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 80	94.07 20	92.46 195	98.13 53	90.69 142	93.75 208	96.25 178	98.03 2	97.02 299	92.08 105	95.55 303	98.45 126

pmmvs6		96.80 12	97.36 9	95.15 97	99.12 8	87.82 129	96.68 30	97.86 88	96.10 27	98.14 24	99.28 3	97.94 3	98.21 211	91.38 129	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	97.54 115	98.16 2	98.94 2	99.33 2	97.84 4	99.08 93	90.73 141	99.73 13	99.59 13

ACMH	88.36 12	96.59 27	97.43 5	94.07 141	98.56 42	85.33 189	96.33 47	98.30 28	94.66 42	98.72 8	98.30 35	97.51 5	98.00 230	94.87 30	99.59 29	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 48	93.11 74	96.48 90	97.36 93	96.92 6	99.34 63	94.31 39	99.38 59	98.92 72

ACMH+	88.43 11	96.48 30	96.82 15	95.47 81	98.54 47	89.06 101	95.65 78	98.61 13	96.10 27	98.16 23	97.52 80	96.90 7	98.62 169	90.30 155	99.60 27	98.72 96

HPM-MVS		96.81 11	96.62 22	97.36 23	98.89 20	93.53 38	97.51 10	98.44 17	92.35 88	95.95 116	96.41 161	96.71 8	99.42 33	93.99 46	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	97.61 110	87.57 208	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 50	86.97 145	95.21 95	98.10 57	91.95 98	97.63 35	97.25 103	96.48 10	99.35 60	93.29 74	99.29 74	97.95 167

test_241102_ONE					98.51 50	86.97 145		98.10 57	91.85 104	97.63 35	97.03 122	96.48 10	98.95 114

LPG-MVS_test		96.38 39	96.23 39	96.84 38	98.36 65	92.13 52	95.33 90	98.25 32	91.78 111	97.07 62	97.22 107	96.38 12	99.28 72	92.07 106	99.59 29	99.11 44

LGP-MVS_train				96.84 38	98.36 65	92.13 52		98.25 32	91.78 111	97.07 62	97.22 107	96.38 12	99.28 72	92.07 106	99.59 29	99.11 44

ACMM	88.83 9	96.30 42	96.07 50	96.97 34	98.39 61	92.95 44	94.74 112	98.03 72	90.82 139	97.15 59	96.85 134	96.25 14	99.00 105	93.10 82	99.33 66	98.95 65
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
wuyk23d		87.83 288	90.79 220	78.96 383	90.46 371	88.63 110	92.72 182	90.67 331	91.65 119	98.68 11	97.64 70	96.06 15	77.53 405	59.84 399	99.41 56	70.73 403

testf1		96.77 14	96.49 26	97.60 8	99.01 14	96.70 3	96.31 50	98.33 23	94.96 38	97.30 54	97.93 54	96.05 16	97.90 237	89.32 180	99.23 86	98.19 142

APD_test2		96.77 14	96.49 26	97.60 8	99.01 14	96.70 3	96.31 50	98.33 23	94.96 38	97.30 54	97.93 54	96.05 16	97.90 237	89.32 180	99.23 86	98.19 142

ACMP	88.15 13	95.71 62	95.43 79	96.54 45	98.17 76	91.73 60	94.24 132	98.08 60	89.46 165	96.61 87	96.47 157	95.85 18	99.12 90	90.45 147	99.56 37	98.77 90
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	97.30 136	89.21 97	94.24 132	98.76 11	86.25 224	97.56 39	98.66 18	95.73 19	98.44 192	97.35 2	98.99 113	98.27 137

TransMVSNet (Re)		95.27 87	96.04 52	92.97 182	98.37 64	81.92 234	95.07 102	96.76 179	93.97 55	97.77 31	98.57 23	95.72 20	97.90 237	88.89 197	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 51	91.74 115	95.34 151	96.36 169	95.68 21	99.44 29	94.41 37	99.28 79	98.97 62

ACMMP_NAP		96.21 44	96.12 46	96.49 48	98.90 19	91.42 63	94.57 120	98.03 72	90.42 150	96.37 93	97.35 96	95.68 21	99.25 75	94.44 36	99.34 64	98.80 85

APD-MVS_3200maxsize		96.82 9	96.65 20	97.32 25	97.95 94	93.82 33	96.31 50	98.25 32	95.51 35	96.99 70	97.05 121	95.63 23	99.39 49	93.31 73	98.88 127	98.75 91

DVP-MVS		95.82 58	96.18 42	94.72 111	98.51 50	86.69 153	95.20 97	97.00 158	91.85 104	97.40 52	97.35 96	95.58 24	99.34 63	93.44 67	99.31 69	98.13 148
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 50	86.69 153	95.34 89	98.18 44	91.85 104	97.63 35	97.37 90	95.58 24

MP-MVS-pluss		96.08 48	95.92 58	96.57 44	99.06 10	91.21 65	93.25 166	98.32 25	87.89 199	96.86 75	97.38 89	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 62	94.31 17	96.79 26	98.32 25	96.69 17	96.86 75	97.56 75	95.48 27	98.77 145	90.11 164	99.44 50	98.31 134
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	93.55 163	96.62 173	88.88 107	94.67 114	98.05 67	91.26 128	97.25 58	96.40 162	95.42 28	94.36 363	92.72 94	99.19 92	97.40 216
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 82	95.27 9	96.37 44	98.12 54	95.66 33	97.00 68	97.03 122	95.40 29		93.49 61	98.84 132	98.00 159

test_241102_TWO								98.10 57	91.95 98	97.54 40	97.25 103	95.37 30	99.35 60	93.29 74	99.25 83	98.49 123

HFP-MVS		96.39 38	96.17 44	97.04 31	98.51 50	93.37 39	96.30 54	97.98 78	92.35 88	95.63 134	96.47 157	95.37 30	99.27 74	93.78 51	99.14 99	98.48 124

jajsoiax		96.59 27	96.42 29	97.12 29	98.76 31	92.49 49	96.44 41	97.42 124	86.96 217	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	96.85 158	89.20 98	93.51 158	98.60 14	85.68 237	97.42 50	98.30 35	95.34 33	98.39 193	96.85 3	98.98 114	98.19 142

TranMVSNet+NR-MVSNet		96.07 49	96.26 38	95.50 80	98.26 70	87.69 131	93.75 151	97.86 88	95.96 32	97.48 46	97.14 113	95.33 34	99.44 29	90.79 139	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	95.85 223	96.47 22	93.40 219	97.46 86	95.31 35	95.47 344	86.18 247	98.78 143	89.11 386
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 62	85.08 192	95.46 87	97.12 151	91.84 107	97.28 56	98.46 30	95.30 36	97.71 262	90.17 162	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 28	91.40 126	95.76 126	96.87 133	95.26 37	99.45 27	92.77 90	99.21 90	99.00 54

PS-CasMVS		96.69 20	97.43 5	94.49 127	99.13 6	84.09 206	96.61 32	97.97 80	97.91 5	98.64 13	98.13 41	95.24 38	99.65 3	93.39 71	99.84 3	99.72 2

test_fmvsmconf_n		95.43 73	95.50 75	95.22 94	96.48 185	89.19 99	93.23 168	98.36 22	85.61 240	96.92 73	98.02 49	95.23 39	98.38 196	96.69 6	98.95 123	98.09 150

GST-MVS		96.24 43	95.99 54	97.00 33	98.65 34	92.71 47	95.69 77	98.01 75	92.08 96	95.74 129	96.28 175	95.22 40	99.42 33	93.17 80	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 95	89.83 85	93.46 160	98.30 28	92.37 86	97.75 32	96.95 127	95.14 42	99.51 20	91.74 116	99.28 79	98.41 128
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 70	87.14 140		98.18 44	94.25 48	96.99 70	97.36 93	95.13 43

nrg030		96.32 40	96.55 25	95.62 76	97.83 101	88.55 115	95.77 73	98.29 31	92.68 79	98.03 26	97.91 58	95.13 43	98.95 114	93.85 49	99.49 42	99.36 24

APDe-MVS		96.46 31	96.64 21	95.93 62	97.68 115	89.38 95	96.90 22	98.41 20	92.52 83	97.43 48	97.92 57	95.11 45	99.50 21	94.45 35	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 44	92.26 91	96.33 95	96.84 136	95.10 46	99.40 46	93.47 64	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 84	94.69 11	96.13 59	98.07 63	95.17 37	96.82 77	96.73 145	95.09 47	99.43 32	92.99 87	98.71 150	98.50 121

OPM-MVS		95.61 65	95.45 77	96.08 54	98.49 57	91.00 68	92.65 187	97.33 134	90.05 155	96.77 80	96.85 134	95.04 48	98.56 178	92.77 90	99.06 103	98.70 100
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	84.68 195	96.51 35	97.94 86	98.14 3	98.67 12	98.32 34	95.04 48	99.69 2	93.27 76	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 81	92.26 91	95.28 155	96.57 154	95.02 50	99.41 39	93.63 55	99.11 101	98.94 66

PEN-MVS		96.69 20	97.39 8	94.61 117	99.16 4	84.50 196	96.54 34	98.05 67	98.06 4	98.64 13	98.25 37	95.01 51	99.65 3	92.95 88	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 75	98.01 75	93.34 70	96.64 85	96.57 154	94.99 52	99.36 58	93.48 63	99.34 64	98.82 82
Skip Steuart: Steuart Systems R&D Blog.
sasdasda		94.59 108	94.69 111	94.30 133	95.60 251	87.03 143	95.59 80	98.24 35	91.56 121	95.21 161	92.04 320	94.95 53	98.66 164	91.45 126	97.57 244	97.20 227

canonicalmvs		94.59 108	94.69 111	94.30 133	95.60 251	87.03 143	95.59 80	98.24 35	91.56 121	95.21 161	92.04 320	94.95 53	98.66 164	91.45 126	97.57 244	97.20 227

MGCFI-Net		94.44 115	94.67 115	93.75 156	95.56 253	85.47 186	95.25 94	98.24 35	91.53 123	95.04 169	92.21 315	94.94 55	98.54 181	91.56 124	97.66 240	97.24 225

ACMMPR		96.46 31	96.14 45	97.41 20	98.60 39	93.82 33	96.30 54	97.96 81	92.35 88	95.57 137	96.61 152	94.93 56	99.41 39	93.78 51	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	94.29 271	96.48 21	95.38 147	93.63 281	94.89 57	97.94 236	95.38 27	96.92 271	95.17 307

SR-MVS-dyc-post		96.84 7	96.60 24	97.56 10	98.07 82	95.27 9	96.37 44	98.12 54	95.66 33	97.00 68	97.03 122	94.85 58	99.42 33	93.49 61	98.84 132	98.00 159

casdiffmvs_mvg		95.10 90	95.62 71	93.53 166	96.25 204	83.23 216	92.66 186	98.19 42	93.06 75	97.49 44	97.15 112	94.78 59	98.71 157	92.27 102	98.72 148	98.65 106
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 67	94.62 14	96.80 25	98.08 60	92.67 81	95.08 168	96.39 166	94.77 60	99.42 33	93.17 80	99.44 50	98.58 118

test_0728_THIRD									93.26 71	97.40 52	97.35 96	94.69 61	99.34 63	93.88 47	99.42 52	98.89 75

9.14			94.81 104		97.49 126		94.11 139	98.37 21	87.56 209	95.38 147	96.03 188	94.66 62	99.08 93	90.70 142	98.97 119

GeoE		94.55 111	94.68 114	94.15 137	97.23 138	85.11 191	94.14 138	97.34 133	88.71 183	95.26 156	95.50 213	94.65 63	99.12 90	90.94 136	98.40 179	98.23 138

TDRefinement		97.68 3	97.60 4	97.93 2	99.02 12	95.95 8	98.61 3	98.81 9	97.41 10	97.28 56	98.46 30	94.62 64	98.84 128	94.64 33	99.53 39	98.99 56

SDMVSNet		94.43 116	95.02 98	92.69 194	97.93 95	82.88 224	91.92 222	95.99 219	93.65 65	95.51 139	98.63 20	94.60 65	96.48 318	87.57 221	99.35 61	98.70 100

XVS		96.49 29	96.18 42	97.44 16	98.56 42	93.99 26	96.50 36	97.95 83	94.58 43	94.38 191	96.49 156	94.56 66	99.39 49	93.57 57	99.05 106	98.93 68

X-MVStestdata		90.70 217	88.45 263	97.44 16	98.56 42	93.99 26	96.50 36	97.95 83	94.58 43	94.38 191	26.89 406	94.56 66	99.39 49	93.57 57	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	97.74 101	92.59 82	95.47 142	96.68 148	94.50 68	99.42 33	93.10 82	99.26 82	98.99 56

sd_testset		93.94 137	94.39 121	92.61 200	97.93 95	83.24 215	93.17 170	95.04 251	93.65 65	95.51 139	98.63 20	94.49 69	95.89 336	81.72 296	99.35 61	98.70 100

DeepC-MVS	91.39 4	95.43 73	95.33 85	95.71 74	97.67 116	90.17 80	93.86 148	98.02 74	87.35 210	96.22 105	97.99 52	94.48 70	99.05 98	92.73 93	99.68 18	97.93 169
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 69	91.19 66	95.09 100	97.79 98	86.48 220	97.42 50	97.51 83	94.47 71	99.29 70	93.55 59	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 78	89.65 87	95.58 83	98.56 15	91.84 107	96.36 94	96.68 148	94.37 72	99.32 69	92.41 100	99.05 106	98.64 111

MP-MVS		96.14 46	95.68 69	97.51 13	98.81 28	94.06 21	96.10 60	97.78 99	92.73 78	93.48 216	96.72 146	94.23 73	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 90	94.03 25	96.97 20	97.61 110	87.68 206	98.45 18	98.77 15	94.20 74	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 75	85.77 179	93.24 167	97.24 142	96.88 16	97.69 33	97.77 64	94.12 75	99.13 88	91.54 125	99.29 74	97.88 175

test_fmvsmvis_n_1920		95.08 91	95.40 81	94.13 139	96.66 168	87.75 130	93.44 162	98.49 16	85.57 241	98.27 20	97.11 116	94.11 76	97.75 258	96.26 11	98.72 148	96.89 241

Effi-MVS+		92.79 171	92.74 171	92.94 185	95.10 266	83.30 214	94.00 142	97.53 117	91.36 127	89.35 316	90.65 343	94.01 77	98.66 164	87.40 225	95.30 312	96.88 243

EC-MVSNet		95.44 72	95.62 71	94.89 103	96.93 153	87.69 131	96.48 38	99.14 4	93.93 56	92.77 244	94.52 253	93.95 78	99.49 24	93.62 56	99.22 89	97.51 207

OMC-MVS		94.22 127	93.69 145	95.81 69	97.25 137	91.27 64	92.27 208	97.40 125	87.10 216	94.56 186	95.42 217	93.74 79	98.11 220	86.62 237	98.85 131	98.06 151

LCM-MVSNet-Re		94.20 128	94.58 118	93.04 179	95.91 231	83.13 220	93.79 150	99.19 3	92.00 97	98.84 5	98.04 47	93.64 80	99.02 103	81.28 300	98.54 169	96.96 238

CS-MVS		95.77 59	95.58 73	96.37 50	96.84 159	91.72 61	96.73 29	99.06 5	94.23 49	92.48 253	94.79 243	93.56 81	99.49 24	93.47 64	99.05 106	97.89 174

MTAPA		96.65 22	96.38 33	97.47 15	98.95 18	94.05 23	95.88 70	97.62 108	94.46 47	96.29 99	96.94 128	93.56 81	99.37 57	94.29 40	99.42 52	98.99 56

CS-MVS-test		95.32 81	95.10 96	95.96 58	96.86 157	90.75 74	96.33 47	99.20 2	93.99 53	91.03 286	93.73 279	93.52 83	99.55 18	91.81 114	99.45 47	97.58 201

UA-Net		97.35 4	97.24 11	97.69 4	98.22 73	93.87 30	98.42 6	98.19 42	96.95 14	95.46 144	99.23 4	93.45 84	99.57 14	95.34 29	99.89 2	99.63 9

MVS_111021_HR		93.63 145	93.42 157	94.26 135	96.65 169	86.96 147	89.30 301	96.23 207	88.36 191	93.57 214	94.60 250	93.45 84	97.77 255	90.23 160	98.38 183	98.03 157

cdsmvs_eth3d_5k		23.35 375	31.13 378	0.00 393	0.00 416	0.00 418	0.00 404	95.58 235	0.00 411	0.00 412	91.15 332	93.43 86	0.00 412	0.00 411	0.00 410	0.00 408

APD-MVS		95.00 93	94.69 111	95.93 62	97.38 131	90.88 71	94.59 117	97.81 94	89.22 172	95.46 144	96.17 183	93.42 87	99.34 63	89.30 182	98.87 130	97.56 204
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ANet_high		94.83 100	96.28 37	90.47 274	96.65 169	73.16 352	94.33 129	98.74 12	96.39 24	98.09 25	98.93 8	93.37 88	98.70 158	90.38 150	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 79	97.64 106	93.38 69	95.89 121	97.23 105	93.35 89	97.66 265	88.20 206	98.66 159	97.79 186

casdiffmvs		94.32 122	94.80 105	92.85 189	96.05 220	81.44 241	92.35 202	98.05 67	91.53 123	95.75 128	96.80 137	93.35 89	98.49 185	91.01 135	98.32 191	98.64 111
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	97.37 126	88.98 176	98.26 22	98.86 10	93.35 89	99.60 9	96.41 9	99.45 47	99.66 6

VPA-MVSNet		95.14 89	95.67 70	93.58 162	97.76 105	83.15 219	94.58 119	97.58 112	93.39 68	97.05 65	98.04 47	93.25 92	98.51 184	89.75 174	99.59 29	99.08 48

Anonymous20240529		95.50 70	95.83 63	94.50 125	97.33 135	85.93 174	95.19 99	96.77 178	96.64 19	97.61 38	98.05 45	93.23 93	98.79 139	88.60 203	99.04 111	98.78 87

baseline		94.26 124	94.80 105	92.64 196	96.08 218	80.99 247	93.69 154	98.04 71	90.80 140	94.89 176	96.32 171	93.19 94	98.48 189	91.68 119	98.51 173	98.43 127

DeepPCF-MVS	90.46 6	94.20 128	93.56 153	96.14 52	95.96 227	92.96 43	89.48 294	97.46 121	85.14 249	96.23 104	95.42 217	93.19 94	98.08 222	90.37 151	98.76 145	97.38 219

Anonymous20231211		96.60 25	97.13 12	95.00 100	97.46 129	86.35 165	97.11 19	98.24 35	97.58 8	98.72 8	98.97 7	93.15 96	99.15 84	93.18 79	99.74 12	99.50 17

DVP-MVS++		95.93 52	96.34 34	94.70 112	96.54 178	86.66 155	98.45 4	98.22 39	93.26 71	97.54 40	97.36 93	93.12 97	99.38 55	93.88 47	98.68 155	98.04 154

OPU-MVS				95.15 97	96.84 159	89.43 92	95.21 95				95.66 206	93.12 97	98.06 223	86.28 246	98.61 161	97.95 167

LS3D		96.11 47	95.83 63	96.95 36	94.75 278	94.20 19	97.34 13	97.98 78	97.31 11	95.32 152	96.77 138	93.08 99	99.20 80	91.79 115	98.16 206	97.44 212

DP-MVS		95.62 64	95.84 62	94.97 101	97.16 143	88.62 111	94.54 124	97.64 106	96.94 15	96.58 88	97.32 100	93.07 100	98.72 151	90.45 147	98.84 132	97.57 202

EG-PatchMatch MVS		94.54 112	94.67 115	94.14 138	97.87 100	86.50 157	92.00 217	96.74 180	88.16 195	96.93 72	97.61 72	93.04 101	97.90 237	91.60 121	98.12 209	98.03 157

Fast-Effi-MVS+		91.28 209	90.86 217	92.53 204	95.45 257	82.53 227	89.25 304	96.52 195	85.00 253	89.91 306	88.55 366	92.94 102	98.84 128	84.72 269	95.44 307	96.22 269

PC_three_1452									75.31 348	95.87 122	95.75 203	92.93 103	96.34 327	87.18 228	98.68 155	98.04 154

v7n		96.82 9	97.31 10	95.33 86	98.54 47	86.81 149	96.83 23	98.07 63	96.59 20	98.46 17	98.43 32	92.91 104	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 60	93.04 41	94.54 124	98.05 67	90.45 149	96.31 97	96.76 140	92.91 104	98.72 151	91.19 130	99.42 52	98.32 132

testgi		90.38 229	91.34 207	87.50 333	97.49 126	71.54 362	89.43 296	95.16 248	88.38 190	94.54 187	94.68 247	92.88 106	93.09 374	71.60 374	97.85 230	97.88 175

MVS_111021_LR		93.66 144	93.28 160	94.80 107	96.25 204	90.95 69	90.21 271	95.43 241	87.91 197	93.74 210	94.40 255	92.88 106	96.38 323	90.39 149	98.28 193	97.07 231

CNVR-MVS		94.58 110	94.29 126	95.46 82	96.94 151	89.35 96	91.81 230	96.80 175	89.66 162	93.90 206	95.44 216	92.80 108	98.72 151	92.74 92	98.52 171	98.32 132

ZD-MVS					97.23 138	90.32 78		97.54 115	84.40 262	94.78 180	95.79 198	92.76 109	99.39 49	88.72 201	98.40 179

XXY-MVS		92.58 178	93.16 163	90.84 264	97.75 106	79.84 265	91.87 226	96.22 209	85.94 231	95.53 138	97.68 66	92.69 110	94.48 359	83.21 279	97.51 246	98.21 140

CDPH-MVS		92.67 176	91.83 195	95.18 96	96.94 151	88.46 118	90.70 255	97.07 154	77.38 332	92.34 263	95.08 231	92.67 111	98.88 121	85.74 250	98.57 166	98.20 141

Fast-Effi-MVS+-dtu		92.77 173	92.16 184	94.58 123	94.66 284	88.25 120	92.05 214	96.65 185	89.62 163	90.08 302	91.23 331	92.56 112	98.60 172	86.30 245	96.27 289	96.90 240

fmvsm_s_conf0.1_n_a		94.26 124	94.37 123	93.95 147	97.36 133	85.72 181	94.15 136	95.44 239	83.25 273	95.51 139	98.05 45	92.54 113	97.19 290	95.55 20	97.46 250	98.94 66

AllTest		94.88 98	94.51 119	96.00 56	98.02 88	92.17 50	95.26 93	98.43 18	90.48 147	95.04 169	96.74 143	92.54 113	97.86 245	85.11 262	98.98 114	97.98 163

TestCases				96.00 56	98.02 88	92.17 50		98.43 18	90.48 147	95.04 169	96.74 143	92.54 113	97.86 245	85.11 262	98.98 114	97.98 163

TinyColmap		92.00 194	92.76 170	89.71 295	95.62 250	77.02 314	90.72 254	96.17 212	87.70 205	95.26 156	96.29 173	92.54 113	96.45 320	81.77 294	98.77 144	95.66 296

EGC-MVSNET		80.97 357	75.73 373	96.67 42	98.85 24	94.55 15	96.83 23	96.60 187	2.44 408	5.32 409	98.25 37	92.24 117	98.02 228	91.85 113	99.21 90	97.45 210

fmvsm_s_conf0.5_n_a		94.02 134	94.08 135	93.84 153	96.72 165	85.73 180	93.65 156	95.23 247	83.30 271	95.13 163	97.56 75	92.22 118	97.17 291	95.51 22	97.41 252	98.64 111

ETV-MVS		92.99 164	92.74 171	93.72 158	95.86 233	86.30 166	92.33 203	97.84 91	91.70 118	92.81 241	86.17 382	92.22 118	99.19 81	88.03 214	97.73 234	95.66 296

CLD-MVS		91.82 195	91.41 205	93.04 179	96.37 188	83.65 211	86.82 346	97.29 138	84.65 259	92.27 265	89.67 354	92.20 120	97.85 247	83.95 274	99.47 43	97.62 199
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
segment_acmp												92.14 121

Vis-MVSNet		95.50 70	95.48 76	95.56 79	98.11 79	89.40 94	95.35 88	98.22 39	92.36 87	94.11 194	98.07 44	92.02 122	99.44 29	93.38 72	97.67 239	97.85 179
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ITE_SJBPF				95.95 59	97.34 134	93.36 40		96.55 194	91.93 100	94.82 178	95.39 221	91.99 123	97.08 296	85.53 253	97.96 224	97.41 213

CP-MVSNet		96.19 45	96.80 16	94.38 132	98.99 16	83.82 209	96.31 50	97.53 117	97.60 7	98.34 19	97.52 80	91.98 124	99.63 6	93.08 84	99.81 8	99.70 3

CSCG		94.69 105	94.75 107	94.52 124	97.55 123	87.87 127	95.01 105	97.57 113	92.68 79	96.20 107	93.44 287	91.92 125	98.78 142	89.11 191	99.24 85	96.92 239

fmvsm_s_conf0.1_n		94.19 130	94.41 120	93.52 168	97.22 140	84.37 197	93.73 152	95.26 246	84.45 261	95.76 126	98.00 50	91.85 126	97.21 287	95.62 17	97.82 231	98.98 60

TSAR-MVS + MP.		94.96 95	94.75 107	95.57 78	98.86 22	88.69 108	96.37 44	96.81 174	85.23 246	94.75 181	97.12 115	91.85 126	99.40 46	93.45 66	98.33 189	98.62 115
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		94.00 135	94.20 131	93.42 172	96.69 166	84.37 197	93.38 164	95.13 249	84.50 260	95.40 146	97.55 79	91.77 128	97.20 288	95.59 18	97.79 232	98.69 103

Gipuma		95.31 84	95.80 65	93.81 155	97.99 93	90.91 70	96.42 42	97.95 83	96.69 17	91.78 273	98.85 12	91.77 128	95.49 343	91.72 117	99.08 102	95.02 315
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	86.44 161	96.78 27	98.08 60	97.42 9	98.48 16	97.86 61	91.76 130	99.63 6	94.23 41	99.84 3	99.66 6

AdaColmap		91.63 200	91.36 206	92.47 206	95.56 253	86.36 164	92.24 211	96.27 204	88.88 180	89.90 307	92.69 305	91.65 131	98.32 202	77.38 338	97.64 241	92.72 368

PHI-MVS		94.34 121	93.80 140	95.95 59	95.65 247	91.67 62	94.82 110	97.86 88	87.86 200	93.04 235	94.16 264	91.58 132	98.78 142	90.27 157	98.96 121	97.41 213

xiu_mvs_v1_base_debu		91.47 204	91.52 200	91.33 243	95.69 244	81.56 238	89.92 281	96.05 216	83.22 274	91.26 280	90.74 338	91.55 133	98.82 130	89.29 183	95.91 295	93.62 355

xiu_mvs_v1_base		91.47 204	91.52 200	91.33 243	95.69 244	81.56 238	89.92 281	96.05 216	83.22 274	91.26 280	90.74 338	91.55 133	98.82 130	89.29 183	95.91 295	93.62 355

xiu_mvs_v1_base_debi		91.47 204	91.52 200	91.33 243	95.69 244	81.56 238	89.92 281	96.05 216	83.22 274	91.26 280	90.74 338	91.55 133	98.82 130	89.29 183	95.91 295	93.62 355

tfpnnormal		94.27 123	94.87 103	92.48 205	97.71 111	80.88 249	94.55 123	95.41 242	93.70 61	96.67 84	97.72 65	91.40 136	98.18 215	87.45 223	99.18 94	98.36 130

3Dnovator+	92.74 2	95.86 57	95.77 66	96.13 53	96.81 162	90.79 73	96.30 54	97.82 93	96.13 26	94.74 182	97.23 105	91.33 137	99.16 83	93.25 77	98.30 192	98.46 125

TEST9					96.45 186	89.46 90	90.60 258	96.92 165	79.09 321	90.49 293	94.39 256	91.31 138	98.88 121

DeepC-MVS_fast	89.96 7	93.73 143	93.44 156	94.60 120	96.14 213	87.90 126	93.36 165	97.14 148	85.53 242	93.90 206	95.45 215	91.30 139	98.59 174	89.51 177	98.62 160	97.31 222
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		94.36 119	94.28 127	94.61 117	92.55 328	85.98 173	92.44 197	94.69 263	93.70 61	96.12 111	95.81 197	91.24 140	98.86 125	93.76 54	98.22 201	98.98 60

MCST-MVS		92.91 166	92.51 178	94.10 140	97.52 124	85.72 181	91.36 240	97.13 150	80.33 306	92.91 240	94.24 260	91.23 141	98.72 151	89.99 168	97.93 226	97.86 177

RPSCF		95.58 68	94.89 102	97.62 7	97.58 121	96.30 7	95.97 66	97.53 117	92.42 84	93.41 217	97.78 62	91.21 142	97.77 255	91.06 132	97.06 263	98.80 85

train_agg		92.71 175	91.83 195	95.35 84	96.45 186	89.46 90	90.60 258	96.92 165	79.37 315	90.49 293	94.39 256	91.20 143	98.88 121	88.66 202	98.43 178	97.72 193

test_8					96.37 188	89.14 100	90.51 261	96.89 168	79.37 315	90.42 295	94.36 258	91.20 143	98.82 130

EI-MVSNet-UG-set		94.35 120	94.27 129	94.59 121	92.46 331	85.87 176	92.42 199	94.69 263	93.67 64	96.13 110	95.84 196	91.20 143	98.86 125	93.78 51	98.23 199	99.03 52

EIA-MVS		92.35 186	92.03 188	93.30 175	95.81 238	83.97 207	92.80 180	98.17 48	87.71 204	89.79 310	87.56 372	91.17 146	99.18 82	87.97 215	97.27 256	96.77 247

dcpmvs_2		93.96 136	95.01 99	90.82 265	97.60 119	74.04 347	93.68 155	98.85 8	89.80 160	97.82 29	97.01 125	91.14 147	99.21 78	90.56 145	98.59 164	99.19 36

xiu_mvs_v2_base		89.00 265	89.19 248	88.46 320	94.86 272	74.63 339	86.97 340	95.60 229	80.88 302	87.83 341	88.62 365	91.04 148	98.81 135	82.51 287	94.38 333	91.93 374

HPM-MVS++		95.02 92	94.39 121	96.91 37	97.88 98	93.58 37	94.09 140	96.99 160	91.05 134	92.40 258	95.22 225	91.03 149	99.25 75	92.11 103	98.69 153	97.90 172

test_fmvsm_n_1920		94.72 103	94.74 109	94.67 113	96.30 199	88.62 111	93.19 169	98.07 63	85.63 239	97.08 61	97.35 96	90.86 150	97.66 265	95.70 16	98.48 176	97.74 192

TAPA-MVS	88.58 10	92.49 181	91.75 197	94.73 110	96.50 182	89.69 86	92.91 177	97.68 104	78.02 329	92.79 243	94.10 265	90.85 151	97.96 234	84.76 268	98.16 206	96.54 252
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
fmvsm_l_conf0.5_n		93.79 141	93.81 138	93.73 157	96.16 210	86.26 167	92.46 195	96.72 181	81.69 295	95.77 125	97.11 116	90.83 152	97.82 248	95.58 19	97.99 221	97.11 230

pcd_1.5k_mvsjas		7.56 378	10.09 381	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	90.77 153	0.00 412	0.00 411	0.00 410	0.00 408

PS-MVSNAJss		96.01 50	96.04 52	95.89 67	98.82 26	88.51 116	95.57 84	97.88 87	88.72 182	98.81 6	98.86 10	90.77 153	99.60 9	95.43 26	99.53 39	99.57 14

PS-MVSNAJ		88.86 271	88.99 254	88.48 319	94.88 270	74.71 337	86.69 349	95.60 229	80.88 302	87.83 341	87.37 375	90.77 153	98.82 130	82.52 286	94.37 334	91.93 374

MVS_Test		92.57 180	93.29 158	90.40 278	93.53 310	75.85 331	92.52 191	96.96 161	88.73 181	92.35 261	96.70 147	90.77 153	98.37 200	92.53 98	95.49 305	96.99 237

MIMVSNet1		95.52 69	95.45 77	95.72 73	99.14 5	89.02 102	96.23 57	96.87 170	93.73 60	97.87 28	98.49 29	90.73 157	99.05 98	86.43 243	99.60 27	99.10 47

ab-mvs		92.40 184	92.62 176	91.74 227	97.02 147	81.65 237	95.84 71	95.50 238	86.95 218	92.95 239	97.56 75	90.70 158	97.50 272	79.63 319	97.43 251	96.06 276

Test By Simon												90.61 159

3Dnovator	92.54 3	94.80 101	94.90 101	94.47 128	95.47 256	87.06 142	96.63 31	97.28 140	91.82 110	94.34 193	97.41 87	90.60 160	98.65 167	92.47 99	98.11 210	97.70 194

NCCC		94.08 132	93.54 154	95.70 75	96.49 183	89.90 83	92.39 201	96.91 167	90.64 144	92.33 264	94.60 250	90.58 161	98.96 111	90.21 161	97.70 237	98.23 138

UniMVSNet_NR-MVSNet		95.35 79	95.21 90	95.76 71	97.69 114	88.59 113	92.26 209	97.84 91	94.91 40	96.80 78	95.78 201	90.42 162	99.41 39	91.60 121	99.58 34	99.29 29

test_prior2							90.21 271		89.33 169	90.77 289	94.81 240	90.41 163		88.21 205	98.55 167

KD-MVS_self_test		94.10 131	94.73 110	92.19 212	97.66 117	79.49 275	94.86 109	97.12 151	89.59 164	96.87 74	97.65 69	90.40 164	98.34 201	89.08 192	99.35 61	98.75 91

MSLP-MVS++		93.25 157	93.88 137	91.37 241	96.34 194	82.81 225	93.11 171	97.74 101	89.37 168	94.08 196	95.29 224	90.40 164	96.35 325	90.35 152	98.25 197	94.96 316

fmvsm_l_conf0.5_n_a		93.59 146	93.63 148	93.49 170	96.10 216	85.66 183	92.32 204	96.57 190	81.32 298	95.63 134	97.14 113	90.19 166	97.73 261	95.37 28	98.03 217	97.07 231

UniMVSNet (Re)		95.32 81	95.15 93	95.80 70	97.79 104	88.91 105	92.91 177	98.07 63	93.46 67	96.31 97	95.97 191	90.14 167	99.34 63	92.11 103	99.64 24	99.16 38

Effi-MVS+-dtu		93.90 140	92.60 177	97.77 3	94.74 279	96.67 5	94.00 142	95.41 242	89.94 156	91.93 272	92.13 318	90.12 168	98.97 110	87.68 220	97.48 248	97.67 197

FMVSNet1		94.84 99	95.13 94	93.97 144	97.60 119	84.29 199	95.99 63	96.56 191	92.38 85	97.03 66	98.53 26	90.12 168	98.98 106	88.78 199	99.16 97	98.65 106

DU-MVS		95.28 85	95.12 95	95.75 72	97.75 106	88.59 113	92.58 189	97.81 94	93.99 53	96.80 78	95.90 192	90.10 170	99.41 39	91.60 121	99.58 34	99.26 30

NR-MVSNet		95.28 85	95.28 88	95.26 90	97.75 106	87.21 138	95.08 101	97.37 126	93.92 58	97.65 34	95.90 192	90.10 170	99.33 68	90.11 164	99.66 21	99.26 30

Baseline_NR-MVSNet		94.47 114	95.09 97	92.60 201	98.50 56	80.82 250	92.08 213	96.68 183	93.82 59	96.29 99	98.56 24	90.10 170	97.75 258	90.10 166	99.66 21	99.24 32

API-MVS		91.52 203	91.61 198	91.26 247	94.16 293	86.26 167	94.66 115	94.82 258	91.17 132	92.13 268	91.08 334	90.03 173	97.06 298	79.09 326	97.35 255	90.45 384

patch_mono-2		92.46 182	92.72 174	91.71 229	96.65 169	78.91 287	88.85 311	97.17 146	83.89 267	92.45 255	96.76 140	89.86 174	97.09 295	90.24 159	98.59 164	99.12 43

test12				94.43 130	95.95 228	86.75 151		96.24 206		89.76 311		89.79 175	98.79 139		97.95 225	97.75 191

旧先验1					96.20 207	84.17 204		94.82 258			95.57 212	89.57 176			97.89 228	96.32 264

DELS-MVS		92.05 193	92.16 184	91.72 228	94.44 288	80.13 256	87.62 326	97.25 141	87.34 211	92.22 266	93.18 294	89.54 177	98.73 150	89.67 175	98.20 204	96.30 265
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		93.08 161	93.76 142	91.03 255	98.60 39	75.83 333	91.51 235	95.62 228	91.84 107	95.74 129	97.10 118	89.31 178	98.32 202	85.07 264	99.06 103	98.93 68

QAPM		92.88 168	92.77 169	93.22 177	95.82 236	83.31 213	96.45 39	97.35 132	83.91 266	93.75 208	96.77 138	89.25 179	98.88 121	84.56 270	97.02 265	97.49 208

MSDG		90.82 213	90.67 223	91.26 247	94.16 293	83.08 221	86.63 351	96.19 210	90.60 146	91.94 271	91.89 322	89.16 180	95.75 338	80.96 305	94.51 331	94.95 317

CPTT-MVS		94.74 102	94.12 133	96.60 43	98.15 77	93.01 42	95.84 71	97.66 105	89.21 173	93.28 223	95.46 214	88.89 181	98.98 106	89.80 171	98.82 138	97.80 185

DP-MVS Recon		92.31 187	91.88 193	93.60 161	97.18 142	86.87 148	91.10 245	97.37 126	84.92 255	92.08 269	94.08 266	88.59 182	98.20 212	83.50 276	98.14 208	95.73 291

FC-MVSNet-test		95.32 81	95.88 59	93.62 160	98.49 57	81.77 235	95.90 69	98.32 25	93.93 56	97.53 42	97.56 75	88.48 183	99.40 46	92.91 89	99.83 5	99.68 4

OpenMVS	89.45 8	92.27 189	92.13 187	92.68 195	94.53 287	84.10 205	95.70 75	97.03 156	82.44 288	91.14 284	96.42 160	88.47 184	98.38 196	85.95 248	97.47 249	95.55 301

F-COLMAP		92.28 188	91.06 213	95.95 59	97.52 124	91.90 56	93.53 157	97.18 145	83.98 265	88.70 328	94.04 267	88.41 185	98.55 180	80.17 312	95.99 294	97.39 217

ambc				92.98 181	96.88 155	83.01 222	95.92 68	96.38 201		96.41 92	97.48 85	88.26 186	97.80 250	89.96 169	98.93 124	98.12 149

v10		94.68 106	95.27 89	92.90 187	96.57 175	80.15 254	94.65 116	97.57 113	90.68 143	97.43 48	98.00 50	88.18 187	99.15 84	94.84 31	99.55 38	99.41 20

v8		94.65 107	95.29 87	92.74 192	96.65 169	79.77 269	94.59 117	97.17 146	91.86 103	97.47 47	97.93 54	88.16 188	99.08 93	94.32 38	99.47 43	99.38 22

TSAR-MVS + GP.		93.07 163	92.41 181	95.06 99	95.82 236	90.87 72	90.97 247	92.61 306	88.04 196	94.61 185	93.79 278	88.08 189	97.81 249	89.41 179	98.39 182	96.50 257

OurMVSNet-221017-0		96.80 12	96.75 17	96.96 35	99.03 11	91.85 57	97.98 7	98.01 75	94.15 51	98.93 3	99.07 5	88.07 190	99.57 14	95.86 15	99.69 14	99.46 18

diffmvs		91.74 197	91.93 192	91.15 253	93.06 317	78.17 297	88.77 314	97.51 120	86.28 223	92.42 257	93.96 272	88.04 191	97.46 275	90.69 143	96.67 280	97.82 183
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				92.87 188	96.91 154	84.22 202		97.01 157	76.84 338	89.64 313	94.46 254	88.00 192	98.70 158	81.53 298	98.01 220	95.70 294

VDD-MVS		94.37 118	94.37 123	94.40 131	97.49 126	86.07 172	93.97 145	93.28 290	94.49 45	96.24 103	97.78 62	87.99 193	98.79 139	88.92 195	99.14 99	98.34 131

XVG-OURS		94.72 103	94.12 133	96.50 47	98.00 90	94.23 18	91.48 236	98.17 48	90.72 141	95.30 153	96.47 157	87.94 194	96.98 300	91.41 128	97.61 243	98.30 135

CANet		92.38 185	91.99 190	93.52 168	93.82 306	83.46 212	91.14 243	97.00 158	89.81 159	86.47 354	94.04 267	87.90 195	99.21 78	89.50 178	98.27 194	97.90 172

BH-untuned		90.68 218	90.90 215	90.05 289	95.98 226	79.57 273	90.04 277	94.94 255	87.91 197	94.07 197	93.00 296	87.76 196	97.78 254	79.19 325	95.17 315	92.80 367

FIs		94.90 97	95.35 83	93.55 163	98.28 68	81.76 236	95.33 90	98.14 52	93.05 76	97.07 62	97.18 110	87.65 197	99.29 70	91.72 117	99.69 14	99.61 11

v1144		93.50 147	93.81 138	92.57 202	96.28 200	79.61 272	91.86 228	96.96 161	86.95 218	95.91 119	96.32 171	87.65 197	98.96 111	93.51 60	98.88 127	99.13 41

mvs_anonymous		90.37 230	91.30 208	87.58 332	92.17 339	68.00 377	89.84 284	94.73 262	83.82 268	93.22 229	97.40 88	87.54 199	97.40 280	87.94 216	95.05 318	97.34 220

PCF-MVS	84.52 17	89.12 259	87.71 284	93.34 173	96.06 219	85.84 177	86.58 354	97.31 135	68.46 386	93.61 213	93.89 275	87.51 200	98.52 183	67.85 387	98.11 210	95.66 296
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
VNet		92.67 176	92.96 164	91.79 225	96.27 201	80.15 254	91.95 218	94.98 253	92.19 94	94.52 188	96.07 186	87.43 201	97.39 281	84.83 266	98.38 183	97.83 181

v148		92.87 169	93.29 158	91.62 233	96.25 204	77.72 306	91.28 241	95.05 250	89.69 161	95.93 118	96.04 187	87.34 202	98.38 196	90.05 167	97.99 221	98.78 87

V42		93.43 150	93.58 151	92.97 182	95.34 262	81.22 244	92.67 185	96.49 196	87.25 212	96.20 107	96.37 168	87.32 203	98.85 127	92.39 101	98.21 202	98.85 81

v1192		93.49 148	93.78 141	92.62 199	96.16 210	79.62 271	91.83 229	97.22 144	86.07 229	96.10 112	96.38 167	87.22 204	99.02 103	94.14 43	98.88 127	99.22 33

WR-MVS		93.49 148	93.72 143	92.80 191	97.57 122	80.03 260	90.14 274	95.68 227	93.70 61	96.62 86	95.39 221	87.21 205	99.04 101	87.50 222	99.64 24	99.33 26

IterMVS-LS		93.78 142	94.28 127	92.27 209	96.27 201	79.21 282	91.87 226	96.78 176	91.77 113	96.57 89	97.07 119	87.15 206	98.74 149	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		92.99 164	93.26 162	92.19 212	92.12 340	79.21 282	92.32 204	94.67 265	91.77 113	95.24 159	95.85 194	87.14 207	98.49 185	91.99 108	98.26 195	98.86 78

v144192		93.20 160	93.54 154	92.16 216	96.05 220	78.26 296	91.95 218	97.14 148	84.98 254	95.96 115	96.11 184	87.08 208	99.04 101	93.79 50	98.84 132	99.17 37

114514_t		90.51 222	89.80 242	92.63 198	98.00 90	82.24 231	93.40 163	97.29 138	65.84 393	89.40 315	94.80 242	86.99 209	98.75 146	83.88 275	98.61 161	96.89 241

新几何1				93.17 178	97.16 143	87.29 135		94.43 268	67.95 387	91.29 279	94.94 236	86.97 210	98.23 210	81.06 304	97.75 233	93.98 345

HQP_MVS		94.26 124	93.93 136	95.23 93	97.71 111	88.12 122	94.56 121	97.81 94	91.74 115	93.31 220	95.59 208	86.93 211	98.95 114	89.26 186	98.51 173	98.60 116

plane_prior6					97.21 141	88.23 121						86.93 211

UGNet		93.08 161	92.50 179	94.79 108	93.87 304	87.99 125	95.07 102	94.26 273	90.64 144	87.33 350	97.67 68	86.89 213	98.49 185	88.10 210	98.71 150	97.91 171
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		92.72 174	92.02 189	94.84 106	95.65 247	91.99 54	92.92 176	96.60 187	85.08 252	92.44 256	93.62 282	86.80 214	96.35 325	86.81 232	98.25 197	96.18 271

v1921920		93.26 155	93.61 150	92.19 212	96.04 224	78.31 295	91.88 225	97.24 142	85.17 248	96.19 109	96.19 180	86.76 215	99.05 98	94.18 42	98.84 132	99.22 33

MVS_0304		93.92 138	93.68 146	94.64 116	95.94 230	85.83 178	94.34 128	88.14 345	92.98 77	91.09 285	97.68 66	86.73 216	99.36 58	96.64 7	99.59 29	98.72 96

v1240		93.29 153	93.71 144	92.06 219	96.01 225	77.89 302	91.81 230	97.37 126	85.12 250	96.69 83	96.40 162	86.67 217	99.07 97	94.51 34	98.76 145	99.22 33

MAR-MVS		90.32 233	88.87 258	94.66 115	94.82 273	91.85 57	94.22 134	94.75 261	80.91 301	87.52 348	88.07 370	86.63 218	97.87 244	76.67 342	96.21 290	94.25 339
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	94.63 117	97.48 14	98.67 33	94.05 23	96.41 43	98.18 44	91.26 128	95.12 164	95.15 226	86.60 219	99.50 21	93.43 70	96.81 275	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		90.47 224	90.44 228	90.56 273	95.21 265	78.65 293	89.15 305	93.94 281	88.21 192	92.74 245	94.22 261	86.38 220	97.88 241	78.67 328	95.39 309	95.14 310

CNLPA		91.72 198	91.20 209	93.26 176	96.17 209	91.02 67	91.14 243	95.55 236	90.16 154	90.87 287	93.56 285	86.31 221	94.40 362	79.92 318	97.12 261	94.37 336

PVSNet_BlendedMVS		90.35 231	89.96 238	91.54 236	94.81 274	78.80 291	90.14 274	96.93 163	79.43 314	88.68 329	95.06 232	86.27 222	98.15 218	80.27 308	98.04 216	97.68 196

PVSNet_Blended		88.74 274	88.16 278	90.46 277	94.81 274	78.80 291	86.64 350	96.93 163	74.67 350	88.68 329	89.18 361	86.27 222	98.15 218	80.27 308	96.00 293	94.44 335

PAPR		87.65 293	86.77 303	90.27 281	92.85 323	77.38 310	88.56 319	96.23 207	76.82 339	84.98 365	89.75 353	86.08 224	97.16 293	72.33 369	93.35 355	96.26 268

v2v482		93.29 153	93.63 148	92.29 208	96.35 193	78.82 289	91.77 232	96.28 203	88.45 188	95.70 133	96.26 177	86.02 225	98.90 118	93.02 85	98.81 140	99.14 40

test20.03		90.80 214	90.85 218	90.63 271	95.63 249	79.24 280	89.81 285	92.87 297	89.90 157	94.39 190	96.40 162	85.77 226	95.27 351	73.86 361	99.05 106	97.39 217

PLC	85.34 15	90.40 226	88.92 255	94.85 105	96.53 181	90.02 81	91.58 234	96.48 197	80.16 307	86.14 356	92.18 316	85.73 227	98.25 209	76.87 341	94.61 330	96.30 265
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVS		84.98 324	84.30 325	87.01 337	91.03 362	77.69 307	91.94 220	94.16 274	59.36 401	84.23 372	87.50 374	85.66 228	96.80 310	71.79 371	93.05 363	86.54 394

testdata				91.03 255	96.87 156	82.01 232		94.28 272	71.55 368	92.46 254	95.42 217	85.65 229	97.38 283	82.64 284	97.27 256	93.70 352

PM-MVS		93.33 152	92.67 175	95.33 86	96.58 174	94.06 21	92.26 209	92.18 311	85.92 232	96.22 105	96.61 152	85.64 230	95.99 334	90.35 152	98.23 199	95.93 282

SSC-MVS		90.16 236	92.96 164	81.78 377	97.88 98	48.48 409	90.75 252	87.69 350	96.02 31	96.70 82	97.63 71	85.60 231	97.80 250	85.73 251	98.60 163	99.06 50

MM		94.41 117	94.14 132	95.22 94	95.84 234	87.21 138	94.31 131	90.92 328	94.48 46	92.80 242	97.52 80	85.27 232	99.49 24	96.58 8	99.57 36	98.97 62

WB-MVS		89.44 254	92.15 186	81.32 378	97.73 109	48.22 410	89.73 287	87.98 348	95.24 36	96.05 113	96.99 126	85.18 233	96.95 301	82.45 288	97.97 223	98.78 87

MDA-MVSNet-bldmvs		91.04 210	90.88 216	91.55 235	94.68 283	80.16 253	85.49 367	92.14 314	90.41 151	94.93 174	95.79 198	85.10 234	96.93 304	85.15 259	94.19 341	97.57 202

PAPM_NR		91.03 211	90.81 219	91.68 231	96.73 164	81.10 246	93.72 153	96.35 202	88.19 193	88.77 326	92.12 319	85.09 235	97.25 285	82.40 289	93.90 346	96.68 250

WB-MVSnew		84.20 331	83.89 330	85.16 359	91.62 355	66.15 388	88.44 321	81.00 392	76.23 341	87.98 339	87.77 371	84.98 236	93.35 372	62.85 397	94.10 344	95.98 279

HQP2-MVS												84.76 237

HQP-MVS		92.09 192	91.49 203	93.88 150	96.36 190	84.89 193	91.37 237	97.31 135	87.16 213	88.81 322	93.40 288	84.76 237	98.60 172	86.55 240	97.73 234	98.14 147

test222					96.95 150	85.27 190	88.83 312	93.61 282	65.09 395	90.74 290	94.85 239	84.62 239			97.36 254	93.91 346

VDDNet		94.03 133	94.27 129	93.31 174	98.87 21	82.36 230	95.51 86	91.78 320	97.19 12	96.32 96	98.60 22	84.24 240	98.75 146	87.09 230	98.83 137	98.81 84

PVSNet_Blended_VisFu		91.63 200	91.20 209	92.94 185	97.73 109	83.95 208	92.14 212	97.46 121	78.85 325	92.35 261	94.98 234	84.16 241	99.08 93	86.36 244	96.77 277	95.79 289

CL-MVSNet_self_test		90.04 244	89.90 240	90.47 274	95.24 264	77.81 304	86.60 353	92.62 305	85.64 238	93.25 227	93.92 273	83.84 242	96.06 332	79.93 316	98.03 217	97.53 206

mvsany_test3		89.11 260	88.21 276	91.83 223	91.30 360	90.25 79	88.09 323	78.76 399	76.37 340	96.43 91	98.39 33	83.79 243	90.43 387	86.57 238	94.20 339	94.80 325

mvsmamba		95.61 65	95.40 81	96.22 51	98.44 59	89.86 84	97.14 17	97.45 123	91.25 130	97.49 44	98.14 39	83.49 244	99.45 27	95.52 21	99.66 21	99.36 24

BH-w/o		87.21 304	87.02 299	87.79 331	94.77 277	77.27 312	87.90 324	93.21 293	81.74 294	89.99 305	88.39 368	83.47 245	96.93 304	71.29 375	92.43 370	89.15 385

PatchMatch-RL		89.18 257	88.02 281	92.64 196	95.90 232	92.87 45	88.67 318	91.06 325	80.34 305	90.03 304	91.67 326	83.34 246	94.42 361	76.35 346	94.84 324	90.64 383

DPM-MVS		89.35 255	88.40 264	92.18 215	96.13 215	84.20 203	86.96 341	96.15 213	75.40 346	87.36 349	91.55 329	83.30 247	98.01 229	82.17 292	96.62 281	94.32 338

OpenMVS_ROB	85.12 16	89.52 252	89.05 251	90.92 260	94.58 286	81.21 245	91.10 245	93.41 289	77.03 336	93.41 217	93.99 271	83.23 248	97.80 250	79.93 316	94.80 325	93.74 351

new-patchmatchnet		88.97 266	90.79 220	83.50 372	94.28 292	55.83 407	85.34 369	93.56 285	86.18 227	95.47 142	95.73 204	83.10 249	96.51 317	85.40 254	98.06 214	98.16 145

mvsany_test1		83.91 333	82.93 337	86.84 342	86.18 401	85.93 174	81.11 391	75.03 406	70.80 376	88.57 331	94.63 248	83.08 250	87.38 396	80.39 306	86.57 392	87.21 392

1314		86.46 314	86.33 311	86.87 341	91.65 354	74.54 340	91.94 220	94.10 275	74.28 353	84.78 367	87.33 376	83.03 251	95.00 353	78.72 327	91.16 379	91.06 381

IS-MVSNet		94.49 113	94.35 125	94.92 102	98.25 72	86.46 160	97.13 18	94.31 270	96.24 25	96.28 101	96.36 169	82.88 252	99.35 60	88.19 207	99.52 41	98.96 64

test_fmvs3		92.42 183	92.40 182	92.46 207	93.80 307	87.28 136	93.86 148	97.05 155	76.86 337	96.25 102	98.66 18	82.87 253	91.26 382	95.44 25	96.83 274	98.82 82

MG-MVS		89.54 251	89.80 242	88.76 311	94.88 270	72.47 359	89.60 290	92.44 309	85.82 233	89.48 314	95.98 190	82.85 254	97.74 260	81.87 293	95.27 313	96.08 275

TR-MVS		87.70 290	87.17 294	89.27 303	94.11 295	79.26 279	88.69 316	91.86 319	81.94 293	90.69 291	89.79 351	82.82 255	97.42 278	72.65 368	91.98 374	91.14 380

c3_l		91.32 208	91.42 204	91.00 258	92.29 333	76.79 321	87.52 332	96.42 199	85.76 235	94.72 184	93.89 275	82.73 256	98.16 217	90.93 137	98.55 167	98.04 154

YYNet1		88.17 283	88.24 273	87.93 328	92.21 336	73.62 349	80.75 392	88.77 337	82.51 287	94.99 172	95.11 229	82.70 257	93.70 368	83.33 277	93.83 347	96.48 258

MDA-MVSNet_test_wron		88.16 284	88.23 274	87.93 328	92.22 335	73.71 348	80.71 393	88.84 336	82.52 286	94.88 177	95.14 227	82.70 257	93.61 369	83.28 278	93.80 348	96.46 259

pmmvs-eth3d		91.54 202	90.73 222	93.99 142	95.76 241	87.86 128	90.83 250	93.98 280	78.23 328	94.02 201	96.22 179	82.62 259	96.83 309	86.57 238	98.33 189	97.29 223

Anonymous20231206		88.77 273	88.29 269	90.20 285	96.31 197	78.81 290	89.56 292	93.49 287	74.26 354	92.38 259	95.58 211	82.21 260	95.43 346	72.07 370	98.75 147	96.34 263

miper_ehance_all_eth		90.48 223	90.42 229	90.69 268	91.62 355	76.57 324	86.83 345	96.18 211	83.38 270	94.06 198	92.66 307	82.20 261	98.04 224	89.79 172	97.02 265	97.45 210

USDC		89.02 262	89.08 250	88.84 310	95.07 267	74.50 342	88.97 307	96.39 200	73.21 360	93.27 224	96.28 175	82.16 262	96.39 322	77.55 335	98.80 141	95.62 299

EPP-MVSNet		93.91 139	93.68 146	94.59 121	98.08 81	85.55 185	97.44 12	94.03 276	94.22 50	94.94 173	96.19 180	82.07 263	99.57 14	87.28 227	98.89 125	98.65 106

UnsupCasMVSNet_eth		90.33 232	90.34 231	90.28 280	94.64 285	80.24 252	89.69 289	95.88 221	85.77 234	93.94 205	95.69 205	81.99 264	92.98 375	84.21 272	91.30 377	97.62 199

alignmvs		93.26 155	92.85 168	94.50 125	95.70 243	87.45 133	93.45 161	95.76 224	91.58 120	95.25 158	92.42 313	81.96 265	98.72 151	91.61 120	97.87 229	97.33 221

TAMVS		90.16 236	89.05 251	93.49 170	96.49 183	86.37 163	90.34 268	92.55 307	80.84 304	92.99 236	94.57 252	81.94 266	98.20 212	73.51 362	98.21 202	95.90 285

Anonymous202405211		92.58 178	92.50 179	92.83 190	96.55 177	83.22 217	92.43 198	91.64 322	94.10 52	95.59 136	96.64 150	81.88 267	97.50 272	85.12 261	98.52 171	97.77 188

bld_raw_dy_0_64		90.86 212	90.99 214	90.47 274	93.95 301	77.88 303	93.99 144	98.93 7	77.75 330	97.03 66	90.61 344	81.82 268	98.58 176	85.18 255	99.61 26	94.95 317

SixPastTwentyTwo		94.91 96	95.21 90	93.98 143	98.52 49	83.19 218	95.93 67	94.84 257	94.86 41	98.49 15	98.74 16	81.45 269	99.60 9	94.69 32	99.39 58	99.15 39

cascas		87.02 310	86.28 312	89.25 304	91.56 357	76.45 325	84.33 379	96.78 176	71.01 373	86.89 353	85.91 383	81.35 270	96.94 302	83.09 280	95.60 302	94.35 337

GBi-Net		93.21 158	92.96 164	93.97 144	95.40 258	84.29 199	95.99 63	96.56 191	88.63 184	95.10 165	98.53 26	81.31 271	98.98 106	86.74 233	98.38 183	98.65 106

test1		93.21 158	92.96 164	93.97 144	95.40 258	84.29 199	95.99 63	96.56 191	88.63 184	95.10 165	98.53 26	81.31 271	98.98 106	86.74 233	98.38 183	98.65 106

FMVSNet2		92.78 172	92.73 173	92.95 184	95.40 258	81.98 233	94.18 135	95.53 237	88.63 184	96.05 113	97.37 90	81.31 271	98.81 135	87.38 226	98.67 157	98.06 151

MVE	59.87 23	73.86 372	72.65 375	77.47 384	87.00 399	74.35 343	61.37 402	60.93 410	67.27 388	69.69 405	86.49 380	81.24 274	72.33 406	56.45 403	83.45 397	85.74 395
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	94.48 267	93.12 73	97.94 27	98.54 25	81.19 275	99.63 6	95.48 23	99.69 14	99.60 12

MVP-Stereo		90.07 242	88.92 255	93.54 165	96.31 197	86.49 158	90.93 248	95.59 233	79.80 308	91.48 276	95.59 208	80.79 276	97.39 281	78.57 329	91.19 378	96.76 248
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UnsupCasMVSNet_bld		88.50 278	88.03 280	89.90 291	95.52 255	78.88 288	87.39 333	94.02 278	79.32 319	93.06 233	94.02 269	80.72 277	94.27 364	75.16 353	93.08 362	96.54 252

MS-PatchMatch		88.05 285	87.75 283	88.95 307	93.28 312	77.93 300	87.88 325	92.49 308	75.42 345	92.57 251	93.59 284	80.44 278	94.24 366	81.28 300	92.75 365	94.69 331

Anonymous20240521		92.86 170	93.57 152	90.74 267	96.57 175	75.50 335	94.15 136	95.60 229	89.38 167	95.90 120	97.90 60	80.39 279	97.96 234	92.60 97	99.68 18	98.75 91

iter_conf05_11		88.91 269	88.32 266	90.66 269	93.95 301	78.09 298	86.98 339	93.06 294	79.35 318	87.64 344	89.80 348	80.25 280	98.96 111	85.18 255	98.69 153	94.95 317

CANet_DTU		89.85 247	89.17 249	91.87 222	92.20 337	80.02 261	90.79 251	95.87 222	86.02 230	82.53 385	91.77 324	80.01 281	98.57 177	85.66 252	97.70 237	97.01 236

PMMVS		83.00 340	81.11 349	88.66 314	83.81 408	86.44 161	82.24 388	85.65 367	61.75 400	82.07 387	85.64 386	79.75 282	91.59 381	75.99 349	93.09 361	87.94 391

ppachtmachnet_test		88.61 277	88.64 260	88.50 318	91.76 350	70.99 366	84.59 376	92.98 295	79.30 320	92.38 259	93.53 286	79.57 283	97.45 276	86.50 242	97.17 260	97.07 231

eth_miper_zixun_eth		90.72 216	90.61 224	91.05 254	92.04 343	76.84 320	86.91 342	96.67 184	85.21 247	94.41 189	93.92 273	79.53 284	98.26 208	89.76 173	97.02 265	98.06 151

test_vis1_rt		85.58 319	84.58 322	88.60 315	87.97 391	86.76 150	85.45 368	93.59 283	66.43 390	87.64 344	89.20 360	79.33 285	85.38 401	81.59 297	89.98 385	93.66 353

N_pmnet		88.90 270	87.25 292	93.83 154	94.40 290	93.81 35	84.73 373	87.09 355	79.36 317	93.26 225	92.43 312	79.29 286	91.68 380	77.50 337	97.22 258	96.00 278

miper_enhance_ethall		88.42 279	87.87 282	90.07 287	88.67 389	75.52 334	85.10 370	95.59 233	75.68 342	92.49 252	89.45 357	78.96 287	97.88 241	87.86 218	97.02 265	96.81 245

EPNet		89.80 249	88.25 272	94.45 129	83.91 407	86.18 169	93.87 147	87.07 356	91.16 133	80.64 395	94.72 245	78.83 288	98.89 120	85.17 257	98.89 125	98.28 136
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
sss		87.23 303	86.82 301	88.46 320	93.96 299	77.94 299	86.84 344	92.78 301	77.59 331	87.61 347	91.83 323	78.75 289	91.92 379	77.84 332	94.20 339	95.52 302

IterMVS-SCA-FT		91.65 199	91.55 199	91.94 221	93.89 303	79.22 281	87.56 329	93.51 286	91.53 123	95.37 149	96.62 151	78.65 290	98.90 118	91.89 112	94.95 320	97.70 194

SCA		87.43 299	87.21 293	88.10 326	92.01 344	71.98 361	89.43 296	88.11 346	82.26 290	88.71 327	92.83 300	78.65 290	97.59 268	79.61 320	93.30 356	94.75 328

our_test_3		87.55 296	87.59 286	87.44 334	91.76 350	70.48 367	83.83 382	90.55 332	79.79 309	92.06 270	92.17 317	78.63 292	95.63 339	84.77 267	94.73 326	96.22 269

jason		89.17 258	88.32 266	91.70 230	95.73 242	80.07 257	88.10 322	93.22 291	71.98 367	90.09 301	92.79 302	78.53 293	98.56 178	87.43 224	97.06 263	96.46 259
jason: jason.
IterMVS		90.18 235	90.16 233	90.21 284	93.15 315	75.98 330	87.56 329	92.97 296	86.43 222	94.09 195	96.40 162	78.32 294	97.43 277	87.87 217	94.69 328	97.23 226
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CHOSEN 1792x2688		87.19 306	85.92 315	91.00 258	97.13 145	79.41 276	84.51 377	95.60 229	64.14 396	90.07 303	94.81 240	78.26 295	97.14 294	73.34 363	95.38 310	96.46 259

WTY-MVS		86.93 311	86.50 310	88.24 323	94.96 268	74.64 338	87.19 336	92.07 316	78.29 327	88.32 334	91.59 328	78.06 296	94.27 364	74.88 354	93.15 360	95.80 288

pmmvs4		88.95 267	87.70 285	92.70 193	94.30 291	85.60 184	87.22 335	92.16 313	74.62 351	89.75 312	94.19 262	77.97 297	96.41 321	82.71 283	96.36 287	96.09 274

DSMNet-mixed		82.21 346	81.56 345	84.16 367	89.57 381	70.00 372	90.65 257	77.66 403	54.99 404	83.30 380	97.57 74	77.89 298	90.50 386	66.86 390	95.54 304	91.97 373

FA-MVS(test-final)		91.81 196	91.85 194	91.68 231	94.95 269	79.99 262	96.00 62	93.44 288	87.80 201	94.02 201	97.29 101	77.60 299	98.45 191	88.04 213	97.49 247	96.61 251

lessismore_v0				93.87 151	98.05 84	83.77 210		80.32 396		97.13 60	97.91 58	77.49 300	99.11 92	92.62 96	98.08 213	98.74 94

Syy-MVS		84.81 325	84.93 319	84.42 365	91.71 352	63.36 399	85.89 362	81.49 389	81.03 299	85.13 362	81.64 398	77.44 301	95.00 353	85.94 249	94.12 342	94.91 322

HY-MVS	82.50 18	86.81 312	85.93 314	89.47 297	93.63 308	77.93 300	94.02 141	91.58 323	75.68 342	83.64 376	93.64 280	77.40 302	97.42 278	71.70 373	92.07 373	93.05 364

1112_ss		88.42 279	87.41 288	91.45 239	96.69 166	80.99 247	89.72 288	96.72 181	73.37 358	87.00 352	90.69 341	77.38 303	98.20 212	81.38 299	93.72 349	95.15 309

DIV-MVS_self_test		90.65 219	90.56 226	90.91 262	91.85 348	76.99 316	86.75 347	95.36 244	85.52 244	94.06 198	94.89 237	77.37 304	97.99 232	90.28 156	98.97 119	97.76 189

cl____		90.65 219	90.56 226	90.91 262	91.85 348	76.98 317	86.75 347	95.36 244	85.53 242	94.06 198	94.89 237	77.36 305	97.98 233	90.27 157	98.98 114	97.76 189

CDS-MVSNet		89.55 250	88.22 275	93.53 166	95.37 261	86.49 158	89.26 302	93.59 283	79.76 310	91.15 283	92.31 314	77.12 306	98.38 196	77.51 336	97.92 227	95.71 292
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test_vis3_rt		90.40 226	90.03 237	91.52 237	92.58 326	88.95 103	90.38 266	97.72 103	73.30 359	97.79 30	97.51 83	77.05 307	87.10 397	89.03 193	94.89 321	98.50 121

MVSFormer		92.18 191	92.23 183	92.04 220	94.74 279	80.06 258	97.15 15	97.37 126	88.98 176	88.83 320	92.79 302	77.02 308	99.60 9	96.41 9	96.75 278	96.46 259

lupinMVS		88.34 281	87.31 289	91.45 239	94.74 279	80.06 258	87.23 334	92.27 310	71.10 372	88.83 320	91.15 332	77.02 308	98.53 182	86.67 236	96.75 278	95.76 290

PMMVS2		81.31 353	83.44 332	74.92 386	90.52 369	46.49 412	69.19 400	85.23 375	84.30 264	87.95 340	94.71 246	76.95 310	84.36 403	64.07 394	98.09 212	93.89 347

h-mvs33		92.89 167	91.99 190	95.58 77	96.97 149	90.55 76	93.94 146	94.01 279	89.23 170	93.95 203	96.19 180	76.88 311	99.14 86	91.02 133	95.71 300	97.04 235

hse-mvs2		92.24 190	91.20 209	95.38 83	96.16 210	90.65 75	92.52 191	92.01 318	89.23 170	93.95 203	92.99 297	76.88 311	98.69 160	91.02 133	96.03 292	96.81 245

pmmvs5		87.87 287	87.14 295	90.07 287	93.26 314	76.97 318	88.89 309	92.18 311	73.71 357	88.36 333	93.89 275	76.86 313	96.73 312	80.32 307	96.81 275	96.51 254

test_vis1_n_1920		89.45 253	89.85 241	88.28 322	93.59 309	76.71 322	90.67 256	97.78 99	79.67 312	90.30 299	96.11 184	76.62 314	92.17 378	90.31 154	93.57 351	95.96 280

K. test v3		93.37 151	93.27 161	93.66 159	98.05 84	82.62 226	94.35 127	86.62 358	96.05 29	97.51 43	98.85 12	76.59 315	99.65 3	93.21 78	98.20 204	98.73 95

miper_lstm_enhance		89.90 246	89.80 242	90.19 286	91.37 359	77.50 308	83.82 383	95.00 252	84.84 257	93.05 234	94.96 235	76.53 316	95.20 352	89.96 169	98.67 157	97.86 177

dmvs_testset		78.23 370	78.99 365	75.94 385	91.99 345	55.34 408	88.86 310	78.70 400	82.69 283	81.64 392	79.46 400	75.93 317	85.74 400	48.78 406	82.85 399	86.76 393

Test_1112_low_res		87.50 298	86.58 305	90.25 282	96.80 163	77.75 305	87.53 331	96.25 205	69.73 382	86.47 354	93.61 283	75.67 318	97.88 241	79.95 314	93.20 358	95.11 313

test_fmvs2		90.62 221	90.40 230	91.29 246	91.93 347	85.46 187	92.70 184	96.48 197	74.44 352	94.91 175	97.59 73	75.52 319	90.57 384	93.44 67	96.56 282	97.84 180

Vis-MVSNet (Re-imp)		90.42 225	90.16 233	91.20 251	97.66 117	77.32 311	94.33 129	87.66 351	91.20 131	92.99 236	95.13 228	75.40 320	98.28 204	77.86 331	99.19 92	97.99 162

test_vis1_n		89.01 264	89.01 253	89.03 306	92.57 327	82.46 229	92.62 188	96.06 214	73.02 362	90.40 296	95.77 202	74.86 321	89.68 390	90.78 140	94.98 319	94.95 317

D2MVS		89.93 245	89.60 247	90.92 260	94.03 298	78.40 294	88.69 316	94.85 256	78.96 323	93.08 232	95.09 230	74.57 322	96.94 302	88.19 207	98.96 121	97.41 213

PVSNet	76.22 20	82.89 342	82.37 341	84.48 364	93.96 299	64.38 396	78.60 395	88.61 338	71.50 369	84.43 370	86.36 381	74.27 323	94.60 358	69.87 383	93.69 350	94.46 334

test_yl		90.11 239	89.73 245	91.26 247	94.09 296	79.82 266	90.44 262	92.65 303	90.90 135	93.19 230	93.30 290	73.90 324	98.03 225	82.23 290	96.87 272	95.93 282

DCV-MVSNet		90.11 239	89.73 245	91.26 247	94.09 296	79.82 266	90.44 262	92.65 303	90.90 135	93.19 230	93.30 290	73.90 324	98.03 225	82.23 290	96.87 272	95.93 282

CMPMVS	68.83 22	87.28 302	85.67 316	92.09 218	88.77 388	85.42 188	90.31 269	94.38 269	70.02 380	88.00 338	93.30 290	73.78 326	94.03 367	75.96 350	96.54 283	96.83 244
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
baseline1		87.62 294	87.31 289	88.54 316	94.71 282	74.27 345	93.10 172	88.20 343	86.20 226	92.18 267	93.04 295	73.21 327	95.52 341	79.32 323	85.82 393	95.83 287

PVSNet_0	70.34 21	74.58 371	72.96 374	79.47 382	90.63 367	66.24 386	73.26 396	83.40 384	63.67 398	78.02 399	78.35 402	72.53 328	89.59 391	56.68 401	60.05 406	82.57 400

dmvs_re		84.69 327	83.94 329	86.95 339	92.24 334	82.93 223	89.51 293	87.37 353	84.38 263	85.37 359	85.08 389	72.44 329	86.59 398	68.05 386	91.03 381	91.33 378

MIMVSNet		87.13 308	86.54 307	88.89 309	96.05 220	76.11 328	94.39 126	88.51 339	81.37 297	88.27 335	96.75 142	72.38 330	95.52 341	65.71 392	95.47 306	95.03 314

PAPM		81.91 351	80.11 361	87.31 335	93.87 304	72.32 360	84.02 381	93.22 291	69.47 383	76.13 402	89.84 347	72.15 331	97.23 286	53.27 404	89.02 386	92.37 371

cl22		89.02 262	88.50 262	90.59 272	89.76 377	76.45 325	86.62 352	94.03 276	82.98 280	92.65 247	92.49 308	72.05 332	97.53 270	88.93 194	97.02 265	97.78 187

LFMVS		91.33 207	91.16 212	91.82 224	96.27 201	79.36 277	95.01 105	85.61 369	96.04 30	94.82 178	97.06 120	72.03 333	98.46 190	84.96 265	98.70 152	97.65 198

test_cas_vis1_n_1920		88.25 282	88.27 271	88.20 324	92.19 338	78.92 286	89.45 295	95.44 239	75.29 349	93.23 228	95.65 207	71.58 334	90.23 388	88.05 212	93.55 353	95.44 303

MVS-HIRNet		78.83 369	80.60 356	73.51 387	93.07 316	47.37 411	87.10 338	78.00 402	68.94 384	77.53 400	97.26 102	71.45 335	94.62 357	63.28 396	88.74 387	78.55 402

EPNet_dtu		85.63 318	84.37 324	89.40 300	86.30 400	74.33 344	91.64 233	88.26 341	84.84 257	72.96 404	89.85 346	71.27 336	97.69 263	76.60 343	97.62 242	96.18 271
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test1111		90.39 228	90.61 224	89.74 294	98.04 87	71.50 363	95.59 80	79.72 398	89.41 166	95.94 117	98.14 39	70.79 337	98.81 135	88.52 204	99.32 68	98.90 74

ECVR-MVS		90.12 238	90.16 233	90.00 290	97.81 102	72.68 357	95.76 74	78.54 401	89.04 174	95.36 150	98.10 42	70.51 338	98.64 168	87.10 229	99.18 94	98.67 104

HyFIR lowres test		87.19 306	85.51 317	92.24 210	97.12 146	80.51 251	85.03 371	96.06 214	66.11 392	91.66 275	92.98 298	70.12 339	99.14 86	75.29 352	95.23 314	97.07 231

FMVSNet3		90.78 215	90.32 232	92.16 216	93.03 319	79.92 264	92.54 190	94.95 254	86.17 228	95.10 165	96.01 189	69.97 340	98.75 146	86.74 233	98.38 183	97.82 183

test_f		86.65 313	87.13 296	85.19 358	90.28 373	86.11 171	86.52 355	91.66 321	69.76 381	95.73 131	97.21 109	69.51 341	81.28 404	89.15 190	94.40 332	88.17 390

RPMNet		90.31 234	90.14 236	90.81 266	91.01 363	78.93 284	92.52 191	98.12 54	91.91 101	89.10 317	96.89 132	68.84 342	99.41 39	90.17 162	92.70 366	94.08 340

test_fmvs1_n		88.73 275	88.38 265	89.76 293	92.06 342	82.53 227	92.30 207	96.59 189	71.14 371	92.58 250	95.41 220	68.55 343	89.57 392	91.12 131	95.66 301	97.18 229

test_fmvs1		87.59 295	87.27 291	88.54 316	88.32 390	81.26 243	90.43 265	95.72 226	70.55 377	91.70 274	94.63 248	68.13 344	89.42 393	90.59 144	95.34 311	94.94 321

ADS-MVSNet2		84.01 332	82.20 343	89.41 299	89.04 385	76.37 327	87.57 327	90.98 327	72.71 365	84.46 368	92.45 309	68.08 345	96.48 318	70.58 381	83.97 395	95.38 304

ADS-MVSNet		82.25 345	81.55 346	84.34 366	89.04 385	65.30 390	87.57 327	85.13 376	72.71 365	84.46 368	92.45 309	68.08 345	92.33 377	70.58 381	83.97 395	95.38 304

CVMVSNet		85.16 322	84.72 320	86.48 345	92.12 340	70.19 368	92.32 204	88.17 344	56.15 403	90.64 292	95.85 194	67.97 347	96.69 313	88.78 199	90.52 382	92.56 369

new_pmnet		81.22 354	81.01 352	81.86 376	90.92 365	70.15 369	84.03 380	80.25 397	70.83 374	85.97 357	89.78 352	67.93 348	84.65 402	67.44 388	91.90 375	90.78 382

CR-MVSNet		87.89 286	87.12 297	90.22 283	91.01 363	78.93 284	92.52 191	92.81 298	73.08 361	89.10 317	96.93 129	67.11 349	97.64 267	88.80 198	92.70 366	94.08 340

Patchmtry		90.11 239	89.92 239	90.66 269	90.35 372	77.00 315	92.96 175	92.81 298	90.25 153	94.74 182	96.93 129	67.11 349	97.52 271	85.17 257	98.98 114	97.46 209

PatchmatchNet		85.22 321	84.64 321	86.98 338	89.51 382	69.83 373	90.52 260	87.34 354	78.87 324	87.22 351	92.74 304	66.91 351	96.53 315	81.77 294	86.88 391	94.58 332
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
GA-MVS		87.70 290	86.82 301	90.31 279	93.27 313	77.22 313	84.72 375	92.79 300	85.11 251	89.82 308	90.07 345	66.80 352	97.76 257	84.56 270	94.27 337	95.96 280

MDTV_nov1_ep13_2view						42.48 413	88.45 320		67.22 389	83.56 377		66.80 352		72.86 367		94.06 342

tpmrst		82.85 343	82.93 337	82.64 374	87.65 392	58.99 405	90.14 274	87.90 349	75.54 344	83.93 374	91.63 327	66.79 354	95.36 347	81.21 302	81.54 401	93.57 358

sam_mvs1												66.64 355				94.75 328

sam_mvs												66.41 356

Patchmatch-RL test		88.81 272	88.52 261	89.69 296	95.33 263	79.94 263	86.22 359	92.71 302	78.46 326	95.80 124	94.18 263	66.25 357	95.33 349	89.22 188	98.53 170	93.78 349

patchmatchnet-post											91.71 325	66.22 358	97.59 268

AUN-MVS		90.05 243	88.30 268	95.32 88	96.09 217	90.52 77	92.42 199	92.05 317	82.08 292	88.45 332	92.86 299	65.76 359	98.69 160	88.91 196	96.07 291	96.75 249

test_post											6.07 409	65.74 360	95.84 337

test_post1							90.21 271				5.85 410	65.36 361	96.00 333	79.61 320

MDTV_nov1_ep13			83.88 331		89.42 383	61.52 400	88.74 315	87.41 352	73.99 355	84.96 366	94.01 270	65.25 362	95.53 340	78.02 330	93.16 359

Patchmatch-test		86.10 316	86.01 313	86.38 349	90.63 367	74.22 346	89.57 291	86.69 357	85.73 236	89.81 309	92.83 300	65.24 363	91.04 383	77.82 334	95.78 299	93.88 348

tpmvs		84.22 330	83.97 328	84.94 360	87.09 397	65.18 391	91.21 242	88.35 340	82.87 281	85.21 360	90.96 336	65.24 363	96.75 311	79.60 322	85.25 394	92.90 366

EU-MVSNet		87.39 300	86.71 304	89.44 298	93.40 311	76.11 328	94.93 108	90.00 334	57.17 402	95.71 132	97.37 90	64.77 365	97.68 264	92.67 95	94.37 334	94.52 333

thres200		85.85 317	85.18 318	87.88 330	94.44 288	72.52 358	89.08 306	86.21 360	88.57 187	91.44 277	88.40 367	64.22 366	98.00 230	68.35 385	95.88 298	93.12 361

PatchT		87.51 297	88.17 277	85.55 354	90.64 366	66.91 381	92.02 216	86.09 362	92.20 93	89.05 319	97.16 111	64.15 367	96.37 324	89.21 189	92.98 364	93.37 359

tfpn200view9		87.05 309	86.52 308	88.67 313	95.77 239	72.94 354	91.89 223	86.00 363	90.84 137	92.61 248	89.80 348	63.93 368	98.28 204	71.27 376	96.54 283	94.79 326

thres400		87.20 305	86.52 308	89.24 305	95.77 239	72.94 354	91.89 223	86.00 363	90.84 137	92.61 248	89.80 348	63.93 368	98.28 204	71.27 376	96.54 283	96.51 254

FPMVS		84.50 328	83.28 333	88.16 325	96.32 196	94.49 16	85.76 365	85.47 370	83.09 277	85.20 361	94.26 259	63.79 370	86.58 399	63.72 395	91.88 376	83.40 397

thres100view900		87.35 301	86.89 300	88.72 312	96.14 213	73.09 353	93.00 174	85.31 372	92.13 95	93.26 225	90.96 336	63.42 371	98.28 204	71.27 376	96.54 283	94.79 326

thres600view7		87.66 292	87.10 298	89.36 301	96.05 220	73.17 351	92.72 182	85.31 372	91.89 102	93.29 222	90.97 335	63.42 371	98.39 193	73.23 364	96.99 270	96.51 254

EMVS		80.35 362	80.28 360	80.54 380	84.73 406	69.07 374	72.54 399	80.73 394	87.80 201	81.66 391	81.73 397	62.89 373	89.84 389	75.79 351	94.65 329	82.71 399

test-LLR		83.58 335	83.17 334	84.79 362	89.68 379	66.86 382	83.08 384	84.52 378	83.07 278	82.85 382	84.78 390	62.86 374	93.49 370	82.85 281	94.86 322	94.03 343

test0.0.03 1		82.48 344	81.47 348	85.48 355	89.70 378	73.57 350	84.73 373	81.64 388	83.07 278	88.13 337	86.61 378	62.86 374	89.10 395	66.24 391	90.29 383	93.77 350

tpm cat1		80.61 360	79.46 363	84.07 368	88.78 387	65.06 394	89.26 302	88.23 342	62.27 399	81.90 390	89.66 355	62.70 376	95.29 350	71.72 372	80.60 402	91.86 376

E-PMN		80.72 359	80.86 353	80.29 381	85.11 404	68.77 375	72.96 397	81.97 387	87.76 203	83.25 381	83.01 396	62.22 377	89.17 394	77.15 340	94.31 336	82.93 398

baseline2		83.38 337	81.54 347	88.90 308	91.38 358	72.84 356	88.78 313	81.22 391	78.97 322	79.82 397	87.56 372	61.73 378	97.80 250	74.30 358	90.05 384	96.05 277

CostFormer		83.09 339	82.21 342	85.73 352	89.27 384	67.01 380	90.35 267	86.47 359	70.42 378	83.52 378	93.23 293	61.18 379	96.85 308	77.21 339	88.26 389	93.34 360

MVSTER		89.32 256	88.75 259	91.03 255	90.10 375	76.62 323	90.85 249	94.67 265	82.27 289	95.24 159	95.79 198	61.09 380	98.49 185	90.49 146	98.26 195	97.97 166

tpm		84.38 329	84.08 327	85.30 357	90.47 370	63.43 398	89.34 299	85.63 368	77.24 335	87.62 346	95.03 233	61.00 381	97.30 284	79.26 324	91.09 380	95.16 308

FE-MVS		89.06 261	88.29 269	91.36 242	94.78 276	79.57 273	96.77 28	90.99 326	84.87 256	92.96 238	96.29 173	60.69 382	98.80 138	80.18 311	97.11 262	95.71 292

EPMVS		81.17 356	80.37 358	83.58 371	85.58 403	65.08 393	90.31 269	71.34 407	77.31 334	85.80 358	91.30 330	59.38 383	92.70 376	79.99 313	82.34 400	92.96 365

tmp_tt		37.97 374	44.33 377	18.88 390	11.80 413	21.54 414	63.51 401	45.66 414	4.23 407	51.34 407	50.48 405	59.08 384	22.11 409	44.50 407	68.35 405	13.00 405

tpm2		81.46 352	80.35 359	84.80 361	89.90 376	65.14 392	90.44 262	85.36 371	65.82 394	82.05 388	92.44 311	57.94 385	96.69 313	70.71 380	88.49 388	92.56 369

ET-MVSNet_ETH3D		86.15 315	84.27 326	91.79 225	93.04 318	81.28 242	87.17 337	86.14 361	79.57 313	83.65 375	88.66 363	57.10 386	98.18 215	87.74 219	95.40 308	95.90 285

CHOSEN 280x420		80.04 364	77.97 371	86.23 351	90.13 374	74.53 341	72.87 398	89.59 335	66.38 391	76.29 401	85.32 388	56.96 387	95.36 347	69.49 384	94.72 327	88.79 388

JIA-IIPM		85.08 323	83.04 335	91.19 252	87.56 393	86.14 170	89.40 298	84.44 380	88.98 176	82.20 386	97.95 53	56.82 388	96.15 328	76.55 345	83.45 397	91.30 379

DeepMVS_CX				53.83 389	70.38 411	64.56 395		48.52 413	33.01 405	65.50 406	74.21 404	56.19 389	46.64 408	38.45 408	70.07 404	50.30 404

dp		79.28 367	78.62 367	81.24 379	85.97 402	56.45 406	86.91 342	85.26 374	72.97 363	81.45 393	89.17 362	56.01 390	95.45 345	73.19 365	76.68 403	91.82 377

test_method		50.44 373	48.94 376	54.93 388	39.68 412	12.38 415	28.59 403	90.09 333	6.82 406	41.10 408	78.41 401	54.41 391	70.69 407	50.12 405	51.26 407	81.72 401

thisisatest0515		84.72 326	82.99 336	89.90 291	92.96 321	75.33 336	84.36 378	83.42 383	77.37 333	88.27 335	86.65 377	53.94 392	98.72 151	82.56 285	97.40 253	95.67 295

tttt0517		89.81 248	88.90 257	92.55 203	97.00 148	79.73 270	95.03 104	83.65 382	89.88 158	95.30 153	94.79 243	53.64 393	99.39 49	91.99 108	98.79 142	98.54 119

thisisatest0530		88.69 276	87.52 287	92.20 211	96.33 195	79.36 277	92.81 179	84.01 381	86.44 221	93.67 211	92.68 306	53.62 394	99.25 75	89.65 176	98.45 177	98.00 159

FMVSNet5		87.82 289	86.56 306	91.62 233	92.31 332	79.81 268	93.49 159	94.81 260	83.26 272	91.36 278	96.93 129	52.77 395	97.49 274	76.07 348	98.03 217	97.55 205

pmmvs3		80.83 358	78.96 366	86.45 346	87.23 396	77.48 309	84.87 372	82.31 386	63.83 397	85.03 364	89.50 356	49.66 396	93.10 373	73.12 366	95.10 316	88.78 389

iter_conf05		88.94 268	88.09 279	91.50 238	92.74 324	76.97 318	92.80 180	95.92 220	82.82 282	93.65 212	95.37 223	49.41 397	99.13 88	90.82 138	99.28 79	98.40 129

IB-MVS	77.21 19	83.11 338	81.05 350	89.29 302	91.15 361	75.85 331	85.66 366	86.00 363	79.70 311	82.02 389	86.61 378	48.26 398	98.39 193	77.84 332	92.22 371	93.63 354
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
testing91		83.56 336	82.45 340	86.91 340	92.92 322	67.29 378	86.33 357	88.07 347	86.22 225	84.26 371	85.76 384	48.15 399	97.17 291	76.27 347	94.08 345	96.27 267

testing99		82.94 341	81.72 344	86.59 343	92.55 328	66.53 384	86.08 361	85.70 366	85.47 245	83.95 373	85.70 385	45.87 400	97.07 297	76.58 344	93.56 352	96.17 273

testing11		81.98 350	80.52 357	86.38 349	92.69 325	67.13 379	85.79 364	84.80 377	82.16 291	81.19 394	85.41 387	45.24 401	96.88 307	74.14 359	93.24 357	95.14 310

gg-mvs-nofinetune		82.10 349	81.02 351	85.34 356	87.46 395	71.04 364	94.74 112	67.56 408	96.44 23	79.43 398	98.99 6	45.24 401	96.15 328	67.18 389	92.17 372	88.85 387

GG-mvs-BLEND				83.24 373	85.06 405	71.03 365	94.99 107	65.55 409		74.09 403	75.51 403	44.57 403	94.46 360	59.57 400	87.54 390	84.24 396

TESTMET0.1,1		79.09 368	78.04 370	82.25 375	87.52 394	64.03 397	83.08 384	80.62 395	70.28 379	80.16 396	83.22 395	44.13 404	90.56 385	79.95 314	93.36 354	92.15 372

UWE-MVS		80.29 363	79.10 364	83.87 369	91.97 346	59.56 403	86.50 356	77.43 404	75.40 346	87.79 343	88.10 369	44.08 405	96.90 306	64.23 393	96.36 287	95.14 310

test-mter		81.21 355	80.01 362	84.79 362	89.68 379	66.86 382	83.08 384	84.52 378	73.85 356	82.85 382	84.78 390	43.66 406	93.49 370	82.85 281	94.86 322	94.03 343

KD-MVS_2432*1600		82.17 347	80.75 354	86.42 347	82.04 409	70.09 370	81.75 389	90.80 329	82.56 284	90.37 297	89.30 358	42.90 407	96.11 330	74.47 356	92.55 368	93.06 362

miper_refine_blended		82.17 347	80.75 354	86.42 347	82.04 409	70.09 370	81.75 389	90.80 329	82.56 284	90.37 297	89.30 358	42.90 407	96.11 330	74.47 356	92.55 368	93.06 362

test2506		85.42 320	84.57 323	87.96 327	97.81 102	66.53 384	96.14 58	56.35 411	89.04 174	93.55 215	98.10 42	42.88 409	98.68 162	88.09 211	99.18 94	98.67 104

ETVMVS		79.85 365	77.94 372	85.59 353	92.97 320	66.20 387	86.13 360	80.99 393	81.41 296	83.52 378	83.89 393	41.81 410	94.98 356	56.47 402	94.25 338	95.61 300

testing222		80.54 361	78.53 368	86.58 344	92.54 330	68.60 376	86.24 358	82.72 385	83.78 269	82.68 384	84.24 392	39.25 411	95.94 335	60.25 398	95.09 317	95.20 306

myMVS_eth3d		79.62 366	78.26 369	83.72 370	91.71 352	61.25 401	85.89 362	81.49 389	81.03 299	85.13 362	81.64 398	32.12 412	95.00 353	71.17 379	94.12 342	94.91 322

testing3		83.66 334	82.52 339	87.08 336	95.84 234	65.84 389	89.80 286	77.17 405	88.17 194	90.84 288	88.63 364	30.95 413	98.11 220	84.05 273	97.19 259	97.28 224

test123		9.49 376	12.01 379	1.91 391	2.87 414	1.30 416	82.38 387	1.34 416	1.36 409	2.84 410	6.56 408	2.45 414	0.97 410	2.73 409	5.56 408	3.47 406

testmvs		9.02 377	11.42 380	1.81 392	2.77 415	1.13 417	79.44 394	1.90 415	1.18 410	2.65 411	6.80 407	1.95 415	0.87 411	2.62 410	3.45 409	3.44 407

test_blank		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet_test		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

DCPMVS		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

sosnet-low-res		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

sosnet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uncertanet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

Regformer		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

ab-mvs-re		7.56 378	10.08 382	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	90.69 341	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

WAC-MVS						61.25 401								74.55 355

FOURS1					99.21 3	94.68 12	98.45 4	98.81 9	97.73 6	98.27 20

MSC_two_6792asdad				95.90 65	96.54 178	89.57 88		96.87 170					99.41 39	94.06 44	99.30 71	98.72 96

No_MVS				95.90 65	96.54 178	89.57 88		96.87 170					99.41 39	94.06 44	99.30 71	98.72 96

eth-test2					0.00 416

eth-test					0.00 416

IU-MVS					98.51 50	86.66 155		96.83 173	72.74 364	95.83 123				93.00 86	99.29 74	98.64 111

save fliter					97.46 129	88.05 124	92.04 215	97.08 153	87.63 207

test_0728_SECOND				94.88 104	98.55 45	86.72 152	95.20 97	98.22 39					99.38 55	93.44 67	99.31 69	98.53 120

GSMVS																94.75 328

test_part2					98.21 74	89.41 93				96.72 81

MTGPA								97.62 108

MTMP							94.82 110	54.62 412

gm-plane-assit					87.08 398	59.33 404			71.22 370		83.58 394		97.20 288	73.95 360

test9_res														88.16 209	98.40 179	97.83 181

agg_prior2														87.06 231	98.36 188	97.98 163

agg_prior					96.20 207	88.89 106		96.88 169		90.21 300			98.78 142

test_prior4						89.91 82	90.74 253

test_prior				94.61 117	95.95 228	87.23 137		97.36 131					98.68 162			97.93 169

旧先验2							90.00 279		68.65 385	92.71 246			96.52 316	85.15 259

新几何2							90.02 278

无先验							89.94 280	95.75 225	70.81 375				98.59 174	81.17 303		94.81 324

原ACMM2							89.34 299

testdata2													98.03 225	80.24 310

testdata1							88.96 308		88.44 189

plane_prior7					97.71 111	88.68 109

plane_prior5								97.81 94					98.95 114	89.26 186	98.51 173	98.60 116

plane_prior4											95.59 208

plane_prior3						88.43 119			90.35 152	93.31 220

plane_prior2							94.56 121		91.74 115

plane_prior1					97.38 131

plane_prior						88.12 122	93.01 173		88.98 176						98.06 214

n2								0.00 417

nn								0.00 417

door-mid								92.13 315

test11								96.65 185

door								91.26 324

HQP5-MVS						84.89 193

HQP-NCC					96.36 190		91.37 237		87.16 213	88.81 322

ACMP_Plane					96.36 190		91.37 237		87.16 213	88.81 322

BP-MVS														86.55 240

HQP4-MVS										88.81 322			98.61 170			98.15 146

HQP3-MVS								97.31 135							97.73 234

NP-MVS					96.82 161	87.10 141					93.40 288

ACMMP++_ref															98.82 138

ACMMP++															99.25 83

High-resolution multi-view benchmark