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		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 13	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 13	100.00 1	99.85 26

UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 17	99.34 19	99.69 5	99.58 63	99.90 3	99.86 20	99.78 10	99.58 6	99.95 24	99.00 68	99.95 34	99.78 39

pmmvs6		99.67 3	99.70 3	99.60 14	99.90 4	99.27 26	99.53 8	99.76 34	99.64 19	99.84 23	99.83 4	99.50 9	99.87 112	99.36 43	99.92 58	99.64 70

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 25	99.85 16	99.11 63	99.90 1	99.78 32	99.63 21	99.78 31	99.67 27	99.48 10	99.81 191	99.30 47	99.97 20	99.77 41
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
mvs_tets		99.63 5	99.67 5	99.49 51	99.88 9	98.61 94	99.34 20	99.71 40	99.27 62	99.90 13	99.74 15	99.68 4	99.97 5	99.55 34	99.99 5	99.88 19

jajsoiax		99.58 6	99.61 8	99.48 53	99.87 12	98.61 94	99.28 37	99.66 52	99.09 90	99.89 16	99.68 22	99.53 7	99.97 5	99.50 38	99.99 5	99.87 20

test_fmvsmconf0.01_n		99.57 7	99.63 7	99.36 66	99.87 12	98.13 134	98.08 170	99.95 1	99.45 40	99.98 2	99.75 13	99.80 1	99.97 5	99.82 9	99.99 5	99.99 2

ANet_high		99.57 7	99.67 5	99.28 88	99.89 6	98.09 138	99.14 54	99.93 5	99.82 5	99.93 6	99.81 6	99.17 19	99.94 38	99.31 46	100.00 1	99.82 31

v7n		99.53 9	99.57 10	99.41 62	99.88 9	98.54 102	99.45 11	99.61 59	99.66 17	99.68 44	99.66 29	98.44 65	99.95 24	99.73 22	99.96 27	99.75 50

test_djsdf		99.52 10	99.51 12	99.53 37	99.86 14	98.74 84	99.39 17	99.56 77	99.11 80	99.70 40	99.73 17	99.00 23	99.97 5	99.26 50	99.98 12	99.89 16

anonymousdsp		99.51 11	99.47 18	99.62 9	99.88 9	99.08 67	99.34 20	99.69 44	98.93 108	99.65 50	99.72 18	98.93 28	99.95 24	99.11 59	100.00 1	99.82 31

test_fmvsmconf0.1_n		99.49 12	99.54 11	99.34 75	99.78 23	98.11 135	97.77 217	99.90 11	99.33 55	99.97 3	99.66 29	99.71 3	99.96 12	99.79 15	99.99 5	99.96 8

UA-Net		99.47 13	99.40 23	99.70 2	99.49 117	99.29 23	99.80 4	99.72 38	99.82 5	99.04 151	99.81 6	98.05 100	99.96 12	98.85 78	99.99 5	99.86 24

PS-MVSNAJss		99.46 14	99.49 13	99.35 72	99.90 4	98.15 131	99.20 45	99.65 53	99.48 34	99.92 8	99.71 19	98.07 97	99.96 12	99.53 35	100.00 1	99.93 11

fmvsm_l_conf0.5_n_3		99.45 15	99.48 15	99.34 75	99.59 77	98.21 128	97.82 209	99.84 21	99.41 47	99.92 8	99.41 84	99.51 8	99.95 24	99.84 7	99.97 20	99.87 20

test_fmvsmconf_n		99.44 16	99.48 15	99.31 86	99.64 70	98.10 137	97.68 228	99.84 21	99.29 60	99.92 8	99.57 46	99.60 5	99.96 12	99.74 21	99.98 12	99.89 16

mamv4		99.44 16	99.39 24	99.58 19	99.30 163	99.74 2	99.04 65	99.81 27	99.77 7	99.82 25	99.57 46	97.82 116	99.98 4	99.53 35	99.89 75	99.01 272

pm-mvs1		99.44 16	99.48 15	99.33 81	99.80 20	98.63 91	99.29 33	99.63 55	99.30 59	99.65 50	99.60 42	99.16 21	99.82 177	99.07 62	99.83 96	99.56 106

TransMVSNet (Re)		99.44 16	99.47 18	99.36 66	99.80 20	98.58 97	99.27 39	99.57 70	99.39 48	99.75 35	99.62 37	99.17 19	99.83 167	99.06 63	99.62 197	99.66 64

DTE-MVSNet		99.43 20	99.35 29	99.66 7	99.71 45	99.30 21	99.31 27	99.51 92	99.64 19	99.56 57	99.46 73	98.23 81	99.97 5	98.78 82	99.93 47	99.72 52

TDRefinement		99.42 21	99.38 25	99.55 27	99.76 29	99.33 20	99.68 6	99.71 40	99.38 49	99.53 65	99.61 40	98.64 46	99.80 198	98.24 115	99.84 89	99.52 128

PEN-MVS		99.41 22	99.34 31	99.62 9	99.73 36	99.14 56	99.29 33	99.54 85	99.62 24	99.56 57	99.42 80	98.16 92	99.96 12	98.78 82	99.93 47	99.77 41

nrg030		99.40 23	99.35 29	99.54 30	99.58 78	99.13 59	98.98 72	99.48 103	99.68 15	99.46 79	99.26 114	98.62 49	99.73 251	99.17 58	99.92 58	99.76 46

PS-CasMVS		99.40 23	99.33 32	99.62 9	99.71 45	99.10 64	99.29 33	99.53 88	99.53 31	99.46 79	99.41 84	98.23 81	99.95 24	98.89 76	99.95 34	99.81 34

MIMVSNet1		99.38 25	99.32 34	99.55 27	99.86 14	99.19 41	99.41 14	99.59 61	99.59 27	99.71 38	99.57 46	97.12 167	99.90 69	99.21 55	99.87 80	99.54 117

OurMVSNet-221017-0		99.37 26	99.31 36	99.53 37	99.91 3	98.98 69	99.63 7	99.58 63	99.44 42	99.78 31	99.76 12	96.39 207	99.92 54	99.44 41	99.92 58	99.68 60

Vis-MVSNet		99.34 27	99.36 28	99.27 91	99.73 36	98.26 120	99.17 50	99.78 32	99.11 80	99.27 116	99.48 71	98.82 33	99.95 24	98.94 72	99.93 47	99.59 89
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_fmvsm_n_1920		99.33 28	99.45 20	98.99 138	99.57 83	97.73 181	97.93 193	99.83 24	99.22 65	99.93 6	99.30 105	99.42 11	99.96 12	99.85 5	99.99 5	99.29 223

WR-MVS_H		99.33 28	99.22 47	99.65 8	99.71 45	99.24 29	99.32 23	99.55 81	99.46 39	99.50 73	99.34 97	97.30 156	99.93 45	98.90 74	99.93 47	99.77 41

mmtdpeth		99.30 30	99.42 21	98.92 150	99.58 78	96.89 230	99.48 10	99.92 7	99.92 2	98.26 256	99.80 9	98.33 74	99.91 63	99.56 33	99.95 34	99.97 4

mvs5depth		99.30 30	99.59 9	98.44 226	99.65 64	95.35 283	99.82 3	99.94 2	99.83 4	99.42 87	99.94 2	98.13 95	99.96 12	99.63 28	99.96 27	100.00 1

VPA-MVSNet		99.30 30	99.30 39	99.28 88	99.49 117	98.36 116	99.00 69	99.45 118	99.63 21	99.52 67	99.44 78	98.25 79	99.88 95	99.09 61	99.84 89	99.62 74

sd_testset		99.28 33	99.31 36	99.19 104	99.68 57	98.06 147	99.41 14	99.30 181	99.69 13	99.63 53	99.68 22	99.25 15	99.96 12	97.25 176	99.92 58	99.57 100

Anonymous20231211		99.27 34	99.27 42	99.26 93	99.29 165	98.18 129	99.49 9	99.51 92	99.70 12	99.80 29	99.68 22	96.84 182	99.83 167	99.21 55	99.91 65	99.77 41

FC-MVSNet-test		99.27 34	99.25 45	99.34 75	99.77 26	98.37 113	99.30 32	99.57 70	99.61 26	99.40 92	99.50 64	97.12 167	99.85 132	99.02 67	99.94 42	99.80 35

test_fmvsmvis_n_1920		99.26 36	99.49 13	98.54 213	99.66 63	96.97 223	98.00 184	99.85 18	99.24 64	99.92 8	99.50 64	99.39 12	99.95 24	99.89 3	99.98 12	98.71 321

testf1		99.25 37	99.16 52	99.51 46	99.89 6	99.63 4	98.71 99	99.69 44	98.90 110	99.43 84	99.35 93	98.86 30	99.67 279	97.81 144	99.81 103	99.24 233

APD_test2		99.25 37	99.16 52	99.51 46	99.89 6	99.63 4	98.71 99	99.69 44	98.90 110	99.43 84	99.35 93	98.86 30	99.67 279	97.81 144	99.81 103	99.24 233

KD-MVS_self_test		99.25 37	99.18 49	99.44 59	99.63 74	99.06 68	98.69 101	99.54 85	99.31 57	99.62 56	99.53 60	97.36 154	99.86 120	99.24 54	99.71 162	99.39 185

ACMH	96.65 7	99.25 37	99.24 46	99.26 93	99.72 42	98.38 111	99.07 61	99.55 81	98.30 149	99.65 50	99.45 77	99.22 16	99.76 234	98.44 106	99.77 130	99.64 70
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SDMVSNet		99.23 41	99.32 34	98.96 142	99.68 57	97.35 201	98.84 89	99.48 103	99.69 13	99.63 53	99.68 22	99.03 22	99.96 12	97.97 135	99.92 58	99.57 100

fmvsm_s_conf0.5_n_3		99.22 42	99.37 27	98.78 170	99.46 128	96.58 245	97.65 234	99.72 38	99.47 37	99.86 20	99.50 64	98.94 26	99.89 81	99.75 20	99.97 20	99.86 24

fmvsm_l_conf0.5_n		99.21 43	99.28 41	99.02 135	99.64 70	97.28 205	97.82 209	99.76 34	98.73 118	99.82 25	99.09 154	98.81 34	99.95 24	99.86 4	99.96 27	99.83 28

CP-MVSNet		99.21 43	99.09 61	99.56 25	99.65 64	98.96 74	99.13 55	99.34 161	99.42 45	99.33 104	99.26 114	97.01 175	99.94 38	98.74 87	99.93 47	99.79 36

fmvsm_s_conf0.1_n_2		99.20 45	99.38 25	98.65 187	99.69 54	96.08 260	97.49 254	99.90 11	99.53 31	99.88 18	99.64 34	98.51 59	99.90 69	99.83 8	99.98 12	99.97 4

fmvsm_l_conf0.5_n_a		99.19 46	99.27 42	98.94 145	99.65 64	97.05 219	97.80 213	99.76 34	98.70 121	99.78 31	99.11 148	98.79 36	99.95 24	99.85 5	99.96 27	99.83 28

fmvsm_s_conf0.1_n_a		99.17 47	99.30 39	98.80 164	99.75 33	96.59 243	97.97 192	99.86 16	98.22 157	99.88 18	99.71 19	98.59 52	99.84 150	99.73 22	99.98 12	99.98 3

TranMVSNet+NR-MVSNet		99.17 47	99.07 64	99.46 58	99.37 150	98.87 77	98.39 138	99.42 131	99.42 45	99.36 99	99.06 155	98.38 68	99.95 24	98.34 111	99.90 71	99.57 100

FMVSNet1		99.17 47	99.17 50	99.17 105	99.55 95	98.24 122	99.20 45	99.44 122	99.21 67	99.43 84	99.55 54	97.82 116	99.86 120	98.42 108	99.89 75	99.41 175

fmvsm_s_conf0.1_n		99.16 50	99.33 32	98.64 189	99.71 45	96.10 255	97.87 204	99.85 18	98.56 135	99.90 13	99.68 22	98.69 43	99.85 132	99.72 24	99.98 12	99.97 4

reproduce_model		99.15 51	98.97 72	99.67 4	99.33 158	99.44 10	98.15 160	99.47 111	99.12 79	99.52 67	99.32 103	98.31 75	99.90 69	97.78 147	99.73 149	99.66 64

fmvsm_s_conf0.5_n_2		99.14 52	99.31 36	98.63 193	99.49 117	96.08 260	97.38 261	99.81 27	99.48 34	99.84 23	99.57 46	98.46 63	99.89 81	99.82 9	99.97 20	99.91 13

test_vis3_rt		99.14 52	99.17 50	99.07 123	99.78 23	98.38 111	98.92 79	99.94 2	97.80 191	99.91 12	99.67 27	97.15 166	98.91 404	99.76 18	99.56 220	99.92 12

FIs		99.14 52	99.09 61	99.29 87	99.70 52	98.28 119	99.13 55	99.52 91	99.48 34	99.24 125	99.41 84	96.79 188	99.82 177	98.69 92	99.88 77	99.76 46

XXY-MVS		99.14 52	99.15 57	99.10 117	99.76 29	97.74 179	98.85 87	99.62 56	98.48 139	99.37 97	99.49 70	98.75 38	99.86 120	98.20 118	99.80 114	99.71 53

CS-MVS		99.13 56	99.10 60	99.24 98	99.06 222	99.15 51	99.36 19	99.88 14	99.36 53	98.21 258	98.46 279	98.68 44	99.93 45	99.03 66	99.85 85	98.64 330

SPE-MVS-test		99.13 56	99.09 61	99.26 93	99.13 206	98.97 70	99.31 27	99.88 14	99.44 42	98.16 262	98.51 271	98.64 46	99.93 45	98.91 73	99.85 85	98.88 298

test_fmvs3		99.12 58	99.41 22	98.25 244	99.76 29	95.07 295	99.05 64	99.94 2	97.78 193	99.82 25	99.84 3	98.56 56	99.71 259	99.96 1	99.96 27	99.97 4

casdiffmvs_mvg		99.12 58	99.16 52	98.99 138	99.43 138	97.73 181	98.00 184	99.62 56	99.22 65	99.55 60	99.22 124	98.93 28	99.75 241	98.66 93	99.81 103	99.50 134
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
fmvsm_s_conf0.5_n_a		99.10 60	99.20 48	98.78 170	99.55 95	96.59 243	97.79 214	99.82 26	98.21 158	99.81 28	99.53 60	98.46 63	99.84 150	99.70 25	99.97 20	99.90 15

reproduce-ours		99.09 61	98.90 77	99.67 4	99.27 168	99.49 6	98.00 184	99.42 131	99.05 95	99.48 74	99.27 110	98.29 77	99.89 81	97.61 157	99.71 162	99.62 74

our_new_method		99.09 61	98.90 77	99.67 4	99.27 168	99.49 6	98.00 184	99.42 131	99.05 95	99.48 74	99.27 110	98.29 77	99.89 81	97.61 157	99.71 162	99.62 74

fmvsm_s_conf0.5_n		99.09 61	99.26 44	98.61 198	99.55 95	96.09 258	97.74 222	99.81 27	98.55 136	99.85 22	99.55 54	98.60 51	99.84 150	99.69 27	99.98 12	99.89 16

EC-MVSNet		99.09 61	99.05 65	99.20 102	99.28 166	98.93 75	99.24 41	99.84 21	99.08 92	98.12 267	98.37 288	98.72 40	99.90 69	99.05 64	99.77 130	98.77 315

ACMH+	96.62 9	99.08 65	99.00 68	99.33 81	99.71 45	98.83 79	98.60 109	99.58 63	99.11 80	99.53 65	99.18 132	98.81 34	99.67 279	96.71 225	99.77 130	99.50 134

GeoE		99.05 66	98.99 70	99.25 96	99.44 133	98.35 117	98.73 96	99.56 77	98.42 141	98.91 176	98.81 222	98.94 26	99.91 63	98.35 110	99.73 149	99.49 138

Gipuma		99.03 67	99.16 52	98.64 189	99.94 2	98.51 104	99.32 23	99.75 37	99.58 29	98.60 221	99.62 37	98.22 84	99.51 346	97.70 153	99.73 149	97.89 376
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
v8		99.01 68	99.16 52	98.57 205	99.47 127	96.31 252	98.90 80	99.47 111	99.03 98	99.52 67	99.57 46	96.93 178	99.81 191	99.60 29	99.98 12	99.60 83

HPM-MVS_fast		99.01 68	98.82 86	99.57 20	99.71 45	99.35 16	99.00 69	99.50 94	97.33 235	98.94 173	98.86 211	98.75 38	99.82 177	97.53 163	99.71 162	99.56 106

APDe-MVS		98.99 70	98.79 89	99.60 14	99.21 182	99.15 51	98.87 84	99.48 103	97.57 208	99.35 101	99.24 119	97.83 113	99.89 81	97.88 141	99.70 169	99.75 50
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
EG-PatchMatch MVS		98.99 70	99.01 67	98.94 145	99.50 110	97.47 194	98.04 177	99.59 61	98.15 169	99.40 92	99.36 92	98.58 55	99.76 234	98.78 82	99.68 177	99.59 89

COLMAP_ROB	96.50 10	98.99 70	98.85 84	99.41 62	99.58 78	99.10 64	98.74 92	99.56 77	99.09 90	99.33 104	99.19 128	98.40 67	99.72 258	95.98 274	99.76 142	99.42 172
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Baseline_NR-MVSNet		98.98 73	98.86 83	99.36 66	99.82 19	98.55 99	97.47 257	99.57 70	99.37 50	99.21 128	99.61 40	96.76 191	99.83 167	98.06 128	99.83 96	99.71 53

v10		98.97 74	99.11 58	98.55 210	99.44 133	96.21 254	98.90 80	99.55 81	98.73 118	99.48 74	99.60 42	96.63 198	99.83 167	99.70 25	99.99 5	99.61 82

DeepC-MVS	97.60 4	98.97 74	98.93 74	99.10 117	99.35 155	97.98 154	98.01 183	99.46 114	97.56 210	99.54 61	99.50 64	98.97 24	99.84 150	98.06 128	99.92 58	99.49 138
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
baseline		98.96 76	99.02 66	98.76 175	99.38 144	97.26 207	98.49 126	99.50 94	98.86 113	99.19 130	99.06 155	98.23 81	99.69 267	98.71 90	99.76 142	99.33 212

casdiffmvs		98.95 77	99.00 68	98.81 162	99.38 144	97.33 202	97.82 209	99.57 70	99.17 76	99.35 101	99.17 136	98.35 72	99.69 267	98.46 105	99.73 149	99.41 175
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
NR-MVSNet		98.95 77	98.82 86	99.36 66	99.16 199	98.72 89	99.22 42	99.20 212	99.10 87	99.72 36	98.76 231	96.38 209	99.86 120	98.00 133	99.82 99	99.50 134

Anonymous20240529		98.93 79	98.87 80	99.12 113	99.19 189	98.22 127	99.01 67	98.99 259	99.25 63	99.54 61	99.37 88	97.04 171	99.80 198	97.89 138	99.52 233	99.35 205

DP-MVS		98.93 79	98.81 88	99.28 88	99.21 182	98.45 108	98.46 131	99.33 166	99.63 21	99.48 74	99.15 142	97.23 162	99.75 241	97.17 179	99.66 188	99.63 73

SED-MVS		98.91 81	98.72 96	99.49 51	99.49 117	99.17 43	98.10 168	99.31 173	98.03 172	99.66 47	99.02 167	98.36 69	99.88 95	96.91 201	99.62 197	99.41 175

ACMM	96.08 12	98.91 81	98.73 94	99.48 53	99.55 95	99.14 56	98.07 172	99.37 146	97.62 202	99.04 151	98.96 189	98.84 32	99.79 211	97.43 167	99.65 189	99.49 138
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DVP-MVS++		98.90 83	98.70 102	99.51 46	98.43 332	99.15 51	99.43 12	99.32 168	98.17 165	99.26 120	99.02 167	98.18 88	99.88 95	97.07 189	99.45 247	99.49 138

tfpnnormal		98.90 83	98.90 77	98.91 151	99.67 61	97.82 171	99.00 69	99.44 122	99.45 40	99.51 72	99.24 119	98.20 87	99.86 120	95.92 276	99.69 172	99.04 268

MTAPA		98.88 85	98.64 111	99.61 12	99.67 61	99.36 15	98.43 134	99.20 212	98.83 117	98.89 179	98.90 201	96.98 177	99.92 54	97.16 180	99.70 169	99.56 106

mvsany_test3		98.87 86	98.92 75	98.74 181	99.38 144	96.94 227	98.58 111	99.10 237	96.49 288	99.96 4	99.81 6	98.18 88	99.45 360	98.97 70	99.79 119	99.83 28

VPNet		98.87 86	98.83 85	99.01 136	99.70 52	97.62 188	98.43 134	99.35 155	99.47 37	99.28 114	99.05 162	96.72 194	99.82 177	98.09 125	99.36 258	99.59 89

UniMVSNet (Re)		98.87 86	98.71 99	99.35 72	99.24 175	98.73 87	97.73 224	99.38 142	98.93 108	99.12 136	98.73 234	96.77 189	99.86 120	98.63 96	99.80 114	99.46 157

UniMVSNet_NR-MVSNet		98.86 89	98.68 105	99.40 64	99.17 197	98.74 84	97.68 228	99.40 138	99.14 78	99.06 144	98.59 262	96.71 195	99.93 45	98.57 99	99.77 130	99.53 125

APD-MVS_3200maxsize		98.84 90	98.61 118	99.53 37	99.19 189	99.27 26	98.49 126	99.33 166	98.64 122	99.03 154	98.98 184	97.89 110	99.85 132	96.54 243	99.42 251	99.46 157

MVSMamba_PlusPlus		98.83 91	98.98 71	98.36 235	99.32 159	96.58 245	98.90 80	99.41 135	99.75 8	98.72 205	99.50 64	96.17 216	99.94 38	99.27 49	99.78 124	98.57 337

APD_test1		98.83 91	98.66 108	99.34 75	99.78 23	99.47 9	98.42 136	99.45 118	98.28 154	98.98 158	99.19 128	97.76 120	99.58 321	96.57 235	99.55 224	98.97 281

PM-MVS		98.82 93	98.72 96	99.12 113	99.64 70	98.54 102	97.98 189	99.68 49	97.62 202	99.34 103	99.18 132	97.54 139	99.77 228	97.79 146	99.74 146	99.04 268

DU-MVS		98.82 93	98.63 112	99.39 65	99.16 199	98.74 84	97.54 248	99.25 201	98.84 116	99.06 144	98.76 231	96.76 191	99.93 45	98.57 99	99.77 130	99.50 134

SR-MVS-dyc-post		98.81 95	98.55 123	99.57 20	99.20 186	99.38 12	98.48 129	99.30 181	98.64 122	98.95 166	98.96 189	97.49 148	99.86 120	96.56 239	99.39 254	99.45 161

3Dnovator	98.27 2	98.81 95	98.73 94	99.05 130	98.76 275	97.81 174	99.25 40	99.30 181	98.57 132	98.55 230	99.33 99	97.95 108	99.90 69	97.16 180	99.67 183	99.44 165

HPM-MVS		98.79 97	98.53 126	99.59 18	99.65 64	99.29 23	99.16 51	99.43 128	96.74 278	98.61 219	98.38 287	98.62 49	99.87 112	96.47 247	99.67 183	99.59 89
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
SteuartSystems-ACMMP		98.79 97	98.54 125	99.54 30	99.73 36	99.16 47	98.23 150	99.31 173	97.92 182	98.90 177	98.90 201	98.00 103	99.88 95	96.15 267	99.72 157	99.58 95
Skip Steuart: Steuart Systems R&D Blog.
dcpmvs_2		98.78 99	99.11 58	97.78 275	99.56 91	93.67 341	99.06 62	99.86 16	99.50 33	99.66 47	99.26 114	97.21 164	99.99 2	98.00 133	99.91 65	99.68 60

V42		98.78 99	98.78 90	98.76 175	99.44 133	97.04 220	98.27 147	99.19 216	97.87 186	99.25 124	99.16 138	96.84 182	99.78 222	99.21 55	99.84 89	99.46 157

test20.03		98.78 99	98.77 91	98.78 170	99.46 128	97.20 212	97.78 215	99.24 206	99.04 97	99.41 89	98.90 201	97.65 127	99.76 234	97.70 153	99.79 119	99.39 185

DVP-MVS		98.77 102	98.52 127	99.52 42	99.50 110	99.21 32	98.02 180	98.84 285	97.97 176	99.08 142	99.02 167	97.61 133	99.88 95	96.99 195	99.63 194	99.48 148
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
test_0402		98.76 103	98.71 99	98.93 147	99.56 91	98.14 133	98.45 133	99.34 161	99.28 61	98.95 166	98.91 198	98.34 73	99.79 211	95.63 291	99.91 65	98.86 300

ACMMP_NAP		98.75 104	98.48 135	99.57 20	99.58 78	99.29 23	97.82 209	99.25 201	96.94 267	98.78 196	99.12 147	98.02 101	99.84 150	97.13 185	99.67 183	99.59 89

SixPastTwentyTwo		98.75 104	98.62 114	99.16 108	99.83 18	97.96 158	99.28 37	98.20 330	99.37 50	99.70 40	99.65 33	92.65 310	99.93 45	99.04 65	99.84 89	99.60 83

ACMMP		98.75 104	98.50 130	99.52 42	99.56 91	99.16 47	98.87 84	99.37 146	97.16 256	98.82 193	99.01 176	97.71 123	99.87 112	96.29 259	99.69 172	99.54 117
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
XVS		98.72 107	98.45 140	99.53 37	99.46 128	99.21 32	98.65 103	99.34 161	98.62 126	97.54 309	98.63 255	97.50 145	99.83 167	96.79 214	99.53 230	99.56 106

SSC-MVS		98.71 108	98.74 92	98.62 195	99.72 42	96.08 260	98.74 92	98.64 310	99.74 10	99.67 46	99.24 119	94.57 272	99.95 24	99.11 59	99.24 278	99.82 31

SR-MVS		98.71 108	98.43 143	99.57 20	99.18 196	99.35 16	98.36 141	99.29 189	98.29 152	98.88 182	98.85 214	97.53 141	99.87 112	96.14 268	99.31 266	99.48 148

HFP-MVS		98.71 108	98.44 142	99.51 46	99.49 117	99.16 47	98.52 118	99.31 173	97.47 219	98.58 225	98.50 275	97.97 107	99.85 132	96.57 235	99.59 208	99.53 125

LPG-MVS_test		98.71 108	98.46 139	99.47 56	99.57 83	98.97 70	98.23 150	99.48 103	96.60 283	99.10 140	99.06 155	98.71 41	99.83 167	95.58 294	99.78 124	99.62 74

test_fmvs2		98.70 112	98.97 72	97.89 268	99.54 100	94.05 322	98.55 114	99.92 7	96.78 276	99.72 36	99.78 10	96.60 199	99.67 279	99.91 2	99.90 71	99.94 10

ACMMPR		98.70 112	98.42 145	99.54 30	99.52 105	99.14 56	98.52 118	99.31 173	97.47 219	98.56 228	98.54 266	97.75 121	99.88 95	96.57 235	99.59 208	99.58 95

CP-MVS		98.70 112	98.42 145	99.52 42	99.36 151	99.12 61	98.72 97	99.36 150	97.54 213	98.30 250	98.40 284	97.86 112	99.89 81	96.53 244	99.72 157	99.56 106

tt0805		98.69 115	98.62 114	98.90 154	99.75 33	99.30 21	99.15 53	96.97 365	98.86 113	98.87 186	97.62 341	98.63 48	98.96 401	99.41 42	98.29 353	98.45 344

Anonymous20240521		98.69 115	98.87 80	98.16 252	99.77 26	95.11 294	99.08 58	99.44 122	99.34 54	99.33 104	99.55 54	94.10 286	99.94 38	99.25 52	99.96 27	99.42 172

region2R		98.69 115	98.40 147	99.54 30	99.53 103	99.17 43	98.52 118	99.31 173	97.46 224	98.44 241	98.51 271	97.83 113	99.88 95	96.46 248	99.58 213	99.58 95

EI-MVSNet-UG-set		98.69 115	98.71 99	98.62 195	99.10 210	96.37 249	97.23 274	98.87 276	99.20 69	99.19 130	98.99 180	97.30 156	99.85 132	98.77 85	99.79 119	99.65 69

3Dnovator+	97.89 3	98.69 115	98.51 128	99.24 98	98.81 270	98.40 109	99.02 66	99.19 216	98.99 101	98.07 271	99.28 108	97.11 169	99.84 150	96.84 212	99.32 264	99.47 155

ZNCC-MVS		98.68 120	98.40 147	99.54 30	99.57 83	99.21 32	98.46 131	99.29 189	97.28 241	98.11 268	98.39 285	98.00 103	99.87 112	96.86 211	99.64 191	99.55 113

EI-MVSNet-Vis-set		98.68 120	98.70 102	98.63 193	99.09 213	96.40 248	97.23 274	98.86 281	99.20 69	99.18 134	98.97 186	97.29 158	99.85 132	98.72 89	99.78 124	99.64 70

CSCG		98.68 120	98.50 130	99.20 102	99.45 132	98.63 91	98.56 113	99.57 70	97.87 186	98.85 187	98.04 316	97.66 126	99.84 150	96.72 223	99.81 103	99.13 257

test_f		98.67 123	98.87 80	98.05 261	99.72 42	95.59 272	98.51 123	99.81 27	96.30 298	99.78 31	99.82 5	96.14 217	98.63 410	99.82 9	99.93 47	99.95 9

PGM-MVS		98.66 124	98.37 153	99.55 27	99.53 103	99.18 42	98.23 150	99.49 101	97.01 264	98.69 207	98.88 208	98.00 103	99.89 81	95.87 280	99.59 208	99.58 95

GBi-Net		98.65 125	98.47 137	99.17 105	98.90 251	98.24 122	99.20 45	99.44 122	98.59 128	98.95 166	99.55 54	94.14 282	99.86 120	97.77 148	99.69 172	99.41 175

test1		98.65 125	98.47 137	99.17 105	98.90 251	98.24 122	99.20 45	99.44 122	98.59 128	98.95 166	99.55 54	94.14 282	99.86 120	97.77 148	99.69 172	99.41 175

LCM-MVSNet-Re		98.64 127	98.48 135	99.11 115	98.85 262	98.51 104	98.49 126	99.83 24	98.37 142	99.69 42	99.46 73	98.21 86	99.92 54	94.13 332	99.30 269	98.91 293

mPP-MVS		98.64 127	98.34 157	99.54 30	99.54 100	99.17 43	98.63 105	99.24 206	97.47 219	98.09 270	98.68 243	97.62 132	99.89 81	96.22 262	99.62 197	99.57 100

balanced_conf03		98.63 129	98.72 96	98.38 232	98.66 303	96.68 242	98.90 80	99.42 131	98.99 101	98.97 162	99.19 128	95.81 237	99.85 132	98.77 85	99.77 130	98.60 333

TSAR-MVS + MP.		98.63 129	98.49 134	99.06 129	99.64 70	97.90 162	98.51 123	98.94 261	96.96 265	99.24 125	98.89 207	97.83 113	99.81 191	96.88 208	99.49 243	99.48 148
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
LS3D		98.63 129	98.38 152	99.36 66	97.25 396	99.38 12	99.12 57	99.32 168	99.21 67	98.44 241	98.88 208	97.31 155	99.80 198	96.58 233	99.34 262	98.92 290

RPSCF		98.62 132	98.36 154	99.42 60	99.65 64	99.42 11	98.55 114	99.57 70	97.72 196	98.90 177	99.26 114	96.12 219	99.52 341	95.72 287	99.71 162	99.32 214

GST-MVS		98.61 133	98.30 162	99.52 42	99.51 107	99.20 38	98.26 148	99.25 201	97.44 227	98.67 210	98.39 285	97.68 124	99.85 132	96.00 272	99.51 235	99.52 128

v1192		98.60 134	98.66 108	98.41 229	99.27 168	95.88 266	97.52 250	99.36 150	97.41 228	99.33 104	99.20 127	96.37 210	99.82 177	99.57 31	99.92 58	99.55 113

v1144		98.60 134	98.66 108	98.41 229	99.36 151	95.90 265	97.58 244	99.34 161	97.51 215	99.27 116	99.15 142	96.34 212	99.80 198	99.47 40	99.93 47	99.51 131

DPE-MVS		98.59 136	98.26 168	99.57 20	99.27 168	99.15 51	97.01 287	99.39 140	97.67 198	99.44 83	98.99 180	97.53 141	99.89 81	95.40 298	99.68 177	99.66 64
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MP-MVS-pluss		98.57 137	98.23 172	99.60 14	99.69 54	99.35 16	97.16 282	99.38 142	94.87 340	98.97 162	98.99 180	98.01 102	99.88 95	97.29 173	99.70 169	99.58 95
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
OPM-MVS		98.56 138	98.32 161	99.25 96	99.41 141	98.73 87	97.13 284	99.18 220	97.10 259	98.75 202	98.92 197	98.18 88	99.65 295	96.68 227	99.56 220	99.37 194
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
VDD-MVS		98.56 138	98.39 150	99.07 123	99.13 206	98.07 144	98.59 110	97.01 363	99.59 27	99.11 137	99.27 110	94.82 264	99.79 211	98.34 111	99.63 194	99.34 207

v2v482		98.56 138	98.62 114	98.37 234	99.42 139	95.81 269	97.58 244	99.16 227	97.90 184	99.28 114	99.01 176	95.98 229	99.79 211	99.33 45	99.90 71	99.51 131

XVG-ACMP-BASELINE		98.56 138	98.34 157	99.22 101	99.54 100	98.59 96	97.71 225	99.46 114	97.25 244	98.98 158	98.99 180	97.54 139	99.84 150	95.88 277	99.74 146	99.23 235

v1240		98.55 142	98.62 114	98.32 238	99.22 180	95.58 274	97.51 252	99.45 118	97.16 256	99.45 82	99.24 119	96.12 219	99.85 132	99.60 29	99.88 77	99.55 113

IterMVS-LS		98.55 142	98.70 102	98.09 254	99.48 125	94.73 303	97.22 277	99.39 140	98.97 104	99.38 95	99.31 104	96.00 224	99.93 45	98.58 97	99.97 20	99.60 83
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v144192		98.54 144	98.57 122	98.45 224	99.21 182	95.98 263	97.63 237	99.36 150	97.15 258	99.32 110	99.18 132	95.84 236	99.84 150	99.50 38	99.91 65	99.54 117

v1921920		98.54 144	98.60 119	98.38 232	99.20 186	95.76 271	97.56 246	99.36 150	97.23 250	99.38 95	99.17 136	96.02 222	99.84 150	99.57 31	99.90 71	99.54 117

SF-MVS		98.53 146	98.27 167	99.32 83	99.31 160	98.75 83	98.19 154	99.41 135	96.77 277	98.83 190	98.90 201	97.80 118	99.82 177	95.68 290	99.52 233	99.38 192

XVG-OURS		98.53 146	98.34 157	99.11 115	99.50 110	98.82 81	95.97 343	99.50 94	97.30 239	99.05 149	98.98 184	99.35 13	99.32 379	95.72 287	99.68 177	99.18 248

UGNet		98.53 146	98.45 140	98.79 167	97.94 361	96.96 225	99.08 58	98.54 314	99.10 87	96.82 350	99.47 72	96.55 201	99.84 150	98.56 102	99.94 42	99.55 113
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
WB-MVS		98.52 149	98.55 123	98.43 227	99.65 64	95.59 272	98.52 118	98.77 296	99.65 18	99.52 67	99.00 179	94.34 278	99.93 45	98.65 94	98.83 325	99.76 46

patch_mono-2		98.51 150	98.63 112	98.17 250	99.38 144	94.78 300	97.36 264	99.69 44	98.16 168	98.49 237	99.29 107	97.06 170	99.97 5	98.29 114	99.91 65	99.76 46

XVG-OURS-SEG-HR		98.49 151	98.28 164	99.14 111	99.49 117	98.83 79	96.54 311	99.48 103	97.32 237	99.11 137	98.61 259	99.33 14	99.30 382	96.23 261	98.38 349	99.28 225

FMVSNet2		98.49 151	98.40 147	98.75 177	98.90 251	97.14 218	98.61 108	99.13 233	98.59 128	99.19 130	99.28 108	94.14 282	99.82 177	97.97 135	99.80 114	99.29 223

pmmvs-eth3d		98.47 153	98.34 157	98.86 156	99.30 163	97.76 177	97.16 282	99.28 192	95.54 322	99.42 87	99.19 128	97.27 159	99.63 301	97.89 138	99.97 20	99.20 240

MP-MVS		98.46 154	98.09 187	99.54 30	99.57 83	99.22 31	98.50 125	99.19 216	97.61 205	97.58 305	98.66 248	97.40 152	99.88 95	94.72 313	99.60 204	99.54 117
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
v148		98.45 155	98.60 119	98.00 264	99.44 133	94.98 296	97.44 259	99.06 242	98.30 149	99.32 110	98.97 186	96.65 197	99.62 304	98.37 109	99.85 85	99.39 185

AllTest		98.44 156	98.20 174	99.16 108	99.50 110	98.55 99	98.25 149	99.58 63	96.80 274	98.88 182	99.06 155	97.65 127	99.57 323	94.45 320	99.61 202	99.37 194

VNet		98.42 157	98.30 162	98.79 167	98.79 274	97.29 204	98.23 150	98.66 307	99.31 57	98.85 187	98.80 223	94.80 267	99.78 222	98.13 122	99.13 297	99.31 218

ab-mvs		98.41 158	98.36 154	98.59 201	99.19 189	97.23 208	99.32 23	98.81 290	97.66 199	98.62 217	99.40 87	96.82 185	99.80 198	95.88 277	99.51 235	98.75 318

ACMP	95.32 15	98.41 158	98.09 187	99.36 66	99.51 107	98.79 82	97.68 228	99.38 142	95.76 316	98.81 195	98.82 220	98.36 69	99.82 177	94.75 310	99.77 130	99.48 148
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n_1920		98.40 160	98.92 75	96.81 340	99.74 35	90.76 391	98.15 160	99.91 9	98.33 145	99.89 16	99.55 54	95.07 257	99.88 95	99.76 18	99.93 47	99.79 36

SMA-MVS		98.40 160	98.03 194	99.51 46	99.16 199	99.21 32	98.05 175	99.22 209	94.16 356	98.98 158	99.10 151	97.52 143	99.79 211	96.45 249	99.64 191	99.53 125
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
MSP-MVS		98.40 160	98.00 197	99.61 12	99.57 83	99.25 28	98.57 112	99.35 155	97.55 212	99.31 112	97.71 334	94.61 271	99.88 95	96.14 268	99.19 289	99.70 58
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
SD-MVS		98.40 160	98.68 105	97.54 301	98.96 239	97.99 151	97.88 201	99.36 150	98.20 162	99.63 53	99.04 164	98.76 37	95.33 424	96.56 239	99.74 146	99.31 218
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
EI-MVSNet		98.40 160	98.51 128	98.04 262	99.10 210	94.73 303	97.20 278	98.87 276	98.97 104	99.06 144	99.02 167	96.00 224	99.80 198	98.58 97	99.82 99	99.60 83

WR-MVS		98.40 160	98.19 176	99.03 133	99.00 232	97.65 185	96.85 297	98.94 261	98.57 132	98.89 179	98.50 275	95.60 242	99.85 132	97.54 162	99.85 85	99.59 89

new-patchmatchnet		98.35 166	98.74 92	97.18 320	99.24 175	92.23 368	96.42 319	99.48 103	98.30 149	99.69 42	99.53 60	97.44 150	99.82 177	98.84 79	99.77 130	99.49 138

MGCFI-Net		98.34 167	98.28 164	98.51 216	98.47 326	97.59 189	98.96 74	99.48 103	99.18 75	97.40 321	95.50 391	98.66 45	99.50 347	98.18 119	98.71 333	98.44 347

sasdasda		98.34 167	98.26 168	98.58 202	98.46 328	97.82 171	98.96 74	99.46 114	99.19 73	97.46 316	95.46 394	98.59 52	99.46 358	98.08 126	98.71 333	98.46 341

canonicalmvs		98.34 167	98.26 168	98.58 202	98.46 328	97.82 171	98.96 74	99.46 114	99.19 73	97.46 316	95.46 394	98.59 52	99.46 358	98.08 126	98.71 333	98.46 341

test_cas_vis1_n_1920		98.33 170	98.68 105	97.27 317	99.69 54	92.29 366	98.03 178	99.85 18	97.62 202	99.96 4	99.62 37	93.98 287	99.74 246	99.52 37	99.86 84	99.79 36

testgi		98.32 171	98.39 150	98.13 253	99.57 83	95.54 275	97.78 215	99.49 101	97.37 232	99.19 130	97.65 338	98.96 25	99.49 350	96.50 246	98.99 314	99.34 207

DeepPCF-MVS	96.93 5	98.32 171	98.01 196	99.23 100	98.39 337	98.97 70	95.03 380	99.18 220	96.88 270	99.33 104	98.78 227	98.16 92	99.28 386	96.74 220	99.62 197	99.44 165

test_vis1_n		98.31 173	98.50 130	97.73 284	99.76 29	94.17 319	98.68 102	99.91 9	96.31 296	99.79 30	99.57 46	92.85 306	99.42 365	99.79 15	99.84 89	99.60 83

MVS_111021_LR		98.30 174	98.12 185	98.83 159	99.16 199	98.03 149	96.09 339	99.30 181	97.58 207	98.10 269	98.24 299	98.25 79	99.34 376	96.69 226	99.65 189	99.12 258

EPP-MVSNet		98.30 174	98.04 193	99.07 123	99.56 91	97.83 168	99.29 33	98.07 336	99.03 98	98.59 223	99.13 146	92.16 315	99.90 69	96.87 209	99.68 177	99.49 138

DeepC-MVS_fast	96.85 6	98.30 174	98.15 182	98.75 177	98.61 308	97.23 208	97.76 220	99.09 239	97.31 238	98.75 202	98.66 248	97.56 137	99.64 298	96.10 271	99.55 224	99.39 185
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PHI-MVS		98.29 177	97.95 202	99.34 75	98.44 331	99.16 47	98.12 165	99.38 142	96.01 308	98.06 272	98.43 282	97.80 118	99.67 279	95.69 289	99.58 213	99.20 240

Fast-Effi-MVS+-dtu		98.27 178	98.09 187	98.81 162	98.43 332	98.11 135	97.61 240	99.50 94	98.64 122	97.39 323	97.52 346	98.12 96	99.95 24	96.90 206	98.71 333	98.38 354

DELS-MVS		98.27 178	98.20 174	98.48 221	98.86 259	96.70 240	95.60 362	99.20 212	97.73 195	98.45 240	98.71 237	97.50 145	99.82 177	98.21 117	99.59 208	98.93 289
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
Effi-MVS+-dtu		98.26 180	97.90 208	99.35 72	98.02 358	99.49 6	98.02 180	99.16 227	98.29 152	97.64 300	97.99 318	96.44 206	99.95 24	96.66 228	98.93 321	98.60 333

MVSFormer		98.26 180	98.43 143	97.77 276	98.88 257	93.89 334	99.39 17	99.56 77	99.11 80	98.16 262	98.13 306	93.81 290	99.97 5	99.26 50	99.57 217	99.43 169

MVS_111021_HR		98.25 182	98.08 190	98.75 177	99.09 213	97.46 195	95.97 343	99.27 195	97.60 206	97.99 278	98.25 298	98.15 94	99.38 371	96.87 209	99.57 217	99.42 172

TAMVS		98.24 183	98.05 192	98.80 164	99.07 217	97.18 214	97.88 201	98.81 290	96.66 282	99.17 135	99.21 125	94.81 266	99.77 228	96.96 199	99.88 77	99.44 165

MM		98.22 184	97.99 198	98.91 151	98.66 303	96.97 223	97.89 200	94.44 398	99.54 30	98.95 166	99.14 145	93.50 294	99.92 54	99.80 14	99.96 27	99.85 26

diffmvs		98.22 184	98.24 171	98.17 250	99.00 232	95.44 280	96.38 321	99.58 63	97.79 192	98.53 233	98.50 275	96.76 191	99.74 246	97.95 137	99.64 191	99.34 207
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Anonymous20231206		98.21 186	98.21 173	98.20 248	99.51 107	95.43 281	98.13 162	99.32 168	96.16 301	98.93 174	98.82 220	96.00 224	99.83 167	97.32 172	99.73 149	99.36 201

VDDNet		98.21 186	97.95 202	99.01 136	99.58 78	97.74 179	99.01 67	97.29 356	99.67 16	98.97 162	99.50 64	90.45 331	99.80 198	97.88 141	99.20 286	99.48 148

IS-MVSNet		98.19 188	97.90 208	99.08 121	99.57 83	97.97 155	99.31 27	98.32 325	99.01 100	98.98 158	99.03 166	91.59 321	99.79 211	95.49 296	99.80 114	99.48 148

MVS_Test		98.18 189	98.36 154	97.67 286	98.48 325	94.73 303	98.18 155	99.02 253	97.69 197	98.04 275	99.11 148	97.22 163	99.56 326	98.57 99	98.90 323	98.71 321

TSAR-MVS + GP.		98.18 189	97.98 199	98.77 174	98.71 284	97.88 163	96.32 325	98.66 307	96.33 294	99.23 127	98.51 271	97.48 149	99.40 367	97.16 180	99.46 245	99.02 271

CNVR-MVS		98.17 191	97.87 210	99.07 123	98.67 298	98.24 122	97.01 287	98.93 264	97.25 244	97.62 301	98.34 292	97.27 159	99.57 323	96.42 250	99.33 263	99.39 185

PVSNet_Blended_VisFu		98.17 191	98.15 182	98.22 247	99.73 36	95.15 291	97.36 264	99.68 49	94.45 350	98.99 157	99.27 110	96.87 181	99.94 38	97.13 185	99.91 65	99.57 100

HPM-MVS++		98.10 193	97.64 227	99.48 53	99.09 213	99.13 59	97.52 250	98.75 300	97.46 224	96.90 345	97.83 329	96.01 223	99.84 150	95.82 284	99.35 260	99.46 157

APD-MVS		98.10 193	97.67 222	99.42 60	99.11 208	98.93 75	97.76 220	99.28 192	94.97 337	98.72 205	98.77 229	97.04 171	99.85 132	93.79 342	99.54 226	99.49 138
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_fmvs1_n		98.09 195	98.28 164	97.52 303	99.68 57	93.47 345	98.63 105	99.93 5	95.41 329	99.68 44	99.64 34	91.88 319	99.48 353	99.82 9	99.87 80	99.62 74

MVP-Stereo		98.08 196	97.92 206	98.57 205	98.96 239	96.79 234	97.90 199	99.18 220	96.41 292	98.46 239	98.95 193	95.93 233	99.60 311	96.51 245	98.98 316	99.31 218
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PMMVS2		98.07 197	98.08 190	98.04 262	99.41 141	94.59 309	94.59 394	99.40 138	97.50 216	98.82 193	98.83 217	96.83 184	99.84 150	97.50 165	99.81 103	99.71 53

ETV-MVS		98.03 198	97.86 211	98.56 209	98.69 293	98.07 144	97.51 252	99.50 94	98.10 170	97.50 313	95.51 390	98.41 66	99.88 95	96.27 260	99.24 278	97.71 388

Effi-MVS+		98.02 199	97.82 213	98.62 195	98.53 322	97.19 213	97.33 266	99.68 49	97.30 239	96.68 354	97.46 350	98.56 56	99.80 198	96.63 229	98.20 356	98.86 300

MSLP-MVS++		98.02 199	98.14 184	97.64 290	98.58 315	95.19 290	97.48 255	99.23 208	97.47 219	97.90 282	98.62 257	97.04 171	98.81 407	97.55 160	99.41 252	98.94 288

EIA-MVS		98.00 201	97.74 217	98.80 164	98.72 281	98.09 138	98.05 175	99.60 60	97.39 230	96.63 356	95.55 389	97.68 124	99.80 198	96.73 222	99.27 273	98.52 339

MCST-MVS		98.00 201	97.63 228	99.10 117	99.24 175	98.17 130	96.89 296	98.73 303	95.66 317	97.92 280	97.70 336	97.17 165	99.66 290	96.18 266	99.23 281	99.47 155

K. test v3		98.00 201	97.66 225	99.03 133	99.79 22	97.56 190	99.19 49	92.47 410	99.62 24	99.52 67	99.66 29	89.61 336	99.96 12	99.25 52	99.81 103	99.56 106

HQP_MVS		97.99 204	97.67 222	98.93 147	99.19 189	97.65 185	97.77 217	99.27 195	98.20 162	97.79 292	97.98 319	94.90 260	99.70 263	94.42 322	99.51 235	99.45 161

MDA-MVSNet-bldmvs		97.94 205	97.91 207	98.06 259	99.44 133	94.96 297	96.63 309	99.15 232	98.35 143	98.83 190	99.11 148	94.31 279	99.85 132	96.60 232	98.72 331	99.37 194

ttmdpeth		97.91 206	98.02 195	97.58 295	98.69 293	94.10 321	98.13 162	98.90 270	97.95 178	97.32 326	99.58 44	95.95 232	98.75 408	96.41 251	99.22 282	99.87 20

Anonymous202405211		97.90 207	97.50 235	99.08 121	98.90 251	98.25 121	98.53 117	96.16 380	98.87 112	99.11 137	98.86 211	90.40 332	99.78 222	97.36 170	99.31 266	99.19 245

LF4IMVS		97.90 207	97.69 221	98.52 215	99.17 197	97.66 184	97.19 281	99.47 111	96.31 296	97.85 288	98.20 303	96.71 195	99.52 341	94.62 314	99.72 157	98.38 354

UnsupCasMVSNet_eth		97.89 209	97.60 230	98.75 177	99.31 160	97.17 215	97.62 238	99.35 155	98.72 120	98.76 201	98.68 243	92.57 311	99.74 246	97.76 152	95.60 409	99.34 207

TinyColmap		97.89 209	97.98 199	97.60 293	98.86 259	94.35 314	96.21 331	99.44 122	97.45 226	99.06 144	98.88 208	97.99 106	99.28 386	94.38 326	99.58 213	99.18 248

RRT-MVS		97.88 211	97.98 199	97.61 292	98.15 351	93.77 338	98.97 73	99.64 54	99.16 77	98.69 207	99.42 80	91.60 320	99.89 81	97.63 156	98.52 347	99.16 255

OMC-MVS		97.88 211	97.49 236	99.04 132	98.89 256	98.63 91	96.94 291	99.25 201	95.02 335	98.53 233	98.51 271	97.27 159	99.47 356	93.50 350	99.51 235	99.01 272

CANet		97.87 213	97.76 215	98.19 249	97.75 368	95.51 277	96.76 302	99.05 245	97.74 194	96.93 339	98.21 302	95.59 243	99.89 81	97.86 143	99.93 47	99.19 245

xiu_mvs_v1_base_debu		97.86 214	98.17 178	96.92 333	98.98 236	93.91 331	96.45 316	99.17 224	97.85 188	98.41 244	97.14 362	98.47 60	99.92 54	98.02 130	99.05 303	96.92 401

xiu_mvs_v1_base		97.86 214	98.17 178	96.92 333	98.98 236	93.91 331	96.45 316	99.17 224	97.85 188	98.41 244	97.14 362	98.47 60	99.92 54	98.02 130	99.05 303	96.92 401

xiu_mvs_v1_base_debi		97.86 214	98.17 178	96.92 333	98.98 236	93.91 331	96.45 316	99.17 224	97.85 188	98.41 244	97.14 362	98.47 60	99.92 54	98.02 130	99.05 303	96.92 401

NCCC		97.86 214	97.47 239	99.05 130	98.61 308	98.07 144	96.98 289	98.90 270	97.63 201	97.04 335	97.93 324	95.99 228	99.66 290	95.31 299	98.82 327	99.43 169

PMVS	91.26 20	97.86 214	97.94 204	97.65 288	99.71 45	97.94 160	98.52 118	98.68 306	98.99 101	97.52 311	99.35 93	97.41 151	98.18 415	91.59 380	99.67 183	96.82 404
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
IterMVS-SCA-FT		97.85 219	98.18 177	96.87 336	99.27 168	91.16 385	95.53 364	99.25 201	99.10 87	99.41 89	99.35 93	93.10 299	99.96 12	98.65 94	99.94 42	99.49 138

D2MVS		97.84 220	97.84 212	97.83 271	99.14 204	94.74 302	96.94 291	98.88 274	95.84 314	98.89 179	98.96 189	94.40 276	99.69 267	97.55 160	99.95 34	99.05 264

CPTT-MVS		97.84 220	97.36 244	99.27 91	99.31 160	98.46 107	98.29 145	99.27 195	94.90 339	97.83 289	98.37 288	94.90 260	99.84 150	93.85 341	99.54 226	99.51 131

mvs_anonymous		97.83 222	98.16 181	96.87 336	98.18 349	91.89 370	97.31 268	98.90 270	97.37 232	98.83 190	99.46 73	96.28 213	99.79 211	98.90 74	98.16 360	98.95 284

h-mvs33		97.77 223	97.33 247	99.10 117	99.21 182	97.84 167	98.35 142	98.57 313	99.11 80	98.58 225	99.02 167	88.65 345	99.96 12	98.11 123	96.34 401	99.49 138

test_vis1_rt		97.75 224	97.72 220	97.83 271	98.81 270	96.35 250	97.30 269	99.69 44	94.61 344	97.87 285	98.05 315	96.26 214	98.32 413	98.74 87	98.18 357	98.82 303

IterMVS		97.73 225	98.11 186	96.57 346	99.24 175	90.28 394	95.52 366	99.21 210	98.86 113	99.33 104	99.33 99	93.11 298	99.94 38	98.49 104	99.94 42	99.48 148
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test_fmvs1		97.72 226	97.94 204	97.07 327	98.66 303	92.39 363	97.68 228	99.81 27	95.20 333	99.54 61	99.44 78	91.56 322	99.41 366	99.78 17	99.77 130	99.40 184

MSDG		97.71 227	97.52 234	98.28 243	98.91 250	96.82 232	94.42 397	99.37 146	97.65 200	98.37 249	98.29 297	97.40 152	99.33 378	94.09 333	99.22 282	98.68 328

CDS-MVSNet		97.69 228	97.35 245	98.69 184	98.73 279	97.02 222	96.92 295	98.75 300	95.89 313	98.59 223	98.67 245	92.08 317	99.74 246	96.72 223	99.81 103	99.32 214
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MS-PatchMatch		97.68 229	97.75 216	97.45 309	98.23 347	93.78 337	97.29 270	98.84 285	96.10 303	98.64 214	98.65 250	96.04 221	99.36 372	96.84 212	99.14 295	99.20 240

Fast-Effi-MVS+		97.67 230	97.38 242	98.57 205	98.71 284	97.43 198	97.23 274	99.45 118	94.82 341	96.13 370	96.51 370	98.52 58	99.91 63	96.19 264	98.83 325	98.37 356

EU-MVSNet		97.66 231	98.50 130	95.13 382	99.63 74	85.84 412	98.35 142	98.21 329	98.23 156	99.54 61	99.46 73	95.02 258	99.68 276	98.24 115	99.87 80	99.87 20

pmmvs5		97.64 232	97.49 236	98.08 257	99.14 204	95.12 293	96.70 306	99.05 245	93.77 363	98.62 217	98.83 217	93.23 295	99.75 241	98.33 113	99.76 142	99.36 201

N_pmnet		97.63 233	97.17 254	98.99 138	99.27 168	97.86 165	95.98 342	93.41 407	95.25 331	99.47 78	98.90 201	95.63 241	99.85 132	96.91 201	99.73 149	99.27 226

mvsany_test1		97.60 234	97.54 232	97.77 276	97.72 369	95.35 283	95.36 372	97.13 361	94.13 357	99.71 38	99.33 99	97.93 109	99.30 382	97.60 159	98.94 320	98.67 329

YYNet1		97.60 234	97.67 222	97.39 313	99.04 226	93.04 352	95.27 373	98.38 324	97.25 244	98.92 175	98.95 193	95.48 248	99.73 251	96.99 195	98.74 329	99.41 175

MDA-MVSNet_test_wron		97.60 234	97.66 225	97.41 312	99.04 226	93.09 348	95.27 373	98.42 321	97.26 243	98.88 182	98.95 193	95.43 249	99.73 251	97.02 192	98.72 331	99.41 175

pmmvs4		97.58 237	97.28 248	98.51 216	98.84 263	96.93 228	95.40 371	98.52 316	93.60 365	98.61 219	98.65 250	95.10 256	99.60 311	96.97 198	99.79 119	98.99 277

mvsmamba		97.57 238	97.26 249	98.51 216	98.69 293	96.73 239	98.74 92	97.25 357	97.03 263	97.88 284	99.23 123	90.95 326	99.87 112	96.61 231	99.00 312	98.91 293

PVSNet_BlendedMVS		97.55 239	97.53 233	97.60 293	98.92 247	93.77 338	96.64 308	99.43 128	94.49 346	97.62 301	99.18 132	96.82 185	99.67 279	94.73 311	99.93 47	99.36 201

GDP-MVS		97.50 240	97.11 259	98.67 186	99.02 230	96.85 231	98.16 159	99.71 40	98.32 147	98.52 235	98.54 266	83.39 381	99.95 24	98.79 81	99.56 220	99.19 245

ppachtmachnet_test		97.50 240	97.74 217	96.78 342	98.70 288	91.23 384	94.55 395	99.05 245	96.36 293	99.21 128	98.79 225	96.39 207	99.78 222	96.74 220	99.82 99	99.34 207

FMVSNet3		97.50 240	97.24 251	98.29 242	98.08 356	95.83 268	97.86 205	98.91 269	97.89 185	98.95 166	98.95 193	87.06 351	99.81 191	97.77 148	99.69 172	99.23 235

CHOSEN 1792x2688		97.49 243	97.14 258	98.54 213	99.68 57	96.09 258	96.50 314	99.62 56	91.58 388	98.84 189	98.97 186	92.36 312	99.88 95	96.76 218	99.95 34	99.67 63

CLD-MVS		97.49 243	97.16 255	98.48 221	99.07 217	97.03 221	94.71 387	99.21 210	94.46 348	98.06 272	97.16 360	97.57 136	99.48 353	94.46 319	99.78 124	98.95 284
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
hse-mvs2		97.46 245	97.07 260	98.64 189	98.73 279	97.33 202	97.45 258	97.64 349	99.11 80	98.58 225	97.98 319	88.65 345	99.79 211	98.11 123	97.39 384	98.81 307

Vis-MVSNet (Re-imp)		97.46 245	97.16 255	98.34 237	99.55 95	96.10 255	98.94 77	98.44 319	98.32 147	98.16 262	98.62 257	88.76 341	99.73 251	93.88 339	99.79 119	99.18 248

jason		97.45 247	97.35 245	97.76 279	99.24 175	93.93 330	95.86 352	98.42 321	94.24 354	98.50 236	98.13 306	94.82 264	99.91 63	97.22 177	99.73 149	99.43 169
jason: jason.
CL-MVSNet_self_test		97.44 248	97.22 252	98.08 257	98.57 317	95.78 270	94.30 400	98.79 293	96.58 285	98.60 221	98.19 304	94.74 270	99.64 298	96.41 251	98.84 324	98.82 303

MVS_0304		97.44 248	97.01 264	98.72 182	96.42 414	96.74 238	97.20 278	91.97 414	98.46 140	98.30 250	98.79 225	92.74 308	99.91 63	99.30 47	99.94 42	99.52 128

DSMNet-mixed		97.42 250	97.60 230	96.87 336	99.15 203	91.46 375	98.54 116	99.12 234	92.87 376	97.58 305	99.63 36	96.21 215	99.90 69	95.74 286	99.54 226	99.27 226

USDC		97.41 251	97.40 240	97.44 310	98.94 241	93.67 341	95.17 376	99.53 88	94.03 360	98.97 162	99.10 151	95.29 251	99.34 376	95.84 283	99.73 149	99.30 221

BP-MVS1		97.40 252	96.97 265	98.71 183	99.07 217	96.81 233	98.34 144	97.18 358	98.58 131	98.17 259	98.61 259	84.01 377	99.94 38	98.97 70	99.78 124	99.37 194

our_test_3		97.39 253	97.73 219	96.34 352	98.70 288	89.78 397	94.61 393	98.97 260	96.50 287	99.04 151	98.85 214	95.98 229	99.84 150	97.26 175	99.67 183	99.41 175

c3_l		97.36 254	97.37 243	97.31 314	98.09 355	93.25 347	95.01 381	99.16 227	97.05 260	98.77 199	98.72 236	92.88 304	99.64 298	96.93 200	99.76 142	99.05 264

alignmvs		97.35 255	96.88 272	98.78 170	98.54 320	98.09 138	97.71 225	97.69 345	99.20 69	97.59 304	95.90 383	88.12 350	99.55 330	98.18 119	98.96 318	98.70 324

Patchmtry		97.35 255	96.97 265	98.50 220	97.31 395	96.47 247	98.18 155	98.92 267	98.95 107	98.78 196	99.37 88	85.44 366	99.85 132	95.96 275	99.83 96	99.17 252

DP-MVS Recon		97.33 257	96.92 269	98.57 205	99.09 213	97.99 151	96.79 299	99.35 155	93.18 370	97.71 296	98.07 314	95.00 259	99.31 380	93.97 335	99.13 297	98.42 351

QAPM		97.31 258	96.81 279	98.82 160	98.80 273	97.49 193	99.06 62	99.19 216	90.22 400	97.69 298	99.16 138	96.91 179	99.90 69	90.89 393	99.41 252	99.07 262

UnsupCasMVSNet_bld		97.30 259	96.92 269	98.45 224	99.28 166	96.78 237	96.20 332	99.27 195	95.42 326	98.28 254	98.30 296	93.16 297	99.71 259	94.99 304	97.37 385	98.87 299

F-COLMAP		97.30 259	96.68 286	99.14 111	99.19 189	98.39 110	97.27 273	99.30 181	92.93 374	96.62 357	98.00 317	95.73 239	99.68 276	92.62 368	98.46 348	99.35 205

1112_ss		97.29 261	96.86 273	98.58 202	99.34 157	96.32 251	96.75 303	99.58 63	93.14 371	96.89 346	97.48 348	92.11 316	99.86 120	96.91 201	99.54 226	99.57 100

CANet_DTU		97.26 262	97.06 261	97.84 270	97.57 379	94.65 307	96.19 333	98.79 293	97.23 250	95.14 391	98.24 299	93.22 296	99.84 150	97.34 171	99.84 89	99.04 268

Patchmatch-RL test		97.26 262	97.02 263	97.99 265	99.52 105	95.53 276	96.13 337	99.71 40	97.47 219	99.27 116	99.16 138	84.30 375	99.62 304	97.89 138	99.77 130	98.81 307

CDPH-MVS		97.26 262	96.66 289	99.07 123	99.00 232	98.15 131	96.03 341	99.01 256	91.21 394	97.79 292	97.85 328	96.89 180	99.69 267	92.75 365	99.38 257	99.39 185

PatchMatch-RL		97.24 265	96.78 280	98.61 198	99.03 229	97.83 168	96.36 322	99.06 242	93.49 368	97.36 325	97.78 330	95.75 238	99.49 350	93.44 351	98.77 328	98.52 339

eth_miper_zixun_eth		97.23 266	97.25 250	97.17 322	98.00 359	92.77 356	94.71 387	99.18 220	97.27 242	98.56 228	98.74 233	91.89 318	99.69 267	97.06 191	99.81 103	99.05 264

sss		97.21 267	96.93 267	98.06 259	98.83 265	95.22 289	96.75 303	98.48 318	94.49 346	97.27 327	97.90 325	92.77 307	99.80 198	96.57 235	99.32 264	99.16 255

LFMVS		97.20 268	96.72 283	98.64 189	98.72 281	96.95 226	98.93 78	94.14 404	99.74 10	98.78 196	99.01 176	84.45 372	99.73 251	97.44 166	99.27 273	99.25 230

HyFIR lowres test		97.19 269	96.60 293	98.96 142	99.62 76	97.28 205	95.17 376	99.50 94	94.21 355	99.01 155	98.32 295	86.61 354	99.99 2	97.10 187	99.84 89	99.60 83

miper_lstm_enhance		97.18 270	97.16 255	97.25 319	98.16 350	92.85 354	95.15 378	99.31 173	97.25 244	98.74 204	98.78 227	90.07 333	99.78 222	97.19 178	99.80 114	99.11 259

CNLPA		97.17 271	96.71 284	98.55 210	98.56 318	98.05 148	96.33 324	98.93 264	96.91 269	97.06 334	97.39 353	94.38 277	99.45 360	91.66 377	99.18 291	98.14 365

xiu_mvs_v2_base		97.16 272	97.49 236	96.17 361	98.54 320	92.46 361	95.45 368	98.84 285	97.25 244	97.48 315	96.49 371	98.31 75	99.90 69	96.34 256	98.68 338	96.15 412

AdaColmap		97.14 273	96.71 284	98.46 223	98.34 339	97.80 175	96.95 290	98.93 264	95.58 321	96.92 340	97.66 337	95.87 235	99.53 337	90.97 390	99.14 295	98.04 370

train_agg		97.10 274	96.45 299	99.07 123	98.71 284	98.08 142	95.96 345	99.03 250	91.64 386	95.85 376	97.53 344	96.47 204	99.76 234	93.67 344	99.16 292	99.36 201

OpenMVS	96.65 7	97.09 275	96.68 286	98.32 238	98.32 340	97.16 216	98.86 86	99.37 146	89.48 404	96.29 368	99.15 142	96.56 200	99.90 69	92.90 359	99.20 286	97.89 376

PS-MVSNAJ		97.08 276	97.39 241	96.16 363	98.56 318	92.46 361	95.24 375	98.85 284	97.25 244	97.49 314	95.99 380	98.07 97	99.90 69	96.37 253	98.67 339	96.12 413

miper_ehance_all_eth		97.06 277	97.03 262	97.16 324	97.83 365	93.06 349	94.66 390	99.09 239	95.99 309	98.69 207	98.45 280	92.73 309	99.61 310	96.79 214	99.03 307	98.82 303

lupinMVS		97.06 277	96.86 273	97.65 288	98.88 257	93.89 334	95.48 367	97.97 338	93.53 366	98.16 262	97.58 342	93.81 290	99.91 63	96.77 217	99.57 217	99.17 252

API-MVS		97.04 279	96.91 271	97.42 311	97.88 364	98.23 126	98.18 155	98.50 317	97.57 208	97.39 323	96.75 367	96.77 189	99.15 395	90.16 397	99.02 310	94.88 418

cl____		97.02 280	96.83 276	97.58 295	97.82 366	94.04 324	94.66 390	99.16 227	97.04 261	98.63 215	98.71 237	88.68 344	99.69 267	97.00 193	99.81 103	99.00 276

DIV-MVS_self_test		97.02 280	96.84 275	97.58 295	97.82 366	94.03 325	94.66 390	99.16 227	97.04 261	98.63 215	98.71 237	88.69 342	99.69 267	97.00 193	99.81 103	99.01 272

RPMNet		97.02 280	96.93 267	97.30 315	97.71 372	94.22 315	98.11 166	99.30 181	99.37 50	96.91 342	99.34 97	86.72 353	99.87 112	97.53 163	97.36 387	97.81 381

HQP-MVS		97.00 283	96.49 298	98.55 210	98.67 298	96.79 234	96.29 327	99.04 248	96.05 304	95.55 382	96.84 365	93.84 288	99.54 335	92.82 362	99.26 276	99.32 214

FA-MVS(test-final)		96.99 284	96.82 277	97.50 305	98.70 288	94.78 300	99.34 20	96.99 364	95.07 334	98.48 238	99.33 99	88.41 348	99.65 295	96.13 270	98.92 322	98.07 369

new_pmnet		96.99 284	96.76 281	97.67 286	98.72 281	94.89 298	95.95 347	98.20 330	92.62 379	98.55 230	98.54 266	94.88 263	99.52 341	93.96 336	99.44 250	98.59 336

Test_1112_low_res		96.99 284	96.55 295	98.31 240	99.35 155	95.47 279	95.84 355	99.53 88	91.51 390	96.80 351	98.48 278	91.36 323	99.83 167	96.58 233	99.53 230	99.62 74

PVSNet_Blended		96.88 287	96.68 286	97.47 308	98.92 247	93.77 338	94.71 387	99.43 128	90.98 396	97.62 301	97.36 356	96.82 185	99.67 279	94.73 311	99.56 220	98.98 278

MVSTER		96.86 288	96.55 295	97.79 274	97.91 363	94.21 317	97.56 246	98.87 276	97.49 218	99.06 144	99.05 162	80.72 390	99.80 198	98.44 106	99.82 99	99.37 194

BH-untuned		96.83 289	96.75 282	97.08 325	98.74 278	93.33 346	96.71 305	98.26 327	96.72 279	98.44 241	97.37 355	95.20 253	99.47 356	91.89 374	97.43 382	98.44 347

BH-RMVSNet		96.83 289	96.58 294	97.58 295	98.47 326	94.05 322	96.67 307	97.36 352	96.70 281	97.87 285	97.98 319	95.14 255	99.44 362	90.47 396	98.58 345	99.25 230

PAPM_NR		96.82 291	96.32 302	98.30 241	99.07 217	96.69 241	97.48 255	98.76 297	95.81 315	96.61 358	96.47 373	94.12 285	99.17 393	90.82 394	97.78 373	99.06 263

MG-MVS		96.77 292	96.61 291	97.26 318	98.31 341	93.06 349	95.93 348	98.12 335	96.45 291	97.92 280	98.73 234	93.77 292	99.39 369	91.19 388	99.04 306	99.33 212

test_yl		96.69 293	96.29 303	97.90 266	98.28 342	95.24 287	97.29 270	97.36 352	98.21 158	98.17 259	97.86 326	86.27 356	99.55 330	94.87 308	98.32 350	98.89 295

DCV-MVSNet		96.69 293	96.29 303	97.90 266	98.28 342	95.24 287	97.29 270	97.36 352	98.21 158	98.17 259	97.86 326	86.27 356	99.55 330	94.87 308	98.32 350	98.89 295

WTY-MVS		96.67 295	96.27 305	97.87 269	98.81 270	94.61 308	96.77 301	97.92 340	94.94 338	97.12 330	97.74 333	91.11 325	99.82 177	93.89 338	98.15 361	99.18 248

PatchT		96.65 296	96.35 300	97.54 301	97.40 392	95.32 285	97.98 189	96.64 374	99.33 55	96.89 346	99.42 80	84.32 374	99.81 191	97.69 155	97.49 378	97.48 394

TAPA-MVS	96.21 11	96.63 297	95.95 308	98.65 187	98.93 243	98.09 138	96.93 293	99.28 192	83.58 417	98.13 266	97.78 330	96.13 218	99.40 367	93.52 348	99.29 271	98.45 344
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MIMVSNet		96.62 298	96.25 306	97.71 285	99.04 226	94.66 306	99.16 51	96.92 369	97.23 250	97.87 285	99.10 151	86.11 360	99.65 295	91.65 378	99.21 285	98.82 303

Patchmatch-test		96.55 299	96.34 301	97.17 322	98.35 338	93.06 349	98.40 137	97.79 341	97.33 235	98.41 244	98.67 245	83.68 380	99.69 267	95.16 302	99.31 266	98.77 315

PMMVS		96.51 300	95.98 307	98.09 254	97.53 384	95.84 267	94.92 383	98.84 285	91.58 388	96.05 374	95.58 388	95.68 240	99.66 290	95.59 293	98.09 364	98.76 317

PLC	94.65 16	96.51 300	95.73 312	98.85 157	98.75 277	97.91 161	96.42 319	99.06 242	90.94 397	95.59 379	97.38 354	94.41 275	99.59 315	90.93 391	98.04 370	99.05 264
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
114514_t		96.50 302	95.77 310	98.69 184	99.48 125	97.43 198	97.84 208	99.55 81	81.42 420	96.51 362	98.58 263	95.53 244	99.67 279	93.41 352	99.58 213	98.98 278

test1111		96.49 303	96.82 277	95.52 375	99.42 139	87.08 409	99.22 42	87.14 423	99.11 80	99.46 79	99.58 44	88.69 342	99.86 120	98.80 80	99.95 34	99.62 74

MAR-MVS		96.47 304	95.70 313	98.79 167	97.92 362	99.12 61	98.28 146	98.60 312	92.16 384	95.54 385	96.17 378	94.77 269	99.52 341	89.62 399	98.23 354	97.72 387
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
ECVR-MVS		96.42 305	96.61 291	95.85 367	99.38 144	88.18 405	99.22 42	86.00 425	99.08 92	99.36 99	99.57 46	88.47 347	99.82 177	98.52 103	99.95 34	99.54 117

SCA		96.41 306	96.66 289	95.67 371	98.24 345	88.35 403	95.85 354	96.88 370	96.11 302	97.67 299	98.67 245	93.10 299	99.85 132	94.16 328	99.22 282	98.81 307

DPM-MVS		96.32 307	95.59 319	98.51 216	98.76 275	97.21 211	94.54 396	98.26 327	91.94 385	96.37 366	97.25 358	93.06 301	99.43 363	91.42 383	98.74 329	98.89 295

CMPMVS	75.91 23	96.29 308	95.44 325	98.84 158	96.25 417	98.69 90	97.02 286	99.12 234	88.90 407	97.83 289	98.86 211	89.51 337	98.90 405	91.92 373	99.51 235	98.92 290
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CR-MVSNet		96.28 309	95.95 308	97.28 316	97.71 372	94.22 315	98.11 166	98.92 267	92.31 382	96.91 342	99.37 88	85.44 366	99.81 191	97.39 169	97.36 387	97.81 381

MonoMVSNet		96.25 310	96.53 297	95.39 379	96.57 410	91.01 386	98.82 90	97.68 346	98.57 132	98.03 276	99.37 88	90.92 327	97.78 417	94.99 304	93.88 417	97.38 397

CVMVSNet		96.25 310	97.21 253	93.38 401	99.10 210	80.56 428	97.20 278	98.19 332	96.94 267	99.00 156	99.02 167	89.50 338	99.80 198	96.36 255	99.59 208	99.78 39

AUN-MVS		96.24 312	95.45 324	98.60 200	98.70 288	97.22 210	97.38 261	97.65 347	95.95 311	95.53 386	97.96 323	82.11 389	99.79 211	96.31 257	97.44 381	98.80 312

EPNet		96.14 313	95.44 325	98.25 244	90.76 429	95.50 278	97.92 196	94.65 396	98.97 104	92.98 412	98.85 214	89.12 340	99.87 112	95.99 273	99.68 177	99.39 185
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
wuyk23d		96.06 314	97.62 229	91.38 404	98.65 307	98.57 98	98.85 87	96.95 367	96.86 272	99.90 13	99.16 138	99.18 18	98.40 412	89.23 401	99.77 130	77.18 424

Syy-MVS		96.04 315	95.56 321	97.49 306	97.10 400	94.48 310	96.18 334	96.58 375	95.65 318	94.77 394	92.29 421	91.27 324	99.36 372	98.17 121	98.05 368	98.63 331

miper_enhance_ethall		96.01 316	95.74 311	96.81 340	96.41 415	92.27 367	93.69 409	98.89 273	91.14 395	98.30 250	97.35 357	90.58 330	99.58 321	96.31 257	99.03 307	98.60 333

FMVSNet5		96.01 316	95.20 335	98.41 229	97.53 384	96.10 255	98.74 92	99.50 94	97.22 253	98.03 276	99.04 164	69.80 412	99.88 95	97.27 174	99.71 162	99.25 230

dmvs_re		95.98 318	95.39 328	97.74 282	98.86 259	97.45 196	98.37 140	95.69 391	97.95 178	96.56 359	95.95 381	90.70 329	97.68 418	88.32 403	96.13 405	98.11 366

baseline1		95.96 319	95.44 325	97.52 303	98.51 324	93.99 328	98.39 138	96.09 382	98.21 158	98.40 248	97.76 332	86.88 352	99.63 301	95.42 297	89.27 422	98.95 284

HY-MVS	95.94 13	95.90 320	95.35 330	97.55 300	97.95 360	94.79 299	98.81 91	96.94 368	92.28 383	95.17 390	98.57 264	89.90 335	99.75 241	91.20 387	97.33 389	98.10 367

MVStest1		95.86 321	95.60 317	96.63 345	95.87 421	91.70 372	97.93 193	98.94 261	98.03 172	99.56 57	99.66 29	71.83 410	98.26 414	99.35 44	99.24 278	99.91 13

GA-MVS		95.86 321	95.32 331	97.49 306	98.60 310	94.15 320	93.83 407	97.93 339	95.49 324	96.68 354	97.42 352	83.21 382	99.30 382	96.22 262	98.55 346	99.01 272

OpenMVS_ROB	95.38 14	95.84 323	95.18 336	97.81 273	98.41 336	97.15 217	97.37 263	98.62 311	83.86 416	98.65 213	98.37 288	94.29 280	99.68 276	88.41 402	98.62 343	96.60 407

cl22		95.79 324	95.39 328	96.98 330	96.77 407	92.79 355	94.40 398	98.53 315	94.59 345	97.89 283	98.17 305	82.82 386	99.24 388	96.37 253	99.03 307	98.92 290

1314		95.74 325	95.60 317	96.17 361	97.53 384	92.75 357	98.07 172	98.31 326	91.22 393	94.25 400	96.68 368	95.53 244	99.03 397	91.64 379	97.18 391	96.74 405

WB-MVSnew		95.73 326	95.57 320	96.23 358	96.70 408	90.70 392	96.07 340	93.86 405	95.60 320	97.04 335	95.45 397	96.00 224	99.55 330	91.04 389	98.31 352	98.43 349

PVSNet	93.40 17	95.67 327	95.70 313	95.57 374	98.83 265	88.57 401	92.50 414	97.72 343	92.69 378	96.49 365	96.44 374	93.72 293	99.43 363	93.61 345	99.28 272	98.71 321

FE-MVS		95.66 328	94.95 341	97.77 276	98.53 322	95.28 286	99.40 16	96.09 382	93.11 372	97.96 279	99.26 114	79.10 399	99.77 228	92.40 371	98.71 333	98.27 360

tttt0517		95.64 329	94.98 339	97.64 290	99.36 151	93.81 336	98.72 97	90.47 418	98.08 171	98.67 210	98.34 292	73.88 408	99.92 54	97.77 148	99.51 235	99.20 240

PatchmatchNet		95.58 330	95.67 315	95.30 381	97.34 394	87.32 408	97.65 234	96.65 373	95.30 330	97.07 333	98.69 241	84.77 369	99.75 241	94.97 306	98.64 340	98.83 302
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
TR-MVS		95.55 331	95.12 337	96.86 339	97.54 382	93.94 329	96.49 315	96.53 377	94.36 353	97.03 337	96.61 369	94.26 281	99.16 394	86.91 409	96.31 402	97.47 395

JIA-IIPM		95.52 332	95.03 338	97.00 328	96.85 405	94.03 325	96.93 293	95.82 387	99.20 69	94.63 398	99.71 19	83.09 383	99.60 311	94.42 322	94.64 413	97.36 398

CHOSEN 280x420		95.51 333	95.47 322	95.65 373	98.25 344	88.27 404	93.25 411	98.88 274	93.53 366	94.65 397	97.15 361	86.17 358	99.93 45	97.41 168	99.93 47	98.73 320

ADS-MVSNet2		95.43 334	94.98 339	96.76 343	98.14 352	91.74 371	97.92 196	97.76 342	90.23 398	96.51 362	98.91 198	85.61 363	99.85 132	92.88 360	96.90 394	98.69 325

PAPR		95.29 335	94.47 346	97.75 280	97.50 390	95.14 292	94.89 384	98.71 305	91.39 392	95.35 389	95.48 393	94.57 272	99.14 396	84.95 412	97.37 385	98.97 281

thisisatest0530		95.27 336	94.45 347	97.74 282	99.19 189	94.37 313	97.86 205	90.20 419	97.17 255	98.22 257	97.65 338	73.53 409	99.90 69	96.90 206	99.35 260	98.95 284

ADS-MVSNet		95.24 337	94.93 342	96.18 360	98.14 352	90.10 396	97.92 196	97.32 355	90.23 398	96.51 362	98.91 198	85.61 363	99.74 246	92.88 360	96.90 394	98.69 325

WBMVS		95.18 338	94.78 344	96.37 351	97.68 377	89.74 398	95.80 356	98.73 303	97.54 213	98.30 250	98.44 281	70.06 411	99.82 177	96.62 230	99.87 80	99.54 117

BH-w/o		95.13 339	94.89 343	95.86 366	98.20 348	91.31 379	95.65 360	97.37 351	93.64 364	96.52 361	95.70 387	93.04 302	99.02 398	88.10 404	95.82 408	97.24 399

tpmrst		95.07 340	95.46 323	93.91 394	97.11 399	84.36 420	97.62 238	96.96 366	94.98 336	96.35 367	98.80 223	85.46 365	99.59 315	95.60 292	96.23 403	97.79 384

pmmvs3		95.03 341	94.40 348	96.93 332	97.70 374	92.53 360	95.08 379	97.71 344	88.57 408	97.71 296	98.08 313	79.39 397	99.82 177	96.19 264	99.11 301	98.43 349

tpmvs		95.02 342	95.25 332	94.33 388	96.39 416	85.87 411	98.08 170	96.83 371	95.46 325	95.51 387	98.69 241	85.91 361	99.53 337	94.16 328	96.23 403	97.58 392

reproduce_monomvs		95.00 343	95.25 332	94.22 390	97.51 389	83.34 422	97.86 205	98.44 319	98.51 137	99.29 113	99.30 105	67.68 417	99.56 326	98.89 76	99.81 103	99.77 41

EPNet_dtu		94.93 344	94.78 344	95.38 380	93.58 425	87.68 407	96.78 300	95.69 391	97.35 234	89.14 422	98.09 312	88.15 349	99.49 350	94.95 307	99.30 269	98.98 278
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
cascas		94.79 345	94.33 351	96.15 364	96.02 420	92.36 365	92.34 416	99.26 200	85.34 415	95.08 392	94.96 403	92.96 303	98.53 411	94.41 325	98.59 344	97.56 393

tpm		94.67 346	94.34 350	95.66 372	97.68 377	88.42 402	97.88 201	94.90 394	94.46 348	96.03 375	98.56 265	78.66 400	99.79 211	95.88 277	95.01 412	98.78 314

test0.0.03 1		94.51 347	93.69 356	96.99 329	96.05 418	93.61 344	94.97 382	93.49 406	96.17 299	97.57 307	94.88 404	82.30 387	99.01 400	93.60 346	94.17 416	98.37 356

thres600view7		94.45 348	93.83 354	96.29 354	99.06 222	91.53 374	97.99 188	94.24 402	98.34 144	97.44 319	95.01 400	79.84 393	99.67 279	84.33 413	98.23 354	97.66 389

PCF-MVS	92.86 18	94.36 349	93.00 366	98.42 228	98.70 288	97.56 190	93.16 412	99.11 236	79.59 421	97.55 308	97.43 351	92.19 314	99.73 251	79.85 421	99.45 247	97.97 375
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
X-MVStestdata		94.32 350	92.59 368	99.53 37	99.46 128	99.21 32	98.65 103	99.34 161	98.62 126	97.54 309	45.85 425	97.50 145	99.83 167	96.79 214	99.53 230	99.56 106

MVS-HIRNet		94.32 350	95.62 316	90.42 405	98.46 328	75.36 429	96.29 327	89.13 421	95.25 331	95.38 388	99.75 13	92.88 304	99.19 392	94.07 334	99.39 254	96.72 406

ET-MVSNet_ETH3D		94.30 352	93.21 362	97.58 295	98.14 352	94.47 311	94.78 386	93.24 409	94.72 342	89.56 420	95.87 384	78.57 402	99.81 191	96.91 201	97.11 393	98.46 341

thres100view900		94.19 353	93.67 357	95.75 370	99.06 222	91.35 378	98.03 178	94.24 402	98.33 145	97.40 321	94.98 402	79.84 393	99.62 304	83.05 415	98.08 365	96.29 408

E-PMN		94.17 354	94.37 349	93.58 398	96.86 404	85.71 414	90.11 420	97.07 362	98.17 165	97.82 291	97.19 359	84.62 371	98.94 402	89.77 398	97.68 375	96.09 414

thres400		94.14 355	93.44 359	96.24 357	98.93 243	91.44 376	97.60 241	94.29 400	97.94 180	97.10 331	94.31 409	79.67 395	99.62 304	83.05 415	98.08 365	97.66 389

thisisatest0515		94.12 356	93.16 363	96.97 331	98.60 310	92.90 353	93.77 408	90.61 417	94.10 358	96.91 342	95.87 384	74.99 407	99.80 198	94.52 317	99.12 300	98.20 362

tfpn200view9		94.03 357	93.44 359	95.78 369	98.93 243	91.44 376	97.60 241	94.29 400	97.94 180	97.10 331	94.31 409	79.67 395	99.62 304	83.05 415	98.08 365	96.29 408

CostFormer		93.97 358	93.78 355	94.51 387	97.53 384	85.83 413	97.98 189	95.96 384	89.29 406	94.99 393	98.63 255	78.63 401	99.62 304	94.54 316	96.50 399	98.09 368

test-LLR		93.90 359	93.85 353	94.04 392	96.53 411	84.62 418	94.05 404	92.39 411	96.17 299	94.12 402	95.07 398	82.30 387	99.67 279	95.87 280	98.18 357	97.82 379

EMVS		93.83 360	94.02 352	93.23 402	96.83 406	84.96 415	89.77 421	96.32 379	97.92 182	97.43 320	96.36 377	86.17 358	98.93 403	87.68 405	97.73 374	95.81 415

baseline2		93.73 361	92.83 367	96.42 350	97.70 374	91.28 381	96.84 298	89.77 420	93.96 362	92.44 415	95.93 382	79.14 398	99.77 228	92.94 358	96.76 398	98.21 361

thres200		93.72 362	93.14 364	95.46 378	98.66 303	91.29 380	96.61 310	94.63 397	97.39 230	96.83 349	93.71 412	79.88 392	99.56 326	82.40 418	98.13 362	95.54 417

EPMVS		93.72 362	93.27 361	95.09 384	96.04 419	87.76 406	98.13 162	85.01 426	94.69 343	96.92 340	98.64 253	78.47 404	99.31 380	95.04 303	96.46 400	98.20 362

testing3		93.51 364	92.09 374	97.75 280	98.60 310	94.40 312	97.32 267	95.26 393	97.56 210	96.79 352	95.50 391	53.57 430	99.77 228	95.26 300	98.97 317	99.08 260

dp		93.47 365	93.59 358	93.13 403	96.64 409	81.62 427	97.66 232	96.42 378	92.80 377	96.11 371	98.64 253	78.55 403	99.59 315	93.31 353	92.18 421	98.16 364

FPMVS		93.44 366	92.23 372	97.08 325	99.25 174	97.86 165	95.61 361	97.16 360	92.90 375	93.76 409	98.65 250	75.94 406	95.66 422	79.30 422	97.49 378	97.73 386

testing91		93.32 367	92.27 371	96.47 349	97.54 382	91.25 382	96.17 336	96.76 372	97.18 254	93.65 410	93.50 414	65.11 424	99.63 301	93.04 357	97.45 380	98.53 338

tpm cat1		93.29 368	93.13 365	93.75 396	97.39 393	84.74 416	97.39 260	97.65 347	83.39 418	94.16 401	98.41 283	82.86 385	99.39 369	91.56 381	95.35 411	97.14 400

UBG		93.25 369	92.32 370	96.04 365	97.72 369	90.16 395	95.92 350	95.91 386	96.03 307	93.95 407	93.04 417	69.60 413	99.52 341	90.72 395	97.98 371	98.45 344

MVS		93.19 370	92.09 374	96.50 348	96.91 403	94.03 325	98.07 172	98.06 337	68.01 423	94.56 399	96.48 372	95.96 231	99.30 382	83.84 414	96.89 396	96.17 410

tpm2		93.09 371	92.58 369	94.62 386	97.56 380	86.53 410	97.66 232	95.79 388	86.15 413	94.07 404	98.23 301	75.95 405	99.53 337	90.91 392	96.86 397	97.81 381

testing11		93.08 372	92.02 376	96.26 356	97.56 380	90.83 390	96.32 325	95.70 389	96.47 290	92.66 414	93.73 411	64.36 425	99.59 315	93.77 343	97.57 376	98.37 356

testing99		93.04 373	91.98 379	96.23 358	97.53 384	90.70 392	96.35 323	95.94 385	96.87 271	93.41 411	93.43 415	63.84 426	99.59 315	93.24 355	97.19 390	98.40 352

dmvs_testset		92.94 374	92.21 373	95.13 382	98.59 313	90.99 387	97.65 234	92.09 413	96.95 266	94.00 405	93.55 413	92.34 313	96.97 421	72.20 424	92.52 419	97.43 396

KD-MVS_2432*1600		92.87 375	91.99 377	95.51 376	91.37 427	89.27 399	94.07 402	98.14 333	95.42 326	97.25 328	96.44 374	67.86 415	99.24 388	91.28 385	96.08 406	98.02 371

miper_refine_blended		92.87 375	91.99 377	95.51 376	91.37 427	89.27 399	94.07 402	98.14 333	95.42 326	97.25 328	96.44 374	67.86 415	99.24 388	91.28 385	96.08 406	98.02 371

ETVMVS		92.60 377	91.08 386	97.18 320	97.70 374	93.65 343	96.54 311	95.70 389	96.51 286	94.68 396	92.39 420	61.80 427	99.50 347	86.97 407	97.41 383	98.40 352

MVE	83.40 22	92.50 378	91.92 380	94.25 389	98.83 265	91.64 373	92.71 413	83.52 427	95.92 312	86.46 425	95.46 394	95.20 253	95.40 423	80.51 420	98.64 340	95.73 416
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test2506		92.39 379	91.89 381	93.89 395	99.38 144	82.28 425	99.32 23	66.03 431	99.08 92	98.77 199	99.57 46	66.26 421	99.84 150	98.71 90	99.95 34	99.54 117

UWE-MVS		92.38 380	91.76 383	94.21 391	97.16 398	84.65 417	95.42 370	88.45 422	95.96 310	96.17 369	95.84 386	66.36 420	99.71 259	91.87 375	98.64 340	98.28 359

gg-mvs-nofinetune		92.37 381	91.20 385	95.85 367	95.80 422	92.38 364	99.31 27	81.84 428	99.75 8	91.83 417	99.74 15	68.29 414	99.02 398	87.15 406	97.12 392	96.16 411

test-mter		92.33 382	91.76 383	94.04 392	96.53 411	84.62 418	94.05 404	92.39 411	94.00 361	94.12 402	95.07 398	65.63 423	99.67 279	95.87 280	98.18 357	97.82 379

IB-MVS	91.63 19	92.24 383	90.90 387	96.27 355	97.22 397	91.24 383	94.36 399	93.33 408	92.37 381	92.24 416	94.58 408	66.20 422	99.89 81	93.16 356	94.63 414	97.66 389
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
TESTMET0.1,1		92.19 384	91.77 382	93.46 399	96.48 413	82.80 424	94.05 404	91.52 416	94.45 350	94.00 405	94.88 404	66.65 419	99.56 326	95.78 285	98.11 363	98.02 371

testing222		91.96 385	90.37 389	96.72 344	97.47 391	92.59 358	96.11 338	94.76 395	96.83 273	92.90 413	92.87 418	57.92 428	99.55 330	86.93 408	97.52 377	98.00 374

myMVS_eth3d		91.92 386	90.45 388	96.30 353	97.10 400	90.90 388	96.18 334	96.58 375	95.65 318	94.77 394	92.29 421	53.88 429	99.36 372	89.59 400	98.05 368	98.63 331

PAPM		91.88 387	90.34 390	96.51 347	98.06 357	92.56 359	92.44 415	97.17 359	86.35 412	90.38 419	96.01 379	86.61 354	99.21 391	70.65 425	95.43 410	97.75 385

PVSNet_0	89.98 21	91.15 388	90.30 391	93.70 397	97.72 369	84.34 421	90.24 418	97.42 350	90.20 401	93.79 408	93.09 416	90.90 328	98.89 406	86.57 410	72.76 425	97.87 378

EGC-MVSNET		85.24 389	80.54 392	99.34 75	99.77 26	99.20 38	99.08 58	99.29 189	12.08 427	20.84 428	99.42 80	97.55 138	99.85 132	97.08 188	99.72 157	98.96 283

test_method		79.78 390	79.50 393	80.62 406	80.21 431	45.76 434	70.82 422	98.41 323	31.08 426	80.89 426	97.71 334	84.85 368	97.37 419	91.51 382	80.03 423	98.75 318

tmp_tt		78.77 391	78.73 394	78.90 407	58.45 432	74.76 431	94.20 401	78.26 430	39.16 425	86.71 424	92.82 419	80.50 391	75.19 427	86.16 411	92.29 420	86.74 421

dongtai		76.24 392	75.95 395	77.12 408	92.39 426	67.91 432	90.16 419	59.44 433	82.04 419	89.42 421	94.67 407	49.68 431	81.74 426	48.06 426	77.66 424	81.72 422

kuosan		69.30 393	68.95 396	70.34 409	87.68 430	65.00 433	91.11 417	59.90 432	69.02 422	74.46 427	88.89 424	48.58 432	68.03 428	28.61 427	72.33 426	77.99 423

cdsmvs_eth3d_5k		24.66 394	32.88 397	0.00 412	0.00 435	0.00 437	0.00 423	99.10 237	0.00 430	0.00 431	97.58 342	99.21 17	0.00 431	0.00 430	0.00 429	0.00 427

testmvs		17.12 395	20.53 398	6.87 411	12.05 433	4.20 436	93.62 410	6.73 434	4.62 429	10.41 429	24.33 426	8.28 434	3.56 430	9.69 429	15.07 427	12.86 426

test123		17.04 396	20.11 399	7.82 410	10.25 434	4.91 435	94.80 385	4.47 435	4.93 428	10.00 430	24.28 427	9.69 433	3.64 429	10.14 428	12.43 428	14.92 425

pcd_1.5k_mvsjas		8.17 397	10.90 400	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	98.07 97	0.00 431	0.00 430	0.00 429	0.00 427

ab-mvs-re		8.12 398	10.83 401	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	97.48 348	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

mmdepth		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

monomultidepth		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

test_blank		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

uanet_test		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

DCPMVS		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

sosnet-low-res		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

sosnet		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

uncertanet		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

Regformer		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

uanet		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

WAC-MVS						90.90 388								91.37 384

FOURS1					99.73 36	99.67 3	99.43 12	99.54 85	99.43 44	99.26 120

MSC_two_6792asdad				99.32 83	98.43 332	98.37 113		98.86 281					99.89 81	97.14 183	99.60 204	99.71 53

PC_three_1452									93.27 369	99.40 92	98.54 266	98.22 84	97.00 420	95.17 301	99.45 247	99.49 138

No_MVS				99.32 83	98.43 332	98.37 113		98.86 281					99.89 81	97.14 183	99.60 204	99.71 53

test_one_0601					99.39 143	99.20 38		99.31 173	98.49 138	98.66 212	99.02 167	97.64 130

eth-test2					0.00 435

eth-test					0.00 435

ZD-MVS					99.01 231	98.84 78		99.07 241	94.10 358	98.05 274	98.12 308	96.36 211	99.86 120	92.70 367	99.19 289

RE-MVS-def			98.58 121		99.20 186	99.38 12	98.48 129	99.30 181	98.64 122	98.95 166	98.96 189	97.75 121		96.56 239	99.39 254	99.45 161

IU-MVS					99.49 117	99.15 51		98.87 276	92.97 373	99.41 89				96.76 218	99.62 197	99.66 64

OPU-MVS				98.82 160	98.59 313	98.30 118	98.10 168				98.52 270	98.18 88	98.75 408	94.62 314	99.48 244	99.41 175

test_241102_TWO								99.30 181	98.03 172	99.26 120	99.02 167	97.51 144	99.88 95	96.91 201	99.60 204	99.66 64

test_241102_ONE					99.49 117	99.17 43		99.31 173	97.98 175	99.66 47	98.90 201	98.36 69	99.48 353

9.14			97.78 214		99.07 217		97.53 249	99.32 168	95.53 323	98.54 232	98.70 240	97.58 135	99.76 234	94.32 327	99.46 245

save fliter					99.11 208	97.97 155	96.53 313	99.02 253	98.24 155

test_0728_THIRD									98.17 165	99.08 142	99.02 167	97.89 110	99.88 95	97.07 189	99.71 162	99.70 58

test_0728_SECOND				99.60 14	99.50 110	99.23 30	98.02 180	99.32 168					99.88 95	96.99 195	99.63 194	99.68 60

test0726					99.50 110	99.21 32	98.17 158	99.35 155	97.97 176	99.26 120	99.06 155	97.61 133

GSMVS																98.81 307

test_part2					99.36 151	99.10 64				99.05 149

sam_mvs1												84.74 370				98.81 307

sam_mvs												84.29 376

ambc				98.24 246	98.82 268	95.97 264	98.62 107	99.00 258		99.27 116	99.21 125	96.99 176	99.50 347	96.55 242	99.50 242	99.26 229

MTGPA								99.20 212

test_post1							97.59 243				20.48 429	83.07 384	99.66 290	94.16 328

test_post											21.25 428	83.86 379	99.70 263

patchmatchnet-post											98.77 229	84.37 373	99.85 132

GG-mvs-BLEND				94.76 385	94.54 424	92.13 369	99.31 27	80.47 429		88.73 423	91.01 423	67.59 418	98.16 416	82.30 419	94.53 415	93.98 419

MTMP							97.93 193	91.91 415

gm-plane-assit					94.83 423	81.97 426			88.07 410		94.99 401		99.60 311	91.76 376

test9_res														93.28 354	99.15 294	99.38 192

TEST9					98.71 284	98.08 142	95.96 345	99.03 250	91.40 391	95.85 376	97.53 344	96.52 202	99.76 234

test_8					98.67 298	98.01 150	95.91 351	99.02 253	91.64 386	95.79 378	97.50 347	96.47 204	99.76 234

agg_prior2														92.50 370	99.16 292	99.37 194

agg_prior					98.68 297	97.99 151		99.01 256		95.59 379			99.77 228

TestCases				99.16 108	99.50 110	98.55 99		99.58 63	96.80 274	98.88 182	99.06 155	97.65 127	99.57 323	94.45 320	99.61 202	99.37 194

test_prior4						97.97 155	95.86 352

test_prior2							95.74 358		96.48 289	96.11 371	97.63 340	95.92 234		94.16 328	99.20 286

test_prior				98.95 144	98.69 293	97.95 159		99.03 250					99.59 315			99.30 221

旧先验2							95.76 357		88.56 409	97.52 311			99.66 290	94.48 318

新几何2							95.93 348

新几何1				98.91 151	98.94 241	97.76 177		98.76 297	87.58 411	96.75 353	98.10 310	94.80 267	99.78 222	92.73 366	99.00 312	99.20 240

旧先验1					98.82 268	97.45 196		98.76 297			98.34 292	95.50 247			99.01 311	99.23 235

无先验							95.74 358	98.74 302	89.38 405				99.73 251	92.38 372		99.22 239

原ACMM2							95.53 364

原ACMM1				98.35 236	98.90 251	96.25 253		98.83 289	92.48 380	96.07 373	98.10 310	95.39 250	99.71 259	92.61 369	98.99 314	99.08 260

test222					98.92 247	96.93 228	95.54 363	98.78 295	85.72 414	96.86 348	98.11 309	94.43 274			99.10 302	99.23 235

testdata2													99.79 211	92.80 364

segment_acmp												97.02 174

testdata				98.09 254	98.93 243	95.40 282		98.80 292	90.08 402	97.45 318	98.37 288	95.26 252	99.70 263	93.58 347	98.95 319	99.17 252

testdata1							95.44 369		96.32 295

test12				98.93 147	98.58 315	97.83 168		98.66 307		96.53 360		95.51 246	99.69 267		99.13 297	99.27 226

plane_prior7					99.19 189	97.87 164

plane_prior6					98.99 235	97.70 183						94.90 260

plane_prior5								99.27 195					99.70 263	94.42 322	99.51 235	99.45 161

plane_prior4											97.98 319

plane_prior3						97.78 176			97.41 228	97.79 292

plane_prior2							97.77 217		98.20 162

plane_prior1					99.05 225

plane_prior						97.65 185	97.07 285		96.72 279						99.36 258

n2								0.00 436

nn								0.00 436

door-mid								99.57 70

lessismore_v0				98.97 141	99.73 36	97.53 192		86.71 424		99.37 97	99.52 63	89.93 334	99.92 54	98.99 69	99.72 157	99.44 165

LGP-MVS_train				99.47 56	99.57 83	98.97 70		99.48 103	96.60 283	99.10 140	99.06 155	98.71 41	99.83 167	95.58 294	99.78 124	99.62 74

test11								98.87 276

door								99.41 135

HQP5-MVS						96.79 234

HQP-NCC					98.67 298		96.29 327		96.05 304	95.55 382

ACMP_Plane					98.67 298		96.29 327		96.05 304	95.55 382

BP-MVS														92.82 362

HQP4-MVS										95.56 381			99.54 335			99.32 214

HQP3-MVS								99.04 248							99.26 276

HQP2-MVS												93.84 288

NP-MVS					98.84 263	97.39 200					96.84 365

MDTV_nov1_ep13_2view						74.92 430	97.69 227		90.06 403	97.75 295		85.78 362		93.52 348		98.69 325

MDTV_nov1_ep13			95.22 334		97.06 402	83.20 423	97.74 222	96.16 380	94.37 352	96.99 338	98.83 217	83.95 378	99.53 337	93.90 337	97.95 372

ACMMP++_ref															99.77 130

ACMMP++															99.68 177

Test By Simon												96.52 202

ITE_SJBPF				98.87 155	99.22 180	98.48 106		99.35 155	97.50 216	98.28 254	98.60 261	97.64 130	99.35 375	93.86 340	99.27 273	98.79 313

DeepMVS_CX				93.44 400	98.24 345	94.21 317		94.34 399	64.28 424	91.34 418	94.87 406	89.45 339	92.77 425	77.54 423	93.14 418	93.35 420

High-resolution multi-view benchmark