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.

DeepPCF-MVS	95.94 2	97.71 82	98.98 10	93.92 258	99.63 84	81.76 327	99.96 23	98.56 76	99.47 1	99.19 70	99.99 1	94.16 86	100.00 1	99.92 9	99.93 62	100.00 1

CNVR-MVS		99.40 1	99.26 1	99.84 4	99.98 2	99.51 4	99.98 8	98.69 54	98.20 3	99.93 1	99.98 2	96.82 19	100.00 1	99.75 22	100.00 1	99.99 20

NCCC		99.37 2	99.25 2	99.71 10	99.96 8	99.15 16	99.97 16	98.62 66	98.02 6	99.90 2	99.95 3	97.33 13	100.00 1	99.54 32	100.00 1	100.00 1

SED-MVS		99.28 5	99.11 6	99.77 6	99.93 26	99.30 8	99.96 23	98.43 112	97.27 20	99.80 16	99.94 4	96.71 20	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_TWO								98.43 112	97.27 20	99.80 16	99.94 4	97.18 17	100.00 1	100.00 1	100.00 1	100.00 1

test0726					99.93 26	99.29 10	99.96 23	98.42 123	97.28 18	99.86 4	99.94 4	97.22 15

DPM-MVS		98.83 21	98.46 30	99.97 1	99.33 102	99.92 1	99.96 23	98.44 104	97.96 7	99.55 42	99.94 4	97.18 17	100.00 1	93.81 182	99.94 56	99.98 51

SMA-MVS		98.76 26	98.48 29	99.62 15	99.87 50	98.87 27	99.86 98	98.38 136	93.19 144	99.77 23	99.94 4	95.54 40	100.00 1	99.74 24	99.99 20	100.00 1

DPE-MVS		99.26 6	99.10 7	99.74 7	99.89 44	99.24 14	99.87 87	98.44 104	97.48 15	99.64 34	99.94 4	96.68 22	99.99 36	99.99 5	100.00 1	99.99 20

MSLP-MVS++		99.13 7	99.01 9	99.49 31	99.94 14	98.46 58	99.98 8	98.86 44	97.10 25	99.80 16	99.94 4	95.92 33	100.00 1	99.51 33	100.00 1	100.00 1

ETH3 D test6400		98.81 22	98.54 26	99.59 18	99.93 26	98.93 22	99.93 61	98.46 101	94.56 92	99.84 8	99.92 11	94.32 79	99.86 90	99.96 8	99.98 33	100.00 1

MCST-MVS		99.32 3	99.14 4	99.86 3	99.97 3	99.59 3	99.97 16	98.64 62	98.47 2	99.13 72	99.92 11	96.38 26	100.00 1	99.74 24	100.00 1	100.00 1

MSP-MVS		99.30 4	99.16 3	99.73 8	99.93 26	99.29 10	99.95 40	98.32 147	97.28 18	99.83 10	99.91 13	97.22 15	100.00 1	99.99 5	100.00 1	99.89 87

test_0728_THIRD									96.48 40	99.83 10	99.91 13	97.87 4	100.00 1	99.92 9	100.00 1	100.00 1

SteuartSystems-ACMMP		99.02 11	98.97 11	99.18 54	98.72 132	97.71 82	99.98 8	98.44 104	96.85 29	99.80 16	99.91 13	97.57 6	99.85 94	99.44 37	99.99 20	99.99 20
Skip Steuart: Steuart Systems R&D Blog.
DeepC-MVS_fast	96.59 1	98.81 22	98.54 26	99.62 15	99.90 41	98.85 29	99.24 209	98.47 99	98.14 4	99.08 73	99.91 13	93.09 113	100.00 1	99.04 52	99.99 20	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
ETH3D-3000-0.1		98.68 29	98.42 31	99.47 34	99.83 61	98.57 51	99.90 73	98.37 139	93.81 126	99.81 12	99.90 17	94.34 75	99.86 90	99.84 13	99.98 33	99.97 62

tmp_tt		65.23 314	62.94 316	72.13 327	44.90 352	50.03 348	81.05 343	89.42 348	38.45 344	48.51 346	99.90 17	54.09 338	78.70 346	91.84 211	18.26 347	87.64 338

xxxxxxxxxxxxxcwj		98.98 14	98.79 15	99.54 23	99.82 63	98.79 33	99.96 23	97.52 227	97.66 10	99.81 12	99.89 19	94.70 64	99.86 90	99.84 13	99.93 62	99.96 67

SF-MVS		98.67 30	98.40 35	99.50 29	99.77 69	98.67 44	99.90 73	98.21 160	93.53 135	99.81 12	99.89 19	94.70 64	99.86 90	99.84 13	99.93 62	99.96 67

9.14			98.38 38		99.87 50		99.91 69	98.33 145	93.22 143	99.78 22	99.89 19	94.57 67	99.85 94	99.84 13	99.97 44

test_241102_ONE					99.93 26	99.30 8		98.43 112	97.26 22	99.80 16	99.88 22	96.71 20	100.00 1

DVP-MVS		99.09 8	99.12 5	98.98 80	99.93 26	97.24 102	99.95 40	98.42 123	97.50 14	99.52 47	99.88 22	97.43 12	99.71 124	99.50 34	99.98 33	100.00 1

zzz-MVS		98.33 54	98.00 59	99.30 47	99.85 53	97.93 77	99.80 119	98.28 151	95.76 60	97.18 133	99.88 22	92.74 120	100.00 1	98.67 73	99.88 72	99.99 20

MTAPA		98.29 56	97.96 64	99.30 47	99.85 53	97.93 77	99.39 192	98.28 151	95.76 60	97.18 133	99.88 22	92.74 120	100.00 1	98.67 73	99.88 72	99.99 20

ETH3D cwj APD-0.16		98.40 51	98.07 56	99.40 41	99.59 86	98.41 59	99.86 98	98.24 156	92.18 181	99.73 26	99.87 26	93.47 102	99.85 94	99.74 24	99.95 50	99.93 78

CDPH-MVS		98.65 31	98.36 42	99.49 31	99.94 14	98.73 41	99.87 87	98.33 145	93.97 118	99.76 24	99.87 26	94.99 57	99.75 116	98.55 80	100.00 1	99.98 51

CP-MVS		98.45 46	98.32 44	98.87 86	99.96 8	96.62 122	99.97 16	98.39 132	94.43 97	98.90 82	99.87 26	94.30 80	100.00 1	99.04 52	99.99 20	99.99 20

xiu_mvs_v2_base		98.23 61	97.97 61	99.02 77	98.69 133	98.66 46	99.52 174	98.08 177	97.05 26	99.86 4	99.86 29	90.65 154	99.71 124	99.39 40	98.63 124	98.69 196

TEST9					99.92 35	98.92 23	99.96 23	98.43 112	93.90 123	99.71 30	99.86 29	95.88 34	99.85 94

train_agg		98.88 19	98.65 20	99.59 18	99.92 35	98.92 23	99.96 23	98.43 112	94.35 100	99.71 30	99.86 29	95.94 31	99.85 94	99.69 30	99.98 33	99.99 20

LS3D		95.84 142	95.11 151	98.02 134	99.85 53	95.10 173	98.74 254	98.50 97	87.22 272	93.66 190	99.86 29	87.45 187	99.95 60	90.94 224	99.81 83	99.02 184

MP-MVS-pluss		98.07 66	97.64 72	99.38 44	99.74 73	98.41 59	99.74 134	98.18 165	93.35 139	96.45 150	99.85 33	92.64 123	99.97 51	98.91 61	99.89 70	99.77 101
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
test_8					99.92 35	98.88 26	99.96 23	98.43 112	94.35 100	99.69 32	99.85 33	95.94 31	99.85 94

agg_prior1		98.88 19	98.66 19	99.54 23	99.93 26	98.77 36	99.96 23	98.43 112	94.63 91	99.63 35	99.85 33	95.79 37	99.85 94	99.72 28	99.99 20	99.99 20

HFP-MVS		98.56 37	98.37 40	99.14 63	99.96 8	97.43 97	99.95 40	98.61 68	94.77 85	99.31 61	99.85 33	94.22 82	100.00 1	98.70 71	99.98 33	99.98 51

region2R		98.54 39	98.37 40	99.05 73	99.96 8	97.18 105	99.96 23	98.55 80	94.87 83	99.45 50	99.85 33	94.07 88	100.00 1	98.67 73	100.00 1	99.98 51

PS-MVSNAJ		98.44 47	98.20 49	99.16 59	98.80 129	98.92 23	99.54 172	98.17 166	97.34 16	99.85 6	99.85 33	91.20 144	99.89 79	99.41 39	99.67 91	98.69 196

#test#		98.59 35	98.41 33	99.14 63	99.96 8	97.43 97	99.95 40	98.61 68	95.00 79	99.31 61	99.85 33	94.22 82	100.00 1	98.78 68	99.98 33	99.98 51

HPM-MVS++		99.07 9	98.88 13	99.63 12	99.90 41	99.02 19	99.95 40	98.56 76	97.56 13	99.44 51	99.85 33	95.38 45	100.00 1	99.31 41	99.99 20	99.87 90

旧先验1					99.76 70	97.52 90		98.64 62			99.85 33	95.63 39			99.94 56	99.99 20

原ACMM1				98.96 82	99.73 77	96.99 112		98.51 93	94.06 114	99.62 37	99.85 33	94.97 58	99.96 53	95.11 149	99.95 50	99.92 84

testdata				98.42 117	99.47 96	95.33 165		98.56 76	93.78 128	99.79 21	99.85 33	93.64 100	99.94 68	94.97 151	99.94 56	100.00 1

APDe-MVS		99.06 10	98.91 12	99.51 28	99.94 14	98.76 40	99.91 69	98.39 132	97.20 24	99.46 49	99.85 33	95.53 42	99.79 108	99.86 12	100.00 1	99.99 20

API-MVS		97.86 72	97.66 71	98.47 112	99.52 92	95.41 163	99.47 182	98.87 43	91.68 195	98.84 83	99.85 33	92.34 128	99.99 36	98.44 83	99.96 47	100.00 1

testtj		98.89 18	98.69 18	99.52 26	99.94 14	98.56 52	99.90 73	98.55 80	95.14 77	99.72 29	99.84 46	95.46 43	100.00 1	99.65 31	99.99 20	99.99 20

ACMMPR		98.50 42	98.32 44	99.05 73	99.96 8	97.18 105	99.95 40	98.60 70	94.77 85	99.31 61	99.84 46	93.73 97	100.00 1	98.70 71	99.98 33	99.98 51

DP-MVS Recon		98.41 49	98.02 58	99.56 21	99.97 3	98.70 43	99.92 65	98.44 104	92.06 186	98.40 104	99.84 46	95.68 38	100.00 1	98.19 89	99.71 89	99.97 62

ACMMP_NAP		98.49 43	98.14 52	99.54 23	99.66 83	98.62 50	99.85 101	98.37 139	94.68 89	99.53 44	99.83 49	92.87 116	100.00 1	98.66 76	99.84 76	99.99 20

test222					99.55 90	97.41 100	99.34 198	98.55 80	91.86 190	99.27 65	99.83 49	93.84 95			99.95 50	99.99 20

1121		98.03 67	97.57 76	99.40 41	99.74 73	98.21 65	98.31 277	98.62 66	92.78 156	99.53 44	99.83 49	95.08 50	100.00 1	94.36 169	99.92 66	99.99 20

ZNCC-MVS		98.31 55	98.03 57	99.17 57	99.88 48	97.59 86	99.94 55	98.44 104	94.31 103	98.50 99	99.82 52	93.06 114	99.99 36	98.30 88	99.99 20	99.93 78

新几何1				99.42 38	99.75 72	98.27 64		98.63 65	92.69 161	99.55 42	99.82 52	94.40 70	100.00 1	91.21 216	99.94 56	99.99 20

CSCG		97.10 100	97.04 93	97.27 162	99.89 44	91.92 238	99.90 73	99.07 31	88.67 252	95.26 172	99.82 52	93.17 112	99.98 42	98.15 92	99.47 105	99.90 86

MAR-MVS		97.43 87	97.19 87	98.15 130	99.47 96	94.79 181	99.05 229	98.76 50	92.65 164	98.66 92	99.82 52	88.52 180	99.98 42	98.12 93	99.63 93	99.67 114
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
MP-MVS		98.23 61	97.97 61	99.03 75	99.94 14	97.17 108	99.95 40	98.39 132	94.70 88	98.26 111	99.81 56	91.84 138	100.00 1	98.85 63	99.97 44	99.93 78
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
OPU-MVS				99.93 2	99.89 44	99.80 2	99.96 23				99.80 57	97.44 11	100.00 1	100.00 1	99.98 33	100.00 1

SR-MVS		98.46 45	98.30 46	98.93 84	99.88 48	97.04 110	99.84 105	98.35 142	94.92 80	99.32 60	99.80 57	93.35 104	99.78 110	99.30 42	99.95 50	99.96 67

mPP-MVS		98.39 52	98.20 49	98.97 81	99.97 3	96.92 115	99.95 40	98.38 136	95.04 78	98.61 95	99.80 57	93.39 103	100.00 1	98.64 77	100.00 1	99.98 51

Regformer-1		98.79 24	98.60 23	99.36 45	99.85 53	98.34 61	99.87 87	98.52 87	96.05 53	99.41 54	99.79 60	94.93 59	99.76 113	99.07 47	99.90 68	99.99 20

Regformer-2		98.78 25	98.59 24	99.36 45	99.85 53	98.32 62	99.87 87	98.52 87	96.04 54	99.41 54	99.79 60	94.92 60	99.76 113	99.05 48	99.90 68	99.98 51

CPTT-MVS		97.64 84	97.32 85	98.58 103	99.97 3	95.77 152	99.96 23	98.35 142	89.90 232	98.36 105	99.79 60	91.18 147	99.99 36	98.37 85	99.99 20	99.99 20

MVS_111021_LR		98.42 48	98.38 38	98.53 109	99.39 99	95.79 151	99.87 87	99.86 2	96.70 36	98.78 86	99.79 60	92.03 134	99.90 75	99.17 44	99.86 75	99.88 89

XVS		98.70 28	98.55 25	99.15 61	99.94 14	97.50 93	99.94 55	98.42 123	96.22 49	99.41 54	99.78 64	94.34 75	99.96 53	98.92 59	99.95 50	99.99 20

PHI-MVS		98.41 49	98.21 48	99.03 75	99.86 52	97.10 109	99.98 8	98.80 49	90.78 219	99.62 37	99.78 64	95.30 46	100.00 1	99.80 18	99.93 62	99.99 20

Regformer-3		98.58 36	98.41 33	99.10 69	99.84 58	97.57 87	99.66 150	98.52 87	95.79 57	99.01 77	99.77 66	94.40 70	99.75 116	98.82 64	99.83 77	99.98 51

Regformer-4		98.56 37	98.39 37	99.08 71	99.84 58	97.52 90	99.66 150	98.52 87	95.76 60	99.01 77	99.77 66	94.33 78	99.75 116	98.80 67	99.83 77	99.98 51

APD-MVS_3200maxsize		98.25 60	98.08 55	98.78 89	99.81 66	96.60 123	99.82 112	98.30 149	93.95 120	99.37 58	99.77 66	92.84 117	99.76 113	98.95 56	99.92 66	99.97 62

MVS_111021_HR		98.72 27	98.62 22	99.01 78	99.36 101	97.18 105	99.93 61	99.90 1	96.81 33	98.67 91	99.77 66	93.92 91	99.89 79	99.27 43	99.94 56	99.96 67

EI-MVSNet-Vis-set		98.27 57	98.11 54	98.75 91	99.83 61	96.59 124	99.40 188	98.51 93	95.29 73	98.51 98	99.76 70	93.60 101	99.71 124	98.53 81	99.52 102	99.95 75

test_prior3		98.99 13	98.84 14	99.43 35	99.94 14	98.49 56	99.95 40	98.65 59	95.78 58	99.73 26	99.76 70	96.00 29	99.80 106	99.78 20	100.00 1	99.99 20

test_prior2							99.95 40		95.78 58	99.73 26	99.76 70	96.00 29		99.78 20	100.00 1

SD-MVS		98.92 16	98.70 17	99.56 21	99.70 81	98.73 41	99.94 55	98.34 144	96.38 44	99.81 12	99.76 70	94.59 66	99.98 42	99.84 13	99.96 47	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
PGM-MVS		98.34 53	98.13 53	98.99 79	99.92 35	97.00 111	99.75 131	99.50 16	93.90 123	99.37 58	99.76 70	93.24 110	100.00 1	97.75 112	99.96 47	99.98 51

EI-MVSNet-UG-set		98.14 63	97.99 60	98.60 100	99.80 67	96.27 131	99.36 197	98.50 97	95.21 76	98.30 108	99.75 75	93.29 108	99.73 123	98.37 85	99.30 111	99.81 95

PAPR		98.52 41	98.16 51	99.58 20	99.97 3	98.77 36	99.95 40	98.43 112	95.35 71	98.03 116	99.75 75	94.03 89	99.98 42	98.11 94	99.83 77	99.99 20

GST-MVS		98.27 57	97.97 61	99.17 57	99.92 35	97.57 87	99.93 61	98.39 132	94.04 116	98.80 85	99.74 77	92.98 115	100.00 1	98.16 91	99.76 85	99.93 78

TSAR-MVS + MP.		98.93 15	98.77 16	99.41 39	99.74 73	98.67 44	99.77 125	98.38 136	96.73 35	99.88 3	99.74 77	94.89 61	99.59 135	99.80 18	99.98 33	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
APD-MVS		98.62 32	98.35 43	99.41 39	99.90 41	98.51 55	99.87 87	98.36 141	94.08 111	99.74 25	99.73 79	94.08 87	99.74 120	99.42 38	99.99 20	99.99 20
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MG-MVS		98.91 17	98.65 20	99.68 11	99.94 14	99.07 18	99.64 157	99.44 18	97.33 17	99.00 79	99.72 80	94.03 89	99.98 42	98.73 70	100.00 1	100.00 1

AdaColmap		97.23 97	96.80 100	98.51 110	99.99 1	95.60 159	99.09 218	98.84 46	93.32 140	96.74 143	99.72 80	86.04 200	100.00 1	98.01 99	99.43 108	99.94 77

CANet		98.27 57	97.82 67	99.63 12	99.72 79	99.10 17	99.98 8	98.51 93	97.00 28	98.52 97	99.71 82	87.80 183	99.95 60	99.75 22	99.38 109	99.83 93

ACMMP		97.74 81	97.44 79	98.66 95	99.92 35	96.13 141	99.18 213	99.45 17	94.84 84	96.41 153	99.71 82	91.40 141	99.99 36	97.99 101	98.03 140	99.87 90
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
abl_6		97.67 83	97.34 83	98.66 95	99.68 82	96.11 144	99.68 147	98.14 172	93.80 127	99.27 65	99.70 84	88.65 179	99.98 42	97.46 116	99.72 88	99.89 87

PAPM_NR		98.12 64	97.93 65	98.70 92	99.94 14	96.13 141	99.82 112	98.43 112	94.56 92	97.52 126	99.70 84	94.40 70	99.98 42	97.00 127	99.98 33	99.99 20

OMC-MVS		97.28 94	97.23 86	97.41 155	99.76 70	93.36 208	99.65 153	97.95 187	96.03 55	97.41 129	99.70 84	89.61 165	99.51 138	96.73 134	98.25 134	99.38 158

xiu_mvs_v1_base_debu		97.43 87	97.06 90	98.55 104	97.74 181	98.14 66	99.31 202	97.86 197	96.43 41	99.62 37	99.69 87	85.56 204	99.68 128	99.05 48	98.31 131	97.83 205

xiu_mvs_v1_base		97.43 87	97.06 90	98.55 104	97.74 181	98.14 66	99.31 202	97.86 197	96.43 41	99.62 37	99.69 87	85.56 204	99.68 128	99.05 48	98.31 131	97.83 205

xiu_mvs_v1_base_debi		97.43 87	97.06 90	98.55 104	97.74 181	98.14 66	99.31 202	97.86 197	96.43 41	99.62 37	99.69 87	85.56 204	99.68 128	99.05 48	98.31 131	97.83 205

CNLPA		97.76 80	97.38 80	98.92 85	99.53 91	96.84 116	99.87 87	98.14 172	93.78 128	96.55 148	99.69 87	92.28 129	99.98 42	97.13 123	99.44 107	99.93 78

cdsmvs_eth3d_5k		23.43 322	31.24 324	0.00 337	0.00 356	0.00 357	0.00 348	98.09 175	0.00 352	0.00 353	99.67 91	83.37 221	0.00 354	0.00 351	0.00 351	0.00 350

lupinMVS		97.85 73	97.60 74	98.62 98	97.28 205	97.70 84	99.99 4	97.55 221	95.50 69	99.43 52	99.67 91	90.92 152	98.71 171	98.40 84	99.62 94	99.45 151

114514_t		97.41 91	96.83 98	99.14 63	99.51 94	97.83 79	99.89 81	98.27 154	88.48 256	99.06 74	99.66 93	90.30 158	99.64 134	96.32 137	99.97 44	99.96 67

PAPM		98.60 33	98.42 31	99.14 63	96.05 237	98.96 20	99.90 73	99.35 23	96.68 37	98.35 106	99.66 93	96.45 25	98.51 181	99.45 36	99.89 70	99.96 67

CS-MVS		97.84 74	97.69 70	98.31 122	98.28 147	96.27 131	100.00 1	97.52 227	95.29 73	99.25 67	99.65 95	91.18 147	98.94 158	98.96 55	99.04 117	99.73 105

CANet_DTU		96.76 113	96.15 116	98.60 100	98.78 130	97.53 89	99.84 105	97.63 209	97.25 23	99.20 68	99.64 96	81.36 234	99.98 42	92.77 202	98.89 118	98.28 199

XVG-OURS		94.82 161	94.74 158	95.06 213	98.00 163	89.19 282	99.08 220	97.55 221	94.10 110	94.71 176	99.62 97	80.51 245	99.74 120	96.04 140	93.06 211	96.25 216

MVS		96.60 121	95.56 139	99.72 9	96.85 220	99.22 15	98.31 277	98.94 36	91.57 198	90.90 213	99.61 98	86.66 195	99.96 53	97.36 118	99.88 72	99.99 20

EIA-MVS		97.53 86	97.46 78	97.76 143	98.04 162	94.84 178	99.98 8	97.61 215	94.41 98	97.90 119	99.59 99	92.40 126	98.87 159	98.04 98	99.13 115	99.59 127

XVG-OURS-SEG-HR		94.79 162	94.70 159	95.08 212	98.05 161	89.19 282	99.08 220	97.54 223	93.66 132	94.87 175	99.58 100	78.78 258	99.79 108	97.31 119	93.40 207	96.25 216

HPM-MVS		97.96 68	97.72 69	98.68 93	99.84 58	96.39 130	99.90 73	98.17 166	92.61 166	98.62 94	99.57 101	91.87 137	99.67 131	98.87 62	99.99 20	99.99 20
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
TSAR-MVS + GP.		98.60 33	98.51 28	98.86 87	99.73 77	96.63 121	99.97 16	97.92 191	98.07 5	98.76 87	99.55 102	95.00 56	99.94 68	99.91 11	97.68 144	99.99 20

DP-MVS		94.54 172	93.42 184	97.91 138	99.46 98	94.04 193	98.93 240	97.48 233	81.15 317	90.04 221	99.55 102	87.02 192	99.95 60	88.97 247	98.11 135	99.73 105

MVSFormer		96.94 105	96.60 105	97.95 135	97.28 205	97.70 84	99.55 170	97.27 252	91.17 208	99.43 52	99.54 104	90.92 152	96.89 272	94.67 164	99.62 94	99.25 171

jason		97.24 96	96.86 97	98.38 120	95.73 249	97.32 101	99.97 16	97.40 243	95.34 72	98.60 96	99.54 104	87.70 184	98.56 178	97.94 104	99.47 105	99.25 171
jason: jason.
HPM-MVS_fast		97.80 78	97.50 77	98.68 93	99.79 68	96.42 127	99.88 84	98.16 169	91.75 194	98.94 81	99.54 104	91.82 139	99.65 133	97.62 114	99.99 20	99.99 20

DeepC-MVS	94.51 4	96.92 107	96.40 112	98.45 114	99.16 106	95.90 148	99.66 150	98.06 178	96.37 47	94.37 181	99.49 107	83.29 222	99.90 75	97.63 113	99.61 97	99.55 136
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
alignmvs		97.81 77	97.33 84	99.25 49	98.77 131	98.66 46	99.99 4	98.44 104	94.40 99	98.41 102	99.47 108	93.65 99	99.42 146	98.57 79	94.26 199	99.67 114

TAPA-MVS	92.12 8	94.42 176	93.60 178	96.90 168	99.33 102	91.78 242	99.78 122	98.00 181	89.89 233	94.52 178	99.47 108	91.97 135	99.18 150	69.90 330	99.52 102	99.73 105
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ETV-MVS		97.92 71	97.80 68	98.25 125	98.14 158	96.48 125	99.98 8	97.63 209	95.61 66	99.29 64	99.46 110	92.55 125	98.82 161	99.02 54	98.54 125	99.46 149

ET-MVSNet_ETH3D		94.37 177	93.28 190	97.64 147	98.30 145	97.99 73	99.99 4	97.61 215	94.35 100	71.57 333	99.45 111	96.23 27	95.34 316	96.91 132	85.14 262	99.59 127

canonicalmvs		97.09 102	96.32 113	99.39 43	98.93 119	98.95 21	99.72 142	97.35 246	94.45 95	97.88 120	99.42 112	86.71 194	99.52 137	98.48 82	93.97 203	99.72 108

VDD-MVS		93.77 188	92.94 193	96.27 187	98.55 136	90.22 271	98.77 253	97.79 202	90.85 217	96.82 141	99.42 112	61.18 331	99.77 111	98.95 56	94.13 200	98.82 192

1112_ss		96.01 139	95.20 148	98.42 117	97.80 176	96.41 128	99.65 153	96.66 300	92.71 159	92.88 199	99.40 114	92.16 131	99.30 147	91.92 209	93.66 204	99.55 136

ab-mvs-re		8.28 324	11.04 326	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	99.40 114	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

LFMVS		94.75 165	93.56 181	98.30 123	99.03 110	95.70 157	98.74 254	97.98 184	87.81 265	98.47 100	99.39 116	67.43 314	99.53 136	98.01 99	95.20 192	99.67 114

WTY-MVS		98.10 65	97.60 74	99.60 17	98.92 121	99.28 12	99.89 81	99.52 13	95.58 67	98.24 112	99.39 116	93.33 105	99.74 120	97.98 103	95.58 186	99.78 100

PMMVS		96.76 113	96.76 101	96.76 172	98.28 147	92.10 233	99.91 69	97.98 184	94.12 109	99.53 44	99.39 116	86.93 193	98.73 169	96.95 130	97.73 142	99.45 151

EPNet		98.49 43	98.40 35	98.77 90	99.62 85	96.80 118	99.90 73	99.51 15	97.60 12	99.20 68	99.36 119	93.71 98	99.91 74	97.99 101	98.71 123	99.61 124
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
VDDNet		93.12 200	91.91 213	96.76 172	96.67 230	92.65 223	98.69 259	98.21 160	82.81 311	97.75 123	99.28 120	61.57 329	99.48 144	98.09 96	94.09 201	98.15 201

diffmvs		97.00 103	96.64 104	98.09 131	97.64 188	96.17 140	99.81 114	97.19 256	94.67 90	98.95 80	99.28 120	86.43 197	98.76 167	98.37 85	97.42 150	99.33 164

baseline		96.43 126	95.98 122	97.76 143	97.34 200	95.17 172	99.51 176	97.17 259	93.92 122	96.90 139	99.28 120	85.37 207	98.64 175	97.50 115	96.86 164	99.46 149

UA-Net		96.54 122	95.96 127	98.27 124	98.23 152	95.71 156	98.00 291	98.45 103	93.72 131	98.41 102	99.27 123	88.71 178	99.66 132	91.19 217	97.69 143	99.44 153

RPSCF		91.80 229	92.79 196	88.83 312	98.15 157	69.87 339	98.11 287	96.60 302	83.93 305	94.33 182	99.27 123	79.60 252	99.46 145	91.99 207	93.16 210	97.18 212

PLC	95.54 3	97.93 70	97.89 66	98.05 133	99.82 63	94.77 182	99.92 65	98.46 101	93.93 121	97.20 132	99.27 123	95.44 44	99.97 51	97.41 117	99.51 104	99.41 156
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
casdiffmvs		96.42 127	95.97 125	97.77 142	97.30 204	94.98 174	99.84 105	97.09 265	93.75 130	96.58 146	99.26 126	85.07 209	98.78 164	97.77 110	97.04 159	99.54 140

BH-RMVSNet		95.18 155	94.31 164	97.80 139	98.17 156	95.23 170	99.76 130	97.53 225	92.52 173	94.27 183	99.25 127	76.84 269	98.80 162	90.89 226	99.54 101	99.35 162

DELS-MVS		98.54 39	98.22 47	99.50 29	99.15 107	98.65 48	100.00 1	98.58 72	97.70 9	98.21 113	99.24 128	92.58 124	99.94 68	98.63 78	99.94 56	99.92 84
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
PCF-MVS	94.20 5	95.18 155	94.10 168	98.43 116	98.55 136	95.99 146	97.91 293	97.31 250	90.35 225	89.48 237	99.22 129	85.19 208	99.89 79	90.40 235	98.47 127	99.41 156
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PVSNet	91.05 13	97.13 99	96.69 103	98.45 114	99.52 92	95.81 150	99.95 40	99.65 10	94.73 87	99.04 75	99.21 130	84.48 213	99.95 60	94.92 152	98.74 122	99.58 133

MSDG		94.37 177	93.36 188	97.40 156	98.88 126	93.95 195	99.37 195	97.38 244	85.75 292	90.80 214	99.17 131	84.11 217	99.88 85	86.35 275	98.43 128	98.36 198

F-COLMAP		96.93 106	96.95 96	96.87 169	99.71 80	91.74 243	99.85 101	97.95 187	93.11 147	95.72 165	99.16 132	92.35 127	99.94 68	95.32 147	99.35 110	98.92 186

Vis-MVSNet (Re-imp)		96.32 130	95.98 122	97.35 160	97.93 167	94.82 179	99.47 182	98.15 171	91.83 191	95.09 173	99.11 133	91.37 142	97.47 236	93.47 191	97.43 148	99.74 104

CHOSEN 280x420		99.01 12	99.03 8	98.95 83	99.38 100	98.87 27	98.46 270	99.42 20	97.03 27	99.02 76	99.09 134	99.35 1	98.21 209	99.73 27	99.78 84	99.77 101

PVSNet_Blended		97.94 69	97.64 72	98.83 88	99.59 86	96.99 112	100.00 1	99.10 28	95.38 70	98.27 109	99.08 135	89.00 174	99.95 60	99.12 45	99.25 112	99.57 134

sss		97.57 85	97.03 94	99.18 54	98.37 143	98.04 71	99.73 139	99.38 21	93.46 137	98.76 87	99.06 136	91.21 143	99.89 79	96.33 136	97.01 160	99.62 122

thisisatest0515		97.41 91	97.02 95	98.59 102	97.71 187	97.52 90	99.97 16	98.54 84	91.83 191	97.45 128	99.04 137	97.50 8	99.10 152	94.75 160	96.37 170	99.16 176

EI-MVSNet		93.73 190	93.40 187	94.74 223	96.80 223	92.69 220	99.06 225	97.67 207	88.96 245	91.39 208	99.02 138	88.75 177	97.30 244	91.07 219	87.85 240	94.22 248

CVMVSNet		94.68 168	94.94 153	93.89 260	96.80 223	86.92 303	99.06 225	98.98 34	94.45 95	94.23 184	99.02 138	85.60 203	95.31 317	90.91 225	95.39 189	99.43 154

EPP-MVSNet		96.69 118	96.60 105	96.96 166	97.74 181	93.05 212	99.37 195	98.56 76	88.75 250	95.83 163	99.01 140	96.01 28	98.56 178	96.92 131	97.20 156	99.25 171

COLMAP_ROB	90.47 14	92.18 221	91.49 222	94.25 245	99.00 113	88.04 298	98.42 275	96.70 299	82.30 314	88.43 259	99.01 140	76.97 267	99.85 94	86.11 278	96.50 168	94.86 221
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
3Dnovator	91.47 12	96.28 134	95.34 144	99.08 71	96.82 222	97.47 96	99.45 185	98.81 47	95.52 68	89.39 238	99.00 142	81.97 227	99.95 60	97.27 120	99.83 77	99.84 92

test_yl		97.83 75	97.37 81	99.21 51	99.18 104	97.98 74	99.64 157	99.27 25	91.43 204	97.88 120	98.99 143	95.84 35	99.84 103	98.82 64	95.32 190	99.79 97

DCV-MVSNet		97.83 75	97.37 81	99.21 51	99.18 104	97.98 74	99.64 157	99.27 25	91.43 204	97.88 120	98.99 143	95.84 35	99.84 103	98.82 64	95.32 190	99.79 97

1314		96.84 109	95.96 127	99.48 33	96.74 227	98.52 54	98.31 277	98.86 44	95.82 56	89.91 224	98.98 145	87.49 186	99.96 53	97.80 107	99.73 87	99.96 67

3Dnovator+	91.53 11	96.31 131	95.24 146	99.52 26	96.88 219	98.64 49	99.72 142	98.24 156	95.27 75	88.42 261	98.98 145	82.76 224	99.94 68	97.10 125	99.83 77	99.96 67

thisisatest0530		97.10 100	96.72 102	98.22 126	97.60 190	96.70 119	99.92 65	98.54 84	91.11 211	97.07 136	98.97 147	97.47 9	99.03 153	93.73 187	96.09 173	98.92 186

baseline2		96.71 117	96.49 109	97.37 158	95.63 256	95.96 147	99.74 134	98.88 42	92.94 149	91.61 206	98.97 147	97.72 5	98.62 176	94.83 156	98.08 139	97.53 211

gm-plane-assit					96.97 215	93.76 199			91.47 202		98.96 149		98.79 163	94.92 152

IS-MVSNet		96.29 133	95.90 131	97.45 153	98.13 159	94.80 180	99.08 220	97.61 215	92.02 187	95.54 168	98.96 149	90.64 155	98.08 213	93.73 187	97.41 151	99.47 148

OpenMVS	90.15 15	94.77 164	93.59 179	98.33 121	96.07 236	97.48 95	99.56 168	98.57 74	90.46 222	86.51 285	98.95 151	78.57 260	99.94 68	93.86 178	99.74 86	97.57 210

Vis-MVSNet		95.72 144	95.15 150	97.45 153	97.62 189	94.28 189	99.28 206	98.24 156	94.27 106	96.84 140	98.94 152	79.39 253	98.76 167	93.25 193	98.49 126	99.30 167
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
tttt0517		96.85 108	96.49 109	97.92 137	97.48 196	95.89 149	99.85 101	98.54 84	90.72 220	96.63 145	98.93 153	97.47 9	99.02 154	93.03 200	95.76 182	98.85 190

DWT-MVSNet_test		97.31 93	97.19 87	97.66 146	98.24 151	94.67 183	98.86 248	98.20 164	93.60 134	98.09 114	98.89 154	97.51 7	98.78 164	94.04 176	97.28 153	99.55 136

QAPM		95.40 152	94.17 166	99.10 69	96.92 216	97.71 82	99.40 188	98.68 55	89.31 237	88.94 250	98.89 154	82.48 225	99.96 53	93.12 199	99.83 77	99.62 122

VNet		97.21 98	96.57 107	99.13 68	98.97 115	97.82 80	99.03 231	99.21 27	94.31 103	99.18 71	98.88 156	86.26 199	99.89 79	98.93 58	94.32 198	99.69 111

thres200		96.96 104	96.21 115	99.22 50	98.97 115	98.84 30	99.85 101	99.71 5	93.17 145	96.26 155	98.88 156	89.87 163	99.51 138	94.26 173	94.91 193	99.31 166

tfpn200view9		96.79 111	95.99 120	99.19 53	98.94 117	98.82 31	99.78 122	99.71 5	92.86 150	96.02 158	98.87 158	89.33 168	99.50 140	93.84 179	94.57 194	99.27 169

thres400		96.78 112	95.99 120	99.16 59	98.94 117	98.82 31	99.78 122	99.71 5	92.86 150	96.02 158	98.87 158	89.33 168	99.50 140	93.84 179	94.57 194	99.16 176

thres100view900		96.74 115	95.92 130	99.18 54	98.90 124	98.77 36	99.74 134	99.71 5	92.59 168	95.84 161	98.86 160	89.25 170	99.50 140	93.84 179	94.57 194	99.27 169

thres600view7		96.69 118	95.87 133	99.14 63	98.90 124	98.78 35	99.74 134	99.71 5	92.59 168	95.84 161	98.86 160	89.25 170	99.50 140	93.44 192	94.50 197	99.16 176

CHOSEN 1792x2688		96.81 110	96.53 108	97.64 147	98.91 123	93.07 210	99.65 153	99.80 3	95.64 65	95.39 169	98.86 160	84.35 215	99.90 75	96.98 128	99.16 114	99.95 75

CLD-MVS		94.06 182	93.90 172	94.55 232	96.02 238	90.69 260	99.98 8	97.72 204	96.62 39	91.05 212	98.85 163	77.21 265	98.47 182	98.11 94	89.51 220	94.48 226
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
BH-w/o		95.71 146	95.38 143	96.68 175	98.49 140	92.28 229	99.84 105	97.50 231	92.12 183	92.06 204	98.79 164	84.69 211	98.67 174	95.29 148	99.66 92	99.09 182

Anonymous202405211		93.10 201	91.99 211	96.40 183	99.10 108	89.65 279	98.88 244	97.93 189	83.71 307	94.00 186	98.75 165	68.79 307	99.88 85	95.08 150	91.71 213	99.68 112

mvs-test1		95.53 149	95.97 125	94.20 246	97.77 178	85.44 311	99.95 40	97.06 268	94.92 80	96.58 146	98.72 166	85.81 201	98.98 155	94.80 157	98.11 135	98.18 200

TR-MVS		94.54 172	93.56 181	97.49 152	97.96 165	94.34 188	98.71 257	97.51 230	90.30 227	94.51 179	98.69 167	75.56 279	98.77 166	92.82 201	95.99 175	99.35 162

BH-untuned		95.18 155	94.83 155	96.22 188	98.36 144	91.22 254	99.80 119	97.32 249	90.91 215	91.08 211	98.67 168	83.51 219	98.54 180	94.23 174	99.61 97	98.92 186

OPM-MVS		93.21 198	92.80 195	94.44 239	93.12 295	90.85 259	99.77 125	97.61 215	96.19 51	91.56 207	98.65 169	75.16 284	98.47 182	93.78 185	89.39 221	93.99 273

NP-MVS					95.77 246	91.79 241					98.65 169

HQP-MVS		94.61 170	94.50 161	94.92 218	95.78 243	91.85 239	99.87 87	97.89 193	96.82 30	93.37 191	98.65 169	80.65 243	98.39 193	97.92 105	89.60 215	94.53 222

baseline1		95.78 143	94.86 154	98.54 107	98.47 141	98.07 69	99.06 225	97.99 182	92.68 162	94.13 185	98.62 172	93.28 109	98.69 173	93.79 184	85.76 254	98.84 191

HQP_MVS		94.49 175	94.36 163	94.87 219	95.71 252	91.74 243	99.84 105	97.87 195	96.38 44	93.01 195	98.59 173	80.47 247	98.37 198	97.79 108	89.55 218	94.52 224

plane_prior4											98.59 173

Anonymous20240529		92.10 222	90.65 232	96.47 179	98.82 127	90.61 263	98.72 256	98.67 58	75.54 331	93.90 188	98.58 175	66.23 317	99.90 75	94.70 163	90.67 214	98.90 189

Effi-MVS+		96.30 132	95.69 136	98.16 127	97.85 173	96.26 133	97.41 300	97.21 255	90.37 224	98.65 93	98.58 175	86.61 196	98.70 172	97.11 124	97.37 152	99.52 143

EPNet_dtu		95.71 146	95.39 142	96.66 176	98.92 121	93.41 206	99.57 166	98.90 40	96.19 51	97.52 126	98.56 177	92.65 122	97.36 239	77.89 316	98.33 130	99.20 174
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test0.0.03 1		93.86 183	93.61 176	94.64 227	95.02 265	92.18 232	99.93 61	98.58 72	94.07 112	87.96 266	98.50 178	93.90 93	94.96 321	81.33 305	93.17 209	96.78 213

LPG-MVS_test		92.96 203	92.71 197	93.71 264	95.43 258	88.67 288	99.75 131	97.62 212	92.81 153	90.05 219	98.49 179	75.24 282	98.40 191	95.84 144	89.12 222	94.07 265

LGP-MVS_train				93.71 264	95.43 258	88.67 288		97.62 212	92.81 153	90.05 219	98.49 179	75.24 282	98.40 191	95.84 144	89.12 222	94.07 265

PVSNet_Blended_VisFu		97.27 95	96.81 99	98.66 95	98.81 128	96.67 120	99.92 65	98.64 62	94.51 94	96.38 154	98.49 179	89.05 173	99.88 85	97.10 125	98.34 129	99.43 154

testmvs		40.60 320	44.45 322	29.05 335	19.49 355	14.11 356	99.68 147	18.47 355	20.74 349	64.59 336	98.48 182	10.95 354	17.09 353	56.66 342	11.01 348	55.94 346

AllTest		92.48 214	91.64 216	95.00 215	99.01 111	88.43 292	98.94 239	96.82 293	86.50 281	88.71 252	98.47 183	74.73 286	99.88 85	85.39 281	96.18 171	96.71 214

TestCases				95.00 215	99.01 111	88.43 292		96.82 293	86.50 281	88.71 252	98.47 183	74.73 286	99.88 85	85.39 281	96.18 171	96.71 214

PatchMatch-RL		96.04 138	95.40 141	97.95 135	99.59 86	95.22 171	99.52 174	99.07 31	93.96 119	96.49 149	98.35 185	82.28 226	99.82 105	90.15 238	99.22 113	98.81 193

CDS-MVSNet		96.34 129	96.07 117	97.13 163	97.37 198	94.96 175	99.53 173	97.91 192	91.55 199	95.37 170	98.32 186	95.05 52	97.13 256	93.80 183	95.75 183	99.30 167
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
ACMP	92.05 9	92.74 208	92.42 205	93.73 262	95.91 242	88.72 287	99.81 114	97.53 225	94.13 108	87.00 279	98.23 187	74.07 290	98.47 182	96.22 138	88.86 227	93.99 273
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
testgi		89.01 279	88.04 279	91.90 291	93.49 288	84.89 314	99.73 139	95.66 319	93.89 125	85.14 298	98.17 188	59.68 332	94.66 325	77.73 317	88.88 225	96.16 219

ITE_SJBPF				92.38 284	95.69 254	85.14 312		95.71 317	92.81 153	89.33 241	98.11 189	70.23 304	98.42 188	85.91 279	88.16 238	93.59 297

HyFIR lowres test		96.66 120	96.43 111	97.36 159	99.05 109	93.91 196	99.70 144	99.80 3	90.54 221	96.26 155	98.08 190	92.15 132	98.23 208	96.84 133	95.46 187	99.93 78

TESTMET0.1,1		96.74 115	96.26 114	98.16 127	97.36 199	96.48 125	99.96 23	98.29 150	91.93 188	95.77 164	98.07 191	95.54 40	98.29 203	90.55 230	98.89 118	99.70 109

TAMVS		95.85 141	95.58 138	96.65 177	97.07 209	93.50 203	99.17 214	97.82 201	91.39 207	95.02 174	98.01 192	92.20 130	97.30 244	93.75 186	95.83 180	99.14 179

ACMM	91.95 10	92.88 205	92.52 203	93.98 257	95.75 248	89.08 285	99.77 125	97.52 227	93.00 148	89.95 223	97.99 193	76.17 276	98.46 185	93.63 190	88.87 226	94.39 235
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Fast-Effi-MVS+		95.02 159	94.19 165	97.52 151	97.88 169	94.55 184	99.97 16	97.08 266	88.85 249	94.47 180	97.96 194	84.59 212	98.41 189	89.84 241	97.10 157	99.59 127

GG-mvs-BLEND				98.54 107	98.21 153	98.01 72	93.87 327	98.52 87		97.92 118	97.92 195	99.02 2	97.94 223	98.17 90	99.58 99	99.67 114

Fast-Effi-MVS+-dtu		93.72 191	93.86 174	93.29 271	97.06 210	86.16 305	99.80 119	96.83 291	92.66 163	92.58 202	97.83 196	81.39 233	97.67 230	89.75 242	96.87 163	96.05 220

RRT_MVS		95.23 154	94.77 157	96.61 178	98.28 147	98.32 62	99.81 114	97.41 241	92.59 168	91.28 210	97.76 197	95.02 53	97.23 250	93.65 189	87.14 247	94.28 244

ACMH+	89.98 16	90.35 257	89.54 253	92.78 282	95.99 239	86.12 306	98.81 251	97.18 258	89.38 236	83.14 306	97.76 197	68.42 311	98.43 187	89.11 246	86.05 253	93.78 289

ACMH	89.72 17	90.64 250	89.63 250	93.66 266	95.64 255	88.64 290	98.55 265	97.45 234	89.03 241	81.62 310	97.61 199	69.75 305	98.41 189	89.37 243	87.62 244	93.92 279
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
cascas		94.64 169	93.61 176	97.74 145	97.82 175	96.26 133	99.96 23	97.78 203	85.76 290	94.00 186	97.54 200	76.95 268	99.21 149	97.23 121	95.43 188	97.76 209

nrg030		93.51 194	92.53 202	96.45 181	94.36 273	97.20 104	99.81 114	97.16 261	91.60 197	89.86 226	97.46 201	86.37 198	97.68 229	95.88 143	80.31 298	94.46 227

VPNet		91.81 226	90.46 234	95.85 198	94.74 268	95.54 160	98.98 234	98.59 71	92.14 182	90.77 215	97.44 202	68.73 309	97.54 234	94.89 155	77.89 311	94.46 227

UniMVSNet_ETH3D		90.06 266	88.58 271	94.49 236	94.67 270	88.09 297	97.81 295	97.57 220	83.91 306	88.44 257	97.41 203	57.44 335	97.62 232	91.41 214	88.59 233	97.77 208

HY-MVS	92.50 7	97.79 79	97.17 89	99.63 12	98.98 114	99.32 6	97.49 299	99.52 13	95.69 64	98.32 107	97.41 203	93.32 106	99.77 111	98.08 97	95.75 183	99.81 95

PVSNet_0	88.03 19	91.80 229	90.27 240	96.38 185	98.27 150	90.46 267	99.94 55	99.61 11	93.99 117	86.26 291	97.39 205	71.13 302	99.89 79	98.77 69	67.05 336	98.79 194

FIs		94.10 181	93.43 183	96.11 190	94.70 269	96.82 117	99.58 164	98.93 39	92.54 172	89.34 240	97.31 206	87.62 185	97.10 259	94.22 175	86.58 250	94.40 234

OurMVSNet-221017-0		89.81 269	89.48 257	90.83 299	91.64 315	81.21 328	98.17 285	95.38 324	91.48 201	85.65 296	97.31 206	72.66 294	97.29 247	88.15 256	84.83 263	93.97 275

FC-MVSNet-test		93.81 186	93.15 192	95.80 199	94.30 275	96.20 138	99.42 187	98.89 41	92.33 178	89.03 249	97.27 208	87.39 188	96.83 276	93.20 194	86.48 251	94.36 236

USDC		90.00 267	88.96 265	93.10 277	94.81 267	88.16 296	98.71 257	95.54 322	93.66 132	83.75 305	97.20 209	65.58 319	98.31 202	83.96 291	87.49 246	92.85 311

MVSTER		95.53 149	95.22 147	96.45 181	98.56 135	97.72 81	99.91 69	97.67 207	92.38 177	91.39 208	97.14 210	97.24 14	97.30 244	94.80 157	87.85 240	94.34 240

LF4IMVS		89.25 278	88.85 266	90.45 303	92.81 303	81.19 329	98.12 286	94.79 331	91.44 203	86.29 290	97.11 211	65.30 321	98.11 212	88.53 252	85.25 259	92.07 316

mvs_anonymous		95.65 148	95.03 152	97.53 150	98.19 154	95.74 154	99.33 199	97.49 232	90.87 216	90.47 217	97.10 212	88.23 181	97.16 253	95.92 142	97.66 145	99.68 112

jajsoiax		91.92 224	91.18 226	94.15 247	91.35 318	90.95 257	99.00 233	97.42 239	92.61 166	87.38 275	97.08 213	72.46 295	97.36 239	94.53 167	88.77 228	94.13 262

XXY-MVS		91.82 225	90.46 234	95.88 196	93.91 281	95.40 164	98.87 247	97.69 206	88.63 254	87.87 267	97.08 213	74.38 289	97.89 224	91.66 212	84.07 270	94.35 239

LTVRE_ROB	88.28 18	90.29 260	89.05 264	94.02 253	95.08 263	90.15 273	97.19 303	97.43 237	84.91 300	83.99 303	97.06 215	74.00 291	98.28 205	84.08 288	87.71 242	93.62 296
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
mvs_tets		91.81 226	91.08 227	94.00 255	91.63 316	90.58 264	98.67 261	97.43 237	92.43 176	87.37 276	97.05 216	71.76 297	97.32 243	94.75 160	88.68 230	94.11 263

MVS_Test		96.46 125	95.74 135	98.61 99	98.18 155	97.23 103	99.31 202	97.15 262	91.07 212	98.84 83	97.05 216	88.17 182	98.97 156	94.39 168	97.50 147	99.61 124

ab-mvs		94.69 166	93.42 184	98.51 110	98.07 160	96.26 133	96.49 311	98.68 55	90.31 226	94.54 177	97.00 218	76.30 274	99.71 124	95.98 141	93.38 208	99.56 135

PS-MVSNAJss		93.64 193	93.31 189	94.61 228	92.11 309	92.19 231	99.12 216	97.38 244	92.51 174	88.45 256	96.99 219	91.20 144	97.29 247	94.36 169	87.71 242	94.36 236

IB-MVS	92.85 6	94.99 160	93.94 171	98.16 127	97.72 185	95.69 158	99.99 4	98.81 47	94.28 105	92.70 201	96.90 220	95.08 50	99.17 151	96.07 139	73.88 327	99.60 126
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
WR-MVS		92.31 218	91.25 225	95.48 204	94.45 272	95.29 166	99.60 162	98.68 55	90.10 228	88.07 265	96.89 221	80.68 242	96.80 278	93.14 197	79.67 302	94.36 236

SixPastTwentyTwo		88.73 280	88.01 280	90.88 297	91.85 313	82.24 323	98.22 283	95.18 329	88.97 244	82.26 308	96.89 221	71.75 298	96.67 283	84.00 289	82.98 275	93.72 294

UniMVSNet_NR-MVSNet		92.95 204	92.11 208	95.49 201	94.61 271	95.28 167	99.83 111	99.08 30	91.49 200	89.21 244	96.86 223	87.14 190	96.73 280	93.20 194	77.52 314	94.46 227

XVG-ACMP-BASELINE		91.22 239	90.75 230	92.63 283	93.73 284	85.61 308	98.52 269	97.44 236	92.77 157	89.90 225	96.85 224	66.64 316	98.39 193	92.29 204	88.61 231	93.89 281

TinyColmap		87.87 285	86.51 287	91.94 290	95.05 264	85.57 309	97.65 297	94.08 336	84.40 303	81.82 309	96.85 224	62.14 328	98.33 200	80.25 310	86.37 252	91.91 320

EU-MVSNet		90.14 265	90.34 238	89.54 309	92.55 305	81.06 330	98.69 259	98.04 180	91.41 206	86.59 284	96.84 226	80.83 240	93.31 334	86.20 276	81.91 282	94.26 245

TranMVSNet+NR-MVSNet		91.68 233	90.61 233	94.87 219	93.69 285	93.98 194	99.69 145	98.65 59	91.03 213	88.44 257	96.83 227	80.05 250	96.18 300	90.26 237	76.89 321	94.45 232

RRT_test8_iter05		94.58 171	94.11 167	95.98 193	97.88 169	96.11 144	99.89 81	97.45 234	91.66 196	88.28 262	96.71 228	96.53 24	97.40 237	94.73 162	83.85 273	94.45 232

GA-MVS		93.83 184	92.84 194	96.80 170	95.73 249	93.57 201	99.88 84	97.24 254	92.57 171	92.92 197	96.66 229	78.73 259	97.67 230	87.75 260	94.06 202	99.17 175

CMPMVS	61.59 21	84.75 298	85.14 291	83.57 320	90.32 326	62.54 342	96.98 306	97.59 219	74.33 334	69.95 335	96.66 229	64.17 323	98.32 201	87.88 259	88.41 236	89.84 332
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
DU-MVS		92.46 215	91.45 223	95.49 201	94.05 278	95.28 167	99.81 114	98.74 51	92.25 180	89.21 244	96.64 231	81.66 230	96.73 280	93.20 194	77.52 314	94.46 227

NR-MVSNet		91.56 234	90.22 241	95.60 200	94.05 278	95.76 153	98.25 280	98.70 53	91.16 210	80.78 313	96.64 231	83.23 223	96.57 286	91.41 214	77.73 313	94.46 227

CP-MVSNet		91.23 238	90.22 241	94.26 244	93.96 280	92.39 228	99.09 218	98.57 74	88.95 246	86.42 288	96.57 233	79.19 255	96.37 292	90.29 236	78.95 304	94.02 268

pmmvs4		92.10 222	91.07 228	95.18 210	92.82 302	94.96 175	99.48 181	96.83 291	87.45 268	88.66 255	96.56 234	83.78 218	96.83 276	89.29 244	84.77 264	93.75 290

PS-CasMVS		90.63 251	89.51 255	93.99 256	93.83 282	91.70 247	98.98 234	98.52 87	88.48 256	86.15 292	96.53 235	75.46 280	96.31 295	88.83 248	78.86 306	93.95 276

test-LLR		96.47 124	96.04 118	97.78 140	97.02 213	95.44 161	99.96 23	98.21 160	94.07 112	95.55 166	96.38 236	93.90 93	98.27 206	90.42 233	98.83 120	99.64 120

test-mter		96.39 128	95.93 129	97.78 140	97.02 213	95.44 161	99.96 23	98.21 160	91.81 193	95.55 166	96.38 236	95.17 47	98.27 206	90.42 233	98.83 120	99.64 120

MS-PatchMatch		90.65 249	90.30 239	91.71 293	94.22 276	85.50 310	98.24 281	97.70 205	88.67 252	86.42 288	96.37 238	67.82 313	98.03 216	83.62 293	99.62 94	91.60 321

PEN-MVS		90.19 263	89.06 263	93.57 267	93.06 297	90.90 258	99.06 225	98.47 99	88.11 260	85.91 294	96.30 239	76.67 270	95.94 310	87.07 268	76.91 320	93.89 281

UGNet		95.33 153	94.57 160	97.62 149	98.55 136	94.85 177	98.67 261	99.32 24	95.75 63	96.80 142	96.27 240	72.18 296	99.96 53	94.58 166	99.05 116	98.04 203
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
DTE-MVSNet		89.40 273	88.24 277	92.88 280	92.66 304	89.95 275	99.10 217	98.22 159	87.29 270	85.12 299	96.22 241	76.27 275	95.30 318	83.56 294	75.74 324	93.41 299

TransMVSNet (Re)		87.25 286	85.28 290	93.16 274	93.56 286	91.03 255	98.54 267	94.05 337	83.69 308	81.09 312	96.16 242	75.32 281	96.40 291	76.69 322	68.41 333	92.06 317

pm-mvs1		89.36 275	87.81 281	94.01 254	93.40 291	91.93 237	98.62 264	96.48 306	86.25 285	83.86 304	96.14 243	73.68 292	97.04 264	86.16 277	75.73 325	93.04 309

Test_1112_low_res		95.72 144	94.83 155	98.42 117	97.79 177	96.41 128	99.65 153	96.65 301	92.70 160	92.86 200	96.13 244	92.15 132	99.30 147	91.88 210	93.64 205	99.55 136

TDRefinement		84.76 297	82.56 301	91.38 295	74.58 343	84.80 315	97.36 301	94.56 334	84.73 301	80.21 315	96.12 245	63.56 325	98.39 193	87.92 258	63.97 337	90.95 326

test_djsdf		92.83 206	92.29 206	94.47 237	91.90 312	92.46 226	99.55 170	97.27 252	91.17 208	89.96 222	96.07 246	81.10 236	96.89 272	94.67 164	88.91 224	94.05 267

miper_enhance_ethall		94.36 179	93.98 170	95.49 201	98.68 134	95.24 169	99.73 139	97.29 251	93.28 142	89.86 226	95.97 247	94.37 74	97.05 262	92.20 206	84.45 266	94.19 251

lessismore_v0				90.53 300	90.58 324	80.90 331		95.80 316		77.01 323	95.84 248	66.15 318	96.95 269	83.03 296	75.05 326	93.74 293

PVSNet_BlendedMVS		96.05 137	95.82 134	96.72 174	99.59 86	96.99 112	99.95 40	99.10 28	94.06 114	98.27 109	95.80 249	89.00 174	99.95 60	99.12 45	87.53 245	93.24 305

ppachtmachnet_test		89.58 272	88.35 274	93.25 273	92.40 306	90.44 268	99.33 199	96.73 298	85.49 296	85.90 295	95.77 250	81.09 237	96.00 309	76.00 324	82.49 277	93.30 303

pmmvs5		90.17 264	89.09 262	93.40 269	92.10 310	89.77 278	99.74 134	95.58 321	85.88 289	87.24 278	95.74 251	73.41 293	96.48 289	88.54 251	83.56 274	93.95 276

MDTV_nov1_ep13			95.69 136		97.90 168	94.15 191	95.98 318	98.44 104	93.12 146	97.98 117	95.74 251	95.10 49	98.58 177	90.02 239	96.92 162

eth_miper_zixun_eth		92.41 216	91.93 212	93.84 261	97.28 205	90.68 261	98.83 250	96.97 279	88.57 255	89.19 246	95.73 253	89.24 172	96.69 282	89.97 240	81.55 284	94.15 258

IterMVS-SCA-FT		90.85 246	90.16 244	92.93 279	96.72 228	89.96 274	98.89 242	96.99 275	88.95 246	86.63 283	95.67 254	76.48 272	95.00 320	87.04 269	84.04 272	93.84 285

Baseline_NR-MVSNet		90.33 258	89.51 255	92.81 281	92.84 301	89.95 275	99.77 125	93.94 338	84.69 302	89.04 248	95.66 255	81.66 230	96.52 287	90.99 222	76.98 319	91.97 319

cl-mvsnet2		93.77 188	93.25 191	95.33 206	99.49 95	94.43 186	99.61 161	98.09 175	90.38 223	89.16 247	95.61 256	90.56 156	97.34 241	91.93 208	84.45 266	94.21 250

K. test v3		88.05 284	87.24 284	90.47 302	91.82 314	82.23 324	98.96 237	97.42 239	89.05 240	76.93 324	95.60 257	68.49 310	95.42 314	85.87 280	81.01 292	93.75 290

SCA		94.69 166	93.81 175	97.33 161	97.10 208	94.44 185	98.86 248	98.32 147	93.30 141	96.17 157	95.59 258	76.48 272	97.95 221	91.06 220	97.43 148	99.59 127

Patchmatch-test		92.65 212	91.50 221	96.10 191	96.85 220	90.49 266	91.50 336	97.19 256	82.76 312	90.23 218	95.59 258	95.02 53	98.00 217	77.41 318	96.98 161	99.82 94

cl-mvsnet1		92.32 217	91.60 217	94.47 237	97.31 203	92.74 217	99.58 164	96.75 297	86.99 276	87.64 269	95.54 260	89.55 166	96.50 288	88.58 250	82.44 278	94.17 252

Anonymous20231211		89.86 268	88.44 273	94.13 249	98.93 119	90.68 261	98.54 267	98.26 155	76.28 327	86.73 281	95.54 260	70.60 303	97.56 233	90.82 227	80.27 299	94.15 258

miper_ehance_all_eth		93.16 199	92.60 199	94.82 222	97.57 191	93.56 202	99.50 177	97.07 267	88.75 250	88.85 251	95.52 262	90.97 151	96.74 279	90.77 228	84.45 266	94.17 252

cl-mvsnet_		92.31 218	91.58 218	94.52 233	97.33 202	92.77 215	99.57 166	96.78 296	86.97 277	87.56 271	95.51 263	89.43 167	96.62 284	88.60 249	82.44 278	94.16 257

tfpnnormal		89.29 276	87.61 282	94.34 243	94.35 274	94.13 192	98.95 238	98.94 36	83.94 304	84.47 301	95.51 263	74.84 285	97.39 238	77.05 321	80.41 296	91.48 322

DeepMVS_CX				82.92 322	95.98 241	58.66 344		96.01 313	92.72 158	78.34 321	95.51 263	58.29 334	98.08 213	82.57 298	85.29 258	92.03 318

cl_fuxian		92.53 213	91.87 214	94.52 233	97.40 197	92.99 213	99.40 188	96.93 284	87.86 263	88.69 254	95.44 266	89.95 162	96.44 290	90.45 232	80.69 295	94.14 261

IterMVS		90.91 243	90.17 243	93.12 275	96.78 226	90.42 269	98.89 242	97.05 270	89.03 241	86.49 286	95.42 267	76.59 271	95.02 319	87.22 267	84.09 269	93.93 278
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UniMVSNet (Re)		93.07 202	92.13 207	95.88 196	94.84 266	96.24 137	99.88 84	98.98 34	92.49 175	89.25 242	95.40 268	87.09 191	97.14 255	93.13 198	78.16 309	94.26 245

tpm2		95.47 151	95.18 149	96.35 186	96.91 217	91.70 247	96.96 307	97.93 189	88.04 262	98.44 101	95.40 268	93.32 106	97.97 218	94.00 177	95.61 185	99.38 158

pmmvs6		85.69 290	83.84 295	91.26 296	90.00 328	84.41 316	97.82 294	96.15 311	75.86 329	81.29 311	95.39 270	61.21 330	96.87 274	83.52 295	73.29 328	92.50 313

IterMVS-LS		92.69 210	92.11 208	94.43 241	96.80 223	92.74 217	99.45 185	96.89 287	88.98 243	89.65 233	95.38 271	88.77 176	96.34 294	90.98 223	82.04 281	94.22 248
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Effi-MVS+-dtu		94.53 174	95.30 145	92.22 286	97.77 178	82.54 321	99.59 163	97.06 268	94.92 80	95.29 171	95.37 272	85.81 201	97.89 224	94.80 157	97.07 158	96.23 218

v2v482		91.30 235	90.07 246	95.01 214	93.13 293	93.79 197	99.77 125	97.02 271	88.05 261	89.25 242	95.37 272	80.73 241	97.15 254	87.28 266	80.04 301	94.09 264

FMVSNet3		92.69 210	91.58 218	95.99 192	98.29 146	97.42 99	99.26 208	97.62 212	89.80 234	89.68 230	95.32 274	81.62 232	96.27 297	87.01 271	85.65 255	94.29 243

MVP-Stereo		90.93 242	90.45 236	92.37 285	91.25 320	88.76 286	98.05 290	96.17 310	87.27 271	84.04 302	95.30 275	78.46 262	97.27 249	83.78 292	99.70 90	91.09 323
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
anonymousdsp		91.79 231	90.92 229	94.41 242	90.76 323	92.93 214	98.93 240	97.17 259	89.08 239	87.46 274	95.30 275	78.43 263	96.92 271	92.38 203	88.73 229	93.39 301

v1921920		90.46 254	89.12 261	94.50 235	92.96 300	92.46 226	99.49 179	96.98 277	86.10 286	89.61 235	95.30 275	78.55 261	97.03 266	82.17 301	80.89 294	94.01 270

VPA-MVSNet		92.70 209	91.55 220	96.16 189	95.09 262	96.20 138	98.88 244	99.00 33	91.02 214	91.82 205	95.29 278	76.05 278	97.96 220	95.62 146	81.19 287	94.30 242

PatchmatchNet		95.94 140	95.45 140	97.39 157	97.83 174	94.41 187	96.05 317	98.40 129	92.86 150	97.09 135	95.28 279	94.21 85	98.07 215	89.26 245	98.11 135	99.70 109
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
miper_lstm_enhance		91.81 226	91.39 224	93.06 278	97.34 200	89.18 284	99.38 193	96.79 295	86.70 280	87.47 273	95.22 280	90.00 161	95.86 311	88.26 254	81.37 286	94.15 258

test_0402		85.58 291	83.94 294	90.50 301	93.81 283	85.04 313	98.55 265	95.20 328	76.01 328	79.72 317	95.13 281	64.15 324	96.26 298	66.04 337	86.88 249	90.21 330

tpmrst		96.27 135	95.98 122	97.13 163	97.96 165	93.15 209	96.34 313	98.17 166	92.07 184	98.71 90	95.12 282	93.91 92	98.73 169	94.91 154	96.62 165	99.50 146

V42		91.28 237	90.12 245	94.74 223	93.42 290	93.46 204	99.68 147	97.02 271	87.36 269	89.85 228	95.05 283	81.31 235	97.34 241	87.34 265	80.07 300	93.40 300

EPMVS		96.53 123	96.01 119	98.09 131	98.43 142	96.12 143	96.36 312	99.43 19	93.53 135	97.64 124	95.04 284	94.41 69	98.38 197	91.13 218	98.11 135	99.75 103

v1192		90.62 252	89.25 259	94.72 225	93.13 293	93.07 210	99.50 177	97.02 271	86.33 284	89.56 236	95.01 285	79.22 254	97.09 261	82.34 300	81.16 288	94.01 270

v148		90.70 248	89.63 250	93.92 258	92.97 299	90.97 256	99.75 131	96.89 287	87.51 266	88.27 263	95.01 285	81.67 229	97.04 264	87.40 264	77.17 318	93.75 290

FMVSNet2		91.02 241	89.56 252	95.41 205	97.53 192	95.74 154	98.98 234	97.41 241	87.05 273	88.43 259	95.00 287	71.34 299	96.24 299	85.12 283	85.21 260	94.25 247

our_test_3		90.39 255	89.48 257	93.12 275	92.40 306	89.57 280	99.33 199	96.35 307	87.84 264	85.30 297	94.99 288	84.14 216	96.09 304	80.38 309	84.56 265	93.71 295

v1144		91.09 240	89.83 247	94.87 219	93.25 292	93.69 200	99.62 160	96.98 277	86.83 279	89.64 234	94.99 288	80.94 238	97.05 262	85.08 284	81.16 288	93.87 283

v144192		90.79 247	89.52 254	94.59 229	93.11 296	92.77 215	99.56 168	96.99 275	86.38 283	89.82 229	94.95 290	80.50 246	97.10 259	83.98 290	80.41 296	93.90 280

CostFormer		96.10 136	95.88 132	96.78 171	97.03 212	92.55 225	97.08 304	97.83 200	90.04 231	98.72 89	94.89 291	95.01 55	98.29 203	96.54 135	95.77 181	99.50 146

v1240		90.20 262	88.79 268	94.44 239	93.05 298	92.27 230	99.38 193	96.92 285	85.89 288	89.36 239	94.87 292	77.89 264	97.03 266	80.66 308	81.08 290	94.01 270

v7n		89.65 271	88.29 276	93.72 263	92.22 308	90.56 265	99.07 224	97.10 264	85.42 298	86.73 281	94.72 293	80.06 249	97.13 256	81.14 306	78.12 310	93.49 298

GBi-Net		90.88 244	89.82 248	94.08 250	97.53 192	91.97 234	98.43 272	96.95 280	87.05 273	89.68 230	94.72 293	71.34 299	96.11 301	87.01 271	85.65 255	94.17 252

test1		90.88 244	89.82 248	94.08 250	97.53 192	91.97 234	98.43 272	96.95 280	87.05 273	89.68 230	94.72 293	71.34 299	96.11 301	87.01 271	85.65 255	94.17 252

FMVSNet1		88.50 281	86.64 286	94.08 250	95.62 257	91.97 234	98.43 272	96.95 280	83.00 310	86.08 293	94.72 293	59.09 333	96.11 301	81.82 304	84.07 270	94.17 252

dp		95.05 158	94.43 162	96.91 167	97.99 164	92.73 219	96.29 314	97.98 184	89.70 235	95.93 160	94.67 297	93.83 96	98.45 186	86.91 274	96.53 167	99.54 140

test20.03		84.72 299	83.99 292	86.91 317	88.19 333	80.62 332	98.88 244	95.94 314	88.36 258	78.87 318	94.62 298	68.75 308	89.11 340	66.52 335	75.82 323	91.00 324

D2MVS		92.76 207	92.59 201	93.27 272	95.13 261	89.54 281	99.69 145	99.38 21	92.26 179	87.59 270	94.61 299	85.05 210	97.79 226	91.59 213	88.01 239	92.47 314

v8		90.54 253	89.17 260	94.66 226	93.43 289	93.40 207	99.20 211	96.94 283	85.76 290	87.56 271	94.51 300	81.96 228	97.19 251	84.94 285	78.25 308	93.38 302

v10		90.25 261	88.82 267	94.57 231	93.53 287	93.43 205	99.08 220	96.87 289	85.00 299	87.34 277	94.51 300	80.93 239	97.02 268	82.85 297	79.23 303	93.26 304

ADS-MVSNet2		93.80 187	93.88 173	93.55 268	97.87 171	85.94 307	94.24 323	96.84 290	90.07 229	96.43 151	94.48 302	90.29 159	95.37 315	87.44 262	97.23 154	99.36 160

ADS-MVSNet		94.79 162	94.02 169	97.11 165	97.87 171	93.79 197	94.24 323	98.16 169	90.07 229	96.43 151	94.48 302	90.29 159	98.19 210	87.44 262	97.23 154	99.36 160

WR-MVS_H		91.30 235	90.35 237	94.15 247	94.17 277	92.62 224	99.17 214	98.94 36	88.87 248	86.48 287	94.46 304	84.36 214	96.61 285	88.19 255	78.51 307	93.21 306

LCM-MVSNet-Re		92.31 218	92.60 199	91.43 294	97.53 192	79.27 335	99.02 232	91.83 342	92.07 184	80.31 314	94.38 305	83.50 220	95.48 313	97.22 122	97.58 146	99.54 140

tpmvs		94.28 180	93.57 180	96.40 183	98.55 136	91.50 252	95.70 322	98.55 80	87.47 267	92.15 203	94.26 306	91.42 140	98.95 157	88.15 256	95.85 179	98.76 195

tpm		93.70 192	93.41 186	94.58 230	95.36 260	87.41 301	97.01 305	96.90 286	90.85 217	96.72 144	94.14 307	90.40 157	96.84 275	90.75 229	88.54 234	99.51 144

Anonymous20231206		86.32 288	85.42 289	89.02 311	89.11 331	80.53 333	99.05 229	95.28 325	85.43 297	82.82 307	93.92 308	74.40 288	93.44 333	66.99 334	81.83 283	93.08 308

UnsupCasMVSNet_eth		85.52 292	83.99 292	90.10 305	89.36 330	83.51 318	96.65 309	97.99 182	89.14 238	75.89 328	93.83 309	63.25 326	93.92 327	81.92 303	67.90 335	92.88 310

tpm cat1		93.51 194	92.52 203	96.47 179	97.77 178	91.47 253	96.13 315	98.06 178	80.98 318	92.91 198	93.78 310	89.66 164	98.87 159	87.03 270	96.39 169	99.09 182

EG-PatchMatch MVS		85.35 295	83.81 296	89.99 307	90.39 325	81.89 326	98.21 284	96.09 312	81.78 316	74.73 330	93.72 311	51.56 340	97.12 258	79.16 313	88.61 231	90.96 325

N_pmnet		80.06 308	80.78 306	77.89 323	91.94 311	45.28 350	98.80 252	56.82 354	78.10 325	80.08 316	93.33 312	77.03 266	95.76 312	68.14 333	82.81 276	92.64 312

MDA-MVSNet-bldmvs		84.09 301	81.52 305	91.81 292	91.32 319	88.00 299	98.67 261	95.92 315	80.22 320	55.60 343	93.32 313	68.29 312	93.60 332	73.76 326	76.61 322	93.82 287

CR-MVSNet		93.45 197	92.62 198	95.94 194	96.29 232	92.66 221	92.01 334	96.23 308	92.62 165	96.94 137	93.31 314	91.04 149	96.03 306	79.23 312	95.96 176	99.13 180

Patchmtry		89.70 270	88.49 272	93.33 270	96.24 234	89.94 277	91.37 337	96.23 308	78.22 324	87.69 268	93.31 314	91.04 149	96.03 306	80.18 311	82.10 280	94.02 268

MIMVSNet		90.30 259	88.67 270	95.17 211	96.45 231	91.64 249	92.39 332	97.15 262	85.99 287	90.50 216	93.19 316	66.95 315	94.86 323	82.01 302	93.43 206	99.01 185

YYNet1		85.50 294	83.33 297	92.00 289	90.89 322	88.38 295	99.22 210	96.55 303	79.60 322	57.26 341	92.72 317	79.09 257	93.78 330	77.25 319	77.37 317	93.84 285

MVS_0304		89.28 277	88.31 275	92.21 287	97.05 211	86.53 304	97.76 296	99.57 12	85.58 295	93.86 189	92.71 318	51.04 341	96.30 296	84.49 287	92.72 212	93.79 288

MDA-MVSNet_test_wron		85.51 293	83.32 298	92.10 288	90.96 321	88.58 291	99.20 211	96.52 304	79.70 321	57.12 342	92.69 319	79.11 256	93.86 329	77.10 320	77.46 316	93.86 284

MIMVSNet1		82.58 304	80.51 307	88.78 313	86.68 334	84.20 317	96.65 309	95.41 323	78.75 323	78.59 320	92.44 320	51.88 339	89.76 339	65.26 338	78.95 304	92.38 315

FMVSNet5		88.32 282	87.47 283	90.88 297	96.90 218	88.39 294	97.28 302	95.68 318	82.60 313	84.67 300	92.40 321	79.83 251	91.16 336	76.39 323	81.51 285	93.09 307

DSMNet-mixed		88.28 283	88.24 277	88.42 315	89.64 329	75.38 337	98.06 289	89.86 345	85.59 294	88.20 264	92.14 322	76.15 277	91.95 335	78.46 314	96.05 174	97.92 204

patchmatchnet-post											91.70 323	95.12 48	97.95 221

OpenMVS_ROB	79.82 20	83.77 303	81.68 304	90.03 306	88.30 332	82.82 319	98.46 270	95.22 327	73.92 335	76.00 327	91.29 324	55.00 337	96.94 270	68.40 332	88.51 235	90.34 328

Patchmatch-RL test		86.90 287	85.98 288	89.67 308	84.45 336	75.59 336	89.71 339	92.43 340	86.89 278	77.83 322	90.94 325	94.22 82	93.63 331	87.75 260	69.61 330	99.79 97

FPMVS		68.72 310	68.72 312	68.71 328	65.95 347	44.27 352	95.97 319	94.74 332	51.13 341	53.26 344	90.50 326	25.11 349	83.00 344	60.80 340	80.97 293	78.87 340

new_pmnet		84.49 300	82.92 300	89.21 310	90.03 327	82.60 320	96.89 308	95.62 320	80.59 319	75.77 329	89.17 327	65.04 322	94.79 324	72.12 327	81.02 291	90.23 329

PM-MVS		80.47 306	78.88 309	85.26 319	83.79 338	72.22 338	95.89 320	91.08 343	85.71 293	76.56 326	88.30 328	36.64 344	93.90 328	82.39 299	69.57 331	89.66 333

pmmvs3		80.27 307	77.77 310	87.76 316	80.32 341	82.43 322	98.23 282	91.97 341	72.74 336	78.75 319	87.97 329	57.30 336	90.99 337	70.31 329	62.37 339	89.87 331

pmmvs-eth3d		84.03 302	81.97 302	90.20 304	84.15 337	87.09 302	98.10 288	94.73 333	83.05 309	74.10 331	87.77 330	65.56 320	94.01 326	81.08 307	69.24 332	89.49 334

test123		37.68 321	39.14 323	33.31 334	19.94 354	24.83 355	98.36 276	9.75 356	15.53 350	51.31 345	87.14 331	19.62 352	17.74 352	47.10 344	3.47 350	57.36 345

new-patchmatchnet		81.19 305	79.34 308	86.76 318	82.86 339	80.36 334	97.92 292	95.27 326	82.09 315	72.02 332	86.87 332	62.81 327	90.74 338	71.10 328	63.08 338	89.19 336

ambc				83.23 321	77.17 342	62.61 341	87.38 341	94.55 335		76.72 325	86.65 333	30.16 345	96.36 293	84.85 286	69.86 329	90.73 327

testing_2		85.10 296	81.72 303	95.22 209	82.25 340	94.16 190	97.54 298	97.01 274	88.15 259	62.23 337	86.43 334	44.43 343	97.18 252	92.28 205	85.20 261	94.31 241

PatchT		90.38 256	88.75 269	95.25 208	95.99 239	90.16 272	91.22 338	97.54 223	76.80 326	97.26 131	86.01 335	91.88 136	96.07 305	66.16 336	95.91 178	99.51 144

RPMNet		89.39 274	87.20 285	95.94 194	96.29 232	92.66 221	92.01 334	97.63 209	70.19 338	96.94 137	85.87 336	87.25 189	96.03 306	62.69 339	95.96 176	99.13 180

UnsupCasMVSNet_bld		79.97 309	77.03 311	88.78 313	85.62 335	81.98 325	93.66 328	97.35 246	75.51 332	70.79 334	83.05 337	48.70 342	94.91 322	78.31 315	60.29 340	89.46 335

LCM-MVSNet		67.77 311	64.73 314	76.87 324	62.95 349	56.25 346	89.37 340	93.74 339	44.53 343	61.99 338	80.74 338	20.42 351	86.53 342	69.37 331	59.50 341	87.84 337

PMMVS2		67.15 312	64.15 315	76.14 325	70.56 346	62.07 343	93.89 326	87.52 349	58.09 340	60.02 339	78.32 339	22.38 350	84.54 343	59.56 341	47.03 342	81.80 339

JIA-IIPM		91.76 232	90.70 231	94.94 217	96.11 235	87.51 300	93.16 330	98.13 174	75.79 330	97.58 125	77.68 340	92.84 117	97.97 218	88.47 253	96.54 166	99.33 164

PMVS	49.05 23	53.75 316	51.34 319	60.97 331	40.80 353	34.68 353	74.82 345	89.62 347	37.55 345	28.67 351	72.12 341	7.09 355	81.63 345	43.17 346	68.21 334	66.59 343
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVS-HIRNet		86.22 289	83.19 299	95.31 207	96.71 229	90.29 270	92.12 333	97.33 248	62.85 339	86.82 280	70.37 342	69.37 306	97.49 235	75.12 325	97.99 141	98.15 201

gg-mvs-nofinetune		93.51 194	91.86 215	98.47 112	97.72 185	97.96 76	92.62 331	98.51 93	74.70 333	97.33 130	69.59 343	98.91 3	97.79 226	97.77 110	99.56 100	99.67 114

Gipuma		66.95 313	65.00 313	72.79 326	91.52 317	67.96 340	66.16 346	95.15 330	47.89 342	58.54 340	67.99 344	29.74 346	87.54 341	50.20 343	77.83 312	62.87 344
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ANet_high		56.10 315	52.24 317	67.66 329	49.27 351	56.82 345	83.94 342	82.02 350	70.47 337	33.28 350	64.54 345	17.23 353	69.16 348	45.59 345	23.85 346	77.02 341

E-PMN		52.30 317	52.18 318	52.67 332	71.51 344	45.40 349	93.62 329	76.60 352	36.01 346	43.50 347	64.13 346	27.11 348	67.31 349	31.06 348	26.06 344	45.30 348

test_post											63.35 347	94.43 68	98.13 211

MVE	53.74 22	51.54 318	47.86 321	62.60 330	59.56 350	50.93 347	79.41 344	77.69 351	35.69 347	36.27 349	61.76 348	5.79 357	69.63 347	37.97 347	36.61 343	67.24 342
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		51.44 319	51.22 320	52.11 333	70.71 345	44.97 351	94.04 325	75.66 353	35.34 348	42.40 348	61.56 349	28.93 347	65.87 350	27.64 349	24.73 345	45.49 347

test_post1							95.78 321				59.23 350	93.20 111	97.74 228	91.06 220

X-MVStestdata		93.83 184	92.06 210	99.15 61	99.94 14	97.50 93	99.94 55	98.42 123	96.22 49	99.41 54	41.37 351	94.34 75	99.96 53	98.92 59	99.95 50	99.99 20

wuyk23d		20.37 323	20.84 325	18.99 336	65.34 348	27.73 354	50.43 347	7.67 357	9.50 351	8.01 352	6.34 352	6.13 356	26.24 351	23.40 350	10.69 349	2.99 349

uanet_test		0.00 326	0.00 328	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

pcd_1.5k_mvsjas		7.60 325	10.13 327	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	91.20 144	0.00 354	0.00 351	0.00 351	0.00 350

sosnet-low-res		0.00 326	0.00 328	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

sosnet		0.00 326	0.00 328	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

uncertanet		0.00 326	0.00 328	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

Regformer		0.00 326	0.00 328	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

uanet		0.00 326	0.00 328	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

IU-MVS					99.93 26	99.31 7		98.41 127	97.71 8	99.84 8				100.00 1	100.00 1	100.00 1

save fliter					99.82 63	98.79 33	99.96 23	98.40 129	97.66 10

test_0728_SECOND				99.82 5	99.94 14	99.47 5	99.95 40	98.43 112					100.00 1	99.99 5	100.00 1	100.00 1

GSMVS																99.59 127

test_part2					99.89 44	99.25 13				99.49 48

test_part1				0.00 337		0.00 357	0.00 348	98.41 127				0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

sam_mvs1												94.72 63				99.59 127

sam_mvs												94.25 81

MTGPA								98.28 151

MTMP							99.87 87	96.49 305

test9_res														99.71 29	99.99 20	100.00 1

agg_prior2														99.48 35	100.00 1	100.00 1

agg_prior					99.93 26	98.77 36		98.43 112		99.63 35			99.85 94

test_prior4						98.05 70	99.94 55

test_prior				99.43 35	99.94 14	98.49 56		98.65 59					99.80 106			99.99 20

旧先验2							99.46 184		94.21 107	99.85 6			99.95 60	96.96 129

新几何2							99.40 188

无先验							99.49 179	98.71 52	93.46 137				100.00 1	94.36 169		99.99 20

原ACMM2							99.90 73

testdata2													99.99 36	90.54 231

segment_acmp												96.68 22

testdata1							99.28 206		96.35 48

test12				99.43 35	99.74 73	98.56 52		98.40 129		99.65 33		94.76 62	99.75 116		99.98 33	99.99 20

plane_prior7					95.71 252	91.59 251

plane_prior6					95.76 247	91.72 246						80.47 247

plane_prior5								97.87 195					98.37 198	97.79 108	89.55 218	94.52 224

plane_prior3						91.64 249			96.63 38	93.01 195

plane_prior2							99.84 105		96.38 44

plane_prior1					95.73 249

plane_prior						91.74 243	99.86 98		96.76 34						89.59 217

n2								0.00 358

nn								0.00 358

door-mid								89.69 346

test11								98.44 104

door								90.31 344

HQP5-MVS						91.85 239

HQP-NCC					95.78 243		99.87 87		96.82 30	93.37 191

ACMP_Plane					95.78 243		99.87 87		96.82 30	93.37 191

BP-MVS														97.92 105

HQP4-MVS										93.37 191			98.39 193			94.53 222

HQP3-MVS								97.89 193							89.60 215

HQP2-MVS												80.65 243

MDTV_nov1_ep13_2view						96.26 133	96.11 316		91.89 189	98.06 115		94.40 70		94.30 172		99.67 114

ACMMP++_ref															87.04 248

ACMMP++															88.23 237

Test By Simon												92.82 119

High-resolution multi-view benchmark