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		97.23 125	96.80 134	98.51 127	99.99 1	95.60 193	99.09 288	98.84 62	93.32 195	96.74 204	99.72 88	86.04 253	100.00 1	98.01 146	99.43 123	99.94 81

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 19	98.69 76	98.20 9	99.93 2	99.98 2	96.82 24	100.00 1	99.75 37	100.00 1	99.99 23

MCST-MVS		99.32 3	99.14 4	99.86 5	99.97 3	99.59 5	99.97 37	98.64 85	98.47 3	99.13 101	99.92 13	96.38 34	100.00 1	99.74 39	100.00 1	100.00 1

mPP-MVS		98.39 53	98.20 51	98.97 87	99.97 3	96.92 132	99.95 66	98.38 178	95.04 117	98.61 132	99.80 54	93.39 114	100.00 1	98.64 109	100.00 1	99.98 52

CPTT-MVS		97.64 105	97.32 109	98.58 116	99.97 3	95.77 182	99.96 47	98.35 184	89.90 320	98.36 147	99.79 58	91.18 173	99.99 36	98.37 125	99.99 21	99.99 23

DP-MVS Recon		98.41 50	98.02 65	99.56 25	99.97 3	98.70 48	99.92 93	98.44 142	92.06 253	98.40 146	99.84 44	95.68 44	100.00 1	98.19 135	99.71 88	99.97 62

PAPR		98.52 40	98.16 55	99.58 24	99.97 3	98.77 42	99.95 66	98.43 150	95.35 111	98.03 161	99.75 75	94.03 99	99.98 47	98.11 140	99.83 77	99.99 23

HFP-MVS		98.56 36	98.37 40	99.14 67	99.96 8	97.43 108	99.95 66	98.61 93	94.77 127	99.31 90	99.85 33	94.22 92	100.00 1	98.70 104	99.98 32	99.98 52

region2R		98.54 38	98.37 40	99.05 77	99.96 8	97.18 118	99.96 47	98.55 113	94.87 124	99.45 77	99.85 33	94.07 98	100.00 1	98.67 106	100.00 1	99.98 52

ACMMPR		98.50 41	98.32 44	99.05 77	99.96 8	97.18 118	99.95 66	98.60 95	94.77 127	99.31 90	99.84 44	93.73 108	100.00 1	98.70 104	99.98 32	99.98 52

NCCC		99.37 2	99.25 2	99.71 15	99.96 8	99.15 22	99.97 37	98.62 92	98.02 20	99.90 5	99.95 3	97.33 17	100.00 1	99.54 53	100.00 1	100.00 1

CP-MVS		98.45 45	98.32 44	98.87 92	99.96 8	96.62 145	99.97 37	98.39 174	94.43 144	98.90 113	99.87 27	94.30 89	100.00 1	99.04 79	99.99 21	99.99 23

test_one_0601					99.94 13	99.30 12		98.41 167	96.63 71	99.75 38	99.93 11	97.49 10

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 66	98.43 150					100.00 1	99.99 5	100.00 1	100.00 1

XVS		98.70 29	98.55 28	99.15 65	99.94 13	97.50 104	99.94 83	98.42 162	96.22 88	99.41 82	99.78 62	94.34 86	99.96 71	98.92 89	99.95 50	99.99 23

X-MVStestdata		93.83 257	92.06 292	99.15 65	99.94 13	97.50 104	99.94 83	98.42 162	96.22 88	99.41 82	41.37 464	94.34 86	99.96 71	98.92 89	99.95 50	99.99 23

test_prior				99.43 36	99.94 13	98.49 61		98.65 82					99.80 136			99.99 23

MSLP-MVS++		99.13 8	99.01 11	99.49 32	99.94 13	98.46 62	99.98 19	98.86 56	97.10 51	99.80 24	99.94 4	95.92 40	100.00 1	99.51 54	100.00 1	100.00 1

APDe-MVS		99.06 11	98.91 14	99.51 29	99.94 13	98.76 45	99.91 101	98.39 174	97.20 49	99.46 76	99.85 33	95.53 48	99.79 138	99.86 23	100.00 1	99.99 23
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MP-MVS		98.23 67	97.97 69	99.03 79	99.94 13	97.17 121	99.95 66	98.39 174	94.70 131	98.26 153	99.81 53	91.84 164	100.00 1	98.85 95	99.97 42	99.93 82
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CDPH-MVS		98.65 32	98.36 42	99.49 32	99.94 13	98.73 46	99.87 123	98.33 189	93.97 169	99.76 37	99.87 27	94.99 64	99.75 147	98.55 113	100.00 1	99.98 52

PAPM_NR		98.12 71	97.93 75	98.70 103	99.94 13	96.13 171	99.82 152	98.43 150	94.56 135	97.52 178	99.70 94	94.40 81	99.98 47	97.00 181	99.98 32	99.99 23

MG-MVS		98.91 19	98.65 24	99.68 16	99.94 13	99.07 24	99.64 209	99.44 19	97.33 42	99.00 109	99.72 88	94.03 99	99.98 47	98.73 103	100.00 1	100.00 1

SED-MVS		99.28 5	99.11 7	99.77 8	99.93 24	99.30 12	99.96 47	98.43 150	97.27 45	99.80 24	99.94 4	96.71 27	100.00 1	100.00 1	100.00 1	100.00 1

IU-MVS					99.93 24	99.31 10		98.41 167	97.71 29	99.84 19				100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 24	99.30 12		98.43 150	97.26 47	99.80 24	99.88 24	96.71 27	100.00 1

DVP-MVS		99.30 4	99.16 3	99.73 12	99.93 24	99.29 15	99.95 66	98.32 191	97.28 43	99.83 20	99.91 14	97.22 19	100.00 1	99.99 5	100.00 1	99.89 91
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test0726					99.93 24	99.29 15	99.96 47	98.42 162	97.28 43	99.86 13	99.94 4	97.22 19

MSP-MVS		99.09 9	99.12 5	98.98 86	99.93 24	97.24 115	99.95 66	98.42 162	97.50 36	99.52 72	99.88 24	97.43 16	99.71 153	99.50 56	99.98 32	100.00 1
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
agg_prior					99.93 24	98.77 42		98.43 150		99.63 55			99.85 123

FOURS1					99.92 31	97.66 98	99.95 66	98.36 182	95.58 105	99.52 72

ZD-MVS					99.92 31	98.57 56		98.52 122	92.34 241	99.31 90	99.83 46	95.06 59	99.80 136	99.70 44	99.97 42

GST-MVS		98.27 60	97.97 69	99.17 60	99.92 31	97.57 100	99.93 90	98.39 174	94.04 167	98.80 118	99.74 82	92.98 130	100.00 1	98.16 137	99.76 85	99.93 82

TEST9					99.92 31	98.92 29	99.96 47	98.43 150	93.90 175	99.71 45	99.86 29	95.88 41	99.85 123

train_agg		98.88 20	98.65 24	99.59 23	99.92 31	98.92 29	99.96 47	98.43 150	94.35 149	99.71 45	99.86 29	95.94 38	99.85 123	99.69 45	99.98 32	99.99 23

test_8					99.92 31	98.88 32	99.96 47	98.43 150	94.35 149	99.69 47	99.85 33	95.94 38	99.85 123

PGM-MVS		98.34 55	98.13 57	98.99 84	99.92 31	97.00 128	99.75 174	99.50 17	93.90 175	99.37 87	99.76 67	93.24 123	100.00 1	97.75 165	99.96 46	99.98 52

ACMMP		97.74 98	97.44 102	98.66 107	99.92 31	96.13 171	99.18 281	99.45 18	94.84 125	96.41 215	99.71 91	91.40 167	99.99 36	97.99 148	98.03 183	99.87 94
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
DVP-MVS++		99.26 6	99.09 9	99.77 8	99.91 39	99.31 10	99.95 66	98.43 150	96.48 76	99.80 24	99.93 11	97.44 14	100.00 1	99.92 13	99.98 32	100.00 1

MSC_two_6792asdad				99.93 2	99.91 39	99.80 2		98.41 167					100.00 1	99.96 9	100.00 1	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 167					100.00 1	99.96 9	100.00 1	100.00 1

HPM-MVS++		99.07 10	98.88 16	99.63 17	99.90 42	99.02 25	99.95 66	98.56 107	97.56 35	99.44 78	99.85 33	95.38 52	100.00 1	99.31 66	99.99 21	99.87 94

APD-MVS		98.62 33	98.35 43	99.41 39	99.90 42	98.51 59	99.87 123	98.36 182	94.08 162	99.74 41	99.73 85	94.08 97	99.74 149	99.42 62	99.99 21	99.99 23
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DeepC-MVS_fast	96.59 1	98.81 23	98.54 29	99.62 20	99.90 42	98.85 35	99.24 276	98.47 134	98.14 14	99.08 104	99.91 14	93.09 127	100.00 1	99.04 79	99.99 21	100.00 1
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
OPU-MVS				99.93 2	99.89 45	99.80 2	99.96 47				99.80 54	97.44 14	100.00 1	100.00 1	99.98 32	100.00 1

DPE-MVS		99.26 6	99.10 8	99.74 11	99.89 45	99.24 19	99.87 123	98.44 142	97.48 37	99.64 54	99.94 4	96.68 29	99.99 36	99.99 5	100.00 1	99.99 23
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_part2					99.89 45	99.25 18				99.49 75

CSCG		97.10 131	97.04 121	97.27 217	99.89 45	91.92 305	99.90 107	99.07 37	88.67 344	95.26 244	99.82 49	93.17 126	99.98 47	98.15 138	99.47 118	99.90 90

ZNCC-MVS		98.31 57	98.03 64	99.17 60	99.88 49	97.59 99	99.94 83	98.44 142	94.31 152	98.50 139	99.82 49	93.06 128	99.99 36	98.30 129	99.99 21	99.93 82

SR-MVS		98.46 44	98.30 47	98.93 90	99.88 49	97.04 127	99.84 142	98.35 184	94.92 121	99.32 89	99.80 54	93.35 116	99.78 140	99.30 67	99.95 50	99.96 70

9.14			98.38 38		99.87 51		99.91 101	98.33 189	93.22 198	99.78 35	99.89 22	94.57 77	99.85 123	99.84 25	99.97 42

SMA-MVS		98.76 26	98.48 32	99.62 20	99.87 51	98.87 33	99.86 134	98.38 178	93.19 199	99.77 36	99.94 4	95.54 46	100.00 1	99.74 39	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 80	97.85 80	98.04 159	99.86 53	95.39 203	99.61 214	97.78 258	96.52 74	98.61 132	99.31 150	92.73 138	99.67 161	96.77 191	99.48 115	99.06 229

lecture		98.67 30	98.46 33	99.28 48	99.86 53	97.88 87	99.97 37	99.25 30	96.07 92	99.79 33	99.70 94	92.53 146	99.98 47	99.51 54	99.48 115	99.97 62

PHI-MVS		98.41 50	98.21 50	99.03 79	99.86 53	97.10 125	99.98 19	98.80 68	90.78 300	99.62 58	99.78 62	95.30 53	100.00 1	99.80 28	99.93 61	99.99 23

MTAPA		98.29 59	97.96 72	99.30 47	99.85 56	97.93 85	99.39 254	98.28 198	95.76 99	97.18 191	99.88 24	92.74 137	100.00 1	98.67 106	99.88 73	99.99 23

LS3D		95.84 192	95.11 204	98.02 160	99.85 56	95.10 221	98.74 338	98.50 131	87.22 366	93.66 265	99.86 29	87.45 231	99.95 80	90.94 303	99.81 83	99.02 233

HPM-MVS		97.96 75	97.72 85	98.68 104	99.84 58	96.39 157	99.90 107	98.17 213	92.61 227	98.62 131	99.57 124	91.87 163	99.67 161	98.87 94	99.99 21	99.99 23
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EI-MVSNet-Vis-set		98.27 60	98.11 59	98.75 100	99.83 59	96.59 149	99.40 250	98.51 125	95.29 113	98.51 138	99.76 67	93.60 112	99.71 153	98.53 116	99.52 108	99.95 77

save fliter					99.82 60	98.79 40	99.96 47	98.40 171	97.66 31

PLC	95.54 3	97.93 78	97.89 78	98.05 158	99.82 60	94.77 231	99.92 93	98.46 136	93.93 172	97.20 189	99.27 155	95.44 51	99.97 59	97.41 170	99.51 111	99.41 183
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
APD-MVS_3200maxsize		98.25 65	98.08 61	98.78 97	99.81 62	96.60 147	99.82 152	98.30 196	93.95 171	99.37 87	99.77 65	92.84 134	99.76 146	98.95 85	99.92 64	99.97 62

EI-MVSNet-UG-set		98.14 70	97.99 67	98.60 112	99.80 63	96.27 160	99.36 260	98.50 131	95.21 115	98.30 150	99.75 75	93.29 120	99.73 152	98.37 125	99.30 132	99.81 103

SR-MVS-dyc-post		98.31 57	98.17 54	98.71 102	99.79 64	96.37 158	99.76 170	98.31 193	94.43 144	99.40 84	99.75 75	93.28 121	99.78 140	98.90 92	99.92 64	99.97 62

RE-MVS-def			98.13 57		99.79 64	96.37 158	99.76 170	98.31 193	94.43 144	99.40 84	99.75 75	92.95 131		98.90 92	99.92 64	99.97 62

HPM-MVS_fast		97.80 92	97.50 98	98.68 104	99.79 64	96.42 153	99.88 120	98.16 218	91.75 264	98.94 111	99.54 127	91.82 165	99.65 165	97.62 168	99.99 21	99.99 23

SF-MVS		98.67 30	98.40 36	99.50 30	99.77 67	98.67 49	99.90 107	98.21 208	93.53 187	99.81 22	99.89 22	94.70 73	99.86 122	99.84 25	99.93 61	99.96 70

MVS_0304		99.06 11	98.84 17	99.72 13	99.76 68	99.21 21	99.99 5	99.34 25	98.70 2	99.44 78	99.75 75	93.24 123	99.99 36	99.94 11	99.41 125	99.95 77

旧先验1					99.76 68	97.52 102		98.64 85			99.85 33	95.63 45			99.94 55	99.99 23

OMC-MVS		97.28 121	97.23 113	97.41 208	99.76 68	93.36 273	99.65 205	97.95 239	96.03 93	97.41 183	99.70 94	89.61 199	99.51 171	96.73 193	98.25 173	99.38 185

新几何1				99.42 38	99.75 71	98.27 66		98.63 91	92.69 222	99.55 67	99.82 49	94.40 81	100.00 1	91.21 295	99.94 55	99.99 23

MP-MVS-pluss		98.07 74	97.64 91	99.38 44	99.74 72	98.41 64	99.74 177	98.18 212	93.35 193	96.45 212	99.85 33	92.64 141	99.97 59	98.91 91	99.89 70	99.77 110
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
TSAR-MVS + MP.		98.93 17	98.77 19	99.41 39	99.74 72	98.67 49	99.77 165	98.38 178	96.73 67	99.88 10	99.74 82	94.89 66	99.59 167	99.80 28	99.98 32	99.97 62
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 36	99.74 72	98.56 57		98.40 171		99.65 51		94.76 69	99.75 147		99.98 32	99.99 23

原ACMM1				98.96 88	99.73 75	96.99 129		98.51 125	94.06 165	99.62 58	99.85 33	94.97 65	99.96 71	95.11 216	99.95 50	99.92 87

TSAR-MVS + GP.		98.60 34	98.51 31	98.86 93	99.73 75	96.63 144	99.97 37	97.92 244	98.07 17	98.76 124	99.55 125	95.00 63	99.94 88	99.91 16	97.68 190	99.99 23

CANet		98.27 60	97.82 82	99.63 17	99.72 77	99.10 23	99.98 19	98.51 125	97.00 57	98.52 136	99.71 91	87.80 223	99.95 80	99.75 37	99.38 127	99.83 99

reproduce_model		98.75 27	98.66 23	99.03 79	99.71 78	97.10 125	99.73 184	98.23 206	97.02 56	99.18 99	99.90 18	94.54 78	99.99 36	99.77 33	99.90 69	99.99 23

F-COLMAP		96.93 143	96.95 124	96.87 229	99.71 78	91.74 310	99.85 137	97.95 239	93.11 205	95.72 233	99.16 168	92.35 152	99.94 88	95.32 212	99.35 130	98.92 241

reproduce-ours		98.78 24	98.67 21	99.09 74	99.70 80	97.30 112	99.74 177	98.25 202	97.10 51	99.10 102	99.90 18	94.59 74	99.99 36	99.77 33	99.91 67	99.99 23

our_new_method		98.78 24	98.67 21	99.09 74	99.70 80	97.30 112	99.74 177	98.25 202	97.10 51	99.10 102	99.90 18	94.59 74	99.99 36	99.77 33	99.91 67	99.99 23

SD-MVS		98.92 18	98.70 20	99.56 25	99.70 80	98.73 46	99.94 83	98.34 188	96.38 82	99.81 22	99.76 67	94.59 74	99.98 47	99.84 25	99.96 46	99.97 62
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 66	99.12 5	95.59 270	99.67 83	86.91 391	99.95 66	98.89 52	97.60 32	99.90 5	99.76 67	96.54 32	99.98 47	99.94 11	99.82 81	99.88 92

ACMMP_NAP		98.49 42	98.14 56	99.54 27	99.66 84	98.62 55	99.85 137	98.37 181	94.68 132	99.53 70	99.83 46	92.87 133	100.00 1	98.66 108	99.84 76	99.99 23

DeepPCF-MVS	95.94 2	97.71 102	98.98 12	93.92 334	99.63 85	81.76 425	99.96 47	98.56 107	99.47 1	99.19 98	99.99 1	94.16 96	100.00 1	99.92 13	99.93 61	100.00 1

EPNet		98.49 42	98.40 36	98.77 99	99.62 86	96.80 138	99.90 107	99.51 16	97.60 32	99.20 96	99.36 145	93.71 109	99.91 104	97.99 148	98.71 158	99.61 141
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MM		98.83 21	98.53 30	99.76 10	99.59 87	99.33 8	99.99 5	99.76 6	98.39 4	99.39 86	99.80 54	90.49 188	99.96 71	99.89 18	99.43 123	99.98 52

PVSNet_BlendedMVS		96.05 184	95.82 180	96.72 235	99.59 87	96.99 129	99.95 66	99.10 34	94.06 165	98.27 151	95.80 339	89.00 211	99.95 80	99.12 73	87.53 331	93.24 393

PVSNet_Blended		97.94 77	97.64 91	98.83 94	99.59 87	96.99 129	100.00 1	99.10 34	95.38 110	98.27 151	99.08 171	89.00 211	99.95 80	99.12 73	99.25 134	99.57 152

PatchMatch-RL		96.04 185	95.40 191	97.95 162	99.59 87	95.22 216	99.52 232	99.07 37	93.96 170	96.49 211	98.35 254	82.28 294	99.82 135	90.15 319	99.22 137	98.81 248

dcpmvs_2		97.42 116	98.09 60	95.42 275	99.58 91	87.24 387	99.23 277	96.95 366	94.28 155	98.93 112	99.73 85	94.39 84	99.16 199	99.89 18	99.82 81	99.86 96

test222					99.55 92	97.41 110	99.34 262	98.55 113	91.86 259	99.27 94	99.83 46	93.84 106			99.95 50	99.99 23

CNLPA		97.76 96	97.38 105	98.92 91	99.53 93	96.84 134	99.87 123	98.14 222	93.78 179	96.55 210	99.69 98	92.28 154	99.98 47	97.13 177	99.44 122	99.93 82

API-MVS		97.86 83	97.66 89	98.47 129	99.52 94	95.41 201	99.47 242	98.87 55	91.68 265	98.84 115	99.85 33	92.34 153	99.99 36	98.44 121	99.96 46	100.00 1

PVSNet	91.05 13	97.13 130	96.69 140	98.45 131	99.52 94	95.81 180	99.95 66	99.65 12	94.73 129	99.04 107	99.21 163	84.48 279	99.95 80	94.92 222	98.74 157	99.58 150

114514_t		97.41 117	96.83 131	99.14 67	99.51 96	97.83 88	99.89 117	98.27 200	88.48 348	99.06 106	99.66 109	90.30 191	99.64 166	96.32 197	99.97 42	99.96 70

cl22		93.77 262	93.25 266	95.33 279	99.49 97	94.43 237	99.61 214	98.09 225	90.38 308	89.16 335	95.61 347	90.56 186	97.34 321	91.93 286	84.45 352	94.21 338

testdata				98.42 135	99.47 98	95.33 207		98.56 107	93.78 179	99.79 33	99.85 33	93.64 111	99.94 88	94.97 220	99.94 55	100.00 1

MAR-MVS		97.43 112	97.19 115	98.15 151	99.47 98	94.79 230	99.05 299	98.76 69	92.65 225	98.66 129	99.82 49	88.52 217	99.98 47	98.12 139	99.63 94	99.67 124
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		94.54 236	93.42 256	97.91 168	99.46 100	94.04 250	98.93 317	97.48 295	81.15 419	90.04 306	99.55 125	87.02 239	99.95 80	88.97 331	98.11 179	99.73 114

MVS_111021_LR		98.42 49	98.38 38	98.53 124	99.39 101	95.79 181	99.87 123	99.86 2	96.70 68	98.78 119	99.79 58	92.03 160	99.90 106	99.17 72	99.86 75	99.88 92

CHOSEN 280x420		99.01 14	99.03 10	98.95 89	99.38 102	98.87 33	98.46 357	99.42 21	97.03 55	99.02 108	99.09 170	99.35 2	98.21 283	99.73 41	99.78 84	99.77 110

MVS_111021_HR		98.72 28	98.62 26	99.01 83	99.36 103	97.18 118	99.93 90	99.90 1	96.81 65	98.67 128	99.77 65	93.92 101	99.89 111	99.27 68	99.94 55	99.96 70

DPM-MVS		98.83 21	98.46 33	99.97 1	99.33 104	99.92 1	99.96 47	98.44 142	97.96 21	99.55 67	99.94 4	97.18 21	100.00 1	93.81 253	99.94 55	99.98 52

TAPA-MVS	92.12 8	94.42 244	93.60 248	96.90 228	99.33 104	91.78 309	99.78 161	98.00 233	89.89 321	94.52 250	99.47 131	91.97 161	99.18 196	69.90 437	99.52 108	99.73 114
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
reproduce_monomvs		95.38 208	95.07 206	96.32 250	99.32 106	96.60 147	99.76 170	98.85 59	96.65 70	87.83 357	96.05 336	99.52 1	98.11 288	96.58 194	81.07 381	94.25 333

fmvsm_s_conf0.5_n_9		98.15 69	98.02 65	98.55 118	99.28 107	95.84 179	99.99 5	98.57 101	98.17 11	99.93 2	99.74 82	87.04 238	99.97 59	99.86 23	99.59 103	99.83 99

SPE-MVS-test		97.88 81	97.94 74	97.70 185	99.28 107	95.20 217	99.98 19	97.15 335	95.53 107	99.62 58	99.79 58	92.08 159	98.38 266	98.75 102	99.28 133	99.52 164

test_fmvsm_n_1920		98.44 46	98.61 27	97.92 166	99.27 109	95.18 218	100.00 1	98.90 50	98.05 18	99.80 24	99.73 85	92.64 141	99.99 36	99.58 52	99.51 111	98.59 258

fmvsm_l_conf0.5_n_a		99.00 15	98.91 14	99.28 48	99.21 110	97.91 86	99.98 19	98.85 59	98.25 5	99.92 4	99.75 75	94.72 71	99.97 59	99.87 21	99.64 92	99.95 77

fmvsm_s_conf0.5_n_8		98.38 54	98.05 63	99.35 45	99.20 111	98.12 72	99.98 19	98.81 64	98.22 7	99.80 24	99.71 91	87.37 233	99.97 59	99.91 16	99.48 115	99.97 62

test_yl		97.83 87	97.37 106	99.21 54	99.18 112	97.98 81	99.64 209	99.27 27	91.43 274	97.88 168	98.99 180	95.84 42	99.84 131	98.82 96	95.32 260	99.79 106

DCV-MVSNet		97.83 87	97.37 106	99.21 54	99.18 112	97.98 81	99.64 209	99.27 27	91.43 274	97.88 168	98.99 180	95.84 42	99.84 131	98.82 96	95.32 260	99.79 106

fmvsm_l_conf0.5_n		98.94 16	98.84 17	99.25 50	99.17 114	97.81 90	99.98 19	98.86 56	98.25 5	99.90 5	99.76 67	94.21 94	99.97 59	99.87 21	99.52 108	99.98 52

DeepC-MVS	94.51 4	96.92 144	96.40 153	98.45 131	99.16 115	95.90 177	99.66 204	98.06 228	96.37 85	94.37 256	99.49 130	83.29 289	99.90 106	97.63 167	99.61 99	99.55 154
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 38	98.22 49	99.50 30	99.15 116	98.65 53	100.00 1	98.58 99	97.70 30	98.21 156	99.24 161	92.58 144	99.94 88	98.63 111	99.94 55	99.92 87
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 50	98.08 61	99.39 41	99.12 117	98.29 65	99.98 19	98.64 85	98.14 14	99.86 13	99.76 67	87.99 222	99.97 59	99.72 42	99.54 106	99.91 89

fmvsm_l_conf0.5_n_9		98.55 37	98.23 48	99.49 32	99.10 118	98.50 60	99.99 5	98.70 74	98.14 14	99.94 1	99.68 105	89.02 210	99.98 47	99.89 18	99.61 99	99.99 23

CS-MVS		97.79 94	97.91 76	97.43 206	99.10 118	94.42 238	99.99 5	97.10 345	95.07 116	99.68 48	99.75 75	92.95 131	98.34 270	98.38 123	99.14 139	99.54 158

Anonymous202405211		93.10 280	91.99 293	96.40 246	99.10 118	89.65 359	98.88 323	97.93 241	83.71 404	94.00 262	98.75 216	68.79 398	99.88 117	95.08 217	91.71 293	99.68 122

fmvsm_s_conf0.5_n		97.80 92	97.85 80	97.67 186	99.06 121	94.41 239	99.98 19	98.97 43	97.34 40	99.63 55	99.69 98	87.27 234	99.97 59	99.62 50	99.06 144	98.62 257

HyFIR lowres test		96.66 159	96.43 151	97.36 213	99.05 122	93.91 255	99.70 196	99.80 3	90.54 304	96.26 218	98.08 267	92.15 157	98.23 282	96.84 190	95.46 255	99.93 82

LFMVS		94.75 230	93.56 251	98.30 141	99.03 123	95.70 187	98.74 338	97.98 236	87.81 359	98.47 140	99.39 142	67.43 407	99.53 168	98.01 146	95.20 263	99.67 124

fmvsm_s_conf0.5_n_4		97.75 97	97.86 79	97.42 207	99.01 124	94.69 232	99.97 37	98.76 69	97.91 23	99.87 11	99.76 67	86.70 244	99.93 97	99.67 47	99.12 142	97.64 284

fmvsm_s_conf0.5_n_2		97.59 107	97.28 110	98.53 124	99.01 124	98.15 67	99.98 19	98.59 97	98.17 11	99.75 38	99.63 115	81.83 300	99.94 88	99.78 31	98.79 155	97.51 292

AllTest		92.48 295	91.64 298	95.00 288	99.01 124	88.43 375	98.94 315	96.82 380	86.50 375	88.71 340	98.47 249	74.73 373	99.88 117	85.39 371	96.18 230	96.71 298

TestCases				95.00 288	99.01 124	88.43 375		96.82 380	86.50 375	88.71 340	98.47 249	74.73 373	99.88 117	85.39 371	96.18 230	96.71 298

COLMAP_ROB	90.47 14	92.18 302	91.49 304	94.25 322	99.00 128	88.04 381	98.42 363	96.70 387	82.30 415	88.43 349	99.01 177	76.97 348	99.85 123	86.11 367	96.50 222	94.86 309
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 76	97.66 89	98.81 95	98.99 129	98.07 75	99.98 19	98.81 64	98.18 10	99.89 8	99.70 94	84.15 282	99.97 59	99.76 36	99.50 113	98.39 263

test_fmvs1		95.35 209	95.68 185	94.36 318	98.99 129	84.98 402	99.96 47	96.65 389	97.60 32	99.73 43	98.96 186	71.58 388	99.93 97	98.31 128	99.37 128	98.17 268

HY-MVS	92.50 7	97.79 94	97.17 117	99.63 17	98.98 131	99.32 9	97.49 390	99.52 14	95.69 102	98.32 149	97.41 287	93.32 118	99.77 143	98.08 143	95.75 245	99.81 103

VNet		97.21 126	96.57 145	99.13 71	98.97 132	97.82 89	99.03 302	99.21 32	94.31 152	99.18 99	98.88 198	86.26 251	99.89 111	98.93 87	94.32 273	99.69 121

thres200		96.96 140	96.21 159	99.22 53	98.97 132	98.84 36	99.85 137	99.71 7	93.17 200	96.26 218	98.88 198	89.87 196	99.51 171	94.26 241	94.91 265	99.31 202

tfpn200view9		96.79 148	95.99 166	99.19 56	98.94 134	98.82 37	99.78 161	99.71 7	92.86 211	96.02 225	98.87 205	89.33 203	99.50 173	93.84 250	94.57 269	99.27 209

thres400		96.78 150	95.99 166	99.16 63	98.94 134	98.82 37	99.78 161	99.71 7	92.86 211	96.02 225	98.87 205	89.33 203	99.50 173	93.84 250	94.57 269	99.16 217

sasdasda		97.09 133	96.32 154	99.39 41	98.93 136	98.95 27	99.72 188	97.35 308	94.45 140	97.88 168	99.42 135	86.71 242	99.52 169	98.48 118	93.97 279	99.72 116

Anonymous20231211		89.86 352	88.44 360	94.13 325	98.93 136	90.68 337	98.54 354	98.26 201	76.28 431	86.73 371	95.54 351	70.60 394	97.56 314	90.82 306	80.27 390	94.15 346

canonicalmvs		97.09 133	96.32 154	99.39 41	98.93 136	98.95 27	99.72 188	97.35 308	94.45 140	97.88 168	99.42 135	86.71 242	99.52 169	98.48 118	93.97 279	99.72 116

SDMVSNet		94.80 225	93.96 240	97.33 215	98.92 139	95.42 200	99.59 218	98.99 40	92.41 238	92.55 280	97.85 278	75.81 363	98.93 214	97.90 154	91.62 294	97.64 284

sd_testset		93.55 269	92.83 273	95.74 268	98.92 139	90.89 333	98.24 370	98.85 59	92.41 238	92.55 280	97.85 278	71.07 393	98.68 238	93.93 247	91.62 294	97.64 284

EPNet_dtu		95.71 197	95.39 192	96.66 237	98.92 139	93.41 269	99.57 223	98.90 50	96.19 90	97.52 178	98.56 239	92.65 140	97.36 319	77.89 418	98.33 168	99.20 215
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WTY-MVS		98.10 72	97.60 93	99.60 22	98.92 139	99.28 17	99.89 117	99.52 14	95.58 105	98.24 155	99.39 142	93.33 117	99.74 149	97.98 150	95.58 254	99.78 109

CHOSEN 1792x2688		96.81 147	96.53 146	97.64 188	98.91 143	93.07 275	99.65 205	99.80 3	95.64 103	95.39 240	98.86 207	84.35 281	99.90 106	96.98 183	99.16 138	99.95 77

thres100view900		96.74 154	95.92 176	99.18 57	98.90 144	98.77 42	99.74 177	99.71 7	92.59 229	95.84 229	98.86 207	89.25 205	99.50 173	93.84 250	94.57 269	99.27 209

thres600view7		96.69 157	95.87 179	99.14 67	98.90 144	98.78 41	99.74 177	99.71 7	92.59 229	95.84 229	98.86 207	89.25 205	99.50 173	93.44 263	94.50 272	99.16 217

MSDG		94.37 246	93.36 263	97.40 209	98.88 146	93.95 254	99.37 258	97.38 304	85.75 386	90.80 299	99.17 167	84.11 284	99.88 117	86.35 363	98.43 166	98.36 265

MGCFI-Net		97.00 138	96.22 158	99.34 46	98.86 147	98.80 39	99.67 203	97.30 316	94.31 152	97.77 174	99.41 139	86.36 249	99.50 173	98.38 123	93.90 281	99.72 116

h-mvs33		94.92 222	94.36 226	96.59 239	98.85 148	91.29 325	98.93 317	98.94 44	95.90 95	98.77 121	98.42 252	90.89 181	99.77 143	97.80 158	70.76 429	98.72 254

Anonymous20240529		92.10 303	90.65 315	96.47 241	98.82 149	90.61 339	98.72 340	98.67 81	75.54 435	93.90 264	98.58 237	66.23 411	99.90 106	94.70 231	90.67 297	98.90 244

PVSNet_Blended_VisFu		97.27 122	96.81 133	98.66 107	98.81 150	96.67 143	99.92 93	98.64 85	94.51 137	96.38 216	98.49 245	89.05 209	99.88 117	97.10 179	98.34 167	99.43 181

PS-MVSNAJ		98.44 46	98.20 51	99.16 63	98.80 151	98.92 29	99.54 230	98.17 213	97.34 40	99.85 16	99.85 33	91.20 170	99.89 111	99.41 63	99.67 90	98.69 255

CANet_DTU		96.76 151	96.15 161	98.60 112	98.78 152	97.53 101	99.84 142	97.63 273	97.25 48	99.20 96	99.64 112	81.36 306	99.98 47	92.77 274	98.89 149	98.28 267

mvsany_test1		97.82 90	97.90 77	97.55 197	98.77 153	93.04 278	99.80 158	97.93 241	96.95 59	99.61 65	99.68 105	90.92 178	99.83 133	99.18 71	98.29 172	99.80 105

alignmvs		97.81 91	97.33 108	99.25 50	98.77 153	98.66 51	99.99 5	98.44 142	94.40 148	98.41 144	99.47 131	93.65 110	99.42 183	98.57 112	94.26 275	99.67 124

SymmetryMVS		97.64 105	97.46 99	98.17 147	98.74 155	95.39 203	99.61 214	99.26 29	96.52 74	98.61 132	99.31 150	92.73 138	99.67 161	96.77 191	95.63 252	99.45 177

SteuartSystems-ACMMP		99.02 13	98.97 13	99.18 57	98.72 156	97.71 93	99.98 19	98.44 142	96.85 60	99.80 24	99.91 14	97.57 8	99.85 123	99.44 61	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
xiu_mvs_v2_base		98.23 67	97.97 69	99.02 82	98.69 157	98.66 51	99.52 232	98.08 227	97.05 54	99.86 13	99.86 29	90.65 183	99.71 153	99.39 65	98.63 159	98.69 255

miper_enhance_ethall		94.36 248	93.98 239	95.49 271	98.68 158	95.24 214	99.73 184	97.29 319	93.28 197	89.86 311	95.97 337	94.37 85	97.05 342	92.20 278	84.45 352	94.19 339

fmvsm_s_conf0.5_n_5		98.08 73	97.71 87	99.17 60	98.67 159	97.69 97	99.99 5	98.57 101	97.40 38	99.89 8	99.69 98	85.99 254	99.96 71	99.80 28	99.40 126	99.85 97

ETVMVS		97.03 137	96.64 141	98.20 146	98.67 159	97.12 122	99.89 117	98.57 101	91.10 286	98.17 157	98.59 234	93.86 105	98.19 284	95.64 209	95.24 262	99.28 208

test2506		97.53 109	97.19 115	98.58 116	98.66 161	96.90 133	98.81 332	99.77 5	94.93 119	97.95 163	98.96 186	92.51 147	99.20 194	94.93 221	98.15 176	99.64 130

ECVR-MVS		95.66 200	95.05 207	97.51 201	98.66 161	93.71 259	98.85 329	98.45 137	94.93 119	96.86 200	98.96 186	75.22 369	99.20 194	95.34 211	98.15 176	99.64 130

mamv4		95.24 212	96.90 126	90.25 396	98.65 163	72.11 443	98.28 368	97.64 272	89.99 319	95.93 227	98.25 262	94.74 70	99.11 200	99.01 84	99.64 92	99.53 162

balanced_conf03		98.27 60	97.99 67	99.11 72	98.64 164	98.43 63	99.47 242	97.79 256	94.56 135	99.74 41	98.35 254	94.33 88	99.25 188	99.12 73	99.96 46	99.64 130

fmvsm_s_conf0.5_n_a		97.73 100	97.72 85	97.77 180	98.63 165	94.26 245	99.96 47	98.92 49	97.18 50	99.75 38	99.69 98	87.00 240	99.97 59	99.46 59	98.89 149	99.08 227

MVSMamba_PlusPlus		97.83 87	97.45 101	98.99 84	98.60 166	98.15 67	99.58 220	97.74 263	90.34 311	99.26 95	98.32 257	94.29 90	99.23 189	99.03 82	99.89 70	99.58 150

testing222		97.08 136	96.75 136	98.06 157	98.56 167	96.82 135	99.85 137	98.61 93	92.53 233	98.84 115	98.84 211	93.36 115	98.30 274	95.84 205	94.30 274	99.05 231

test1111		95.57 203	94.98 210	97.37 211	98.56 167	93.37 272	98.86 327	98.45 137	94.95 118	96.63 206	98.95 191	75.21 370	99.11 200	95.02 218	98.14 178	99.64 130

MVSTER		95.53 204	95.22 199	96.45 244	98.56 167	97.72 92	99.91 101	97.67 268	92.38 240	91.39 290	97.14 294	97.24 18	97.30 326	94.80 227	87.85 326	94.34 328

testing3-2		97.72 101	97.43 104	98.60 112	98.55 170	97.11 124	100.00 1	99.23 31	93.78 179	97.90 165	98.73 218	95.50 49	99.69 157	98.53 116	94.63 267	98.99 235

VDD-MVS		93.77 262	92.94 271	96.27 251	98.55 170	90.22 348	98.77 337	97.79 256	90.85 292	96.82 202	99.42 135	61.18 431	99.77 143	98.95 85	94.13 276	98.82 247

tpmvs		94.28 250	93.57 250	96.40 246	98.55 170	91.50 323	95.70 427	98.55 113	87.47 361	92.15 283	94.26 402	91.42 166	98.95 213	88.15 342	95.85 241	98.76 250

UGNet		95.33 210	94.57 222	97.62 192	98.55 170	94.85 226	98.67 346	99.32 26	95.75 100	96.80 203	96.27 326	72.18 385	99.96 71	94.58 234	99.05 145	98.04 273
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	95.18 214	94.10 233	98.43 133	98.55 170	95.99 175	97.91 383	97.31 315	90.35 310	89.48 324	99.22 162	85.19 267	99.89 111	90.40 316	98.47 165	99.41 183
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS-28		95.95 187	96.49 147	94.34 319	98.51 175	89.99 353	99.39 254	98.57 101	93.14 202	97.33 185	98.31 259	93.44 113	94.68 419	93.69 260	95.98 235	98.34 266

UWE-MVS		96.79 148	96.72 138	97.00 223	98.51 175	93.70 260	99.71 191	98.60 95	92.96 207	97.09 192	98.34 256	96.67 31	98.85 217	92.11 284	96.50 222	98.44 261

myMVS_eth3d28		97.86 83	97.59 95	98.68 104	98.50 177	97.26 114	99.92 93	98.55 113	93.79 178	98.26 153	98.75 216	95.20 54	99.48 179	98.93 87	96.40 225	99.29 206

test_vis1_n_1920		95.44 206	95.31 195	95.82 265	98.50 177	88.74 369	99.98 19	97.30 316	97.84 26	99.85 16	99.19 165	66.82 409	99.97 59	98.82 96	99.46 120	98.76 250

BH-w/o		95.71 197	95.38 193	96.68 236	98.49 179	92.28 296	99.84 142	97.50 293	92.12 250	92.06 286	98.79 214	84.69 275	98.67 239	95.29 213	99.66 91	99.09 225

baseline1		95.78 193	94.86 213	98.54 122	98.47 180	98.07 75	99.06 295	97.99 234	92.68 223	94.13 261	98.62 231	93.28 121	98.69 237	93.79 255	85.76 339	98.84 246

fmvsm_s_conf0.5_n_7		97.70 103	97.74 84	97.59 195	98.44 181	95.16 220	99.97 37	98.65 82	97.95 22	99.62 58	99.78 62	86.09 252	99.94 88	99.69 45	99.50 113	97.66 283

EPMVS		96.53 165	96.01 165	98.09 155	98.43 182	96.12 173	96.36 414	99.43 20	93.53 187	97.64 176	95.04 379	94.41 80	98.38 266	91.13 297	98.11 179	99.75 112

kuosan		93.17 277	92.60 279	94.86 295	98.40 183	89.54 361	98.44 359	98.53 120	84.46 399	88.49 345	97.92 275	90.57 185	97.05 342	83.10 388	93.49 284	97.99 274

WBMVS		94.52 239	94.03 237	95.98 257	98.38 184	96.68 142	99.92 93	97.63 273	90.75 301	89.64 319	95.25 372	96.77 25	96.90 354	94.35 239	83.57 359	94.35 326

UBG		97.84 86	97.69 88	98.29 142	98.38 184	96.59 149	99.90 107	98.53 120	93.91 174	98.52 136	98.42 252	96.77 25	99.17 197	98.54 114	96.20 229	99.11 224

sss		97.57 108	97.03 122	99.18 57	98.37 186	98.04 78	99.73 184	99.38 22	93.46 190	98.76 124	99.06 173	91.21 169	99.89 111	96.33 196	97.01 214	99.62 137

testing11		97.48 111	97.27 111	98.10 154	98.36 187	96.02 174	99.92 93	98.45 137	93.45 192	98.15 158	98.70 221	95.48 50	99.22 190	97.85 156	95.05 264	99.07 228

BH-untuned		95.18 214	94.83 214	96.22 252	98.36 187	91.22 326	99.80 158	97.32 314	90.91 290	91.08 293	98.67 223	83.51 286	98.54 248	94.23 242	99.61 99	98.92 241

testing91		97.16 128	96.90 126	97.97 161	98.35 189	95.67 190	99.91 101	98.42 162	92.91 210	97.33 185	98.72 219	94.81 68	99.21 191	96.98 183	94.63 267	99.03 232

testing99		97.17 127	96.91 125	97.95 162	98.35 189	95.70 187	99.91 101	98.43 150	92.94 208	97.36 184	98.72 219	94.83 67	99.21 191	97.00 181	94.64 266	98.95 237

ET-MVSNet_ETH3D		94.37 246	93.28 265	97.64 188	98.30 191	97.99 80	99.99 5	97.61 279	94.35 149	71.57 441	99.45 134	96.23 35	95.34 409	96.91 188	85.14 346	99.59 144

AUN-MVS		93.28 274	92.60 279	95.34 278	98.29 192	90.09 351	99.31 266	98.56 107	91.80 263	96.35 217	98.00 270	89.38 202	98.28 277	92.46 275	69.22 434	97.64 284

FMVSNet3		92.69 290	91.58 300	95.99 256	98.29 192	97.42 109	99.26 275	97.62 276	89.80 322	89.68 315	95.32 366	81.62 304	96.27 385	87.01 359	85.65 340	94.29 330

PMMVS		96.76 151	96.76 135	96.76 233	98.28 194	92.10 300	99.91 101	97.98 236	94.12 160	99.53 70	99.39 142	86.93 241	98.73 230	96.95 186	97.73 187	99.45 177

hse-mvs2		94.38 245	94.08 236	95.31 280	98.27 195	90.02 352	99.29 271	98.56 107	95.90 95	98.77 121	98.00 270	90.89 181	98.26 281	97.80 158	69.20 435	97.64 284

PVSNet_0	88.03 19	91.80 310	90.27 324	96.38 248	98.27 195	90.46 343	99.94 83	99.61 13	93.99 168	86.26 381	97.39 289	71.13 392	99.89 111	98.77 100	67.05 440	98.79 249

UA-Net		96.54 164	95.96 172	98.27 143	98.23 197	95.71 186	98.00 381	98.45 137	93.72 183	98.41 144	99.27 155	88.71 216	99.66 164	91.19 296	97.69 188	99.44 180

test_cas_vis1_n_1920		96.59 162	96.23 157	97.65 187	98.22 198	94.23 246	99.99 5	97.25 323	97.77 27	99.58 66	99.08 171	77.10 345	99.97 59	97.64 166	99.45 121	98.74 252

FE-MVS		95.70 199	95.01 209	97.79 176	98.21 199	94.57 234	95.03 428	98.69 76	88.90 338	97.50 180	96.19 328	92.60 143	99.49 178	89.99 321	97.94 185	99.31 202

GG-mvs-BLEND				98.54 122	98.21 199	98.01 79	93.87 433	98.52 122		97.92 164	97.92 275	99.02 3	97.94 301	98.17 136	99.58 104	99.67 124

mvs_anonymous		95.65 201	95.03 208	97.53 199	98.19 201	95.74 184	99.33 263	97.49 294	90.87 291	90.47 302	97.10 296	88.23 219	97.16 333	95.92 203	97.66 191	99.68 122

MVS_Test		96.46 167	95.74 181	98.61 111	98.18 202	97.23 116	99.31 266	97.15 335	91.07 287	98.84 115	97.05 300	88.17 220	98.97 210	94.39 236	97.50 193	99.61 141

BH-RMVSNet		95.18 214	94.31 229	97.80 174	98.17 203	95.23 215	99.76 170	97.53 289	92.52 234	94.27 259	99.25 160	76.84 350	98.80 220	90.89 305	99.54 106	99.35 193

dongtai		91.55 316	91.13 309	92.82 364	98.16 204	86.35 392	99.47 242	98.51 125	83.24 407	85.07 391	97.56 283	90.33 190	94.94 415	76.09 426	91.73 292	97.18 295

RPSCF		91.80 310	92.79 275	88.83 407	98.15 205	69.87 445	98.11 377	96.60 391	83.93 402	94.33 257	99.27 155	79.60 328	99.46 182	91.99 285	93.16 289	97.18 295

ETV-MVS		97.92 79	97.80 83	98.25 144	98.14 206	96.48 151	99.98 19	97.63 273	95.61 104	99.29 93	99.46 133	92.55 145	98.82 218	99.02 83	98.54 163	99.46 175

IS-MVSNet		96.29 178	95.90 177	97.45 204	98.13 207	94.80 229	99.08 290	97.61 279	92.02 255	95.54 238	98.96 186	90.64 184	98.08 290	93.73 258	97.41 197	99.47 173

test_fmvsmconf_n		98.43 48	98.32 44	98.78 97	98.12 208	96.41 154	99.99 5	98.83 63	98.22 7	99.67 49	99.64 112	91.11 174	99.94 88	99.67 47	99.62 95	99.98 52

fmvsm_s_conf0.1_n_2		97.25 123	96.85 130	98.43 133	98.08 209	98.08 74	99.92 93	97.76 262	98.05 18	99.65 51	99.58 121	80.88 313	99.93 97	99.59 51	98.17 174	97.29 293

ab-mvs		94.69 231	93.42 256	98.51 127	98.07 210	96.26 161	96.49 412	98.68 78	90.31 312	94.54 249	97.00 302	76.30 358	99.71 153	95.98 202	93.38 287	99.56 153

XVG-OURS-SEG-HR		94.79 226	94.70 221	95.08 285	98.05 211	89.19 363	99.08 290	97.54 287	93.66 184	94.87 247	99.58 121	78.78 336	99.79 138	97.31 172	93.40 286	96.25 302

EIA-MVS		97.53 109	97.46 99	97.76 182	98.04 212	94.84 227	99.98 19	97.61 279	94.41 147	97.90 165	99.59 118	92.40 151	98.87 215	98.04 145	99.13 140	99.59 144

XVG-OURS		94.82 223	94.74 220	95.06 286	98.00 213	89.19 363	99.08 290	97.55 285	94.10 161	94.71 248	99.62 116	80.51 319	99.74 149	96.04 201	93.06 291	96.25 302

mvsmamba		96.94 141	96.73 137	97.55 197	97.99 214	94.37 242	99.62 212	97.70 265	93.13 203	98.42 143	97.92 275	88.02 221	98.75 228	98.78 99	99.01 146	99.52 164

dp		95.05 217	94.43 224	96.91 226	97.99 214	92.73 285	96.29 417	97.98 236	89.70 323	95.93 227	94.67 392	93.83 107	98.45 254	86.91 362	96.53 221	99.54 158

tpmrst		96.27 180	95.98 168	97.13 219	97.96 216	93.15 274	96.34 415	98.17 213	92.07 251	98.71 127	95.12 376	93.91 102	98.73 230	94.91 224	96.62 219	99.50 170

TR-MVS		94.54 236	93.56 251	97.49 203	97.96 216	94.34 243	98.71 341	97.51 292	90.30 313	94.51 251	98.69 222	75.56 364	98.77 224	92.82 273	95.99 234	99.35 193

Vis-MVSNet (Re-imp)		96.32 175	95.98 168	97.35 214	97.93 218	94.82 228	99.47 242	98.15 221	91.83 260	95.09 245	99.11 169	91.37 168	97.47 317	93.47 262	97.43 194	99.74 113

MDTV_nov1_ep13			95.69 183		97.90 219	94.15 248	95.98 423	98.44 142	93.12 204	97.98 162	95.74 341	95.10 57	98.58 244	90.02 320	96.92 216

Fast-Effi-MVS+		95.02 219	94.19 231	97.52 200	97.88 220	94.55 235	99.97 37	97.08 349	88.85 340	94.47 252	97.96 274	84.59 276	98.41 258	89.84 323	97.10 209	99.59 144

ADS-MVSNet2		93.80 261	93.88 243	93.55 347	97.87 221	85.94 396	94.24 429	96.84 377	90.07 316	96.43 213	94.48 397	90.29 192	95.37 408	87.44 349	97.23 202	99.36 189

ADS-MVSNet		94.79 226	94.02 238	97.11 221	97.87 221	93.79 256	94.24 429	98.16 218	90.07 316	96.43 213	94.48 397	90.29 192	98.19 284	87.44 349	97.23 202	99.36 189

Effi-MVS+		96.30 177	95.69 183	98.16 148	97.85 223	96.26 161	97.41 392	97.21 327	90.37 309	98.65 130	98.58 237	86.61 246	98.70 236	97.11 178	97.37 198	99.52 164

PatchmatchNet		95.94 188	95.45 190	97.39 210	97.83 224	94.41 239	96.05 421	98.40 171	92.86 211	97.09 192	95.28 371	94.21 94	98.07 292	89.26 329	98.11 179	99.70 119
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
cascas		94.64 234	93.61 246	97.74 184	97.82 225	96.26 161	99.96 47	97.78 258	85.76 384	94.00 262	97.54 284	76.95 349	99.21 191	97.23 175	95.43 257	97.76 282

1112_ss		96.01 186	95.20 200	98.42 135	97.80 226	96.41 154	99.65 205	96.66 388	92.71 220	92.88 276	99.40 140	92.16 156	99.30 186	91.92 287	93.66 282	99.55 154

Test_1112_low_res		95.72 195	94.83 214	98.42 135	97.79 227	96.41 154	99.65 205	96.65 389	92.70 221	92.86 277	96.13 332	92.15 157	99.30 186	91.88 288	93.64 283	99.55 154

Effi-MVS+-dtu		94.53 238	95.30 196	92.22 372	97.77 228	82.54 418	99.59 218	97.06 353	94.92 121	95.29 242	95.37 364	85.81 255	97.89 302	94.80 227	97.07 210	96.23 304

tpm cat1		93.51 270	92.52 285	96.47 241	97.77 228	91.47 324	96.13 419	98.06 228	80.98 420	92.91 275	93.78 406	89.66 197	98.87 215	87.03 358	96.39 226	99.09 225

FA-MVS(test-final)		95.86 190	95.09 205	98.15 151	97.74 230	95.62 192	96.31 416	98.17 213	91.42 276	96.26 218	96.13 332	90.56 186	99.47 181	92.18 279	97.07 210	99.35 193

xiu_mvs_v1_base_debu		97.43 112	97.06 118	98.55 118	97.74 230	98.14 69	99.31 266	97.86 250	96.43 79	99.62 58	99.69 98	85.56 262	99.68 158	99.05 76	98.31 169	97.83 278

xiu_mvs_v1_base		97.43 112	97.06 118	98.55 118	97.74 230	98.14 69	99.31 266	97.86 250	96.43 79	99.62 58	99.69 98	85.56 262	99.68 158	99.05 76	98.31 169	97.83 278

xiu_mvs_v1_base_debi		97.43 112	97.06 118	98.55 118	97.74 230	98.14 69	99.31 266	97.86 250	96.43 79	99.62 58	99.69 98	85.56 262	99.68 158	99.05 76	98.31 169	97.83 278

EPP-MVSNet		96.69 157	96.60 143	96.96 225	97.74 230	93.05 277	99.37 258	98.56 107	88.75 342	95.83 231	99.01 177	96.01 36	98.56 246	96.92 187	97.20 204	99.25 211

gg-mvs-nofinetune		93.51 270	91.86 297	98.47 129	97.72 235	97.96 84	92.62 439	98.51 125	74.70 438	97.33 185	69.59 455	98.91 4	97.79 305	97.77 163	99.56 105	99.67 124

IB-MVS	92.85 6	94.99 220	93.94 241	98.16 148	97.72 235	95.69 189	99.99 5	98.81 64	94.28 155	92.70 278	96.90 304	95.08 58	99.17 197	96.07 200	73.88 422	99.60 143
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		97.41 117	97.02 123	98.59 115	97.71 237	97.52 102	99.97 37	98.54 117	91.83 260	97.45 181	99.04 174	97.50 9	99.10 202	94.75 229	96.37 227	99.16 217

VortexMVS		94.11 252	93.50 253	95.94 259	97.70 238	96.61 146	99.35 261	97.18 330	93.52 189	89.57 322	95.74 341	87.55 228	96.97 350	95.76 208	85.13 347	94.23 335

Syy-MVS		90.00 350	90.63 316	88.11 414	97.68 239	74.66 441	99.71 191	98.35 184	90.79 298	92.10 284	98.67 223	79.10 334	93.09 434	63.35 448	95.95 238	96.59 300

myMVS_eth3d		94.46 243	94.76 219	93.55 347	97.68 239	90.97 328	99.71 191	98.35 184	90.79 298	92.10 284	98.67 223	92.46 150	93.09 434	87.13 355	95.95 238	96.59 300

test_fmvs1_n		94.25 251	94.36 226	93.92 334	97.68 239	83.70 409	99.90 107	96.57 392	97.40 38	99.67 49	98.88 198	61.82 428	99.92 103	98.23 134	99.13 140	98.14 271

fmvsm_s_conf0.5_n_6		98.27 60	97.96 72	99.23 52	97.66 242	98.11 73	99.98 19	98.64 85	97.85 25	99.87 11	99.72 88	88.86 213	99.93 97	99.64 49	99.36 129	99.63 136

RRT-MVS		96.24 181	95.68 185	97.94 165	97.65 243	94.92 225	99.27 274	97.10 345	92.79 217	97.43 182	97.99 272	81.85 299	99.37 185	98.46 120	98.57 160	99.53 162

diffmvs		97.00 138	96.64 141	98.09 155	97.64 244	96.17 170	99.81 154	97.19 328	94.67 133	98.95 110	99.28 152	86.43 247	98.76 226	98.37 125	97.42 196	99.33 196
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Vis-MVSNet		95.72 195	95.15 203	97.45 204	97.62 245	94.28 244	99.28 272	98.24 204	94.27 157	96.84 201	98.94 193	79.39 329	98.76 226	93.25 264	98.49 164	99.30 204
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
thisisatest0530		97.10 131	96.72 138	98.22 145	97.60 246	96.70 139	99.92 93	98.54 117	91.11 285	97.07 194	98.97 184	97.47 12	99.03 205	93.73 258	96.09 232	98.92 241

GDP-MVS		97.88 81	97.59 95	98.75 100	97.59 247	97.81 90	99.95 66	97.37 307	94.44 143	99.08 104	99.58 121	97.13 23	99.08 203	94.99 219	98.17 174	99.37 187

miper_ehance_all_eth		93.16 278	92.60 279	94.82 296	97.57 248	93.56 264	99.50 236	97.07 352	88.75 342	88.85 339	95.52 353	90.97 177	96.74 364	90.77 307	84.45 352	94.17 340

guyue		97.15 129	96.82 132	98.15 151	97.56 249	96.25 165	99.71 191	97.84 253	95.75 100	98.13 159	98.65 226	87.58 227	98.82 218	98.29 130	97.91 186	99.36 189

viewmanbaseed2359cas		96.45 168	96.07 162	97.59 195	97.55 250	94.59 233	99.70 196	97.33 312	93.62 186	97.00 196	99.32 147	85.57 261	98.71 233	97.26 174	97.33 199	99.47 173

testing3		93.92 255	94.23 230	92.99 361	97.54 251	90.23 347	99.99 5	99.16 33	90.57 303	91.33 292	98.63 230	92.99 129	92.52 438	82.46 392	95.39 258	96.22 305

SSM_0404		95.75 194	95.16 202	97.50 202	97.53 252	95.39 203	99.11 286	97.25 323	90.81 294	95.27 243	98.83 212	84.74 272	98.67 239	95.24 214	97.69 188	98.45 260

LCM-MVSNet-Re		92.31 299	92.60 279	91.43 381	97.53 252	79.27 435	99.02 304	91.83 451	92.07 251	80.31 415	94.38 400	83.50 287	95.48 405	97.22 176	97.58 192	99.54 158

GBi-Net		90.88 327	89.82 333	94.08 326	97.53 252	91.97 301	98.43 360	96.95 366	87.05 367	89.68 315	94.72 388	71.34 389	96.11 391	87.01 359	85.65 340	94.17 340

test1		90.88 327	89.82 333	94.08 326	97.53 252	91.97 301	98.43 360	96.95 366	87.05 367	89.68 315	94.72 388	71.34 389	96.11 391	87.01 359	85.65 340	94.17 340

FMVSNet2		91.02 324	89.56 338	95.41 276	97.53 252	95.74 184	98.98 307	97.41 302	87.05 367	88.43 349	95.00 382	71.34 389	96.24 387	85.12 374	85.21 345	94.25 333

tttt0517		96.85 145	96.49 147	97.92 166	97.48 257	95.89 178	99.85 137	98.54 117	90.72 302	96.63 206	98.93 196	97.47 12	99.02 206	93.03 271	95.76 244	98.85 245

BP-MVS1		98.33 56	98.18 53	98.81 95	97.44 258	97.98 81	99.96 47	98.17 213	94.88 123	98.77 121	99.59 118	97.59 7	99.08 203	98.24 133	98.93 148	99.36 189

casdiffmvs_mvg		96.43 169	95.94 174	97.89 170	97.44 258	95.47 196	99.86 134	97.29 319	93.35 193	96.03 224	99.19 165	85.39 265	98.72 232	97.89 155	97.04 212	99.49 172
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EC-MVSNet		97.38 119	97.24 112	97.80 174	97.41 260	95.64 191	99.99 5	97.06 353	94.59 134	99.63 55	99.32 147	89.20 208	98.14 286	98.76 101	99.23 136	99.62 137

c3_l		92.53 294	91.87 296	94.52 308	97.40 261	92.99 279	99.40 250	96.93 371	87.86 357	88.69 342	95.44 358	89.95 195	96.44 377	90.45 313	80.69 386	94.14 349

viewmambaseed2359dif		95.92 189	95.55 189	97.04 222	97.38 262	93.41 269	99.78 161	96.97 364	91.14 284	96.58 208	99.27 155	84.85 271	98.75 228	96.87 189	97.12 208	98.97 236

fmvsm_s_conf0.1_n		97.30 120	97.21 114	97.60 194	97.38 262	94.40 241	99.90 107	98.64 85	96.47 78	99.51 74	99.65 111	84.99 270	99.93 97	99.22 70	99.09 143	98.46 259

CDS-MVSNet		96.34 174	96.07 162	97.13 219	97.37 264	94.96 223	99.53 231	97.91 245	91.55 268	95.37 241	98.32 257	95.05 60	97.13 336	93.80 254	95.75 245	99.30 204
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TESTMET0.1,1		96.74 154	96.26 156	98.16 148	97.36 265	96.48 151	99.96 47	98.29 197	91.93 256	95.77 232	98.07 268	95.54 46	98.29 275	90.55 311	98.89 149	99.70 119

miper_lstm_enhance		91.81 307	91.39 306	93.06 360	97.34 266	89.18 365	99.38 256	96.79 382	86.70 374	87.47 363	95.22 373	90.00 194	95.86 400	88.26 340	81.37 375	94.15 346

baseline		96.43 169	95.98 168	97.76 182	97.34 266	95.17 219	99.51 234	97.17 332	93.92 173	96.90 199	99.28 152	85.37 266	98.64 242	97.50 169	96.86 218	99.46 175

cl____		92.31 299	91.58 300	94.52 308	97.33 268	92.77 281	99.57 223	96.78 383	86.97 371	87.56 361	95.51 354	89.43 201	96.62 369	88.60 334	82.44 367	94.16 345

SD_0403		92.63 293	93.38 260	90.40 395	97.32 269	77.91 437	97.75 388	98.03 232	91.89 257	90.83 298	98.29 261	82.00 296	93.79 428	88.51 338	95.75 245	99.52 164

DIV-MVS_self_test		92.32 298	91.60 299	94.47 312	97.31 270	92.74 283	99.58 220	96.75 384	86.99 370	87.64 359	95.54 351	89.55 200	96.50 374	88.58 335	82.44 367	94.17 340

casdiffmvs		96.42 171	95.97 171	97.77 180	97.30 271	94.98 222	99.84 142	97.09 348	93.75 182	96.58 208	99.26 159	85.07 268	98.78 223	97.77 163	97.04 212	99.54 158
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		94.36 248	93.48 254	96.99 224	97.29 272	93.54 265	99.96 47	96.72 386	88.35 351	93.43 266	98.94 193	82.05 295	98.05 293	88.12 344	96.48 224	99.37 187

eth_miper_zixun_eth		92.41 297	91.93 294	93.84 338	97.28 273	90.68 337	98.83 330	96.97 364	88.57 347	89.19 334	95.73 344	89.24 207	96.69 367	89.97 322	81.55 373	94.15 346

MVSFormer		96.94 141	96.60 143	97.95 162	97.28 273	97.70 95	99.55 228	97.27 321	91.17 281	99.43 80	99.54 127	90.92 178	96.89 355	94.67 232	99.62 95	99.25 211

lupinMVS		97.85 85	97.60 93	98.62 110	97.28 273	97.70 95	99.99 5	97.55 285	95.50 109	99.43 80	99.67 107	90.92 178	98.71 233	98.40 122	99.62 95	99.45 177

diffmvs_AUTHOR		96.75 153	96.41 152	97.79 176	97.20 276	95.46 197	99.69 198	97.15 335	94.46 139	98.78 119	99.21 163	85.64 259	98.77 224	98.27 131	97.31 200	99.13 221

mamba_0408		94.98 221	94.09 234	97.64 188	97.14 277	95.31 208	93.48 436	97.08 349	90.48 305	94.40 253	98.62 231	84.49 277	98.67 239	93.99 245	97.18 205	98.93 238

SSM_04072		94.77 228	94.09 234	96.82 230	97.14 277	95.31 208	93.48 436	97.08 349	90.48 305	94.40 253	98.62 231	84.49 277	96.21 388	93.99 245	97.18 205	98.93 238

SSM_0407		95.62 202	94.95 211	97.61 193	97.14 277	95.31 208	99.00 305	97.25 323	90.81 294	94.40 253	98.83 212	84.74 272	98.58 244	95.24 214	97.18 205	98.93 238

SCA		94.69 231	93.81 245	97.33 215	97.10 280	94.44 236	98.86 327	98.32 191	93.30 196	96.17 223	95.59 349	76.48 356	97.95 299	91.06 299	97.43 194	99.59 144

KinetiMVS		96.10 182	95.29 197	98.53 124	97.08 281	97.12 122	99.56 225	98.12 224	94.78 126	98.44 141	98.94 193	80.30 323	99.39 184	91.56 292	98.79 155	99.06 229

TAMVS		95.85 191	95.58 187	96.65 238	97.07 282	93.50 266	99.17 282	97.82 255	91.39 278	95.02 246	98.01 269	92.20 155	97.30 326	93.75 257	95.83 242	99.14 220

Fast-Effi-MVS+-dtu		93.72 265	93.86 244	93.29 352	97.06 283	86.16 393	99.80 158	96.83 378	92.66 224	92.58 279	97.83 280	81.39 305	97.67 310	89.75 324	96.87 217	96.05 307

CostFormer		96.10 182	95.88 178	96.78 232	97.03 284	92.55 291	97.08 401	97.83 254	90.04 318	98.72 126	94.89 386	95.01 62	98.29 275	96.54 195	95.77 243	99.50 170

test_fmvsmvis_n_1920		97.67 104	97.59 95	97.91 168	97.02 285	95.34 206	99.95 66	98.45 137	97.87 24	97.02 195	99.59 118	89.64 198	99.98 47	99.41 63	99.34 131	98.42 262

test-LLR		96.47 166	96.04 164	97.78 178	97.02 285	95.44 198	99.96 47	98.21 208	94.07 163	95.55 236	96.38 321	93.90 103	98.27 279	90.42 314	98.83 153	99.64 130

test-mter		96.39 172	95.93 175	97.78 178	97.02 285	95.44 198	99.96 47	98.21 208	91.81 262	95.55 236	96.38 321	95.17 55	98.27 279	90.42 314	98.83 153	99.64 130

icg_test_0407_2		95.04 218	94.78 218	95.84 264	96.97 288	91.64 316	98.63 349	97.12 339	92.33 242	95.60 234	98.88 198	85.65 257	96.56 372	92.12 280	95.70 248	99.32 198

IMVS_0407		95.21 213	94.80 217	96.46 243	96.97 288	91.64 316	98.81 332	97.12 339	92.33 242	95.60 234	98.88 198	85.65 257	98.42 256	92.12 280	95.70 248	99.32 198

IMVS_0404		93.83 257	93.17 267	95.80 266	96.97 288	91.64 316	97.78 387	97.12 339	92.33 242	90.87 297	98.88 198	76.78 351	96.43 378	92.12 280	95.70 248	99.32 198

IMVS_0403		95.25 211	94.81 216	96.58 240	96.97 288	91.64 316	98.97 312	97.12 339	92.33 242	95.43 239	98.88 198	85.78 256	98.79 221	92.12 280	95.70 248	99.32 198

gm-plane-assit					96.97 288	93.76 258			91.47 272		98.96 186		98.79 221	94.92 222

WB-MVSnew		92.90 284	92.77 276	93.26 354	96.95 293	93.63 262	99.71 191	98.16 218	91.49 269	94.28 258	98.14 265	81.33 307	96.48 375	79.47 409	95.46 255	89.68 435

QAPM		95.40 207	94.17 232	99.10 73	96.92 294	97.71 93	99.40 250	98.68 78	89.31 326	88.94 338	98.89 197	82.48 293	99.96 71	93.12 270	99.83 77	99.62 137

KD-MVS_2432*1600		88.00 372	86.10 376	93.70 343	96.91 295	94.04 250	97.17 398	97.12 339	84.93 394	81.96 405	92.41 419	92.48 148	94.51 421	79.23 410	52.68 454	92.56 405

miper_refine_blended		88.00 372	86.10 376	93.70 343	96.91 295	94.04 250	97.17 398	97.12 339	84.93 394	81.96 405	92.41 419	92.48 148	94.51 421	79.23 410	52.68 454	92.56 405

tpm2		95.47 205	95.18 201	96.35 249	96.91 295	91.70 314	96.96 404	97.93 241	88.04 355	98.44 141	95.40 360	93.32 118	97.97 296	94.00 244	95.61 253	99.38 185

FMVSNet5		88.32 368	87.47 370	90.88 384	96.90 298	88.39 377	97.28 395	95.68 413	82.60 414	84.67 393	92.40 421	79.83 326	91.16 443	76.39 425	81.51 374	93.09 396

3Dnovator+	91.53 11	96.31 176	95.24 198	99.52 28	96.88 299	98.64 54	99.72 188	98.24 204	95.27 114	88.42 351	98.98 182	82.76 292	99.94 88	97.10 179	99.83 77	99.96 70

Patchmatch-test		92.65 292	91.50 303	96.10 255	96.85 300	90.49 342	91.50 444	97.19 328	82.76 413	90.23 303	95.59 349	95.02 61	98.00 295	77.41 420	96.98 215	99.82 101

MVS		96.60 161	95.56 188	99.72 13	96.85 300	99.22 20	98.31 366	98.94 44	91.57 267	90.90 296	99.61 117	86.66 245	99.96 71	97.36 171	99.88 73	99.99 23

3Dnovator	91.47 12	96.28 179	95.34 194	99.08 76	96.82 302	97.47 107	99.45 247	98.81 64	95.52 108	89.39 325	99.00 179	81.97 297	99.95 80	97.27 173	99.83 77	99.84 98

EI-MVSNet		93.73 264	93.40 259	94.74 297	96.80 303	92.69 286	99.06 295	97.67 268	88.96 335	91.39 290	99.02 175	88.75 215	97.30 326	91.07 298	87.85 326	94.22 336

CVMVSNet		94.68 233	94.94 212	93.89 337	96.80 303	86.92 390	99.06 295	98.98 41	94.45 140	94.23 260	99.02 175	85.60 260	95.31 410	90.91 304	95.39 258	99.43 181

IterMVS-LS		92.69 290	92.11 290	94.43 316	96.80 303	92.74 283	99.45 247	96.89 374	88.98 333	89.65 318	95.38 363	88.77 214	96.34 382	90.98 302	82.04 370	94.22 336
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
AstraMVS		96.57 163	96.46 150	96.91 226	96.79 306	92.50 292	99.90 107	97.38 304	96.02 94	97.79 173	99.32 147	86.36 249	98.99 207	98.26 132	96.33 228	99.23 214

IterMVS		90.91 326	90.17 328	93.12 357	96.78 307	90.42 345	98.89 321	97.05 356	89.03 330	86.49 376	95.42 359	76.59 354	95.02 412	87.22 354	84.09 355	93.93 367
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
1314		96.84 146	95.96 172	99.48 35	96.74 308	98.52 58	98.31 366	98.86 56	95.82 97	89.91 309	98.98 182	87.49 230	99.96 71	97.80 158	99.73 87	99.96 70

IterMVS-SCA-FT		90.85 329	90.16 329	92.93 362	96.72 309	89.96 354	98.89 321	96.99 360	88.95 336	86.63 373	95.67 345	76.48 356	95.00 413	87.04 357	84.04 358	93.84 374

MVS-HIRNet		86.22 379	83.19 392	95.31 280	96.71 310	90.29 346	92.12 441	97.33 312	62.85 449	86.82 370	70.37 454	69.37 397	97.49 316	75.12 428	97.99 184	98.15 269

VDDNet		93.12 279	91.91 295	96.76 233	96.67 311	92.65 289	98.69 344	98.21 208	82.81 412	97.75 175	99.28 152	61.57 429	99.48 179	98.09 142	94.09 277	98.15 269

dmvs_re		93.20 276	93.15 268	93.34 350	96.54 312	83.81 408	98.71 341	98.51 125	91.39 278	92.37 282	98.56 239	78.66 338	97.83 304	93.89 248	89.74 298	98.38 264

Elysia		94.50 240	93.38 260	97.85 172	96.49 313	96.70 139	98.98 307	97.78 258	90.81 294	96.19 221	98.55 241	73.63 380	98.98 208	89.41 325	98.56 161	97.88 276

StellarMVS		94.50 240	93.38 260	97.85 172	96.49 313	96.70 139	98.98 307	97.78 258	90.81 294	96.19 221	98.55 241	73.63 380	98.98 208	89.41 325	98.56 161	97.88 276

MIMVSNet		90.30 342	88.67 356	95.17 284	96.45 315	91.64 316	92.39 440	97.15 335	85.99 381	90.50 301	93.19 414	66.95 408	94.86 417	82.01 396	93.43 285	99.01 234

CR-MVSNet		93.45 273	92.62 278	95.94 259	96.29 316	92.66 287	92.01 442	96.23 400	92.62 226	96.94 197	93.31 412	91.04 175	96.03 396	79.23 410	95.96 236	99.13 221

RPMNet		89.76 354	87.28 371	97.19 218	96.29 316	92.66 287	92.01 442	98.31 193	70.19 445	96.94 197	85.87 447	87.25 235	99.78 140	62.69 449	95.96 236	99.13 221

tt0805		91.28 319	90.18 327	94.60 303	96.26 318	87.55 383	98.39 364	98.72 72	89.00 332	89.22 331	98.47 249	62.98 424	98.96 212	90.57 310	88.00 325	97.28 294

Patchmtry		89.70 355	88.49 359	93.33 351	96.24 319	89.94 357	91.37 445	96.23 400	78.22 428	87.69 358	93.31 412	91.04 175	96.03 396	80.18 408	82.10 369	94.02 357

test_vis1_rt		86.87 377	86.05 379	89.34 403	96.12 320	78.07 436	99.87 123	83.54 462	92.03 254	78.21 426	89.51 433	45.80 448	99.91 104	96.25 198	93.11 290	90.03 432

JIA-IIPM		91.76 313	90.70 314	94.94 290	96.11 321	87.51 384	93.16 438	98.13 223	75.79 434	97.58 177	77.68 452	92.84 134	97.97 296	88.47 339	96.54 220	99.33 196

OpenMVS	90.15 15	94.77 228	93.59 249	98.33 139	96.07 322	97.48 106	99.56 225	98.57 101	90.46 307	86.51 375	98.95 191	78.57 339	99.94 88	93.86 249	99.74 86	97.57 289

PAPM		98.60 34	98.42 35	99.14 67	96.05 323	98.96 26	99.90 107	99.35 24	96.68 69	98.35 148	99.66 109	96.45 33	98.51 249	99.45 60	99.89 70	99.96 70

CLD-MVS		94.06 254	93.90 242	94.55 307	96.02 324	90.69 336	99.98 19	97.72 264	96.62 73	91.05 295	98.85 210	77.21 344	98.47 250	98.11 140	89.51 304	94.48 314
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PatchT		90.38 339	88.75 355	95.25 282	95.99 325	90.16 349	91.22 446	97.54 287	76.80 430	97.26 188	86.01 446	91.88 162	96.07 395	66.16 445	95.91 240	99.51 168

ACMH+	89.98 16	90.35 340	89.54 339	92.78 366	95.99 325	86.12 394	98.81 332	97.18 330	89.38 325	83.14 401	97.76 281	68.42 402	98.43 255	89.11 330	86.05 338	93.78 377

DeepMVS_CX				82.92 424	95.98 327	58.66 455		96.01 405	92.72 219	78.34 425	95.51 354	58.29 434	98.08 290	82.57 391	85.29 343	92.03 413

ACMP	92.05 9	92.74 288	92.42 287	93.73 339	95.91 328	88.72 370	99.81 154	97.53 289	94.13 159	87.00 369	98.23 263	74.07 377	98.47 250	96.22 199	88.86 311	93.99 362
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n		93.61 268	93.03 270	95.35 277	95.86 329	86.94 389	99.87 123	96.36 398	96.85 60	99.54 69	98.79 214	52.41 442	99.83 133	98.64 109	98.97 147	99.29 206

HQP-NCC					95.78 330		99.87 123		96.82 62	93.37 267

ACMP_Plane					95.78 330		99.87 123		96.82 62	93.37 267

HQP-MVS		94.61 235	94.50 223	94.92 291	95.78 330	91.85 306	99.87 123	97.89 246	96.82 62	93.37 267	98.65 226	80.65 317	98.39 262	97.92 152	89.60 299	94.53 310

NP-MVS					95.77 333	91.79 308					98.65 226

test_fmvsmconf0.1_n		97.74 98	97.44 102	98.64 109	95.76 334	96.20 167	99.94 83	98.05 230	98.17 11	98.89 114	99.42 135	87.65 225	99.90 106	99.50 56	99.60 102	99.82 101

plane_prior6					95.76 334	91.72 313						80.47 321

ACMM	91.95 10	92.88 285	92.52 285	93.98 333	95.75 336	89.08 367	99.77 165	97.52 291	93.00 206	89.95 308	97.99 272	76.17 360	98.46 253	93.63 261	88.87 310	94.39 322
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GA-MVS		93.83 257	92.84 272	96.80 231	95.73 337	93.57 263	99.88 120	97.24 326	92.57 231	92.92 274	96.66 313	78.73 337	97.67 310	87.75 347	94.06 278	99.17 216

plane_prior1					95.73 337

jason		97.24 124	96.86 129	98.38 138	95.73 337	97.32 111	99.97 37	97.40 303	95.34 112	98.60 135	99.54 127	87.70 224	98.56 246	97.94 151	99.47 118	99.25 211
jason: jason.
mmtdpeth		88.52 366	87.75 368	90.85 386	95.71 340	83.47 413	98.94 315	94.85 428	88.78 341	97.19 190	89.58 432	63.29 422	98.97 210	98.54 114	62.86 448	90.10 431

HQP_MVS		94.49 242	94.36 226	94.87 292	95.71 340	91.74 310	99.84 142	97.87 248	96.38 82	93.01 272	98.59 234	80.47 321	98.37 268	97.79 161	89.55 302	94.52 312

plane_prior7					95.71 340	91.59 322

ITE_SJBPF				92.38 369	95.69 343	85.14 400		95.71 412	92.81 214	89.33 328	98.11 266	70.23 395	98.42 256	85.91 369	88.16 323	93.59 385

fmvsm_s_conf0.1_n_a		97.09 133	96.90 126	97.63 191	95.65 344	94.21 247	99.83 149	98.50 131	96.27 87	99.65 51	99.64 112	84.72 274	99.93 97	99.04 79	98.84 152	98.74 252

ACMH	89.72 17	90.64 333	89.63 336	93.66 345	95.64 345	88.64 373	98.55 352	97.45 296	89.03 330	81.62 408	97.61 282	69.75 396	98.41 258	89.37 327	87.62 330	93.92 368
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline2		96.71 156	96.49 147	97.37 211	95.63 346	95.96 176	99.74 177	98.88 54	92.94 208	91.61 288	98.97 184	97.72 6	98.62 243	94.83 226	98.08 182	97.53 291

FMVSNet1		88.50 367	86.64 374	94.08 326	95.62 347	91.97 301	98.43 360	96.95 366	83.00 410	86.08 383	94.72 388	59.09 433	96.11 391	81.82 398	84.07 356	94.17 340

LuminaMVS		96.63 160	96.21 159	97.87 171	95.58 348	96.82 135	99.12 284	97.67 268	94.47 138	97.88 168	98.31 259	87.50 229	98.71 233	98.07 144	97.29 201	98.10 272

LPG-MVS_test		92.96 282	92.71 277	93.71 341	95.43 349	88.67 371	99.75 174	97.62 276	92.81 214	90.05 304	98.49 245	75.24 367	98.40 260	95.84 205	89.12 306	94.07 354

LGP-MVS_train				93.71 341	95.43 349	88.67 371		97.62 276	92.81 214	90.05 304	98.49 245	75.24 367	98.40 260	95.84 205	89.12 306	94.07 354

tpm		93.70 266	93.41 258	94.58 305	95.36 351	87.41 385	97.01 402	96.90 373	90.85 292	96.72 205	94.14 403	90.40 189	96.84 359	90.75 308	88.54 318	99.51 168

D2MVS		92.76 287	92.59 283	93.27 353	95.13 352	89.54 361	99.69 198	99.38 22	92.26 247	87.59 360	94.61 394	85.05 269	97.79 305	91.59 291	88.01 324	92.47 408

VPA-MVSNet		92.70 289	91.55 302	96.16 253	95.09 353	96.20 167	98.88 323	99.00 39	91.02 289	91.82 287	95.29 370	76.05 362	97.96 298	95.62 210	81.19 376	94.30 329

LTVRE_ROB	88.28 18	90.29 343	89.05 350	94.02 329	95.08 354	90.15 350	97.19 397	97.43 298	84.91 396	83.99 397	97.06 299	74.00 378	98.28 277	84.08 380	87.71 328	93.62 384
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		87.87 374	86.51 375	91.94 375	95.05 355	85.57 398	97.65 389	94.08 438	84.40 400	81.82 407	96.85 308	62.14 427	98.33 271	80.25 407	86.37 337	91.91 415

test0.0.03 1		93.86 256	93.61 246	94.64 301	95.02 356	92.18 299	99.93 90	98.58 99	94.07 163	87.96 355	98.50 244	93.90 103	94.96 414	81.33 399	93.17 288	96.78 297

UniMVSNet (Re)		93.07 281	92.13 289	95.88 261	94.84 357	96.24 166	99.88 120	98.98 41	92.49 236	89.25 329	95.40 360	87.09 237	97.14 335	93.13 269	78.16 400	94.26 331

USDC		90.00 350	88.96 351	93.10 359	94.81 358	88.16 379	98.71 341	95.54 417	93.66 184	83.75 399	97.20 293	65.58 413	98.31 273	83.96 383	87.49 332	92.85 402

VPNet		91.81 307	90.46 318	95.85 263	94.74 359	95.54 195	98.98 307	98.59 97	92.14 249	90.77 300	97.44 286	68.73 400	97.54 315	94.89 225	77.89 402	94.46 315

FIs		94.10 253	93.43 255	96.11 254	94.70 360	96.82 135	99.58 220	98.93 48	92.54 232	89.34 327	97.31 290	87.62 226	97.10 339	94.22 243	86.58 335	94.40 321

UniMVSNet_ETH3D		90.06 349	88.58 358	94.49 311	94.67 361	88.09 380	97.81 386	97.57 284	83.91 403	88.44 347	97.41 287	57.44 435	97.62 312	91.41 293	88.59 317	97.77 281

UniMVSNet_NR-MVSNet		92.95 283	92.11 290	95.49 271	94.61 362	95.28 212	99.83 149	99.08 36	91.49 269	89.21 332	96.86 307	87.14 236	96.73 365	93.20 265	77.52 405	94.46 315

test_fmvs2		89.47 359	89.70 335	88.77 410	94.54 363	75.74 438	99.83 149	94.70 434	94.71 130	91.08 293	96.82 312	54.46 438	97.78 307	92.87 272	88.27 321	92.80 403

MonoMVSNet		94.82 223	94.43 224	95.98 257	94.54 363	90.73 335	99.03 302	97.06 353	93.16 201	93.15 271	95.47 357	88.29 218	97.57 313	97.85 156	91.33 296	99.62 137

WR-MVS		92.31 299	91.25 307	95.48 274	94.45 365	95.29 211	99.60 217	98.68 78	90.10 315	88.07 354	96.89 305	80.68 316	96.80 363	93.14 268	79.67 393	94.36 323

nrg030		93.51 270	92.53 284	96.45 244	94.36 366	97.20 117	99.81 154	97.16 334	91.60 266	89.86 311	97.46 285	86.37 248	97.68 309	95.88 204	80.31 389	94.46 315

tfpnnormal		89.29 362	87.61 369	94.34 319	94.35 367	94.13 249	98.95 314	98.94 44	83.94 401	84.47 394	95.51 354	74.84 372	97.39 318	77.05 423	80.41 387	91.48 418

FC-MVSNet-test		93.81 260	93.15 268	95.80 266	94.30 368	96.20 167	99.42 249	98.89 52	92.33 242	89.03 337	97.27 292	87.39 232	96.83 361	93.20 265	86.48 336	94.36 323

SSC-MVS3.2		89.59 357	88.66 357	92.38 369	94.29 369	86.12 394	99.49 238	97.66 271	90.28 314	88.63 344	95.18 374	64.46 418	96.88 357	85.30 373	82.66 364	94.14 349

MS-PatchMatch		90.65 332	90.30 323	91.71 380	94.22 370	85.50 399	98.24 370	97.70 265	88.67 344	86.42 378	96.37 323	67.82 405	98.03 294	83.62 385	99.62 95	91.60 416

WR-MVS_H		91.30 317	90.35 321	94.15 323	94.17 371	92.62 290	99.17 282	98.94 44	88.87 339	86.48 377	94.46 399	84.36 280	96.61 370	88.19 341	78.51 398	93.21 394

DU-MVS		92.46 296	91.45 305	95.49 271	94.05 372	95.28 212	99.81 154	98.74 71	92.25 248	89.21 332	96.64 315	81.66 302	96.73 365	93.20 265	77.52 405	94.46 315

NR-MVSNet		91.56 315	90.22 325	95.60 269	94.05 372	95.76 183	98.25 369	98.70 74	91.16 283	80.78 414	96.64 315	83.23 290	96.57 371	91.41 293	77.73 404	94.46 315

CP-MVSNet		91.23 321	90.22 325	94.26 321	93.96 374	92.39 295	99.09 288	98.57 101	88.95 336	86.42 378	96.57 318	79.19 332	96.37 380	90.29 317	78.95 395	94.02 357

XXY-MVS		91.82 306	90.46 318	95.88 261	93.91 375	95.40 202	98.87 326	97.69 267	88.63 346	87.87 356	97.08 297	74.38 376	97.89 302	91.66 290	84.07 356	94.35 326

PS-CasMVS		90.63 334	89.51 341	93.99 332	93.83 376	91.70 314	98.98 307	98.52 122	88.48 348	86.15 382	96.53 320	75.46 365	96.31 384	88.83 332	78.86 397	93.95 365

test_0402		85.58 381	83.94 386	90.50 392	93.81 377	85.04 401	98.55 352	95.20 425	76.01 432	79.72 420	95.13 375	64.15 420	96.26 386	66.04 446	86.88 334	90.21 429

XVG-ACMP-BASELINE		91.22 322	90.75 313	92.63 368	93.73 378	85.61 397	98.52 356	97.44 297	92.77 218	89.90 310	96.85 308	66.64 410	98.39 262	92.29 277	88.61 315	93.89 370

TranMVSNet+NR-MVSNet		91.68 314	90.61 317	94.87 292	93.69 379	93.98 253	99.69 198	98.65 82	91.03 288	88.44 347	96.83 311	80.05 325	96.18 389	90.26 318	76.89 413	94.45 320

TransMVSNet (Re)		87.25 375	85.28 382	93.16 356	93.56 380	91.03 327	98.54 354	94.05 440	83.69 405	81.09 412	96.16 329	75.32 366	96.40 379	76.69 424	68.41 436	92.06 412

v10		90.25 344	88.82 353	94.57 306	93.53 381	93.43 268	99.08 290	96.87 376	85.00 393	87.34 367	94.51 395	80.93 312	97.02 349	82.85 390	79.23 394	93.26 392

testgi		89.01 364	88.04 365	91.90 376	93.49 382	84.89 403	99.73 184	95.66 414	93.89 177	85.14 389	98.17 264	59.68 432	94.66 420	77.73 419	88.88 309	96.16 306

v8		90.54 336	89.17 346	94.66 300	93.43 383	93.40 271	99.20 279	96.94 370	85.76 384	87.56 361	94.51 395	81.96 298	97.19 332	84.94 376	78.25 399	93.38 390

V42		91.28 319	90.12 330	94.74 297	93.42 384	93.46 267	99.68 201	97.02 357	87.36 363	89.85 313	95.05 378	81.31 308	97.34 321	87.34 352	80.07 391	93.40 388

pm-mvs1		89.36 361	87.81 367	94.01 330	93.40 385	91.93 304	98.62 350	96.48 396	86.25 379	83.86 398	96.14 331	73.68 379	97.04 345	86.16 366	75.73 418	93.04 398

v1144		91.09 323	89.83 332	94.87 292	93.25 386	93.69 261	99.62 212	96.98 362	86.83 373	89.64 319	94.99 383	80.94 311	97.05 342	85.08 375	81.16 377	93.87 372

v1192		90.62 335	89.25 345	94.72 299	93.13 387	93.07 275	99.50 236	97.02 357	86.33 378	89.56 323	95.01 380	79.22 331	97.09 341	82.34 394	81.16 377	94.01 359

v2v482		91.30 317	90.07 331	95.01 287	93.13 387	93.79 256	99.77 165	97.02 357	88.05 354	89.25 329	95.37 364	80.73 315	97.15 334	87.28 353	80.04 392	94.09 353

OPM-MVS		93.21 275	92.80 274	94.44 314	93.12 389	90.85 334	99.77 165	97.61 279	96.19 90	91.56 289	98.65 226	75.16 371	98.47 250	93.78 256	89.39 305	93.99 362
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v144192		90.79 330	89.52 340	94.59 304	93.11 390	92.77 281	99.56 225	96.99 360	86.38 377	89.82 314	94.95 385	80.50 320	97.10 339	83.98 382	80.41 387	93.90 369

PEN-MVS		90.19 346	89.06 349	93.57 346	93.06 391	90.90 332	99.06 295	98.47 134	88.11 353	85.91 384	96.30 325	76.67 352	95.94 399	87.07 356	76.91 412	93.89 370

v1240		90.20 345	88.79 354	94.44 314	93.05 392	92.27 297	99.38 256	96.92 372	85.89 382	89.36 326	94.87 387	77.89 343	97.03 347	80.66 403	81.08 380	94.01 359

v148		90.70 331	89.63 336	93.92 334	92.97 393	90.97 328	99.75 174	96.89 374	87.51 360	88.27 352	95.01 380	81.67 301	97.04 345	87.40 351	77.17 410	93.75 378

v1921920		90.46 337	89.12 347	94.50 310	92.96 394	92.46 293	99.49 238	96.98 362	86.10 380	89.61 321	95.30 367	78.55 340	97.03 347	82.17 395	80.89 385	94.01 359

MVStest1		85.03 387	82.76 396	91.83 377	92.95 395	89.16 366	98.57 351	94.82 429	71.68 443	68.54 446	95.11 377	83.17 291	95.66 403	74.69 429	65.32 443	90.65 425

tt0320-xc		82.94 401	80.35 408	90.72 390	92.90 396	83.54 411	96.85 407	94.73 432	63.12 448	79.85 419	93.77 407	49.43 446	95.46 406	80.98 402	71.54 427	93.16 395

Baseline_NR-MVSNet		90.33 341	89.51 341	92.81 365	92.84 397	89.95 355	99.77 165	93.94 441	84.69 398	89.04 336	95.66 346	81.66 302	96.52 373	90.99 301	76.98 411	91.97 414

test_method		80.79 406	79.70 410	84.08 421	92.83 398	67.06 447	99.51 234	95.42 419	54.34 453	81.07 413	93.53 409	44.48 449	92.22 440	78.90 414	77.23 409	92.94 400

pmmvs4		92.10 303	91.07 311	95.18 283	92.82 399	94.96 223	99.48 241	96.83 378	87.45 362	88.66 343	96.56 319	83.78 285	96.83 361	89.29 328	84.77 350	93.75 378

LF4IMVS		89.25 363	88.85 352	90.45 394	92.81 400	81.19 428	98.12 376	94.79 430	91.44 273	86.29 380	97.11 295	65.30 416	98.11 288	88.53 337	85.25 344	92.07 411

tt0320		83.56 400	81.15 403	90.77 388	92.77 401	83.58 410	96.83 408	95.52 418	63.26 447	81.36 410	92.54 417	53.26 440	95.77 401	80.45 404	74.38 421	92.96 399

DTE-MVSNet		89.40 360	88.24 363	92.88 363	92.66 402	89.95 355	99.10 287	98.22 207	87.29 364	85.12 390	96.22 327	76.27 359	95.30 411	83.56 386	75.74 417	93.41 387

EU-MVSNet		90.14 348	90.34 322	89.54 402	92.55 403	81.06 429	98.69 344	98.04 231	91.41 277	86.59 374	96.84 310	80.83 314	93.31 433	86.20 365	81.91 371	94.26 331

APD_test1		81.15 405	80.92 405	81.86 425	92.45 404	59.76 454	96.04 422	93.61 444	73.29 441	77.06 429	96.64 315	44.28 450	96.16 390	72.35 433	82.52 365	89.67 436

sc_t1		85.01 388	82.46 398	92.67 367	92.44 405	83.09 414	97.39 393	95.72 411	65.06 446	85.64 387	96.16 329	49.50 445	97.34 321	84.86 377	75.39 419	97.57 289

our_test_3		90.39 338	89.48 343	93.12 357	92.40 406	89.57 360	99.33 263	96.35 399	87.84 358	85.30 388	94.99 383	84.14 283	96.09 394	80.38 405	84.56 351	93.71 383

ppachtmachnet_test		89.58 358	88.35 361	93.25 355	92.40 406	90.44 344	99.33 263	96.73 385	85.49 389	85.90 385	95.77 340	81.09 310	96.00 398	76.00 427	82.49 366	93.30 391

v7n		89.65 356	88.29 362	93.72 340	92.22 408	90.56 341	99.07 294	97.10 345	85.42 391	86.73 371	94.72 388	80.06 324	97.13 336	81.14 400	78.12 401	93.49 386

dmvs_testset		83.79 397	86.07 378	76.94 429	92.14 409	48.60 464	96.75 409	90.27 454	89.48 324	78.65 423	98.55 241	79.25 330	86.65 452	66.85 443	82.69 363	95.57 308

PS-MVSNAJss		93.64 267	93.31 264	94.61 302	92.11 410	92.19 298	99.12 284	97.38 304	92.51 235	88.45 346	96.99 303	91.20 170	97.29 329	94.36 237	87.71 328	94.36 323

pmmvs5		90.17 347	89.09 348	93.40 349	92.10 411	89.77 358	99.74 177	95.58 416	85.88 383	87.24 368	95.74 341	73.41 382	96.48 375	88.54 336	83.56 360	93.95 365

N_pmnet		80.06 409	80.78 406	77.89 428	91.94 412	45.28 466	98.80 335	56.82 468	78.10 429	80.08 417	93.33 410	77.03 346	95.76 402	68.14 441	82.81 362	92.64 404

test_djsdf		92.83 286	92.29 288	94.47 312	91.90 413	92.46 293	99.55 228	97.27 321	91.17 281	89.96 307	96.07 335	81.10 309	96.89 355	94.67 232	88.91 308	94.05 356

SixPastTwentyTwo		88.73 365	88.01 366	90.88 384	91.85 414	82.24 420	98.22 373	95.18 426	88.97 334	82.26 404	96.89 305	71.75 387	96.67 368	84.00 381	82.98 361	93.72 382

K. test v3		88.05 371	87.24 372	90.47 393	91.82 415	82.23 421	98.96 313	97.42 300	89.05 329	76.93 431	95.60 348	68.49 401	95.42 407	85.87 370	81.01 383	93.75 378

OurMVSNet-221017-0		89.81 353	89.48 343	90.83 387	91.64 416	81.21 427	98.17 375	95.38 421	91.48 271	85.65 386	97.31 290	72.66 383	97.29 329	88.15 342	84.83 349	93.97 364

mvs_tets		91.81 307	91.08 310	94.00 331	91.63 417	90.58 340	98.67 346	97.43 298	92.43 237	87.37 366	97.05 300	71.76 386	97.32 324	94.75 229	88.68 314	94.11 352

Gipuma		66.95 422	65.00 422	72.79 434	91.52 418	67.96 446	66.16 457	95.15 427	47.89 455	58.54 452	67.99 457	29.74 454	87.54 451	50.20 456	77.83 403	62.87 457
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_fmvsmconf0.01_n		96.39 172	95.74 181	98.32 140	91.47 419	95.56 194	99.84 142	97.30 316	97.74 28	97.89 167	99.35 146	79.62 327	99.85 123	99.25 69	99.24 135	99.55 154

jajsoiax		91.92 305	91.18 308	94.15 323	91.35 420	90.95 331	99.00 305	97.42 300	92.61 227	87.38 365	97.08 297	72.46 384	97.36 319	94.53 235	88.77 312	94.13 351

MDA-MVSNet-bldmvs		84.09 395	81.52 402	91.81 378	91.32 421	88.00 382	98.67 346	95.92 407	80.22 423	55.60 455	93.32 411	68.29 403	93.60 431	73.76 430	76.61 414	93.82 376

MVP-Stereo		90.93 325	90.45 320	92.37 371	91.25 422	88.76 368	98.05 380	96.17 402	87.27 365	84.04 395	95.30 367	78.46 341	97.27 331	83.78 384	99.70 89	91.09 419
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MDA-MVSNet_test_wron		85.51 383	83.32 391	92.10 373	90.96 423	88.58 374	99.20 279	96.52 394	79.70 425	57.12 454	92.69 416	79.11 333	93.86 427	77.10 422	77.46 407	93.86 373

YYNet1		85.50 384	83.33 390	92.00 374	90.89 424	88.38 378	99.22 278	96.55 393	79.60 426	57.26 453	92.72 415	79.09 335	93.78 429	77.25 421	77.37 408	93.84 374

anonymousdsp		91.79 312	90.92 312	94.41 317	90.76 425	92.93 280	98.93 317	97.17 332	89.08 328	87.46 364	95.30 367	78.43 342	96.92 353	92.38 276	88.73 313	93.39 389

lessismore_v0				90.53 391	90.58 426	80.90 430		95.80 408		77.01 430	95.84 338	66.15 412	96.95 351	83.03 389	75.05 420	93.74 381

EG-PatchMatch MVS		85.35 385	83.81 388	89.99 400	90.39 427	81.89 423	98.21 374	96.09 404	81.78 417	74.73 437	93.72 408	51.56 444	97.12 338	79.16 413	88.61 315	90.96 422

EGC-MVSNET		69.38 415	63.76 425	86.26 418	90.32 428	81.66 426	96.24 418	93.85 442	0.99 465	3.22 466	92.33 422	52.44 441	92.92 436	59.53 452	84.90 348	84.21 446

CMPMVS	61.59 21	84.75 391	85.14 383	83.57 422	90.32 428	62.54 450	96.98 403	97.59 283	74.33 439	69.95 443	96.66 313	64.17 419	98.32 272	87.88 346	88.41 320	89.84 434
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
new_pmnet		84.49 394	82.92 394	89.21 404	90.03 430	82.60 417	96.89 406	95.62 415	80.59 421	75.77 436	89.17 434	65.04 417	94.79 418	72.12 434	81.02 382	90.23 428

pmmvs6		85.69 380	83.84 387	91.26 383	90.00 431	84.41 406	97.82 385	96.15 403	75.86 433	81.29 411	95.39 362	61.21 430	96.87 358	83.52 387	73.29 423	92.50 407

ttmdpeth		88.23 370	87.06 373	91.75 379	89.91 432	87.35 386	98.92 320	95.73 410	87.92 356	84.02 396	96.31 324	68.23 404	96.84 359	86.33 364	76.12 415	91.06 420

DSMNet-mixed		88.28 369	88.24 363	88.42 412	89.64 433	75.38 440	98.06 379	89.86 455	85.59 388	88.20 353	92.14 423	76.15 361	91.95 441	78.46 416	96.05 233	97.92 275

UnsupCasMVSNet_eth		85.52 382	83.99 384	90.10 398	89.36 434	83.51 412	96.65 410	97.99 234	89.14 327	75.89 435	93.83 405	63.25 423	93.92 425	81.92 397	67.90 439	92.88 401

Anonymous20231206		86.32 378	85.42 381	89.02 406	89.11 435	80.53 433	99.05 299	95.28 422	85.43 390	82.82 402	93.92 404	74.40 375	93.44 432	66.99 442	81.83 372	93.08 397

Anonymous20240521		85.15 386	83.81 388	89.16 405	88.32 436	82.69 416	98.80 335	95.74 409	79.72 424	81.53 409	90.99 426	65.38 415	94.16 423	72.69 432	81.11 379	90.63 426

OpenMVS_ROB	79.82 20	83.77 398	81.68 401	90.03 399	88.30 437	82.82 415	98.46 357	95.22 424	73.92 440	76.00 434	91.29 425	55.00 437	96.94 352	68.40 440	88.51 319	90.34 427

test20.03		84.72 392	83.99 384	86.91 416	88.19 438	80.62 432	98.88 323	95.94 406	88.36 350	78.87 421	94.62 393	68.75 399	89.11 447	66.52 444	75.82 416	91.00 421

KD-MVS_self_test		83.59 399	82.06 399	88.20 413	86.93 439	80.70 431	97.21 396	96.38 397	82.87 411	82.49 403	88.97 435	67.63 406	92.32 439	73.75 431	62.30 450	91.58 417

MIMVSNet1		82.58 402	80.51 407	88.78 408	86.68 440	84.20 407	96.65 410	95.41 420	78.75 427	78.59 424	92.44 418	51.88 443	89.76 446	65.26 447	78.95 395	92.38 410

CL-MVSNet_self_test		84.50 393	83.15 393	88.53 411	86.00 441	81.79 424	98.82 331	97.35 308	85.12 392	83.62 400	90.91 428	76.66 353	91.40 442	69.53 438	60.36 451	92.40 409

UnsupCasMVSNet_bld		79.97 411	77.03 416	88.78 408	85.62 442	81.98 422	93.66 434	97.35 308	75.51 436	70.79 442	83.05 449	48.70 447	94.91 416	78.31 417	60.29 452	89.46 439

mvs5depth		84.87 389	82.90 395	90.77 388	85.59 443	84.84 404	91.10 447	93.29 446	83.14 408	85.07 391	94.33 401	62.17 426	97.32 324	78.83 415	72.59 426	90.14 430

Patchmatch-RL test		86.90 376	85.98 380	89.67 401	84.45 444	75.59 439	89.71 450	92.43 448	86.89 372	77.83 428	90.94 427	94.22 92	93.63 430	87.75 347	69.61 431	99.79 106

pmmvs-eth3d		84.03 396	81.97 400	90.20 397	84.15 445	87.09 388	98.10 378	94.73 432	83.05 409	74.10 439	87.77 441	65.56 414	94.01 424	81.08 401	69.24 433	89.49 438

test_fmvs3		79.99 410	80.17 409	79.45 427	84.02 446	62.83 448	99.05 299	93.49 445	88.29 352	80.06 418	86.65 444	28.09 456	88.00 448	88.63 333	73.27 424	87.54 444

PM-MVS		80.47 407	78.88 412	85.26 419	83.79 447	72.22 442	95.89 425	91.08 452	85.71 387	76.56 433	88.30 437	36.64 452	93.90 426	82.39 393	69.57 432	89.66 437

new-patchmatchnet		81.19 404	79.34 411	86.76 417	82.86 448	80.36 434	97.92 382	95.27 423	82.09 416	72.02 440	86.87 443	62.81 425	90.74 445	71.10 435	63.08 447	89.19 441

mvsany_test3		82.12 403	81.14 404	85.06 420	81.87 449	70.41 444	97.09 400	92.14 449	91.27 280	77.84 427	88.73 436	39.31 451	95.49 404	90.75 308	71.24 428	89.29 440

WB-MVS		76.28 413	77.28 415	73.29 433	81.18 450	54.68 458	97.87 384	94.19 437	81.30 418	69.43 444	90.70 429	77.02 347	82.06 456	35.71 461	68.11 438	83.13 447

test_f		78.40 412	77.59 414	80.81 426	80.82 451	62.48 451	96.96 404	93.08 447	83.44 406	74.57 438	84.57 448	27.95 457	92.63 437	84.15 379	72.79 425	87.32 445

SSC-MVS		75.42 414	76.40 417	72.49 437	80.68 452	53.62 459	97.42 391	94.06 439	80.42 422	68.75 445	90.14 431	76.54 355	81.66 457	33.25 462	66.34 442	82.19 448

pmmvs3		80.27 408	77.77 413	87.76 415	80.32 453	82.43 419	98.23 372	91.97 450	72.74 442	78.75 422	87.97 440	57.30 436	90.99 444	70.31 436	62.37 449	89.87 433

testf1		68.38 418	66.92 419	72.78 435	78.80 454	50.36 461	90.95 448	87.35 460	55.47 451	58.95 450	88.14 438	20.64 461	87.60 449	57.28 453	64.69 444	80.39 450

APD_test2		68.38 418	66.92 419	72.78 435	78.80 454	50.36 461	90.95 448	87.35 460	55.47 451	58.95 450	88.14 438	20.64 461	87.60 449	57.28 453	64.69 444	80.39 450

ambc				83.23 423	77.17 456	62.61 449	87.38 452	94.55 436		76.72 432	86.65 444	30.16 453	96.36 381	84.85 378	69.86 430	90.73 424

test_vis3_rt		68.82 416	66.69 421	75.21 432	76.24 457	60.41 453	96.44 413	68.71 467	75.13 437	50.54 458	69.52 456	16.42 466	96.32 383	80.27 406	66.92 441	68.89 454

TDRefinement		84.76 390	82.56 397	91.38 382	74.58 458	84.80 405	97.36 394	94.56 435	84.73 397	80.21 416	96.12 334	63.56 421	98.39 262	87.92 345	63.97 446	90.95 423

E-PMN		52.30 426	52.18 428	52.67 443	71.51 459	45.40 465	93.62 435	76.60 465	36.01 459	43.50 460	64.13 459	27.11 458	67.31 462	31.06 463	26.06 458	45.30 461

EMVS		51.44 428	51.22 430	52.11 444	70.71 460	44.97 467	94.04 431	75.66 466	35.34 461	42.40 461	61.56 462	28.93 455	65.87 463	27.64 464	24.73 459	45.49 460

PMMVS2		67.15 421	64.15 424	76.14 431	70.56 461	62.07 452	93.89 432	87.52 459	58.09 450	60.02 449	78.32 451	22.38 460	84.54 454	59.56 451	47.03 456	81.80 449

FPMVS		68.72 417	68.72 418	68.71 439	65.95 462	44.27 468	95.97 424	94.74 431	51.13 454	53.26 456	90.50 430	25.11 459	83.00 455	60.80 450	80.97 384	78.87 452

wuyk23d		20.37 432	20.84 435	18.99 447	65.34 463	27.73 470	50.43 458	7.67 471	9.50 464	8.01 465	6.34 465	6.13 469	26.24 464	23.40 465	10.69 463	2.99 462

LCM-MVSNet		67.77 420	64.73 423	76.87 430	62.95 464	56.25 457	89.37 451	93.74 443	44.53 456	61.99 448	80.74 450	20.42 463	86.53 453	69.37 439	59.50 453	87.84 442

MVE	53.74 22	51.54 427	47.86 431	62.60 441	59.56 465	50.93 460	79.41 455	77.69 464	35.69 460	36.27 462	61.76 461	5.79 470	69.63 460	37.97 460	36.61 457	67.24 455
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		56.10 424	52.24 427	67.66 440	49.27 466	56.82 456	83.94 453	82.02 463	70.47 444	33.28 463	64.54 458	17.23 465	69.16 461	45.59 458	23.85 460	77.02 453

tmp_tt		65.23 423	62.94 426	72.13 438	44.90 467	50.03 463	81.05 454	89.42 458	38.45 457	48.51 459	99.90 18	54.09 439	78.70 459	91.84 289	18.26 461	87.64 443

PMVS	49.05 23	53.75 425	51.34 429	60.97 442	40.80 468	34.68 469	74.82 456	89.62 457	37.55 458	28.67 464	72.12 453	7.09 468	81.63 458	43.17 459	68.21 437	66.59 456
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test123		37.68 430	39.14 433	33.31 445	19.94 469	24.83 471	98.36 365	9.75 470	15.53 463	51.31 457	87.14 442	19.62 464	17.74 465	47.10 457	3.47 464	57.36 458

testmvs		40.60 429	44.45 432	29.05 446	19.49 470	14.11 472	99.68 201	18.47 469	20.74 462	64.59 447	98.48 248	10.95 467	17.09 466	56.66 455	11.01 462	55.94 459

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

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

test_blank		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.02 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

eth-test2					0.00 471

eth-test					0.00 471

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

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

cdsmvs_eth3d_5k		23.43 431	31.24 434	0.00 448	0.00 471	0.00 473	0.00 459	98.09 225	0.00 466	0.00 467	99.67 107	83.37 288	0.00 467	0.00 466	0.00 465	0.00 463

pcd_1.5k_mvsjas		7.60 434	10.13 437	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 467	91.20 170	0.00 467	0.00 466	0.00 465	0.00 463

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

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

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

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

ab-mvs-re		8.28 433	11.04 436	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	99.40 140	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

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

WAC-MVS						90.97 328								86.10 368

PC_three_1452									96.96 58	99.80 24	99.79 58	97.49 10	100.00 1	99.99 5	99.98 32	100.00 1

test_241102_TWO								98.43 150	97.27 45	99.80 24	99.94 4	97.18 21	100.00 1	100.00 1	100.00 1	100.00 1

test_0728_THIRD									96.48 76	99.83 20	99.91 14	97.87 5	100.00 1	99.92 13	100.00 1	100.00 1

GSMVS																99.59 144

sam_mvs1												94.72 71				99.59 144

sam_mvs												94.25 91

MTGPA								98.28 198

test_post1							95.78 426				59.23 463	93.20 125	97.74 308	91.06 299

test_post											63.35 460	94.43 79	98.13 287

patchmatchnet-post											91.70 424	95.12 56	97.95 299

MTMP							99.87 123	96.49 395

test9_res														99.71 43	99.99 21	100.00 1

agg_prior2														99.48 58	100.00 1	100.00 1

test_prior4						98.05 77	99.94 83

test_prior2							99.95 66		95.78 98	99.73 43	99.76 67	96.00 37		99.78 31	100.00 1

旧先验2							99.46 246		94.21 158	99.85 16			99.95 80	96.96 185

新几何2							99.40 250

无先验							99.49 238	98.71 73	93.46 190				100.00 1	94.36 237		99.99 23

原ACMM2							99.90 107

testdata2													99.99 36	90.54 312

segment_acmp												96.68 29

testdata1							99.28 272		96.35 86

plane_prior5								97.87 248					98.37 268	97.79 161	89.55 302	94.52 312

plane_prior4											98.59 234

plane_prior3						91.64 316			96.63 71	93.01 272

plane_prior2							99.84 142		96.38 82

plane_prior						91.74 310	99.86 134		96.76 66						89.59 301

n2								0.00 472

nn								0.00 472

door-mid								89.69 456

test11								98.44 142

door								90.31 453

HQP5-MVS						91.85 306

BP-MVS														97.92 152

HQP4-MVS										93.37 267			98.39 262			94.53 310

HQP3-MVS								97.89 246							89.60 299

HQP2-MVS												80.65 317

MDTV_nov1_ep13_2view						96.26 161	96.11 420		91.89 257	98.06 160		94.40 81		94.30 240		99.67 124

ACMMP++_ref															87.04 333

ACMMP++															88.23 322

Test By Simon												92.82 136

High-resolution multi-view benchmark