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.

LCM-MVSNet		99.43 1	99.49 1	99.24 1	99.95 1	98.13 1	99.37 1	99.57 1	99.82 1	99.86 1	99.85 1	99.52 1	99.73 1	97.58 1	99.94 1	99.85 1

XVG-OURS-SEG-HR		95.38 78	95.00 100	96.51 46	98.10 81	94.07 20	92.46 194	98.13 50	90.69 140	93.75 204	96.25 177	98.03 2	97.02 293	92.08 105	95.55 298	98.45 127

pmmvs6		96.80 12	97.36 9	95.15 97	99.12 8	87.82 129	96.68 30	97.86 85	96.10 27	98.14 24	99.28 3	97.94 3	98.21 209	91.38 127	99.69 14	99.42 19

UniMVSNet_ETH3D		97.13 5	97.72 3	95.35 84	99.51 2	87.38 134	97.70 8	97.54 112	98.16 2	98.94 2	99.33 2	97.84 4	99.08 94	90.73 139	99.73 13	99.59 13

ACMH	88.36 12	96.59 27	97.43 5	94.07 141	98.56 42	85.33 186	96.33 47	98.30 27	94.66 42	98.72 8	98.30 35	97.51 5	98.00 228	94.87 29	99.59 28	98.86 78
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HPM-MVS_fast		97.01 6	96.89 14	97.39 21	99.12 8	93.92 28	97.16 14	98.17 45	93.11 74	96.48 90	97.36 94	96.92 6	99.34 63	94.31 38	99.38 59	98.92 72

ACMH+	88.43 11	96.48 30	96.82 15	95.47 81	98.54 48	89.06 101	95.65 79	98.61 12	96.10 27	98.16 23	97.52 81	96.90 7	98.62 169	90.30 153	99.60 26	98.72 97

HPM-MVS		96.81 11	96.62 22	97.36 23	98.89 20	93.53 38	97.51 10	98.44 16	92.35 88	95.95 116	96.41 160	96.71 8	99.42 33	93.99 45	99.36 60	99.13 41
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mvs_tets		96.83 8	96.71 18	97.17 27	98.83 25	92.51 48	96.58 33	97.61 107	87.57 207	98.80 7	98.90 9	96.50 9	99.59 13	96.15 13	99.47 43	99.40 21

SED-MVS		96.00 51	96.41 32	94.76 109	98.51 51	86.97 144	95.21 94	98.10 54	91.95 98	97.63 35	97.25 104	96.48 10	99.35 60	93.29 73	99.29 74	97.95 169

test_241102_ONE					98.51 51	86.97 144		98.10 54	91.85 104	97.63 35	97.03 121	96.48 10	98.95 114

LPG-MVS_test		96.38 39	96.23 39	96.84 38	98.36 66	92.13 52	95.33 90	98.25 31	91.78 111	97.07 63	97.22 108	96.38 12	99.28 72	92.07 106	99.59 28	99.11 44

LGP-MVS_train				96.84 38	98.36 66	92.13 52		98.25 31	91.78 111	97.07 63	97.22 108	96.38 12	99.28 72	92.07 106	99.59 28	99.11 44

ACMM	88.83 9	96.30 42	96.07 50	96.97 34	98.39 62	92.95 44	94.74 111	98.03 69	90.82 137	97.15 59	96.85 133	96.25 14	99.00 106	93.10 81	99.33 66	98.95 65
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
wuyk23d		87.83 283	90.79 215	78.96 372	90.46 359	88.63 110	92.72 181	90.67 327	91.65 119	98.68 11	97.64 71	96.06 15	77.53 394	59.84 389	99.41 56	70.73 392

testf1		96.77 14	96.49 26	97.60 8	99.01 14	96.70 3	96.31 50	98.33 22	94.96 38	97.30 54	97.93 55	96.05 16	97.90 235	89.32 178	99.23 86	98.19 144

APD_test2		96.77 14	96.49 26	97.60 8	99.01 14	96.70 3	96.31 50	98.33 22	94.96 38	97.30 54	97.93 55	96.05 16	97.90 235	89.32 178	99.23 86	98.19 144

ACMP	88.15 13	95.71 62	95.43 79	96.54 45	98.17 77	91.73 60	94.24 132	98.08 57	89.46 163	96.61 87	96.47 156	95.85 18	99.12 91	90.45 145	99.56 36	98.77 91
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_fmvsmconf0.01_n		95.90 54	96.09 47	95.31 89	97.30 137	89.21 97	94.24 132	98.76 10	86.25 223	97.56 39	98.66 18	95.73 19	98.44 190	97.35 2	98.99 113	98.27 138

TransMVSNet (Re)		95.27 87	96.04 52	92.97 179	98.37 65	81.92 231	95.07 101	96.76 176	93.97 55	97.77 31	98.57 23	95.72 20	97.90 235	88.89 195	99.23 86	99.08 48

ZNCC-MVS		96.42 35	96.20 41	97.07 30	98.80 30	92.79 46	96.08 61	98.16 48	91.74 115	95.34 149	96.36 168	95.68 21	99.44 29	94.41 36	99.28 79	98.97 62

ACMMP_NAP		96.21 44	96.12 46	96.49 48	98.90 19	91.42 63	94.57 119	98.03 69	90.42 148	96.37 93	97.35 97	95.68 21	99.25 75	94.44 35	99.34 64	98.80 86

APD-MVS_3200maxsize		96.82 9	96.65 20	97.32 25	97.95 95	93.82 33	96.31 50	98.25 31	95.51 35	96.99 70	97.05 120	95.63 23	99.39 49	93.31 72	98.88 128	98.75 92

DVP-MVS		95.82 58	96.18 42	94.72 111	98.51 51	86.69 152	95.20 96	97.00 155	91.85 104	97.40 52	97.35 97	95.58 24	99.34 63	93.44 66	99.31 69	98.13 150
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					98.51 51	86.69 152	95.34 89	98.18 41	91.85 104	97.63 35	97.37 91	95.58 24

MP-MVS-pluss		96.08 48	95.92 58	96.57 44	99.06 10	91.21 65	93.25 165	98.32 24	87.89 198	96.86 75	97.38 90	95.55 26	99.39 49	95.47 24	99.47 43	99.11 44
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
COLMAP_ROB	91.06 5	96.75 16	96.62 22	97.13 28	98.38 63	94.31 17	96.79 26	98.32 24	96.69 17	96.86 75	97.56 76	95.48 27	98.77 146	90.11 162	99.44 50	98.31 135
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
SD-MVS		95.19 88	95.73 67	93.55 161	96.62 174	88.88 107	94.67 113	98.05 64	91.26 126	97.25 58	96.40 161	95.42 28	94.36 353	92.72 93	99.19 92	97.40 218
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
RE-MVS-def			96.66 19		98.07 83	95.27 9	96.37 44	98.12 51	95.66 33	97.00 68	97.03 121	95.40 29		93.49 60	98.84 133	98.00 161

test_241102_TWO								98.10 54	91.95 98	97.54 40	97.25 104	95.37 30	99.35 60	93.29 73	99.25 83	98.49 124

HFP-MVS		96.39 38	96.17 44	97.04 31	98.51 51	93.37 39	96.30 54	97.98 75	92.35 88	95.63 133	96.47 156	95.37 30	99.27 74	93.78 50	99.14 99	98.48 125

jajsoiax		96.59 27	96.42 29	97.12 29	98.76 31	92.49 49	96.44 41	97.42 121	86.96 216	98.71 10	98.72 17	95.36 32	99.56 17	95.92 14	99.45 47	99.32 27

test_fmvsmconf0.1_n		95.61 65	95.72 68	95.26 90	96.85 159	89.20 98	93.51 157	98.60 13	85.68 235	97.42 50	98.30 35	95.34 33	98.39 191	96.85 3	98.98 114	98.19 144

TranMVSNet+NR-MVSNet		96.07 49	96.26 38	95.50 80	98.26 71	87.69 131	93.75 150	97.86 85	95.96 32	97.48 46	97.14 114	95.33 34	99.44 29	90.79 137	99.76 10	99.38 22

PMVS	87.21 14	94.97 94	95.33 85	93.91 149	98.97 17	97.16 2	95.54 85	95.85 218	96.47 22	93.40 215	97.46 87	95.31 35	95.47 335	86.18 245	98.78 144	89.11 375
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
pm-mvs1		95.43 73	95.94 55	93.93 148	98.38 63	85.08 189	95.46 87	97.12 148	91.84 107	97.28 56	98.46 30	95.30 36	97.71 258	90.17 160	99.42 52	98.99 56

PGM-MVS		96.32 40	95.94 55	97.43 18	98.59 41	93.84 32	95.33 90	98.30 27	91.40 124	95.76 125	96.87 132	95.26 37	99.45 27	92.77 89	99.21 90	99.00 54

PS-CasMVS		96.69 20	97.43 5	94.49 128	99.13 6	84.09 203	96.61 32	97.97 77	97.91 5	98.64 13	98.13 41	95.24 38	99.65 3	93.39 70	99.84 3	99.72 2

test_fmvsmconf_n		95.43 73	95.50 75	95.22 94	96.48 186	89.19 99	93.23 167	98.36 21	85.61 238	96.92 73	98.02 50	95.23 39	98.38 194	96.69 6	98.95 123	98.09 152

GST-MVS		96.24 43	95.99 54	97.00 33	98.65 34	92.71 47	95.69 78	98.01 72	92.08 96	95.74 128	96.28 174	95.22 40	99.42 33	93.17 79	99.06 103	98.88 77

LTVRE_ROB	93.87 1	97.93 2	98.16 2	97.26 26	98.81 28	93.86 31	99.07 2	98.98 6	97.01 13	98.92 4	98.78 14	95.22 40	98.61 170	96.85 3	99.77 9	99.31 28
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
DPE-MVS		95.89 55	95.88 59	95.92 64	97.93 96	89.83 85	93.46 159	98.30 27	92.37 86	97.75 32	96.95 126	95.14 42	99.51 20	91.74 116	99.28 79	98.41 129
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_one_0601					98.26 71	87.14 140		98.18 41	94.25 48	96.99 70	97.36 94	95.13 43

nrg030		96.32 40	96.55 25	95.62 76	97.83 102	88.55 115	95.77 74	98.29 30	92.68 79	98.03 26	97.91 59	95.13 43	98.95 114	93.85 48	99.49 42	99.36 24

APDe-MVS		96.46 31	96.64 21	95.93 62	97.68 116	89.38 95	96.90 22	98.41 19	92.52 83	97.43 48	97.92 58	95.11 45	99.50 21	94.45 34	99.30 71	98.92 72
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMP		96.61 24	96.34 34	97.43 18	98.61 38	93.88 29	96.95 21	98.18 41	92.26 91	96.33 95	96.84 135	95.10 46	99.40 46	93.47 63	99.33 66	99.02 53
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
SR-MVS		96.70 19	96.42 29	97.54 11	98.05 85	94.69 11	96.13 59	98.07 60	95.17 37	96.82 77	96.73 144	95.09 47	99.43 32	92.99 86	98.71 151	98.50 122

OPM-MVS		95.61 65	95.45 77	96.08 54	98.49 58	91.00 68	92.65 186	97.33 131	90.05 153	96.77 80	96.85 133	95.04 48	98.56 177	92.77 89	99.06 103	98.70 101
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DTE-MVSNet		96.74 17	97.43 5	94.67 113	99.13 6	84.68 192	96.51 35	97.94 83	98.14 3	98.67 12	98.32 34	95.04 48	99.69 2	93.27 75	99.82 7	99.62 10

region2R		96.41 36	96.09 47	97.38 22	98.62 36	93.81 35	96.32 49	97.96 78	92.26 91	95.28 153	96.57 153	95.02 50	99.41 39	93.63 54	99.11 101	98.94 66

PEN-MVS		96.69 20	97.39 8	94.61 118	99.16 4	84.50 193	96.54 34	98.05 64	98.06 4	98.64 13	98.25 37	95.01 51	99.65 3	92.95 87	99.83 5	99.68 4

SteuartSystems-ACMMP		96.40 37	96.30 36	96.71 40	98.63 35	91.96 55	95.70 76	98.01 72	93.34 70	96.64 85	96.57 153	94.99 52	99.36 58	93.48 62	99.34 64	98.82 82
Skip Steuart: Steuart Systems R&D Blog.
canonicalmvs		94.59 108	94.69 111	94.30 134	95.60 249	87.03 143	95.59 81	98.24 34	91.56 121	95.21 159	92.04 319	94.95 53	98.66 165	91.45 125	97.57 241	97.20 228

ACMMPR		96.46 31	96.14 45	97.41 20	98.60 39	93.82 33	96.30 54	97.96 78	92.35 88	95.57 135	96.61 151	94.93 54	99.41 39	93.78 50	99.15 98	99.00 54

tt0805		95.42 76	95.93 57	93.86 152	98.75 32	88.47 117	97.68 9	94.29 268	96.48 21	95.38 145	93.63 281	94.89 55	97.94 234	95.38 27	96.92 267	95.17 300

SR-MVS-dyc-post		96.84 7	96.60 24	97.56 10	98.07 83	95.27 9	96.37 44	98.12 51	95.66 33	97.00 68	97.03 121	94.85 56	99.42 33	93.49 60	98.84 133	98.00 161

casdiffmvs_mvg		95.10 90	95.62 71	93.53 164	96.25 205	83.23 213	92.66 185	98.19 39	93.06 75	97.49 44	97.15 113	94.78 57	98.71 158	92.27 101	98.72 149	98.65 107
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CP-MVS		96.44 34	96.08 49	97.54 11	98.29 68	94.62 14	96.80 25	98.08 57	92.67 81	95.08 165	96.39 165	94.77 58	99.42 33	93.17 79	99.44 50	98.58 119

test_0728_THIRD									93.26 71	97.40 52	97.35 97	94.69 59	99.34 63	93.88 46	99.42 52	98.89 75

9.14			94.81 104		97.49 127		94.11 139	98.37 20	87.56 208	95.38 145	96.03 187	94.66 60	99.08 94	90.70 140	98.97 119

GeoE		94.55 110	94.68 113	94.15 137	97.23 139	85.11 188	94.14 138	97.34 130	88.71 181	95.26 154	95.50 212	94.65 61	99.12 91	90.94 134	98.40 179	98.23 140

TDRefinement		97.68 3	97.60 4	97.93 2	99.02 12	95.95 8	98.61 3	98.81 8	97.41 10	97.28 56	98.46 30	94.62 62	98.84 129	94.64 32	99.53 38	98.99 56

SDMVSNet		94.43 114	95.02 98	92.69 192	97.93 96	82.88 221	91.92 219	95.99 214	93.65 65	95.51 137	98.63 20	94.60 63	96.48 310	87.57 219	99.35 61	98.70 101

XVS		96.49 29	96.18 42	97.44 16	98.56 42	93.99 26	96.50 36	97.95 80	94.58 43	94.38 187	96.49 155	94.56 64	99.39 49	93.57 56	99.05 106	98.93 68

X-MVStestdata		90.70 212	88.45 259	97.44 16	98.56 42	93.99 26	96.50 36	97.95 80	94.58 43	94.38 187	26.89 395	94.56 64	99.39 49	93.57 56	99.05 106	98.93 68

mPP-MVS		96.46 31	96.05 51	97.69 4	98.62 36	94.65 13	96.45 39	97.74 98	92.59 82	95.47 140	96.68 147	94.50 66	99.42 33	93.10 81	99.26 82	98.99 56

sd_testset		93.94 135	94.39 119	92.61 198	97.93 96	83.24 212	93.17 169	95.04 248	93.65 65	95.51 137	98.63 20	94.49 67	95.89 327	81.72 292	99.35 61	98.70 101

DeepC-MVS	91.39 4	95.43 73	95.33 85	95.71 74	97.67 117	90.17 80	93.86 147	98.02 71	87.35 209	96.22 105	97.99 53	94.48 68	99.05 99	92.73 92	99.68 18	97.93 171
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SMA-MVS		95.77 59	95.54 74	96.47 49	98.27 70	91.19 66	95.09 99	97.79 95	86.48 219	97.42 50	97.51 84	94.47 69	99.29 70	93.55 58	99.29 74	98.93 68
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
SF-MVS		95.88 56	95.88 59	95.87 68	98.12 79	89.65 87	95.58 83	98.56 14	91.84 107	96.36 94	96.68 147	94.37 70	99.32 69	92.41 99	99.05 106	98.64 112

MP-MVS		96.14 46	95.68 69	97.51 13	98.81 28	94.06 21	96.10 60	97.78 96	92.73 78	93.48 212	96.72 145	94.23 71	99.42 33	91.99 108	99.29 74	99.05 51
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
anonymousdsp		96.74 17	96.42 29	97.68 6	98.00 91	94.03 25	96.97 20	97.61 107	87.68 205	98.45 18	98.77 15	94.20 72	99.50 21	96.70 5	99.40 57	99.53 15

test_0402		95.73 61	96.22 40	94.26 135	98.19 76	85.77 178	93.24 166	97.24 139	96.88 16	97.69 33	97.77 65	94.12 73	99.13 88	91.54 124	99.29 74	97.88 177

test_fmvsmvis_n_1920		95.08 91	95.40 81	94.13 139	96.66 169	87.75 130	93.44 161	98.49 15	85.57 240	98.27 20	97.11 116	94.11 74	97.75 255	96.26 11	98.72 149	96.89 239

Effi-MVS+		92.79 167	92.74 167	92.94 183	95.10 262	83.30 211	94.00 142	97.53 114	91.36 125	89.35 313	90.65 341	94.01 75	98.66 165	87.40 223	95.30 307	96.88 241

EC-MVSNet		95.44 72	95.62 71	94.89 103	96.93 154	87.69 131	96.48 38	99.14 4	93.93 56	92.77 241	94.52 253	93.95 76	99.49 24	93.62 55	99.22 89	97.51 209

OMC-MVS		94.22 125	93.69 142	95.81 69	97.25 138	91.27 64	92.27 205	97.40 122	87.10 215	94.56 182	95.42 216	93.74 77	98.11 218	86.62 235	98.85 132	98.06 153

LCM-MVSNet-Re		94.20 126	94.58 116	93.04 176	95.91 230	83.13 217	93.79 149	99.19 3	92.00 97	98.84 5	98.04 48	93.64 78	99.02 104	81.28 296	98.54 169	96.96 236

CS-MVS		95.77 59	95.58 73	96.37 50	96.84 160	91.72 61	96.73 29	99.06 5	94.23 49	92.48 250	94.79 243	93.56 79	99.49 24	93.47 63	99.05 106	97.89 176

MTAPA		96.65 22	96.38 33	97.47 15	98.95 18	94.05 23	95.88 70	97.62 105	94.46 47	96.29 99	96.94 127	93.56 79	99.37 57	94.29 39	99.42 52	98.99 56

CS-MVS-test		95.32 81	95.10 96	95.96 58	96.86 158	90.75 74	96.33 47	99.20 2	93.99 53	91.03 283	93.73 279	93.52 81	99.55 18	91.81 114	99.45 47	97.58 203

UA-Net		97.35 4	97.24 11	97.69 4	98.22 74	93.87 30	98.42 6	98.19 39	96.95 14	95.46 142	99.23 4	93.45 82	99.57 14	95.34 28	99.89 2	99.63 9

MVS_111021_HR		93.63 142	93.42 153	94.26 135	96.65 170	86.96 146	89.30 298	96.23 202	88.36 190	93.57 210	94.60 250	93.45 82	97.77 252	90.23 158	98.38 183	98.03 159

cdsmvs_eth3d_5k		23.35 363	31.13 366	0.00 382	0.00 404	0.00 407	0.00 393	95.58 230	0.00 400	0.00 401	91.15 330	93.43 84	0.00 401	0.00 400	0.00 399	0.00 397

APD-MVS		95.00 93	94.69 111	95.93 62	97.38 132	90.88 71	94.59 116	97.81 91	89.22 170	95.46 142	96.17 182	93.42 85	99.34 63	89.30 180	98.87 131	97.56 206
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ANet_high		94.83 100	96.28 37	90.47 271	96.65 170	73.16 348	94.33 128	98.74 11	96.39 24	98.09 25	98.93 8	93.37 86	98.70 159	90.38 148	99.68 18	99.53 15

APD_test1		95.91 53	95.42 80	97.36 23	98.82 26	96.62 6	95.64 80	97.64 103	93.38 69	95.89 121	97.23 106	93.35 87	97.66 261	88.20 204	98.66 159	97.79 188

casdiffmvs		94.32 119	94.80 105	92.85 187	96.05 219	81.44 239	92.35 200	98.05 64	91.53 122	95.75 127	96.80 136	93.35 87	98.49 183	91.01 133	98.32 191	98.64 112
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_djsdf		96.62 23	96.49 26	97.01 32	98.55 45	91.77 59	97.15 15	97.37 123	88.98 174	98.26 22	98.86 10	93.35 87	99.60 9	96.41 9	99.45 47	99.66 6

VPA-MVSNet		95.14 89	95.67 70	93.58 160	97.76 106	83.15 216	94.58 118	97.58 109	93.39 68	97.05 66	98.04 48	93.25 90	98.51 182	89.75 172	99.59 28	99.08 48

Anonymous20240529		95.50 70	95.83 63	94.50 126	97.33 136	85.93 173	95.19 98	96.77 175	96.64 19	97.61 38	98.05 46	93.23 91	98.79 140	88.60 201	99.04 111	98.78 88

baseline		94.26 122	94.80 105	92.64 194	96.08 217	80.99 245	93.69 153	98.04 68	90.80 138	94.89 172	96.32 170	93.19 92	98.48 187	91.68 119	98.51 173	98.43 128

DeepPCF-MVS	90.46 6	94.20 126	93.56 149	96.14 52	95.96 226	92.96 43	89.48 291	97.46 118	85.14 247	96.23 104	95.42 216	93.19 92	98.08 220	90.37 149	98.76 146	97.38 221

Anonymous20231211		96.60 25	97.13 12	95.00 100	97.46 130	86.35 164	97.11 19	98.24 34	97.58 8	98.72 8	98.97 7	93.15 94	99.15 84	93.18 78	99.74 12	99.50 17

DVP-MVS++		95.93 52	96.34 34	94.70 112	96.54 179	86.66 154	98.45 4	98.22 36	93.26 71	97.54 40	97.36 94	93.12 95	99.38 55	93.88 46	98.68 155	98.04 156

OPU-MVS				95.15 97	96.84 160	89.43 92	95.21 94				95.66 205	93.12 95	98.06 221	86.28 244	98.61 161	97.95 169

LS3D		96.11 47	95.83 63	96.95 36	94.75 274	94.20 19	97.34 13	97.98 75	97.31 11	95.32 150	96.77 137	93.08 97	99.20 80	91.79 115	98.16 206	97.44 214

DP-MVS		95.62 64	95.84 62	94.97 101	97.16 144	88.62 111	94.54 123	97.64 103	96.94 15	96.58 88	97.32 101	93.07 98	98.72 152	90.45 145	98.84 133	97.57 204

EG-PatchMatch MVS		94.54 111	94.67 114	94.14 138	97.87 101	86.50 156	92.00 214	96.74 177	88.16 194	96.93 72	97.61 73	93.04 99	97.90 235	91.60 121	98.12 209	98.03 159

Fast-Effi-MVS+		91.28 205	90.86 212	92.53 202	95.45 253	82.53 224	89.25 301	96.52 190	85.00 251	89.91 303	88.55 362	92.94 100	98.84 129	84.72 265	95.44 302	96.22 266

PC_three_1452									75.31 337	95.87 122	95.75 202	92.93 101	96.34 319	87.18 226	98.68 155	98.04 156

v7n		96.82 9	97.31 10	95.33 86	98.54 48	86.81 148	96.83 23	98.07 60	96.59 20	98.46 17	98.43 32	92.91 102	99.52 19	96.25 12	99.76 10	99.65 8

XVG-ACMP-BASELINE		95.68 63	95.34 84	96.69 41	98.40 61	93.04 41	94.54 123	98.05 64	90.45 147	96.31 97	96.76 139	92.91 102	98.72 152	91.19 128	99.42 52	98.32 133

testgi		90.38 224	91.34 203	87.50 329	97.49 127	71.54 358	89.43 293	95.16 245	88.38 189	94.54 183	94.68 247	92.88 104	93.09 363	71.60 367	97.85 228	97.88 177

MVS_111021_LR		93.66 141	93.28 156	94.80 107	96.25 205	90.95 69	90.21 268	95.43 237	87.91 196	93.74 206	94.40 255	92.88 104	96.38 315	90.39 147	98.28 193	97.07 230

CNVR-MVS		94.58 109	94.29 124	95.46 82	96.94 152	89.35 96	91.81 227	96.80 172	89.66 160	93.90 202	95.44 215	92.80 106	98.72 152	92.74 91	98.52 171	98.32 133

ZD-MVS					97.23 139	90.32 78		97.54 112	84.40 260	94.78 176	95.79 197	92.76 107	99.39 49	88.72 199	98.40 179

XXY-MVS		92.58 174	93.16 159	90.84 262	97.75 107	79.84 263	91.87 223	96.22 204	85.94 229	95.53 136	97.68 67	92.69 108	94.48 349	83.21 275	97.51 242	98.21 142

CDPH-MVS		92.67 172	91.83 191	95.18 96	96.94 152	88.46 118	90.70 252	97.07 151	77.38 323	92.34 260	95.08 231	92.67 109	98.88 121	85.74 248	98.57 166	98.20 143

Fast-Effi-MVS+-dtu		92.77 169	92.16 180	94.58 124	94.66 280	88.25 120	92.05 211	96.65 181	89.62 161	90.08 299	91.23 329	92.56 110	98.60 172	86.30 243	96.27 284	96.90 238

fmvsm_s_conf0.1_n_a		94.26 122	94.37 121	93.95 147	97.36 134	85.72 180	94.15 136	95.44 235	83.25 270	95.51 137	98.05 46	92.54 111	97.19 286	95.55 20	97.46 246	98.94 66

AllTest		94.88 98	94.51 117	96.00 56	98.02 89	92.17 50	95.26 93	98.43 17	90.48 145	95.04 166	96.74 142	92.54 111	97.86 243	85.11 258	98.98 114	97.98 165

TestCases				96.00 56	98.02 89	92.17 50		98.43 17	90.48 145	95.04 166	96.74 142	92.54 111	97.86 243	85.11 258	98.98 114	97.98 165

TinyColmap		92.00 190	92.76 166	89.71 291	95.62 248	77.02 310	90.72 251	96.17 207	87.70 204	95.26 154	96.29 172	92.54 111	96.45 312	81.77 290	98.77 145	95.66 291

EGC-MVSNET		80.97 348	75.73 361	96.67 42	98.85 24	94.55 15	96.83 23	96.60 183	2.44 397	5.32 398	98.25 37	92.24 115	98.02 226	91.85 113	99.21 90	97.45 212

fmvsm_s_conf0.5_n_a		94.02 132	94.08 133	93.84 153	96.72 166	85.73 179	93.65 155	95.23 244	83.30 268	95.13 160	97.56 76	92.22 116	97.17 287	95.51 22	97.41 248	98.64 112

ETV-MVS		92.99 160	92.74 167	93.72 156	95.86 232	86.30 165	92.33 201	97.84 88	91.70 118	92.81 238	86.17 376	92.22 116	99.19 81	88.03 212	97.73 232	95.66 291

CLD-MVS		91.82 191	91.41 201	93.04 176	96.37 189	83.65 208	86.82 341	97.29 135	84.65 257	92.27 262	89.67 350	92.20 118	97.85 245	83.95 270	99.47 43	97.62 201
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
segment_acmp												92.14 119

Vis-MVSNet		95.50 70	95.48 76	95.56 79	98.11 80	89.40 94	95.35 88	98.22 36	92.36 87	94.11 190	98.07 45	92.02 120	99.44 29	93.38 71	97.67 237	97.85 181
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ITE_SJBPF				95.95 59	97.34 135	93.36 40		96.55 189	91.93 100	94.82 174	95.39 220	91.99 121	97.08 291	85.53 251	97.96 222	97.41 215

CP-MVSNet		96.19 45	96.80 16	94.38 133	98.99 16	83.82 206	96.31 50	97.53 114	97.60 7	98.34 19	97.52 81	91.98 122	99.63 6	93.08 83	99.81 8	99.70 3

CSCG		94.69 105	94.75 107	94.52 125	97.55 124	87.87 127	95.01 104	97.57 110	92.68 79	96.20 107	93.44 287	91.92 123	98.78 143	89.11 189	99.24 85	96.92 237

fmvsm_s_conf0.1_n		94.19 128	94.41 118	93.52 166	97.22 141	84.37 194	93.73 151	95.26 243	84.45 259	95.76 125	98.00 51	91.85 124	97.21 283	95.62 18	97.82 229	98.98 60

TSAR-MVS + MP.		94.96 95	94.75 107	95.57 78	98.86 22	88.69 108	96.37 44	96.81 171	85.23 244	94.75 177	97.12 115	91.85 124	99.40 46	93.45 65	98.33 189	98.62 116
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
fmvsm_s_conf0.5_n		94.00 133	94.20 129	93.42 169	96.69 167	84.37 194	93.38 163	95.13 246	84.50 258	95.40 144	97.55 80	91.77 126	97.20 284	95.59 19	97.79 230	98.69 104

Gipuma		95.31 84	95.80 65	93.81 155	97.99 94	90.91 70	96.42 42	97.95 80	96.69 17	91.78 270	98.85 12	91.77 126	95.49 334	91.72 117	99.08 102	95.02 306
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
WR-MVS_H		96.60 25	97.05 13	95.24 92	99.02 12	86.44 160	96.78 27	98.08 57	97.42 9	98.48 16	97.86 62	91.76 128	99.63 6	94.23 40	99.84 3	99.66 6

AdaColmap		91.63 196	91.36 202	92.47 204	95.56 250	86.36 163	92.24 208	96.27 199	88.88 178	89.90 304	92.69 305	91.65 129	98.32 200	77.38 334	97.64 238	92.72 357

PHI-MVS		94.34 118	93.80 137	95.95 59	95.65 245	91.67 62	94.82 109	97.86 85	87.86 199	93.04 231	94.16 264	91.58 130	98.78 143	90.27 155	98.96 121	97.41 215

xiu_mvs_v1_base_debu		91.47 200	91.52 196	91.33 241	95.69 242	81.56 235	89.92 278	96.05 211	83.22 271	91.26 277	90.74 336	91.55 131	98.82 131	89.29 181	95.91 290	93.62 344

xiu_mvs_v1_base		91.47 200	91.52 196	91.33 241	95.69 242	81.56 235	89.92 278	96.05 211	83.22 271	91.26 277	90.74 336	91.55 131	98.82 131	89.29 181	95.91 290	93.62 344

xiu_mvs_v1_base_debi		91.47 200	91.52 196	91.33 241	95.69 242	81.56 235	89.92 278	96.05 211	83.22 271	91.26 277	90.74 336	91.55 131	98.82 131	89.29 181	95.91 290	93.62 344

tfpnnormal		94.27 120	94.87 103	92.48 203	97.71 112	80.88 247	94.55 122	95.41 238	93.70 61	96.67 84	97.72 66	91.40 134	98.18 213	87.45 221	99.18 94	98.36 131

3Dnovator+	92.74 2	95.86 57	95.77 66	96.13 53	96.81 163	90.79 73	96.30 54	97.82 90	96.13 26	94.74 178	97.23 106	91.33 135	99.16 83	93.25 76	98.30 192	98.46 126

TEST9					96.45 187	89.46 90	90.60 255	96.92 162	79.09 313	90.49 290	94.39 256	91.31 136	98.88 121

DeepC-MVS_fast	89.96 7	93.73 140	93.44 152	94.60 121	96.14 213	87.90 126	93.36 164	97.14 145	85.53 241	93.90 202	95.45 214	91.30 137	98.59 174	89.51 175	98.62 160	97.31 224
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EI-MVSNet-Vis-set		94.36 116	94.28 125	94.61 118	92.55 320	85.98 172	92.44 195	94.69 260	93.70 61	96.12 111	95.81 196	91.24 138	98.86 126	93.76 53	98.22 201	98.98 60

MCST-MVS		92.91 162	92.51 174	94.10 140	97.52 125	85.72 180	91.36 237	97.13 147	80.33 299	92.91 236	94.24 260	91.23 139	98.72 152	89.99 166	97.93 224	97.86 179

RPSCF		95.58 68	94.89 102	97.62 7	97.58 122	96.30 7	95.97 66	97.53 114	92.42 84	93.41 213	97.78 63	91.21 140	97.77 252	91.06 130	97.06 259	98.80 86

train_agg		92.71 171	91.83 191	95.35 84	96.45 187	89.46 90	90.60 255	96.92 162	79.37 308	90.49 290	94.39 256	91.20 141	98.88 121	88.66 200	98.43 178	97.72 195

test_8					96.37 189	89.14 100	90.51 258	96.89 165	79.37 308	90.42 292	94.36 258	91.20 141	98.82 131

EI-MVSNet-UG-set		94.35 117	94.27 127	94.59 122	92.46 321	85.87 175	92.42 197	94.69 260	93.67 64	96.13 110	95.84 195	91.20 141	98.86 126	93.78 50	98.23 199	99.03 52

EIA-MVS		92.35 182	92.03 184	93.30 172	95.81 236	83.97 204	92.80 179	98.17 45	87.71 203	89.79 307	87.56 366	91.17 144	99.18 82	87.97 213	97.27 252	96.77 245

dcpmvs_2		93.96 134	95.01 99	90.82 263	97.60 120	74.04 343	93.68 154	98.85 7	89.80 158	97.82 29	97.01 124	91.14 145	99.21 78	90.56 143	98.59 164	99.19 36

xiu_mvs_v2_base		89.00 261	89.19 244	88.46 316	94.86 268	74.63 335	86.97 335	95.60 224	80.88 295	87.83 337	88.62 361	91.04 146	98.81 136	82.51 283	94.38 327	91.93 363

HPM-MVS++		95.02 92	94.39 119	96.91 37	97.88 99	93.58 37	94.09 140	96.99 157	91.05 132	92.40 255	95.22 225	91.03 147	99.25 75	92.11 103	98.69 154	97.90 174

test_fmvsm_n_1920		94.72 103	94.74 109	94.67 113	96.30 200	88.62 111	93.19 168	98.07 60	85.63 237	97.08 62	97.35 97	90.86 148	97.66 261	95.70 16	98.48 176	97.74 194

TAPA-MVS	88.58 10	92.49 177	91.75 193	94.73 110	96.50 183	89.69 86	92.91 176	97.68 101	78.02 321	92.79 240	94.10 265	90.85 149	97.96 232	84.76 264	98.16 206	96.54 250
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
pcd_1.5k_mvsjas		7.56 366	10.09 369	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	90.77 150	0.00 401	0.00 400	0.00 399	0.00 397

PS-MVSNAJss		96.01 50	96.04 52	95.89 67	98.82 26	88.51 116	95.57 84	97.88 84	88.72 180	98.81 6	98.86 10	90.77 150	99.60 9	95.43 26	99.53 38	99.57 14

PS-MVSNAJ		88.86 266	88.99 250	88.48 315	94.88 266	74.71 333	86.69 344	95.60 224	80.88 295	87.83 337	87.37 369	90.77 150	98.82 131	82.52 282	94.37 328	91.93 363

MVS_Test		92.57 176	93.29 154	90.40 274	93.53 305	75.85 327	92.52 190	96.96 158	88.73 179	92.35 258	96.70 146	90.77 150	98.37 198	92.53 97	95.49 300	96.99 235

MIMVSNet1		95.52 69	95.45 77	95.72 73	99.14 5	89.02 102	96.23 57	96.87 167	93.73 60	97.87 28	98.49 29	90.73 154	99.05 99	86.43 241	99.60 26	99.10 47

ab-mvs		92.40 180	92.62 172	91.74 225	97.02 148	81.65 234	95.84 71	95.50 234	86.95 217	92.95 235	97.56 76	90.70 155	97.50 268	79.63 315	97.43 247	96.06 272

Test By Simon												90.61 156

3Dnovator	92.54 3	94.80 101	94.90 101	94.47 129	95.47 252	87.06 142	96.63 31	97.28 137	91.82 110	94.34 189	97.41 88	90.60 157	98.65 167	92.47 98	98.11 210	97.70 196

NCCC		94.08 130	93.54 150	95.70 75	96.49 184	89.90 83	92.39 199	96.91 164	90.64 142	92.33 261	94.60 250	90.58 158	98.96 112	90.21 159	97.70 235	98.23 140

UniMVSNet_NR-MVSNet		95.35 79	95.21 90	95.76 71	97.69 115	88.59 113	92.26 206	97.84 88	94.91 40	96.80 78	95.78 200	90.42 159	99.41 39	91.60 121	99.58 33	99.29 29

test_prior2							90.21 268		89.33 167	90.77 286	94.81 240	90.41 160		88.21 203	98.55 167

KD-MVS_self_test		94.10 129	94.73 110	92.19 210	97.66 118	79.49 273	94.86 108	97.12 148	89.59 162	96.87 74	97.65 70	90.40 161	98.34 199	89.08 190	99.35 61	98.75 92

MSLP-MVS++		93.25 153	93.88 135	91.37 239	96.34 195	82.81 222	93.11 170	97.74 98	89.37 166	94.08 192	95.29 224	90.40 161	96.35 317	90.35 150	98.25 197	94.96 307

UniMVSNet (Re)		95.32 81	95.15 93	95.80 70	97.79 105	88.91 105	92.91 176	98.07 60	93.46 67	96.31 97	95.97 190	90.14 163	99.34 63	92.11 103	99.64 24	99.16 38

Effi-MVS+-dtu		93.90 138	92.60 173	97.77 3	94.74 275	96.67 5	94.00 142	95.41 238	89.94 154	91.93 269	92.13 317	90.12 164	98.97 111	87.68 218	97.48 244	97.67 199

FMVSNet1		94.84 99	95.13 94	93.97 144	97.60 120	84.29 196	95.99 63	96.56 186	92.38 85	97.03 67	98.53 26	90.12 164	98.98 107	88.78 197	99.16 97	98.65 107

DU-MVS		95.28 85	95.12 95	95.75 72	97.75 107	88.59 113	92.58 188	97.81 91	93.99 53	96.80 78	95.90 191	90.10 166	99.41 39	91.60 121	99.58 33	99.26 30

NR-MVSNet		95.28 85	95.28 88	95.26 90	97.75 107	87.21 138	95.08 100	97.37 123	93.92 58	97.65 34	95.90 191	90.10 166	99.33 68	90.11 162	99.66 21	99.26 30

Baseline_NR-MVSNet		94.47 113	95.09 97	92.60 199	98.50 57	80.82 248	92.08 210	96.68 179	93.82 59	96.29 99	98.56 24	90.10 166	97.75 255	90.10 164	99.66 21	99.24 32

API-MVS		91.52 199	91.61 194	91.26 245	94.16 290	86.26 167	94.66 114	94.82 255	91.17 130	92.13 265	91.08 332	90.03 169	97.06 292	79.09 322	97.35 251	90.45 373

patch_mono-2		92.46 178	92.72 170	91.71 227	96.65 170	78.91 285	88.85 308	97.17 143	83.89 265	92.45 252	96.76 139	89.86 170	97.09 290	90.24 157	98.59 164	99.12 43

test12				94.43 131	95.95 227	86.75 150		96.24 201		89.76 308		89.79 171	98.79 140		97.95 223	97.75 193

旧先验1					96.20 208	84.17 201		94.82 255			95.57 211	89.57 172			97.89 226	96.32 262

DELS-MVS		92.05 189	92.16 180	91.72 226	94.44 285	80.13 254	87.62 322	97.25 138	87.34 210	92.22 263	93.18 294	89.54 173	98.73 151	89.67 173	98.20 204	96.30 263
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
VPNet		93.08 157	93.76 139	91.03 253	98.60 39	75.83 329	91.51 232	95.62 223	91.84 107	95.74 128	97.10 117	89.31 174	98.32 200	85.07 260	99.06 103	98.93 68

QAPM		92.88 164	92.77 165	93.22 174	95.82 234	83.31 210	96.45 39	97.35 129	83.91 264	93.75 204	96.77 137	89.25 175	98.88 121	84.56 266	97.02 261	97.49 210

MSDG		90.82 208	90.67 218	91.26 245	94.16 290	83.08 218	86.63 346	96.19 205	90.60 144	91.94 268	91.89 320	89.16 176	95.75 329	80.96 301	94.51 325	94.95 308

CPTT-MVS		94.74 102	94.12 131	96.60 43	98.15 78	93.01 42	95.84 71	97.66 102	89.21 171	93.28 219	95.46 213	88.89 177	98.98 107	89.80 169	98.82 139	97.80 187

DP-MVS Recon		92.31 183	91.88 189	93.60 159	97.18 143	86.87 147	91.10 242	97.37 123	84.92 253	92.08 266	94.08 266	88.59 178	98.20 210	83.50 272	98.14 208	95.73 286

FC-MVSNet-test		95.32 81	95.88 59	93.62 158	98.49 58	81.77 232	95.90 69	98.32 24	93.93 56	97.53 42	97.56 76	88.48 179	99.40 46	92.91 88	99.83 5	99.68 4

OpenMVS	89.45 8	92.27 185	92.13 183	92.68 193	94.53 284	84.10 202	95.70 76	97.03 153	82.44 285	91.14 281	96.42 159	88.47 180	98.38 194	85.95 246	97.47 245	95.55 295

F-COLMAP		92.28 184	91.06 209	95.95 59	97.52 125	91.90 56	93.53 156	97.18 142	83.98 263	88.70 325	94.04 267	88.41 181	98.55 179	80.17 308	95.99 289	97.39 219

ambc				92.98 178	96.88 156	83.01 219	95.92 68	96.38 196		96.41 92	97.48 86	88.26 182	97.80 247	89.96 167	98.93 125	98.12 151

v10		94.68 106	95.27 89	92.90 185	96.57 176	80.15 252	94.65 115	97.57 110	90.68 141	97.43 48	98.00 51	88.18 183	99.15 84	94.84 30	99.55 37	99.41 20

v8		94.65 107	95.29 87	92.74 190	96.65 170	79.77 267	94.59 116	97.17 143	91.86 103	97.47 47	97.93 55	88.16 184	99.08 94	94.32 37	99.47 43	99.38 22

TSAR-MVS + GP.		93.07 159	92.41 177	95.06 99	95.82 234	90.87 72	90.97 244	92.61 302	88.04 195	94.61 181	93.79 278	88.08 185	97.81 246	89.41 177	98.39 182	96.50 255

OurMVSNet-221017-0		96.80 12	96.75 17	96.96 35	99.03 11	91.85 57	97.98 7	98.01 72	94.15 51	98.93 3	99.07 5	88.07 186	99.57 14	95.86 15	99.69 14	99.46 18

diffmvs		91.74 193	91.93 188	91.15 251	93.06 312	78.17 295	88.77 311	97.51 117	86.28 222	92.42 254	93.96 272	88.04 187	97.46 271	90.69 141	96.67 276	97.82 185
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
原ACMM1				92.87 186	96.91 155	84.22 199		97.01 154	76.84 329	89.64 310	94.46 254	88.00 188	98.70 159	81.53 294	98.01 219	95.70 289

VDD-MVS		94.37 115	94.37 121	94.40 132	97.49 127	86.07 171	93.97 144	93.28 287	94.49 45	96.24 103	97.78 63	87.99 189	98.79 140	88.92 193	99.14 99	98.34 132

XVG-OURS		94.72 103	94.12 131	96.50 47	98.00 91	94.23 18	91.48 233	98.17 45	90.72 139	95.30 151	96.47 156	87.94 190	96.98 294	91.41 126	97.61 240	98.30 136

CANet		92.38 181	91.99 186	93.52 166	93.82 301	83.46 209	91.14 240	97.00 155	89.81 157	86.47 348	94.04 267	87.90 191	99.21 78	89.50 176	98.27 194	97.90 174

BH-untuned		90.68 213	90.90 210	90.05 285	95.98 225	79.57 271	90.04 274	94.94 252	87.91 196	94.07 193	93.00 296	87.76 192	97.78 251	79.19 321	95.17 310	92.80 356

FIs		94.90 97	95.35 83	93.55 161	98.28 69	81.76 233	95.33 90	98.14 49	93.05 76	97.07 63	97.18 111	87.65 193	99.29 70	91.72 117	99.69 14	99.61 11

v1144		93.50 143	93.81 136	92.57 200	96.28 201	79.61 270	91.86 225	96.96 158	86.95 217	95.91 119	96.32 170	87.65 193	98.96 112	93.51 59	98.88 128	99.13 41

mvs_anonymous		90.37 225	91.30 204	87.58 328	92.17 329	68.00 372	89.84 281	94.73 259	83.82 266	93.22 225	97.40 89	87.54 195	97.40 276	87.94 214	95.05 312	97.34 222

PCF-MVS	84.52 17	89.12 255	87.71 279	93.34 170	96.06 218	85.84 176	86.58 349	97.31 132	68.46 375	93.61 209	93.89 275	87.51 196	98.52 181	67.85 380	98.11 210	95.66 291
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
VNet		92.67 172	92.96 160	91.79 223	96.27 202	80.15 252	91.95 215	94.98 250	92.19 94	94.52 184	96.07 185	87.43 197	97.39 277	84.83 262	98.38 183	97.83 183

v148		92.87 165	93.29 154	91.62 231	96.25 205	77.72 302	91.28 238	95.05 247	89.69 159	95.93 118	96.04 186	87.34 198	98.38 194	90.05 165	97.99 220	98.78 88

V42		93.43 146	93.58 147	92.97 179	95.34 258	81.22 242	92.67 184	96.49 191	87.25 211	96.20 107	96.37 167	87.32 199	98.85 128	92.39 100	98.21 202	98.85 81

v1192		93.49 144	93.78 138	92.62 197	96.16 211	79.62 269	91.83 226	97.22 141	86.07 227	96.10 112	96.38 166	87.22 200	99.02 104	94.14 42	98.88 128	99.22 33

WR-MVS		93.49 144	93.72 140	92.80 189	97.57 123	80.03 258	90.14 271	95.68 222	93.70 61	96.62 86	95.39 220	87.21 201	99.04 102	87.50 220	99.64 24	99.33 26

IterMVS-LS		93.78 139	94.28 125	92.27 207	96.27 202	79.21 280	91.87 223	96.78 173	91.77 113	96.57 89	97.07 118	87.15 202	98.74 150	91.99 108	99.03 112	98.86 78
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		92.99 160	93.26 158	92.19 210	92.12 330	79.21 280	92.32 202	94.67 262	91.77 113	95.24 157	95.85 193	87.14 203	98.49 183	91.99 108	98.26 195	98.86 78

v144192		93.20 156	93.54 150	92.16 214	96.05 219	78.26 294	91.95 215	97.14 145	84.98 252	95.96 115	96.11 183	87.08 204	99.04 102	93.79 49	98.84 133	99.17 37

114514_t		90.51 217	89.80 237	92.63 196	98.00 91	82.24 228	93.40 162	97.29 135	65.84 382	89.40 312	94.80 242	86.99 205	98.75 147	83.88 271	98.61 161	96.89 239

新几何1				93.17 175	97.16 144	87.29 135		94.43 265	67.95 376	91.29 276	94.94 236	86.97 206	98.23 208	81.06 300	97.75 231	93.98 334

HQP_MVS		94.26 122	93.93 134	95.23 93	97.71 112	88.12 122	94.56 120	97.81 91	91.74 115	93.31 216	95.59 207	86.93 207	98.95 114	89.26 184	98.51 173	98.60 117

plane_prior6					97.21 142	88.23 121						86.93 207

UGNet		93.08 157	92.50 175	94.79 108	93.87 299	87.99 125	95.07 101	94.26 270	90.64 142	87.33 344	97.67 69	86.89 209	98.49 183	88.10 208	98.71 151	97.91 173
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
LF4IMVS		92.72 170	92.02 185	94.84 106	95.65 245	91.99 54	92.92 175	96.60 183	85.08 250	92.44 253	93.62 282	86.80 210	96.35 317	86.81 230	98.25 197	96.18 268

v1921920		93.26 151	93.61 146	92.19 210	96.04 223	78.31 293	91.88 222	97.24 139	85.17 246	96.19 109	96.19 179	86.76 211	99.05 99	94.18 41	98.84 133	99.22 33

MVS_0304		93.92 136	93.68 143	94.64 117	95.94 229	85.83 177	94.34 127	88.14 341	92.98 77	91.09 282	97.68 67	86.73 212	99.36 58	96.64 7	99.59 28	98.72 97

v1240		93.29 149	93.71 141	92.06 217	96.01 224	77.89 299	91.81 227	97.37 123	85.12 248	96.69 83	96.40 161	86.67 213	99.07 98	94.51 33	98.76 146	99.22 33

MAR-MVS		90.32 228	88.87 254	94.66 115	94.82 269	91.85 57	94.22 134	94.75 258	80.91 294	87.52 342	88.07 365	86.63 214	97.87 242	76.67 338	96.21 285	94.25 328
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
MSP-MVS		95.34 80	94.63 115	97.48 14	98.67 33	94.05 23	96.41 43	98.18 41	91.26 126	95.12 161	95.15 226	86.60 215	99.50 21	93.43 69	96.81 271	98.89 75
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
BH-RMVSNet		90.47 219	90.44 223	90.56 270	95.21 261	78.65 291	89.15 302	93.94 278	88.21 191	92.74 242	94.22 261	86.38 216	97.88 239	78.67 324	95.39 304	95.14 303

CNLPA		91.72 194	91.20 205	93.26 173	96.17 210	91.02 67	91.14 240	95.55 231	90.16 152	90.87 284	93.56 285	86.31 217	94.40 352	79.92 314	97.12 257	94.37 325

PVSNet_BlendedMVS		90.35 226	89.96 233	91.54 234	94.81 270	78.80 289	90.14 271	96.93 160	79.43 307	88.68 326	95.06 232	86.27 218	98.15 216	80.27 304	98.04 216	97.68 198

PVSNet_Blended		88.74 269	88.16 273	90.46 273	94.81 270	78.80 289	86.64 345	96.93 160	74.67 339	88.68 326	89.18 357	86.27 218	98.15 216	80.27 304	96.00 288	94.44 324

PAPR		87.65 288	86.77 298	90.27 277	92.85 316	77.38 306	88.56 316	96.23 202	76.82 330	84.98 359	89.75 349	86.08 220	97.16 288	72.33 362	93.35 345	96.26 265

v2v482		93.29 149	93.63 145	92.29 206	96.35 194	78.82 287	91.77 229	96.28 198	88.45 186	95.70 132	96.26 176	86.02 221	98.90 118	93.02 84	98.81 141	99.14 40

test20.03		90.80 209	90.85 213	90.63 268	95.63 247	79.24 278	89.81 282	92.87 293	89.90 155	94.39 186	96.40 161	85.77 222	95.27 342	73.86 354	99.05 106	97.39 219

PLC	85.34 15	90.40 221	88.92 251	94.85 105	96.53 182	90.02 81	91.58 231	96.48 192	80.16 300	86.14 350	92.18 315	85.73 223	98.25 207	76.87 337	94.61 324	96.30 263
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVS		84.98 319	84.30 320	87.01 333	91.03 350	77.69 303	91.94 217	94.16 271	59.36 390	84.23 365	87.50 368	85.66 224	96.80 302	71.79 364	93.05 352	86.54 383

testdata				91.03 253	96.87 157	82.01 229		94.28 269	71.55 357	92.46 251	95.42 216	85.65 225	97.38 279	82.64 280	97.27 252	93.70 341

PM-MVS		93.33 148	92.67 171	95.33 86	96.58 175	94.06 21	92.26 206	92.18 307	85.92 230	96.22 105	96.61 151	85.64 226	95.99 326	90.35 150	98.23 199	95.93 277

SSC-MVS		90.16 232	92.96 160	81.78 366	97.88 99	48.48 398	90.75 249	87.69 345	96.02 31	96.70 82	97.63 72	85.60 227	97.80 247	85.73 249	98.60 163	99.06 50

MM				95.22 94		87.21 138	94.31 131	90.92 324	94.48 46	92.80 239	97.52 81	85.27 228	99.49 24	96.58 8	99.57 35	98.97 62

WB-MVS		89.44 250	92.15 182	81.32 367	97.73 110	48.22 399	89.73 284	87.98 343	95.24 36	96.05 113	96.99 125	85.18 229	96.95 295	82.45 284	97.97 221	98.78 88

MDA-MVSNet-bldmvs		91.04 206	90.88 211	91.55 233	94.68 279	80.16 251	85.49 356	92.14 310	90.41 149	94.93 170	95.79 197	85.10 230	96.93 298	85.15 255	94.19 334	97.57 204

PAPM_NR		91.03 207	90.81 214	91.68 229	96.73 165	81.10 244	93.72 152	96.35 197	88.19 192	88.77 323	92.12 318	85.09 231	97.25 281	82.40 285	93.90 337	96.68 248

HQP2-MVS												84.76 232

HQP-MVS		92.09 188	91.49 199	93.88 150	96.36 191	84.89 190	91.37 234	97.31 132	87.16 212	88.81 319	93.40 288	84.76 232	98.60 172	86.55 238	97.73 232	98.14 149

test222					96.95 151	85.27 187	88.83 309	93.61 279	65.09 384	90.74 287	94.85 239	84.62 234			97.36 250	93.91 335

VDDNet		94.03 131	94.27 127	93.31 171	98.87 21	82.36 227	95.51 86	91.78 316	97.19 12	96.32 96	98.60 22	84.24 235	98.75 147	87.09 228	98.83 138	98.81 84

PVSNet_Blended_VisFu		91.63 196	91.20 205	92.94 183	97.73 110	83.95 205	92.14 209	97.46 118	78.85 317	92.35 258	94.98 234	84.16 236	99.08 94	86.36 242	96.77 273	95.79 284

CL-MVSNet_self_test		90.04 240	89.90 235	90.47 271	95.24 260	77.81 300	86.60 348	92.62 301	85.64 236	93.25 223	93.92 273	83.84 237	96.06 324	79.93 312	98.03 217	97.53 208

mvsany_test3		89.11 256	88.21 271	91.83 221	91.30 348	90.25 79	88.09 319	78.76 389	76.37 331	96.43 91	98.39 33	83.79 238	90.43 376	86.57 236	94.20 332	94.80 314

mvsmamba		95.61 65	95.40 81	96.22 51	98.44 60	89.86 84	97.14 17	97.45 120	91.25 128	97.49 44	98.14 39	83.49 239	99.45 27	95.52 21	99.66 21	99.36 24

BH-w/o		87.21 299	87.02 294	87.79 327	94.77 273	77.27 308	87.90 320	93.21 290	81.74 290	89.99 302	88.39 364	83.47 240	96.93 298	71.29 368	92.43 359	89.15 374

PatchMatch-RL		89.18 253	88.02 276	92.64 194	95.90 231	92.87 45	88.67 315	91.06 321	80.34 298	90.03 301	91.67 324	83.34 241	94.42 351	76.35 341	94.84 318	90.64 372

DPM-MVS		89.35 251	88.40 260	92.18 213	96.13 215	84.20 200	86.96 336	96.15 208	75.40 336	87.36 343	91.55 327	83.30 242	98.01 227	82.17 288	96.62 277	94.32 327

OpenMVS_ROB	85.12 16	89.52 248	89.05 247	90.92 258	94.58 283	81.21 243	91.10 242	93.41 286	77.03 327	93.41 213	93.99 271	83.23 243	97.80 247	79.93 312	94.80 319	93.74 340

new-patchmatchnet		88.97 262	90.79 215	83.50 361	94.28 289	55.83 396	85.34 358	93.56 282	86.18 225	95.47 140	95.73 203	83.10 244	96.51 309	85.40 252	98.06 214	98.16 147

mvsany_test1		83.91 327	82.93 331	86.84 337	86.18 389	85.93 173	81.11 380	75.03 395	70.80 365	88.57 328	94.63 248	83.08 245	87.38 385	80.39 302	86.57 381	87.21 381

1314		86.46 309	86.33 306	86.87 336	91.65 343	74.54 336	91.94 217	94.10 272	74.28 342	84.78 361	87.33 370	83.03 246	95.00 344	78.72 323	91.16 368	91.06 370

IS-MVSNet		94.49 112	94.35 123	94.92 102	98.25 73	86.46 159	97.13 18	94.31 267	96.24 25	96.28 101	96.36 168	82.88 247	99.35 60	88.19 205	99.52 41	98.96 64

test_fmvs3		92.42 179	92.40 178	92.46 205	93.80 302	87.28 136	93.86 147	97.05 152	76.86 328	96.25 102	98.66 18	82.87 248	91.26 371	95.44 25	96.83 270	98.82 82

MG-MVS		89.54 247	89.80 237	88.76 307	94.88 266	72.47 355	89.60 287	92.44 305	85.82 231	89.48 311	95.98 189	82.85 249	97.74 257	81.87 289	95.27 308	96.08 271

TR-MVS		87.70 285	87.17 289	89.27 299	94.11 292	79.26 277	88.69 313	91.86 315	81.94 289	90.69 288	89.79 347	82.82 250	97.42 274	72.65 361	91.98 363	91.14 369

c3_l		91.32 204	91.42 200	91.00 256	92.29 323	76.79 317	87.52 328	96.42 194	85.76 233	94.72 180	93.89 275	82.73 251	98.16 215	90.93 135	98.55 167	98.04 156

YYNet1		88.17 278	88.24 268	87.93 324	92.21 326	73.62 345	80.75 381	88.77 333	82.51 284	94.99 168	95.11 229	82.70 252	93.70 358	83.33 273	93.83 338	96.48 256

MDA-MVSNet_test_wron		88.16 279	88.23 269	87.93 324	92.22 325	73.71 344	80.71 382	88.84 332	82.52 283	94.88 173	95.14 227	82.70 252	93.61 359	83.28 274	93.80 339	96.46 257

pmmvs-eth3d		91.54 198	90.73 217	93.99 142	95.76 239	87.86 128	90.83 247	93.98 277	78.23 320	94.02 197	96.22 178	82.62 254	96.83 301	86.57 236	98.33 189	97.29 225

Anonymous20231206		88.77 268	88.29 264	90.20 281	96.31 198	78.81 288	89.56 289	93.49 284	74.26 343	92.38 256	95.58 210	82.21 255	95.43 337	72.07 363	98.75 148	96.34 261

miper_ehance_all_eth		90.48 218	90.42 224	90.69 266	91.62 344	76.57 320	86.83 340	96.18 206	83.38 267	94.06 194	92.66 307	82.20 256	98.04 222	89.79 170	97.02 261	97.45 212

USDC		89.02 258	89.08 246	88.84 306	95.07 263	74.50 338	88.97 304	96.39 195	73.21 349	93.27 220	96.28 174	82.16 257	96.39 314	77.55 331	98.80 142	95.62 294

EPP-MVSNet		93.91 137	93.68 143	94.59 122	98.08 82	85.55 183	97.44 12	94.03 273	94.22 50	94.94 169	96.19 179	82.07 258	99.57 14	87.28 225	98.89 126	98.65 107

UnsupCasMVSNet_eth		90.33 227	90.34 226	90.28 276	94.64 282	80.24 250	89.69 286	95.88 216	85.77 232	93.94 201	95.69 204	81.99 259	92.98 364	84.21 268	91.30 366	97.62 201

alignmvs		93.26 151	92.85 164	94.50 126	95.70 241	87.45 133	93.45 160	95.76 219	91.58 120	95.25 156	92.42 313	81.96 260	98.72 152	91.61 120	97.87 227	97.33 223

TAMVS		90.16 232	89.05 247	93.49 168	96.49 184	86.37 162	90.34 265	92.55 303	80.84 297	92.99 232	94.57 252	81.94 261	98.20 210	73.51 355	98.21 202	95.90 280

Anonymous202405211		92.58 174	92.50 175	92.83 188	96.55 178	83.22 214	92.43 196	91.64 318	94.10 52	95.59 134	96.64 149	81.88 262	97.50 268	85.12 257	98.52 171	97.77 190

SixPastTwentyTwo		94.91 96	95.21 90	93.98 143	98.52 50	83.19 215	95.93 67	94.84 254	94.86 41	98.49 15	98.74 16	81.45 263	99.60 9	94.69 31	99.39 58	99.15 39

cascas		87.02 305	86.28 307	89.25 300	91.56 345	76.45 321	84.33 368	96.78 173	71.01 362	86.89 347	85.91 377	81.35 264	96.94 296	83.09 276	95.60 297	94.35 326

GBi-Net		93.21 154	92.96 160	93.97 144	95.40 254	84.29 196	95.99 63	96.56 186	88.63 182	95.10 162	98.53 26	81.31 265	98.98 107	86.74 231	98.38 183	98.65 107

test1		93.21 154	92.96 160	93.97 144	95.40 254	84.29 196	95.99 63	96.56 186	88.63 182	95.10 162	98.53 26	81.31 265	98.98 107	86.74 231	98.38 183	98.65 107

FMVSNet2		92.78 168	92.73 169	92.95 181	95.40 254	81.98 230	94.18 135	95.53 233	88.63 182	96.05 113	97.37 91	81.31 265	98.81 136	87.38 224	98.67 157	98.06 153

MVE	59.87 23	73.86 360	72.65 363	77.47 373	87.00 387	74.35 339	61.37 391	60.93 399	67.27 377	69.69 394	86.49 374	81.24 268	72.33 395	56.45 392	83.45 386	85.74 384
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
RRT_MVS		95.41 77	95.20 92	96.05 55	98.86 22	88.92 104	97.49 11	94.48 264	93.12 73	97.94 27	98.54 25	81.19 269	99.63 6	95.48 23	99.69 14	99.60 12

MVP-Stereo		90.07 238	88.92 251	93.54 163	96.31 198	86.49 157	90.93 245	95.59 228	79.80 301	91.48 273	95.59 207	80.79 270	97.39 277	78.57 325	91.19 367	96.76 246
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UnsupCasMVSNet_bld		88.50 273	88.03 275	89.90 287	95.52 251	78.88 286	87.39 329	94.02 275	79.32 311	93.06 229	94.02 269	80.72 271	94.27 354	75.16 347	93.08 351	96.54 250

MS-PatchMatch		88.05 280	87.75 278	88.95 303	93.28 307	77.93 297	87.88 321	92.49 304	75.42 335	92.57 248	93.59 284	80.44 272	94.24 356	81.28 296	92.75 354	94.69 320

Anonymous20240521		92.86 166	93.57 148	90.74 265	96.57 176	75.50 331	94.15 136	95.60 224	89.38 165	95.90 120	97.90 61	80.39 273	97.96 232	92.60 96	99.68 18	98.75 92

CANet_DTU		89.85 243	89.17 245	91.87 220	92.20 327	80.02 259	90.79 248	95.87 217	86.02 228	82.53 375	91.77 322	80.01 274	98.57 176	85.66 250	97.70 235	97.01 234

PMMVS		83.00 333	81.11 341	88.66 310	83.81 396	86.44 160	82.24 377	85.65 361	61.75 389	82.07 377	85.64 378	79.75 275	91.59 370	75.99 343	93.09 350	87.94 380

ppachtmachnet_test		88.61 272	88.64 256	88.50 314	91.76 339	70.99 362	84.59 365	92.98 291	79.30 312	92.38 256	93.53 286	79.57 276	97.45 272	86.50 240	97.17 256	97.07 230

eth_miper_zixun_eth		90.72 211	90.61 219	91.05 252	92.04 333	76.84 316	86.91 337	96.67 180	85.21 245	94.41 185	93.92 273	79.53 277	98.26 206	89.76 171	97.02 261	98.06 153

test_vis1_rt		85.58 314	84.58 317	88.60 311	87.97 379	86.76 149	85.45 357	93.59 280	66.43 379	87.64 339	89.20 356	79.33 278	85.38 390	81.59 293	89.98 374	93.66 342

N_pmnet		88.90 265	87.25 287	93.83 154	94.40 287	93.81 35	84.73 362	87.09 350	79.36 310	93.26 221	92.43 312	79.29 279	91.68 369	77.50 333	97.22 254	96.00 274

miper_enhance_ethall		88.42 274	87.87 277	90.07 283	88.67 377	75.52 330	85.10 359	95.59 228	75.68 332	92.49 249	89.45 353	78.96 280	97.88 239	87.86 216	97.02 261	96.81 243

EPNet		89.80 245	88.25 267	94.45 130	83.91 395	86.18 168	93.87 146	87.07 351	91.16 131	80.64 384	94.72 245	78.83 281	98.89 120	85.17 253	98.89 126	98.28 137
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
sss		87.23 298	86.82 296	88.46 316	93.96 296	77.94 296	86.84 339	92.78 297	77.59 322	87.61 341	91.83 321	78.75 282	91.92 368	77.84 328	94.20 332	95.52 296

bld_raw_dy_0_64		94.27 120	94.15 130	94.65 116	98.55 45	86.28 166	95.80 73	95.55 231	88.41 188	97.09 61	98.08 44	78.69 283	98.87 125	95.63 17	99.53 38	98.81 84

IterMVS-SCA-FT		91.65 195	91.55 195	91.94 219	93.89 298	79.22 279	87.56 325	93.51 283	91.53 122	95.37 147	96.62 150	78.65 284	98.90 118	91.89 112	94.95 314	97.70 196

SCA		87.43 294	87.21 288	88.10 322	92.01 334	71.98 357	89.43 293	88.11 342	82.26 287	88.71 324	92.83 300	78.65 284	97.59 264	79.61 316	93.30 346	94.75 317

our_test_3		87.55 291	87.59 281	87.44 330	91.76 339	70.48 363	83.83 371	90.55 328	79.79 302	92.06 267	92.17 316	78.63 286	95.63 330	84.77 263	94.73 320	96.22 266

jason		89.17 254	88.32 262	91.70 228	95.73 240	80.07 255	88.10 318	93.22 288	71.98 356	90.09 298	92.79 302	78.53 287	98.56 177	87.43 222	97.06 259	96.46 257
jason: jason.
IterMVS		90.18 231	90.16 228	90.21 280	93.15 310	75.98 326	87.56 325	92.97 292	86.43 221	94.09 191	96.40 161	78.32 288	97.43 273	87.87 215	94.69 322	97.23 227
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CHOSEN 1792x2688		87.19 301	85.92 310	91.00 256	97.13 146	79.41 274	84.51 366	95.60 224	64.14 385	90.07 300	94.81 240	78.26 289	97.14 289	73.34 356	95.38 305	96.46 257

WTY-MVS		86.93 306	86.50 305	88.24 319	94.96 264	74.64 334	87.19 332	92.07 312	78.29 319	88.32 331	91.59 326	78.06 290	94.27 354	74.88 348	93.15 349	95.80 283

pmmvs4		88.95 263	87.70 280	92.70 191	94.30 288	85.60 182	87.22 331	92.16 309	74.62 340	89.75 309	94.19 262	77.97 291	96.41 313	82.71 279	96.36 283	96.09 270

DSMNet-mixed		82.21 338	81.56 337	84.16 357	89.57 369	70.00 368	90.65 254	77.66 393	54.99 393	83.30 371	97.57 75	77.89 292	90.50 375	66.86 383	95.54 299	91.97 362

FA-MVS(test-final)		91.81 192	91.85 190	91.68 229	94.95 265	79.99 260	96.00 62	93.44 285	87.80 200	94.02 197	97.29 102	77.60 293	98.45 189	88.04 211	97.49 243	96.61 249

lessismore_v0				93.87 151	98.05 85	83.77 207		80.32 386		97.13 60	97.91 59	77.49 294	99.11 93	92.62 95	98.08 213	98.74 95

Syy-MVS		84.81 320	84.93 314	84.42 355	91.71 341	63.36 389	85.89 352	81.49 381	81.03 292	85.13 356	81.64 387	77.44 295	95.00 344	85.94 247	94.12 335	94.91 311

HY-MVS	82.50 18	86.81 307	85.93 309	89.47 293	93.63 303	77.93 297	94.02 141	91.58 319	75.68 332	83.64 368	93.64 280	77.40 296	97.42 274	71.70 366	92.07 362	93.05 353

1112_ss		88.42 274	87.41 283	91.45 237	96.69 167	80.99 245	89.72 285	96.72 178	73.37 347	87.00 346	90.69 339	77.38 297	98.20 210	81.38 295	93.72 340	95.15 302

DIV-MVS_self_test		90.65 214	90.56 221	90.91 260	91.85 337	76.99 312	86.75 342	95.36 241	85.52 243	94.06 194	94.89 237	77.37 298	97.99 230	90.28 154	98.97 119	97.76 191

cl____		90.65 214	90.56 221	90.91 260	91.85 337	76.98 313	86.75 342	95.36 241	85.53 241	94.06 194	94.89 237	77.36 299	97.98 231	90.27 155	98.98 114	97.76 191

CDS-MVSNet		89.55 246	88.22 270	93.53 164	95.37 257	86.49 157	89.26 299	93.59 280	79.76 303	91.15 280	92.31 314	77.12 300	98.38 194	77.51 332	97.92 225	95.71 287
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test_vis3_rt		90.40 221	90.03 232	91.52 235	92.58 318	88.95 103	90.38 263	97.72 100	73.30 348	97.79 30	97.51 84	77.05 301	87.10 386	89.03 191	94.89 315	98.50 122

MVSFormer		92.18 187	92.23 179	92.04 218	94.74 275	80.06 256	97.15 15	97.37 123	88.98 174	88.83 317	92.79 302	77.02 302	99.60 9	96.41 9	96.75 274	96.46 257

lupinMVS		88.34 276	87.31 284	91.45 237	94.74 275	80.06 256	87.23 330	92.27 306	71.10 361	88.83 317	91.15 330	77.02 302	98.53 180	86.67 234	96.75 274	95.76 285

PMMVS2		81.31 344	83.44 326	74.92 375	90.52 357	46.49 401	69.19 389	85.23 369	84.30 262	87.95 336	94.71 246	76.95 304	84.36 392	64.07 386	98.09 212	93.89 336

h-mvs33		92.89 163	91.99 186	95.58 77	96.97 150	90.55 76	93.94 145	94.01 276	89.23 168	93.95 199	96.19 179	76.88 305	99.14 86	91.02 131	95.71 295	97.04 233

hse-mvs2		92.24 186	91.20 205	95.38 83	96.16 211	90.65 75	92.52 190	92.01 314	89.23 168	93.95 199	92.99 297	76.88 305	98.69 161	91.02 131	96.03 287	96.81 243

pmmvs5		87.87 282	87.14 290	90.07 283	93.26 309	76.97 314	88.89 306	92.18 307	73.71 346	88.36 330	93.89 275	76.86 307	96.73 304	80.32 303	96.81 271	96.51 252

test_vis1_n_1920		89.45 249	89.85 236	88.28 318	93.59 304	76.71 318	90.67 253	97.78 96	79.67 305	90.30 296	96.11 183	76.62 308	92.17 367	90.31 152	93.57 342	95.96 275

K. test v3		93.37 147	93.27 157	93.66 157	98.05 85	82.62 223	94.35 126	86.62 353	96.05 29	97.51 43	98.85 12	76.59 309	99.65 3	93.21 77	98.20 204	98.73 96

miper_lstm_enhance		89.90 242	89.80 237	90.19 282	91.37 347	77.50 304	83.82 372	95.00 249	84.84 255	93.05 230	94.96 235	76.53 310	95.20 343	89.96 167	98.67 157	97.86 179

dmvs_testset		78.23 358	78.99 355	75.94 374	91.99 335	55.34 397	88.86 307	78.70 390	82.69 280	81.64 382	79.46 389	75.93 311	85.74 389	48.78 395	82.85 388	86.76 382

Test_1112_low_res		87.50 293	86.58 300	90.25 278	96.80 164	77.75 301	87.53 327	96.25 200	69.73 371	86.47 348	93.61 283	75.67 312	97.88 239	79.95 310	93.20 347	95.11 304

test_fmvs2		90.62 216	90.40 225	91.29 244	91.93 336	85.46 184	92.70 183	96.48 192	74.44 341	94.91 171	97.59 74	75.52 313	90.57 373	93.44 66	96.56 278	97.84 182

Vis-MVSNet (Re-imp)		90.42 220	90.16 228	91.20 249	97.66 118	77.32 307	94.33 128	87.66 346	91.20 129	92.99 232	95.13 228	75.40 314	98.28 202	77.86 327	99.19 92	97.99 164

test_vis1_n		89.01 260	89.01 249	89.03 302	92.57 319	82.46 226	92.62 187	96.06 209	73.02 351	90.40 293	95.77 201	74.86 315	89.68 379	90.78 138	94.98 313	94.95 308

D2MVS		89.93 241	89.60 242	90.92 258	94.03 295	78.40 292	88.69 313	94.85 253	78.96 315	93.08 228	95.09 230	74.57 316	96.94 296	88.19 205	98.96 121	97.41 215

PVSNet	76.22 20	82.89 334	82.37 334	84.48 354	93.96 296	64.38 386	78.60 384	88.61 334	71.50 358	84.43 364	86.36 375	74.27 317	94.60 348	69.87 376	93.69 341	94.46 323

test_yl		90.11 235	89.73 240	91.26 245	94.09 293	79.82 264	90.44 259	92.65 299	90.90 133	93.19 226	93.30 290	73.90 318	98.03 223	82.23 286	96.87 268	95.93 277

DCV-MVSNet		90.11 235	89.73 240	91.26 245	94.09 293	79.82 264	90.44 259	92.65 299	90.90 133	93.19 226	93.30 290	73.90 318	98.03 223	82.23 286	96.87 268	95.93 277

CMPMVS	68.83 22	87.28 297	85.67 311	92.09 216	88.77 376	85.42 185	90.31 266	94.38 266	70.02 369	88.00 335	93.30 290	73.78 320	94.03 357	75.96 344	96.54 279	96.83 242
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
baseline1		87.62 289	87.31 284	88.54 312	94.71 278	74.27 341	93.10 171	88.20 339	86.20 224	92.18 264	93.04 295	73.21 321	95.52 332	79.32 319	85.82 382	95.83 282

PVSNet_0	70.34 21	74.58 359	72.96 362	79.47 371	90.63 355	66.24 378	73.26 385	83.40 377	63.67 387	78.02 388	78.35 391	72.53 322	89.59 380	56.68 391	60.05 395	82.57 389

dmvs_re		84.69 322	83.94 324	86.95 335	92.24 324	82.93 220	89.51 290	87.37 348	84.38 261	85.37 353	85.08 380	72.44 323	86.59 387	68.05 379	91.03 370	91.33 367

MIMVSNet		87.13 303	86.54 302	88.89 305	96.05 219	76.11 324	94.39 125	88.51 335	81.37 291	88.27 332	96.75 141	72.38 324	95.52 332	65.71 385	95.47 301	95.03 305

PAPM		81.91 342	80.11 352	87.31 331	93.87 299	72.32 356	84.02 370	93.22 288	69.47 372	76.13 391	89.84 344	72.15 325	97.23 282	53.27 393	89.02 375	92.37 360

cl22		89.02 258	88.50 258	90.59 269	89.76 365	76.45 321	86.62 347	94.03 273	82.98 277	92.65 244	92.49 308	72.05 326	97.53 266	88.93 192	97.02 261	97.78 189

LFMVS		91.33 203	91.16 208	91.82 222	96.27 202	79.36 275	95.01 104	85.61 363	96.04 30	94.82 174	97.06 119	72.03 327	98.46 188	84.96 261	98.70 153	97.65 200

test_cas_vis1_n_1920		88.25 277	88.27 266	88.20 320	92.19 328	78.92 284	89.45 292	95.44 235	75.29 338	93.23 224	95.65 206	71.58 328	90.23 377	88.05 210	93.55 343	95.44 297

MVS-HIRNet		78.83 357	80.60 348	73.51 376	93.07 311	47.37 400	87.10 334	78.00 392	68.94 373	77.53 389	97.26 103	71.45 329	94.62 347	63.28 388	88.74 376	78.55 391

EPNet_dtu		85.63 313	84.37 319	89.40 296	86.30 388	74.33 340	91.64 230	88.26 337	84.84 255	72.96 393	89.85 343	71.27 330	97.69 259	76.60 339	97.62 239	96.18 268
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test1111		90.39 223	90.61 219	89.74 290	98.04 88	71.50 359	95.59 81	79.72 388	89.41 164	95.94 117	98.14 39	70.79 331	98.81 136	88.52 202	99.32 68	98.90 74

ECVR-MVS		90.12 234	90.16 228	90.00 286	97.81 103	72.68 353	95.76 75	78.54 391	89.04 172	95.36 148	98.10 42	70.51 332	98.64 168	87.10 227	99.18 94	98.67 105

HyFIR lowres test		87.19 301	85.51 312	92.24 208	97.12 147	80.51 249	85.03 360	96.06 209	66.11 381	91.66 272	92.98 298	70.12 333	99.14 86	75.29 346	95.23 309	97.07 230

FMVSNet3		90.78 210	90.32 227	92.16 214	93.03 314	79.92 262	92.54 189	94.95 251	86.17 226	95.10 162	96.01 188	69.97 334	98.75 147	86.74 231	98.38 183	97.82 185

test_f		86.65 308	87.13 291	85.19 349	90.28 361	86.11 170	86.52 350	91.66 317	69.76 370	95.73 130	97.21 110	69.51 335	81.28 393	89.15 188	94.40 326	88.17 379

RPMNet		90.31 229	90.14 231	90.81 264	91.01 351	78.93 282	92.52 190	98.12 51	91.91 101	89.10 314	96.89 131	68.84 336	99.41 39	90.17 160	92.70 355	94.08 329

test_fmvs1_n		88.73 270	88.38 261	89.76 289	92.06 332	82.53 224	92.30 204	96.59 185	71.14 360	92.58 247	95.41 219	68.55 337	89.57 381	91.12 129	95.66 296	97.18 229

test_fmvs1		87.59 290	87.27 286	88.54 312	88.32 378	81.26 241	90.43 262	95.72 221	70.55 366	91.70 271	94.63 248	68.13 338	89.42 382	90.59 142	95.34 306	94.94 310

ADS-MVSNet2		84.01 326	82.20 336	89.41 295	89.04 373	76.37 323	87.57 323	90.98 323	72.71 354	84.46 362	92.45 309	68.08 339	96.48 310	70.58 374	83.97 384	95.38 298

ADS-MVSNet		82.25 337	81.55 338	84.34 356	89.04 373	65.30 380	87.57 323	85.13 370	72.71 354	84.46 362	92.45 309	68.08 339	92.33 366	70.58 374	83.97 384	95.38 298

CVMVSNet		85.16 317	84.72 315	86.48 338	92.12 330	70.19 364	92.32 202	88.17 340	56.15 392	90.64 289	95.85 193	67.97 341	96.69 305	88.78 197	90.52 371	92.56 358

new_pmnet		81.22 345	81.01 344	81.86 365	90.92 353	70.15 365	84.03 369	80.25 387	70.83 363	85.97 351	89.78 348	67.93 342	84.65 391	67.44 381	91.90 364	90.78 371

CR-MVSNet		87.89 281	87.12 292	90.22 279	91.01 351	78.93 282	92.52 190	92.81 294	73.08 350	89.10 314	96.93 128	67.11 343	97.64 263	88.80 196	92.70 355	94.08 329

Patchmtry		90.11 235	89.92 234	90.66 267	90.35 360	77.00 311	92.96 174	92.81 294	90.25 151	94.74 178	96.93 128	67.11 343	97.52 267	85.17 253	98.98 114	97.46 211

PatchmatchNet		85.22 316	84.64 316	86.98 334	89.51 370	69.83 369	90.52 257	87.34 349	78.87 316	87.22 345	92.74 304	66.91 345	96.53 307	81.77 290	86.88 380	94.58 321
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
GA-MVS		87.70 285	86.82 296	90.31 275	93.27 308	77.22 309	84.72 364	92.79 296	85.11 249	89.82 305	90.07 342	66.80 346	97.76 254	84.56 266	94.27 331	95.96 275

MDTV_nov1_ep13_2view						42.48 402	88.45 317		67.22 378	83.56 369		66.80 346		72.86 360		94.06 331

tpmrst		82.85 335	82.93 331	82.64 363	87.65 380	58.99 394	90.14 271	87.90 344	75.54 334	83.93 366	91.63 325	66.79 348	95.36 338	81.21 298	81.54 390	93.57 347

sam_mvs1												66.64 349				94.75 317

sam_mvs												66.41 350

Patchmatch-RL test		88.81 267	88.52 257	89.69 292	95.33 259	79.94 261	86.22 351	92.71 298	78.46 318	95.80 124	94.18 263	66.25 351	95.33 340	89.22 186	98.53 170	93.78 338

patchmatchnet-post											91.71 323	66.22 352	97.59 264

AUN-MVS		90.05 239	88.30 263	95.32 88	96.09 216	90.52 77	92.42 197	92.05 313	82.08 288	88.45 329	92.86 299	65.76 353	98.69 161	88.91 194	96.07 286	96.75 247

test_post											6.07 398	65.74 354	95.84 328

test_post1							90.21 268				5.85 399	65.36 355	96.00 325	79.61 316

MDTV_nov1_ep13			83.88 325		89.42 371	61.52 390	88.74 312	87.41 347	73.99 344	84.96 360	94.01 270	65.25 356	95.53 331	78.02 326	93.16 348

Patchmatch-test		86.10 311	86.01 308	86.38 342	90.63 355	74.22 342	89.57 288	86.69 352	85.73 234	89.81 306	92.83 300	65.24 357	91.04 372	77.82 330	95.78 294	93.88 337

tpmvs		84.22 325	83.97 323	84.94 350	87.09 385	65.18 381	91.21 239	88.35 336	82.87 278	85.21 354	90.96 334	65.24 357	96.75 303	79.60 318	85.25 383	92.90 355

EU-MVSNet		87.39 295	86.71 299	89.44 294	93.40 306	76.11 324	94.93 107	90.00 330	57.17 391	95.71 131	97.37 91	64.77 359	97.68 260	92.67 94	94.37 328	94.52 322

thres200		85.85 312	85.18 313	87.88 326	94.44 285	72.52 354	89.08 303	86.21 355	88.57 185	91.44 274	88.40 363	64.22 360	98.00 228	68.35 378	95.88 293	93.12 350

PatchT		87.51 292	88.17 272	85.55 345	90.64 354	66.91 374	92.02 213	86.09 357	92.20 93	89.05 316	97.16 112	64.15 361	96.37 316	89.21 187	92.98 353	93.37 348

tfpn200view9		87.05 304	86.52 303	88.67 309	95.77 237	72.94 350	91.89 220	86.00 358	90.84 135	92.61 245	89.80 345	63.93 362	98.28 202	71.27 369	96.54 279	94.79 315

thres400		87.20 300	86.52 303	89.24 301	95.77 237	72.94 350	91.89 220	86.00 358	90.84 135	92.61 245	89.80 345	63.93 362	98.28 202	71.27 369	96.54 279	96.51 252

FPMVS		84.50 323	83.28 327	88.16 321	96.32 197	94.49 16	85.76 354	85.47 364	83.09 274	85.20 355	94.26 259	63.79 364	86.58 388	63.72 387	91.88 365	83.40 386

thres100view900		87.35 296	86.89 295	88.72 308	96.14 213	73.09 349	93.00 173	85.31 366	92.13 95	93.26 221	90.96 334	63.42 365	98.28 202	71.27 369	96.54 279	94.79 315

thres600view7		87.66 287	87.10 293	89.36 297	96.05 219	73.17 347	92.72 181	85.31 366	91.89 102	93.29 218	90.97 333	63.42 365	98.39 191	73.23 357	96.99 266	96.51 252

EMVS		80.35 352	80.28 351	80.54 369	84.73 394	69.07 370	72.54 388	80.73 384	87.80 200	81.66 381	81.73 386	62.89 367	89.84 378	75.79 345	94.65 323	82.71 388

test-LLR		83.58 329	83.17 328	84.79 352	89.68 367	66.86 375	83.08 373	84.52 371	83.07 275	82.85 373	84.78 381	62.86 368	93.49 360	82.85 277	94.86 316	94.03 332

test0.0.03 1		82.48 336	81.47 340	85.48 346	89.70 366	73.57 346	84.73 362	81.64 380	83.07 275	88.13 334	86.61 372	62.86 368	89.10 384	66.24 384	90.29 372	93.77 339

tpm cat1		80.61 351	79.46 354	84.07 358	88.78 375	65.06 384	89.26 299	88.23 338	62.27 388	81.90 380	89.66 351	62.70 370	95.29 341	71.72 365	80.60 391	91.86 365

E-PMN		80.72 350	80.86 345	80.29 370	85.11 392	68.77 371	72.96 386	81.97 379	87.76 202	83.25 372	83.01 385	62.22 371	89.17 383	77.15 336	94.31 330	82.93 387

baseline2		83.38 330	81.54 339	88.90 304	91.38 346	72.84 352	88.78 310	81.22 383	78.97 314	79.82 386	87.56 366	61.73 372	97.80 247	74.30 352	90.05 373	96.05 273

CostFormer		83.09 332	82.21 335	85.73 344	89.27 372	67.01 373	90.35 264	86.47 354	70.42 367	83.52 370	93.23 293	61.18 373	96.85 300	77.21 335	88.26 378	93.34 349

MVSTER		89.32 252	88.75 255	91.03 253	90.10 363	76.62 319	90.85 246	94.67 262	82.27 286	95.24 157	95.79 197	61.09 374	98.49 183	90.49 144	98.26 195	97.97 168

tpm		84.38 324	84.08 322	85.30 348	90.47 358	63.43 388	89.34 296	85.63 362	77.24 326	87.62 340	95.03 233	61.00 375	97.30 280	79.26 320	91.09 369	95.16 301

FE-MVS		89.06 257	88.29 264	91.36 240	94.78 272	79.57 271	96.77 28	90.99 322	84.87 254	92.96 234	96.29 172	60.69 376	98.80 139	80.18 307	97.11 258	95.71 287

EPMVS		81.17 347	80.37 349	83.58 360	85.58 391	65.08 383	90.31 266	71.34 396	77.31 325	85.80 352	91.30 328	59.38 377	92.70 365	79.99 309	82.34 389	92.96 354

tmp_tt		37.97 362	44.33 365	18.88 379	11.80 401	21.54 403	63.51 390	45.66 403	4.23 396	51.34 396	50.48 394	59.08 378	22.11 398	44.50 396	68.35 394	13.00 394

tpm2		81.46 343	80.35 350	84.80 351	89.90 364	65.14 382	90.44 259	85.36 365	65.82 383	82.05 378	92.44 311	57.94 379	96.69 305	70.71 373	88.49 377	92.56 358

ET-MVSNet_ETH3D		86.15 310	84.27 321	91.79 223	93.04 313	81.28 240	87.17 333	86.14 356	79.57 306	83.65 367	88.66 359	57.10 380	98.18 213	87.74 217	95.40 303	95.90 280

CHOSEN 280x420		80.04 353	77.97 360	86.23 343	90.13 362	74.53 337	72.87 387	89.59 331	66.38 380	76.29 390	85.32 379	56.96 381	95.36 338	69.49 377	94.72 321	88.79 377

JIA-IIPM		85.08 318	83.04 329	91.19 250	87.56 381	86.14 169	89.40 295	84.44 373	88.98 174	82.20 376	97.95 54	56.82 382	96.15 320	76.55 340	83.45 386	91.30 368

DeepMVS_CX				53.83 378	70.38 399	64.56 385		48.52 402	33.01 394	65.50 395	74.21 393	56.19 383	46.64 397	38.45 397	70.07 393	50.30 393

dp		79.28 355	78.62 357	81.24 368	85.97 390	56.45 395	86.91 337	85.26 368	72.97 352	81.45 383	89.17 358	56.01 384	95.45 336	73.19 358	76.68 392	91.82 366

iter_conf_final		90.23 230	89.32 243	92.95 181	94.65 281	81.46 238	94.32 130	95.40 240	85.61 238	92.84 237	95.37 222	54.58 385	99.13 88	92.16 102	98.94 124	98.25 139

test_method		50.44 361	48.94 364	54.93 377	39.68 400	12.38 404	28.59 392	90.09 329	6.82 395	41.10 397	78.41 390	54.41 386	70.69 396	50.12 394	51.26 396	81.72 390

thisisatest0515		84.72 321	82.99 330	89.90 287	92.96 315	75.33 332	84.36 367	83.42 376	77.37 324	88.27 332	86.65 371	53.94 387	98.72 152	82.56 281	97.40 249	95.67 290

tttt0517		89.81 244	88.90 253	92.55 201	97.00 149	79.73 268	95.03 103	83.65 375	89.88 156	95.30 151	94.79 243	53.64 388	99.39 49	91.99 108	98.79 143	98.54 120

thisisatest0530		88.69 271	87.52 282	92.20 209	96.33 196	79.36 275	92.81 178	84.01 374	86.44 220	93.67 207	92.68 306	53.62 389	99.25 75	89.65 174	98.45 177	98.00 161

FMVSNet5		87.82 284	86.56 301	91.62 231	92.31 322	79.81 266	93.49 158	94.81 257	83.26 269	91.36 275	96.93 128	52.77 390	97.49 270	76.07 342	98.03 217	97.55 207

pmmvs3		80.83 349	78.96 356	86.45 339	87.23 384	77.48 305	84.87 361	82.31 378	63.83 386	85.03 358	89.50 352	49.66 391	93.10 362	73.12 359	95.10 311	88.78 378

iter_conf05		88.94 264	88.09 274	91.50 236	92.74 317	76.97 314	92.80 179	95.92 215	82.82 279	93.65 208	95.37 222	49.41 392	99.13 88	90.82 136	99.28 79	98.40 130

IB-MVS	77.21 19	83.11 331	81.05 342	89.29 298	91.15 349	75.85 327	85.66 355	86.00 358	79.70 304	82.02 379	86.61 372	48.26 393	98.39 191	77.84 328	92.22 360	93.63 343
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
gg-mvs-nofinetune		82.10 341	81.02 343	85.34 347	87.46 383	71.04 360	94.74 111	67.56 397	96.44 23	79.43 387	98.99 6	45.24 394	96.15 320	67.18 382	92.17 361	88.85 376

GG-mvs-BLEND				83.24 362	85.06 393	71.03 361	94.99 106	65.55 398		74.09 392	75.51 392	44.57 395	94.46 350	59.57 390	87.54 379	84.24 385

TESTMET0.1,1		79.09 356	78.04 359	82.25 364	87.52 382	64.03 387	83.08 373	80.62 385	70.28 368	80.16 385	83.22 384	44.13 396	90.56 374	79.95 310	93.36 344	92.15 361

test-mter		81.21 346	80.01 353	84.79 352	89.68 367	66.86 375	83.08 373	84.52 371	73.85 345	82.85 373	84.78 381	43.66 397	93.49 360	82.85 277	94.86 316	94.03 332

KD-MVS_2432*1600		82.17 339	80.75 346	86.42 340	82.04 397	70.09 366	81.75 378	90.80 325	82.56 281	90.37 294	89.30 354	42.90 398	96.11 322	74.47 350	92.55 357	93.06 351

miper_refine_blended		82.17 339	80.75 346	86.42 340	82.04 397	70.09 366	81.75 378	90.80 325	82.56 281	90.37 294	89.30 354	42.90 398	96.11 322	74.47 350	92.55 357	93.06 351

test2506		85.42 315	84.57 318	87.96 323	97.81 103	66.53 377	96.14 58	56.35 400	89.04 172	93.55 211	98.10 42	42.88 400	98.68 163	88.09 209	99.18 94	98.67 105

myMVS_eth3d		79.62 354	78.26 358	83.72 359	91.71 341	61.25 391	85.89 352	81.49 381	81.03 292	85.13 356	81.64 387	32.12 401	95.00 344	71.17 372	94.12 335	94.91 311

testing3		83.66 328	82.52 333	87.08 332	95.84 233	65.84 379	89.80 283	77.17 394	88.17 193	90.84 285	88.63 360	30.95 402	98.11 218	84.05 269	97.19 255	97.28 226

test123		9.49 364	12.01 367	1.91 380	2.87 402	1.30 405	82.38 376	1.34 405	1.36 398	2.84 399	6.56 397	2.45 403	0.97 399	2.73 398	5.56 397	3.47 395

testmvs		9.02 365	11.42 368	1.81 381	2.77 403	1.13 406	79.44 383	1.90 404	1.18 399	2.65 400	6.80 396	1.95 404	0.87 400	2.62 399	3.45 398	3.44 396

test_blank		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uanet_test		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

DCPMVS		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

sosnet-low-res		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

sosnet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uncertanet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

Regformer		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

ab-mvs-re		7.56 366	10.08 370	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	90.69 339	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uanet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

WAC-MVS						61.25 391								74.55 349

FOURS1					99.21 3	94.68 12	98.45 4	98.81 8	97.73 6	98.27 20

MSC_two_6792asdad				95.90 65	96.54 179	89.57 88		96.87 167					99.41 39	94.06 43	99.30 71	98.72 97

No_MVS				95.90 65	96.54 179	89.57 88		96.87 167					99.41 39	94.06 43	99.30 71	98.72 97

eth-test2					0.00 404

eth-test					0.00 404

IU-MVS					98.51 51	86.66 154		96.83 170	72.74 353	95.83 123				93.00 85	99.29 74	98.64 112

save fliter					97.46 130	88.05 124	92.04 212	97.08 150	87.63 206

test_0728_SECOND				94.88 104	98.55 45	86.72 151	95.20 96	98.22 36					99.38 55	93.44 66	99.31 69	98.53 121

GSMVS																94.75 317

test_part2					98.21 75	89.41 93				96.72 81

MTGPA								97.62 105

MTMP							94.82 109	54.62 401

gm-plane-assit					87.08 386	59.33 393			71.22 359		83.58 383		97.20 284	73.95 353

test9_res														88.16 207	98.40 179	97.83 183

agg_prior2														87.06 229	98.36 188	97.98 165

agg_prior					96.20 208	88.89 106		96.88 166		90.21 297			98.78 143

test_prior4						89.91 82	90.74 250

test_prior				94.61 118	95.95 227	87.23 137		97.36 128					98.68 163			97.93 171

旧先验2							90.00 276		68.65 374	92.71 243			96.52 308	85.15 255

新几何2							90.02 275

无先验							89.94 277	95.75 220	70.81 364				98.59 174	81.17 299		94.81 313

原ACMM2							89.34 296

testdata2													98.03 223	80.24 306

testdata1							88.96 305		88.44 187

plane_prior7					97.71 112	88.68 109

plane_prior5								97.81 91					98.95 114	89.26 184	98.51 173	98.60 117

plane_prior4											95.59 207

plane_prior3						88.43 119			90.35 150	93.31 216

plane_prior2							94.56 120		91.74 115

plane_prior1					97.38 132

plane_prior						88.12 122	93.01 172		88.98 174						98.06 214

n2								0.00 406

nn								0.00 406

door-mid								92.13 311

test11								96.65 181

door								91.26 320

HQP5-MVS						84.89 190

HQP-NCC					96.36 191		91.37 234		87.16 212	88.81 319

ACMP_Plane					96.36 191		91.37 234		87.16 212	88.81 319

BP-MVS														86.55 238

HQP4-MVS										88.81 319			98.61 170			98.15 148

HQP3-MVS								97.31 132							97.73 232

NP-MVS					96.82 162	87.10 141					93.40 288

ACMMP++_ref															98.82 139

ACMMP++															99.25 83

High-resolution multi-view benchmark