEG-HR		94.79 250	94.70 244	95.08 320	98.05 218	89.19 403	99.08 332	97.54 299	93.66 192	94.87 277	99.58 128	78.78 368	99.79 145	97.31 182	93.40 313	96.25 334

EIA-MVS		97.53 114	97.46 104	97.76 191	98.04 219	94.84 239	99.98 24	97.61 290	94.41 154	97.90 175	99.59 125	92.40 155	98.87 225	98.04 151	99.13 146	99.59 154

XVG-OURS		94.82 247	94.74 243	95.06 321	98.00 220	89.19 403	99.08 332	97.55 297	94.10 169	94.71 279	99.62 123	80.51 351	99.74 156	96.04 230	93.06 318	96.25 334

mvsmamba		96.94 146	96.73 141	97.55 211	97.99 221	94.37 262	99.62 241	97.70 277	93.13 219	98.42 151	97.92 303	88.02 228	98.75 249	98.78 104	99.01 153	99.52 173

dp		95.05 241	94.43 247	96.91 256	97.99 221	92.73 317	96.29 463	97.98 246	89.70 355	95.93 256	94.67 427	93.83 110	98.45 285	86.91 402	96.53 246	99.54 168

tpmrst		96.27 192	95.98 177	97.13 247	97.96 223	93.15 305	96.34 461	98.17 222	92.07 278	98.71 135	95.12 409	93.91 105	98.73 251	94.91 253	96.62 244	99.50 179

TR-MVS		94.54 260	93.56 277	97.49 221	97.96 223	94.34 263	98.71 383	97.51 304	90.30 346	94.51 283	98.69 251	75.56 403	98.77 245	92.82 303	95.99 260	99.35 209

Vis-MVSNet (Re-imp)		96.32 187	95.98 177	97.35 237	97.93 225	94.82 241	99.47 277	98.15 230	91.83 287	95.09 275	99.11 187	91.37 175	97.47 349	93.47 291	97.43 201	99.74 119

MDTV_nov1_ep13			95.69 197		97.90 226	94.15 271	95.98 469	98.44 148	93.12 220	97.98 172	95.74 373	95.10 61	98.58 272	90.02 350	96.92 235

Fast-Effi-MVS+		95.02 243	94.19 255	97.52 215	97.88 227	94.55 250	99.97 42	97.08 381	88.85 372	94.47 284	97.96 302	84.59 296	98.41 289	89.84 353	97.10 224	99.59 154

ADS-MVSNet2		93.80 291	93.88 267	93.55 389	97.87 228	85.94 439	94.24 475	96.84 416	90.07 349	96.43 239	94.48 432	90.29 199	95.37 452	87.44 388	97.23 212	99.36 205

ADS-MVSNet		94.79 250	94.02 262	97.11 249	97.87 228	93.79 281	94.24 475	98.16 227	90.07 349	96.43 239	94.48 432	90.29 199	98.19 316	87.44 388	97.23 212	99.36 205

Effi-MVS+		96.30 189	95.69 197	98.16 155	97.85 230	96.26 170	97.41 437	97.21 354	90.37 342	98.65 138	98.58 266	86.61 255	98.70 258	97.11 191	97.37 206	99.52 173

PatchmatchNet		95.94 205	95.45 206	97.39 232	97.83 231	94.41 258	96.05 467	98.40 177	92.86 231	97.09 205	95.28 404	94.21 97	98.07 324	89.26 362	98.11 186	99.70 125
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
cascas		94.64 258	93.61 272	97.74 193	97.82 232	96.26 170	99.96 56	97.78 270	85.76 420	94.00 294	97.54 313	76.95 388	99.21 199	97.23 187	95.43 284	97.76 313

1112_ss		96.01 202	95.20 223	98.42 142	97.80 233	96.41 163	99.65 234	96.66 427	92.71 242	92.88 308	99.40 147	92.16 163	99.30 194	91.92 317	93.66 309	99.55 164

E3new		96.75 159	96.43 156	97.71 194	97.79 234	94.83 240	99.80 173	97.33 325	93.52 198	97.49 191	99.31 157	87.73 231	98.83 229	97.52 177	97.40 205	99.48 182

Test_1112_low_res		95.72 219	94.83 237	98.42 142	97.79 234	96.41 163	99.65 234	96.65 428	92.70 243	92.86 309	96.13 364	92.15 164	99.30 194	91.88 318	93.64 310	99.55 164

Effi-MVS+-dtu		94.53 262	95.30 219	92.22 414	97.77 236	82.54 462	99.59 250	97.06 390	94.92 128	95.29 272	95.37 397	85.81 266	97.89 334	94.80 256	97.07 225	96.23 336

tpm cat1		93.51 300	92.52 315	96.47 271	97.77 236	91.47 364	96.13 465	98.06 237	80.98 459	92.91 307	93.78 443	89.66 204	98.87 225	87.03 398	96.39 251	99.09 248

FA-MVS(test-final)		95.86 208	95.09 228	98.15 158	97.74 238	95.62 201	96.31 462	98.17 222	91.42 305	96.26 244	96.13 364	90.56 193	99.47 188	92.18 309	97.07 225	99.35 209

xiu_mvs_v1_base_debu		97.43 117	97.06 123	98.55 124	97.74 238	98.14 74	99.31 304	97.86 260	96.43 83	99.62 62	99.69 105	85.56 273	99.68 165	99.05 82	98.31 176	97.83 309

xiu_mvs_v1_base		97.43 117	97.06 123	98.55 124	97.74 238	98.14 74	99.31 304	97.86 260	96.43 83	99.62 62	99.69 105	85.56 273	99.68 165	99.05 82	98.31 176	97.83 309

xiu_mvs_v1_base_debi		97.43 117	97.06 123	98.55 124	97.74 238	98.14 74	99.31 304	97.86 260	96.43 83	99.62 62	99.69 105	85.56 273	99.68 165	99.05 82	98.31 176	97.83 309

EPP-MVSNet		96.69 164	96.60 147	96.96 254	97.74 238	93.05 308	99.37 294	98.56 113	88.75 374	95.83 259	99.01 199	96.01 40	98.56 275	96.92 201	97.20 214	99.25 232

gg-mvs-nofinetune		93.51 300	91.86 327	98.47 135	97.72 243	97.96 89	92.62 489	98.51 131	74.70 483	97.33 197	69.59 512	98.91 4	97.79 337	97.77 171	99.56 110	99.67 133

IB-MVS	92.85 6	94.99 244	93.94 265	98.16 155	97.72 243	95.69 198	99.99 8	98.81 67	94.28 162	92.70 310	96.90 336	95.08 62	99.17 205	96.07 229	73.88 454	99.60 153
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		97.41 122	97.02 128	98.59 121	97.71 245	97.52 109	99.97 42	98.54 123	91.83 287	97.45 192	99.04 195	97.50 10	99.10 209	94.75 258	96.37 252	99.16 240

VortexMVS		94.11 278	93.50 279	95.94 290	97.70 246	96.61 155	99.35 297	97.18 357	93.52 198	89.57 356	95.74 373	87.55 236	96.97 382	95.76 237	85.13 378	94.23 367

viewdifsd2359ckpt09		96.21 195	95.77 193	97.53 213	97.69 247	94.50 253	99.78 179	97.23 351	92.88 230	96.58 227	99.26 169	84.85 287	98.66 266	96.61 215	97.02 231	99.43 194

Syy-MVS		90.00 383	90.63 348	88.11 457	97.68 248	74.66 488	99.71 217	98.35 190	90.79 328	92.10 316	98.67 252	79.10 366	93.09 479	63.35 496	95.95 264	96.59 332

myMVS_eth3d		94.46 267	94.76 242	93.55 389	97.68 248	90.97 368	99.71 217	98.35 190	90.79 328	92.10 316	98.67 252	92.46 154	93.09 479	87.13 395	95.95 264	96.59 332

test_fmvs1_n		94.25 275	94.36 249	93.92 376	97.68 248	83.70 452	99.90 117	96.57 431	97.40 40	99.67 53	98.88 225	61.82 469	99.92 110	98.23 140	99.13 146	98.14 302

fmvsm_s_conf0.5_n_6		98.27 63	97.96 75	99.23 58	97.66 251	98.11 78	99.98 24	98.64 91	97.85 27	99.87 14	99.72 95	88.86 220	99.93 104	99.64 54	99.36 135	99.63 146

RRT-MVS		96.24 194	95.68 199	97.94 173	97.65 252	94.92 237	99.27 314	97.10 377	92.79 237	97.43 193	97.99 300	81.85 329	99.37 192	98.46 125	98.57 167	99.53 172

diffmvs		97.00 143	96.64 145	98.09 162	97.64 253	96.17 179	99.81 167	97.19 355	94.67 140	98.95 118	99.28 161	86.43 256	98.76 247	98.37 130	97.42 203	99.33 212
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewcassd2359sk11		96.59 169	96.23 163	97.66 198	97.63 254	94.70 245	99.77 185	97.33 325	93.41 203	97.34 196	99.17 181	86.72 250	98.83 229	97.40 180	97.32 209	99.46 185

viewdifsd2359ckpt13		96.19 196	95.77 193	97.45 223	97.62 255	94.40 260	99.70 224	97.23 351	92.76 239	96.63 224	99.05 194	84.96 286	98.64 268	96.65 214	97.35 207	99.31 219

Vis-MVSNet		95.72 219	95.15 226	97.45 223	97.62 255	94.28 264	99.28 312	98.24 210	94.27 164	96.84 217	98.94 219	79.39 361	98.76 247	93.25 294	98.49 171	99.30 222
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
thisisatest0530		97.10 136	96.72 142	98.22 152	97.60 257	96.70 148	99.92 103	98.54 123	91.11 315	97.07 207	98.97 210	97.47 13	99.03 212	93.73 287	96.09 258	98.92 268

GDP-MVS		97.88 86	97.59 100	98.75 106	97.59 258	97.81 96	99.95 75	97.37 319	94.44 150	99.08 110	99.58 128	97.13 25	99.08 210	94.99 248	98.17 181	99.37 203

miper_ehance_all_eth		93.16 308	92.60 309	94.82 331	97.57 259	93.56 294	99.50 271	97.07 389	88.75 374	88.85 373	95.52 386	90.97 184	96.74 398	90.77 337	84.45 383	94.17 375

guyue		97.15 134	96.82 136	98.15 158	97.56 260	96.25 174	99.71 217	97.84 263	95.75 107	98.13 168	98.65 255	87.58 235	98.82 232	98.29 136	97.91 193	99.36 205

viewmanbaseed2359cas		96.45 178	96.07 171	97.59 209	97.55 261	94.59 248	99.70 224	97.33 325	93.62 194	97.00 211	99.32 154	85.57 272	98.71 255	97.26 186	97.33 208	99.47 183

testing3		93.92 284	94.23 254	92.99 403	97.54 262	90.23 387	99.99 8	99.16 33	90.57 335	91.33 324	98.63 259	92.99 132	92.52 483	82.46 432	95.39 285	96.22 337

SSM_0404		95.75 218	95.16 225	97.50 218	97.53 263	95.39 212	99.11 328	97.25 346	90.81 324	95.27 273	98.83 239	84.74 291	98.67 263	95.24 243	97.69 195	98.45 290

LCM-MVSNet-Re		92.31 331	92.60 309	91.43 423	97.53 263	79.27 480	99.02 346	91.83 497	92.07 278	80.31 458	94.38 436	83.50 310	95.48 449	97.22 188	97.58 199	99.54 168

GBi-Net		90.88 359	89.82 365	94.08 367	97.53 263	91.97 333	98.43 402	96.95 404	87.05 402	89.68 349	94.72 423	71.34 429	96.11 434	87.01 399	85.65 371	94.17 375

test1		90.88 359	89.82 365	94.08 367	97.53 263	91.97 333	98.43 402	96.95 404	87.05 402	89.68 349	94.72 423	71.34 429	96.11 434	87.01 399	85.65 371	94.17 375

FMVSNet2		91.02 356	89.56 370	95.41 311	97.53 263	95.74 193	98.98 349	97.41 314	87.05 402	88.43 386	95.00 417	71.34 429	96.24 430	85.12 414	85.21 376	94.25 365

tttt0517		96.85 151	96.49 152	97.92 174	97.48 268	95.89 187	99.85 147	98.54 123	90.72 332	96.63 224	98.93 222	97.47 13	99.02 213	93.03 301	95.76 271	98.85 273

cashybrid2		96.25 193	95.89 189	97.32 240	97.45 269	93.68 287	99.80 173	97.22 353	93.38 204	96.86 215	99.28 161	84.64 295	98.87 225	97.18 189	97.19 215	99.41 198

BP-MVS1		98.33 59	98.18 56	98.81 101	97.44 270	97.98 86	99.96 56	98.17 222	94.88 130	98.77 129	99.59 125	97.59 8	99.08 210	98.24 139	98.93 155	99.36 205

casdiffmvs_mvg		96.43 179	95.94 185	97.89 178	97.44 270	95.47 205	99.86 144	97.29 341	93.35 206	96.03 252	99.19 179	85.39 277	98.72 254	97.89 162	97.04 228	99.49 181
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
E2		96.36 184	95.95 183	97.60 206	97.41 272	94.52 251	99.71 217	97.33 325	93.20 212	97.02 208	99.07 191	85.37 278	98.82 232	97.27 183	97.14 221	99.46 185

EC-MVSNet		97.38 124	97.24 117	97.80 183	97.41 272	95.64 200	99.99 8	97.06 390	94.59 141	99.63 59	99.32 154	89.20 215	98.14 318	98.76 106	99.23 142	99.62 147

viewdifsd2359ckpt07		95.83 211	95.42 208	97.07 250	97.40 274	93.04 309	99.60 248	97.24 349	92.39 266	96.09 251	99.14 186	83.07 320	98.93 221	97.02 194	96.87 236	99.23 235

c3_l		92.53 326	91.87 326	94.52 343	97.40 274	92.99 311	99.40 286	96.93 409	87.86 392	88.69 376	95.44 391	89.95 202	96.44 416	90.45 343	80.69 417	94.14 385

hybrid		96.53 174	96.15 169	97.67 196	97.39 276	95.12 231	99.80 173	97.15 363	93.38 204	98.23 164	99.16 184	85.20 280	98.70 258	97.92 158	97.15 220	99.20 237

viewmambaseed2359dif		95.92 207	95.55 204	97.04 251	97.38 277	93.41 299	99.78 179	96.97 402	91.14 314	96.58 227	99.27 165	84.85 287	98.75 249	96.87 204	97.12 223	98.97 263

fmvsm_s_conf0.1_n		97.30 125	97.21 119	97.60 206	97.38 277	94.40 260	99.90 117	98.64 91	96.47 82	99.51 78	99.65 118	84.99 285	99.93 104	99.22 76	99.09 149	98.46 289

hybridcas		96.09 199	95.62 201	97.50 218	97.37 279	94.44 254	99.84 152	97.16 361	93.16 216	96.03 252	99.21 176	84.19 302	98.65 267	96.53 219	97.07 225	99.42 197

E3		96.36 184	95.95 183	97.60 206	97.37 279	94.52 251	99.71 217	97.33 325	93.18 214	97.02 208	99.07 191	85.45 276	98.82 232	97.27 183	97.14 221	99.46 185

CDS-MVSNet		96.34 186	96.07 171	97.13 247	97.37 279	94.96 234	99.53 266	97.91 255	91.55 297	95.37 271	98.32 286	95.05 64	97.13 368	93.80 283	95.75 272	99.30 222
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
hybridnocas07		96.57 171	96.16 168	97.81 182	97.36 282	95.32 217	99.81 167	97.12 369	94.17 166	98.02 171	98.90 223	85.05 283	98.80 240	97.85 163	97.18 216	99.32 214

TESTMET0.1,1		96.74 161	96.26 162	98.16 155	97.36 282	96.48 160	99.96 56	98.29 203	91.93 283	95.77 260	98.07 296	95.54 50	98.29 307	90.55 341	98.89 156	99.70 125

miper_lstm_enhance		91.81 339	91.39 338	93.06 402	97.34 284	89.18 405	99.38 292	96.79 421	86.70 410	87.47 404	95.22 406	90.00 201	95.86 443	88.26 377	81.37 406	94.15 381

baseline		96.43 179	95.98 177	97.76 191	97.34 284	95.17 229	99.51 269	97.17 359	93.92 181	96.90 214	99.28 161	85.37 278	98.64 268	97.50 178	96.86 238	99.46 185

cl____		92.31 331	91.58 332	94.52 343	97.33 286	92.77 313	99.57 256	96.78 422	86.97 406	87.56 402	95.51 387	89.43 208	96.62 405	88.60 367	82.44 398	94.16 380

SD_0403		92.63 325	93.38 286	90.40 437	97.32 287	77.91 482	97.75 432	98.03 242	91.89 284	90.83 330	98.29 290	82.00 326	93.79 472	88.51 372	95.75 272	99.52 173

DIV-MVS_self_test		92.32 330	91.60 331	94.47 347	97.31 288	92.74 315	99.58 252	96.75 423	86.99 405	87.64 400	95.54 384	89.55 207	96.50 411	88.58 368	82.44 398	94.17 375

casdiffmvs		96.42 181	95.97 180	97.77 189	97.30 289	94.98 233	99.84 152	97.09 380	93.75 190	96.58 227	99.26 169	85.07 282	98.78 244	97.77 171	97.04 228	99.54 168
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		94.36 272	93.48 280	96.99 253	97.29 290	93.54 295	99.96 56	96.72 425	88.35 385	93.43 298	98.94 219	82.05 325	98.05 325	88.12 383	96.48 249	99.37 203

eth_miper_zixun_eth		92.41 329	91.93 324	93.84 380	97.28 291	90.68 377	98.83 372	96.97 402	88.57 379	89.19 368	95.73 376	89.24 214	96.69 403	89.97 352	81.55 404	94.15 381

MVSFormer		96.94 146	96.60 147	97.95 170	97.28 291	97.70 102	99.55 263	97.27 343	91.17 311	99.43 84	99.54 134	90.92 185	96.89 388	94.67 261	99.62 99	99.25 232

lupinMVS		97.85 90	97.60 98	98.62 116	97.28 291	97.70 102	99.99 8	97.55 297	95.50 116	99.43 84	99.67 114	90.92 185	98.71 255	98.40 127	99.62 99	99.45 190

dtuplus		95.79 216	95.42 208	96.93 255	97.24 294	93.16 304	99.78 179	96.93 409	91.69 293	96.18 249	99.29 160	83.80 307	98.73 251	96.83 206	97.02 231	98.89 272

diffmvs_AUTHOR		96.75 159	96.41 158	97.79 185	97.20 295	95.46 206	99.69 227	97.15 363	94.46 146	98.78 127	99.21 176	85.64 270	98.77 245	98.27 137	97.31 210	99.13 244

mamba_0408		94.98 245	94.09 258	97.64 200	97.14 296	95.31 218	93.48 485	97.08 381	90.48 338	94.40 285	98.62 260	84.49 297	98.67 263	93.99 274	97.18 216	98.93 265

SSM_04072		94.77 252	94.09 258	96.82 260	97.14 296	95.31 218	93.48 485	97.08 381	90.48 338	94.40 285	98.62 260	84.49 297	96.21 431	93.99 274	97.18 216	98.93 265

SSM_0407		95.62 226	94.95 234	97.61 205	97.14 296	95.31 218	99.00 347	97.25 346	90.81 324	94.40 285	98.83 239	84.74 291	98.58 272	95.24 243	97.18 216	98.93 265

SCA		94.69 255	93.81 269	97.33 238	97.10 299	94.44 254	98.86 369	98.32 197	93.30 209	96.17 250	95.59 382	76.48 395	97.95 331	91.06 329	97.43 201	99.59 154

viewmacassd2359aftdt		95.93 206	95.45 206	97.36 235	97.09 300	94.12 273	99.57 256	97.26 345	93.05 224	96.50 231	99.17 181	82.76 321	98.68 261	96.61 215	97.04 228	99.28 226

KinetiMVS		96.10 197	95.29 220	98.53 130	97.08 301	97.12 129	99.56 260	98.12 233	94.78 133	98.44 149	98.94 219	80.30 355	99.39 191	91.56 322	98.79 162	99.06 252

TAMVS		95.85 209	95.58 202	96.65 268	97.07 302	93.50 296	99.17 323	97.82 265	91.39 307	95.02 276	98.01 297	92.20 162	97.30 358	93.75 286	95.83 268	99.14 243

Fast-Effi-MVS+-dtu		93.72 295	93.86 268	93.29 394	97.06 303	86.16 436	99.80 173	96.83 417	92.66 246	92.58 311	97.83 309	81.39 335	97.67 342	89.75 354	96.87 236	96.05 339

E4		96.01 202	95.53 205	97.44 226	97.05 304	94.23 267	99.57 256	97.30 333	92.72 240	96.47 233	99.03 196	83.98 306	98.83 229	96.92 201	96.77 239	99.27 228

E5new		95.83 211	95.39 211	97.15 243	97.03 305	93.59 289	99.32 302	97.30 333	92.58 253	96.45 234	99.00 203	83.37 313	98.81 236	96.81 207	96.65 242	99.04 255

E5		95.83 211	95.39 211	97.15 243	97.03 305	93.59 289	99.32 302	97.30 333	92.58 253	96.45 234	99.00 203	83.37 313	98.81 236	96.81 207	96.65 242	99.04 255

CostFormer		96.10 197	95.88 190	96.78 262	97.03 305	92.55 323	97.08 446	97.83 264	90.04 351	98.72 134	94.89 421	95.01 66	98.29 307	96.54 218	95.77 270	99.50 179

test_fmvsmvis_n_1920		97.67 109	97.59 100	97.91 176	97.02 308	95.34 215	99.95 75	98.45 143	97.87 26	97.02 208	99.59 125	89.64 205	99.98 51	99.41 68	99.34 137	98.42 292

test-LLR		96.47 176	96.04 173	97.78 187	97.02 308	95.44 207	99.96 56	98.21 217	94.07 171	95.55 266	96.38 353	93.90 106	98.27 311	90.42 344	98.83 160	99.64 139

test-mter		96.39 182	95.93 186	97.78 187	97.02 308	95.44 207	99.96 56	98.21 217	91.81 289	95.55 266	96.38 353	95.17 59	98.27 311	90.42 344	98.83 160	99.64 139

casdiffseed414692147		95.07 240	94.26 253	97.50 218	97.01 311	94.70 245	99.58 252	97.02 394	91.27 309	94.66 280	98.82 241	80.79 346	98.55 278	93.39 293	95.79 269	99.27 228

E6new		95.83 211	95.39 211	97.14 245	97.00 312	93.58 291	99.31 304	97.30 333	92.57 255	96.45 234	99.01 199	83.44 311	98.81 236	96.80 209	96.66 240	99.04 255

E6		95.83 211	95.39 211	97.14 245	97.00 312	93.58 291	99.31 304	97.30 333	92.57 255	96.45 234	99.01 199	83.44 311	98.81 236	96.80 209	96.66 240	99.04 255

icg_test_0407_2		95.04 242	94.78 241	95.84 297	96.97 314	91.64 355	98.63 391	97.12 369	92.33 269	95.60 264	98.88 225	85.65 268	96.56 408	92.12 310	95.70 275	99.32 214

IMVS_0407		95.21 236	94.80 240	96.46 273	96.97 314	91.64 355	98.81 374	97.12 369	92.33 269	95.60 264	98.88 225	85.65 268	98.42 287	92.12 310	95.70 275	99.32 214

IMVS_0404		93.83 287	93.17 293	95.80 299	96.97 314	91.64 355	97.78 431	97.12 369	92.33 269	90.87 329	98.88 225	76.78 390	96.43 417	92.12 310	95.70 275	99.32 214

IMVS_0403		95.25 235	94.81 239	96.58 270	96.97 314	91.64 355	98.97 354	97.12 369	92.33 269	95.43 269	98.88 225	85.78 267	98.79 242	92.12 310	95.70 275	99.32 214

gm-plane-assit					96.97 314	93.76 283			91.47 301		98.96 212		98.79 242	94.92 251

WB-MVSnew		92.90 314	92.77 306	93.26 396	96.95 319	93.63 288	99.71 217	98.16 227	91.49 298	94.28 290	98.14 293	81.33 337	96.48 414	79.47 451	95.46 282	89.68 481

QAPM		95.40 231	94.17 256	99.10 79	96.92 320	97.71 100	99.40 286	98.68 84	89.31 358	88.94 372	98.89 224	82.48 323	99.96 76	93.12 300	99.83 80	99.62 147

KD-MVS_2432*1600		88.00 405	86.10 409	93.70 385	96.91 321	94.04 274	97.17 443	97.12 369	84.93 431	81.96 447	92.41 459	92.48 152	94.51 465	79.23 453	52.68 510	92.56 446

miper_refine_blended		88.00 405	86.10 409	93.70 385	96.91 321	94.04 274	97.17 443	97.12 369	84.93 431	81.96 447	92.41 459	92.48 152	94.51 465	79.23 453	52.68 510	92.56 446

tpm2		95.47 229	95.18 224	96.35 279	96.91 321	91.70 352	96.96 449	97.93 251	88.04 390	98.44 149	95.40 393	93.32 121	97.97 328	94.00 273	95.61 280	99.38 201

FMVSNet5		88.32 401	87.47 403	90.88 426	96.90 324	88.39 419	97.28 440	95.68 453	82.60 452	84.67 435	92.40 461	79.83 358	91.16 489	76.39 469	81.51 405	93.09 437

3Dnovator+	91.53 11	96.31 188	95.24 221	99.52 33	96.88 325	98.64 59	99.72 212	98.24 210	95.27 121	88.42 388	98.98 208	82.76 321	99.94 94	97.10 192	99.83 80	99.96 75

Patchmatch-test		92.65 324	91.50 335	96.10 285	96.85 326	90.49 382	91.50 495	97.19 355	82.76 451	90.23 335	95.59 382	95.02 65	98.00 327	77.41 464	96.98 234	99.82 107

MVS		96.60 168	95.56 203	99.72 14	96.85 326	99.22 21	98.31 408	98.94 44	91.57 296	90.90 328	99.61 124	86.66 254	99.96 76	97.36 181	99.88 76	99.99 26

3Dnovator	91.47 12	96.28 191	95.34 217	99.08 82	96.82 328	97.47 114	99.45 282	98.81 67	95.52 115	89.39 359	99.00 203	81.97 327	99.95 85	97.27 183	99.83 80	99.84 104

EI-MVSNet		93.73 294	93.40 285	94.74 332	96.80 329	92.69 318	99.06 337	97.67 280	88.96 367	91.39 322	99.02 197	88.75 222	97.30 358	91.07 328	87.85 353	94.22 370

CVMVSNet		94.68 257	94.94 235	93.89 379	96.80 329	86.92 433	99.06 337	98.98 41	94.45 147	94.23 292	99.02 197	85.60 271	95.31 454	90.91 334	95.39 285	99.43 194

IterMVS-LS		92.69 322	92.11 320	94.43 351	96.80 329	92.74 315	99.45 282	96.89 413	88.98 365	89.65 352	95.38 396	88.77 221	96.34 424	90.98 332	82.04 401	94.22 370
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
AstraMVS		96.57 171	96.46 155	96.91 256	96.79 332	92.50 324	99.90 117	97.38 316	96.02 99	97.79 183	99.32 154	86.36 258	98.99 214	98.26 138	96.33 253	99.23 235

IterMVS		90.91 358	90.17 360	93.12 399	96.78 333	90.42 385	98.89 363	97.05 393	89.03 362	86.49 417	95.42 392	76.59 393	95.02 456	87.22 394	84.09 386	93.93 408
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
1314		96.84 152	95.96 181	99.48 40	96.74 334	98.52 63	98.31 408	98.86 59	95.82 104	89.91 343	98.98 208	87.49 238	99.96 76	97.80 166	99.73 90	99.96 75

IterMVS-SCA-FT		90.85 361	90.16 361	92.93 404	96.72 335	89.96 394	98.89 363	96.99 398	88.95 368	86.63 414	95.67 377	76.48 395	95.00 457	87.04 397	84.04 389	93.84 415

MVS-HIRNet		86.22 418	83.19 433	95.31 315	96.71 336	90.29 386	92.12 491	97.33 325	62.85 499	86.82 411	70.37 510	69.37 437	97.49 348	75.12 472	97.99 191	98.15 300

viewdifsd2359ckpt11		94.09 280	93.63 271	95.46 308	96.68 337	88.92 408	99.62 241	97.12 369	93.07 222	95.73 261	99.22 173	77.05 383	98.88 224	96.52 220	87.69 358	98.58 287

viewmsd2359difaftdt		94.09 280	93.64 270	95.46 308	96.68 337	88.92 408	99.62 241	97.13 368	93.07 222	95.73 261	99.22 173	77.05 383	98.89 223	96.52 220	87.70 357	98.58 287

VDDNet		93.12 309	91.91 325	96.76 263	96.67 339	92.65 321	98.69 386	98.21 217	82.81 450	97.75 185	99.28 161	61.57 470	99.48 186	98.09 148	94.09 304	98.15 300

dmvs_re		93.20 306	93.15 295	93.34 392	96.54 340	83.81 451	98.71 383	98.51 131	91.39 307	92.37 314	98.56 268	78.66 370	97.83 336	93.89 277	89.74 325	98.38 294

Elysia		94.50 264	93.38 286	97.85 180	96.49 341	96.70 148	98.98 349	97.78 270	90.81 324	96.19 247	98.55 270	73.63 420	98.98 215	89.41 355	98.56 168	97.88 307

StellarMVS		94.50 264	93.38 286	97.85 180	96.49 341	96.70 148	98.98 349	97.78 270	90.81 324	96.19 247	98.55 270	73.63 420	98.98 215	89.41 355	98.56 168	97.88 307

MIMVSNet		90.30 374	88.67 389	95.17 319	96.45 343	91.64 355	92.39 490	97.15 363	85.99 417	90.50 333	93.19 452	66.95 448	94.86 461	82.01 436	93.43 312	99.01 261

CR-MVSNet		93.45 303	92.62 308	95.94 290	96.29 344	92.66 319	92.01 492	96.23 439	92.62 248	96.94 212	93.31 449	91.04 182	96.03 439	79.23 453	95.96 262	99.13 244

RPMNet		89.76 387	87.28 404	97.19 242	96.29 344	92.66 319	92.01 492	98.31 199	70.19 490	96.94 212	85.87 497	87.25 243	99.78 147	62.69 497	95.96 262	99.13 244

tt0805		91.28 351	90.18 359	94.60 338	96.26 346	87.55 426	98.39 406	98.72 78	89.00 364	89.22 365	98.47 278	62.98 465	98.96 219	90.57 340	88.00 352	97.28 326

Patchmtry		89.70 388	88.49 392	93.33 393	96.24 347	89.94 397	91.37 496	96.23 439	78.22 473	87.69 399	93.31 449	91.04 182	96.03 439	80.18 450	82.10 400	94.02 398

test_vis1_rt		86.87 415	86.05 412	89.34 445	96.12 348	78.07 481	99.87 133	83.54 513	92.03 281	78.21 470	89.51 479	45.80 492	99.91 111	96.25 226	93.11 317	90.03 477

JIA-IIPM		91.76 345	90.70 346	94.94 325	96.11 349	87.51 427	93.16 487	98.13 232	75.79 479	97.58 187	77.68 505	92.84 137	97.97 328	88.47 373	96.54 245	99.33 212

OpenMVS	90.15 15	94.77 252	93.59 275	98.33 146	96.07 350	97.48 113	99.56 260	98.57 107	90.46 340	86.51 416	98.95 217	78.57 371	99.94 94	93.86 278	99.74 89	97.57 321

PAPM		98.60 37	98.42 38	99.14 73	96.05 351	98.96 28	99.90 117	99.35 24	96.68 73	98.35 156	99.66 116	96.45 35	98.51 280	99.45 65	99.89 73	99.96 75

CLD-MVS		94.06 283	93.90 266	94.55 342	96.02 352	90.69 376	99.98 24	97.72 276	96.62 77	91.05 327	98.85 237	77.21 381	98.47 281	98.11 146	89.51 331	94.48 346
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PatchT		90.38 371	88.75 388	95.25 317	95.99 353	90.16 389	91.22 497	97.54 299	76.80 475	97.26 200	86.01 496	91.88 169	96.07 438	66.16 490	95.91 266	99.51 177

ACMH+	89.98 16	90.35 372	89.54 371	92.78 408	95.99 353	86.12 437	98.81 374	97.18 357	89.38 357	83.14 443	97.76 310	68.42 442	98.43 286	89.11 363	86.05 369	93.78 418

DeepMVS_CX				82.92 472	95.98 355	58.66 505		96.01 445	92.72 240	78.34 469	95.51 387	58.29 477	98.08 322	82.57 431	85.29 374	92.03 456

ACMP	92.05 9	92.74 320	92.42 317	93.73 381	95.91 356	88.72 412	99.81 167	97.53 301	94.13 167	87.00 410	98.23 291	74.07 416	98.47 281	96.22 227	88.86 338	93.99 403
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n		93.61 298	93.03 298	95.35 312	95.86 357	86.94 432	99.87 133	96.36 437	96.85 64	99.54 73	98.79 242	52.41 485	99.83 140	98.64 114	98.97 154	99.29 224

HQP-NCC					95.78 358		99.87 133		96.82 66	93.37 299

ACMP_Plane					95.78 358		99.87 133		96.82 66	93.37 299

HQP-MVS		94.61 259	94.50 246	94.92 326	95.78 358	91.85 340	99.87 133	97.89 256	96.82 66	93.37 299	98.65 255	80.65 349	98.39 293	97.92 158	89.60 326	94.53 342

NP-MVS					95.77 361	91.79 344					98.65 255

test_fmvsmconf0.1_n		97.74 103	97.44 107	98.64 115	95.76 362	96.20 176	99.94 93	98.05 239	98.17 13	98.89 122	99.42 142	87.65 233	99.90 113	99.50 61	99.60 107	99.82 107

plane_prior6					95.76 362	91.72 351						80.47 353

ACMM	91.95 10	92.88 315	92.52 315	93.98 375	95.75 364	89.08 407	99.77 185	97.52 303	93.00 225	89.95 342	97.99 300	76.17 399	98.46 284	93.63 290	88.87 337	94.39 354
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GA-MVS		93.83 287	92.84 302	96.80 261	95.73 365	93.57 293	99.88 130	97.24 349	92.57 255	92.92 306	96.66 345	78.73 369	97.67 342	87.75 386	94.06 305	99.17 239

plane_prior1					95.73 365

jason		97.24 129	96.86 133	98.38 145	95.73 365	97.32 118	99.97 42	97.40 315	95.34 119	98.60 143	99.54 134	87.70 232	98.56 275	97.94 157	99.47 124	99.25 232
jason: jason.
mmtdpeth		88.52 399	87.75 401	90.85 428	95.71 368	83.47 457	98.94 357	94.85 471	88.78 373	97.19 202	89.58 478	63.29 463	98.97 217	98.54 119	62.86 489	90.10 476

HQP_MVS		94.49 266	94.36 249	94.87 327	95.71 368	91.74 347	99.84 152	97.87 258	96.38 86	93.01 304	98.59 263	80.47 353	98.37 299	97.79 169	89.55 329	94.52 344

plane_prior7					95.71 368	91.59 361

ITE_SJBPF				92.38 411	95.69 371	85.14 443		95.71 452	92.81 234	89.33 362	98.11 294	70.23 435	98.42 287	85.91 409	88.16 350	93.59 426

fmvsm_s_conf0.1_n_a		97.09 138	96.90 131	97.63 203	95.65 372	94.21 269	99.83 160	98.50 137	96.27 92	99.65 55	99.64 119	84.72 293	99.93 104	99.04 85	98.84 159	98.74 280

ACMH	89.72 17	90.64 365	89.63 368	93.66 387	95.64 373	88.64 415	98.55 394	97.45 308	89.03 362	81.62 450	97.61 311	69.75 436	98.41 289	89.37 357	87.62 359	93.92 409
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline2		96.71 163	96.49 152	97.37 233	95.63 374	95.96 185	99.74 201	98.88 55	92.94 227	91.61 320	98.97 210	97.72 7	98.62 270	94.83 255	98.08 189	97.53 323

FMVSNet1		88.50 400	86.64 407	94.08 367	95.62 375	91.97 333	98.43 402	96.95 404	83.00 448	86.08 424	94.72 423	59.09 476	96.11 434	81.82 438	84.07 387	94.17 375

LuminaMVS		96.63 167	96.21 166	97.87 179	95.58 376	96.82 142	99.12 326	97.67 280	94.47 145	97.88 178	98.31 288	87.50 237	98.71 255	98.07 150	97.29 211	98.10 303

0.3-1-1-0.015		94.22 276	93.13 297	97.49 221	95.50 377	94.17 270	100.00 1	98.22 213	88.44 383	97.14 204	97.04 331	92.73 141	98.59 271	96.45 222	72.65 460	99.70 125

0.4-1-1-0.2		94.14 277	93.02 299	97.51 216	95.45 378	94.25 266	100.00 1	98.22 213	88.53 380	96.83 218	96.95 334	92.25 160	98.57 274	96.34 223	72.65 460	99.70 125

LPG-MVS_test		92.96 312	92.71 307	93.71 383	95.43 379	88.67 413	99.75 197	97.62 287	92.81 234	90.05 338	98.49 274	75.24 406	98.40 291	95.84 234	89.12 333	94.07 394

LGP-MVS_train				93.71 383	95.43 379	88.67 413		97.62 287	92.81 234	90.05 338	98.49 274	75.24 406	98.40 291	95.84 234	89.12 333	94.07 394

tpm		93.70 296	93.41 284	94.58 340	95.36 381	87.41 428	97.01 447	96.90 412	90.85 322	96.72 223	94.14 440	90.40 196	96.84 392	90.75 338	88.54 345	99.51 177

0.4-1-1-0.1		94.07 282	92.95 300	97.42 228	95.24 382	94.00 277	100.00 1	98.22 213	88.27 387	96.81 220	96.93 335	92.27 159	98.56 275	96.21 228	72.63 462	99.70 125

D2MVS		92.76 319	92.59 313	93.27 395	95.13 383	89.54 401	99.69 227	99.38 22	92.26 274	87.59 401	94.61 429	85.05 283	97.79 337	91.59 321	88.01 351	92.47 450

VPA-MVSNet		92.70 321	91.55 334	96.16 283	95.09 384	96.20 176	98.88 365	99.00 39	91.02 319	91.82 319	95.29 403	76.05 401	97.96 330	95.62 239	81.19 407	94.30 361

LTVRE_ROB	88.28 18	90.29 375	89.05 382	94.02 370	95.08 385	90.15 390	97.19 442	97.43 310	84.91 433	83.99 439	97.06 328	74.00 417	98.28 309	84.08 420	87.71 355	93.62 425
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		87.87 407	86.51 408	91.94 417	95.05 386	85.57 441	97.65 433	94.08 482	84.40 437	81.82 449	96.85 340	62.14 468	98.33 302	80.25 449	86.37 366	91.91 458

test0.0.03 1		93.86 286	93.61 272	94.64 336	95.02 387	92.18 331	99.93 100	98.58 105	94.07 171	87.96 396	98.50 273	93.90 106	94.96 458	81.33 439	93.17 315	96.78 329

UniMVSNet (Re)		93.07 311	92.13 319	95.88 294	94.84 388	96.24 175	99.88 130	98.98 41	92.49 262	89.25 363	95.40 393	87.09 245	97.14 367	93.13 299	78.16 432	94.26 363

USDC		90.00 383	88.96 383	93.10 401	94.81 389	88.16 421	98.71 383	95.54 457	93.66 192	83.75 441	97.20 322	65.58 454	98.31 304	83.96 423	87.49 361	92.85 443

VPNet		91.81 339	90.46 350	95.85 296	94.74 390	95.54 204	98.98 349	98.59 103	92.14 276	90.77 332	97.44 315	68.73 440	97.54 347	94.89 254	77.89 434	94.46 347

FIs		94.10 279	93.43 281	96.11 284	94.70 391	96.82 142	99.58 252	98.93 48	92.54 258	89.34 361	97.31 319	87.62 234	97.10 371	94.22 272	86.58 364	94.40 353

UniMVSNet_ETH3D		90.06 382	88.58 391	94.49 346	94.67 392	88.09 422	97.81 430	97.57 295	83.91 440	88.44 383	97.41 316	57.44 478	97.62 344	91.41 323	88.59 344	97.77 312

UniMVSNet_NR-MVSNet		92.95 313	92.11 320	95.49 304	94.61 393	95.28 222	99.83 160	99.08 36	91.49 298	89.21 366	96.86 339	87.14 244	96.73 399	93.20 295	77.52 437	94.46 347

test_fmvs2		89.47 392	89.70 367	88.77 452	94.54 394	75.74 484	99.83 160	94.70 477	94.71 137	91.08 325	96.82 344	54.46 481	97.78 339	92.87 302	88.27 348	92.80 444

MonoMVSNet		94.82 247	94.43 247	95.98 288	94.54 394	90.73 375	99.03 344	97.06 390	93.16 216	93.15 303	95.47 390	88.29 225	97.57 345	97.85 163	91.33 323	99.62 147

WR-MVS		92.31 331	91.25 339	95.48 307	94.45 396	95.29 221	99.60 248	98.68 84	90.10 348	88.07 395	96.89 337	80.68 348	96.80 396	93.14 298	79.67 424	94.36 355

dtuonly		93.89 285	93.16 294	96.08 286	94.37 397	91.67 354	99.15 325	95.04 469	91.79 291	94.74 278	98.72 247	81.01 341	98.31 304	87.29 392	96.33 253	98.27 298

nrg030		93.51 300	92.53 314	96.45 274	94.36 398	97.20 124	99.81 167	97.16 361	91.60 295	89.86 345	97.46 314	86.37 257	97.68 341	95.88 233	80.31 420	94.46 347

tfpnnormal		89.29 395	87.61 402	94.34 354	94.35 399	94.13 272	98.95 356	98.94 44	83.94 438	84.47 436	95.51 387	74.84 411	97.39 350	77.05 467	80.41 418	91.48 461

FC-MVSNet-test		93.81 290	93.15 295	95.80 299	94.30 400	96.20 176	99.42 284	98.89 52	92.33 269	89.03 371	97.27 321	87.39 240	96.83 394	93.20 295	86.48 365	94.36 355

SSC-MVS3.2		89.59 390	88.66 390	92.38 411	94.29 401	86.12 437	99.49 273	97.66 283	90.28 347	88.63 379	95.18 407	64.46 459	96.88 390	85.30 413	82.66 395	94.14 385

MS-PatchMatch		90.65 364	90.30 355	91.71 422	94.22 402	85.50 442	98.24 412	97.70 277	88.67 376	86.42 419	96.37 355	67.82 445	98.03 326	83.62 425	99.62 99	91.60 459

WR-MVS_H		91.30 349	90.35 353	94.15 361	94.17 403	92.62 322	99.17 323	98.94 44	88.87 371	86.48 418	94.46 434	84.36 300	96.61 406	88.19 379	78.51 429	93.21 435

DU-MVS		92.46 328	91.45 337	95.49 304	94.05 404	95.28 222	99.81 167	98.74 76	92.25 275	89.21 366	96.64 347	81.66 332	96.73 399	93.20 295	77.52 437	94.46 347

NR-MVSNet		91.56 347	90.22 357	95.60 302	94.05 404	95.76 192	98.25 411	98.70 80	91.16 313	80.78 457	96.64 347	83.23 318	96.57 407	91.41 323	77.73 436	94.46 347

CP-MVSNet		91.23 353	90.22 357	94.26 356	93.96 406	92.39 327	99.09 330	98.57 107	88.95 368	86.42 419	96.57 350	79.19 364	96.37 422	90.29 347	78.95 426	94.02 398

XXY-MVS		91.82 338	90.46 350	95.88 294	93.91 407	95.40 211	98.87 368	97.69 279	88.63 378	87.87 397	97.08 326	74.38 415	97.89 334	91.66 320	84.07 387	94.35 358

PS-CasMVS		90.63 366	89.51 373	93.99 373	93.83 408	91.70 352	98.98 349	98.52 128	88.48 381	86.15 423	96.53 352	75.46 404	96.31 427	88.83 365	78.86 428	93.95 406

test_0402		85.58 421	83.94 427	90.50 434	93.81 409	85.04 444	98.55 394	95.20 466	76.01 477	79.72 463	95.13 408	64.15 461	96.26 429	66.04 492	86.88 363	90.21 473

XVG-ACMP-BASELINE		91.22 354	90.75 345	92.63 410	93.73 410	85.61 440	98.52 398	97.44 309	92.77 238	89.90 344	96.85 340	66.64 451	98.39 293	92.29 307	88.61 342	93.89 411

TranMVSNet+NR-MVSNet		91.68 346	90.61 349	94.87 327	93.69 411	93.98 278	99.69 227	98.65 88	91.03 318	88.44 383	96.83 343	80.05 357	96.18 432	90.26 348	76.89 445	94.45 352

TransMVSNet (Re)		87.25 413	85.28 421	93.16 398	93.56 412	91.03 367	98.54 396	94.05 484	83.69 442	81.09 454	96.16 361	75.32 405	96.40 421	76.69 468	68.41 476	92.06 455

v10		90.25 376	88.82 385	94.57 341	93.53 413	93.43 298	99.08 332	96.87 415	85.00 430	87.34 408	94.51 430	80.93 343	97.02 381	82.85 430	79.23 425	93.26 433

testgi		89.01 397	88.04 398	91.90 418	93.49 414	84.89 446	99.73 208	95.66 454	93.89 185	85.14 430	98.17 292	59.68 474	94.66 464	77.73 463	88.88 336	96.16 338

v8		90.54 368	89.17 378	94.66 335	93.43 415	93.40 301	99.20 320	96.94 408	85.76 420	87.56 402	94.51 430	81.96 328	97.19 364	84.94 416	78.25 431	93.38 431

V42		91.28 351	90.12 362	94.74 332	93.42 416	93.46 297	99.68 230	97.02 394	87.36 398	89.85 347	95.05 411	81.31 338	97.34 353	87.34 391	80.07 422	93.40 429

pm-mvs1		89.36 394	87.81 400	94.01 371	93.40 417	91.93 336	98.62 392	96.48 435	86.25 415	83.86 440	96.14 363	73.68 419	97.04 377	86.16 406	75.73 450	93.04 439

v1144		91.09 355	89.83 364	94.87 327	93.25 418	93.69 286	99.62 241	96.98 400	86.83 408	89.64 353	94.99 418	80.94 342	97.05 374	85.08 415	81.16 408	93.87 413

v1192		90.62 367	89.25 377	94.72 334	93.13 419	93.07 306	99.50 271	97.02 394	86.33 414	89.56 357	95.01 415	79.22 363	97.09 373	82.34 434	81.16 408	94.01 400

v2v482		91.30 349	90.07 363	95.01 322	93.13 419	93.79 281	99.77 185	97.02 394	88.05 389	89.25 363	95.37 397	80.73 347	97.15 366	87.28 393	80.04 423	94.09 393

OPM-MVS		93.21 305	92.80 304	94.44 349	93.12 421	90.85 374	99.77 185	97.61 290	96.19 95	91.56 321	98.65 255	75.16 410	98.47 281	93.78 285	89.39 332	93.99 403
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v144192		90.79 362	89.52 372	94.59 339	93.11 422	92.77 313	99.56 260	96.99 398	86.38 413	89.82 348	94.95 420	80.50 352	97.10 371	83.98 422	80.41 418	93.90 410

PEN-MVS		90.19 378	89.06 381	93.57 388	93.06 423	90.90 372	99.06 337	98.47 140	88.11 388	85.91 425	96.30 357	76.67 391	95.94 442	87.07 396	76.91 444	93.89 411

v1240		90.20 377	88.79 386	94.44 349	93.05 424	92.27 329	99.38 292	96.92 411	85.89 418	89.36 360	94.87 422	77.89 378	97.03 379	80.66 444	81.08 411	94.01 400

usedtu_dtu_shiyan1		92.78 317	91.73 328	95.92 292	93.03 425	96.82 142	99.83 160	97.79 266	90.58 333	90.09 336	95.04 412	84.75 289	96.72 401	88.19 379	86.23 367	94.23 367

FE-MVSNET3		92.78 317	91.73 328	95.92 292	93.03 425	96.82 142	99.83 160	97.79 266	90.58 333	90.09 336	95.04 412	84.75 289	96.72 401	88.20 378	86.23 367	94.23 367

ArgMatch-SfM		85.25 426	84.17 424	88.48 454	92.99 427	77.23 483	97.92 425	94.24 480	90.50 337	85.08 432	95.65 379	49.84 488	95.83 444	81.06 442	70.22 467	92.39 452

v148		90.70 363	89.63 368	93.92 376	92.97 428	90.97 368	99.75 197	96.89 413	87.51 395	88.27 392	95.01 415	81.67 331	97.04 377	87.40 390	77.17 442	93.75 419

v1921920		90.46 369	89.12 379	94.50 345	92.96 429	92.46 325	99.49 273	96.98 400	86.10 416	89.61 355	95.30 400	78.55 372	97.03 379	82.17 435	80.89 416	94.01 400

MVStest1		85.03 428	82.76 437	91.83 419	92.95 430	89.16 406	98.57 393	94.82 472	71.68 488	68.54 493	95.11 410	83.17 319	95.66 447	74.69 473	65.32 483	90.65 468

tt0320-xc		82.94 443	80.35 450	90.72 432	92.90 431	83.54 455	96.85 452	94.73 475	63.12 498	79.85 462	93.77 444	49.43 490	95.46 450	80.98 443	71.54 464	93.16 436

Baseline_NR-MVSNet		90.33 373	89.51 373	92.81 407	92.84 432	89.95 395	99.77 185	93.94 485	84.69 435	89.04 370	95.66 378	81.66 332	96.52 410	90.99 331	76.98 443	91.97 457

test_method		80.79 449	79.70 452	84.08 468	92.83 433	67.06 495	99.51 269	95.42 459	54.34 506	81.07 455	93.53 446	44.48 493	92.22 486	78.90 458	77.23 441	92.94 441

pmmvs4		92.10 335	91.07 343	95.18 318	92.82 434	94.96 234	99.48 276	96.83 417	87.45 397	88.66 378	96.56 351	83.78 308	96.83 394	89.29 360	84.77 381	93.75 419

LF4IMVS		89.25 396	88.85 384	90.45 436	92.81 435	81.19 472	98.12 419	94.79 473	91.44 302	86.29 421	97.11 324	65.30 457	98.11 320	88.53 370	85.25 375	92.07 454

tt0320		83.56 442	81.15 445	90.77 430	92.77 436	83.58 454	96.83 453	95.52 458	63.26 497	81.36 452	92.54 456	53.26 483	95.77 445	80.45 445	74.38 453	92.96 440

DTE-MVSNet		89.40 393	88.24 396	92.88 405	92.66 437	89.95 395	99.10 329	98.22 213	87.29 399	85.12 431	96.22 359	76.27 398	95.30 455	83.56 426	75.74 449	93.41 428

EU-MVSNet		90.14 380	90.34 354	89.54 444	92.55 438	81.06 473	98.69 386	98.04 240	91.41 306	86.59 415	96.84 342	80.83 345	93.31 477	86.20 405	81.91 402	94.26 363

APD_test1		81.15 447	80.92 447	81.86 473	92.45 439	59.76 504	96.04 468	93.61 489	73.29 486	77.06 473	96.64 347	44.28 494	96.16 433	72.35 477	82.52 396	89.67 482

sc_t1		85.01 429	82.46 439	92.67 409	92.44 440	83.09 458	97.39 438	95.72 451	65.06 495	85.64 428	96.16 361	49.50 489	97.34 353	84.86 417	75.39 451	97.57 321

our_test_3		90.39 370	89.48 375	93.12 399	92.40 441	89.57 400	99.33 299	96.35 438	87.84 393	85.30 429	94.99 418	84.14 304	96.09 437	80.38 447	84.56 382	93.71 424

ppachtmachnet_test		89.58 391	88.35 394	93.25 397	92.40 441	90.44 384	99.33 299	96.73 424	85.49 425	85.90 426	95.77 372	81.09 340	96.00 441	76.00 471	82.49 397	93.30 432

v7n		89.65 389	88.29 395	93.72 382	92.22 443	90.56 381	99.07 336	97.10 377	85.42 427	86.73 412	94.72 423	80.06 356	97.13 368	81.14 440	78.12 433	93.49 427

dmvs_testset		83.79 438	86.07 411	76.94 480	92.14 444	48.60 517	96.75 454	90.27 501	89.48 356	78.65 467	98.55 270	79.25 362	86.65 503	66.85 488	82.69 394	95.57 340

PS-MVSNAJss		93.64 297	93.31 290	94.61 337	92.11 445	92.19 330	99.12 326	97.38 316	92.51 261	88.45 382	96.99 333	91.20 177	97.29 361	94.36 266	87.71 355	94.36 355

pmmvs5		90.17 379	89.09 380	93.40 391	92.10 446	89.77 398	99.74 201	95.58 456	85.88 419	87.24 409	95.74 373	73.41 422	96.48 414	88.54 369	83.56 391	93.95 406

N_pmnet		80.06 452	80.78 448	77.89 478	91.94 447	45.28 521	98.80 377	56.82 524	78.10 474	80.08 460	93.33 447	77.03 385	95.76 446	68.14 485	82.81 393	92.64 445

test_djsdf		92.83 316	92.29 318	94.47 347	91.90 448	92.46 325	99.55 263	97.27 343	91.17 311	89.96 341	96.07 367	81.10 339	96.89 388	94.67 261	88.91 335	94.05 397

SixPastTwentyTwo		88.73 398	88.01 399	90.88 426	91.85 449	82.24 464	98.22 416	95.18 467	88.97 366	82.26 446	96.89 337	71.75 427	96.67 404	84.00 421	82.98 392	93.72 423

dtuonlycased		86.10 419	85.82 414	86.95 460	91.84 450	79.57 479	99.27 314	94.89 470	86.79 409	79.46 464	94.46 434	66.85 449	90.93 492	80.41 446	78.44 430	90.34 470

K. test v3		88.05 404	87.24 405	90.47 435	91.82 451	82.23 465	98.96 355	97.42 312	89.05 361	76.93 475	95.60 381	68.49 441	95.42 451	85.87 410	81.01 414	93.75 419

OurMVSNet-221017-0		89.81 386	89.48 375	90.83 429	91.64 452	81.21 471	98.17 418	95.38 461	91.48 300	85.65 427	97.31 319	72.66 423	97.29 361	88.15 381	84.83 380	93.97 405

mvs_tets		91.81 339	91.08 342	94.00 372	91.63 453	90.58 380	98.67 388	97.43 310	92.43 263	87.37 407	97.05 329	71.76 426	97.32 356	94.75 258	88.68 341	94.11 392

Gipuma		66.95 471	65.00 471	72.79 486	91.52 454	67.96 492	66.16 521	95.15 468	47.89 508	58.54 501	67.99 517	29.74 502	87.54 502	50.20 508	77.83 435	62.87 516
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_fmvsmconf0.01_n		96.39 182	95.74 195	98.32 147	91.47 455	95.56 203	99.84 152	97.30 333	97.74 30	97.89 177	99.35 153	79.62 359	99.85 130	99.25 75	99.24 141	99.55 164

jajsoiax		91.92 337	91.18 340	94.15 361	91.35 456	90.95 371	99.00 347	97.42 312	92.61 249	87.38 406	97.08 326	72.46 424	97.36 351	94.53 264	88.77 339	94.13 390

MDA-MVSNet-bldmvs		84.09 436	81.52 443	91.81 420	91.32 457	88.00 424	98.67 388	95.92 447	80.22 462	55.60 504	93.32 448	68.29 443	93.60 475	73.76 474	76.61 446	93.82 417

MVP-Stereo		90.93 357	90.45 352	92.37 413	91.25 458	88.76 410	98.05 423	96.17 441	87.27 400	84.04 437	95.30 400	78.46 373	97.27 363	83.78 424	99.70 92	91.09 462
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MDA-MVSNet_test_wron		85.51 423	83.32 432	92.10 415	90.96 459	88.58 416	99.20 320	96.52 433	79.70 464	57.12 503	92.69 455	79.11 365	93.86 471	77.10 466	77.46 439	93.86 414

YYNet1		85.50 424	83.33 431	92.00 416	90.89 460	88.38 420	99.22 319	96.55 432	79.60 465	57.26 502	92.72 454	79.09 367	93.78 473	77.25 465	77.37 440	93.84 415

ALIKED-NN		54.48 480	52.67 482	59.89 502	90.79 461	45.45 519	81.25 514	55.75 528	34.99 517	44.87 514	71.98 508	25.50 510	74.36 516	21.88 526	47.04 512	59.85 518

anonymousdsp		91.79 344	90.92 344	94.41 352	90.76 462	92.93 312	98.93 359	97.17 359	89.08 360	87.46 405	95.30 400	78.43 374	96.92 385	92.38 306	88.73 340	93.39 430

lessismore_v0				90.53 433	90.58 463	80.90 474		95.80 448		77.01 474	95.84 370	66.15 453	96.95 383	83.03 429	75.05 452	93.74 422

EG-PatchMatch MVS		85.35 425	83.81 429	89.99 442	90.39 464	81.89 467	98.21 417	96.09 443	81.78 455	74.73 481	93.72 445	51.56 487	97.12 370	79.16 456	88.61 342	90.96 465

EGC-MVSNET		69.38 464	63.76 474	86.26 464	90.32 465	81.66 470	96.24 464	93.85 486	0.99 543	3.22 544	92.33 466	52.44 484	92.92 481	59.53 502	84.90 379	84.21 498

CMPMVS	61.59 21	84.75 432	85.14 422	83.57 469	90.32 465	62.54 500	96.98 448	97.59 294	74.33 484	69.95 490	96.66 345	64.17 460	98.32 303	87.88 385	88.41 347	89.84 479
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ALIKED-MNN		52.51 484	50.15 489	59.60 504	90.05 467	44.33 523	81.60 513	54.93 529	32.36 520	40.96 521	68.77 514	20.90 519	75.30 514	20.00 527	41.78 516	59.18 519

new_pmnet		84.49 435	82.92 435	89.21 446	90.03 468	82.60 461	96.89 451	95.62 455	80.59 460	75.77 480	89.17 480	65.04 458	94.79 462	72.12 478	81.02 413	90.23 472

pmmvs6		85.69 420	83.84 428	91.26 425	90.00 469	84.41 449	97.82 429	96.15 442	75.86 478	81.29 453	95.39 395	61.21 471	96.87 391	83.52 427	73.29 456	92.50 449

ttmdpeth		88.23 403	87.06 406	91.75 421	89.91 470	87.35 429	98.92 362	95.73 450	87.92 391	84.02 438	96.31 356	68.23 444	96.84 392	86.33 404	76.12 447	91.06 463

DSMNet-mixed		88.28 402	88.24 396	88.42 455	89.64 471	75.38 487	98.06 422	89.86 502	85.59 424	88.20 394	92.14 468	76.15 400	91.95 487	78.46 460	96.05 259	97.92 306

UnsupCasMVSNet_eth		85.52 422	83.99 425	90.10 440	89.36 472	83.51 456	96.65 455	97.99 244	89.14 359	75.89 479	93.83 442	63.25 464	93.92 469	81.92 437	67.90 479	92.88 442

Anonymous20231206		86.32 417	85.42 420	89.02 448	89.11 473	80.53 477	99.05 341	95.28 462	85.43 426	82.82 444	93.92 441	74.40 414	93.44 476	66.99 487	81.83 403	93.08 438

ALIKED-LG		54.29 481	52.28 483	60.32 498	88.90 474	45.51 518	81.66 512	56.33 525	38.60 510	42.62 519	70.81 509	25.00 512	75.20 515	19.87 528	46.76 514	60.24 517

Anonymous20240521		85.15 427	83.81 429	89.16 447	88.32 475	82.69 460	98.80 377	95.74 449	79.72 463	81.53 451	90.99 471	65.38 456	94.16 467	72.69 476	81.11 410	90.63 469

OpenMVS_ROB	79.82 20	83.77 439	81.68 442	90.03 441	88.30 476	82.82 459	98.46 399	95.22 465	73.92 485	76.00 478	91.29 470	55.00 480	96.94 384	68.40 484	88.51 346	90.34 470

test20.03		84.72 433	83.99 425	86.91 461	88.19 477	80.62 476	98.88 365	95.94 446	88.36 384	78.87 465	94.62 428	68.75 439	89.11 497	66.52 489	75.82 448	91.00 464

RoMa-SfM		74.91 460	72.77 462	81.35 474	88.00 478	67.35 494	93.55 484	86.23 511	68.27 493	66.79 494	92.92 453	30.40 500	87.68 499	66.14 491	62.62 490	89.02 488

gbinet_0.2-2-1-0.02		87.63 412	85.51 419	93.99 373	87.22 479	91.56 362	99.81 167	97.36 320	79.54 466	88.60 380	93.29 451	73.76 418	96.34 424	89.27 361	60.78 498	94.06 396

blend_shiyan4		90.13 381	88.79 386	94.17 358	87.12 480	91.83 342	99.75 197	97.08 381	79.27 471	88.69 376	92.53 457	92.25 160	96.50 411	89.35 358	73.04 458	94.18 374

KD-MVS_self_test		83.59 440	82.06 440	88.20 456	86.93 481	80.70 475	97.21 441	96.38 436	82.87 449	82.49 445	88.97 481	67.63 446	92.32 484	73.75 475	62.30 492	91.58 460

DKM		72.18 462	69.80 465	79.34 477	86.79 482	65.15 496	92.70 488	84.00 512	67.67 494	61.97 497	89.63 477	23.69 515	85.17 505	67.39 486	54.35 508	87.70 493

MIMVSNet1		82.58 444	80.51 449	88.78 450	86.68 483	84.20 450	96.65 455	95.41 460	78.75 472	78.59 468	92.44 458	51.88 486	89.76 495	65.26 493	78.95 426	92.38 453

wanda-best-256-512		87.82 408	85.71 415	94.15 361	86.66 484	91.88 338	99.76 191	97.08 381	79.46 467	88.37 389	92.36 462	78.01 375	96.43 417	88.39 374	61.26 494	94.14 385

FE-blended-shiyan7		87.82 408	85.71 415	94.15 361	86.66 484	91.88 338	99.76 191	97.08 381	79.46 467	88.37 389	92.36 462	78.01 375	96.43 417	88.39 374	61.26 494	94.14 385

usedtu_blend_shiyan5		86.75 416	84.29 423	94.16 359	86.66 484	91.83 342	97.42 435	95.23 464	69.94 491	88.37 389	92.36 462	78.01 375	96.50 411	89.35 358	61.26 494	94.14 385

SP-NN		55.28 479	53.59 481	60.34 497	86.63 487	39.01 528	86.70 506	56.31 526	31.08 522	43.77 517	68.45 515	23.39 516	60.24 521	29.19 521	56.76 505	81.77 503

LoFTR		74.41 461	70.88 464	84.99 467	86.56 488	67.85 493	93.74 480	89.63 504	69.46 492	54.95 505	87.39 491	30.76 499	96.92 385	61.37 499	64.06 486	90.19 474

blended_shiyan8		87.82 408	85.71 415	94.16 359	86.54 489	91.79 344	99.72 212	97.08 381	79.32 469	88.44 383	92.35 465	77.88 379	96.56 408	88.53 370	61.51 493	94.15 381

blended_shiyan6		87.74 411	85.62 418	94.09 366	86.53 490	91.73 350	99.72 212	97.08 381	79.32 469	88.22 393	92.31 467	77.82 380	96.43 417	88.31 376	61.26 494	94.13 390

CL-MVSNet_self_test		84.50 434	83.15 434	88.53 453	86.00 491	81.79 468	98.82 373	97.35 321	85.12 429	83.62 442	90.91 473	76.66 392	91.40 488	69.53 482	60.36 499	92.40 451

MatchFormer		70.84 463	66.72 469	83.19 471	85.99 492	64.61 497	93.58 483	88.62 507	59.32 502	50.64 508	82.31 502	28.00 505	96.79 397	52.52 507	59.50 501	88.18 490

UnsupCasMVSNet_bld		79.97 454	77.03 460	88.78 450	85.62 493	81.98 466	93.66 481	97.35 321	75.51 481	70.79 489	83.05 499	48.70 491	94.91 460	78.31 461	60.29 500	89.46 485

mvs5depth		84.87 430	82.90 436	90.77 430	85.59 494	84.84 447	91.10 498	93.29 491	83.14 446	85.07 433	94.33 437	62.17 467	97.32 356	78.83 459	72.59 463	90.14 475

SP-LightGlue		55.29 477	53.65 480	60.20 499	85.58 495	39.12 527	86.36 509	57.52 523	32.34 521	44.34 516	67.75 518	24.36 513	59.32 524	29.62 519	54.98 506	82.17 501

SP-SuperGlue		55.29 477	53.71 479	60.00 501	85.11 496	38.86 529	86.96 505	57.95 522	32.77 519	44.54 515	68.00 516	23.90 514	59.51 523	29.61 520	54.59 507	81.63 504

SP-MNN		53.97 482	52.04 486	59.73 503	84.72 497	38.63 530	86.51 507	55.94 527	29.25 523	40.20 522	67.48 519	22.18 518	59.59 522	27.79 522	54.33 509	80.98 505

Patchmatch-RL test		86.90 414	85.98 413	89.67 443	84.45 498	75.59 485	89.71 501	92.43 493	86.89 407	77.83 472	90.94 472	94.22 95	93.63 474	87.75 386	69.61 470	99.79 112

MASt3R-SfM		78.94 455	79.57 453	77.07 479	84.15 499	50.74 513	91.56 494	92.34 494	83.22 445	80.84 456	94.16 439	36.67 497	92.30 485	79.45 452	73.71 455	88.16 491

pmmvs-eth3d		84.03 437	81.97 441	90.20 438	84.15 499	87.09 431	98.10 421	94.73 475	83.05 447	74.10 485	87.77 488	65.56 455	94.01 468	81.08 441	69.24 472	89.49 484

test_fmvs3		79.99 453	80.17 451	79.45 476	84.02 501	62.83 498	99.05 341	93.49 490	88.29 386	80.06 461	86.65 494	28.09 504	88.00 498	88.63 366	73.27 457	87.54 495

PM-MVS		80.47 450	78.88 455	85.26 465	83.79 502	72.22 489	95.89 471	91.08 499	85.71 423	76.56 477	88.30 484	36.64 498	93.90 470	82.39 433	69.57 471	89.66 483

new-patchmatchnet		81.19 446	79.34 454	86.76 462	82.86 503	80.36 478	97.92 425	95.27 463	82.09 454	72.02 487	86.87 493	62.81 466	90.74 493	71.10 479	63.08 488	89.19 487

FE-MVSNET2		83.57 441	81.36 444	90.20 438	82.83 504	87.59 425	98.28 410	96.04 444	85.33 428	74.13 484	87.45 489	59.16 475	93.26 478	79.12 457	69.91 468	89.77 480

FE-MVSNET		81.05 448	78.81 456	87.79 458	81.98 505	83.70 452	98.23 414	91.78 498	81.27 457	74.29 483	87.44 490	60.92 473	90.67 494	64.92 494	68.43 475	89.01 489

mvsany_test3		82.12 445	81.14 446	85.06 466	81.87 506	70.41 490	97.09 445	92.14 495	91.27 309	77.84 471	88.73 482	39.31 495	95.49 448	90.75 338	71.24 465	89.29 486

WB-MVS		76.28 457	77.28 459	73.29 485	81.18 507	54.68 509	97.87 428	94.19 481	81.30 456	69.43 491	90.70 474	77.02 386	82.06 508	35.71 515	68.11 478	83.13 499

test_f		78.40 456	77.59 458	80.81 475	80.82 508	62.48 501	96.96 449	93.08 492	83.44 443	74.57 482	84.57 498	27.95 506	92.63 482	84.15 419	72.79 459	87.32 496

SSC-MVS		75.42 459	76.40 461	72.49 489	80.68 509	53.62 510	97.42 435	94.06 483	80.42 461	68.75 492	90.14 476	76.54 394	81.66 509	33.25 516	66.34 482	82.19 500

pmmvs3		80.27 451	77.77 457	87.76 459	80.32 510	82.43 463	98.23 414	91.97 496	72.74 487	78.75 466	87.97 487	57.30 479	90.99 491	70.31 480	62.37 491	89.87 478

testf1		68.38 467	66.92 467	72.78 487	78.80 511	50.36 514	90.95 499	87.35 509	55.47 504	58.95 499	88.14 485	20.64 521	87.60 500	57.28 503	64.69 484	80.39 507

APD_test2		68.38 467	66.92 467	72.78 487	78.80 511	50.36 514	90.95 499	87.35 509	55.47 504	58.95 499	88.14 485	20.64 521	87.60 500	57.28 503	64.69 484	80.39 507

ambc				83.23 470	77.17 513	62.61 499	87.38 503	94.55 479		76.72 476	86.65 494	30.16 501	96.36 423	84.85 418	69.86 469	90.73 467

test_vis3_rt		68.82 465	66.69 470	75.21 484	76.24 514	60.41 503	96.44 459	68.71 519	75.13 482	50.54 509	69.52 513	16.42 527	96.32 426	80.27 448	66.92 481	68.89 513

PDCNetPlus		59.83 474	57.26 477	67.55 493	76.18 515	56.71 507	87.01 504	45.27 532	59.54 501	48.80 511	83.01 500	26.63 508	76.54 513	62.12 498	26.78 524	69.40 512

usedtu_dtu_shiyan2		75.87 458	72.37 463	86.39 463	76.18 515	75.49 486	96.53 457	93.82 487	64.74 496	72.53 486	88.48 483	37.67 496	91.12 490	64.13 495	57.22 503	92.56 446

TDRefinement		84.76 431	82.56 438	91.38 424	74.58 517	84.80 448	97.36 439	94.56 478	84.73 434	80.21 459	96.12 366	63.56 462	98.39 293	87.92 384	63.97 487	90.95 466

SIFT-NN		35.94 493	36.54 496	34.16 509	73.93 518	29.52 532	62.74 522	37.28 533	19.65 527	27.91 529	49.19 528	11.66 530	46.35 528	9.19 529	37.30 517	26.61 526

ELoFTR		64.32 473	60.56 476	75.60 483	73.46 519	53.20 511	86.50 508	80.09 515	60.74 500	45.95 513	82.48 501	16.05 528	89.20 496	56.48 506	43.34 515	84.38 497

E-PMN		52.30 485	52.18 485	52.67 505	71.51 520	45.40 520	93.62 482	76.60 517	36.01 514	43.50 518	64.13 522	27.11 507	67.31 519	31.06 517	26.06 525	45.30 525

EMVS		51.44 487	51.22 488	52.11 506	70.71 521	44.97 522	94.04 477	75.66 518	35.34 516	42.40 520	61.56 526	28.93 503	65.87 520	27.64 523	24.73 526	45.49 523

PMMVS2		67.15 470	64.15 473	76.14 482	70.56 522	62.07 502	93.89 478	87.52 508	58.09 503	60.02 498	78.32 504	22.38 517	84.54 506	59.56 501	47.03 513	81.80 502

SIFT-MNN		34.10 494	34.41 497	33.17 511	68.99 523	28.51 533	60.22 524	36.81 534	19.08 530	24.04 531	47.28 531	10.06 534	45.04 529	8.72 530	34.47 519	25.97 529

SIFT-NCM-Cal		31.73 496	31.67 499	31.91 514	67.18 524	27.55 539	58.36 526	33.09 538	18.38 533	14.93 538	45.16 537	8.60 537	43.82 531	7.62 539	31.68 522	24.36 532

SIFT-NN-NCMNet		33.88 495	34.14 498	33.10 512	66.88 525	28.42 534	60.42 523	36.72 535	19.15 528	24.06 530	47.14 532	10.24 532	44.77 530	8.72 530	33.94 521	26.10 528

FPMVS		68.72 466	68.72 466	68.71 491	65.95 526	44.27 524	95.97 470	94.74 474	51.13 507	53.26 506	90.50 475	25.11 511	83.00 507	60.80 500	80.97 415	78.87 509

SP-DiffGlue		56.84 475	55.72 478	60.19 500	65.70 527	40.86 525	81.89 511	60.28 521	34.62 518	50.39 510	76.88 506	26.61 509	58.81 525	48.21 509	56.94 504	80.90 506

wuyk23d		20.37 508	20.84 511	18.99 525	65.34 528	27.73 537	50.43 534	7.67 549	9.50 542	8.01 543	6.34 543	6.13 545	26.24 542	23.40 525	10.69 540	2.99 540

SIFT-ConvMatch		30.09 499	29.76 503	31.09 516	65.16 529	27.56 538	54.13 530	31.17 539	18.55 532	17.88 534	45.89 534	8.40 538	42.26 535	8.11 535	18.51 531	23.46 534

SIFT-CM-Cal		28.34 502	27.90 506	29.63 518	63.75 530	25.98 543	50.66 533	26.18 543	18.12 536	16.88 536	44.64 538	8.08 540	39.70 536	7.65 538	15.19 536	23.22 535

LCM-MVSNet		67.77 469	64.73 472	76.87 481	62.95 531	56.25 508	89.37 502	93.74 488	44.53 509	61.99 496	80.74 503	20.42 523	86.53 504	69.37 483	59.50 501	87.84 492

SIFT-NN-CMatch		31.71 497	31.56 500	32.16 513	62.58 532	27.53 540	56.45 527	33.28 537	19.00 531	23.65 532	47.34 529	10.05 535	42.72 533	8.71 532	22.96 529	26.24 527

SIFT-UM-Cal		27.47 503	27.02 507	28.83 521	62.12 533	24.58 545	53.60 531	23.46 544	18.14 535	12.85 540	45.56 535	7.49 541	39.45 537	7.68 537	12.30 537	22.45 536

SIFT-UMatch		29.40 501	28.87 505	30.98 517	62.08 534	26.57 542	56.09 528	29.45 541	18.31 534	15.86 537	46.00 533	8.23 539	42.54 534	7.99 536	15.81 534	23.85 533

GLUNet-SfM		51.10 488	46.61 491	64.56 494	61.54 535	39.88 526	79.38 517	65.13 520	36.09 513	33.36 526	69.94 511	14.50 529	78.76 511	42.46 513	17.10 533	75.02 511

SIFT-NN-UMatch		31.23 498	31.05 502	31.79 515	60.08 536	27.23 541	58.49 525	33.65 536	19.14 529	17.30 535	47.31 530	10.12 533	42.88 532	8.67 533	24.67 527	25.27 530

XFeat-NN		42.54 489	42.87 493	41.54 508	59.73 537	27.86 536	69.53 519	45.34 531	24.36 524	37.16 523	64.79 520	20.84 520	51.40 527	30.01 518	34.12 520	45.36 524

MVE	53.74 22	51.54 486	47.86 490	62.60 495	59.56 538	50.93 512	79.41 516	77.69 516	35.69 515	36.27 524	61.76 525	5.79 546	69.63 517	37.97 514	36.61 518	67.24 514
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
SIFT-NN-PointCN		29.63 500	29.72 504	29.36 519	57.55 539	23.55 546	56.07 529	30.57 540	17.99 537	20.99 533	45.21 536	9.94 536	39.33 538	8.40 534	20.81 530	25.20 531

SIFT-PointCN		25.49 504	25.71 508	24.84 522	56.17 540	18.65 547	51.37 532	26.53 542	16.31 538	12.78 541	39.87 541	6.41 544	34.09 540	6.51 541	15.42 535	21.77 537

SIFT-PCN-Cal		24.67 505	24.81 509	24.24 523	56.13 541	18.04 548	49.05 535	23.39 545	16.07 539	12.99 539	40.17 540	6.97 543	34.68 539	6.71 540	11.81 538	19.99 538

XFeat-MNN		41.51 490	41.24 494	42.32 507	55.40 542	28.19 535	69.39 520	46.53 530	23.57 525	34.47 525	63.21 524	20.04 524	52.41 526	27.43 524	31.08 523	46.37 522

SIFT-NCMNet		21.21 507	21.22 510	21.17 524	52.99 543	16.41 549	42.12 536	14.05 547	15.89 540	10.70 542	35.85 542	5.14 547	29.82 541	5.80 542	8.44 541	17.28 539

ANet_high		56.10 476	52.24 484	67.66 492	49.27 544	56.82 506	83.94 510	82.02 514	70.47 489	33.28 527	64.54 521	17.23 526	69.16 518	45.59 511	23.85 528	77.02 510

tmp_tt		65.23 472	62.94 475	72.13 490	44.90 545	50.03 516	81.05 515	89.42 506	38.45 511	48.51 512	99.90 23	54.09 482	78.70 512	91.84 319	18.26 532	87.64 494

PMVS	49.05 23	53.75 483	51.34 487	60.97 496	40.80 546	34.68 531	74.82 518	89.62 505	37.55 512	28.67 528	72.12 507	7.09 542	81.63 510	43.17 512	68.21 477	66.59 515
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test123		37.68 492	39.14 495	33.31 510	19.94 547	24.83 544	98.36 407	9.75 548	15.53 541	51.31 507	87.14 492	19.62 525	17.74 543	47.10 510	3.47 542	57.36 520

testmvs		40.60 491	44.45 492	29.05 520	19.49 548	14.11 550	99.68 230	18.47 546	20.74 526	64.59 495	98.48 277	10.95 531	17.09 544	56.66 505	11.01 539	55.94 521

mmdepth		0.00 511	0.00 514	0.00 526	0.00 549	0.00 551	0.00 537	0.00 550	0.00 544	0.00 545	0.00 545	0.00 548	0.00 545	0.00 543	0.00 543	0.00 541

monomultidepth		0.00 511	0.00 514	0.00 526	0.00 549	0.00 551	0.00 537	0.00 550	0.00 544	0.00 545	0.00 545	0.00 548	0.00 545	0.00 543	0.00 543	0.00 541

test_blank		0.00 511	0.00 514	0.00 526	0.00 549	0.00 551	0.00 537	0.00 550	0.00 544	0.00 545	0.02 544	0.00 548	0.00 545	0.00 543	0.00 543	0.00 541

eth-test2					0.00 549

eth-test					0.00 549

uanet_test		0.00 511	0.00 514	0.00 526	0.00 549	0.00 551	0.00 537	0.00 550	0.00 544	0.00 545	0.00 545	0.00 548	0.00 545	0.00 543	0.00 543	0.00 541

DCPMVS		0.00 511	0.00 514	0.00 526	0.00 549	0.00 551	0.00 537	0.00 550	0.00 544	0.00 545	0.00 545	0.00 548	0.00 545	0.00 543	0.00 543	0.00 541

cdsmvs_eth3d_5k		23.43 506	31.24 501	0.00 526	0.00 549	0.00 551	0.00 537	98.09 234	0.00 544	0.00 545	99.67 114	83.37 313	0.00 545	0.00 543	0.00 543	0.00 541

pcd_1.5k_mvsjas		7.60 510	10.13 513	0.00 526	0.00 549	0.00 551	0.00 537	0.00 550	0.00 544	0.00 545	0.00 545	91.20 177	0.00 545	0.00 543	0.00 543	0.00 541

sosnet-low-res		0.00 511	0.00 514	0.00 526	0.00 549	0.00 551	0.00 537	0.00 550	0.00 544	0.00 545	0.00 545	0.00 548	0.00 545	0.00 543	0.00 543	0.00 541

sosnet		0.00 511	0.00 514	0.00 526	0.00 549	0.00 551	0.00 537	0.00 550	0.00 544	0.00 545	0.00 545	0.00 548	0.00 545	0.00 543	0.00 543	0.00 541

uncertanet		0.00 511	0.00 514	0.00 526	0.00 549	0.00 551	0.00 537	0.00 550	0.00 544	0.00 545	0.00 545	0.00 548	0.00 545	0.00 543	0.00 543	0.00 541

Regformer		0.00 511	0.00 514	0.00 526	0.00 549	0.00 551	0.00 537	0.00 550	0.00 544	0.00 545	0.00 545	0.00 548	0.00 545	0.00 543	0.00 543	0.00 541

ab-mvs-re		8.28 509	11.04 512	0.00 526	0.00 549	0.00 551	0.00 537	0.00 550	0.00 544	0.00 545	99.40 147	0.00 548	0.00 545	0.00 543	0.00 543	0.00 541

uanet		0.00 511	0.00 514	0.00 526	0.00 549	0.00 551	0.00 537	0.00 550	0.00 544	0.00 545	0.00 545	0.00 548	0.00 545	0.00 543	0.00 543	0.00 541

WAC-MVS						90.97 368								86.10 408

PC_three_1452									96.96 60	99.80 28	99.79 63	97.49 11	100.00 1	99.99 5	99.98 32	100.00 1

test_241102_TWO								98.43 156	97.27 47	99.80 28	99.94 5	97.18 23	100.00 1	100.00 1	100.00 1	100.00 1

test_0728_THIRD									96.48 80	99.83 24	99.91 19	97.87 6	100.00 1	99.92 16	100.00 1	100.00 1

GSMVS																99.59 154

sam_mvs1												94.72 74				99.59 154

sam_mvs												94.25 94

MTGPA								98.28 204

test_post1							95.78 472				59.23 527	93.20 128	97.74 340	91.06 329

test_post											63.35 523	94.43 82	98.13 319

patchmatchnet-post											91.70 469	95.12 60	97.95 331

MTMP							99.87 133	96.49 434

test9_res														99.71 48	99.99 21	100.00 1

agg_prior2														99.48 63	100.00 1	100.00 1

test_prior4						98.05 82	99.94 93

test_prior2							99.95 75		95.78 105	99.73 47	99.76 73	96.00 41		99.78 35	100.00 1

旧先验2							99.46 281		94.21 165	99.85 20			99.95 85	96.96 199

新几何2							99.40 286

无先验							99.49 273	98.71 79	93.46 200				100.00 1	94.36 266		99.99 26

原ACMM2							99.90 117

testdata2													99.99 39	90.54 342

segment_acmp												96.68 31

testdata1							99.28 312		96.35 91

plane_prior5								97.87 258					98.37 299	97.79 169	89.55 329	94.52 344

plane_prior4											98.59 263

plane_prior3						91.64 355			96.63 75	93.01 304

plane_prior2							99.84 152		96.38 86

plane_prior						91.74 347	99.86 144		96.76 70						89.59 328

n2								0.00 550

nn								0.00 550

door-mid								89.69 503

test11								98.44 148

door								90.31 500

HQP5-MVS						91.85 340

BP-MVS														97.92 158

HQP4-MVS										93.37 299			98.39 293			94.53 342

HQP3-MVS								97.89 256							89.60 326

HQP2-MVS												80.65 349

MDTV_nov1_ep13_2view						96.26 170	96.11 466		91.89 284	98.06 169		94.40 84		94.30 269		99.67 133

ACMMP++_ref															87.04 362

ACMMP++															88.23 349

Test By Simon												92.82 139

High-resolution multi-view benchmark