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	92.46 193	98.13 51	90.69 140	93.75 206	96.25 178	98.03 2	97.02 297	92.08 105	95.55 301	98.45 126

pmmvs6		96.80 12	97.36 9	95.15 97	99.12 8	87.82 129	96.68 30	97.86 86	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	97.54 113	98.16 2	98.94 2	99.33 2	97.84 4	99.08 93	90.73 139	99.73 13	99.59 13

ACMH	88.36 12	96.59 27	97.43 5	94.07 140	98.56 42	85.33 187	96.33 47	98.30 28	94.66 42	98.72 8	98.30 35	97.51 5	98.00 228	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 46	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	98.62 168	90.30 153	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	97.61 108	87.57 206	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	86.97 144	95.21 93	98.10 55	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	86.97 144		98.10 55	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 89	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	94.74 110	98.03 70	90.82 137	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		87.83 286	90.79 218	78.96 381	90.46 369	88.63 110	92.72 180	90.67 329	91.65 119	98.68 11	97.64 70	96.06 15	77.53 403	59.84 397	99.41 56	70.73 401

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	97.90 235	89.32 178	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	97.90 235	89.32 178	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	94.24 130	98.08 58	89.46 163	96.61 87	96.47 157	95.85 18	99.12 90	90.45 145	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	94.24 130	98.76 11	86.25 222	97.56 39	98.66 18	95.73 19	98.44 190	97.35 2	98.99 113	98.27 137

TransMVSNet (Re)		95.27 87	96.04 52	92.97 180	98.37 64	81.92 232	95.07 100	96.76 177	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 49	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	94.57 118	98.03 70	90.42 148	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	86.69 152	95.20 95	97.00 156	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	86.69 152	95.34 88	98.18 42	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	93.25 164	98.32 25	87.89 197	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	90.11 162	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	93.55 161	96.62 173	88.88 107	94.67 112	98.05 65	91.26 126	97.25 58	96.40 162	95.42 28	94.36 361	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 52	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 55	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 76	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	97.42 122	86.96 215	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	93.51 156	98.60 14	85.68 235	97.42 50	98.30 35	95.34 33	98.39 191	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	93.75 149	97.86 86	95.96 32	97.48 46	97.14 113	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	93.91 148	98.97 17	97.16 2	95.54 84	95.85 221	96.47 22	93.40 217	97.46 86	95.31 35	95.47 342	86.18 245	98.78 143	89.11 384
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
pm-mvs1		95.43 73	95.94 55	93.93 147	98.38 62	85.08 190	95.46 86	97.12 149	91.84 107	97.28 56	98.46 30	95.30 36	97.71 260	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 89	98.30 28	91.40 124	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	84.09 204	96.61 32	97.97 78	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	93.23 166	98.36 22	85.61 238	96.92 73	98.02 49	95.23 39	98.38 194	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 73	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	98.61 169	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	93.46 158	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 42	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 42	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 61	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	92.65 185	97.33 132	90.05 153	96.77 80	96.85 134	95.04 48	98.56 177	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	84.68 193	96.51 35	97.94 84	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 79	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	84.50 194	96.54 34	98.05 65	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 73	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.
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	92.04 319	94.95 53	98.66 164	91.45 125	97.57 243	97.20 226

ACMMPR		96.46 31	96.14 45	97.41 20	98.60 39	93.82 33	96.30 54	97.96 79	92.35 88	95.57 137	96.61 152	94.93 54	99.41 39	93.78 51	99.15 98	99.00 54

tt0805		95.42 76	95.93 57	93.86 151	98.75 32	88.47 117	97.68 9	94.29 269	96.48 21	95.38 147	93.63 281	94.89 55	97.94 234	95.38 27	96.92 269	95.17 305

SR-MVS-dyc-post		96.84 7	96.60 24	97.56 10	98.07 82	95.27 9	96.37 44	98.12 52	95.66 33	97.00 68	97.03 122	94.85 56	99.42 33	93.49 61	98.84 132	98.00 159

casdiffmvs_mvg		95.10 90	95.62 71	93.53 164	96.25 204	83.23 214	92.66 184	98.19 40	93.06 75	97.49 44	97.15 112	94.78 57	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 58	92.67 81	95.08 167	96.39 166	94.77 58	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 59	99.34 63	93.88 47	99.42 52	98.89 75

9.14			94.81 104		97.49 126		94.11 137	98.37 21	87.56 207	95.38 147	96.03 188	94.66 60	99.08 93	90.70 140	98.97 119

GeoE		94.55 110	94.68 113	94.15 136	97.23 138	85.11 189	94.14 136	97.34 131	88.71 181	95.26 156	95.50 213	94.65 61	99.12 90	90.94 134	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 62	98.84 128	94.64 33	99.53 39	98.99 56

SDMVSNet		94.43 114	95.02 98	92.69 192	97.93 95	82.88 222	91.92 220	95.99 217	93.65 65	95.51 139	98.63 20	94.60 63	96.48 316	87.57 219	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 81	94.58 43	94.38 189	96.49 156	94.56 64	99.39 49	93.57 57	99.05 106	98.93 68

X-MVStestdata		90.70 215	88.45 261	97.44 16	98.56 42	93.99 26	96.50 36	97.95 81	94.58 43	94.38 189	26.89 404	94.56 64	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 99	92.59 82	95.47 142	96.68 148	94.50 66	99.42 33	93.10 82	99.26 82	98.99 56

sd_testset		93.94 135	94.39 119	92.61 198	97.93 95	83.24 213	93.17 168	95.04 249	93.65 65	95.51 139	98.63 20	94.49 67	95.89 334	81.72 294	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	93.86 146	98.02 72	87.35 208	96.22 105	97.99 52	94.48 68	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 98	97.79 96	86.48 218	97.42 50	97.51 83	94.47 69	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 82	98.56 15	91.84 107	96.36 94	96.68 148	94.37 70	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 97	92.73 78	93.48 214	96.72 146	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 90	94.03 25	96.97 20	97.61 108	87.68 204	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	94.26 134	98.19 75	85.77 178	93.24 165	97.24 140	96.88 16	97.69 33	97.77 64	94.12 73	99.13 88	91.54 124	99.29 74	97.88 175

test_fmvsmvis_n_1920		95.08 91	95.40 81	94.13 138	96.66 168	87.75 130	93.44 160	98.49 16	85.57 239	98.27 20	97.11 116	94.11 74	97.75 256	96.26 11	98.72 148	96.89 239

Effi-MVS+		92.79 169	92.74 169	92.94 183	95.10 264	83.30 212	94.00 140	97.53 115	91.36 125	89.35 314	90.65 341	94.01 75	98.66 164	87.40 223	95.30 310	96.88 241

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	92.77 242	94.52 253	93.95 76	99.49 24	93.62 56	99.22 89	97.51 207

OMC-MVS		94.22 125	93.69 143	95.81 69	97.25 137	91.27 64	92.27 206	97.40 123	87.10 214	94.56 184	95.42 217	93.74 77	98.11 218	86.62 235	98.85 131	98.06 151

LCM-MVSNet-Re		94.20 126	94.58 116	93.04 177	95.91 231	83.13 218	93.79 148	99.19 3	92.00 97	98.84 5	98.04 47	93.64 78	99.02 103	81.28 298	98.54 169	96.96 236

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	92.48 251	94.79 243	93.56 79	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	97.62 106	94.46 47	96.29 99	96.94 128	93.56 79	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	91.03 284	93.73 279	93.52 81	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 40	96.95 14	95.46 144	99.23 4	93.45 82	99.57 14	95.34 29	99.89 2	99.63 9

MVS_111021_HR		93.63 143	93.42 155	94.26 134	96.65 169	86.96 146	89.30 299	96.23 205	88.36 189	93.57 212	94.60 250	93.45 82	97.77 253	90.23 158	98.38 183	98.03 157

cdsmvs_eth3d_5k		23.35 373	31.13 376	0.00 391	0.00 414	0.00 416	0.00 402	95.58 233	0.00 409	0.00 410	91.15 330	93.43 84	0.00 410	0.00 409	0.00 408	0.00 406

APD-MVS		95.00 93	94.69 111	95.93 62	97.38 131	90.88 71	94.59 115	97.81 92	89.22 170	95.46 144	96.17 183	93.42 85	99.34 63	89.30 180	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	90.47 272	96.65 169	73.16 350	94.33 127	98.74 12	96.39 24	98.09 25	98.93 8	93.37 86	98.70 158	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 79	97.64 104	93.38 69	95.89 121	97.23 105	93.35 87	97.66 263	88.20 204	98.66 159	97.79 186

casdiffmvs		94.32 120	94.80 105	92.85 187	96.05 220	81.44 239	92.35 200	98.05 65	91.53 122	95.75 128	96.80 137	93.35 87	98.49 183	91.01 133	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	97.37 124	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	97.76 105	83.15 217	94.58 117	97.58 110	93.39 68	97.05 65	98.04 47	93.25 90	98.51 182	89.75 172	99.59 29	99.08 48

Anonymous20240529		95.50 70	95.83 63	94.50 125	97.33 135	85.93 173	95.19 97	96.77 176	96.64 19	97.61 38	98.05 45	93.23 91	98.79 139	88.60 201	99.04 111	98.78 87

baseline		94.26 122	94.80 105	92.64 194	96.08 218	80.99 245	93.69 152	98.04 69	90.80 138	94.89 174	96.32 171	93.19 92	98.48 187	91.68 119	98.51 173	98.43 127

DeepPCF-MVS	90.46 6	94.20 126	93.56 151	96.14 52	95.96 227	92.96 43	89.48 292	97.46 119	85.14 247	96.23 104	95.42 217	93.19 92	98.08 220	90.37 149	98.76 145	97.38 219

Anonymous20231211		96.60 25	97.13 12	95.00 100	97.46 129	86.35 164	97.11 19	98.24 35	97.58 8	98.72 8	98.97 7	93.15 94	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	86.66 154	98.45 4	98.22 37	93.26 71	97.54 40	97.36 93	93.12 95	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 93				95.66 206	93.12 95	98.06 221	86.28 244	98.61 161	97.95 167

LS3D		96.11 47	95.83 63	96.95 36	94.75 276	94.20 19	97.34 13	97.98 76	97.31 11	95.32 152	96.77 138	93.08 97	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	94.54 122	97.64 104	96.94 15	96.58 88	97.32 100	93.07 98	98.72 151	90.45 145	98.84 132	97.57 202

EG-PatchMatch MVS		94.54 111	94.67 114	94.14 137	97.87 100	86.50 156	92.00 215	96.74 178	88.16 193	96.93 72	97.61 72	93.04 99	97.90 235	91.60 121	98.12 209	98.03 157

Fast-Effi-MVS+		91.28 207	90.86 215	92.53 202	95.45 255	82.53 225	89.25 302	96.52 193	85.00 251	89.91 304	88.55 364	92.94 100	98.84 128	84.72 267	95.44 305	96.22 267

PC_three_1452									75.31 346	95.87 122	95.75 203	92.93 101	96.34 325	87.18 226	98.68 155	98.04 154

v7n		96.82 9	97.31 10	95.33 86	98.54 47	86.81 148	96.83 23	98.07 61	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 60	93.04 41	94.54 122	98.05 65	90.45 147	96.31 97	96.76 140	92.91 102	98.72 151	91.19 128	99.42 52	98.32 132

testgi		90.38 227	91.34 205	87.50 331	97.49 126	71.54 360	89.43 294	95.16 246	88.38 188	94.54 185	94.68 247	92.88 104	93.09 372	71.60 372	97.85 230	97.88 175

MVS_111021_LR		93.66 142	93.28 158	94.80 107	96.25 204	90.95 69	90.21 269	95.43 239	87.91 195	93.74 208	94.40 255	92.88 104	96.38 321	90.39 147	98.28 193	97.07 229

CNVR-MVS		94.58 109	94.29 124	95.46 82	96.94 151	89.35 96	91.81 228	96.80 173	89.66 160	93.90 204	95.44 216	92.80 106	98.72 151	92.74 92	98.52 171	98.32 132

ZD-MVS					97.23 138	90.32 78		97.54 113	84.40 260	94.78 178	95.79 198	92.76 107	99.39 49	88.72 199	98.40 179

XXY-MVS		92.58 176	93.16 161	90.84 262	97.75 106	79.84 263	91.87 224	96.22 207	85.94 229	95.53 138	97.68 66	92.69 108	94.48 357	83.21 277	97.51 244	98.21 140

CDPH-MVS		92.67 174	91.83 193	95.18 96	96.94 151	88.46 118	90.70 253	97.07 152	77.38 330	92.34 261	95.08 231	92.67 109	98.88 121	85.74 248	98.57 166	98.20 141

Fast-Effi-MVS+-dtu		92.77 171	92.16 182	94.58 123	94.66 282	88.25 120	92.05 212	96.65 183	89.62 161	90.08 300	91.23 329	92.56 110	98.60 171	86.30 243	96.27 287	96.90 238

fmvsm_s_conf0.1_n_a		94.26 122	94.37 121	93.95 146	97.36 133	85.72 180	94.15 134	95.44 237	83.25 271	95.51 139	98.05 45	92.54 111	97.19 288	95.55 20	97.46 248	98.94 66

AllTest		94.88 98	94.51 117	96.00 56	98.02 88	92.17 50	95.26 92	98.43 18	90.48 145	95.04 168	96.74 143	92.54 111	97.86 243	85.11 260	98.98 114	97.98 163

TestCases				96.00 56	98.02 88	92.17 50		98.43 18	90.48 145	95.04 168	96.74 143	92.54 111	97.86 243	85.11 260	98.98 114	97.98 163

TinyColmap		92.00 192	92.76 168	89.71 293	95.62 250	77.02 312	90.72 252	96.17 210	87.70 203	95.26 156	96.29 173	92.54 111	96.45 318	81.77 292	98.77 144	95.66 294

EGC-MVSNET		80.97 355	75.73 371	96.67 42	98.85 24	94.55 15	96.83 23	96.60 185	2.44 406	5.32 407	98.25 37	92.24 115	98.02 226	91.85 113	99.21 90	97.45 210

fmvsm_s_conf0.5_n_a		94.02 132	94.08 133	93.84 152	96.72 165	85.73 179	93.65 154	95.23 245	83.30 269	95.13 162	97.56 75	92.22 116	97.17 289	95.51 22	97.41 250	98.64 111

ETV-MVS		92.99 162	92.74 169	93.72 156	95.86 233	86.30 165	92.33 201	97.84 89	91.70 118	92.81 239	86.17 380	92.22 116	99.19 81	88.03 212	97.73 234	95.66 294

CLD-MVS		91.82 193	91.41 203	93.04 177	96.37 188	83.65 209	86.82 344	97.29 136	84.65 257	92.27 263	89.67 352	92.20 118	97.85 245	83.95 272	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												92.14 119

Vis-MVSNet		95.50 70	95.48 76	95.56 79	98.11 79	89.40 94	95.35 87	98.22 37	92.36 87	94.11 192	98.07 44	92.02 120	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		96.55 192	91.93 100	94.82 176	95.39 221	91.99 121	97.08 294	85.53 251	97.96 224	97.41 213

CP-MVSNet		96.19 45	96.80 16	94.38 132	98.99 16	83.82 207	96.31 50	97.53 115	97.60 7	98.34 19	97.52 80	91.98 122	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	95.01 103	97.57 111	92.68 79	96.20 107	93.44 287	91.92 123	98.78 142	89.11 189	99.24 85	96.92 237

fmvsm_s_conf0.1_n		94.19 128	94.41 118	93.52 166	97.22 140	84.37 195	93.73 150	95.26 244	84.45 259	95.76 126	98.00 50	91.85 124	97.21 285	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	96.81 172	85.23 244	94.75 179	97.12 115	91.85 124	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		94.00 133	94.20 129	93.42 170	96.69 166	84.37 195	93.38 162	95.13 247	84.50 258	95.40 146	97.55 79	91.77 126	97.20 286	95.59 18	97.79 232	98.69 103

Gipuma		95.31 84	95.80 65	93.81 154	97.99 93	90.91 70	96.42 42	97.95 81	96.69 17	91.78 271	98.85 12	91.77 126	95.49 341	91.72 117	99.08 102	95.02 313
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 58	97.42 9	98.48 16	97.86 61	91.76 128	99.63 6	94.23 41	99.84 3	99.66 6

AdaColmap		91.63 198	91.36 204	92.47 204	95.56 252	86.36 163	92.24 209	96.27 202	88.88 178	89.90 305	92.69 305	91.65 129	98.32 200	77.38 336	97.64 240	92.72 366

PHI-MVS		94.34 119	93.80 138	95.95 59	95.65 247	91.67 62	94.82 108	97.86 86	87.86 198	93.04 233	94.16 264	91.58 130	98.78 142	90.27 155	98.96 121	97.41 213

xiu_mvs_v1_base_debu		91.47 202	91.52 198	91.33 241	95.69 244	81.56 236	89.92 279	96.05 214	83.22 272	91.26 278	90.74 336	91.55 131	98.82 130	89.29 181	95.91 293	93.62 353

xiu_mvs_v1_base		91.47 202	91.52 198	91.33 241	95.69 244	81.56 236	89.92 279	96.05 214	83.22 272	91.26 278	90.74 336	91.55 131	98.82 130	89.29 181	95.91 293	93.62 353

xiu_mvs_v1_base_debi		91.47 202	91.52 198	91.33 241	95.69 244	81.56 236	89.92 279	96.05 214	83.22 272	91.26 278	90.74 336	91.55 131	98.82 130	89.29 181	95.91 293	93.62 353

tfpnnormal		94.27 121	94.87 103	92.48 203	97.71 111	80.88 247	94.55 121	95.41 240	93.70 61	96.67 84	97.72 65	91.40 134	98.18 213	87.45 221	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 91	96.13 26	94.74 180	97.23 105	91.33 135	99.16 83	93.25 77	98.30 192	98.46 125

TEST9					96.45 186	89.46 90	90.60 256	96.92 163	79.09 319	90.49 291	94.39 256	91.31 136	98.88 121

DeepC-MVS_fast	89.96 7	93.73 141	93.44 154	94.60 120	96.14 213	87.90 126	93.36 163	97.14 146	85.53 240	93.90 204	95.45 215	91.30 137	98.59 173	89.51 175	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		94.36 117	94.28 125	94.61 117	92.55 326	85.98 172	92.44 195	94.69 261	93.70 61	96.12 111	95.81 197	91.24 138	98.86 125	93.76 54	98.22 201	98.98 60

MCST-MVS		92.91 164	92.51 176	94.10 139	97.52 124	85.72 180	91.36 238	97.13 148	80.33 304	92.91 238	94.24 260	91.23 139	98.72 151	89.99 166	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	97.53 115	92.42 84	93.41 215	97.78 62	91.21 140	97.77 253	91.06 130	97.06 261	98.80 85

train_agg		92.71 173	91.83 193	95.35 84	96.45 186	89.46 90	90.60 256	96.92 163	79.37 313	90.49 291	94.39 256	91.20 141	98.88 121	88.66 200	98.43 178	97.72 193

test_8					96.37 188	89.14 100	90.51 259	96.89 166	79.37 313	90.42 293	94.36 258	91.20 141	98.82 130

EI-MVSNet-UG-set		94.35 118	94.27 127	94.59 121	92.46 329	85.87 175	92.42 197	94.69 261	93.67 64	96.13 110	95.84 196	91.20 141	98.86 125	93.78 51	98.23 199	99.03 52

EIA-MVS		92.35 184	92.03 186	93.30 173	95.81 238	83.97 205	92.80 178	98.17 46	87.71 202	89.79 308	87.56 370	91.17 144	99.18 82	87.97 213	97.27 254	96.77 245

dcpmvs_2		93.96 134	95.01 99	90.82 263	97.60 119	74.04 345	93.68 153	98.85 8	89.80 158	97.82 29	97.01 125	91.14 145	99.21 78	90.56 143	98.59 164	99.19 36

xiu_mvs_v2_base		89.00 263	89.19 246	88.46 318	94.86 270	74.63 337	86.97 338	95.60 227	80.88 300	87.83 339	88.62 363	91.04 146	98.81 135	82.51 285	94.38 331	91.93 372

HPM-MVS++		95.02 92	94.39 119	96.91 37	97.88 98	93.58 37	94.09 138	96.99 158	91.05 132	92.40 256	95.22 225	91.03 147	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	93.19 167	98.07 61	85.63 237	97.08 61	97.35 96	90.86 148	97.66 263	95.70 16	98.48 176	97.74 192

TAPA-MVS	88.58 10	92.49 179	91.75 195	94.73 110	96.50 182	89.69 86	92.91 175	97.68 102	78.02 327	92.79 241	94.10 265	90.85 149	97.96 232	84.76 266	98.16 206	96.54 250
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
fmvsm_l_conf0.5_n		93.79 139	93.81 136	93.73 155	96.16 210	86.26 166	92.46 193	96.72 179	81.69 293	95.77 125	97.11 116	90.83 150	97.82 246	95.58 19	97.99 221	97.11 228

pcd_1.5k_mvsjas		7.56 376	10.09 379	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	90.77 151	0.00 410	0.00 409	0.00 408	0.00 406

PS-MVSNAJss		96.01 50	96.04 52	95.89 67	98.82 26	88.51 116	95.57 83	97.88 85	88.72 180	98.81 6	98.86 10	90.77 151	99.60 9	95.43 26	99.53 39	99.57 14

PS-MVSNAJ		88.86 269	88.99 252	88.48 317	94.88 268	74.71 335	86.69 347	95.60 227	80.88 300	87.83 339	87.37 373	90.77 151	98.82 130	82.52 284	94.37 332	91.93 372

MVS_Test		92.57 178	93.29 156	90.40 276	93.53 308	75.85 329	92.52 189	96.96 159	88.73 179	92.35 259	96.70 147	90.77 151	98.37 198	92.53 98	95.49 303	96.99 235

MIMVSNet1		95.52 69	95.45 77	95.72 73	99.14 5	89.02 102	96.23 57	96.87 168	93.73 60	97.87 28	98.49 29	90.73 155	99.05 98	86.43 241	99.60 27	99.10 47

ab-mvs		92.40 182	92.62 174	91.74 225	97.02 147	81.65 235	95.84 71	95.50 236	86.95 216	92.95 237	97.56 75	90.70 156	97.50 270	79.63 317	97.43 249	96.06 274

Test By Simon												90.61 157

3Dnovator	92.54 3	94.80 101	94.90 101	94.47 128	95.47 254	87.06 142	96.63 31	97.28 138	91.82 110	94.34 191	97.41 87	90.60 158	98.65 166	92.47 99	98.11 210	97.70 194

NCCC		94.08 130	93.54 152	95.70 75	96.49 183	89.90 83	92.39 199	96.91 165	90.64 142	92.33 262	94.60 250	90.58 159	98.96 111	90.21 159	97.70 237	98.23 138

UniMVSNet_NR-MVSNet		95.35 79	95.21 90	95.76 71	97.69 114	88.59 113	92.26 207	97.84 89	94.91 40	96.80 78	95.78 201	90.42 160	99.41 39	91.60 121	99.58 34	99.29 29

test_prior2							90.21 269		89.33 167	90.77 287	94.81 240	90.41 161		88.21 203	98.55 167

KD-MVS_self_test		94.10 129	94.73 110	92.19 210	97.66 117	79.49 273	94.86 107	97.12 149	89.59 162	96.87 74	97.65 69	90.40 162	98.34 199	89.08 190	99.35 61	98.75 91

MSLP-MVS++		93.25 155	93.88 135	91.37 239	96.34 194	82.81 223	93.11 169	97.74 99	89.37 166	94.08 194	95.29 224	90.40 162	96.35 323	90.35 150	98.25 197	94.96 314

fmvsm_l_conf0.5_n_a		93.59 144	93.63 146	93.49 168	96.10 216	85.66 182	92.32 202	96.57 188	81.32 296	95.63 134	97.14 113	90.19 164	97.73 259	95.37 28	98.03 217	97.07 229

UniMVSNet (Re)		95.32 81	95.15 93	95.80 70	97.79 104	88.91 105	92.91 175	98.07 61	93.46 67	96.31 97	95.97 191	90.14 165	99.34 63	92.11 103	99.64 24	99.16 38

Effi-MVS+-dtu		93.90 138	92.60 175	97.77 3	94.74 277	96.67 5	94.00 140	95.41 240	89.94 154	91.93 270	92.13 317	90.12 166	98.97 110	87.68 218	97.48 246	97.67 197

FMVSNet1		94.84 99	95.13 94	93.97 143	97.60 119	84.29 197	95.99 63	96.56 189	92.38 85	97.03 66	98.53 26	90.12 166	98.98 106	88.78 197	99.16 97	98.65 106

DU-MVS		95.28 85	95.12 95	95.75 72	97.75 106	88.59 113	92.58 187	97.81 92	93.99 53	96.80 78	95.90 192	90.10 168	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 99	97.37 124	93.92 58	97.65 34	95.90 192	90.10 168	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 56	80.82 248	92.08 211	96.68 181	93.82 59	96.29 99	98.56 24	90.10 168	97.75 256	90.10 164	99.66 21	99.24 32

API-MVS		91.52 201	91.61 196	91.26 245	94.16 291	86.26 166	94.66 113	94.82 256	91.17 130	92.13 266	91.08 332	90.03 171	97.06 296	79.09 324	97.35 253	90.45 382

patch_mono-2		92.46 180	92.72 172	91.71 227	96.65 169	78.91 285	88.85 309	97.17 144	83.89 265	92.45 253	96.76 140	89.86 172	97.09 293	90.24 157	98.59 164	99.12 43

test12				94.43 130	95.95 228	86.75 150		96.24 204		89.76 309		89.79 173	98.79 139		97.95 225	97.75 191

旧先验1					96.20 207	84.17 202		94.82 256			95.57 212	89.57 174			97.89 228	96.32 262

DELS-MVS		92.05 191	92.16 182	91.72 226	94.44 286	80.13 254	87.62 324	97.25 139	87.34 209	92.22 264	93.18 294	89.54 175	98.73 150	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		93.08 159	93.76 140	91.03 253	98.60 39	75.83 331	91.51 233	95.62 226	91.84 107	95.74 129	97.10 118	89.31 176	98.32 200	85.07 262	99.06 103	98.93 68

QAPM		92.88 166	92.77 167	93.22 175	95.82 236	83.31 211	96.45 39	97.35 130	83.91 264	93.75 206	96.77 138	89.25 177	98.88 121	84.56 268	97.02 263	97.49 208

MSDG		90.82 211	90.67 221	91.26 245	94.16 291	83.08 219	86.63 349	96.19 208	90.60 144	91.94 269	91.89 320	89.16 178	95.75 336	80.96 303	94.51 329	94.95 315

CPTT-MVS		94.74 102	94.12 131	96.60 43	98.15 77	93.01 42	95.84 71	97.66 103	89.21 171	93.28 221	95.46 214	88.89 179	98.98 106	89.80 169	98.82 138	97.80 185

DP-MVS Recon		92.31 185	91.88 191	93.60 159	97.18 142	86.87 147	91.10 243	97.37 124	84.92 253	92.08 267	94.08 266	88.59 180	98.20 210	83.50 274	98.14 208	95.73 289

FC-MVSNet-test		95.32 81	95.88 59	93.62 158	98.49 57	81.77 233	95.90 69	98.32 25	93.93 56	97.53 42	97.56 75	88.48 181	99.40 46	92.91 89	99.83 5	99.68 4

OpenMVS	89.45 8	92.27 187	92.13 185	92.68 193	94.53 285	84.10 203	95.70 75	97.03 154	82.44 286	91.14 282	96.42 160	88.47 182	98.38 194	85.95 246	97.47 247	95.55 299

F-COLMAP		92.28 186	91.06 211	95.95 59	97.52 124	91.90 56	93.53 155	97.18 143	83.98 263	88.70 326	94.04 267	88.41 183	98.55 179	80.17 310	95.99 292	97.39 217

ambc				92.98 179	96.88 155	83.01 220	95.92 68	96.38 199		96.41 92	97.48 85	88.26 184	97.80 248	89.96 167	98.93 124	98.12 149

v10		94.68 106	95.27 89	92.90 185	96.57 175	80.15 252	94.65 114	97.57 111	90.68 141	97.43 48	98.00 50	88.18 185	99.15 84	94.84 31	99.55 38	99.41 20

v8		94.65 107	95.29 87	92.74 190	96.65 169	79.77 267	94.59 115	97.17 144	91.86 103	97.47 47	97.93 54	88.16 186	99.08 93	94.32 38	99.47 43	99.38 22

TSAR-MVS + GP.		93.07 161	92.41 179	95.06 99	95.82 236	90.87 72	90.97 245	92.61 304	88.04 194	94.61 183	93.79 278	88.08 187	97.81 247	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 73	94.15 51	98.93 3	99.07 5	88.07 188	99.57 14	95.86 15	99.69 14	99.46 18

diffmvs		91.74 195	91.93 190	91.15 251	93.06 315	78.17 295	88.77 312	97.51 118	86.28 221	92.42 255	93.96 272	88.04 189	97.46 273	90.69 141	96.67 278	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				92.87 186	96.91 154	84.22 200		97.01 155	76.84 336	89.64 311	94.46 254	88.00 190	98.70 158	81.53 296	98.01 220	95.70 292

VDD-MVS		94.37 116	94.37 121	94.40 131	97.49 126	86.07 171	93.97 143	93.28 288	94.49 45	96.24 103	97.78 62	87.99 191	98.79 139	88.92 193	99.14 99	98.34 131

XVG-OURS		94.72 103	94.12 131	96.50 47	98.00 90	94.23 18	91.48 234	98.17 46	90.72 139	95.30 153	96.47 157	87.94 192	96.98 298	91.41 126	97.61 242	98.30 135

CANet		92.38 183	91.99 188	93.52 166	93.82 304	83.46 210	91.14 241	97.00 156	89.81 157	86.47 352	94.04 267	87.90 193	99.21 78	89.50 176	98.27 194	97.90 172

BH-untuned		90.68 216	90.90 213	90.05 287	95.98 226	79.57 271	90.04 275	94.94 253	87.91 195	94.07 195	93.00 296	87.76 194	97.78 252	79.19 323	95.17 313	92.80 365

FIs		94.90 97	95.35 83	93.55 161	98.28 68	81.76 234	95.33 89	98.14 50	93.05 76	97.07 62	97.18 110	87.65 195	99.29 70	91.72 117	99.69 14	99.61 11

v1144		93.50 145	93.81 136	92.57 200	96.28 200	79.61 270	91.86 226	96.96 159	86.95 216	95.91 119	96.32 171	87.65 195	98.96 111	93.51 60	98.88 127	99.13 41

mvs_anonymous		90.37 228	91.30 206	87.58 330	92.17 337	68.00 375	89.84 282	94.73 260	83.82 266	93.22 227	97.40 88	87.54 197	97.40 278	87.94 214	95.05 316	97.34 220

PCF-MVS	84.52 17	89.12 257	87.71 282	93.34 171	96.06 219	85.84 176	86.58 352	97.31 133	68.46 384	93.61 211	93.89 275	87.51 198	98.52 181	67.85 385	98.11 210	95.66 294
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
VNet		92.67 174	92.96 162	91.79 223	96.27 201	80.15 252	91.95 216	94.98 251	92.19 94	94.52 186	96.07 186	87.43 199	97.39 279	84.83 264	98.38 183	97.83 181

v148		92.87 167	93.29 156	91.62 231	96.25 204	77.72 304	91.28 239	95.05 248	89.69 159	95.93 118	96.04 187	87.34 200	98.38 194	90.05 165	97.99 221	98.78 87

V42		93.43 148	93.58 149	92.97 180	95.34 260	81.22 242	92.67 183	96.49 194	87.25 210	96.20 107	96.37 168	87.32 201	98.85 127	92.39 101	98.21 202	98.85 81

v1192		93.49 146	93.78 139	92.62 197	96.16 210	79.62 269	91.83 227	97.22 142	86.07 227	96.10 112	96.38 167	87.22 202	99.02 103	94.14 43	98.88 127	99.22 33

WR-MVS		93.49 146	93.72 141	92.80 189	97.57 122	80.03 258	90.14 272	95.68 225	93.70 61	96.62 86	95.39 221	87.21 203	99.04 101	87.50 220	99.64 24	99.33 26

IterMVS-LS		93.78 140	94.28 125	92.27 207	96.27 201	79.21 280	91.87 224	96.78 174	91.77 113	96.57 89	97.07 119	87.15 204	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		92.99 162	93.26 160	92.19 210	92.12 338	79.21 280	92.32 202	94.67 263	91.77 113	95.24 159	95.85 194	87.14 205	98.49 183	91.99 108	98.26 195	98.86 78

v144192		93.20 158	93.54 152	92.16 214	96.05 220	78.26 294	91.95 216	97.14 146	84.98 252	95.96 115	96.11 184	87.08 206	99.04 101	93.79 50	98.84 132	99.17 37

114514_t		90.51 220	89.80 240	92.63 196	98.00 90	82.24 229	93.40 161	97.29 136	65.84 391	89.40 313	94.80 242	86.99 207	98.75 146	83.88 273	98.61 161	96.89 239

新几何1				93.17 176	97.16 143	87.29 135		94.43 266	67.95 385	91.29 277	94.94 236	86.97 208	98.23 208	81.06 302	97.75 233	93.98 343

HQP_MVS		94.26 122	93.93 134	95.23 93	97.71 111	88.12 122	94.56 119	97.81 92	91.74 115	93.31 218	95.59 208	86.93 209	98.95 114	89.26 184	98.51 173	98.60 116

plane_prior6					97.21 141	88.23 121						86.93 209

UGNet		93.08 159	92.50 177	94.79 108	93.87 302	87.99 125	95.07 100	94.26 271	90.64 142	87.33 348	97.67 68	86.89 211	98.49 183	88.10 208	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		92.72 172	92.02 187	94.84 106	95.65 247	91.99 54	92.92 174	96.60 185	85.08 250	92.44 254	93.62 282	86.80 212	96.35 323	86.81 230	98.25 197	96.18 269

v1921920		93.26 153	93.61 148	92.19 210	96.04 224	78.31 293	91.88 223	97.24 140	85.17 246	96.19 109	96.19 180	86.76 213	99.05 98	94.18 42	98.84 132	99.22 33

MVS_0304		93.92 136	93.68 144	94.64 116	95.94 230	85.83 177	94.34 126	88.14 343	92.98 77	91.09 283	97.68 66	86.73 214	99.36 58	96.64 7	99.59 29	98.72 96

v1240		93.29 151	93.71 142	92.06 217	96.01 225	77.89 300	91.81 228	97.37 124	85.12 248	96.69 83	96.40 162	86.67 215	99.07 97	94.51 34	98.76 145	99.22 33

MAR-MVS		90.32 231	88.87 256	94.66 115	94.82 271	91.85 57	94.22 132	94.75 259	80.91 299	87.52 346	88.07 368	86.63 216	97.87 242	76.67 340	96.21 288	94.25 337
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 42	91.26 126	95.12 163	95.15 226	86.60 217	99.50 21	93.43 70	96.81 273	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		90.47 222	90.44 226	90.56 271	95.21 263	78.65 291	89.15 303	93.94 279	88.21 190	92.74 243	94.22 261	86.38 218	97.88 239	78.67 326	95.39 307	95.14 308

CNLPA		91.72 196	91.20 207	93.26 174	96.17 209	91.02 67	91.14 241	95.55 234	90.16 152	90.87 285	93.56 285	86.31 219	94.40 360	79.92 316	97.12 259	94.37 334

PVSNet_BlendedMVS		90.35 229	89.96 236	91.54 234	94.81 272	78.80 289	90.14 272	96.93 161	79.43 312	88.68 327	95.06 232	86.27 220	98.15 216	80.27 306	98.04 216	97.68 196

PVSNet_Blended		88.74 272	88.16 276	90.46 275	94.81 272	78.80 289	86.64 348	96.93 161	74.67 348	88.68 327	89.18 359	86.27 220	98.15 216	80.27 306	96.00 291	94.44 333

PAPR		87.65 291	86.77 301	90.27 279	92.85 321	77.38 308	88.56 317	96.23 205	76.82 337	84.98 363	89.75 351	86.08 222	97.16 291	72.33 367	93.35 353	96.26 266

v2v482		93.29 151	93.63 146	92.29 206	96.35 193	78.82 287	91.77 230	96.28 201	88.45 186	95.70 133	96.26 177	86.02 223	98.90 118	93.02 85	98.81 140	99.14 40

test20.03		90.80 212	90.85 216	90.63 269	95.63 249	79.24 278	89.81 283	92.87 295	89.90 155	94.39 188	96.40 162	85.77 224	95.27 349	73.86 359	99.05 106	97.39 217

PLC	85.34 15	90.40 224	88.92 253	94.85 105	96.53 181	90.02 81	91.58 232	96.48 195	80.16 305	86.14 354	92.18 315	85.73 225	98.25 207	76.87 339	94.61 328	96.30 263
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVS		84.98 322	84.30 323	87.01 335	91.03 360	77.69 305	91.94 218	94.16 272	59.36 399	84.23 370	87.50 372	85.66 226	96.80 308	71.79 369	93.05 361	86.54 392

testdata				91.03 253	96.87 156	82.01 230		94.28 270	71.55 366	92.46 252	95.42 217	85.65 227	97.38 281	82.64 282	97.27 254	93.70 350

PM-MVS		93.33 150	92.67 173	95.33 86	96.58 174	94.06 21	92.26 207	92.18 309	85.92 230	96.22 105	96.61 152	85.64 228	95.99 332	90.35 150	98.23 199	95.93 280

SSC-MVS		90.16 234	92.96 162	81.78 375	97.88 98	48.48 407	90.75 250	87.69 348	96.02 31	96.70 82	97.63 71	85.60 229	97.80 248	85.73 249	98.60 163	99.06 50

MM		94.41 115	94.14 130	95.22 94	95.84 234	87.21 138	94.31 129	90.92 326	94.48 46	92.80 240	97.52 80	85.27 230	99.49 24	96.58 8	99.57 36	98.97 62

WB-MVS		89.44 252	92.15 184	81.32 376	97.73 109	48.22 408	89.73 285	87.98 346	95.24 36	96.05 113	96.99 126	85.18 231	96.95 299	82.45 286	97.97 223	98.78 87

MDA-MVSNet-bldmvs		91.04 208	90.88 214	91.55 233	94.68 281	80.16 251	85.49 365	92.14 312	90.41 149	94.93 172	95.79 198	85.10 232	96.93 302	85.15 257	94.19 339	97.57 202

PAPM_NR		91.03 209	90.81 217	91.68 229	96.73 164	81.10 244	93.72 151	96.35 200	88.19 191	88.77 324	92.12 318	85.09 233	97.25 283	82.40 287	93.90 344	96.68 248

WB-MVSnew		84.20 329	83.89 328	85.16 357	91.62 353	66.15 386	88.44 319	81.00 390	76.23 339	87.98 337	87.77 369	84.98 234	93.35 370	62.85 395	94.10 342	95.98 277

HQP2-MVS												84.76 235

HQP-MVS		92.09 190	91.49 201	93.88 149	96.36 190	84.89 191	91.37 235	97.31 133	87.16 211	88.81 320	93.40 288	84.76 235	98.60 171	86.55 238	97.73 234	98.14 147

test222					96.95 150	85.27 188	88.83 310	93.61 280	65.09 393	90.74 288	94.85 239	84.62 237			97.36 252	93.91 344

VDDNet		94.03 131	94.27 127	93.31 172	98.87 21	82.36 228	95.51 85	91.78 318	97.19 12	96.32 96	98.60 22	84.24 238	98.75 146	87.09 228	98.83 137	98.81 84

PVSNet_Blended_VisFu		91.63 198	91.20 207	92.94 183	97.73 109	83.95 206	92.14 210	97.46 119	78.85 323	92.35 259	94.98 234	84.16 239	99.08 93	86.36 242	96.77 275	95.79 287

CL-MVSNet_self_test		90.04 242	89.90 238	90.47 272	95.24 262	77.81 302	86.60 351	92.62 303	85.64 236	93.25 225	93.92 273	83.84 240	96.06 330	79.93 314	98.03 217	97.53 206

mvsany_test3		89.11 258	88.21 274	91.83 221	91.30 358	90.25 79	88.09 321	78.76 397	76.37 338	96.43 91	98.39 33	83.79 241	90.43 385	86.57 236	94.20 337	94.80 323

mvsmamba		95.61 65	95.40 81	96.22 51	98.44 59	89.86 84	97.14 17	97.45 121	91.25 128	97.49 44	98.14 39	83.49 242	99.45 27	95.52 21	99.66 21	99.36 24

BH-w/o		87.21 302	87.02 297	87.79 329	94.77 275	77.27 310	87.90 322	93.21 291	81.74 292	89.99 303	88.39 366	83.47 243	96.93 302	71.29 373	92.43 368	89.15 383

PatchMatch-RL		89.18 255	88.02 279	92.64 194	95.90 232	92.87 45	88.67 316	91.06 323	80.34 303	90.03 302	91.67 324	83.34 244	94.42 359	76.35 344	94.84 322	90.64 381

DPM-MVS		89.35 253	88.40 262	92.18 213	96.13 215	84.20 201	86.96 339	96.15 211	75.40 344	87.36 347	91.55 327	83.30 245	98.01 227	82.17 290	96.62 279	94.32 336

OpenMVS_ROB	85.12 16	89.52 250	89.05 249	90.92 258	94.58 284	81.21 243	91.10 243	93.41 287	77.03 334	93.41 215	93.99 271	83.23 246	97.80 248	79.93 314	94.80 323	93.74 349

new-patchmatchnet		88.97 264	90.79 218	83.50 370	94.28 290	55.83 405	85.34 367	93.56 283	86.18 225	95.47 142	95.73 204	83.10 247	96.51 315	85.40 252	98.06 214	98.16 145

mvsany_test1		83.91 331	82.93 335	86.84 340	86.18 399	85.93 173	81.11 389	75.03 404	70.80 374	88.57 329	94.63 248	83.08 248	87.38 394	80.39 304	86.57 390	87.21 390

1314		86.46 312	86.33 309	86.87 339	91.65 352	74.54 338	91.94 218	94.10 273	74.28 351	84.78 365	87.33 374	83.03 249	95.00 351	78.72 325	91.16 377	91.06 379

IS-MVSNet		94.49 112	94.35 123	94.92 102	98.25 72	86.46 159	97.13 18	94.31 268	96.24 25	96.28 101	96.36 169	82.88 250	99.35 60	88.19 205	99.52 41	98.96 64

test_fmvs3		92.42 181	92.40 180	92.46 205	93.80 305	87.28 136	93.86 146	97.05 153	76.86 335	96.25 102	98.66 18	82.87 251	91.26 380	95.44 25	96.83 272	98.82 82

MG-MVS		89.54 249	89.80 240	88.76 309	94.88 268	72.47 357	89.60 288	92.44 307	85.82 231	89.48 312	95.98 190	82.85 252	97.74 258	81.87 291	95.27 311	96.08 273

TR-MVS		87.70 288	87.17 292	89.27 301	94.11 293	79.26 277	88.69 314	91.86 317	81.94 291	90.69 289	89.79 349	82.82 253	97.42 276	72.65 366	91.98 372	91.14 378

c3_l		91.32 206	91.42 202	91.00 256	92.29 331	76.79 319	87.52 330	96.42 197	85.76 233	94.72 182	93.89 275	82.73 254	98.16 215	90.93 135	98.55 167	98.04 154

YYNet1		88.17 281	88.24 271	87.93 326	92.21 334	73.62 347	80.75 390	88.77 335	82.51 285	94.99 170	95.11 229	82.70 255	93.70 366	83.33 275	93.83 345	96.48 256

MDA-MVSNet_test_wron		88.16 282	88.23 272	87.93 326	92.22 333	73.71 346	80.71 391	88.84 334	82.52 284	94.88 175	95.14 227	82.70 255	93.61 367	83.28 276	93.80 346	96.46 257

pmmvs-eth3d		91.54 200	90.73 220	93.99 141	95.76 241	87.86 128	90.83 248	93.98 278	78.23 326	94.02 199	96.22 179	82.62 257	96.83 307	86.57 236	98.33 189	97.29 223

Anonymous20231206		88.77 271	88.29 267	90.20 283	96.31 197	78.81 288	89.56 290	93.49 285	74.26 352	92.38 257	95.58 211	82.21 258	95.43 344	72.07 368	98.75 147	96.34 261

miper_ehance_all_eth		90.48 221	90.42 227	90.69 266	91.62 353	76.57 322	86.83 343	96.18 209	83.38 268	94.06 196	92.66 307	82.20 259	98.04 222	89.79 170	97.02 263	97.45 210

USDC		89.02 260	89.08 248	88.84 308	95.07 265	74.50 340	88.97 305	96.39 198	73.21 358	93.27 222	96.28 175	82.16 260	96.39 320	77.55 333	98.80 141	95.62 297

EPP-MVSNet		93.91 137	93.68 144	94.59 121	98.08 81	85.55 184	97.44 12	94.03 274	94.22 50	94.94 171	96.19 180	82.07 261	99.57 14	87.28 225	98.89 125	98.65 106

UnsupCasMVSNet_eth		90.33 230	90.34 229	90.28 278	94.64 283	80.24 250	89.69 287	95.88 219	85.77 232	93.94 203	95.69 205	81.99 262	92.98 373	84.21 270	91.30 375	97.62 199

alignmvs		93.26 153	92.85 166	94.50 125	95.70 243	87.45 133	93.45 159	95.76 222	91.58 120	95.25 158	92.42 313	81.96 263	98.72 151	91.61 120	97.87 229	97.33 221

TAMVS		90.16 234	89.05 249	93.49 168	96.49 183	86.37 162	90.34 266	92.55 305	80.84 302	92.99 234	94.57 252	81.94 264	98.20 210	73.51 360	98.21 202	95.90 283

Anonymous202405211		92.58 176	92.50 177	92.83 188	96.55 177	83.22 215	92.43 196	91.64 320	94.10 52	95.59 136	96.64 150	81.88 265	97.50 270	85.12 259	98.52 171	97.77 188

bld_raw_dy_0_64		90.86 210	90.99 212	90.47 272	93.95 299	77.88 301	93.99 142	98.93 7	77.75 328	97.03 66	90.61 342	81.82 266	98.58 175	85.18 253	99.61 26	94.95 315

SixPastTwentyTwo		94.91 96	95.21 90	93.98 142	98.52 49	83.19 216	95.93 67	94.84 255	94.86 41	98.49 15	98.74 16	81.45 267	99.60 9	94.69 32	99.39 58	99.15 39

cascas		87.02 308	86.28 310	89.25 302	91.56 355	76.45 323	84.33 377	96.78 174	71.01 371	86.89 351	85.91 381	81.35 268	96.94 300	83.09 278	95.60 300	94.35 335

GBi-Net		93.21 156	92.96 162	93.97 143	95.40 256	84.29 197	95.99 63	96.56 189	88.63 182	95.10 164	98.53 26	81.31 269	98.98 106	86.74 231	98.38 183	98.65 106

test1		93.21 156	92.96 162	93.97 143	95.40 256	84.29 197	95.99 63	96.56 189	88.63 182	95.10 164	98.53 26	81.31 269	98.98 106	86.74 231	98.38 183	98.65 106

FMVSNet2		92.78 170	92.73 171	92.95 182	95.40 256	81.98 231	94.18 133	95.53 235	88.63 182	96.05 113	97.37 90	81.31 269	98.81 135	87.38 224	98.67 157	98.06 151

MVE	59.87 23	73.86 370	72.65 373	77.47 382	87.00 397	74.35 341	61.37 400	60.93 408	67.27 386	69.69 403	86.49 378	81.24 272	72.33 404	56.45 401	83.45 395	85.74 393
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	94.48 265	93.12 73	97.94 27	98.54 25	81.19 273	99.63 6	95.48 23	99.69 14	99.60 12

MVP-Stereo		90.07 240	88.92 253	93.54 163	96.31 197	86.49 157	90.93 246	95.59 231	79.80 306	91.48 274	95.59 208	80.79 274	97.39 279	78.57 327	91.19 376	96.76 246
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UnsupCasMVSNet_bld		88.50 276	88.03 278	89.90 289	95.52 253	78.88 286	87.39 331	94.02 276	79.32 317	93.06 231	94.02 269	80.72 275	94.27 362	75.16 351	93.08 360	96.54 250

MS-PatchMatch		88.05 283	87.75 281	88.95 305	93.28 310	77.93 298	87.88 323	92.49 306	75.42 343	92.57 249	93.59 284	80.44 276	94.24 364	81.28 298	92.75 363	94.69 329

Anonymous20240521		92.86 168	93.57 150	90.74 265	96.57 175	75.50 333	94.15 134	95.60 227	89.38 165	95.90 120	97.90 60	80.39 277	97.96 232	92.60 97	99.68 18	98.75 91

iter_conf05_11		88.91 267	88.32 264	90.66 267	93.95 299	78.09 296	86.98 337	93.06 292	79.35 316	87.64 342	89.80 346	80.25 278	98.96 111	85.18 253	98.69 153	94.95 315

CANet_DTU		89.85 245	89.17 247	91.87 220	92.20 335	80.02 259	90.79 249	95.87 220	86.02 228	82.53 383	91.77 322	80.01 279	98.57 176	85.66 250	97.70 237	97.01 234

PMMVS		83.00 338	81.11 347	88.66 312	83.81 406	86.44 160	82.24 386	85.65 365	61.75 398	82.07 385	85.64 384	79.75 280	91.59 379	75.99 347	93.09 359	87.94 389

ppachtmachnet_test		88.61 275	88.64 258	88.50 316	91.76 348	70.99 364	84.59 374	92.98 293	79.30 318	92.38 257	93.53 286	79.57 281	97.45 274	86.50 240	97.17 258	97.07 229

eth_miper_zixun_eth		90.72 214	90.61 222	91.05 252	92.04 341	76.84 318	86.91 340	96.67 182	85.21 245	94.41 187	93.92 273	79.53 282	98.26 206	89.76 171	97.02 263	98.06 151

test_vis1_rt		85.58 317	84.58 320	88.60 313	87.97 389	86.76 149	85.45 366	93.59 281	66.43 388	87.64 342	89.20 358	79.33 283	85.38 399	81.59 295	89.98 383	93.66 351

N_pmnet		88.90 268	87.25 290	93.83 153	94.40 288	93.81 35	84.73 371	87.09 353	79.36 315	93.26 223	92.43 312	79.29 284	91.68 378	77.50 335	97.22 256	96.00 276

miper_enhance_ethall		88.42 277	87.87 280	90.07 285	88.67 387	75.52 332	85.10 368	95.59 231	75.68 340	92.49 250	89.45 355	78.96 285	97.88 239	87.86 216	97.02 263	96.81 243

EPNet		89.80 247	88.25 270	94.45 129	83.91 405	86.18 168	93.87 145	87.07 354	91.16 131	80.64 393	94.72 245	78.83 286	98.89 120	85.17 255	98.89 125	98.28 136
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
sss		87.23 301	86.82 299	88.46 318	93.96 297	77.94 297	86.84 342	92.78 299	77.59 329	87.61 345	91.83 321	78.75 287	91.92 377	77.84 330	94.20 337	95.52 300

IterMVS-SCA-FT		91.65 197	91.55 197	91.94 219	93.89 301	79.22 279	87.56 327	93.51 284	91.53 122	95.37 149	96.62 151	78.65 288	98.90 118	91.89 112	94.95 318	97.70 194

SCA		87.43 297	87.21 291	88.10 324	92.01 342	71.98 359	89.43 294	88.11 344	82.26 288	88.71 325	92.83 300	78.65 288	97.59 266	79.61 318	93.30 354	94.75 326

our_test_3		87.55 294	87.59 284	87.44 332	91.76 348	70.48 365	83.83 380	90.55 330	79.79 307	92.06 268	92.17 316	78.63 290	95.63 337	84.77 265	94.73 324	96.22 267

jason		89.17 256	88.32 264	91.70 228	95.73 242	80.07 255	88.10 320	93.22 289	71.98 365	90.09 299	92.79 302	78.53 291	98.56 177	87.43 222	97.06 261	96.46 257
jason: jason.
IterMVS		90.18 233	90.16 231	90.21 282	93.15 313	75.98 328	87.56 327	92.97 294	86.43 220	94.09 193	96.40 162	78.32 292	97.43 275	87.87 215	94.69 326	97.23 225
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CHOSEN 1792x2688		87.19 304	85.92 313	91.00 256	97.13 145	79.41 274	84.51 375	95.60 227	64.14 394	90.07 301	94.81 240	78.26 293	97.14 292	73.34 361	95.38 308	96.46 257

WTY-MVS		86.93 309	86.50 308	88.24 321	94.96 266	74.64 336	87.19 334	92.07 314	78.29 325	88.32 332	91.59 326	78.06 294	94.27 362	74.88 352	93.15 358	95.80 286

pmmvs4		88.95 265	87.70 283	92.70 191	94.30 289	85.60 183	87.22 333	92.16 311	74.62 349	89.75 310	94.19 262	77.97 295	96.41 319	82.71 281	96.36 285	96.09 272

DSMNet-mixed		82.21 344	81.56 343	84.16 365	89.57 379	70.00 370	90.65 255	77.66 401	54.99 402	83.30 378	97.57 74	77.89 296	90.50 384	66.86 388	95.54 302	91.97 371

FA-MVS(test-final)		91.81 194	91.85 192	91.68 229	94.95 267	79.99 260	96.00 62	93.44 286	87.80 199	94.02 199	97.29 101	77.60 297	98.45 189	88.04 211	97.49 245	96.61 249

lessismore_v0				93.87 150	98.05 84	83.77 208		80.32 394		97.13 60	97.91 58	77.49 298	99.11 92	92.62 96	98.08 213	98.74 94

Syy-MVS		84.81 323	84.93 317	84.42 363	91.71 350	63.36 397	85.89 360	81.49 387	81.03 297	85.13 360	81.64 396	77.44 299	95.00 351	85.94 247	94.12 340	94.91 320

HY-MVS	82.50 18	86.81 310	85.93 312	89.47 295	93.63 306	77.93 298	94.02 139	91.58 321	75.68 340	83.64 374	93.64 280	77.40 300	97.42 276	71.70 371	92.07 371	93.05 362

1112_ss		88.42 277	87.41 286	91.45 237	96.69 166	80.99 245	89.72 286	96.72 179	73.37 356	87.00 350	90.69 339	77.38 301	98.20 210	81.38 297	93.72 347	95.15 307

DIV-MVS_self_test		90.65 217	90.56 224	90.91 260	91.85 346	76.99 314	86.75 345	95.36 242	85.52 242	94.06 196	94.89 237	77.37 302	97.99 230	90.28 154	98.97 119	97.76 189

cl____		90.65 217	90.56 224	90.91 260	91.85 346	76.98 315	86.75 345	95.36 242	85.53 240	94.06 196	94.89 237	77.36 303	97.98 231	90.27 155	98.98 114	97.76 189

CDS-MVSNet		89.55 248	88.22 273	93.53 164	95.37 259	86.49 157	89.26 300	93.59 281	79.76 308	91.15 281	92.31 314	77.12 304	98.38 194	77.51 334	97.92 227	95.71 290
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test_vis3_rt		90.40 224	90.03 235	91.52 235	92.58 324	88.95 103	90.38 264	97.72 101	73.30 357	97.79 30	97.51 83	77.05 305	87.10 395	89.03 191	94.89 319	98.50 121

MVSFormer		92.18 189	92.23 181	92.04 218	94.74 277	80.06 256	97.15 15	97.37 124	88.98 174	88.83 318	92.79 302	77.02 306	99.60 9	96.41 9	96.75 276	96.46 257

lupinMVS		88.34 279	87.31 287	91.45 237	94.74 277	80.06 256	87.23 332	92.27 308	71.10 370	88.83 318	91.15 330	77.02 306	98.53 180	86.67 234	96.75 276	95.76 288

PMMVS2		81.31 351	83.44 330	74.92 384	90.52 367	46.49 410	69.19 398	85.23 373	84.30 262	87.95 338	94.71 246	76.95 308	84.36 401	64.07 392	98.09 212	93.89 345

h-mvs33		92.89 165	91.99 188	95.58 77	96.97 149	90.55 76	93.94 144	94.01 277	89.23 168	93.95 201	96.19 180	76.88 309	99.14 86	91.02 131	95.71 298	97.04 233

hse-mvs2		92.24 188	91.20 207	95.38 83	96.16 210	90.65 75	92.52 189	92.01 316	89.23 168	93.95 201	92.99 297	76.88 309	98.69 160	91.02 131	96.03 290	96.81 243

pmmvs5		87.87 285	87.14 293	90.07 285	93.26 312	76.97 316	88.89 307	92.18 309	73.71 355	88.36 331	93.89 275	76.86 311	96.73 310	80.32 305	96.81 273	96.51 252

test_vis1_n_1920		89.45 251	89.85 239	88.28 320	93.59 307	76.71 320	90.67 254	97.78 97	79.67 310	90.30 297	96.11 184	76.62 312	92.17 376	90.31 152	93.57 349	95.96 278

K. test v3		93.37 149	93.27 159	93.66 157	98.05 84	82.62 224	94.35 125	86.62 356	96.05 29	97.51 43	98.85 12	76.59 313	99.65 3	93.21 78	98.20 204	98.73 95

miper_lstm_enhance		89.90 244	89.80 240	90.19 284	91.37 357	77.50 306	83.82 381	95.00 250	84.84 255	93.05 232	94.96 235	76.53 314	95.20 350	89.96 167	98.67 157	97.86 177

dmvs_testset		78.23 368	78.99 363	75.94 383	91.99 343	55.34 406	88.86 308	78.70 398	82.69 281	81.64 390	79.46 398	75.93 315	85.74 398	48.78 404	82.85 397	86.76 391

Test_1112_low_res		87.50 296	86.58 303	90.25 280	96.80 163	77.75 303	87.53 329	96.25 203	69.73 380	86.47 352	93.61 283	75.67 316	97.88 239	79.95 312	93.20 356	95.11 311

test_fmvs2		90.62 219	90.40 228	91.29 244	91.93 345	85.46 185	92.70 182	96.48 195	74.44 350	94.91 173	97.59 73	75.52 317	90.57 382	93.44 67	96.56 280	97.84 180

Vis-MVSNet (Re-imp)		90.42 223	90.16 231	91.20 249	97.66 117	77.32 309	94.33 127	87.66 349	91.20 129	92.99 234	95.13 228	75.40 318	98.28 202	77.86 329	99.19 92	97.99 162

test_vis1_n		89.01 262	89.01 251	89.03 304	92.57 325	82.46 227	92.62 186	96.06 212	73.02 360	90.40 294	95.77 202	74.86 319	89.68 388	90.78 138	94.98 317	94.95 315

D2MVS		89.93 243	89.60 245	90.92 258	94.03 296	78.40 292	88.69 314	94.85 254	78.96 321	93.08 230	95.09 230	74.57 320	96.94 300	88.19 205	98.96 121	97.41 213

PVSNet	76.22 20	82.89 340	82.37 339	84.48 362	93.96 297	64.38 394	78.60 393	88.61 336	71.50 367	84.43 368	86.36 379	74.27 321	94.60 356	69.87 381	93.69 348	94.46 332

test_yl		90.11 237	89.73 243	91.26 245	94.09 294	79.82 264	90.44 260	92.65 301	90.90 133	93.19 228	93.30 290	73.90 322	98.03 223	82.23 288	96.87 270	95.93 280

DCV-MVSNet		90.11 237	89.73 243	91.26 245	94.09 294	79.82 264	90.44 260	92.65 301	90.90 133	93.19 228	93.30 290	73.90 322	98.03 223	82.23 288	96.87 270	95.93 280

CMPMVS	68.83 22	87.28 300	85.67 314	92.09 216	88.77 386	85.42 186	90.31 267	94.38 267	70.02 378	88.00 336	93.30 290	73.78 324	94.03 365	75.96 348	96.54 281	96.83 242
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
baseline1		87.62 292	87.31 287	88.54 314	94.71 280	74.27 343	93.10 170	88.20 341	86.20 224	92.18 265	93.04 295	73.21 325	95.52 339	79.32 321	85.82 391	95.83 285

PVSNet_0	70.34 21	74.58 369	72.96 372	79.47 380	90.63 365	66.24 384	73.26 394	83.40 382	63.67 396	78.02 397	78.35 400	72.53 326	89.59 389	56.68 399	60.05 404	82.57 398

dmvs_re		84.69 325	83.94 327	86.95 337	92.24 332	82.93 221	89.51 291	87.37 351	84.38 261	85.37 357	85.08 387	72.44 327	86.59 396	68.05 384	91.03 379	91.33 376

MIMVSNet		87.13 306	86.54 305	88.89 307	96.05 220	76.11 326	94.39 124	88.51 337	81.37 295	88.27 333	96.75 142	72.38 328	95.52 339	65.71 390	95.47 304	95.03 312

PAPM		81.91 349	80.11 359	87.31 333	93.87 302	72.32 358	84.02 379	93.22 289	69.47 381	76.13 400	89.84 345	72.15 329	97.23 284	53.27 402	89.02 384	92.37 369

cl22		89.02 260	88.50 260	90.59 270	89.76 375	76.45 323	86.62 350	94.03 274	82.98 278	92.65 245	92.49 308	72.05 330	97.53 268	88.93 192	97.02 263	97.78 187

LFMVS		91.33 205	91.16 210	91.82 222	96.27 201	79.36 275	95.01 103	85.61 367	96.04 30	94.82 176	97.06 120	72.03 331	98.46 188	84.96 263	98.70 152	97.65 198

test_cas_vis1_n_1920		88.25 280	88.27 269	88.20 322	92.19 336	78.92 284	89.45 293	95.44 237	75.29 347	93.23 226	95.65 207	71.58 332	90.23 386	88.05 210	93.55 351	95.44 301

MVS-HIRNet		78.83 367	80.60 354	73.51 385	93.07 314	47.37 409	87.10 336	78.00 400	68.94 382	77.53 398	97.26 102	71.45 333	94.62 355	63.28 394	88.74 385	78.55 400

EPNet_dtu		85.63 316	84.37 322	89.40 298	86.30 398	74.33 342	91.64 231	88.26 339	84.84 255	72.96 402	89.85 344	71.27 334	97.69 261	76.60 341	97.62 241	96.18 269
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test1111		90.39 226	90.61 222	89.74 292	98.04 87	71.50 361	95.59 80	79.72 396	89.41 164	95.94 117	98.14 39	70.79 335	98.81 135	88.52 202	99.32 68	98.90 74

ECVR-MVS		90.12 236	90.16 231	90.00 288	97.81 102	72.68 355	95.76 74	78.54 399	89.04 172	95.36 150	98.10 42	70.51 336	98.64 167	87.10 227	99.18 94	98.67 104

HyFIR lowres test		87.19 304	85.51 315	92.24 208	97.12 146	80.51 249	85.03 369	96.06 212	66.11 390	91.66 273	92.98 298	70.12 337	99.14 86	75.29 350	95.23 312	97.07 229

FMVSNet3		90.78 213	90.32 230	92.16 214	93.03 317	79.92 262	92.54 188	94.95 252	86.17 226	95.10 164	96.01 189	69.97 338	98.75 146	86.74 231	98.38 183	97.82 183

test_f		86.65 311	87.13 294	85.19 356	90.28 371	86.11 170	86.52 353	91.66 319	69.76 379	95.73 131	97.21 109	69.51 339	81.28 402	89.15 188	94.40 330	88.17 388

RPMNet		90.31 232	90.14 234	90.81 264	91.01 361	78.93 282	92.52 189	98.12 52	91.91 101	89.10 315	96.89 132	68.84 340	99.41 39	90.17 160	92.70 364	94.08 338

test_fmvs1_n		88.73 273	88.38 263	89.76 291	92.06 340	82.53 225	92.30 205	96.59 187	71.14 369	92.58 248	95.41 220	68.55 341	89.57 390	91.12 129	95.66 299	97.18 227

test_fmvs1		87.59 293	87.27 289	88.54 314	88.32 388	81.26 241	90.43 263	95.72 224	70.55 375	91.70 272	94.63 248	68.13 342	89.42 391	90.59 142	95.34 309	94.94 319

ADS-MVSNet2		84.01 330	82.20 341	89.41 297	89.04 383	76.37 325	87.57 325	90.98 325	72.71 363	84.46 366	92.45 309	68.08 343	96.48 316	70.58 379	83.97 393	95.38 302

ADS-MVSNet		82.25 343	81.55 344	84.34 364	89.04 383	65.30 388	87.57 325	85.13 374	72.71 363	84.46 366	92.45 309	68.08 343	92.33 375	70.58 379	83.97 393	95.38 302

CVMVSNet		85.16 320	84.72 318	86.48 343	92.12 338	70.19 366	92.32 202	88.17 342	56.15 401	90.64 290	95.85 194	67.97 345	96.69 311	88.78 197	90.52 380	92.56 367

new_pmnet		81.22 352	81.01 350	81.86 374	90.92 363	70.15 367	84.03 378	80.25 395	70.83 372	85.97 355	89.78 350	67.93 346	84.65 400	67.44 386	91.90 373	90.78 380

CR-MVSNet		87.89 284	87.12 295	90.22 281	91.01 361	78.93 282	92.52 189	92.81 296	73.08 359	89.10 315	96.93 129	67.11 347	97.64 265	88.80 196	92.70 364	94.08 338

Patchmtry		90.11 237	89.92 237	90.66 267	90.35 370	77.00 313	92.96 173	92.81 296	90.25 151	94.74 180	96.93 129	67.11 347	97.52 269	85.17 255	98.98 114	97.46 209

PatchmatchNet		85.22 319	84.64 319	86.98 336	89.51 380	69.83 371	90.52 258	87.34 352	78.87 322	87.22 349	92.74 304	66.91 349	96.53 313	81.77 292	86.88 389	94.58 330
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
GA-MVS		87.70 288	86.82 299	90.31 277	93.27 311	77.22 311	84.72 373	92.79 298	85.11 249	89.82 306	90.07 343	66.80 350	97.76 255	84.56 268	94.27 335	95.96 278

MDTV_nov1_ep13_2view						42.48 411	88.45 318		67.22 387	83.56 375		66.80 350		72.86 365		94.06 340

tpmrst		82.85 341	82.93 335	82.64 372	87.65 390	58.99 403	90.14 272	87.90 347	75.54 342	83.93 372	91.63 325	66.79 352	95.36 345	81.21 300	81.54 399	93.57 356

sam_mvs1												66.64 353				94.75 326

sam_mvs												66.41 354

Patchmatch-RL test		88.81 270	88.52 259	89.69 294	95.33 261	79.94 261	86.22 357	92.71 300	78.46 324	95.80 124	94.18 263	66.25 355	95.33 347	89.22 186	98.53 170	93.78 347

patchmatchnet-post											91.71 323	66.22 356	97.59 266

AUN-MVS		90.05 241	88.30 266	95.32 88	96.09 217	90.52 77	92.42 197	92.05 315	82.08 290	88.45 330	92.86 299	65.76 357	98.69 160	88.91 194	96.07 289	96.75 247

test_post											6.07 407	65.74 358	95.84 335

test_post1							90.21 269				5.85 408	65.36 359	96.00 331	79.61 318

MDTV_nov1_ep13			83.88 329		89.42 381	61.52 398	88.74 313	87.41 350	73.99 353	84.96 364	94.01 270	65.25 360	95.53 338	78.02 328	93.16 357

Patchmatch-test		86.10 314	86.01 311	86.38 347	90.63 365	74.22 344	89.57 289	86.69 355	85.73 234	89.81 307	92.83 300	65.24 361	91.04 381	77.82 332	95.78 297	93.88 346

tpmvs		84.22 328	83.97 326	84.94 358	87.09 395	65.18 389	91.21 240	88.35 338	82.87 279	85.21 358	90.96 334	65.24 361	96.75 309	79.60 320	85.25 392	92.90 364

EU-MVSNet		87.39 298	86.71 302	89.44 296	93.40 309	76.11 326	94.93 106	90.00 332	57.17 400	95.71 132	97.37 90	64.77 363	97.68 262	92.67 95	94.37 332	94.52 331

thres200		85.85 315	85.18 316	87.88 328	94.44 286	72.52 356	89.08 304	86.21 358	88.57 185	91.44 275	88.40 365	64.22 364	98.00 228	68.35 383	95.88 296	93.12 359

PatchT		87.51 295	88.17 275	85.55 352	90.64 364	66.91 379	92.02 214	86.09 360	92.20 93	89.05 317	97.16 111	64.15 365	96.37 322	89.21 187	92.98 362	93.37 357

tfpn200view9		87.05 307	86.52 306	88.67 311	95.77 239	72.94 352	91.89 221	86.00 361	90.84 135	92.61 246	89.80 346	63.93 366	98.28 202	71.27 374	96.54 281	94.79 324

thres400		87.20 303	86.52 306	89.24 303	95.77 239	72.94 352	91.89 221	86.00 361	90.84 135	92.61 246	89.80 346	63.93 366	98.28 202	71.27 374	96.54 281	96.51 252

FPMVS		84.50 326	83.28 331	88.16 323	96.32 196	94.49 16	85.76 363	85.47 368	83.09 275	85.20 359	94.26 259	63.79 368	86.58 397	63.72 393	91.88 374	83.40 395

thres100view900		87.35 299	86.89 298	88.72 310	96.14 213	73.09 351	93.00 172	85.31 370	92.13 95	93.26 223	90.96 334	63.42 369	98.28 202	71.27 374	96.54 281	94.79 324

thres600view7		87.66 290	87.10 296	89.36 299	96.05 220	73.17 349	92.72 180	85.31 370	91.89 102	93.29 220	90.97 333	63.42 369	98.39 191	73.23 362	96.99 268	96.51 252

EMVS		80.35 360	80.28 358	80.54 378	84.73 404	69.07 372	72.54 397	80.73 392	87.80 199	81.66 389	81.73 395	62.89 371	89.84 387	75.79 349	94.65 327	82.71 397

test-LLR		83.58 333	83.17 332	84.79 360	89.68 377	66.86 380	83.08 382	84.52 376	83.07 276	82.85 380	84.78 388	62.86 372	93.49 368	82.85 279	94.86 320	94.03 341

test0.0.03 1		82.48 342	81.47 346	85.48 353	89.70 376	73.57 348	84.73 371	81.64 386	83.07 276	88.13 335	86.61 376	62.86 372	89.10 393	66.24 389	90.29 381	93.77 348

tpm cat1		80.61 358	79.46 361	84.07 366	88.78 385	65.06 392	89.26 300	88.23 340	62.27 397	81.90 388	89.66 353	62.70 374	95.29 348	71.72 370	80.60 400	91.86 374

E-PMN		80.72 357	80.86 351	80.29 379	85.11 402	68.77 373	72.96 395	81.97 385	87.76 201	83.25 379	83.01 394	62.22 375	89.17 392	77.15 338	94.31 334	82.93 396

baseline2		83.38 335	81.54 345	88.90 306	91.38 356	72.84 354	88.78 311	81.22 389	78.97 320	79.82 395	87.56 370	61.73 376	97.80 248	74.30 356	90.05 382	96.05 275

CostFormer		83.09 337	82.21 340	85.73 350	89.27 382	67.01 378	90.35 265	86.47 357	70.42 376	83.52 376	93.23 293	61.18 377	96.85 306	77.21 337	88.26 387	93.34 358

MVSTER		89.32 254	88.75 257	91.03 253	90.10 373	76.62 321	90.85 247	94.67 263	82.27 287	95.24 159	95.79 198	61.09 378	98.49 183	90.49 144	98.26 195	97.97 166

tpm		84.38 327	84.08 325	85.30 355	90.47 368	63.43 396	89.34 297	85.63 366	77.24 333	87.62 344	95.03 233	61.00 379	97.30 282	79.26 322	91.09 378	95.16 306

FE-MVS		89.06 259	88.29 267	91.36 240	94.78 274	79.57 271	96.77 28	90.99 324	84.87 254	92.96 236	96.29 173	60.69 380	98.80 138	80.18 309	97.11 260	95.71 290

EPMVS		81.17 354	80.37 356	83.58 369	85.58 401	65.08 391	90.31 267	71.34 405	77.31 332	85.80 356	91.30 328	59.38 381	92.70 374	79.99 311	82.34 398	92.96 363

tmp_tt		37.97 372	44.33 375	18.88 388	11.80 411	21.54 412	63.51 399	45.66 412	4.23 405	51.34 405	50.48 403	59.08 382	22.11 407	44.50 405	68.35 403	13.00 403

tpm2		81.46 350	80.35 357	84.80 359	89.90 374	65.14 390	90.44 260	85.36 369	65.82 392	82.05 386	92.44 311	57.94 383	96.69 311	70.71 378	88.49 386	92.56 367

ET-MVSNet_ETH3D		86.15 313	84.27 324	91.79 223	93.04 316	81.28 240	87.17 335	86.14 359	79.57 311	83.65 373	88.66 361	57.10 384	98.18 213	87.74 217	95.40 306	95.90 283

CHOSEN 280x420		80.04 362	77.97 369	86.23 349	90.13 372	74.53 339	72.87 396	89.59 333	66.38 389	76.29 399	85.32 386	56.96 385	95.36 345	69.49 382	94.72 325	88.79 386

JIA-IIPM		85.08 321	83.04 333	91.19 250	87.56 391	86.14 169	89.40 296	84.44 378	88.98 174	82.20 384	97.95 53	56.82 386	96.15 326	76.55 343	83.45 395	91.30 377

DeepMVS_CX				53.83 387	70.38 409	64.56 393		48.52 411	33.01 403	65.50 404	74.21 402	56.19 387	46.64 406	38.45 406	70.07 402	50.30 402

dp		79.28 365	78.62 365	81.24 377	85.97 400	56.45 404	86.91 340	85.26 372	72.97 361	81.45 391	89.17 360	56.01 388	95.45 343	73.19 363	76.68 401	91.82 375

test_method		50.44 371	48.94 374	54.93 386	39.68 410	12.38 413	28.59 401	90.09 331	6.82 404	41.10 406	78.41 399	54.41 389	70.69 405	50.12 403	51.26 405	81.72 399

thisisatest0515		84.72 324	82.99 334	89.90 289	92.96 319	75.33 334	84.36 376	83.42 381	77.37 331	88.27 333	86.65 375	53.94 390	98.72 151	82.56 283	97.40 251	95.67 293

tttt0517		89.81 246	88.90 255	92.55 201	97.00 148	79.73 268	95.03 102	83.65 380	89.88 156	95.30 153	94.79 243	53.64 391	99.39 49	91.99 108	98.79 142	98.54 119

thisisatest0530		88.69 274	87.52 285	92.20 209	96.33 195	79.36 275	92.81 177	84.01 379	86.44 219	93.67 209	92.68 306	53.62 392	99.25 75	89.65 174	98.45 177	98.00 159

FMVSNet5		87.82 287	86.56 304	91.62 231	92.31 330	79.81 266	93.49 157	94.81 258	83.26 270	91.36 276	96.93 129	52.77 393	97.49 272	76.07 346	98.03 217	97.55 205

pmmvs3		80.83 356	78.96 364	86.45 344	87.23 394	77.48 307	84.87 370	82.31 384	63.83 395	85.03 362	89.50 354	49.66 394	93.10 371	73.12 364	95.10 314	88.78 387

iter_conf05		88.94 266	88.09 277	91.50 236	92.74 322	76.97 316	92.80 178	95.92 218	82.82 280	93.65 210	95.37 223	49.41 395	99.13 88	90.82 136	99.28 79	98.40 129

IB-MVS	77.21 19	83.11 336	81.05 348	89.29 300	91.15 359	75.85 329	85.66 364	86.00 361	79.70 309	82.02 387	86.61 376	48.26 396	98.39 191	77.84 330	92.22 369	93.63 352
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		83.56 334	82.45 338	86.91 338	92.92 320	67.29 376	86.33 355	88.07 345	86.22 223	84.26 369	85.76 382	48.15 397	97.17 289	76.27 345	94.08 343	96.27 265

testing99		82.94 339	81.72 342	86.59 341	92.55 326	66.53 382	86.08 359	85.70 364	85.47 243	83.95 371	85.70 383	45.87 398	97.07 295	76.58 342	93.56 350	96.17 271

testing11		81.98 348	80.52 355	86.38 347	92.69 323	67.13 377	85.79 362	84.80 375	82.16 289	81.19 392	85.41 385	45.24 399	96.88 305	74.14 357	93.24 355	95.14 308

gg-mvs-nofinetune		82.10 347	81.02 349	85.34 354	87.46 393	71.04 362	94.74 110	67.56 406	96.44 23	79.43 396	98.99 6	45.24 399	96.15 326	67.18 387	92.17 370	88.85 385

GG-mvs-BLEND				83.24 371	85.06 403	71.03 363	94.99 105	65.55 407		74.09 401	75.51 401	44.57 401	94.46 358	59.57 398	87.54 388	84.24 394

TESTMET0.1,1		79.09 366	78.04 368	82.25 373	87.52 392	64.03 395	83.08 382	80.62 393	70.28 377	80.16 394	83.22 393	44.13 402	90.56 383	79.95 312	93.36 352	92.15 370

UWE-MVS		80.29 361	79.10 362	83.87 367	91.97 344	59.56 401	86.50 354	77.43 402	75.40 344	87.79 341	88.10 367	44.08 403	96.90 304	64.23 391	96.36 285	95.14 308

test-mter		81.21 353	80.01 360	84.79 360	89.68 377	66.86 380	83.08 382	84.52 376	73.85 354	82.85 380	84.78 388	43.66 404	93.49 368	82.85 279	94.86 320	94.03 341

KD-MVS_2432*1600		82.17 345	80.75 352	86.42 345	82.04 407	70.09 368	81.75 387	90.80 327	82.56 282	90.37 295	89.30 356	42.90 405	96.11 328	74.47 354	92.55 366	93.06 360

miper_refine_blended		82.17 345	80.75 352	86.42 345	82.04 407	70.09 368	81.75 387	90.80 327	82.56 282	90.37 295	89.30 356	42.90 405	96.11 328	74.47 354	92.55 366	93.06 360

test2506		85.42 318	84.57 321	87.96 325	97.81 102	66.53 382	96.14 58	56.35 409	89.04 172	93.55 213	98.10 42	42.88 407	98.68 162	88.09 209	99.18 94	98.67 104

ETVMVS		79.85 363	77.94 370	85.59 351	92.97 318	66.20 385	86.13 358	80.99 391	81.41 294	83.52 376	83.89 391	41.81 408	94.98 354	56.47 400	94.25 336	95.61 298

testing222		80.54 359	78.53 366	86.58 342	92.54 328	68.60 374	86.24 356	82.72 383	83.78 267	82.68 382	84.24 390	39.25 409	95.94 333	60.25 396	95.09 315	95.20 304

myMVS_eth3d		79.62 364	78.26 367	83.72 368	91.71 350	61.25 399	85.89 360	81.49 387	81.03 297	85.13 360	81.64 396	32.12 410	95.00 351	71.17 377	94.12 340	94.91 320

testing3		83.66 332	82.52 337	87.08 334	95.84 234	65.84 387	89.80 284	77.17 403	88.17 192	90.84 286	88.63 362	30.95 411	98.11 218	84.05 271	97.19 257	97.28 224

test123		9.49 374	12.01 377	1.91 389	2.87 412	1.30 414	82.38 385	1.34 414	1.36 407	2.84 408	6.56 406	2.45 412	0.97 408	2.73 407	5.56 406	3.47 404

testmvs		9.02 375	11.42 378	1.81 390	2.77 413	1.13 415	79.44 392	1.90 413	1.18 408	2.65 409	6.80 405	1.95 413	0.87 409	2.62 408	3.45 407	3.44 405

test_blank		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uanet_test		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

DCPMVS		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

sosnet-low-res		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

sosnet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uncertanet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

Regformer		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

ab-mvs-re		7.56 376	10.08 380	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	90.69 339	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uanet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

WAC-MVS						61.25 399								74.55 353

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		96.87 168					99.41 39	94.06 44	99.30 71	98.72 96

No_MVS				95.90 65	96.54 178	89.57 88		96.87 168					99.41 39	94.06 44	99.30 71	98.72 96

eth-test2					0.00 414

eth-test					0.00 414

IU-MVS					98.51 50	86.66 154		96.83 171	72.74 362	95.83 123				93.00 86	99.29 74	98.64 111

save fliter					97.46 129	88.05 124	92.04 213	97.08 151	87.63 205

test_0728_SECOND				94.88 104	98.55 45	86.72 151	95.20 95	98.22 37					99.38 55	93.44 67	99.31 69	98.53 120

GSMVS																94.75 326

test_part2					98.21 74	89.41 93				96.72 81

MTGPA								97.62 106

MTMP							94.82 108	54.62 410

gm-plane-assit					87.08 396	59.33 402			71.22 368		83.58 392		97.20 286	73.95 358

test9_res														88.16 207	98.40 179	97.83 181

agg_prior2														87.06 229	98.36 188	97.98 163

agg_prior					96.20 207	88.89 106		96.88 167		90.21 298			98.78 142

test_prior4						89.91 82	90.74 251

test_prior				94.61 117	95.95 228	87.23 137		97.36 129					98.68 162			97.93 169

旧先验2							90.00 277		68.65 383	92.71 244			96.52 314	85.15 257

新几何2							90.02 276

无先验							89.94 278	95.75 223	70.81 373				98.59 173	81.17 301		94.81 322

原ACMM2							89.34 297

testdata2													98.03 223	80.24 308

testdata1							88.96 306		88.44 187

plane_prior7					97.71 111	88.68 109

plane_prior5								97.81 92					98.95 114	89.26 184	98.51 173	98.60 116

plane_prior4											95.59 208

plane_prior3						88.43 119			90.35 150	93.31 218

plane_prior2							94.56 119		91.74 115

plane_prior1					97.38 131

plane_prior						88.12 122	93.01 171		88.98 174						98.06 214

n2								0.00 415

nn								0.00 415

door-mid								92.13 313

test11								96.65 183

door								91.26 322

HQP5-MVS						84.89 191

HQP-NCC					96.36 190		91.37 235		87.16 211	88.81 320

ACMP_Plane					96.36 190		91.37 235		87.16 211	88.81 320

BP-MVS														86.55 238

HQP4-MVS										88.81 320			98.61 169			98.15 146

HQP3-MVS								97.31 133							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