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	99.09 332	98.84 65	93.32 210	96.74 224	99.72 95	86.04 264	100.00 1	98.01 153	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	98.61 141	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	89.90 355	98.36 156	99.79 63	91.18 180	99.99 39	98.37 131	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	92.06 282	98.40 155	99.84 49	95.68 48	100.00 1	98.19 142	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	98.03 171	99.75 81	94.03 102	99.98 51	98.11 147	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	98.32 134	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	94.43 152	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		93.83 289	92.06 324	99.15 71	99.94 17	97.50 111	99.94 93	98.42 168	96.22 93	99.41 87	41.37 547	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	98.26 162	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	93.97 179	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	99.82 167	98.43 156	94.56 142	97.52 190	99.70 101	94.40 84	99.98 51	97.00 197	99.98 32	99.99 26

MG-MVS		98.91 22	98.65 27	99.68 18	99.94 17	99.07 26	99.64 240	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	92.34 270	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	94.04 177	98.80 126	99.74 88	92.98 133	100.00 1	98.16 144	99.76 88	99.93 88

TEST9					99.92 36	98.92 31	99.96 56	98.43 156	93.90 185	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	94.35 157	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	94.35 157	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	99.75 199	99.50 17	93.90 185	99.37 92	99.76 73	93.24 126	100.00 1	97.75 174	99.96 46	99.98 57

ACMMP		97.74 103	97.44 107	98.66 113	99.92 36	96.13 180	99.18 324	99.45 18	94.84 132	96.41 243	99.71 98	91.40 174	99.99 39	97.99 155	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	94.08 172	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	99.24 319	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	97.27 243	99.89 50	91.92 339	99.90 117	99.07 37	88.67 379	95.26 276	99.82 54	93.17 129	99.98 51	98.15 145	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	94.31 160	98.50 148	99.82 54	93.06 131	99.99 39	98.30 136	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	93.22 213	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	93.19 215	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	99.61 247	97.78 270	96.52 78	98.61 141	99.31 157	92.73 141	99.67 168	96.77 213	99.48 121	99.06 254

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	90.78 332	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	99.39 292	98.28 204	95.76 106	97.18 205	99.88 29	92.74 140	100.00 1	98.67 111	99.88 76	99.99 26

LS3D		95.84 212	95.11 229	98.02 167	99.85 61	95.10 232	98.74 382	98.50 137	87.22 404	93.66 299	99.86 34	87.45 239	99.95 85	90.94 335	99.81 86	99.02 262

HPM-MVS		97.96 80	97.72 90	98.68 110	99.84 63	96.39 166	99.90 117	98.17 222	92.61 251	98.62 140	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	99.40 288	98.51 131	95.29 120	98.51 147	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	94.77 245	99.92 103	98.46 142	93.93 182	97.20 203	99.27 165	95.44 55	99.97 64	97.41 181	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	99.82 167	98.30 202	93.95 181	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	99.36 298	98.50 137	95.21 122	98.30 159	99.75 81	93.29 123	99.73 159	98.37 131	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	99.76 193	98.31 199	94.43 152	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	99.76 193	98.31 199	94.43 152	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	91.75 294	98.94 119	99.54 134	91.82 172	99.65 172	97.62 178	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	93.53 197	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	97.41 232	99.76 73	93.36 305	99.65 236	97.95 249	96.03 98	97.41 196	99.70 101	89.61 206	99.51 178	96.73 215	98.25 180	99.38 201

新几何1				99.42 43	99.75 76	98.27 71		98.63 97	92.69 246	99.55 71	99.82 54	94.40 84	100.00 1	91.21 327	99.94 58	99.99 26

MP-MVS-pluss		98.07 78	97.64 96	99.38 49	99.74 77	98.41 69	99.74 203	98.18 221	93.35 208	96.45 236	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	99.77 187	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	94.06 175	99.62 62	99.85 38	94.97 69	99.96 76	95.11 247	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	98.52 145	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	99.73 210	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	96.87 261	99.71 83	91.74 349	99.85 147	97.95 249	93.11 223	95.72 265	99.16 186	92.35 156	99.94 94	95.32 243	99.35 136	98.92 270

reproduce-ours		98.78 27	98.67 24	99.09 80	99.70 85	97.30 119	99.74 203	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	99.74 203	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	95.59 305	99.67 88	86.91 436	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	93.92 378	99.63 90	81.76 471	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	97.99 155	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		96.05 202	95.82 194	96.72 267	99.59 92	96.99 136	99.95 75	99.10 34	94.06 175	98.27 160	95.80 374	89.00 218	99.95 85	99.12 79	87.53 362	93.24 436

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	98.27 160	99.08 191	89.00 218	99.95 85	99.12 79	99.25 140	99.57 162

PatchMatch-RL		96.04 203	95.40 212	97.95 170	99.59 92	95.22 226	99.52 269	99.07 37	93.96 180	96.49 234	98.35 285	82.28 326	99.82 142	90.15 351	99.22 143	98.81 278

dcpmvs_2		97.42 121	98.09 63	95.42 312	99.58 96	87.24 432	99.23 320	96.95 406	94.28 163	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	99.34 300	98.55 119	91.86 288	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	93.78 189	96.55 232	99.69 105	92.28 158	99.98 51	97.13 192	99.44 128	99.93 88

API-MVS		97.86 88	97.66 94	98.47 135	99.52 99	95.41 210	99.47 279	98.87 58	91.68 296	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	99.21 178	84.48 301	99.95 85	94.92 253	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	88.48 384	99.06 114	99.66 116	90.30 198	99.64 173	96.32 227	99.97 42	99.96 75

cl22		93.77 294	93.25 294	95.33 316	99.49 102	94.43 257	99.61 247	98.09 234	90.38 343	89.16 371	95.61 383	90.56 193	97.34 355	91.93 318	84.45 385	94.21 374

testdata				98.42 142	99.47 103	95.33 216		98.56 113	93.78 189	99.79 37	99.85 38	93.64 114	99.94 94	94.97 251	99.94 58	100.00 1

MAR-MVS		97.43 117	97.19 120	98.15 158	99.47 103	94.79 244	99.05 343	98.76 73	92.65 249	98.66 137	99.82 54	88.52 224	99.98 51	98.12 146	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		94.54 262	93.42 284	97.91 176	99.46 105	94.04 276	98.93 361	97.48 307	81.15 461	90.04 342	99.55 132	87.02 247	99.95 85	88.97 366	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	98.46 401	99.42 21	97.03 57	99.02 116	99.09 190	99.35 2	98.21 317	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	86.21 262	99.95 85	99.89 21	99.68 93	97.65 317

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	93.81 284	99.94 58	99.98 57

TAPA-MVS	92.12 8	94.42 270	93.60 276	96.90 260	99.33 110	91.78 348	99.78 181	98.00 243	89.89 356	94.52 284	99.47 138	91.97 168	99.18 204	69.90 484	99.52 114	99.73 120
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
reproduce_monomvs		95.38 234	95.07 231	96.32 282	99.32 112	96.60 156	99.76 193	98.85 62	96.65 74	87.83 400	96.05 371	99.52 1	98.11 322	96.58 219	81.07 414	94.25 367

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	97.70 196	99.28 113	95.20 227	99.98 24	97.15 365	95.53 114	99.62 62	99.79 63	92.08 166	98.38 299	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	98.59 288

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	85.97 266	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	99.64 240	99.27 27	91.43 305	97.88 180	98.99 208	95.84 46	99.84 138	98.82 101	95.32 289	99.79 112

DCV-MVSNet		97.83 92	97.37 111	99.21 60	99.18 119	97.98 86	99.64 240	99.27 27	91.43 305	97.88 180	98.99 208	95.84 46	99.84 138	98.82 101	95.32 289	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	96.40 160	98.45 138	99.16 122	95.90 186	99.66 235	98.06 237	96.37 89	94.37 290	99.49 137	83.29 319	99.90 113	97.63 177	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	98.21 166	99.24 174	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	97.43 228	99.10 125	94.42 258	99.99 8	97.10 379	95.07 123	99.68 52	99.75 81	92.95 134	98.34 303	98.38 129	99.14 145	99.54 168

Anonymous202405211		93.10 312	91.99 325	96.40 278	99.10 125	89.65 401	98.88 367	97.93 251	83.71 444	94.00 296	98.75 246	68.79 440	99.88 124	95.08 248	91.71 322	99.68 131

fmvsm_s_conf0.5_n		97.80 97	97.85 85	97.67 197	99.06 128	94.41 259	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	98.62 287

HyFIR lowres test		96.66 167	96.43 157	97.36 237	99.05 129	93.91 282	99.70 226	99.80 3	90.54 338	96.26 246	98.08 297	92.15 164	98.23 316	96.84 207	95.46 284	99.93 88

LFMVS		94.75 256	93.56 279	98.30 148	99.03 130	95.70 196	98.74 382	97.98 246	87.81 397	98.47 149	99.39 149	67.43 449	99.53 175	98.01 153	95.20 292	99.67 133

fmvsm_s_conf0.5_n_4		97.75 102	97.86 84	97.42 229	99.01 131	94.69 248	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	97.64 318

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	81.83 332	99.94 94	99.78 35	98.79 162	97.51 326

AllTest		92.48 329	91.64 332	95.00 325	99.01 131	88.43 419	98.94 359	96.82 421	86.50 414	88.71 376	98.47 280	74.73 414	99.88 124	85.39 413	96.18 258	96.71 332

TestCases				95.00 325	99.01 131	88.43 419		96.82 421	86.50 414	88.71 376	98.47 280	74.73 414	99.88 124	85.39 413	96.18 258	96.71 332

COLMAP_ROB	90.47 14	92.18 336	91.49 338	94.25 359	99.00 135	88.04 425	98.42 407	96.70 428	82.30 456	88.43 388	99.01 201	76.97 389	99.85 130	86.11 409	96.50 249	94.86 343
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	84.15 305	99.97 64	99.76 40	99.50 119	98.39 295

test_fmvs1		95.35 235	95.68 201	94.36 355	98.99 136	84.98 447	99.96 56	96.65 430	97.60 34	99.73 47	98.96 214	71.58 430	99.93 104	98.31 135	99.37 134	98.17 301

HY-MVS	92.50 7	97.79 99	97.17 122	99.63 19	98.98 138	99.32 10	97.49 437	99.52 14	95.69 109	98.32 158	97.41 318	93.32 121	99.77 150	98.08 150	95.75 274	99.81 109

VNet		97.21 131	96.57 149	99.13 77	98.97 139	97.82 95	99.03 346	99.21 32	94.31 160	99.18 105	98.88 227	86.26 261	99.89 118	98.93 92	94.32 302	99.69 130

thres200		96.96 145	96.21 168	99.22 59	98.97 139	98.84 38	99.85 147	99.71 7	93.17 217	96.26 246	98.88 227	89.87 203	99.51 178	94.26 272	94.91 294	99.31 219

tfpn200view9		96.79 154	95.99 177	99.19 62	98.94 141	98.82 39	99.78 181	99.71 7	92.86 233	96.02 256	98.87 234	89.33 210	99.50 180	93.84 281	94.57 298	99.27 229

thres400		96.78 156	95.99 177	99.16 69	98.94 141	98.82 39	99.78 181	99.71 7	92.86 233	96.02 256	98.87 234	89.33 210	99.50 180	93.84 281	94.57 298	99.16 242

sasdasda		97.09 138	96.32 162	99.39 46	98.93 143	98.95 29	99.72 214	97.35 321	94.45 148	97.88 180	99.42 142	86.71 251	99.52 176	98.48 123	93.97 308	99.72 122

Anonymous20231211		89.86 387	88.44 395	94.13 367	98.93 143	90.68 379	98.54 398	98.26 207	76.28 479	86.73 414	95.54 387	70.60 436	97.56 348	90.82 338	80.27 423	94.15 383

canonicalmvs		97.09 138	96.32 162	99.39 46	98.93 143	98.95 29	99.72 214	97.35 321	94.45 148	97.88 180	99.42 142	86.71 251	99.52 176	98.48 123	93.97 308	99.72 122

SDMVSNet		94.80 251	93.96 266	97.33 240	98.92 146	95.42 209	99.59 252	98.99 40	92.41 266	92.55 314	97.85 309	75.81 404	98.93 221	97.90 162	91.62 323	97.64 318

sd_testset		93.55 301	92.83 305	95.74 303	98.92 146	90.89 375	98.24 415	98.85 62	92.41 266	92.55 314	97.85 309	71.07 435	98.68 262	93.93 278	91.62 323	97.64 318

EPNet_dtu		95.71 223	95.39 213	96.66 269	98.92 146	93.41 301	99.57 258	98.90 50	96.19 95	97.52 190	98.56 270	92.65 144	97.36 353	77.89 465	98.33 175	99.20 239
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	98.24 164	99.39 149	93.33 120	99.74 156	97.98 157	95.58 283	99.78 115

CHOSEN 1792x2688		96.81 153	96.53 150	97.64 201	98.91 150	93.07 308	99.65 236	99.80 3	95.64 110	95.39 272	98.86 236	84.35 303	99.90 113	96.98 199	99.16 144	99.95 83

thres100view900		96.74 162	95.92 189	99.18 63	98.90 151	98.77 47	99.74 203	99.71 7	92.59 253	95.84 259	98.86 236	89.25 212	99.50 180	93.84 281	94.57 298	99.27 229

thres600view7		96.69 165	95.87 193	99.14 73	98.90 151	98.78 46	99.74 203	99.71 7	92.59 253	95.84 259	98.86 236	89.25 212	99.50 180	93.44 294	94.50 301	99.16 242

MSDG		94.37 272	93.36 291	97.40 233	98.88 153	93.95 281	99.37 296	97.38 316	85.75 425	90.80 333	99.17 183	84.11 307	99.88 124	86.35 405	98.43 173	98.36 297

MGCFI-Net		97.00 143	96.22 167	99.34 51	98.86 154	98.80 41	99.67 234	97.30 333	94.31 160	97.77 186	99.41 146	86.36 259	99.50 180	98.38 129	93.90 310	99.72 122

h-mvs33		94.92 248	94.36 251	96.59 271	98.85 155	91.29 367	98.93 361	98.94 44	95.90 101	98.77 129	98.42 283	90.89 188	99.77 150	97.80 167	70.76 469	98.72 284

Anonymous20240529		92.10 337	90.65 349	96.47 273	98.82 156	90.61 381	98.72 384	98.67 87	75.54 483	93.90 298	98.58 268	66.23 454	99.90 113	94.70 262	90.67 326	98.90 273

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	96.38 244	98.49 276	89.05 216	99.88 124	97.10 194	98.34 174	99.43 194

PS-MVSNAJ		98.44 49	98.20 54	99.16 69	98.80 158	98.92 31	99.54 267	98.17 222	97.34 42	99.85 20	99.85 38	91.20 177	99.89 118	99.41 68	99.67 94	98.69 285

CANet_DTU		96.76 157	96.15 171	98.60 118	98.78 159	97.53 108	99.84 152	97.63 284	97.25 50	99.20 102	99.64 119	81.36 338	99.98 51	92.77 306	98.89 156	98.28 299

mvsany_test1		97.82 95	97.90 80	97.55 212	98.77 160	93.04 311	99.80 175	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	94.40 156	98.41 153	99.47 138	93.65 113	99.42 190	98.57 117	94.26 304	99.67 133

SymmetryMVS		97.64 110	97.46 104	98.17 154	98.74 162	95.39 212	99.61 247	99.26 29	96.52 78	98.61 141	99.31 157	92.73 141	99.67 168	96.77 213	95.63 281	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	99.52 269	98.08 236	97.05 56	99.86 16	99.86 34	90.65 190	99.71 160	99.39 70	98.63 166	98.69 285

miper_enhance_ethall		94.36 274	93.98 265	95.49 306	98.68 165	95.24 224	99.73 210	97.29 341	93.28 212	89.86 347	95.97 372	94.37 88	97.05 376	92.20 310	84.45 385	94.19 375

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	85.99 265	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	91.10 318	98.17 167	98.59 265	93.86 108	98.19 318	95.64 240	95.24 291	99.28 226

test2506		97.53 114	97.19 120	98.58 122	98.66 168	96.90 140	98.81 376	99.77 5	94.93 126	97.95 174	98.96 214	92.51 151	99.20 202	94.93 252	98.15 183	99.64 139

ECVR-MVS		95.66 226	95.05 232	97.51 217	98.66 168	93.71 286	98.85 373	98.45 143	94.93 126	96.86 217	98.96 214	75.22 410	99.20 202	95.34 242	98.15 183	99.64 139

BridgeMVS		98.27 63	97.99 70	99.11 78	98.64 170	98.43 68	99.47 279	97.79 266	94.56 142	99.74 45	98.35 285	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	94.26 267	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	99.08 252

MVSMamba_PlusPlus		97.83 92	97.45 106	98.99 90	98.60 172	98.15 72	99.58 254	97.74 275	90.34 346	99.26 101	98.32 288	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	94.94 237	99.41 287	97.56 296	93.53 197	99.42 86	97.89 308	83.33 318	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	92.53 261	98.84 123	98.84 240	93.36 118	98.30 308	95.84 236	94.30 303	99.05 256

test1111		95.57 229	94.98 235	97.37 235	98.56 174	93.37 304	98.86 371	98.45 143	94.95 125	96.63 226	98.95 219	75.21 411	99.11 208	95.02 249	98.14 185	99.64 139

MVSTER		95.53 230	95.22 224	96.45 276	98.56 174	97.72 99	99.91 111	97.67 280	92.38 269	91.39 324	97.14 325	97.24 20	97.30 360	94.80 258	87.85 355	94.34 362

testing3-2		97.72 106	97.43 109	98.60 118	98.55 177	97.11 131	100.00 1	99.23 31	93.78 189	97.90 176	98.73 248	95.50 53	99.69 164	98.53 121	94.63 296	98.99 264

VDD-MVS		93.77 294	92.94 303	96.27 283	98.55 177	90.22 390	98.77 381	97.79 266	90.85 324	96.82 221	99.42 142	61.18 474	99.77 150	98.95 90	94.13 305	98.82 277

tpmvs		94.28 276	93.57 278	96.40 278	98.55 177	91.50 365	95.70 476	98.55 119	87.47 399	92.15 317	94.26 441	91.42 173	98.95 220	88.15 383	95.85 269	98.76 280

UGNet		95.33 236	94.57 247	97.62 205	98.55 177	94.85 239	98.67 390	99.32 26	95.75 107	96.80 223	96.27 361	72.18 427	99.96 76	94.58 265	99.05 152	98.04 306
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	95.18 239	94.10 259	98.43 140	98.55 177	95.99 184	97.91 430	97.31 332	90.35 345	89.48 360	99.22 175	85.19 283	99.89 118	90.40 348	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		95.95 206	96.49 152	94.34 356	98.51 182	89.99 395	99.39 292	98.57 107	93.14 220	97.33 199	98.31 290	93.44 116	94.68 466	93.69 291	95.98 263	98.34 298

UWE-MVS		96.79 154	96.72 142	97.00 254	98.51 182	93.70 287	99.71 219	98.60 101	92.96 228	97.09 207	98.34 287	96.67 33	98.85 228	92.11 316	96.50 249	98.44 293

myMVS_eth3d28		97.86 88	97.59 100	98.68 110	98.50 184	97.26 121	99.92 103	98.55 119	93.79 188	98.26 162	98.75 246	95.20 58	99.48 186	98.93 92	96.40 252	99.29 224

test_vis1_n_1920		95.44 232	95.31 220	95.82 300	98.50 184	88.74 413	99.98 24	97.30 333	97.84 28	99.85 20	99.19 181	66.82 452	99.97 64	98.82 101	99.46 126	98.76 280

BH-w/o		95.71 223	95.38 218	96.68 268	98.49 186	92.28 330	99.84 152	97.50 305	92.12 279	92.06 320	98.79 244	84.69 296	98.67 264	95.29 244	99.66 95	99.09 250

baseline1		95.78 219	94.86 238	98.54 128	98.47 187	98.07 80	99.06 339	97.99 244	92.68 247	94.13 295	98.62 262	93.28 124	98.69 261	93.79 286	85.76 372	98.84 276

fmvsm_s_conf0.5_n_7		97.70 108	97.74 89	97.59 210	98.44 188	95.16 230	99.97 42	98.65 88	97.95 24	99.62 62	99.78 67	86.09 263	99.94 94	99.69 50	99.50 119	97.66 316

EPMVS		96.53 176	96.01 176	98.09 162	98.43 189	96.12 182	96.36 463	99.43 20	93.53 197	97.64 188	95.04 415	94.41 83	98.38 299	91.13 329	98.11 186	99.75 118

kuosan		93.17 309	92.60 311	94.86 332	98.40 190	89.54 403	98.44 403	98.53 126	84.46 439	88.49 383	97.92 305	90.57 192	97.05 376	83.10 430	93.49 313	97.99 307

WBMVS		94.52 265	94.03 263	95.98 290	98.38 191	96.68 151	99.92 103	97.63 284	90.75 333	89.64 355	95.25 408	96.77 27	96.90 389	94.35 270	83.57 392	94.35 360

UBG		97.84 91	97.69 93	98.29 149	98.38 191	96.59 158	99.90 117	98.53 126	93.91 184	98.52 145	98.42 283	96.77 27	99.17 205	98.54 119	96.20 257	99.11 249

sss		97.57 113	97.03 127	99.18 63	98.37 193	98.04 83	99.73 210	99.38 22	93.46 202	98.76 132	99.06 195	91.21 176	99.89 118	96.33 226	97.01 235	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	93.45 204	98.15 168	98.70 252	95.48 54	99.22 198	97.85 164	95.05 293	99.07 253

BH-untuned		95.18 239	94.83 239	96.22 284	98.36 194	91.22 368	99.80 175	97.32 331	90.91 322	91.08 327	98.67 254	83.51 311	98.54 281	94.23 273	99.61 104	98.92 270

testing91		97.16 133	96.90 131	97.97 168	98.35 196	95.67 199	99.91 111	98.42 168	92.91 231	97.33 199	98.72 249	94.81 72	99.21 199	96.98 199	94.63 296	99.03 261

testing99		97.17 132	96.91 130	97.95 170	98.35 196	95.70 196	99.91 111	98.43 156	92.94 229	97.36 197	98.72 249	94.83 71	99.21 199	97.00 197	94.64 295	98.95 266

ET-MVSNet_ETH3D		94.37 272	93.28 293	97.64 201	98.30 198	97.99 85	99.99 8	97.61 290	94.35 157	71.57 491	99.45 141	96.23 39	95.34 455	96.91 205	85.14 379	99.59 154

AUN-MVS		93.28 306	92.60 311	95.34 315	98.29 199	90.09 393	99.31 306	98.56 113	91.80 292	96.35 245	98.00 300	89.38 209	98.28 311	92.46 307	69.22 476	97.64 318

FMVSNet3		92.69 324	91.58 334	95.99 289	98.29 199	97.42 116	99.26 318	97.62 287	89.80 357	89.68 351	95.32 402	81.62 336	96.27 430	87.01 401	85.65 373	94.29 364

PMMVS		96.76 157	96.76 139	96.76 265	98.28 201	92.10 334	99.91 111	97.98 246	94.12 170	99.53 74	99.39 149	86.93 249	98.73 252	96.95 202	97.73 194	99.45 190

hse-mvs2		94.38 271	94.08 262	95.31 317	98.27 202	90.02 394	99.29 313	98.56 113	95.90 101	98.77 129	98.00 300	90.89 188	98.26 315	97.80 167	69.20 477	97.64 318

PVSNet_0	88.03 19	91.80 344	90.27 358	96.38 280	98.27 202	90.46 385	99.94 93	99.61 13	93.99 178	86.26 424	97.39 320	71.13 434	99.89 118	98.77 105	67.05 483	98.79 279

UA-Net		96.54 175	95.96 183	98.27 150	98.23 204	95.71 195	98.00 427	98.45 143	93.72 193	98.41 153	99.27 165	88.71 223	99.66 171	91.19 328	97.69 195	99.44 193

test_cas_vis1_n_1920		96.59 171	96.23 165	97.65 200	98.22 205	94.23 269	99.99 8	97.25 347	97.77 29	99.58 70	99.08 191	77.10 384	99.97 64	97.64 176	99.45 127	98.74 282

FE-MVS		95.70 225	95.01 234	97.79 185	98.21 206	94.57 250	95.03 477	98.69 82	88.90 373	97.50 192	96.19 363	92.60 147	99.49 185	89.99 353	97.94 192	99.31 219

GG-mvs-BLEND				98.54 128	98.21 206	98.01 84	93.87 482	98.52 128		97.92 175	97.92 305	99.02 3	97.94 335	98.17 143	99.58 109	99.67 133

mvs_anonymous		95.65 227	95.03 233	97.53 214	98.19 208	95.74 193	99.33 301	97.49 306	90.87 323	90.47 336	97.10 327	88.23 226	97.16 367	95.92 234	97.66 198	99.68 131

MVS_Test		96.46 179	95.74 197	98.61 117	98.18 209	97.23 123	99.31 306	97.15 365	91.07 319	98.84 123	97.05 331	88.17 227	98.97 217	94.39 267	97.50 200	99.61 151

BH-RMVSNet		95.18 239	94.31 254	97.80 183	98.17 210	95.23 225	99.76 193	97.53 301	92.52 262	94.27 293	99.25 172	76.84 391	98.80 241	90.89 337	99.54 111	99.35 209

dongtai		91.55 350	91.13 343	92.82 408	98.16 211	86.35 437	99.47 279	98.51 131	83.24 447	85.07 435	97.56 314	90.33 197	94.94 461	76.09 473	91.73 321	97.18 329

RPSCF		91.80 344	92.79 307	88.83 451	98.15 212	69.87 495	98.11 423	96.60 432	83.93 442	94.33 291	99.27 165	79.60 362	99.46 189	91.99 317	93.16 318	97.18 329

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		96.29 192	95.90 190	97.45 224	98.13 214	94.80 243	99.08 334	97.61 290	92.02 284	95.54 270	98.96 214	90.64 191	98.08 324	93.73 289	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	80.88 346	99.93 104	99.59 56	98.17 181	97.29 327

ab-mvs		94.69 257	93.42 284	98.51 133	98.07 217	96.26 170	96.49 461	98.68 84	90.31 347	94.54 283	97.00 334	76.30 399	99.71 160	95.98 233	93.38 316	99.56 163

XVG-OURS-SEG-HR		94.79 252	94.70 246	95.08 322	98.05 218	89.19 405	99.08 334	97.54 299	93.66 194	94.87 279	99.58 128	78.78 370	99.79 145	97.31 184	93.40 315	96.25 336

EIA-MVS		97.53 114	97.46 104	97.76 191	98.04 219	94.84 240	99.98 24	97.61 290	94.41 155	97.90 176	99.59 125	92.40 155	98.87 225	98.04 152	99.13 146	99.59 154

XVG-OURS		94.82 249	94.74 245	95.06 323	98.00 220	89.19 405	99.08 334	97.55 297	94.10 171	94.71 281	99.62 123	80.51 353	99.74 156	96.04 232	93.06 320	96.25 336

mvsmamba		96.94 146	96.73 141	97.55 212	97.99 221	94.37 263	99.62 243	97.70 277	93.13 221	98.42 152	97.92 305	88.02 228	98.75 250	98.78 104	99.01 153	99.52 173

dp		95.05 243	94.43 249	96.91 258	97.99 221	92.73 319	96.29 466	97.98 246	89.70 358	95.93 258	94.67 430	93.83 110	98.45 287	86.91 404	96.53 248	99.54 168

tpmrst		96.27 194	95.98 179	97.13 249	97.96 223	93.15 307	96.34 464	98.17 222	92.07 280	98.71 135	95.12 412	93.91 105	98.73 252	94.91 255	96.62 246	99.50 179

TR-MVS		94.54 262	93.56 279	97.49 222	97.96 223	94.34 265	98.71 385	97.51 304	90.30 348	94.51 285	98.69 253	75.56 405	98.77 246	92.82 305	95.99 262	99.35 209

Vis-MVSNet (Re-imp)		96.32 189	95.98 179	97.35 239	97.93 225	94.82 242	99.47 279	98.15 230	91.83 289	95.09 277	99.11 189	91.37 175	97.47 351	93.47 293	97.43 201	99.74 119

MDTV_nov1_ep13			95.69 199		97.90 226	94.15 273	95.98 472	98.44 148	93.12 222	97.98 173	95.74 376	95.10 61	98.58 274	90.02 352	96.92 237

Fast-Effi-MVS+		95.02 245	94.19 257	97.52 216	97.88 227	94.55 251	99.97 42	97.08 383	88.85 375	94.47 286	97.96 304	84.59 298	98.41 291	89.84 355	97.10 225	99.59 154

ADS-MVSNet2		93.80 293	93.88 269	93.55 391	97.87 228	85.94 441	94.24 478	96.84 418	90.07 351	96.43 241	94.48 435	90.29 199	95.37 454	87.44 390	97.23 212	99.36 205

ADS-MVSNet		94.79 252	94.02 264	97.11 251	97.87 228	93.79 283	94.24 478	98.16 227	90.07 351	96.43 241	94.48 435	90.29 199	98.19 318	87.44 390	97.23 212	99.36 205

Effi-MVS+		96.30 191	95.69 199	98.16 155	97.85 230	96.26 170	97.41 440	97.21 355	90.37 344	98.65 139	98.58 268	86.61 255	98.70 259	97.11 193	97.37 206	99.52 173

PatchmatchNet		95.94 207	95.45 208	97.39 234	97.83 231	94.41 259	96.05 470	98.40 177	92.86 233	97.09 207	95.28 407	94.21 97	98.07 326	89.26 364	98.11 186	99.70 125
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
cascas		94.64 260	93.61 274	97.74 193	97.82 232	96.26 170	99.96 56	97.78 270	85.76 423	94.00 296	97.54 315	76.95 390	99.21 199	97.23 189	95.43 286	97.76 315

1112_ss		96.01 204	95.20 225	98.42 142	97.80 233	96.41 163	99.65 236	96.66 429	92.71 244	92.88 310	99.40 147	92.16 163	99.30 194	91.92 319	93.66 311	99.55 164

E3new		96.75 159	96.43 157	97.71 194	97.79 234	94.83 241	99.80 175	97.33 325	93.52 200	97.49 193	99.31 157	87.73 231	98.83 229	97.52 179	97.40 205	99.48 182

Test_1112_low_res		95.72 221	94.83 239	98.42 142	97.79 234	96.41 163	99.65 236	96.65 430	92.70 245	92.86 311	96.13 367	92.15 164	99.30 194	91.88 320	93.64 312	99.55 164

Effi-MVS+-dtu		94.53 264	95.30 221	92.22 416	97.77 236	82.54 464	99.59 252	97.06 392	94.92 128	95.29 274	95.37 400	85.81 267	97.89 336	94.80 258	97.07 226	96.23 338

tpm cat1		93.51 302	92.52 317	96.47 273	97.77 236	91.47 366	96.13 468	98.06 237	80.98 462	92.91 309	93.78 446	89.66 204	98.87 225	87.03 400	96.39 253	99.09 250

FA-MVS(test-final)		95.86 210	95.09 230	98.15 158	97.74 238	95.62 201	96.31 465	98.17 222	91.42 307	96.26 246	96.13 367	90.56 193	99.47 188	92.18 311	97.07 226	99.35 209

xiu_mvs_v1_base_debu		97.43 117	97.06 123	98.55 124	97.74 238	98.14 74	99.31 306	97.86 260	96.43 83	99.62 62	99.69 105	85.56 275	99.68 165	99.05 82	98.31 176	97.83 311

xiu_mvs_v1_base		97.43 117	97.06 123	98.55 124	97.74 238	98.14 74	99.31 306	97.86 260	96.43 83	99.62 62	99.69 105	85.56 275	99.68 165	99.05 82	98.31 176	97.83 311

xiu_mvs_v1_base_debi		97.43 117	97.06 123	98.55 124	97.74 238	98.14 74	99.31 306	97.86 260	96.43 83	99.62 62	99.69 105	85.56 275	99.68 165	99.05 82	98.31 176	97.83 311

EPP-MVSNet		96.69 165	96.60 147	96.96 256	97.74 238	93.05 310	99.37 296	98.56 113	88.75 377	95.83 261	99.01 201	96.01 40	98.56 277	96.92 203	97.20 214	99.25 233

gg-mvs-nofinetune		93.51 302	91.86 329	98.47 135	97.72 243	97.96 89	92.62 493	98.51 131	74.70 486	97.33 199	69.59 520	98.91 4	97.79 339	97.77 172	99.56 110	99.67 133

IB-MVS	92.85 6	94.99 246	93.94 267	98.16 155	97.72 243	95.69 198	99.99 8	98.81 67	94.28 163	92.70 312	96.90 338	95.08 62	99.17 205	96.07 231	73.88 457	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	91.83 289	97.45 194	99.04 197	97.50 10	99.10 209	94.75 260	96.37 254	99.16 242

VortexMVS		94.11 280	93.50 281	95.94 292	97.70 246	96.61 155	99.35 299	97.18 358	93.52 200	89.57 358	95.74 376	87.55 236	96.97 384	95.76 239	85.13 380	94.23 369

viewdifsd2359ckpt09		96.21 197	95.77 195	97.53 214	97.69 247	94.50 254	99.78 181	97.23 352	92.88 232	96.58 229	99.26 169	84.85 289	98.66 267	96.61 217	97.02 233	99.43 194

Syy-MVS		90.00 385	90.63 350	88.11 460	97.68 248	74.66 491	99.71 219	98.35 190	90.79 330	92.10 318	98.67 254	79.10 368	93.09 482	63.35 500	95.95 266	96.59 334

myMVS_eth3d		94.46 269	94.76 244	93.55 391	97.68 248	90.97 370	99.71 219	98.35 190	90.79 330	92.10 318	98.67 254	92.46 154	93.09 482	87.13 397	95.95 266	96.59 334

test_fmvs1_n		94.25 277	94.36 251	93.92 378	97.68 248	83.70 454	99.90 117	96.57 433	97.40 40	99.67 53	98.88 227	61.82 471	99.92 110	98.23 141	99.13 146	98.14 304

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		96.24 196	95.68 201	97.94 173	97.65 252	94.92 238	99.27 316	97.10 379	92.79 239	97.43 195	97.99 302	81.85 331	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	99.81 169	97.19 356	94.67 140	98.95 118	99.28 161	86.43 256	98.76 248	98.37 131	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		96.59 171	96.23 165	97.66 199	97.63 254	94.70 246	99.77 187	97.33 325	93.41 205	97.34 198	99.17 183	86.72 250	98.83 229	97.40 182	97.32 209	99.46 185

viewdifsd2359ckpt13		96.19 198	95.77 195	97.45 224	97.62 255	94.40 261	99.70 226	97.23 352	92.76 241	96.63 226	99.05 196	84.96 288	98.64 270	96.65 216	97.35 207	99.31 219

Vis-MVSNet		95.72 221	95.15 228	97.45 224	97.62 255	94.28 266	99.28 314	98.24 210	94.27 165	96.84 219	98.94 221	79.39 363	98.76 248	93.25 296	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	91.11 317	97.07 209	98.97 212	97.47 13	99.03 212	93.73 289	96.09 260	98.92 270

GDP-MVS		97.88 86	97.59 100	98.75 106	97.59 258	97.81 96	99.95 75	97.37 319	94.44 151	99.08 110	99.58 128	97.13 25	99.08 210	94.99 250	98.17 181	99.37 203

miper_ehance_all_eth		93.16 310	92.60 311	94.82 333	97.57 259	93.56 296	99.50 273	97.07 391	88.75 377	88.85 375	95.52 389	90.97 184	96.74 400	90.77 339	84.45 385	94.17 377

guyue		97.15 134	96.82 136	98.15 158	97.56 260	96.25 174	99.71 219	97.84 263	95.75 107	98.13 169	98.65 257	87.58 235	98.82 232	98.29 137	97.91 193	99.36 205

viewmanbaseed2359cas		96.45 180	96.07 173	97.59 210	97.55 261	94.59 249	99.70 226	97.33 325	93.62 196	97.00 213	99.32 154	85.57 274	98.71 256	97.26 188	97.33 208	99.47 183

testing3		93.92 286	94.23 256	92.99 405	97.54 262	90.23 389	99.99 8	99.16 33	90.57 337	91.33 326	98.63 261	92.99 132	92.52 486	82.46 435	95.39 287	96.22 339

SSM_0404		95.75 220	95.16 227	97.50 219	97.53 263	95.39 212	99.11 330	97.25 347	90.81 326	95.27 275	98.83 241	84.74 293	98.67 264	95.24 245	97.69 195	98.45 292

LCM-MVSNet-Re		92.31 333	92.60 311	91.43 425	97.53 263	79.27 482	99.02 348	91.83 500	92.07 280	80.31 461	94.38 439	83.50 312	95.48 451	97.22 190	97.58 199	99.54 168

GBi-Net		90.88 361	89.82 367	94.08 369	97.53 263	91.97 335	98.43 404	96.95 406	87.05 405	89.68 351	94.72 426	71.34 431	96.11 436	87.01 401	85.65 373	94.17 377

test1		90.88 361	89.82 367	94.08 369	97.53 263	91.97 335	98.43 404	96.95 406	87.05 405	89.68 351	94.72 426	71.34 431	96.11 436	87.01 401	85.65 373	94.17 377

FMVSNet2		91.02 358	89.56 372	95.41 313	97.53 263	95.74 193	98.98 351	97.41 314	87.05 405	88.43 388	95.00 420	71.34 431	96.24 432	85.12 416	85.21 378	94.25 367

tttt0517		96.85 151	96.49 152	97.92 174	97.48 268	95.89 187	99.85 147	98.54 123	90.72 334	96.63 226	98.93 224	97.47 13	99.02 213	93.03 303	95.76 273	98.85 275

onestephybrid01		96.75 159	96.44 156	97.71 194	97.47 269	95.03 233	99.83 160	97.27 343	94.15 168	98.66 137	99.25 172	85.72 269	98.81 236	98.42 127	97.17 220	99.28 226

cashybrid2		96.25 195	95.89 191	97.32 242	97.45 270	93.68 289	99.80 175	97.22 354	93.38 206	96.86 217	99.28 161	84.64 297	98.87 225	97.18 191	97.19 215	99.41 198

BP-MVS1		98.33 59	98.18 56	98.81 101	97.44 271	97.98 86	99.96 56	98.17 222	94.88 130	98.77 129	99.59 125	97.59 8	99.08 210	98.24 140	98.93 155	99.36 205

casdiffmvs_mvg		96.43 181	95.94 187	97.89 178	97.44 271	95.47 205	99.86 144	97.29 341	93.35 208	96.03 254	99.19 181	85.39 279	98.72 255	97.89 163	97.04 230	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		96.36 186	95.95 185	97.60 207	97.41 273	94.52 252	99.71 219	97.33 325	93.20 214	97.02 210	99.07 193	85.37 280	98.82 232	97.27 185	97.14 222	99.46 185

EC-MVSNet		97.38 124	97.24 117	97.80 183	97.41 273	95.64 200	99.99 8	97.06 392	94.59 141	99.63 59	99.32 154	89.20 215	98.14 320	98.76 106	99.23 142	99.62 147

viewdifsd2359ckpt07		95.83 213	95.42 210	97.07 252	97.40 275	93.04 311	99.60 250	97.24 350	92.39 268	96.09 253	99.14 188	83.07 322	98.93 221	97.02 196	96.87 238	99.23 236

c3_l		92.53 328	91.87 328	94.52 345	97.40 275	92.99 313	99.40 288	96.93 411	87.86 395	88.69 378	95.44 394	89.95 202	96.44 418	90.45 345	80.69 419	94.14 387

hybrid		96.53 176	96.15 171	97.67 197	97.39 277	95.12 231	99.80 175	97.15 365	93.38 206	98.23 165	99.16 186	85.20 282	98.70 259	97.92 159	97.15 221	99.20 239

viewmambaseed2359dif		95.92 209	95.55 206	97.04 253	97.38 278	93.41 301	99.78 181	96.97 404	91.14 316	96.58 229	99.27 165	84.85 289	98.75 250	96.87 206	97.12 224	98.97 265

fmvsm_s_conf0.1_n		97.30 125	97.21 119	97.60 207	97.38 278	94.40 261	99.90 117	98.64 91	96.47 82	99.51 78	99.65 118	84.99 287	99.93 104	99.22 76	99.09 149	98.46 291

hybridcas		96.09 201	95.62 203	97.50 219	97.37 280	94.44 255	99.84 152	97.16 362	93.16 218	96.03 254	99.21 178	84.19 304	98.65 269	96.53 221	97.07 226	99.42 197

E3		96.36 186	95.95 185	97.60 207	97.37 280	94.52 252	99.71 219	97.33 325	93.18 216	97.02 210	99.07 193	85.45 278	98.82 232	97.27 185	97.14 222	99.46 185

CDS-MVSNet		96.34 188	96.07 173	97.13 249	97.37 280	94.96 235	99.53 268	97.91 255	91.55 299	95.37 273	98.32 288	95.05 64	97.13 370	93.80 285	95.75 274	99.30 222
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
hybridnocas07		96.57 173	96.16 170	97.81 182	97.36 283	95.32 217	99.81 169	97.12 371	94.17 167	98.02 172	98.90 225	85.05 285	98.80 241	97.85 164	97.18 216	99.32 214

TESTMET0.1,1		96.74 162	96.26 164	98.16 155	97.36 283	96.48 160	99.96 56	98.29 203	91.93 285	95.77 262	98.07 298	95.54 50	98.29 309	90.55 343	98.89 156	99.70 125

miper_lstm_enhance		91.81 341	91.39 340	93.06 404	97.34 285	89.18 407	99.38 294	96.79 423	86.70 413	87.47 406	95.22 409	90.00 201	95.86 445	88.26 379	81.37 408	94.15 383

baseline		96.43 181	95.98 179	97.76 191	97.34 285	95.17 229	99.51 271	97.17 360	93.92 183	96.90 216	99.28 161	85.37 280	98.64 270	97.50 180	96.86 240	99.46 185

cl____		92.31 333	91.58 334	94.52 345	97.33 287	92.77 315	99.57 258	96.78 424	86.97 409	87.56 404	95.51 390	89.43 208	96.62 407	88.60 369	82.44 400	94.16 382

SD_0403		92.63 327	93.38 288	90.40 439	97.32 288	77.91 484	97.75 435	98.03 242	91.89 286	90.83 332	98.29 292	82.00 328	93.79 475	88.51 374	95.75 274	99.52 173

DIV-MVS_self_test		92.32 332	91.60 333	94.47 349	97.31 289	92.74 317	99.58 254	96.75 425	86.99 408	87.64 402	95.54 387	89.55 207	96.50 413	88.58 370	82.44 400	94.17 377

casdiffmvs		96.42 183	95.97 182	97.77 189	97.30 290	94.98 234	99.84 152	97.09 382	93.75 192	96.58 229	99.26 169	85.07 284	98.78 245	97.77 172	97.04 230	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		94.36 274	93.48 282	96.99 255	97.29 291	93.54 297	99.96 56	96.72 427	88.35 388	93.43 300	98.94 221	82.05 327	98.05 327	88.12 385	96.48 251	99.37 203

eth_miper_zixun_eth		92.41 331	91.93 326	93.84 382	97.28 292	90.68 379	98.83 374	96.97 404	88.57 382	89.19 370	95.73 379	89.24 214	96.69 405	89.97 354	81.55 406	94.15 383

MVSFormer		96.94 146	96.60 147	97.95 170	97.28 292	97.70 102	99.55 265	97.27 343	91.17 313	99.43 84	99.54 134	90.92 185	96.89 390	94.67 263	99.62 99	99.25 233

lupinMVS		97.85 90	97.60 98	98.62 116	97.28 292	97.70 102	99.99 8	97.55 297	95.50 116	99.43 84	99.67 114	90.92 185	98.71 256	98.40 128	99.62 99	99.45 190

nocashy02		96.61 169	96.34 161	97.42 229	97.26 295	94.37 263	99.83 160	97.16 362	94.51 144	97.89 178	99.26 169	86.38 257	98.66 267	97.70 175	97.06 229	99.23 236

dtuplus		95.79 218	95.42 210	96.93 257	97.24 296	93.16 306	99.78 181	96.93 411	91.69 295	96.18 251	99.29 160	83.80 309	98.73 252	96.83 208	97.02 233	98.89 274

diffmvs_AUTHOR		96.75 159	96.41 159	97.79 185	97.20 297	95.46 206	99.69 229	97.15 365	94.46 147	98.78 127	99.21 178	85.64 272	98.77 246	98.27 138	97.31 210	99.13 246

mamba_0408		94.98 247	94.09 260	97.64 201	97.14 298	95.31 218	93.48 488	97.08 383	90.48 340	94.40 287	98.62 262	84.49 299	98.67 264	93.99 276	97.18 216	98.93 267

SSM_04072		94.77 254	94.09 260	96.82 262	97.14 298	95.31 218	93.48 488	97.08 383	90.48 340	94.40 287	98.62 262	84.49 299	96.21 433	93.99 276	97.18 216	98.93 267

SSM_0407		95.62 228	94.95 236	97.61 206	97.14 298	95.31 218	99.00 349	97.25 347	90.81 326	94.40 287	98.83 241	84.74 293	98.58 274	95.24 245	97.18 216	98.93 267

SCA		94.69 257	93.81 271	97.33 240	97.10 301	94.44 255	98.86 371	98.32 197	93.30 211	96.17 252	95.59 385	76.48 397	97.95 333	91.06 331	97.43 201	99.59 154

viewmacassd2359aftdt		95.93 208	95.45 208	97.36 237	97.09 302	94.12 275	99.57 258	97.26 346	93.05 226	96.50 233	99.17 183	82.76 323	98.68 262	96.61 217	97.04 230	99.28 226

KinetiMVS		96.10 199	95.29 222	98.53 130	97.08 303	97.12 129	99.56 262	98.12 233	94.78 133	98.44 150	98.94 221	80.30 357	99.39 191	91.56 324	98.79 162	99.06 254

TAMVS		95.85 211	95.58 204	96.65 270	97.07 304	93.50 298	99.17 325	97.82 265	91.39 309	95.02 278	98.01 299	92.20 162	97.30 360	93.75 288	95.83 270	99.14 245

Fast-Effi-MVS+-dtu		93.72 297	93.86 270	93.29 396	97.06 305	86.16 438	99.80 175	96.83 419	92.66 248	92.58 313	97.83 311	81.39 337	97.67 344	89.75 356	96.87 238	96.05 341

E4		96.01 204	95.53 207	97.44 227	97.05 306	94.23 269	99.57 258	97.30 333	92.72 242	96.47 235	99.03 198	83.98 308	98.83 229	96.92 203	96.77 241	99.27 229

E5new		95.83 213	95.39 213	97.15 245	97.03 307	93.59 291	99.32 304	97.30 333	92.58 255	96.45 236	99.00 205	83.37 315	98.81 236	96.81 209	96.65 244	99.04 257

E5		95.83 213	95.39 213	97.15 245	97.03 307	93.59 291	99.32 304	97.30 333	92.58 255	96.45 236	99.00 205	83.37 315	98.81 236	96.81 209	96.65 244	99.04 257

CostFormer		96.10 199	95.88 192	96.78 264	97.03 307	92.55 325	97.08 449	97.83 264	90.04 353	98.72 134	94.89 424	95.01 66	98.29 309	96.54 220	95.77 272	99.50 179

test_fmvsmvis_n_1920		97.67 109	97.59 100	97.91 176	97.02 310	95.34 215	99.95 75	98.45 143	97.87 26	97.02 210	99.59 125	89.64 205	99.98 51	99.41 68	99.34 137	98.42 294

test-LLR		96.47 178	96.04 175	97.78 187	97.02 310	95.44 207	99.96 56	98.21 217	94.07 173	95.55 268	96.38 356	93.90 106	98.27 313	90.42 346	98.83 160	99.64 139

test-mter		96.39 184	95.93 188	97.78 187	97.02 310	95.44 207	99.96 56	98.21 217	91.81 291	95.55 268	96.38 356	95.17 59	98.27 313	90.42 346	98.83 160	99.64 139

casdiffseed414692147		95.07 242	94.26 255	97.50 219	97.01 313	94.70 246	99.58 254	97.02 396	91.27 311	94.66 282	98.82 243	80.79 348	98.55 280	93.39 295	95.79 271	99.27 229

E6new		95.83 213	95.39 213	97.14 247	97.00 314	93.58 293	99.31 306	97.30 333	92.57 257	96.45 236	99.01 201	83.44 313	98.81 236	96.80 211	96.66 242	99.04 257

E6		95.83 213	95.39 213	97.14 247	97.00 314	93.58 293	99.31 306	97.30 333	92.57 257	96.45 236	99.01 201	83.44 313	98.81 236	96.80 211	96.66 242	99.04 257

icg_test_0407_2		95.04 244	94.78 243	95.84 299	96.97 316	91.64 357	98.63 393	97.12 371	92.33 271	95.60 266	98.88 227	85.65 270	96.56 410	92.12 312	95.70 277	99.32 214

IMVS_0407		95.21 238	94.80 242	96.46 275	96.97 316	91.64 357	98.81 376	97.12 371	92.33 271	95.60 266	98.88 227	85.65 270	98.42 289	92.12 312	95.70 277	99.32 214

IMVS_0404		93.83 289	93.17 295	95.80 301	96.97 316	91.64 357	97.78 434	97.12 371	92.33 271	90.87 331	98.88 227	76.78 392	96.43 419	92.12 312	95.70 277	99.32 214

IMVS_0403		95.25 237	94.81 241	96.58 272	96.97 316	91.64 357	98.97 356	97.12 371	92.33 271	95.43 271	98.88 227	85.78 268	98.79 243	92.12 312	95.70 277	99.32 214

gm-plane-assit					96.97 316	93.76 285			91.47 303		98.96 214		98.79 243	94.92 253

WB-MVSnew		92.90 316	92.77 308	93.26 398	96.95 321	93.63 290	99.71 219	98.16 227	91.49 300	94.28 292	98.14 295	81.33 339	96.48 416	79.47 454	95.46 284	89.68 484

QAPM		95.40 233	94.17 258	99.10 79	96.92 322	97.71 100	99.40 288	98.68 84	89.31 361	88.94 374	98.89 226	82.48 325	99.96 76	93.12 302	99.83 80	99.62 147

KD-MVS_2432*1600		88.00 407	86.10 411	93.70 387	96.91 323	94.04 276	97.17 446	97.12 371	84.93 434	81.96 450	92.41 462	92.48 152	94.51 468	79.23 456	52.68 514	92.56 448

miper_refine_blended		88.00 407	86.10 411	93.70 387	96.91 323	94.04 276	97.17 446	97.12 371	84.93 434	81.96 450	92.41 462	92.48 152	94.51 468	79.23 456	52.68 514	92.56 448

tpm2		95.47 231	95.18 226	96.35 281	96.91 323	91.70 354	96.96 452	97.93 251	88.04 393	98.44 150	95.40 396	93.32 121	97.97 330	94.00 275	95.61 282	99.38 201

FMVSNet5		88.32 403	87.47 405	90.88 428	96.90 326	88.39 421	97.28 443	95.68 455	82.60 455	84.67 437	92.40 464	79.83 360	91.16 492	76.39 472	81.51 407	93.09 439

3Dnovator+	91.53 11	96.31 190	95.24 223	99.52 33	96.88 327	98.64 59	99.72 214	98.24 210	95.27 121	88.42 390	98.98 210	82.76 323	99.94 94	97.10 194	99.83 80	99.96 75

Patchmatch-test		92.65 326	91.50 337	96.10 287	96.85 328	90.49 384	91.50 499	97.19 356	82.76 454	90.23 337	95.59 385	95.02 65	98.00 329	77.41 467	96.98 236	99.82 107

MVS		96.60 170	95.56 205	99.72 14	96.85 328	99.22 21	98.31 411	98.94 44	91.57 298	90.90 330	99.61 124	86.66 254	99.96 76	97.36 183	99.88 76	99.99 26

3Dnovator	91.47 12	96.28 193	95.34 219	99.08 82	96.82 330	97.47 114	99.45 284	98.81 67	95.52 115	89.39 361	99.00 205	81.97 329	99.95 85	97.27 185	99.83 80	99.84 104

EI-MVSNet		93.73 296	93.40 287	94.74 334	96.80 331	92.69 320	99.06 339	97.67 280	88.96 370	91.39 324	99.02 199	88.75 222	97.30 360	91.07 330	87.85 355	94.22 372

CVMVSNet		94.68 259	94.94 237	93.89 381	96.80 331	86.92 435	99.06 339	98.98 41	94.45 148	94.23 294	99.02 199	85.60 273	95.31 456	90.91 336	95.39 287	99.43 194

IterMVS-LS		92.69 324	92.11 322	94.43 353	96.80 331	92.74 317	99.45 284	96.89 415	88.98 368	89.65 354	95.38 399	88.77 221	96.34 426	90.98 334	82.04 403	94.22 372
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
AstraMVS		96.57 173	96.46 155	96.91 258	96.79 334	92.50 326	99.90 117	97.38 316	96.02 99	97.79 185	99.32 154	86.36 259	98.99 214	98.26 139	96.33 255	99.23 236

IterMVS		90.91 360	90.17 362	93.12 401	96.78 335	90.42 387	98.89 365	97.05 395	89.03 365	86.49 419	95.42 395	76.59 395	95.02 458	87.22 396	84.09 388	93.93 410
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
1314		96.84 152	95.96 183	99.48 40	96.74 336	98.52 63	98.31 411	98.86 59	95.82 104	89.91 345	98.98 210	87.49 238	99.96 76	97.80 167	99.73 90	99.96 75

IterMVS-SCA-FT		90.85 363	90.16 363	92.93 406	96.72 337	89.96 396	98.89 365	96.99 400	88.95 371	86.63 416	95.67 380	76.48 397	95.00 459	87.04 399	84.04 391	93.84 417

MVS-HIRNet		86.22 420	83.19 436	95.31 317	96.71 338	90.29 388	92.12 495	97.33 325	62.85 503	86.82 413	70.37 518	69.37 439	97.49 350	75.12 475	97.99 191	98.15 302

viewdifsd2359ckpt11		94.09 282	93.63 273	95.46 310	96.68 339	88.92 410	99.62 243	97.12 371	93.07 224	95.73 263	99.22 175	77.05 385	98.88 224	96.52 222	87.69 360	98.58 289

viewmsd2359difaftdt		94.09 282	93.64 272	95.46 310	96.68 339	88.92 410	99.62 243	97.13 370	93.07 224	95.73 263	99.22 175	77.05 385	98.89 223	96.52 222	87.70 359	98.58 289

VDDNet		93.12 311	91.91 327	96.76 265	96.67 341	92.65 323	98.69 388	98.21 217	82.81 453	97.75 187	99.28 161	61.57 472	99.48 186	98.09 149	94.09 306	98.15 302

dmvs_re		93.20 308	93.15 297	93.34 394	96.54 342	83.81 453	98.71 385	98.51 131	91.39 309	92.37 316	98.56 270	78.66 372	97.83 338	93.89 279	89.74 327	98.38 296

Elysia		94.50 266	93.38 288	97.85 180	96.49 343	96.70 148	98.98 351	97.78 270	90.81 326	96.19 249	98.55 272	73.63 422	98.98 215	89.41 357	98.56 168	97.88 309

StellarMVS		94.50 266	93.38 288	97.85 180	96.49 343	96.70 148	98.98 351	97.78 270	90.81 326	96.19 249	98.55 272	73.63 422	98.98 215	89.41 357	98.56 168	97.88 309

MIMVSNet		90.30 376	88.67 391	95.17 321	96.45 345	91.64 357	92.39 494	97.15 365	85.99 420	90.50 335	93.19 455	66.95 450	94.86 464	82.01 439	93.43 314	99.01 263

CR-MVSNet		93.45 305	92.62 310	95.94 292	96.29 346	92.66 321	92.01 496	96.23 441	92.62 250	96.94 214	93.31 452	91.04 182	96.03 441	79.23 456	95.96 264	99.13 246

RPMNet		89.76 389	87.28 406	97.19 244	96.29 346	92.66 321	92.01 496	98.31 199	70.19 494	96.94 214	85.87 503	87.25 243	99.78 147	62.69 502	95.96 264	99.13 246

tt0805		91.28 353	90.18 361	94.60 340	96.26 348	87.55 428	98.39 409	98.72 78	89.00 367	89.22 367	98.47 280	62.98 467	98.96 219	90.57 342	88.00 354	97.28 328

Patchmtry		89.70 390	88.49 394	93.33 395	96.24 349	89.94 399	91.37 500	96.23 441	78.22 476	87.69 401	93.31 452	91.04 182	96.03 441	80.18 453	82.10 402	94.02 400

test_vis1_rt		86.87 417	86.05 414	89.34 447	96.12 350	78.07 483	99.87 133	83.54 517	92.03 283	78.21 473	89.51 484	45.80 495	99.91 111	96.25 228	93.11 319	90.03 480

JIA-IIPM		91.76 347	90.70 348	94.94 327	96.11 351	87.51 429	93.16 491	98.13 232	75.79 482	97.58 189	77.68 513	92.84 137	97.97 330	88.47 375	96.54 247	99.33 212

OpenMVS	90.15 15	94.77 254	93.59 277	98.33 146	96.07 352	97.48 113	99.56 262	98.57 107	90.46 342	86.51 418	98.95 219	78.57 373	99.94 94	93.86 280	99.74 89	97.57 323

PAPM		98.60 37	98.42 38	99.14 73	96.05 353	98.96 28	99.90 117	99.35 24	96.68 73	98.35 157	99.66 116	96.45 35	98.51 282	99.45 65	99.89 73	99.96 75

CLD-MVS		94.06 285	93.90 268	94.55 344	96.02 354	90.69 378	99.98 24	97.72 276	96.62 77	91.05 329	98.85 239	77.21 383	98.47 283	98.11 147	89.51 333	94.48 348
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PatchT		90.38 373	88.75 390	95.25 319	95.99 355	90.16 391	91.22 501	97.54 299	76.80 478	97.26 202	86.01 502	91.88 169	96.07 440	66.16 494	95.91 268	99.51 177

ACMH+	89.98 16	90.35 374	89.54 373	92.78 410	95.99 355	86.12 439	98.81 376	97.18 358	89.38 360	83.14 446	97.76 312	68.42 444	98.43 288	89.11 365	86.05 371	93.78 420

DeepMVS_CX				82.92 476	95.98 357	58.66 511		96.01 447	92.72 242	78.34 472	95.51 390	58.29 479	98.08 324	82.57 433	85.29 376	92.03 459

ACMP	92.05 9	92.74 322	92.42 319	93.73 383	95.91 358	88.72 414	99.81 169	97.53 301	94.13 169	87.00 412	98.23 293	74.07 418	98.47 283	96.22 229	88.86 340	93.99 405
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n		93.61 300	93.03 300	95.35 314	95.86 359	86.94 434	99.87 133	96.36 439	96.85 64	99.54 73	98.79 244	52.41 487	99.83 140	98.64 114	98.97 154	99.29 224

HQP-NCC					95.78 360		99.87 133		96.82 66	93.37 301

ACMP_Plane					95.78 360		99.87 133		96.82 66	93.37 301

HQP-MVS		94.61 261	94.50 248	94.92 328	95.78 360	91.85 342	99.87 133	97.89 256	96.82 66	93.37 301	98.65 257	80.65 351	98.39 295	97.92 159	89.60 328	94.53 344

NP-MVS					95.77 363	91.79 346					98.65 257

test_fmvsmconf0.1_n		97.74 103	97.44 107	98.64 115	95.76 364	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					95.76 364	91.72 353						80.47 355

ACMM	91.95 10	92.88 317	92.52 317	93.98 377	95.75 366	89.08 409	99.77 187	97.52 303	93.00 227	89.95 344	97.99 302	76.17 401	98.46 286	93.63 292	88.87 339	94.39 356
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GA-MVS		93.83 289	92.84 304	96.80 263	95.73 367	93.57 295	99.88 130	97.24 350	92.57 257	92.92 308	96.66 348	78.73 371	97.67 344	87.75 388	94.06 307	99.17 241

plane_prior1					95.73 367

jason		97.24 129	96.86 133	98.38 145	95.73 367	97.32 118	99.97 42	97.40 315	95.34 119	98.60 144	99.54 134	87.70 232	98.56 277	97.94 158	99.47 124	99.25 233
jason: jason.
mmtdpeth		88.52 401	87.75 403	90.85 430	95.71 370	83.47 459	98.94 359	94.85 473	88.78 376	97.19 204	89.58 483	63.29 465	98.97 217	98.54 119	62.86 492	90.10 479

HQP_MVS		94.49 268	94.36 251	94.87 329	95.71 370	91.74 349	99.84 152	97.87 258	96.38 86	93.01 306	98.59 265	80.47 355	98.37 301	97.79 170	89.55 331	94.52 346

plane_prior7					95.71 370	91.59 363

ITE_SJBPF				92.38 413	95.69 373	85.14 445		95.71 454	92.81 236	89.33 364	98.11 296	70.23 437	98.42 289	85.91 411	88.16 352	93.59 428

fmvsm_s_conf0.1_n_a		97.09 138	96.90 131	97.63 204	95.65 374	94.21 271	99.83 160	98.50 137	96.27 92	99.65 55	99.64 119	84.72 295	99.93 104	99.04 85	98.84 159	98.74 282

ACMH	89.72 17	90.64 367	89.63 370	93.66 389	95.64 375	88.64 417	98.55 396	97.45 308	89.03 365	81.62 453	97.61 313	69.75 438	98.41 291	89.37 359	87.62 361	93.92 411
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline2		96.71 164	96.49 152	97.37 235	95.63 376	95.96 185	99.74 203	98.88 55	92.94 229	91.61 322	98.97 212	97.72 7	98.62 272	94.83 257	98.08 189	97.53 325

FMVSNet1		88.50 402	86.64 409	94.08 369	95.62 377	91.97 335	98.43 404	96.95 406	83.00 451	86.08 426	94.72 426	59.09 478	96.11 436	81.82 441	84.07 389	94.17 377

LuminaMVS		96.63 168	96.21 168	97.87 179	95.58 378	96.82 142	99.12 328	97.67 280	94.47 146	97.88 180	98.31 290	87.50 237	98.71 256	98.07 151	97.29 211	98.10 305

0.3-1-1-0.015		94.22 278	93.13 299	97.49 222	95.50 379	94.17 272	100.00 1	98.22 213	88.44 386	97.14 206	97.04 333	92.73 141	98.59 273	96.45 224	72.65 463	99.70 125

0.4-1-1-0.2		94.14 279	93.02 301	97.51 217	95.45 380	94.25 268	100.00 1	98.22 213	88.53 383	96.83 220	96.95 336	92.25 160	98.57 276	96.34 225	72.65 463	99.70 125

LPG-MVS_test		92.96 314	92.71 309	93.71 385	95.43 381	88.67 415	99.75 199	97.62 287	92.81 236	90.05 340	98.49 276	75.24 408	98.40 293	95.84 236	89.12 335	94.07 396

LGP-MVS_train				93.71 385	95.43 381	88.67 415		97.62 287	92.81 236	90.05 340	98.49 276	75.24 408	98.40 293	95.84 236	89.12 335	94.07 396

tpm		93.70 298	93.41 286	94.58 342	95.36 383	87.41 430	97.01 450	96.90 414	90.85 324	96.72 225	94.14 443	90.40 196	96.84 394	90.75 340	88.54 347	99.51 177

0.4-1-1-0.1		94.07 284	92.95 302	97.42 229	95.24 384	94.00 279	100.00 1	98.22 213	88.27 390	96.81 222	96.93 337	92.27 159	98.56 277	96.21 230	72.63 465	99.70 125

D2MVS		92.76 321	92.59 315	93.27 397	95.13 385	89.54 403	99.69 229	99.38 22	92.26 276	87.59 403	94.61 432	85.05 285	97.79 339	91.59 323	88.01 353	92.47 452

VPA-MVSNet		92.70 323	91.55 336	96.16 285	95.09 386	96.20 176	98.88 367	99.00 39	91.02 321	91.82 321	95.29 406	76.05 403	97.96 332	95.62 241	81.19 409	94.30 363

LTVRE_ROB	88.28 18	90.29 377	89.05 384	94.02 372	95.08 387	90.15 392	97.19 445	97.43 310	84.91 436	83.99 442	97.06 330	74.00 419	98.28 311	84.08 422	87.71 357	93.62 427
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		87.87 409	86.51 410	91.94 419	95.05 388	85.57 443	97.65 436	94.08 485	84.40 440	81.82 452	96.85 342	62.14 470	98.33 304	80.25 452	86.37 368	91.91 461

test0.0.03 1		93.86 288	93.61 274	94.64 338	95.02 389	92.18 333	99.93 100	98.58 105	94.07 173	87.96 398	98.50 275	93.90 106	94.96 460	81.33 442	93.17 317	96.78 331

UniMVSNet (Re)		93.07 313	92.13 321	95.88 296	94.84 390	96.24 175	99.88 130	98.98 41	92.49 264	89.25 365	95.40 396	87.09 245	97.14 369	93.13 301	78.16 434	94.26 365

USDC		90.00 385	88.96 385	93.10 403	94.81 391	88.16 423	98.71 385	95.54 459	93.66 194	83.75 444	97.20 324	65.58 456	98.31 306	83.96 425	87.49 363	92.85 445

VPNet		91.81 341	90.46 352	95.85 298	94.74 392	95.54 204	98.98 351	98.59 103	92.14 278	90.77 334	97.44 317	68.73 442	97.54 349	94.89 256	77.89 436	94.46 349

FIs		94.10 281	93.43 283	96.11 286	94.70 393	96.82 142	99.58 254	98.93 48	92.54 260	89.34 363	97.31 321	87.62 234	97.10 373	94.22 274	86.58 366	94.40 355

UniMVSNet_ETH3D		90.06 384	88.58 393	94.49 348	94.67 394	88.09 424	97.81 433	97.57 295	83.91 443	88.44 385	97.41 318	57.44 480	97.62 346	91.41 325	88.59 346	97.77 314

UniMVSNet_NR-MVSNet		92.95 315	92.11 322	95.49 306	94.61 395	95.28 222	99.83 160	99.08 36	91.49 300	89.21 368	96.86 341	87.14 244	96.73 401	93.20 297	77.52 439	94.46 349

test_fmvs2		89.47 394	89.70 369	88.77 454	94.54 396	75.74 487	99.83 160	94.70 479	94.71 137	91.08 327	96.82 346	54.46 483	97.78 341	92.87 304	88.27 350	92.80 446

MonoMVSNet		94.82 249	94.43 249	95.98 290	94.54 396	90.73 377	99.03 346	97.06 392	93.16 218	93.15 305	95.47 393	88.29 225	97.57 347	97.85 164	91.33 325	99.62 147

WR-MVS		92.31 333	91.25 341	95.48 309	94.45 398	95.29 221	99.60 250	98.68 84	90.10 350	88.07 397	96.89 339	80.68 350	96.80 398	93.14 300	79.67 426	94.36 357

dtuonly		93.89 287	93.16 296	96.08 288	94.37 399	91.67 356	99.15 327	95.04 471	91.79 293	94.74 280	98.72 249	81.01 343	98.31 306	87.29 394	96.33 255	98.27 300

nrg030		93.51 302	92.53 316	96.45 276	94.36 400	97.20 124	99.81 169	97.16 362	91.60 297	89.86 347	97.46 316	86.37 258	97.68 343	95.88 235	80.31 422	94.46 349

tfpnnormal		89.29 397	87.61 404	94.34 356	94.35 401	94.13 274	98.95 358	98.94 44	83.94 441	84.47 438	95.51 390	74.84 413	97.39 352	77.05 470	80.41 420	91.48 464

FC-MVSNet-test		93.81 292	93.15 297	95.80 301	94.30 402	96.20 176	99.42 286	98.89 52	92.33 271	89.03 373	97.27 323	87.39 240	96.83 396	93.20 297	86.48 367	94.36 357

SSC-MVS3.2		89.59 392	88.66 392	92.38 413	94.29 403	86.12 439	99.49 275	97.66 283	90.28 349	88.63 381	95.18 410	64.46 461	96.88 392	85.30 415	82.66 397	94.14 387

MS-PatchMatch		90.65 366	90.30 357	91.71 424	94.22 404	85.50 444	98.24 415	97.70 277	88.67 379	86.42 421	96.37 358	67.82 447	98.03 328	83.62 427	99.62 99	91.60 462

WR-MVS_H		91.30 351	90.35 355	94.15 363	94.17 405	92.62 324	99.17 325	98.94 44	88.87 374	86.48 420	94.46 437	84.36 302	96.61 408	88.19 381	78.51 431	93.21 437

DU-MVS		92.46 330	91.45 339	95.49 306	94.05 406	95.28 222	99.81 169	98.74 76	92.25 277	89.21 368	96.64 350	81.66 334	96.73 401	93.20 297	77.52 439	94.46 349

NR-MVSNet		91.56 349	90.22 359	95.60 304	94.05 406	95.76 192	98.25 414	98.70 80	91.16 315	80.78 460	96.64 350	83.23 320	96.57 409	91.41 325	77.73 438	94.46 349

CP-MVSNet		91.23 355	90.22 359	94.26 358	93.96 408	92.39 329	99.09 332	98.57 107	88.95 371	86.42 421	96.57 353	79.19 366	96.37 424	90.29 349	78.95 428	94.02 400

XXY-MVS		91.82 340	90.46 352	95.88 296	93.91 409	95.40 211	98.87 370	97.69 279	88.63 381	87.87 399	97.08 328	74.38 417	97.89 336	91.66 322	84.07 389	94.35 360

PS-CasMVS		90.63 368	89.51 375	93.99 375	93.83 410	91.70 354	98.98 351	98.52 128	88.48 384	86.15 425	96.53 355	75.46 406	96.31 429	88.83 367	78.86 430	93.95 408

test_0402		85.58 424	83.94 430	90.50 436	93.81 411	85.04 446	98.55 396	95.20 468	76.01 480	79.72 466	95.13 411	64.15 463	96.26 431	66.04 496	86.88 365	90.21 476

XVG-ACMP-BASELINE		91.22 356	90.75 347	92.63 412	93.73 412	85.61 442	98.52 400	97.44 309	92.77 240	89.90 346	96.85 342	66.64 453	98.39 295	92.29 309	88.61 344	93.89 413

TranMVSNet+NR-MVSNet		91.68 348	90.61 351	94.87 329	93.69 413	93.98 280	99.69 229	98.65 88	91.03 320	88.44 385	96.83 345	80.05 359	96.18 434	90.26 350	76.89 447	94.45 354

TransMVSNet (Re)		87.25 415	85.28 423	93.16 400	93.56 414	91.03 369	98.54 398	94.05 487	83.69 445	81.09 457	96.16 364	75.32 407	96.40 423	76.69 471	68.41 479	92.06 458

v10		90.25 378	88.82 387	94.57 343	93.53 415	93.43 300	99.08 334	96.87 417	85.00 433	87.34 410	94.51 433	80.93 345	97.02 383	82.85 432	79.23 427	93.26 435

testgi		89.01 399	88.04 400	91.90 420	93.49 416	84.89 448	99.73 210	95.66 456	93.89 187	85.14 432	98.17 294	59.68 476	94.66 467	77.73 466	88.88 338	96.16 340

v8		90.54 370	89.17 380	94.66 337	93.43 417	93.40 303	99.20 322	96.94 410	85.76 423	87.56 404	94.51 433	81.96 330	97.19 366	84.94 418	78.25 433	93.38 433

V42		91.28 353	90.12 364	94.74 334	93.42 418	93.46 299	99.68 232	97.02 396	87.36 401	89.85 349	95.05 414	81.31 340	97.34 355	87.34 393	80.07 424	93.40 431

pm-mvs1		89.36 396	87.81 402	94.01 373	93.40 419	91.93 338	98.62 394	96.48 437	86.25 418	83.86 443	96.14 366	73.68 421	97.04 379	86.16 408	75.73 452	93.04 441

v1144		91.09 357	89.83 366	94.87 329	93.25 420	93.69 288	99.62 243	96.98 402	86.83 411	89.64 355	94.99 421	80.94 344	97.05 376	85.08 417	81.16 410	93.87 415

v1192		90.62 369	89.25 379	94.72 336	93.13 421	93.07 308	99.50 273	97.02 396	86.33 417	89.56 359	95.01 418	79.22 365	97.09 375	82.34 437	81.16 410	94.01 402

v2v482		91.30 351	90.07 365	95.01 324	93.13 421	93.79 283	99.77 187	97.02 396	88.05 392	89.25 365	95.37 400	80.73 349	97.15 368	87.28 395	80.04 425	94.09 395

OPM-MVS		93.21 307	92.80 306	94.44 351	93.12 423	90.85 376	99.77 187	97.61 290	96.19 95	91.56 323	98.65 257	75.16 412	98.47 283	93.78 287	89.39 334	93.99 405
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v144192		90.79 364	89.52 374	94.59 341	93.11 424	92.77 315	99.56 262	96.99 400	86.38 416	89.82 350	94.95 423	80.50 354	97.10 373	83.98 424	80.41 420	93.90 412

PEN-MVS		90.19 380	89.06 383	93.57 390	93.06 425	90.90 374	99.06 339	98.47 140	88.11 391	85.91 427	96.30 360	76.67 393	95.94 444	87.07 398	76.91 446	93.89 413

v1240		90.20 379	88.79 388	94.44 351	93.05 426	92.27 331	99.38 294	96.92 413	85.89 421	89.36 362	94.87 425	77.89 380	97.03 381	80.66 447	81.08 413	94.01 402

usedtu_dtu_shiyan1		92.78 319	91.73 330	95.92 294	93.03 427	96.82 142	99.83 160	97.79 266	90.58 335	90.09 338	95.04 415	84.75 291	96.72 403	88.19 381	86.23 369	94.23 369

FE-MVSNET3		92.78 319	91.73 330	95.92 294	93.03 427	96.82 142	99.83 160	97.79 266	90.58 335	90.09 338	95.04 415	84.75 291	96.72 403	88.20 380	86.23 369	94.23 369

ArgMatch-SfM		85.25 429	84.17 427	88.48 456	92.99 429	77.23 486	97.92 428	94.24 483	90.50 339	85.08 434	95.65 382	49.84 491	95.83 446	81.06 445	70.22 470	92.39 454

v148		90.70 365	89.63 370	93.92 378	92.97 430	90.97 370	99.75 199	96.89 415	87.51 398	88.27 394	95.01 418	81.67 333	97.04 379	87.40 392	77.17 444	93.75 421

v1921920		90.46 371	89.12 381	94.50 347	92.96 431	92.46 327	99.49 275	96.98 402	86.10 419	89.61 357	95.30 403	78.55 374	97.03 381	82.17 438	80.89 418	94.01 402

MVStest1		85.03 431	82.76 440	91.83 421	92.95 432	89.16 408	98.57 395	94.82 474	71.68 491	68.54 496	95.11 413	83.17 321	95.66 449	74.69 476	65.32 486	90.65 471

tt0320-xc		82.94 446	80.35 453	90.72 434	92.90 433	83.54 457	96.85 455	94.73 477	63.12 502	79.85 465	93.77 447	49.43 493	95.46 452	80.98 446	71.54 467	93.16 438

ArgMatch-Sym		85.85 422	85.07 425	88.21 458	92.84 434	77.63 485	98.42 407	94.70 479	89.91 354	84.33 439	96.72 347	51.42 490	94.89 463	82.48 434	74.80 455	92.10 456

Baseline_NR-MVSNet		90.33 375	89.51 375	92.81 409	92.84 434	89.95 397	99.77 187	93.94 488	84.69 438	89.04 372	95.66 381	81.66 334	96.52 412	90.99 333	76.98 445	91.97 460

test_method		80.79 452	79.70 455	84.08 471	92.83 436	67.06 499	99.51 271	95.42 461	54.34 513	81.07 458	93.53 449	44.48 496	92.22 489	78.90 461	77.23 443	92.94 443

pmmvs4		92.10 337	91.07 345	95.18 320	92.82 437	94.96 235	99.48 278	96.83 419	87.45 400	88.66 380	96.56 354	83.78 310	96.83 396	89.29 362	84.77 383	93.75 421

LF4IMVS		89.25 398	88.85 386	90.45 438	92.81 438	81.19 474	98.12 422	94.79 475	91.44 304	86.29 423	97.11 326	65.30 459	98.11 322	88.53 372	85.25 377	92.07 457

tt0320		83.56 445	81.15 448	90.77 432	92.77 439	83.58 456	96.83 456	95.52 460	63.26 501	81.36 455	92.54 459	53.26 485	95.77 447	80.45 448	74.38 456	92.96 442

DTE-MVSNet		89.40 395	88.24 398	92.88 407	92.66 440	89.95 397	99.10 331	98.22 213	87.29 402	85.12 433	96.22 362	76.27 400	95.30 457	83.56 428	75.74 451	93.41 430

EU-MVSNet		90.14 382	90.34 356	89.54 446	92.55 441	81.06 475	98.69 388	98.04 240	91.41 308	86.59 417	96.84 344	80.83 347	93.31 480	86.20 407	81.91 404	94.26 365

APD_test1		81.15 450	80.92 450	81.86 477	92.45 442	59.76 510	96.04 471	93.61 492	73.29 489	77.06 476	96.64 350	44.28 497	96.16 435	72.35 480	82.52 398	89.67 485

sc_t1		85.01 432	82.46 442	92.67 411	92.44 443	83.09 460	97.39 441	95.72 453	65.06 499	85.64 430	96.16 364	49.50 492	97.34 355	84.86 419	75.39 453	97.57 323

our_test_3		90.39 372	89.48 377	93.12 401	92.40 444	89.57 402	99.33 301	96.35 440	87.84 396	85.30 431	94.99 421	84.14 306	96.09 439	80.38 450	84.56 384	93.71 426

ppachtmachnet_test		89.58 393	88.35 396	93.25 399	92.40 444	90.44 386	99.33 301	96.73 426	85.49 428	85.90 428	95.77 375	81.09 342	96.00 443	76.00 474	82.49 399	93.30 434

v7n		89.65 391	88.29 397	93.72 384	92.22 446	90.56 383	99.07 338	97.10 379	85.42 430	86.73 414	94.72 426	80.06 358	97.13 370	81.14 443	78.12 435	93.49 429

dmvs_testset		83.79 441	86.07 413	76.94 484	92.14 447	48.60 524	96.75 457	90.27 504	89.48 359	78.65 470	98.55 272	79.25 364	86.65 507	66.85 492	82.69 396	95.57 342

PS-MVSNAJss		93.64 299	93.31 292	94.61 339	92.11 448	92.19 332	99.12 328	97.38 316	92.51 263	88.45 384	96.99 335	91.20 177	97.29 363	94.36 268	87.71 357	94.36 357

pmmvs5		90.17 381	89.09 382	93.40 393	92.10 449	89.77 400	99.74 203	95.58 458	85.88 422	87.24 411	95.74 376	73.41 424	96.48 416	88.54 371	83.56 393	93.95 408

N_pmnet		80.06 455	80.78 451	77.89 482	91.94 450	45.28 529	98.80 379	56.82 531	78.10 477	80.08 463	93.33 450	77.03 387	95.76 448	68.14 489	82.81 395	92.64 447

test_djsdf		92.83 318	92.29 320	94.47 349	91.90 451	92.46 327	99.55 265	97.27 343	91.17 313	89.96 343	96.07 370	81.10 341	96.89 390	94.67 263	88.91 337	94.05 399

SixPastTwentyTwo		88.73 400	88.01 401	90.88 428	91.85 452	82.24 466	98.22 419	95.18 469	88.97 369	82.26 449	96.89 339	71.75 429	96.67 406	84.00 423	82.98 394	93.72 425

dtuonlycased		86.10 421	85.82 416	86.95 463	91.84 453	79.57 481	99.27 316	94.89 472	86.79 412	79.46 467	94.46 437	66.85 451	90.93 495	80.41 449	78.44 432	90.34 473

K. test v3		88.05 406	87.24 407	90.47 437	91.82 454	82.23 467	98.96 357	97.42 312	89.05 364	76.93 478	95.60 384	68.49 443	95.42 453	85.87 412	81.01 416	93.75 421

OurMVSNet-221017-0		89.81 388	89.48 377	90.83 431	91.64 455	81.21 473	98.17 421	95.38 463	91.48 302	85.65 429	97.31 321	72.66 425	97.29 363	88.15 383	84.83 382	93.97 407

mvs_tets		91.81 341	91.08 344	94.00 374	91.63 456	90.58 382	98.67 390	97.43 310	92.43 265	87.37 409	97.05 331	71.76 428	97.32 358	94.75 260	88.68 343	94.11 394

Gipuma		66.95 477	65.00 477	72.79 492	91.52 457	67.96 496	66.16 529	95.15 470	47.89 516	58.54 507	67.99 525	29.74 506	87.54 506	50.20 516	77.83 437	62.87 524
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_fmvsmconf0.01_n		96.39 184	95.74 197	98.32 147	91.47 458	95.56 203	99.84 152	97.30 333	97.74 30	97.89 178	99.35 153	79.62 361	99.85 130	99.25 75	99.24 141	99.55 164

jajsoiax		91.92 339	91.18 342	94.15 363	91.35 459	90.95 373	99.00 349	97.42 312	92.61 251	87.38 408	97.08 328	72.46 426	97.36 353	94.53 266	88.77 341	94.13 392

MDA-MVSNet-bldmvs		84.09 439	81.52 446	91.81 422	91.32 460	88.00 426	98.67 390	95.92 449	80.22 465	55.60 510	93.32 451	68.29 445	93.60 478	73.76 477	76.61 448	93.82 419

MVP-Stereo		90.93 359	90.45 354	92.37 415	91.25 461	88.76 412	98.05 426	96.17 443	87.27 403	84.04 440	95.30 403	78.46 375	97.27 365	83.78 426	99.70 92	91.09 465
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MDA-MVSNet_test_wron		85.51 426	83.32 435	92.10 417	90.96 462	88.58 418	99.20 322	96.52 435	79.70 467	57.12 509	92.69 458	79.11 367	93.86 474	77.10 469	77.46 441	93.86 416

YYNet1		85.50 427	83.33 434	92.00 418	90.89 463	88.38 422	99.22 321	96.55 434	79.60 468	57.26 508	92.72 457	79.09 369	93.78 476	77.25 468	77.37 442	93.84 417

ALIKED-NN		54.48 488	52.67 490	59.89 510	90.79 464	45.45 527	81.25 522	55.75 535	34.99 525	44.87 521	71.98 516	25.50 514	74.36 524	21.88 534	47.04 518	59.85 526

anonymousdsp		91.79 346	90.92 346	94.41 354	90.76 465	92.93 314	98.93 361	97.17 360	89.08 363	87.46 407	95.30 403	78.43 376	96.92 387	92.38 308	88.73 342	93.39 432

lessismore_v0				90.53 435	90.58 466	80.90 476		95.80 450		77.01 477	95.84 373	66.15 455	96.95 385	83.03 431	75.05 454	93.74 424

EG-PatchMatch MVS		85.35 428	83.81 432	89.99 444	90.39 467	81.89 469	98.21 420	96.09 445	81.78 458	74.73 484	93.72 448	51.56 489	97.12 372	79.16 459	88.61 344	90.96 468

EGC-MVSNET		69.38 468	63.76 480	86.26 467	90.32 468	81.66 472	96.24 467	93.85 489	0.99 551	3.22 552	92.33 469	52.44 486	92.92 484	59.53 509	84.90 381	84.21 505

CMPMVS	61.59 21	84.75 435	85.14 424	83.57 472	90.32 468	62.54 504	96.98 451	97.59 294	74.33 487	69.95 493	96.66 348	64.17 462	98.32 305	87.88 387	88.41 349	89.84 482
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ALIKED-MNN		52.51 492	50.15 497	59.60 512	90.05 470	44.33 531	81.60 520	54.93 537	32.36 528	40.96 529	68.77 522	20.90 525	75.30 522	20.00 535	41.78 523	59.18 527

new_pmnet		84.49 438	82.92 438	89.21 448	90.03 471	82.60 463	96.89 454	95.62 457	80.59 463	75.77 483	89.17 485	65.04 460	94.79 465	72.12 481	81.02 415	90.23 475

pmmvs6		85.69 423	83.84 431	91.26 427	90.00 472	84.41 451	97.82 432	96.15 444	75.86 481	81.29 456	95.39 398	61.21 473	96.87 393	83.52 429	73.29 459	92.50 451

ttmdpeth		88.23 405	87.06 408	91.75 423	89.91 473	87.35 431	98.92 364	95.73 452	87.92 394	84.02 441	96.31 359	68.23 446	96.84 394	86.33 406	76.12 449	91.06 466

DSMNet-mixed		88.28 404	88.24 398	88.42 457	89.64 474	75.38 490	98.06 425	89.86 505	85.59 427	88.20 396	92.14 471	76.15 402	91.95 490	78.46 463	96.05 261	97.92 308

DenseAffine		75.91 461	73.39 465	83.47 473	89.52 475	71.86 493	93.39 490	89.29 510	71.44 492	66.83 497	90.32 480	30.65 503	89.67 499	68.20 488	60.88 501	88.88 493

UnsupCasMVSNet_eth		85.52 425	83.99 428	90.10 442	89.36 476	83.51 458	96.65 458	97.99 244	89.14 362	75.89 482	93.83 445	63.25 466	93.92 472	81.92 440	67.90 482	92.88 444

Anonymous20231206		86.32 419	85.42 422	89.02 450	89.11 477	80.53 479	99.05 343	95.28 464	85.43 429	82.82 447	93.92 444	74.40 416	93.44 479	66.99 491	81.83 405	93.08 440

ALIKED-LG		54.29 489	52.28 491	60.32 506	88.90 478	45.51 526	81.66 519	56.33 532	38.60 518	42.62 527	70.81 517	25.00 516	75.20 523	19.87 536	46.76 520	60.24 525

Anonymous20240521		85.15 430	83.81 432	89.16 449	88.32 479	82.69 462	98.80 379	95.74 451	79.72 466	81.53 454	90.99 474	65.38 458	94.16 470	72.69 479	81.11 412	90.63 472

OpenMVS_ROB	79.82 20	83.77 442	81.68 445	90.03 443	88.30 480	82.82 461	98.46 401	95.22 467	73.92 488	76.00 481	91.29 473	55.00 482	96.94 386	68.40 487	88.51 348	90.34 473

test20.03		84.72 436	83.99 428	86.91 464	88.19 481	80.62 478	98.88 367	95.94 448	88.36 387	78.87 468	94.62 431	68.75 441	89.11 501	66.52 493	75.82 450	91.00 467

RoMa-SfM		74.91 464	72.77 466	81.35 478	88.00 482	67.35 498	93.55 487	86.23 515	68.27 497	66.79 498	92.92 456	30.40 504	87.68 503	66.14 495	62.62 493	89.02 491

gbinet_0.2-2-1-0.02		87.63 414	85.51 421	93.99 375	87.22 483	91.56 364	99.81 169	97.36 320	79.54 469	88.60 382	93.29 454	73.76 420	96.34 426	89.27 363	60.78 502	94.06 398

blend_shiyan4		90.13 383	88.79 388	94.17 360	87.12 484	91.83 344	99.75 199	97.08 383	79.27 474	88.69 378	92.53 460	92.25 160	96.50 413	89.35 360	73.04 461	94.18 376

KD-MVS_self_test		83.59 443	82.06 443	88.20 459	86.93 485	80.70 477	97.21 444	96.38 438	82.87 452	82.49 448	88.97 486	67.63 448	92.32 487	73.75 478	62.30 495	91.58 463

DKM		72.18 466	69.80 469	79.34 481	86.79 486	65.15 500	92.70 492	84.00 516	67.67 498	61.97 502	89.63 482	23.69 520	85.17 509	67.39 490	54.35 512	87.70 497

MIMVSNet1		82.58 447	80.51 452	88.78 452	86.68 487	84.20 452	96.65 458	95.41 462	78.75 475	78.59 471	92.44 461	51.88 488	89.76 498	65.26 497	78.95 428	92.38 455

wanda-best-256-512		87.82 410	85.71 417	94.15 363	86.66 488	91.88 340	99.76 193	97.08 383	79.46 470	88.37 391	92.36 465	78.01 377	96.43 419	88.39 376	61.26 497	94.14 387

FE-blended-shiyan7		87.82 410	85.71 417	94.15 363	86.66 488	91.88 340	99.76 193	97.08 383	79.46 470	88.37 391	92.36 465	78.01 377	96.43 419	88.39 376	61.26 497	94.14 387

usedtu_blend_shiyan5		86.75 418	84.29 426	94.16 361	86.66 488	91.83 344	97.42 438	95.23 466	69.94 495	88.37 391	92.36 465	78.01 377	96.50 413	89.35 360	61.26 497	94.14 387

SP-NN		55.28 487	53.59 489	60.34 505	86.63 491	39.01 536	86.70 512	56.31 533	31.08 530	43.77 524	68.45 523	23.39 521	60.24 529	29.19 529	56.76 509	81.77 511

LoFTR		74.41 465	70.88 468	84.99 470	86.56 492	67.85 497	93.74 483	89.63 507	69.46 496	54.95 511	87.39 497	30.76 502	96.92 387	61.37 504	64.06 489	90.19 477

blended_shiyan8		87.82 410	85.71 417	94.16 361	86.54 493	91.79 346	99.72 214	97.08 383	79.32 472	88.44 385	92.35 468	77.88 381	96.56 410	88.53 372	61.51 496	94.15 383

blended_shiyan6		87.74 413	85.62 420	94.09 368	86.53 494	91.73 352	99.72 214	97.08 383	79.32 472	88.22 395	92.31 470	77.82 382	96.43 419	88.31 378	61.26 497	94.13 392

CL-MVSNet_self_test		84.50 437	83.15 437	88.53 455	86.00 495	81.79 470	98.82 375	97.35 321	85.12 432	83.62 445	90.91 476	76.66 394	91.40 491	69.53 485	60.36 503	92.40 453

MatchFormer		70.84 467	66.72 474	83.19 475	85.99 496	64.61 501	93.58 486	88.62 511	59.32 508	50.64 514	82.31 510	28.00 509	96.79 399	52.52 515	59.50 505	88.18 494

UnsupCasMVSNet_bld		79.97 457	77.03 463	88.78 452	85.62 497	81.98 468	93.66 484	97.35 321	75.51 484	70.79 492	83.05 506	48.70 494	94.91 462	78.31 464	60.29 504	89.46 488

mvs5depth		84.87 433	82.90 439	90.77 432	85.59 498	84.84 449	91.10 502	93.29 494	83.14 449	85.07 435	94.33 440	62.17 469	97.32 358	78.83 462	72.59 466	90.14 478

SP-LightGlue		55.29 485	53.65 488	60.20 507	85.58 499	39.12 535	86.36 515	57.52 530	32.34 529	44.34 523	67.75 526	24.36 518	59.32 532	29.62 527	54.98 510	82.17 509

SP-SuperGlue		55.29 485	53.71 487	60.00 509	85.11 500	38.86 537	86.96 511	57.95 529	32.77 527	44.54 522	68.00 524	23.90 519	59.51 531	29.61 528	54.59 511	81.63 512

SP-MNN		53.97 490	52.04 494	59.73 511	84.72 501	38.63 538	86.51 513	55.94 534	29.25 531	40.20 530	67.48 527	22.18 523	59.59 530	27.79 530	54.33 513	80.98 513

Patchmatch-RL test		86.90 416	85.98 415	89.67 445	84.45 502	75.59 488	89.71 507	92.43 496	86.89 410	77.83 475	90.94 475	94.22 95	93.63 477	87.75 388	69.61 473	99.79 112

DKM-HiRes		68.91 470	66.34 476	76.62 486	84.17 503	60.69 507	90.78 506	78.55 520	62.17 505	58.82 506	87.54 494	20.94 524	82.56 513	63.05 501	51.00 516	86.61 501

MASt3R-SfM		78.94 458	79.57 456	77.07 483	84.15 504	50.74 520	91.56 498	92.34 497	83.22 448	80.84 459	94.16 442	36.67 500	92.30 488	79.45 455	73.71 458	88.16 495

pmmvs-eth3d		84.03 440	81.97 444	90.20 440	84.15 504	87.09 433	98.10 424	94.73 477	83.05 450	74.10 488	87.77 493	65.56 457	94.01 471	81.08 444	69.24 475	89.49 487

test_fmvs3		79.99 456	80.17 454	79.45 480	84.02 506	62.83 502	99.05 343	93.49 493	88.29 389	80.06 464	86.65 500	28.09 508	88.00 502	88.63 368	73.27 460	87.54 499

PM-MVS		80.47 453	78.88 458	85.26 468	83.79 507	72.22 492	95.89 474	91.08 502	85.71 426	76.56 480	88.30 489	36.64 501	93.90 473	82.39 436	69.57 474	89.66 486

RoMa-HiRes		69.18 469	67.02 471	75.65 488	83.52 508	60.31 509	90.80 505	76.82 522	62.46 504	62.85 500	90.44 479	24.75 517	83.07 511	60.58 506	50.97 517	83.58 506

new-patchmatchnet		81.19 449	79.34 457	86.76 465	82.86 509	80.36 480	97.92 428	95.27 465	82.09 457	72.02 490	86.87 499	62.81 468	90.74 496	71.10 482	63.08 491	89.19 490

FE-MVSNET2		83.57 444	81.36 447	90.20 440	82.83 510	87.59 427	98.28 413	96.04 446	85.33 431	74.13 487	87.45 495	59.16 477	93.26 481	79.12 460	69.91 471	89.77 483

FE-MVSNET		81.05 451	78.81 459	87.79 461	81.98 511	83.70 454	98.23 417	91.78 501	81.27 460	74.29 486	87.44 496	60.92 475	90.67 497	64.92 498	68.43 478	89.01 492

mvsany_test3		82.12 448	81.14 449	85.06 469	81.87 512	70.41 494	97.09 448	92.14 498	91.27 311	77.84 474	88.73 487	39.31 498	95.49 450	90.75 340	71.24 468	89.29 489

WB-MVS		76.28 460	77.28 462	73.29 491	81.18 513	54.68 515	97.87 431	94.19 484	81.30 459	69.43 494	90.70 477	77.02 388	82.06 514	35.71 523	68.11 481	83.13 507

test_f		78.40 459	77.59 461	80.81 479	80.82 514	62.48 505	96.96 452	93.08 495	83.44 446	74.57 485	84.57 505	27.95 510	92.63 485	84.15 421	72.79 462	87.32 500

SSC-MVS		75.42 463	76.40 464	72.49 496	80.68 515	53.62 516	97.42 438	94.06 486	80.42 464	68.75 495	90.14 481	76.54 396	81.66 515	33.25 524	66.34 485	82.19 508

pmmvs3		80.27 454	77.77 460	87.76 462	80.32 516	82.43 465	98.23 417	91.97 499	72.74 490	78.75 469	87.97 492	57.30 481	90.99 494	70.31 483	62.37 494	89.87 481

testf1		68.38 473	66.92 472	72.78 493	78.80 517	50.36 521	90.95 503	87.35 513	55.47 511	58.95 504	88.14 490	20.64 527	87.60 504	57.28 510	64.69 487	80.39 515

APD_test2		68.38 473	66.92 472	72.78 493	78.80 517	50.36 521	90.95 503	87.35 513	55.47 511	58.95 504	88.14 490	20.64 527	87.60 504	57.28 510	64.69 487	80.39 515

ambc				83.23 474	77.17 519	62.61 503	87.38 509	94.55 482		76.72 479	86.65 500	30.16 505	96.36 425	84.85 420	69.86 472	90.73 470

test_vis3_rt		68.82 471	66.69 475	75.21 490	76.24 520	60.41 508	96.44 462	68.71 525	75.13 485	50.54 515	69.52 521	16.42 533	96.32 428	80.27 451	66.92 484	68.89 521

PDCNetPlus		59.83 481	57.26 484	67.55 501	76.18 521	56.71 513	87.01 510	45.27 540	59.54 507	48.80 517	83.01 507	26.63 512	76.54 521	62.12 503	26.78 532	69.40 520

usedtu_dtu_shiyan2		75.87 462	72.37 467	86.39 466	76.18 521	75.49 489	96.53 460	93.82 490	64.74 500	72.53 489	88.48 488	37.67 499	91.12 493	64.13 499	57.22 507	92.56 448

TDRefinement		84.76 434	82.56 441	91.38 426	74.58 523	84.80 450	97.36 442	94.56 481	84.73 437	80.21 462	96.12 369	63.56 464	98.39 295	87.92 386	63.97 490	90.95 469

PMatch-SfM		62.12 480	58.57 483	72.76 495	74.34 524	52.97 518	84.95 516	65.57 526	56.89 510	46.61 519	85.70 504	9.51 543	80.54 517	60.53 507	43.03 522	84.77 502

SIFT-NN		35.94 501	36.54 504	34.16 517	73.93 525	29.52 540	62.74 530	37.28 541	19.65 535	27.91 537	49.19 536	11.66 536	46.35 536	9.19 537	37.30 524	26.61 534

ELoFTR		64.32 479	60.56 482	75.60 489	73.46 526	53.20 517	86.50 514	80.09 519	60.74 506	45.95 520	82.48 509	16.05 534	89.20 500	56.48 514	43.34 521	84.38 504

E-PMN		52.30 493	52.18 493	52.67 513	71.51 527	45.40 528	93.62 485	76.60 523	36.01 522	43.50 525	64.13 530	27.11 511	67.31 527	31.06 525	26.06 533	45.30 533

EMVS		51.44 495	51.22 496	52.11 514	70.71 528	44.97 530	94.04 480	75.66 524	35.34 524	42.40 528	61.56 534	28.93 507	65.87 528	27.64 531	24.73 534	45.49 531

PMMVS2		67.15 476	64.15 479	76.14 487	70.56 529	62.07 506	93.89 481	87.52 512	58.09 509	60.02 503	78.32 512	22.38 522	84.54 510	59.56 508	47.03 519	81.80 510

PMatch-Up-SfM		57.92 482	53.93 486	69.90 498	69.97 530	46.69 525	81.36 521	55.29 536	51.90 514	43.17 526	82.54 508	7.86 548	78.44 520	57.13 512	36.17 526	84.58 503

SIFT-MNN		34.10 502	34.41 505	33.17 519	68.99 531	28.51 541	60.22 532	36.81 542	19.08 538	24.04 539	47.28 539	10.06 540	45.04 537	8.72 538	34.47 527	25.97 537

SIFT-NCM-Cal		31.73 504	31.67 507	31.91 522	67.18 532	27.55 547	58.36 534	33.09 546	18.38 541	14.93 546	45.16 545	8.60 544	43.82 539	7.62 547	31.68 530	24.36 540

SIFT-NN-NCMNet		33.88 503	34.14 506	33.10 520	66.88 533	28.42 542	60.42 531	36.72 543	19.15 536	24.06 538	47.14 540	10.24 538	44.77 538	8.72 538	33.94 529	26.10 536

FPMVS		68.72 472	68.72 470	68.71 499	65.95 534	44.27 532	95.97 473	94.74 476	51.13 515	53.26 512	90.50 478	25.11 515	83.00 512	60.80 505	80.97 417	78.87 517

SP-DiffGlue		56.84 483	55.72 485	60.19 508	65.70 535	40.86 533	81.89 518	60.28 528	34.62 526	50.39 516	76.88 514	26.61 513	58.81 533	48.21 517	56.94 508	80.90 514

wuyk23d		20.37 516	20.84 519	18.99 533	65.34 536	27.73 545	50.43 542	7.67 557	9.50 550	8.01 551	6.34 551	6.13 553	26.24 550	23.40 533	10.69 548	2.99 548

SIFT-ConvMatch		30.09 507	29.76 511	31.09 524	65.16 537	27.56 546	54.13 538	31.17 547	18.55 540	17.88 542	45.89 542	8.40 545	42.26 543	8.11 543	18.51 539	23.46 542

SIFT-CM-Cal		28.34 510	27.90 514	29.63 526	63.75 538	25.98 551	50.66 541	26.18 551	18.12 544	16.88 544	44.64 546	8.08 547	39.70 544	7.65 546	15.19 544	23.22 543

LCM-MVSNet		67.77 475	64.73 478	76.87 485	62.95 539	56.25 514	89.37 508	93.74 491	44.53 517	61.99 501	80.74 511	20.42 529	86.53 508	69.37 486	59.50 505	87.84 496

SIFT-NN-CMatch		31.71 505	31.56 508	32.16 521	62.58 540	27.53 548	56.45 535	33.28 545	19.00 539	23.65 540	47.34 537	10.05 541	42.72 541	8.71 540	22.96 537	26.24 535

SIFT-UM-Cal		27.47 511	27.02 515	28.83 529	62.12 541	24.58 553	53.60 539	23.46 552	18.14 543	12.85 548	45.56 543	7.49 549	39.45 545	7.68 545	12.30 545	22.45 544

SIFT-UMatch		29.40 509	28.87 513	30.98 525	62.08 542	26.57 550	56.09 536	29.45 549	18.31 542	15.86 545	46.00 541	8.23 546	42.54 542	7.99 544	15.81 542	23.85 541

GLUNet-SfM		51.10 496	46.61 499	64.56 502	61.54 543	39.88 534	79.38 525	65.13 527	36.09 521	33.36 534	69.94 519	14.50 535	78.76 518	42.46 521	17.10 541	75.02 519

SIFT-NN-UMatch		31.23 506	31.05 510	31.79 523	60.08 544	27.23 549	58.49 533	33.65 544	19.14 537	17.30 543	47.31 538	10.12 539	42.88 540	8.67 541	24.67 535	25.27 538

XFeat-NN		42.54 497	42.87 501	41.54 516	59.73 545	27.86 544	69.53 527	45.34 539	24.36 532	37.16 531	64.79 528	20.84 526	51.40 535	30.01 526	34.12 528	45.36 532

MVE	53.74 22	51.54 494	47.86 498	62.60 503	59.56 546	50.93 519	79.41 524	77.69 521	35.69 523	36.27 532	61.76 533	5.79 554	69.63 525	37.97 522	36.61 525	67.24 522
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
SIFT-NN-PointCN		29.63 508	29.72 512	29.36 527	57.55 547	23.55 554	56.07 537	30.57 548	17.99 545	20.99 541	45.21 544	9.94 542	39.33 546	8.40 542	20.81 538	25.20 539

SIFT-PointCN		25.49 512	25.71 516	24.84 530	56.17 548	18.65 555	51.37 540	26.53 550	16.31 546	12.78 549	39.87 549	6.41 552	34.09 548	6.51 549	15.42 543	21.77 545

SIFT-PCN-Cal		24.67 513	24.81 517	24.24 531	56.13 549	18.04 556	49.05 543	23.39 553	16.07 547	12.99 547	40.17 548	6.97 551	34.68 547	6.71 548	11.81 546	19.99 546

XFeat-MNN		41.51 498	41.24 502	42.32 515	55.40 550	28.19 543	69.39 528	46.53 538	23.57 533	34.47 533	63.21 532	20.04 530	52.41 534	27.43 532	31.08 531	46.37 530

SIFT-NCMNet		21.21 515	21.22 518	21.17 532	52.99 551	16.41 557	42.12 544	14.05 555	15.89 548	10.70 550	35.85 550	5.14 555	29.82 549	5.80 550	8.44 549	17.28 547

ANet_high		56.10 484	52.24 492	67.66 500	49.27 552	56.82 512	83.94 517	82.02 518	70.47 493	33.28 535	64.54 529	17.23 532	69.16 526	45.59 519	23.85 536	77.02 518

tmp_tt		65.23 478	62.94 481	72.13 497	44.90 553	50.03 523	81.05 523	89.42 509	38.45 519	48.51 518	99.90 23	54.09 484	78.70 519	91.84 321	18.26 540	87.64 498

PMVS	49.05 23	53.75 491	51.34 495	60.97 504	40.80 554	34.68 539	74.82 526	89.62 508	37.55 520	28.67 536	72.12 515	7.09 550	81.63 516	43.17 520	68.21 480	66.59 523
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test123		37.68 500	39.14 503	33.31 518	19.94 555	24.83 552	98.36 410	9.75 556	15.53 549	51.31 513	87.14 498	19.62 531	17.74 551	47.10 518	3.47 550	57.36 528

testmvs		40.60 499	44.45 500	29.05 528	19.49 556	14.11 558	99.68 232	18.47 554	20.74 534	64.59 499	98.48 279	10.95 537	17.09 552	56.66 513	11.01 547	55.94 529

mmdepth		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 553	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

monomultidepth		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 553	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

test_blank		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.02 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

eth-test2					0.00 557

eth-test					0.00 557

uanet_test		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 553	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

DCPMVS		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 553	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

cdsmvs_eth3d_5k		23.43 514	31.24 509	0.00 534	0.00 557	0.00 559	0.00 545	98.09 234	0.00 552	0.00 553	99.67 114	83.37 315	0.00 553	0.00 551	0.00 551	0.00 549

pcd_1.5k_mvsjas		7.60 518	10.13 521	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 553	91.20 177	0.00 553	0.00 551	0.00 551	0.00 549

sosnet-low-res		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 553	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

sosnet		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 553	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

uncertanet		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 553	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

Regformer		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 553	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

ab-mvs-re		8.28 517	11.04 520	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	99.40 147	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

uanet		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 553	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

WAC-MVS						90.97 370								86.10 410

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							95.78 475				59.23 535	93.20 128	97.74 342	91.06 331

test_post											63.35 531	94.43 82	98.13 321

patchmatchnet-post											91.70 472	95.12 60	97.95 333

MTMP							99.87 133	96.49 436

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							99.46 283		94.21 166	99.85 20			99.95 85	96.96 201

新几何2							99.40 288

无先验							99.49 275	98.71 79	93.46 202				100.00 1	94.36 268		99.99 26

原ACMM2							99.90 117

testdata2													99.99 39	90.54 344

segment_acmp												96.68 31

testdata1							99.28 314		96.35 91

plane_prior5								97.87 258					98.37 301	97.79 170	89.55 331	94.52 346

plane_prior4											98.59 265

plane_prior3						91.64 357			96.63 75	93.01 306

plane_prior2							99.84 152		96.38 86

plane_prior						91.74 349	99.86 144		96.76 70						89.59 330

n2								0.00 558

nn								0.00 558

door-mid								89.69 506

test11								98.44 148

door								90.31 503

HQP5-MVS						91.85 342

BP-MVS														97.92 159

HQP4-MVS										93.37 301			98.39 295			94.53 344

HQP3-MVS								97.89 256							89.60 328

HQP2-MVS												80.65 351

MDTV_nov1_ep13_2view						96.26 170	96.11 469		91.89 286	98.06 170		94.40 84		94.30 271		99.67 133

ACMMP++_ref															87.04 364

ACMMP++															88.23 351

Test By Simon												92.82 139

High-resolution multi-view benchmark