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		99.86 1	99.86 1	99.87 1	99.99 1	99.77 1	99.77 1	99.80 1	99.97 1	99.97 1	99.95 1	99.74 1	99.98 1	99.56 1	100.00 1	99.85 3

pmmvs6		99.07 5	99.24 5	98.56 46	99.81 2	96.38 57	98.87 8	99.30 9	99.01 16	99.63 10	99.66 4	99.27 2	99.68 103	97.75 29	99.89 21	99.62 24

test_normal		99.15 3	99.48 2	98.16 71	99.77 3	95.00 102	99.49 3	99.33 7	98.90 18	99.76 2	99.75 2	99.16 3	99.73 65	99.16 3	99.98 2	99.74 15

UniMVSNet_ETH3D		99.12 4	99.28 4	98.65 40	99.77 3	96.34 59	99.18 6	99.20 14	99.67 2	99.73 4	99.65 5	99.15 4	99.86 20	97.22 43	99.92 13	99.77 8

XVG-OURS-SEG-HR		97.38 93	97.07 105	98.30 64	99.01 87	97.41 31	94.66 220	99.02 48	95.20 143	98.15 93	97.52 167	98.83 5	98.43 302	94.87 130	96.41 294	99.07 140

ACMH	93.61 9	98.44 23	98.76 14	97.51 112	99.43 33	93.54 156	98.23 33	99.05 39	97.40 68	99.37 19	99.08 35	98.79 6	99.47 167	97.74 30	99.71 49	99.50 42
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mvs_tets		98.90 6	98.94 7	98.75 30	99.69 9	96.48 55	98.54 19	99.22 11	96.23 100	99.71 5	99.48 8	98.77 7	99.93 2	98.89 4	99.95 6	99.84 5

LTVRE_ROB	96.88 1	99.18 2	99.34 3	98.72 35	99.71 8	96.99 40	99.69 2	99.57 3	99.02 15	99.62 11	99.36 15	98.53 8	99.52 155	98.58 13	99.95 6	99.66 21
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
TransMVSNet (Re)		98.38 26	98.67 18	97.51 112	99.51 23	93.39 160	98.20 38	98.87 79	98.23 35	99.48 13	99.27 20	98.47 9	99.55 147	96.52 62	99.53 91	99.60 25

pm-mvs1		98.47 22	98.67 18	97.86 90	99.52 22	94.58 117	98.28 30	99.00 56	97.57 58	99.27 24	99.22 23	98.32 10	99.50 160	97.09 50	99.75 41	99.50 42

jajsoiax		98.77 10	98.79 13	98.74 32	99.66 11	96.48 55	98.45 24	99.12 26	95.83 122	99.67 7	99.37 13	98.25 11	99.92 4	98.77 6	99.94 9	99.82 6

ACMH+	93.58 10	98.23 33	98.31 30	97.98 84	99.39 38	95.22 96	97.55 73	99.20 14	98.21 36	99.25 25	98.51 71	98.21 12	99.40 191	94.79 135	99.72 46	99.32 91

HPM-MVS_fast		98.32 28	98.13 34	98.88 22	99.54 20	97.48 27	98.35 27	99.03 46	95.88 117	97.88 123	98.22 101	98.15 13	99.74 61	96.50 64	99.62 62	99.42 74

wuyk23d		93.25 250	95.20 178	87.40 317	96.07 291	95.38 89	97.04 96	94.97 277	95.33 139	99.70 6	98.11 110	98.14 14	91.94 332	77.76 324	99.68 55	74.89 331

ACMM	93.33 11	98.05 40	97.79 50	98.85 23	99.15 67	97.55 23	96.68 112	98.83 92	95.21 142	98.36 72	98.13 107	98.13 15	99.62 125	96.04 77	99.54 88	99.39 80
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HPM-MVS		98.11 38	97.83 48	98.92 20	99.42 35	97.46 28	98.57 16	99.05 39	95.43 137	97.41 146	97.50 169	97.98 16	99.79 37	95.58 100	99.57 78	99.50 42
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
testgi		96.07 155	96.50 138	94.80 246	99.26 47	87.69 261	95.96 150	98.58 141	95.08 149	98.02 109	96.25 241	97.92 17	97.60 322	88.68 269	98.74 217	99.11 133

LPG-MVS_test		97.94 50	97.67 60	98.74 32	99.15 67	97.02 38	97.09 94	99.02 48	95.15 146	98.34 74	98.23 98	97.91 18	99.70 90	94.41 148	99.73 43	99.50 42

LGP-MVS_train				98.74 32	99.15 67	97.02 38		99.02 48	95.15 146	98.34 74	98.23 98	97.91 18	99.70 90	94.41 148	99.73 43	99.50 42

abl_6		98.42 24	98.19 33	99.09 3	99.16 64	98.10 5	97.73 64	99.11 27	97.76 47	98.62 49	98.27 96	97.88 20	99.80 36	95.67 91	99.50 100	99.38 82

SD-MVS		97.37 94	97.70 57	96.35 186	98.14 171	95.13 99	96.54 115	98.92 69	95.94 113	99.19 28	98.08 112	97.74 21	95.06 330	95.24 114	99.54 88	98.87 173
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
DeepC-MVS	95.41 4	97.82 63	97.70 57	98.16 71	98.78 100	95.72 76	96.23 133	99.02 48	93.92 188	98.62 49	98.99 38	97.69 22	99.62 125	96.18 72	99.87 23	99.15 121
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
nrg030		98.54 19	98.62 22	98.32 61	99.22 56	95.66 80	97.90 53	99.08 34	98.31 32	99.02 32	98.74 54	97.68 23	99.61 132	97.77 28	99.85 26	99.70 19

ANet_high		98.31 29	98.94 7	96.41 185	99.33 43	89.64 222	97.92 52	99.56 4	99.27 6	99.66 9	99.50 7	97.67 24	99.83 27	97.55 34	99.98 2	99.77 8

canonicalmvs		97.23 103	97.21 97	97.30 133	97.65 226	94.39 122	97.84 56	99.05 39	97.42 64	96.68 178	93.85 293	97.63 25	99.33 213	96.29 69	98.47 236	98.18 231

TranMVSNet+NR-MVSNet		98.33 27	98.30 32	98.43 53	99.07 81	95.87 72	96.73 110	99.05 39	98.67 23	98.84 38	98.45 75	97.58 26	99.88 18	96.45 66	99.86 24	99.54 35

cdsmvs_eth3d_5k		24.22 308	32.30 310	0.00 323	0.00 340	0.00 341	0.00 334	98.10 192	0.00 336	0.00 338	95.06 274	97.54 27	0.00 339	0.00 336	0.00 336	0.00 335

ACMP	92.54 13	97.47 86	97.10 102	98.55 47	99.04 85	96.70 47	96.24 132	98.89 72	93.71 192	97.97 114	97.75 149	97.44 28	99.63 119	93.22 188	99.70 52	99.32 91
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_djsdf		98.73 12	98.74 17	98.69 37	99.63 13	96.30 61	98.67 12	99.02 48	96.50 89	99.32 21	99.44 11	97.43 29	99.92 4	98.73 8	99.95 6	99.86 2

TDRefinement		98.90 6	98.86 9	99.02 8	99.54 20	98.06 6	99.34 5	99.44 6	98.85 20	99.00 34	99.20 24	97.42 30	99.59 134	97.21 44	99.76 37	99.40 77

anonymousdsp		98.72 15	98.63 20	98.99 11	99.62 14	97.29 34	98.65 15	99.19 16	95.62 128	99.35 20	99.37 13	97.38 31	99.90 13	98.59 12	99.91 16	99.77 8

PS-CasMVS		98.73 12	98.85 11	98.39 56	99.55 18	95.47 88	98.49 21	99.13 25	99.22 8	99.22 27	98.96 41	97.35 32	99.92 4	97.79 27	99.93 11	99.79 7

COLMAP_ROB	94.48 6	98.25 32	98.11 35	98.64 41	99.21 59	97.35 32	97.96 49	99.16 18	98.34 31	98.78 41	98.52 70	97.32 33	99.45 174	94.08 163	99.67 56	99.13 125
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
EG-PatchMatch MVS		97.69 71	97.79 50	97.40 128	99.06 82	93.52 157	95.96 150	98.97 64	94.55 169	98.82 39	98.76 53	97.31 34	99.29 221	97.20 46	99.44 117	99.38 82

XXY-MVS		97.54 80	97.70 57	97.07 144	99.46 29	92.21 181	97.22 88	99.00 56	94.93 156	98.58 53	98.92 45	97.31 34	99.41 189	94.44 146	99.43 124	99.59 26

PEN-MVS		98.75 11	98.85 11	98.44 52	99.58 15	95.67 79	98.45 24	99.15 22	99.33 5	99.30 22	99.00 37	97.27 36	99.92 4	97.64 32	99.92 13	99.75 13

DTE-MVSNet		98.79 9	98.86 9	98.59 44	99.55 18	96.12 66	98.48 23	99.10 29	99.36 4	99.29 23	99.06 36	97.27 36	99.93 2	97.71 31	99.91 16	99.70 19

MP-MVS-pluss		97.69 71	97.36 85	98.70 36	99.50 26	96.84 43	95.38 179	98.99 59	92.45 222	98.11 96	98.31 85	97.25 38	99.77 46	96.60 58	99.62 62	99.48 53
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		97.89 56	97.63 68	98.67 38	99.35 42	96.84 43	96.36 124	98.79 99	95.07 150	97.88 123	98.35 81	97.24 39	99.72 70	96.05 76	99.58 75	99.45 63

Effi-MVS+		96.19 151	96.01 155	96.71 164	97.43 241	92.19 184	96.12 138	99.10 29	95.45 135	93.33 283	94.71 281	97.23 40	99.56 143	93.21 189	97.54 270	98.37 210

PGM-MVS		97.88 57	97.52 77	98.96 14	99.20 60	97.62 18	97.09 94	99.06 37	95.45 135	97.55 133	97.94 131	97.11 41	99.78 38	94.77 138	99.46 112	99.48 53

test_0728_THIRD									96.62 84	98.40 67	98.28 92	97.10 42	99.71 81	95.70 89	99.62 62	99.58 27

APD-MVS_3200maxsize		98.13 37	97.90 44	98.79 28	98.79 98	97.31 33	97.55 73	98.92 69	97.72 51	98.25 85	98.13 107	97.10 42	99.75 54	95.44 106	99.24 166	99.32 91

OPM-MVS		97.54 80	97.25 92	98.41 54	99.11 77	96.61 51	95.24 191	98.46 148	94.58 168	98.10 99	98.07 114	97.09 44	99.39 196	95.16 119	99.44 117	99.21 113

HFP-MVS		97.94 50	97.64 66	98.83 24	99.15 67	97.50 25	97.59 70	98.84 85	96.05 105	97.49 138	97.54 164	97.07 45	99.70 90	95.61 97	99.46 112	99.30 97

#test#		97.62 75	97.22 96	98.83 24	99.15 67	97.50 25	96.81 104	98.84 85	94.25 177	97.49 138	97.54 164	97.07 45	99.70 90	94.37 152	99.46 112	99.30 97

DVP-MVS		97.78 66	97.65 63	98.16 71	99.24 51	95.51 85	96.74 106	98.23 175	95.92 114	98.40 67	98.28 92	97.06 47	99.71 81	95.48 102	99.52 95	99.26 109

test0726					99.24 51	95.51 85	96.89 101	98.89 72	95.92 114	98.64 48	98.31 85	97.06 47

casdiffmvs		97.50 83	97.81 49	96.56 176	98.51 131	91.04 203	95.83 157	99.09 33	97.23 73	98.33 77	98.30 89	97.03 49	99.37 204	96.58 60	99.38 136	99.28 104

SteuartSystems-ACMMP		98.02 42	97.76 54	98.79 28	99.43 33	97.21 37	97.15 90	98.90 71	96.58 87	98.08 102	97.87 138	97.02 50	99.76 50	95.25 113	99.59 73	99.40 77
Skip Steuart: Steuart Systems R&D Blog.
APDe-MVS		98.14 35	98.03 40	98.47 51	98.72 105	96.04 68	98.07 45	99.10 29	95.96 111	98.59 52	98.69 58	96.94 51	99.81 30	96.64 57	99.58 75	99.57 31

GST-MVS		97.82 63	97.49 80	98.81 26	99.23 53	97.25 35	97.16 89	98.79 99	95.96 111	97.53 134	97.40 175	96.93 52	99.77 46	95.04 125	99.35 144	99.42 74

LCM-MVSNet-Re		97.33 97	97.33 87	97.32 132	98.13 174	93.79 147	96.99 99	99.65 2	96.74 82	99.47 14	98.93 44	96.91 53	99.84 25	90.11 247	99.06 187	98.32 217

VPA-MVSNet		98.27 30	98.46 25	97.70 99	99.06 82	93.80 146	97.76 60	99.00 56	98.40 29	99.07 31	98.98 39	96.89 54	99.75 54	97.19 47	99.79 34	99.55 34

ACMMP		98.05 40	97.75 55	98.93 19	99.23 53	97.60 19	98.09 44	98.96 65	95.75 125	97.91 119	98.06 117	96.89 54	99.76 50	95.32 110	99.57 78	99.43 73
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
PMVS	89.60 17	96.71 131	96.97 109	95.95 204	99.51 23	97.81 13	97.42 80	97.49 230	97.93 43	95.95 210	98.58 64	96.88 56	96.91 325	89.59 255	99.36 140	93.12 323
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
region2R		97.92 53	97.59 72	98.92 20	99.22 56	97.55 23	97.60 69	98.84 85	96.00 109	97.22 150	97.62 160	96.87 57	99.76 50	95.48 102	99.43 124	99.46 58

CP-MVS		97.92 53	97.56 75	98.99 11	98.99 88	97.82 12	97.93 51	98.96 65	96.11 104	96.89 170	97.45 173	96.85 58	99.78 38	95.19 115	99.63 61	99.38 82

DPE-MVS		97.64 73	97.35 86	98.50 48	98.85 95	96.18 63	95.21 193	98.99 59	95.84 121	98.78 41	98.08 112	96.84 59	99.81 30	93.98 170	99.57 78	99.52 39

test_0402		97.84 60	97.97 41	97.47 120	99.19 62	94.07 135	96.71 111	98.73 111	98.66 24	98.56 54	98.41 77	96.84 59	99.69 98	94.82 132	99.81 30	98.64 192

ACMMPR		97.95 48	97.62 70	98.94 16	99.20 60	97.56 22	97.59 70	98.83 92	96.05 105	97.46 144	97.63 159	96.77 61	99.76 50	95.61 97	99.46 112	99.49 50

Vis-MVSNet		98.27 30	98.34 29	98.07 77	99.33 43	95.21 98	98.04 46	99.46 5	97.32 70	97.82 129	99.11 32	96.75 62	99.86 20	97.84 24	99.36 140	99.15 121
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
Fast-Effi-MVS+		95.49 176	95.07 183	96.75 162	97.67 225	92.82 170	94.22 235	98.60 138	91.61 233	93.42 281	92.90 301	96.73 63	99.70 90	92.60 195	97.89 254	97.74 257

baseline		97.44 88	97.78 53	96.43 182	98.52 130	90.75 211	96.84 102	99.03 46	96.51 88	97.86 127	98.02 121	96.67 64	99.36 206	97.09 50	99.47 109	99.19 115

SR-MVS		98.00 44	97.66 61	99.01 9	98.77 101	97.93 7	97.38 81	98.83 92	97.32 70	98.06 104	97.85 139	96.65 65	99.77 46	95.00 128	99.11 178	99.32 91

tfpnnormal		97.72 69	97.97 41	96.94 150	99.26 47	92.23 180	97.83 57	98.45 149	98.25 34	99.13 30	98.66 60	96.65 65	99.69 98	93.92 172	99.62 62	98.91 164

DeepPCF-MVS	94.58 5	96.90 116	96.43 139	98.31 63	97.48 235	97.23 36	92.56 287	98.60 138	92.84 217	98.54 55	97.40 175	96.64 67	98.78 277	94.40 150	99.41 133	98.93 160

MVS_111021_LR		96.82 122	96.55 132	97.62 104	98.27 152	95.34 91	93.81 257	98.33 167	94.59 167	96.56 183	96.63 224	96.61 68	98.73 281	94.80 134	99.34 147	98.78 182

Gipuma		98.07 39	98.31 30	97.36 130	99.76 6	96.28 62	98.51 20	99.10 29	98.76 22	96.79 172	99.34 18	96.61 68	98.82 273	96.38 67	99.50 100	96.98 279
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MVS_111021_HR		96.73 128	96.54 134	97.27 134	98.35 145	93.66 153	93.42 267	98.36 163	94.74 160	96.58 181	96.76 218	96.54 70	98.99 258	94.87 130	99.27 164	99.15 121

SMA-MVS		97.48 85	97.11 101	98.60 43	98.83 96	96.67 48	96.74 106	98.73 111	91.61 233	98.48 60	98.36 80	96.53 71	99.68 103	95.17 117	99.54 88	99.45 63

v7n		98.73 12	98.99 6	97.95 85	99.64 12	94.20 132	98.67 12	99.14 24	99.08 10	99.42 16	99.23 22	96.53 71	99.91 12	99.27 2	99.93 11	99.73 16

mPP-MVS		97.91 55	97.53 76	99.04 6	99.22 56	97.87 11	97.74 62	98.78 103	96.04 107	97.10 157	97.73 152	96.53 71	99.78 38	95.16 119	99.50 100	99.46 58

XVS		97.96 45	97.63 68	98.94 16	99.15 67	97.66 16	97.77 58	98.83 92	97.42 64	96.32 195	97.64 158	96.49 74	99.72 70	95.66 93	99.37 137	99.45 63

X-MVStestdata		92.86 252	90.83 275	98.94 16	99.15 67	97.66 16	97.77 58	98.83 92	97.42 64	96.32 195	36.50 333	96.49 74	99.72 70	95.66 93	99.37 137	99.45 63

9.14			96.69 124		98.53 129		96.02 144	98.98 62	93.23 200	97.18 152	97.46 172	96.47 76	99.62 125	92.99 192	99.32 155

UA-Net		98.88 8	98.76 14	99.22 2	99.11 77	97.89 10	99.47 4	99.32 8	99.08 10	97.87 126	99.67 3	96.47 76	99.92 4	97.88 22	99.98 2	99.85 3

xiu_mvs_v1_base_debu		95.62 171	95.96 159	94.60 252	98.01 181	88.42 243	93.99 248	98.21 176	92.98 211	95.91 211	94.53 283	96.39 78	99.72 70	95.43 107	98.19 241	95.64 308

xiu_mvs_v1_base		95.62 171	95.96 159	94.60 252	98.01 181	88.42 243	93.99 248	98.21 176	92.98 211	95.91 211	94.53 283	96.39 78	99.72 70	95.43 107	98.19 241	95.64 308

xiu_mvs_v1_base_debi		95.62 171	95.96 159	94.60 252	98.01 181	88.42 243	93.99 248	98.21 176	92.98 211	95.91 211	94.53 283	96.39 78	99.72 70	95.43 107	98.19 241	95.64 308

EIA-MVS		96.13 154	95.90 162	96.82 158	97.76 216	93.89 141	95.40 177	98.95 67	95.87 118	95.58 224	91.00 321	96.36 81	99.72 70	93.36 182	98.83 210	96.85 286

testing_2		97.43 89	97.71 56	96.60 170	98.91 92	90.85 206	96.01 146	98.54 142	94.78 159	98.78 41	98.96 41	96.35 82	99.54 149	97.25 41	99.82 29	99.40 77

MP-MVS		97.64 73	97.18 98	99.00 10	99.32 45	97.77 14	97.49 76	98.73 111	96.27 97	95.59 223	97.75 149	96.30 83	99.78 38	93.70 178	99.48 107	99.45 63
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TinyColmap		96.00 160	96.34 142	94.96 239	97.90 191	87.91 254	94.13 243	98.49 147	94.41 171	98.16 91	97.76 146	96.29 84	98.68 288	90.52 240	99.42 127	98.30 220

Fast-Effi-MVS+-dtu		96.44 144	96.12 150	97.39 129	97.18 258	94.39 122	95.46 171	98.73 111	96.03 108	94.72 238	94.92 278	96.28 85	99.69 98	93.81 175	97.98 249	98.09 232

OMC-MVS		96.48 142	96.00 156	97.91 88	98.30 147	96.01 71	94.86 212	98.60 138	91.88 231	97.18 152	97.21 188	96.11 86	99.04 251	90.49 243	99.34 147	98.69 189

xiu_mvs_v2_base		94.22 222	94.63 201	92.99 285	97.32 252	84.84 293	92.12 295	97.84 208	91.96 228	94.17 251	93.43 294	96.07 87	99.71 81	91.27 216	97.48 273	94.42 317

CS-MVS		95.86 165	95.59 171	96.69 166	97.85 193	93.14 164	96.42 119	99.25 10	94.17 181	93.56 274	90.76 324	96.05 88	99.72 70	93.28 185	98.91 199	97.21 273

CSCG		97.40 92	97.30 88	97.69 101	98.95 90	94.83 107	97.28 84	98.99 59	96.35 96	98.13 95	95.95 256	95.99 89	99.66 113	94.36 155	99.73 43	98.59 197

PHI-MVS		96.96 112	96.53 135	98.25 68	97.48 235	96.50 54	96.76 105	98.85 82	93.52 195	96.19 204	96.85 209	95.94 90	99.42 180	93.79 176	99.43 124	98.83 176

TSAR-MVS + MP.		97.42 90	97.23 95	98.00 83	99.38 39	95.00 102	97.63 68	98.20 179	93.00 210	98.16 91	98.06 117	95.89 91	99.72 70	95.67 91	99.10 180	99.28 104
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
XVG-ACMP-BASELINE		97.58 78	97.28 91	98.49 49	99.16 64	96.90 42	96.39 121	98.98 62	95.05 151	98.06 104	98.02 121	95.86 92	99.56 143	94.37 152	99.64 60	99.00 148

AllTest		97.20 104	96.92 113	98.06 78	99.08 79	96.16 64	97.14 92	99.16 18	94.35 173	97.78 130	98.07 114	95.84 93	99.12 240	91.41 213	99.42 127	98.91 164

TestCases				98.06 78	99.08 79	96.16 64		99.16 18	94.35 173	97.78 130	98.07 114	95.84 93	99.12 240	91.41 213	99.42 127	98.91 164

APD-MVS		97.00 107	96.53 135	98.41 54	98.55 127	96.31 60	96.32 127	98.77 104	92.96 215	97.44 145	97.58 163	95.84 93	99.74 61	91.96 202	99.35 144	99.19 115
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
pcd_1.5k_mvsjas		7.98 311	10.65 313	0.00 323	0.00 340	0.00 341	0.00 334	0.00 342	0.00 336	0.00 338	0.00 338	95.82 96	0.00 339	0.00 336	0.00 336	0.00 335

PS-MVSNAJss		98.53 20	98.63 20	98.21 70	99.68 10	94.82 108	98.10 43	99.21 12	96.91 77	99.75 3	99.45 10	95.82 96	99.92 4	98.80 5	99.96 5	99.89 1

PS-MVSNAJ		94.10 229	94.47 209	93.00 284	97.35 245	84.88 292	91.86 299	97.84 208	91.96 228	94.17 251	92.50 308	95.82 96	99.71 81	91.27 216	97.48 273	94.40 318

3Dnovator	96.53 2	97.61 76	97.64 66	97.50 115	97.74 218	93.65 154	98.49 21	98.88 77	96.86 79	97.11 156	98.55 68	95.82 96	99.73 65	95.94 84	99.42 127	99.13 125

zzz-MVS		98.01 43	97.66 61	99.06 4	99.44 31	97.90 8	95.66 164	98.73 111	97.69 54	97.90 120	97.96 127	95.81 100	99.82 28	96.13 73	99.61 68	99.45 63

MTAPA		98.14 35	97.84 47	99.06 4	99.44 31	97.90 8	97.25 85	98.73 111	97.69 54	97.90 120	97.96 127	95.81 100	99.82 28	96.13 73	99.61 68	99.45 63

DP-MVS		97.87 58	97.89 45	97.81 93	98.62 119	94.82 108	97.13 93	98.79 99	98.98 17	98.74 45	98.49 72	95.80 102	99.49 161	95.04 125	99.44 117	99.11 133

Anonymous20240529		97.96 45	98.04 39	97.71 97	98.69 112	94.28 129	97.86 55	98.31 170	98.79 21	99.23 26	98.86 48	95.76 103	99.61 132	95.49 101	99.36 140	99.23 111

LS3D		97.77 67	97.50 79	98.57 45	96.24 282	97.58 21	98.45 24	98.85 82	98.58 26	97.51 136	97.94 131	95.74 104	99.63 119	95.19 115	98.97 192	98.51 202

ETV-MVS		96.04 157	95.77 166	96.85 156	97.80 205	92.98 168	96.12 138	99.16 18	94.65 163	93.77 264	91.69 316	95.68 105	99.67 108	94.18 160	98.85 208	97.91 250

CNVR-MVS		96.92 114	96.55 132	98.03 82	98.00 184	95.54 83	94.87 211	98.17 185	94.60 165	96.38 192	97.05 197	95.67 106	99.36 206	95.12 123	99.08 182	99.19 115

CLD-MVS		95.47 179	95.07 183	96.69 166	98.27 152	92.53 174	91.36 304	98.67 128	91.22 237	95.78 217	94.12 291	95.65 107	98.98 260	90.81 226	99.72 46	98.57 198
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Anonymous20231211		98.55 18	98.76 14	97.94 86	98.79 98	94.37 124	98.84 9	99.15 22	99.37 3	99.67 7	99.43 12	95.61 108	99.72 70	98.12 17	99.86 24	99.73 16

Regformer-2		97.41 91	97.24 94	97.93 87	97.21 256	94.72 111	94.85 213	98.27 171	97.74 48	98.11 96	97.50 169	95.58 109	99.69 98	96.57 61	99.31 157	99.37 87

ITE_SJBPF				97.85 91	98.64 114	96.66 49		98.51 146	95.63 127	97.22 150	97.30 185	95.52 110	98.55 297	90.97 221	98.90 200	98.34 216

Regformer-4		97.53 82	97.47 82	97.71 97	97.35 245	93.91 140	95.26 189	98.14 189	97.97 42	98.34 74	97.89 136	95.49 111	99.71 81	97.41 38	99.42 127	99.51 41

DeepC-MVS_fast	94.34 7	96.74 126	96.51 137	97.44 124	97.69 221	94.15 133	96.02 144	98.43 152	93.17 206	97.30 148	97.38 181	95.48 112	99.28 223	93.74 177	99.34 147	98.88 171
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
WR-MVS_H		98.65 16	98.62 22	98.75 30	99.51 23	96.61 51	98.55 18	99.17 17	99.05 13	99.17 29	98.79 50	95.47 113	99.89 16	97.95 21	99.91 16	99.75 13

FMVSNet1		97.95 48	98.08 36	97.56 107	99.14 75	93.67 150	98.23 33	98.66 130	97.41 67	99.00 34	99.19 25	95.47 113	99.73 65	95.83 87	99.76 37	99.30 97

MIMVSNet1		98.51 21	98.45 27	98.67 38	99.72 7	96.71 46	98.76 10	98.89 72	98.49 27	99.38 18	99.14 31	95.44 115	99.84 25	96.47 65	99.80 33	99.47 56

CP-MVSNet		98.42 24	98.46 25	98.30 64	99.46 29	95.22 96	98.27 32	98.84 85	99.05 13	99.01 33	98.65 62	95.37 116	99.90 13	97.57 33	99.91 16	99.77 8

Regformer-1		97.27 100	97.16 99	97.61 105	97.21 256	93.86 143	94.85 213	98.04 200	97.62 57	98.03 108	97.50 169	95.34 117	99.63 119	96.52 62	99.31 157	99.35 89

segment_acmp												95.34 117

CDPH-MVS		95.45 182	94.65 200	97.84 92	98.28 150	94.96 104	93.73 259	98.33 167	85.03 294	95.44 225	96.60 225	95.31 119	99.44 177	90.01 249	99.13 174	99.11 133

3Dnovator+	96.13 3	97.73 68	97.59 72	98.15 74	98.11 175	95.60 81	98.04 46	98.70 121	98.13 38	96.93 168	98.45 75	95.30 120	99.62 125	95.64 95	98.96 193	99.24 110

MVS_Test		96.27 148	96.79 121	94.73 249	96.94 267	86.63 275	96.18 135	98.33 167	94.94 154	96.07 207	98.28 92	95.25 121	99.26 225	97.21 44	97.90 253	98.30 220

XVG-OURS		97.12 105	96.74 122	98.26 66	98.99 88	97.45 29	93.82 255	99.05 39	95.19 144	98.32 78	97.70 154	95.22 122	98.41 303	94.27 157	98.13 244	98.93 160

MCST-MVS		96.24 149	95.80 164	97.56 107	98.75 102	94.13 134	94.66 220	98.17 185	90.17 245	96.21 203	96.10 250	95.14 123	99.43 179	94.13 162	98.85 208	99.13 125

EI-MVSNet-Vis-set		97.32 98	97.39 84	97.11 141	97.36 244	92.08 187	95.34 182	97.65 222	97.74 48	98.29 83	98.11 110	95.05 124	99.68 103	97.50 36	99.50 100	99.56 32

Regformer-3		97.25 102	97.29 89	97.11 141	97.35 245	92.32 178	95.26 189	97.62 227	97.67 56	98.17 90	97.89 136	95.05 124	99.56 143	97.16 48	99.42 127	99.46 58

EI-MVSNet-UG-set		97.32 98	97.40 83	97.09 143	97.34 249	92.01 189	95.33 183	97.65 222	97.74 48	98.30 82	98.14 106	95.04 126	99.69 98	97.55 34	99.52 95	99.58 27

DELS-MVS		96.17 152	96.23 145	95.99 200	97.55 233	90.04 218	92.38 292	98.52 144	94.13 182	96.55 185	97.06 196	94.99 127	99.58 136	95.62 96	99.28 162	98.37 210
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
ab-mvs		96.59 137	96.59 128	96.60 170	98.64 114	92.21 181	98.35 27	97.67 218	94.45 170	96.99 163	98.79 50	94.96 128	99.49 161	90.39 244	99.07 184	98.08 233

MSLP-MVS++		96.42 146	96.71 123	95.57 217	97.82 200	90.56 215	95.71 159	98.84 85	94.72 161	96.71 177	97.39 179	94.91 129	98.10 317	95.28 111	99.02 189	98.05 242

QAPM		95.88 164	95.57 172	96.80 159	97.90 191	91.84 193	98.18 40	98.73 111	88.41 261	96.42 190	98.13 107	94.73 130	99.75 54	88.72 267	98.94 197	98.81 178

RPSCF		97.87 58	97.51 78	98.95 15	99.15 67	98.43 3	97.56 72	99.06 37	96.19 101	98.48 60	98.70 57	94.72 131	99.24 228	94.37 152	99.33 153	99.17 118

DU-MVS		97.79 65	97.60 71	98.36 58	98.73 103	95.78 74	95.65 166	98.87 79	97.57 58	98.31 80	97.83 140	94.69 132	99.85 22	97.02 53	99.71 49	99.46 58

Baseline_NR-MVSNet		97.72 69	97.79 50	97.50 115	99.56 16	93.29 161	95.44 172	98.86 81	98.20 37	98.37 70	99.24 21	94.69 132	99.55 147	95.98 83	99.79 34	99.65 22

TEST9					97.84 198	95.23 93	93.62 261	98.39 159	86.81 277	93.78 262	95.99 251	94.68 134	99.52 155

UniMVSNet (Re)		97.83 61	97.65 63	98.35 60	98.80 97	95.86 73	95.92 153	99.04 45	97.51 61	98.22 87	97.81 144	94.68 134	99.78 38	97.14 49	99.75 41	99.41 76

agg_prior1		95.39 184	94.60 203	97.75 95	97.80 205	94.96 104	93.39 269	98.36 163	87.20 273	93.49 276	95.97 254	94.65 136	99.53 151	91.69 211	98.86 206	98.77 183

UniMVSNet_NR-MVSNet		97.83 61	97.65 63	98.37 57	98.72 105	95.78 74	95.66 164	99.02 48	98.11 39	98.31 80	97.69 156	94.65 136	99.85 22	97.02 53	99.71 49	99.48 53

VPNet		97.26 101	97.49 80	96.59 172	99.47 28	90.58 213	96.27 128	98.53 143	97.77 46	98.46 63	98.41 77	94.59 138	99.68 103	94.61 141	99.29 161	99.52 39

train_agg		95.46 180	94.66 199	97.88 89	97.84 198	95.23 93	93.62 261	98.39 159	87.04 275	93.78 262	95.99 251	94.58 139	99.52 155	91.76 209	98.90 200	98.89 168

test_8					97.81 201	95.07 101	93.54 264	98.38 161	87.04 275	93.71 266	95.96 255	94.58 139	99.52 155

API-MVS		95.09 196	95.01 187	95.31 229	96.61 273	94.02 137	96.83 103	97.18 239	95.60 129	95.79 216	94.33 288	94.54 141	98.37 308	85.70 295	98.52 232	93.52 320

Test By Simon												94.51 142

MSDG		95.33 186	95.13 181	95.94 206	97.40 243	91.85 192	91.02 309	98.37 162	95.30 140	96.31 197	95.99 251	94.51 142	98.38 306	89.59 255	97.65 267	97.60 264

save filter2										96.55 185	97.15 189	94.49 144	99.62 125	94.39 151	99.40 134	99.14 124

TSAR-MVS + GP.		96.47 143	96.12 150	97.49 118	97.74 218	95.23 93	94.15 240	96.90 249	93.26 199	98.04 107	96.70 221	94.41 145	98.89 268	94.77 138	99.14 172	98.37 210

NR-MVSNet		97.96 45	97.86 46	98.26 66	98.73 103	95.54 83	98.14 41	98.73 111	97.79 45	99.42 16	97.83 140	94.40 146	99.78 38	95.91 86	99.76 37	99.46 58

AdaColmap		95.11 194	94.62 202	96.58 173	97.33 251	94.45 121	94.92 209	98.08 195	93.15 207	93.98 260	95.53 267	94.34 147	99.10 245	85.69 296	98.61 228	96.20 301

FC-MVSNet-test		98.16 34	98.37 28	97.56 107	99.49 27	93.10 166	98.35 27	99.21 12	98.43 28	98.89 37	98.83 49	94.30 148	99.81 30	97.87 23	99.91 16	99.77 8

Effi-MVS+-dtu		96.81 123	96.09 152	98.99 11	96.90 269	98.69 2	96.42 119	98.09 193	95.86 119	95.15 231	95.54 266	94.26 149	99.81 30	94.06 164	98.51 234	98.47 203

mvs-test1		96.20 150	95.50 174	98.32 61	96.90 269	98.16 4	95.07 201	98.09 193	95.86 119	93.63 269	94.32 289	94.26 149	99.71 81	94.06 164	97.27 281	97.07 276

ambc				96.56 176	98.23 158	91.68 196	97.88 54	98.13 190		98.42 66	98.56 67	94.22 151	99.04 251	94.05 167	99.35 144	98.95 154

test20.03		96.58 138	96.61 127	96.48 180	98.49 134	91.72 195	95.68 163	97.69 217	96.81 80	98.27 84	97.92 134	94.18 152	98.71 283	90.78 228	99.66 58	99.00 148

HPM-MVS++		96.99 108	96.38 140	98.81 26	98.64 114	97.59 20	95.97 149	98.20 179	95.51 133	95.06 232	96.53 229	94.10 153	99.70 90	94.29 156	99.15 171	99.13 125

testtj		96.69 132	96.13 149	98.36 58	98.46 139	96.02 70	96.44 118	98.70 121	94.26 176	96.79 172	97.13 191	94.07 154	99.75 54	90.53 239	98.80 211	99.31 96

PM-MVS		97.36 96	97.10 102	98.14 75	98.91 92	96.77 45	96.20 134	98.63 136	93.82 189	98.54 55	98.33 83	93.98 155	99.05 250	95.99 82	99.45 116	98.61 196

OpenMVS	94.22 8	95.48 178	95.20 178	96.32 188	97.16 259	91.96 190	97.74 62	98.84 85	87.26 272	94.36 248	98.01 123	93.95 156	99.67 108	90.70 234	98.75 216	97.35 272

v8		97.60 77	98.06 38	96.23 191	98.71 108	89.44 226	97.43 79	98.82 97	97.29 72	98.74 45	99.10 33	93.86 157	99.68 103	98.61 11	99.94 9	99.56 32

diffmvs		96.04 157	96.23 145	95.46 225	97.35 245	88.03 253	93.42 267	99.08 34	94.09 184	96.66 179	96.93 205	93.85 158	99.29 221	96.01 81	98.67 222	99.06 142

NCCC		96.52 140	95.99 157	98.10 76	97.81 201	95.68 78	95.00 207	98.20 179	95.39 138	95.40 227	96.36 238	93.81 159	99.45 174	93.55 181	98.42 237	99.17 118

TAPA-MVS	93.32 12	94.93 200	94.23 216	97.04 146	98.18 164	94.51 118	95.22 192	98.73 111	81.22 311	96.25 201	95.95 256	93.80 160	98.98 260	89.89 251	98.87 204	97.62 262
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
FIs		97.93 52	98.07 37	97.48 119	99.38 39	92.95 169	98.03 48	99.11 27	98.04 41	98.62 49	98.66 60	93.75 161	99.78 38	97.23 42	99.84 27	99.73 16

OurMVSNet-221017-0		98.61 17	98.61 24	98.63 42	99.77 3	96.35 58	99.17 7	99.05 39	98.05 40	99.61 12	99.52 6	93.72 162	99.88 18	98.72 10	99.88 22	99.65 22

test_prior3		95.91 162	95.39 176	97.46 121	97.79 210	94.26 130	93.33 272	98.42 155	94.21 178	94.02 257	96.25 241	93.64 163	99.34 210	91.90 203	98.96 193	98.79 180

test_prior2							93.33 272		94.21 178	94.02 257	96.25 241	93.64 163		91.90 203	98.96 193

旧先验1					97.80 205	93.87 142		97.75 213			97.04 198	93.57 165			98.68 221	98.72 188

v10		97.55 79	97.97 41	96.31 189	98.60 121	89.64 222	97.44 77	99.02 48	96.60 85	98.72 47	99.16 30	93.48 166	99.72 70	98.76 7	99.92 13	99.58 27

v148		96.58 138	96.97 109	95.42 226	98.63 118	87.57 262	95.09 198	97.90 204	95.91 116	98.24 86	97.96 127	93.42 167	99.39 196	96.04 77	99.52 95	99.29 103

V42		97.04 106	97.16 99	96.68 168	98.59 123	91.05 202	96.33 126	98.36 163	94.60 165	97.99 110	98.30 89	93.32 168	99.62 125	97.40 39	99.53 91	99.38 82

new-patchmatchnet		95.67 170	96.58 129	92.94 287	97.48 235	80.21 314	92.96 278	98.19 184	94.83 157	98.82 39	98.79 50	93.31 169	99.51 159	95.83 87	99.04 188	99.12 130

test12				97.46 121	97.61 229	94.07 135		97.78 212		93.57 273		93.31 169	99.42 180		98.78 213	98.89 168

UGNet		96.81 123	96.56 131	97.58 106	96.64 272	93.84 145	97.75 61	97.12 242	96.47 92	93.62 270	98.88 47	93.22 171	99.53 151	95.61 97	99.69 53	99.36 88
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
pmmvs-eth3d		96.49 141	96.18 148	97.42 126	98.25 155	94.29 126	94.77 217	98.07 197	89.81 248	97.97 114	98.33 83	93.11 172	99.08 247	95.46 105	99.84 27	98.89 168

v1144		96.84 118	97.08 104	96.13 197	98.42 140	89.28 229	95.41 176	98.67 128	94.21 178	97.97 114	98.31 85	93.06 173	99.65 114	98.06 19	99.62 62	99.45 63

PVSNet_BlendedMVS		95.02 199	94.93 190	95.27 230	97.79 210	87.40 266	94.14 242	98.68 125	88.94 256	94.51 244	98.01 123	93.04 174	99.30 218	89.77 253	99.49 104	99.11 133

PVSNet_Blended		93.96 233	93.65 231	94.91 240	97.79 210	87.40 266	91.43 303	98.68 125	84.50 299	94.51 244	94.48 286	93.04 174	99.30 218	89.77 253	98.61 228	98.02 245

mvs_anonymous		95.36 185	96.07 154	93.21 279	96.29 280	81.56 309	94.60 222	97.66 220	93.30 198	96.95 167	98.91 46	93.03 176	99.38 201	96.60 58	97.30 280	98.69 189

v1192		96.83 121	97.06 106	96.15 196	98.28 150	89.29 228	95.36 180	98.77 104	93.73 191	98.11 96	98.34 82	93.02 177	99.67 108	98.35 15	99.58 75	99.50 42

F-COLMAP		95.30 188	94.38 213	98.05 81	98.64 114	96.04 68	95.61 169	98.66 130	89.00 255	93.22 284	96.40 237	92.90 178	99.35 209	87.45 286	97.53 271	98.77 183

WR-MVS		96.90 116	96.81 118	97.16 138	98.56 126	92.20 183	94.33 228	98.12 191	97.34 69	98.20 88	97.33 184	92.81 179	99.75 54	94.79 135	99.81 30	99.54 35

v1240		96.74 126	97.02 108	95.91 207	98.18 164	88.52 242	95.39 178	98.88 77	93.15 207	98.46 63	98.40 79	92.80 180	99.71 81	98.45 14	99.49 104	99.49 50

MVE	73.61 22	86.48 305	85.92 306	88.18 315	96.23 284	85.28 286	81.78 333	75.79 334	86.01 282	82.53 332	91.88 313	92.74 181	87.47 334	71.42 330	94.86 308	91.78 325
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DP-MVS Recon		95.55 174	95.13 181	96.80 159	98.51 131	93.99 139	94.60 222	98.69 123	90.20 244	95.78 217	96.21 244	92.73 182	98.98 260	90.58 238	98.86 206	97.42 269

CANet		95.86 165	95.65 169	96.49 179	96.41 278	90.82 208	94.36 227	98.41 157	94.94 154	92.62 296	96.73 219	92.68 183	99.71 81	95.12 123	99.60 71	98.94 156

v1921920		96.72 129	96.96 111	95.99 200	98.21 159	88.79 239	95.42 174	98.79 99	93.22 201	98.19 89	98.26 97	92.68 183	99.70 90	98.34 16	99.55 86	99.49 50

BH-untuned		94.69 208	94.75 198	94.52 257	97.95 189	87.53 263	94.07 245	97.01 245	93.99 186	97.10 157	95.65 262	92.65 185	98.95 265	87.60 282	96.74 288	97.09 275

LF4IMVS		96.07 155	95.63 170	97.36 130	98.19 161	95.55 82	95.44 172	98.82 97	92.29 224	95.70 221	96.55 227	92.63 186	98.69 285	91.75 210	99.33 153	97.85 252

v2v482		96.78 125	97.06 106	95.95 204	98.57 125	88.77 240	95.36 180	98.26 173	95.18 145	97.85 128	98.23 98	92.58 187	99.63 119	97.80 26	99.69 53	99.45 63

EI-MVSNet		96.63 136	96.93 112	95.74 211	97.26 254	88.13 251	95.29 187	97.65 222	96.99 74	97.94 117	98.19 103	92.55 188	99.58 136	96.91 55	99.56 81	99.50 42

IterMVS-LS		96.92 114	97.29 89	95.79 210	98.51 131	88.13 251	95.10 196	98.66 130	96.99 74	98.46 63	98.68 59	92.55 188	99.74 61	96.91 55	99.79 34	99.50 42
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
VDD-MVS		97.37 94	97.25 92	97.74 96	98.69 112	94.50 120	97.04 96	95.61 272	98.59 25	98.51 57	98.72 55	92.54 190	99.58 136	96.02 79	99.49 104	99.12 130

MVS		90.02 284	89.20 290	92.47 292	94.71 309	86.90 272	95.86 154	96.74 255	64.72 331	90.62 307	92.77 303	92.54 190	98.39 305	79.30 319	95.56 305	92.12 324

v144192		96.69 132	96.90 115	96.03 199	98.25 155	88.92 233	95.49 170	98.77 104	93.05 209	98.09 100	98.29 91	92.51 192	99.70 90	98.11 18	99.56 81	99.47 56

原ACMM1				96.58 173	98.16 168	92.12 185		98.15 188	85.90 285	93.49 276	96.43 234	92.47 193	99.38 201	87.66 281	98.62 227	98.23 226

VNet		96.84 118	96.83 117	96.88 154	98.06 176	92.02 188	96.35 125	97.57 229	97.70 53	97.88 123	97.80 145	92.40 194	99.54 149	94.73 140	98.96 193	99.08 138

114514_t		93.96 233	93.22 239	96.19 194	99.06 82	90.97 205	95.99 147	98.94 68	73.88 329	93.43 280	96.93 205	92.38 195	99.37 204	89.09 262	99.28 162	98.25 225

CPTT-MVS		96.69 132	96.08 153	98.49 49	98.89 94	96.64 50	97.25 85	98.77 104	92.89 216	96.01 209	97.13 191	92.23 196	99.67 108	92.24 200	99.34 147	99.17 118

MSP-MVS		97.45 87	96.92 113	99.03 7	99.26 47	97.70 15	97.66 65	98.89 72	95.65 126	98.51 57	96.46 233	92.15 197	99.81 30	95.14 121	98.58 231	99.58 27

MAR-MVS		94.21 225	93.03 241	97.76 94	96.94 267	97.44 30	96.97 100	97.15 240	87.89 270	92.00 301	92.73 305	92.14 198	99.12 240	83.92 307	97.51 272	96.73 291
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
PVSNet_Blended_VisFu		95.95 161	95.80 164	96.42 183	99.28 46	90.62 212	95.31 185	99.08 34	88.40 262	96.97 166	98.17 105	92.11 199	99.78 38	93.64 179	99.21 167	98.86 174

BH-RMVSNet		94.56 214	94.44 212	94.91 240	97.57 230	87.44 265	93.78 258	96.26 259	93.69 193	96.41 191	96.50 232	92.10 200	99.00 256	85.96 293	97.71 261	98.31 218

新几何1				97.25 137	98.29 148	94.70 114		97.73 214	77.98 322	94.83 237	96.67 223	92.08 201	99.45 174	88.17 276	98.65 225	97.61 263

testdata				95.70 214	98.16 168	90.58 213		97.72 215	80.38 314	95.62 222	97.02 199	92.06 202	98.98 260	89.06 264	98.52 232	97.54 265

YYNet1		94.73 205	94.84 194	94.41 259	97.47 239	85.09 290	90.29 315	95.85 268	92.52 219	97.53 134	97.76 146	91.97 203	99.18 233	93.31 184	96.86 284	98.95 154

Anonymous20231206		95.27 189	95.06 185	95.88 208	98.72 105	89.37 227	95.70 160	97.85 207	88.00 268	96.98 165	97.62 160	91.95 204	99.34 210	89.21 260	99.53 91	98.94 156

MS-PatchMatch		94.83 202	94.91 191	94.57 255	96.81 271	87.10 271	94.23 234	97.34 234	88.74 259	97.14 154	97.11 194	91.94 205	98.23 313	92.99 192	97.92 251	98.37 210

1121		94.26 220	93.26 237	97.27 134	98.26 154	94.73 110	95.86 154	97.71 216	77.96 323	94.53 243	96.71 220	91.93 206	99.40 191	87.71 278	98.64 226	97.69 260

MDA-MVSNet_test_wron		94.73 205	94.83 196	94.42 258	97.48 235	85.15 288	90.28 316	95.87 267	92.52 219	97.48 141	97.76 146	91.92 207	99.17 237	93.32 183	96.80 287	98.94 156

HQP_MVS		96.66 135	96.33 143	97.68 102	98.70 110	94.29 126	96.50 116	98.75 108	96.36 94	96.16 205	96.77 216	91.91 208	99.46 170	92.59 196	99.20 168	99.28 104

plane_prior6					98.38 142	94.37 124						91.91 208

MVP-Stereo		95.69 168	95.28 177	96.92 151	98.15 170	93.03 167	95.64 168	98.20 179	90.39 242	96.63 180	97.73 152	91.63 210	99.10 245	91.84 207	97.31 279	98.63 194
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
DI_MVS_plusplus_test		95.46 180	95.43 175	95.55 220	98.05 177	88.84 237	94.18 237	95.75 269	91.92 230	97.32 147	96.94 204	91.44 211	99.39 196	94.81 133	98.48 235	98.43 206

PatchMatch-RL		94.61 212	93.81 229	97.02 148	98.19 161	95.72 76	93.66 260	97.23 236	88.17 266	94.94 235	95.62 264	91.43 212	98.57 294	87.36 287	97.68 264	96.76 290

MDA-MVSNet-bldmvs		95.69 168	95.67 168	95.74 211	98.48 136	88.76 241	92.84 279	97.25 235	96.00 109	97.59 132	97.95 130	91.38 213	99.46 170	93.16 190	96.35 295	98.99 151

PAPR		92.22 262	91.27 267	95.07 237	95.73 296	88.81 238	91.97 298	97.87 206	85.80 286	90.91 306	92.73 305	91.16 214	98.33 310	79.48 318	95.76 303	98.08 233

1314		92.38 259	92.30 254	92.64 291	95.42 303	85.15 288	95.86 154	96.97 247	85.40 291	90.62 307	93.06 299	91.12 215	97.80 320	86.74 290	95.49 306	94.97 315

ppachtmachnet_test		94.49 216	94.84 194	93.46 273	96.16 287	82.10 308	90.59 312	97.48 231	90.53 241	97.01 162	97.59 162	91.01 216	99.36 206	93.97 171	99.18 170	98.94 156

PLC	91.02 16	94.05 232	92.90 243	97.51 112	98.00 184	95.12 100	94.25 232	98.25 174	86.17 281	91.48 304	95.25 270	91.01 216	99.19 232	85.02 302	96.69 289	98.22 227
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test222					98.17 166	93.24 163	92.74 284	97.61 228	75.17 327	94.65 240	96.69 222	90.96 218			98.66 224	97.66 261

USDC		94.56 214	94.57 207	94.55 256	97.78 214	86.43 278	92.75 282	98.65 135	85.96 283	96.91 169	97.93 133	90.82 219	98.74 280	90.71 233	99.59 73	98.47 203

PCF-MVS	89.43 18	92.12 265	90.64 278	96.57 175	97.80 205	93.48 158	89.88 321	98.45 149	74.46 328	96.04 208	95.68 261	90.71 220	99.31 216	73.73 326	99.01 191	96.91 283
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PAPM_NR		94.61 212	94.17 220	95.96 202	98.36 144	91.23 200	95.93 152	97.95 201	92.98 211	93.42 281	94.43 287	90.53 221	98.38 306	87.60 282	96.29 296	98.27 223

our_test_3		94.20 227	94.58 205	93.07 281	96.16 287	81.20 311	90.42 314	96.84 250	90.72 240	97.14 154	97.13 191	90.47 222	99.11 243	94.04 168	98.25 240	98.91 164

OpenMVS_ROB	91.80 14	93.64 241	93.05 240	95.42 226	97.31 253	91.21 201	95.08 200	96.68 257	81.56 308	96.88 171	96.41 235	90.44 223	99.25 227	85.39 300	97.67 265	95.80 306

HQP2-MVS												90.33 224

N_pmnet		95.18 191	94.23 216	98.06 78	97.85 193	96.55 53	92.49 288	91.63 309	89.34 251	98.09 100	97.41 174	90.33 224	99.06 249	91.58 212	99.31 157	98.56 199

HQP-MVS		95.17 193	94.58 205	96.92 151	97.85 193	92.47 175	94.26 229	98.43 152	93.18 203	92.86 289	95.08 272	90.33 224	99.23 230	90.51 241	98.74 217	99.05 144

CNLPA		95.04 197	94.47 209	96.75 162	97.81 201	95.25 92	94.12 244	97.89 205	94.41 171	94.57 241	95.69 260	90.30 227	98.35 309	86.72 291	98.76 215	96.64 293

PMMVS		92.39 258	91.08 269	96.30 190	93.12 326	92.81 171	90.58 313	95.96 265	79.17 319	91.85 303	92.27 309	90.29 228	98.66 290	89.85 252	96.68 290	97.43 268

TR-MVS		92.54 257	92.20 255	93.57 271	96.49 276	86.66 274	93.51 265	94.73 279	89.96 247	94.95 234	93.87 292	90.24 229	98.61 291	81.18 316	94.88 307	95.45 312

MVS_0304		95.50 175	95.05 186	96.84 157	96.28 281	93.12 165	97.00 98	96.16 260	95.03 152	89.22 319	97.70 154	90.16 230	99.48 164	94.51 145	99.34 147	97.93 249

TAMVS		95.49 176	94.94 188	97.16 138	98.31 146	93.41 159	95.07 201	96.82 252	91.09 238	97.51 136	97.82 143	89.96 231	99.42 180	88.42 272	99.44 117	98.64 192

DPM-MVS		93.68 239	92.77 248	96.42 183	97.91 190	92.54 173	91.17 307	97.47 232	84.99 295	93.08 286	94.74 280	89.90 232	99.00 256	87.54 284	98.09 246	97.72 258

PMMVS2		93.66 240	94.07 222	92.45 293	97.57 230	80.67 313	86.46 327	96.00 263	93.99 186	97.10 157	97.38 181	89.90 232	97.82 319	88.76 266	99.47 109	98.86 174

BH-w/o		92.14 264	91.94 257	92.73 290	97.13 260	85.30 285	92.46 289	95.64 271	89.33 252	94.21 250	92.74 304	89.60 234	98.24 312	81.68 314	94.66 309	94.66 316

UnsupCasMVSNet_bld		94.72 207	94.26 215	96.08 198	98.62 119	90.54 216	93.38 270	98.05 199	90.30 243	97.02 161	96.80 215	89.54 235	99.16 238	88.44 271	96.18 297	98.56 199

MG-MVS		94.08 231	94.00 225	94.32 261	97.09 261	85.89 279	93.19 276	95.96 265	92.52 219	94.93 236	97.51 168	89.54 235	98.77 278	87.52 285	97.71 261	98.31 218

UnsupCasMVSNet_eth		95.91 162	95.73 167	96.44 181	98.48 136	91.52 198	95.31 185	98.45 149	95.76 124	97.48 141	97.54 164	89.53 237	98.69 285	94.43 147	94.61 310	99.13 125

GBi-Net		96.99 108	96.80 119	97.56 107	97.96 186	93.67 150	98.23 33	98.66 130	95.59 130	97.99 110	99.19 25	89.51 238	99.73 65	94.60 142	99.44 117	99.30 97

test1		96.99 108	96.80 119	97.56 107	97.96 186	93.67 150	98.23 33	98.66 130	95.59 130	97.99 110	99.19 25	89.51 238	99.73 65	94.60 142	99.44 117	99.30 97

FMVSNet2		96.72 129	96.67 126	96.87 155	97.96 186	91.88 191	97.15 90	98.06 198	95.59 130	98.50 59	98.62 63	89.51 238	99.65 114	94.99 129	99.60 71	99.07 140

pmmvs4		94.82 203	94.19 219	96.70 165	97.42 242	92.75 172	92.09 297	96.76 253	86.80 278	95.73 220	97.22 187	89.28 241	98.89 268	93.28 185	99.14 172	98.46 205

cascas		91.89 268	91.35 265	93.51 272	94.27 314	85.60 281	88.86 324	98.61 137	79.32 318	92.16 300	91.44 317	89.22 242	98.12 316	90.80 227	97.47 275	96.82 287

DSMNet-mixed		92.19 263	91.83 259	93.25 277	96.18 286	83.68 303	96.27 128	93.68 289	76.97 326	92.54 297	99.18 28	89.20 243	98.55 297	83.88 308	98.60 230	97.51 266

CANet_DTU		94.65 210	94.21 218	95.96 202	95.90 292	89.68 221	93.92 252	97.83 210	93.19 202	90.12 314	95.64 263	88.52 244	99.57 142	93.27 187	99.47 109	98.62 195

EPP-MVSNet		96.84 118	96.58 129	97.65 103	99.18 63	93.78 148	98.68 11	96.34 258	97.91 44	97.30 148	98.06 117	88.46 245	99.85 22	93.85 174	99.40 134	99.32 91

SixPastTwentyTwo		97.49 84	97.57 74	97.26 136	99.56 16	92.33 177	98.28 30	96.97 247	98.30 33	99.45 15	99.35 17	88.43 246	99.89 16	98.01 20	99.76 37	99.54 35

IS-MVSNet		96.93 113	96.68 125	97.70 99	99.25 50	94.00 138	98.57 16	96.74 255	98.36 30	98.14 94	97.98 126	88.23 247	99.71 81	93.10 191	99.72 46	99.38 82

jason		94.39 219	94.04 223	95.41 228	98.29 148	87.85 257	92.74 284	96.75 254	85.38 292	95.29 228	96.15 245	88.21 248	99.65 114	94.24 158	99.34 147	98.74 185
jason: jason.
IterMVS-SCA-FT		95.86 165	96.19 147	94.85 244	97.68 222	85.53 282	92.42 290	97.63 226	96.99 74	98.36 72	98.54 69	87.94 249	99.75 54	97.07 52	99.08 182	99.27 108

SCA		93.38 247	93.52 233	92.96 286	96.24 282	81.40 310	93.24 274	94.00 285	91.58 235	94.57 241	96.97 201	87.94 249	99.42 180	89.47 257	97.66 266	98.06 239

sss		94.22 222	93.72 230	95.74 211	97.71 220	89.95 220	93.84 254	96.98 246	88.38 264	93.75 265	95.74 259	87.94 249	98.89 268	91.02 220	98.10 245	98.37 210

IterMVS		95.42 183	95.83 163	94.20 264	97.52 234	83.78 302	92.41 291	97.47 232	95.49 134	98.06 104	98.49 72	87.94 249	99.58 136	96.02 79	99.02 189	99.23 111
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CHOSEN 1792x2688		94.10 229	93.41 235	96.18 195	99.16 64	90.04 218	92.15 294	98.68 125	79.90 316	96.22 202	97.83 140	87.92 253	99.42 180	89.18 261	99.65 59	99.08 138

VDDNet		96.98 111	96.84 116	97.41 127	99.40 37	93.26 162	97.94 50	95.31 276	99.26 7	98.39 69	99.18 28	87.85 254	99.62 125	95.13 122	99.09 181	99.35 89

pmmvs5		94.63 211	94.34 214	95.50 222	97.63 228	88.34 246	94.02 246	97.13 241	87.15 274	95.22 230	97.15 189	87.50 255	99.27 224	93.99 169	99.26 165	98.88 171

D2MVS		95.18 191	95.17 180	95.21 232	97.76 216	87.76 260	94.15 240	97.94 202	89.77 249	96.99 163	97.68 157	87.45 256	99.14 239	95.03 127	99.81 30	98.74 185

PVSNet	86.72 19	91.10 276	90.97 272	91.49 298	97.56 232	78.04 320	87.17 326	94.60 281	84.65 297	92.34 298	92.20 310	87.37 257	98.47 300	85.17 301	97.69 263	97.96 247

Anonymous202405211		96.34 147	95.98 158	97.43 125	98.25 155	93.85 144	96.74 106	94.41 283	97.72 51	98.37 70	98.03 120	87.15 258	99.53 151	94.06 164	99.07 184	98.92 163

MVSFormer		96.14 153	96.36 141	95.49 223	97.68 222	87.81 258	98.67 12	99.02 48	96.50 89	94.48 246	96.15 245	86.90 259	99.92 4	98.73 8	99.13 174	98.74 185

lupinMVS		93.77 235	93.28 236	95.24 231	97.68 222	87.81 258	92.12 295	96.05 262	84.52 298	94.48 246	95.06 274	86.90 259	99.63 119	93.62 180	99.13 174	98.27 223

WTY-MVS		93.55 243	93.00 242	95.19 233	97.81 201	87.86 255	93.89 253	96.00 263	89.02 254	94.07 255	95.44 269	86.27 261	99.33 213	87.69 280	96.82 285	98.39 209

CDS-MVSNet		94.88 201	94.12 221	97.14 140	97.64 227	93.57 155	93.96 251	97.06 244	90.05 246	96.30 198	96.55 227	86.10 262	99.47 167	90.10 248	99.31 157	98.40 207
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
1112_ss		94.12 228	93.42 234	96.23 191	98.59 123	90.85 206	94.24 233	98.85 82	85.49 288	92.97 287	94.94 276	86.01 263	99.64 117	91.78 208	97.92 251	98.20 229

new_pmnet		92.34 260	91.69 262	94.32 261	96.23 284	89.16 231	92.27 293	92.88 298	84.39 301	95.29 228	96.35 239	85.66 264	96.74 328	84.53 305	97.56 269	97.05 277

alignmvs		96.01 159	95.52 173	97.50 115	97.77 215	94.71 112	96.07 140	96.84 250	97.48 62	96.78 176	94.28 290	85.50 265	99.40 191	96.22 70	98.73 220	98.40 207

lessismore_v0				97.05 145	99.36 41	92.12 185		84.07 332		98.77 44	98.98 39	85.36 266	99.74 61	97.34 40	99.37 137	99.30 97

HY-MVS	91.43 15	92.58 256	91.81 260	94.90 242	96.49 276	88.87 235	97.31 82	94.62 280	85.92 284	90.50 311	96.84 210	85.05 267	99.40 191	83.77 310	95.78 302	96.43 298

EPNet		93.72 237	92.62 251	97.03 147	87.61 336	92.25 179	96.27 128	91.28 311	96.74 82	87.65 325	97.39 179	85.00 268	99.64 117	92.14 201	99.48 107	99.20 114
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_lstm_enhance		94.81 204	94.80 197	94.85 244	96.16 287	86.45 277	91.14 308	98.20 179	93.49 196	97.03 160	97.37 183	84.97 269	99.26 225	95.28 111	99.56 81	98.83 176

Test_1112_low_res		93.53 244	92.86 244	95.54 221	98.60 121	88.86 236	92.75 282	98.69 123	82.66 305	92.65 294	96.92 207	84.75 270	99.56 143	90.94 222	97.76 257	98.19 230

MVS-HIRNet		88.40 297	90.20 283	82.99 318	97.01 263	60.04 336	93.11 277	85.61 331	84.45 300	88.72 321	99.09 34	84.72 271	98.23 313	82.52 313	96.59 292	90.69 329

K. test v3		96.44 144	96.28 144	96.95 149	99.41 36	91.53 197	97.65 66	90.31 320	98.89 19	98.93 36	99.36 15	84.57 272	99.92 4	97.81 25	99.56 81	99.39 80

Vis-MVSNet (Re-imp)		95.11 194	94.85 193	95.87 209	99.12 76	89.17 230	97.54 75	94.92 278	96.50 89	96.58 181	97.27 186	83.64 273	99.48 164	88.42 272	99.67 56	98.97 152

PVSNet_0	81.89 21	84.49 306	83.21 308	88.34 314	95.76 295	74.97 330	83.49 330	92.70 302	78.47 321	87.94 324	86.90 330	83.38 274	96.63 329	73.44 327	66.86 333	93.40 321

CMPMVS	73.10 23	92.74 254	91.39 264	96.77 161	93.57 323	94.67 115	94.21 236	97.67 218	80.36 315	93.61 271	96.60 225	82.85 275	97.35 323	84.86 303	98.78 213	98.29 222
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EU-MVSNet		94.25 221	94.47 209	93.60 270	98.14 171	82.60 306	97.24 87	92.72 301	85.08 293	98.48 60	98.94 43	82.59 276	98.76 279	97.47 37	99.53 91	99.44 72

baseline1		93.14 251	92.64 250	94.62 251	97.34 249	87.20 270	96.67 113	93.02 296	94.71 162	96.51 187	95.83 258	81.64 277	98.60 293	90.00 250	88.06 326	98.07 235

CVMVSNet		92.33 261	92.79 246	90.95 303	97.26 254	75.84 327	95.29 187	92.33 304	81.86 306	96.27 199	98.19 103	81.44 278	98.46 301	94.23 159	98.29 239	98.55 201

EPNet_dtu		91.39 274	90.75 276	93.31 275	90.48 335	82.61 305	94.80 215	92.88 298	93.39 197	81.74 333	94.90 279	81.36 279	99.11 243	88.28 274	98.87 204	98.21 228
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_yl		94.40 217	94.00 225	95.59 215	96.95 265	89.52 224	94.75 218	95.55 274	96.18 102	96.79 172	96.14 247	81.09 280	99.18 233	90.75 229	97.77 255	98.07 235

DCV-MVSNet		94.40 217	94.00 225	95.59 215	96.95 265	89.52 224	94.75 218	95.55 274	96.18 102	96.79 172	96.14 247	81.09 280	99.18 233	90.75 229	97.77 255	98.07 235

MIMVSNet		93.42 245	92.86 244	95.10 236	98.17 166	88.19 248	98.13 42	93.69 287	92.07 225	95.04 233	98.21 102	80.95 282	99.03 254	81.42 315	98.06 247	98.07 235

PAPM		87.64 303	85.84 307	93.04 282	96.54 274	84.99 291	88.42 325	95.57 273	79.52 317	83.82 330	93.05 300	80.57 283	98.41 303	62.29 332	92.79 316	95.71 307

HyFIR lowres test		93.72 237	92.65 249	96.91 153	98.93 91	91.81 194	91.23 306	98.52 144	82.69 304	96.46 189	96.52 231	80.38 284	99.90 13	90.36 245	98.79 212	99.03 145

FMVSNet3		95.26 190	94.94 188	96.22 193	96.53 275	90.06 217	95.99 147	97.66 220	94.11 183	97.99 110	97.91 135	80.22 285	99.63 119	94.60 142	99.44 117	98.96 153

RPMNet		94.22 222	94.03 224	94.78 247	95.44 301	88.15 249	96.18 135	93.73 286	97.43 63	94.10 253	98.49 72	79.40 286	99.39 196	95.69 90	95.81 299	96.81 288

LFMVS		95.32 187	94.88 192	96.62 169	98.03 178	91.47 199	97.65 66	90.72 317	99.11 9	97.89 122	98.31 85	79.20 287	99.48 164	93.91 173	99.12 177	98.93 160

ADS-MVSNet2		91.47 273	90.51 280	94.36 260	95.51 299	85.63 280	95.05 204	95.70 270	83.46 302	92.69 292	96.84 210	79.15 288	99.41 189	85.66 297	90.52 320	98.04 243

ADS-MVSNet		90.95 279	90.26 282	93.04 282	95.51 299	82.37 307	95.05 204	93.41 293	83.46 302	92.69 292	96.84 210	79.15 288	98.70 284	85.66 297	90.52 320	98.04 243

MDTV_nov1_ep13_2view						57.28 337	94.89 210		80.59 313	94.02 257		78.66 290		85.50 299		97.82 254

PatchmatchNet		91.98 267	91.87 258	92.30 295	94.60 311	79.71 315	95.12 195	93.59 292	89.52 250	93.61 271	97.02 199	77.94 291	99.18 233	90.84 225	94.57 312	98.01 246
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												77.80 292				98.06 239

CR-MVSNet		93.29 249	92.79 246	94.78 247	95.44 301	88.15 249	96.18 135	97.20 237	84.94 296	94.10 253	98.57 65	77.67 293	99.39 196	95.17 117	95.81 299	96.81 288

Patchmtry		95.03 198	94.59 204	96.33 187	94.83 308	90.82 208	96.38 123	97.20 237	96.59 86	97.49 138	98.57 65	77.67 293	99.38 201	92.95 194	99.62 62	98.80 179

tpmrst		90.31 282	90.61 279	89.41 310	94.06 318	72.37 333	95.06 203	93.69 287	88.01 267	92.32 299	96.86 208	77.45 295	98.82 273	91.04 219	87.01 328	97.04 278

sam_mvs												77.38 296

patchmatchnet-post											96.84 210	77.36 297	99.42 180

Patchmatch-RL test		94.66 209	94.49 208	95.19 233	98.54 128	88.91 234	92.57 286	98.74 110	91.46 236	98.32 78	97.75 149	77.31 298	98.81 275	96.06 75	99.61 68	97.85 252

tpmvs		90.79 280	90.87 273	90.57 306	92.75 330	76.30 325	95.79 158	93.64 290	91.04 239	91.91 302	96.26 240	77.19 299	98.86 272	89.38 259	89.85 323	96.56 296

test_post											10.87 336	76.83 300	99.07 248

Patchmatch-test		93.60 242	93.25 238	94.63 250	96.14 290	87.47 264	96.04 142	94.50 282	93.57 194	96.47 188	96.97 201	76.50 301	98.61 291	90.67 235	98.41 238	97.81 256

MDTV_nov1_ep13			91.28 266		94.31 313	73.51 331	94.80 215	93.16 295	86.75 279	93.45 279	97.40 175	76.37 302	98.55 297	88.85 265	96.43 293

EMVS		89.06 294	89.22 288	88.61 313	93.00 327	77.34 323	82.91 332	90.92 314	94.64 164	92.63 295	91.81 314	76.30 303	97.02 324	83.83 309	96.90 283	91.48 327

test_post1							94.98 208				10.37 337	76.21 304	99.04 251	89.47 257

GA-MVS		92.83 253	92.15 256	94.87 243	96.97 264	87.27 269	90.03 317	96.12 261	91.83 232	94.05 256	94.57 282	76.01 305	98.97 264	92.46 198	97.34 278	98.36 215

PatchT		93.75 236	93.57 232	94.29 263	95.05 306	87.32 268	96.05 141	92.98 297	97.54 60	94.25 249	98.72 55	75.79 306	99.24 228	95.92 85	95.81 299	96.32 299

E-PMN		89.52 292	89.78 285	88.73 312	93.14 325	77.61 322	83.26 331	92.02 305	94.82 158	93.71 266	93.11 296	75.31 307	96.81 326	85.81 294	96.81 286	91.77 326

DeepMVS_CX				77.17 319	90.94 334	85.28 286		74.08 337	52.51 332	80.87 334	88.03 329	75.25 308	70.63 335	59.23 333	84.94 330	75.62 330

CHOSEN 280x420		89.98 286	89.19 291	92.37 294	95.60 298	81.13 312	86.22 328	97.09 243	81.44 310	87.44 326	93.15 295	73.99 309	99.47 167	88.69 268	99.07 184	96.52 297

thres200		91.00 278	90.42 281	92.77 289	97.47 239	83.98 301	94.01 247	91.18 313	95.12 148	95.44 225	91.21 319	73.93 310	99.31 216	77.76 324	97.63 268	95.01 314

test-LLR		89.97 287	89.90 284	90.16 307	94.24 315	74.98 328	89.89 318	89.06 323	92.02 226	89.97 315	90.77 322	73.92 311	98.57 294	91.88 205	97.36 276	96.92 281

test0.0.03 1		90.11 283	89.21 289	92.83 288	93.89 319	86.87 273	91.74 300	88.74 325	92.02 226	94.71 239	91.14 320	73.92 311	94.48 331	83.75 311	92.94 315	97.16 274

tpm cat1		88.01 300	87.33 300	90.05 309	94.48 312	76.28 326	94.47 226	94.35 284	73.84 330	89.26 318	95.61 265	73.64 313	98.30 311	84.13 306	86.20 329	95.57 311

tfpn200view9		91.55 272	91.00 270	93.21 279	98.02 179	84.35 298	95.70 160	90.79 315	96.26 98	95.90 214	92.13 311	73.62 314	99.42 180	78.85 321	97.74 258	95.85 304

thres400		91.68 271	91.00 270	93.71 268	98.02 179	84.35 298	95.70 160	90.79 315	96.26 98	95.90 214	92.13 311	73.62 314	99.42 180	78.85 321	97.74 258	97.36 270

thres100view900		91.76 270	91.26 268	93.26 276	98.21 159	84.50 296	96.39 121	90.39 318	96.87 78	96.33 194	93.08 298	73.44 316	99.42 180	78.85 321	97.74 258	95.85 304

thres600view7		92.03 266	91.43 263	93.82 266	98.19 161	84.61 295	96.27 128	90.39 318	96.81 80	96.37 193	93.11 296	73.44 316	99.49 161	80.32 317	97.95 250	97.36 270

MVSTER		94.21 225	93.93 228	95.05 238	95.83 293	86.46 276	95.18 194	97.65 222	92.41 223	97.94 117	98.00 125	72.39 318	99.58 136	96.36 68	99.56 81	99.12 130

PatchFormer-LS_test		89.62 291	89.12 293	91.11 302	93.62 321	78.42 318	94.57 224	93.62 291	88.39 263	90.54 310	88.40 328	72.33 319	99.03 254	92.41 199	88.20 325	95.89 303

JIA-IIPM		91.79 269	90.69 277	95.11 235	93.80 320	90.98 204	94.16 239	91.78 308	96.38 93	90.30 313	99.30 19	72.02 320	98.90 266	88.28 274	90.17 322	95.45 312

tpm		91.08 277	90.85 274	91.75 297	95.33 304	78.09 319	95.03 206	91.27 312	88.75 258	93.53 275	97.40 175	71.24 321	99.30 218	91.25 218	93.87 313	97.87 251

baseline2		89.65 290	88.44 297	93.25 277	95.62 297	82.71 304	93.82 255	85.94 330	88.89 257	87.35 327	92.54 307	71.23 322	99.33 213	86.01 292	94.60 311	97.72 258

CostFormer		89.75 289	89.25 287	91.26 301	94.69 310	78.00 321	95.32 184	91.98 306	81.50 309	90.55 309	96.96 203	71.06 323	98.89 268	88.59 270	92.63 317	96.87 284

FPMVS		89.92 288	88.63 295	93.82 266	98.37 143	96.94 41	91.58 301	93.34 294	88.00 268	90.32 312	97.10 195	70.87 324	91.13 333	71.91 329	96.16 298	93.39 322

EPMVS		89.26 293	88.55 296	91.39 299	92.36 331	79.11 316	95.65 166	79.86 333	88.60 260	93.12 285	96.53 229	70.73 325	98.10 317	90.75 229	89.32 324	96.98 279

tmp_tt		57.23 307	62.50 309	41.44 320	34.77 337	49.21 338	83.93 329	60.22 339	15.31 333	71.11 335	79.37 332	70.09 326	44.86 336	64.76 331	82.93 332	30.25 332

ET-MVSNet_ETH3D		91.12 275	89.67 286	95.47 224	96.41 278	89.15 232	91.54 302	90.23 321	89.07 253	86.78 329	92.84 302	69.39 327	99.44 177	94.16 161	96.61 291	97.82 254

dp		88.08 299	88.05 298	88.16 316	92.85 328	68.81 335	94.17 238	92.88 298	85.47 289	91.38 305	96.14 247	68.87 328	98.81 275	86.88 289	83.80 331	96.87 284

tpm2		88.47 296	87.69 299	90.79 304	94.98 307	77.34 323	95.09 198	91.83 307	77.51 325	89.40 317	96.41 235	67.83 329	98.73 281	83.58 312	92.60 318	96.29 300

pmmvs3		90.00 285	88.90 294	93.32 274	94.20 317	85.34 284	91.25 305	92.56 303	78.59 320	93.82 261	95.17 271	67.36 330	98.69 285	89.08 263	98.03 248	95.92 302

thisisatest0515		90.43 281	89.18 292	94.17 265	97.07 262	85.44 283	89.75 322	87.58 326	88.28 265	93.69 268	91.72 315	65.27 331	99.58 136	90.59 237	98.67 222	97.50 267

tttt0517		93.31 248	92.56 252	95.57 217	98.71 108	87.86 255	97.44 77	87.17 328	95.79 123	97.47 143	96.84 210	64.12 332	99.81 30	96.20 71	99.32 155	99.02 147

thisisatest0530		92.71 255	91.76 261	95.56 219	98.42 140	88.23 247	96.03 143	87.35 327	94.04 185	96.56 183	95.47 268	64.03 333	99.77 46	94.78 137	99.11 178	98.68 191

FMVSNet5		93.39 246	92.35 253	96.50 178	95.83 293	90.81 210	97.31 82	98.27 171	92.74 218	96.27 199	98.28 92	62.23 334	99.67 108	90.86 224	99.36 140	99.03 145

DWT-MVSNet_test		87.92 301	86.77 304	91.39 299	93.18 324	78.62 317	95.10 196	91.42 310	85.58 287	88.00 323	88.73 327	60.60 335	98.90 266	90.60 236	87.70 327	96.65 292

IB-MVS	85.98 20	88.63 295	86.95 303	93.68 269	95.12 305	84.82 294	90.85 310	90.17 322	87.55 271	88.48 322	91.34 318	58.01 336	99.59 134	87.24 288	93.80 314	96.63 295
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
gg-mvs-nofinetune		88.28 298	86.96 302	92.23 296	92.84 329	84.44 297	98.19 39	74.60 335	99.08 10	87.01 328	99.47 9	56.93 337	98.23 313	78.91 320	95.61 304	94.01 319

GG-mvs-BLEND				90.60 305	91.00 333	84.21 300	98.23 33	72.63 338		82.76 331	84.11 331	56.14 338	96.79 327	72.20 328	92.09 319	90.78 328

TESTMET0.1,1		87.20 304	86.57 305	89.07 311	93.62 321	72.84 332	89.89 318	87.01 329	85.46 290	89.12 320	90.20 325	56.00 339	97.72 321	90.91 223	96.92 282	96.64 293

test-mter		87.92 301	87.17 301	90.16 307	94.24 315	74.98 328	89.89 318	89.06 323	86.44 280	89.97 315	90.77 322	54.96 340	98.57 294	91.88 205	97.36 276	96.92 281

test123		12.59 309	15.49 311	3.87 321	6.07 338	2.55 339	90.75 311	2.59 341	2.52 334	5.20 337	13.02 335	4.96 341	1.85 338	5.20 334	9.09 334	7.23 333

testmvs		12.33 310	15.23 312	3.64 322	5.77 339	2.23 340	88.99 323	3.62 340	2.30 335	5.29 336	13.09 334	4.52 342	1.95 337	5.16 335	8.32 335	6.75 334

test_part1				0.00 323		0.00 341	0.00 334	98.84 85				0.00 343	0.00 339	0.00 336	0.00 336	0.00 335

sosnet-low-res		0.00 313	0.00 315	0.00 323	0.00 340	0.00 341	0.00 334	0.00 342	0.00 336	0.00 338	0.00 338	0.00 343	0.00 339	0.00 336	0.00 336	0.00 335

sosnet		0.00 313	0.00 315	0.00 323	0.00 340	0.00 341	0.00 334	0.00 342	0.00 336	0.00 338	0.00 338	0.00 343	0.00 339	0.00 336	0.00 336	0.00 335

uncertanet		0.00 313	0.00 315	0.00 323	0.00 340	0.00 341	0.00 334	0.00 342	0.00 336	0.00 338	0.00 338	0.00 343	0.00 339	0.00 336	0.00 336	0.00 335

Regformer		0.00 313	0.00 315	0.00 323	0.00 340	0.00 341	0.00 334	0.00 342	0.00 336	0.00 338	0.00 338	0.00 343	0.00 339	0.00 336	0.00 336	0.00 335

ab-mvs-re		7.91 312	10.55 314	0.00 323	0.00 340	0.00 341	0.00 334	0.00 342	0.00 336	0.00 338	94.94 276	0.00 343	0.00 339	0.00 336	0.00 336	0.00 335

uanet		0.00 313	0.00 315	0.00 323	0.00 340	0.00 341	0.00 334	0.00 342	0.00 336	0.00 338	0.00 338	0.00 343	0.00 339	0.00 336	0.00 336	0.00 335

save fliter					98.48 136	94.71 112	94.53 225	98.41 157	95.02 153

test_0728_SECOND				98.25 68	99.23 53	95.49 87	96.74 106	98.89 72					99.75 54	95.48 102	99.52 95	99.53 38

GSMVS																98.06 239

test_part2					99.03 86	96.07 67				98.08 102

MTGPA								98.73 111

MTMP							96.55 114	74.60 335

gm-plane-assit					91.79 332	71.40 334			81.67 307		90.11 326		98.99 258	84.86 303

test9_res														91.29 215	98.89 203	99.00 148

agg_prior2														90.34 246	98.90 200	99.10 137

agg_prior					97.80 205	94.96 104		98.36 163		93.49 276			99.53 151

test_prior4						95.38 89	93.61 263

test_prior				97.46 121	97.79 210	94.26 130		98.42 155					99.34 210			98.79 180

旧先验2							93.35 271		77.95 324	95.77 219			98.67 289	90.74 232

新几何2							93.43 266

无先验							93.20 275	97.91 203	80.78 312				99.40 191	87.71 278		97.94 248

原ACMM2							92.82 280

testdata2													99.46 170	87.84 277

testdata1							92.77 281		93.78 190

plane_prior7					98.70 110	94.67 115

plane_prior5								98.75 108					99.46 170	92.59 196	99.20 168	99.28 104

plane_prior4											96.77 216

plane_prior3						94.51 118			95.29 141	96.16 205

plane_prior2							96.50 116		96.36 94

plane_prior1					98.49 134

plane_prior						94.29 126	95.42 174		94.31 175						98.93 198

n2								0.00 342

nn								0.00 342

door-mid								98.17 185

test11								98.08 195

door								97.81 211

HQP5-MVS						92.47 175

HQP-NCC					97.85 193		94.26 229		93.18 203	92.86 289

ACMP_Plane					97.85 193		94.26 229		93.18 203	92.86 289

BP-MVS														90.51 241

HQP4-MVS										92.87 288			99.23 230			99.06 142

HQP3-MVS								98.43 152							98.74 217

NP-MVS					98.14 171	93.72 149					95.08 272

ACMMP++_ref															99.52 95

ACMMP++															99.55 86

High-resolution multi-view benchmark