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 3	99.97 1	99.97 1	99.95 1	99.74 1	99.98 1	99.56 1	100.00 1	99.85 6

pmmvs6		99.07 4	99.24 4	98.56 52	99.81 2	96.38 66	98.87 10	99.30 33	99.01 20	99.63 12	99.66 4	99.27 2	99.68 130	97.75 58	99.89 23	99.62 40

UniMVSNet_ETH3D		99.12 3	99.28 3	98.65 46	99.77 5	96.34 69	99.18 6	99.20 42	99.67 2	99.73 4	99.65 6	99.15 3	99.86 26	97.22 75	99.92 14	99.77 15

test_fmvsmconf0.01_n		98.57 18	98.74 17	98.06 90	99.39 44	94.63 138	96.70 155	99.82 1	95.44 181	99.64 11	99.52 9	98.96 4	99.74 83	99.38 5	99.86 30	99.81 10

XVG-OURS-SEG-HR		97.38 125	97.07 142	98.30 70	99.01 110	97.41 38	94.66 287	99.02 86	95.20 190	98.15 137	97.52 229	98.83 5	98.43 375	94.87 199	96.41 378	99.07 183

ACMH	93.61 9	98.44 29	98.76 14	97.51 131	99.43 37	93.54 183	98.23 46	99.05 76	97.40 84	99.37 26	99.08 57	98.79 6	99.47 209	97.74 59	99.71 78	99.50 72
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mvs_tets		98.90 6	98.94 6	98.75 35	99.69 10	96.48 64	98.54 23	99.22 39	96.23 131	99.71 5	99.48 12	98.77 7	99.93 4	98.89 21	99.95 5	99.84 8

test_fmvsmconf0.1_n		98.41 31	98.54 27	98.03 95	99.16 80	94.61 139	96.18 184	99.73 5	95.05 199	99.60 15	99.34 26	98.68 8	99.72 95	99.21 10	99.85 39	99.76 20

LTVRE_ROB	96.88 1	99.18 2	99.34 2	98.72 41	99.71 9	96.99 48	99.69 2	99.57 19	99.02 19	99.62 13	99.36 23	98.53 9	99.52 194	98.58 32	99.95 5	99.66 33
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
test_fmvsmconf_n		98.30 37	98.41 36	97.99 98	98.94 119	94.60 140	96.00 200	99.64 16	94.99 202	99.43 21	99.18 43	98.51 10	99.71 109	99.13 13	99.84 41	99.67 31

TransMVSNet (Re)		98.38 32	98.67 19	97.51 131	99.51 28	93.39 190	98.20 51	98.87 124	98.23 47	99.48 17	99.27 31	98.47 11	99.55 186	96.52 102	99.53 135	99.60 41

pm-mvs1		98.47 28	98.67 19	97.86 105	99.52 27	94.58 141	98.28 42	99.00 97	97.57 72	99.27 33	99.22 36	98.32 12	99.50 199	97.09 83	99.75 69	99.50 72

fmvsm_l_conf0.5_n_3		98.29 38	98.46 30	97.79 109	98.90 126	94.05 163	96.06 194	99.63 17	96.07 140	99.37 26	98.93 71	98.29 13	99.68 130	99.11 14	99.79 55	99.65 36

jajsoiax		98.77 10	98.79 13	98.74 38	99.66 12	96.48 64	98.45 31	99.12 56	95.83 161	99.67 8	99.37 21	98.25 14	99.92 6	98.77 24	99.94 8	99.82 9

sd_testset		97.97 58	98.12 50	97.51 131	99.41 40	93.44 186	97.96 64	98.25 227	98.58 32	98.78 70	99.39 18	98.21 15	99.56 182	92.65 267	99.86 30	99.52 65

ACMH+	93.58 10	98.23 42	98.31 41	97.98 99	99.39 44	95.22 120	97.55 99	99.20 42	98.21 48	99.25 35	98.51 116	98.21 15	99.40 235	94.79 203	99.72 75	99.32 127

HPM-MVS_fast		98.32 35	98.13 49	98.88 27	99.54 25	97.48 34	98.35 35	99.03 84	95.88 157	97.88 167	98.22 160	98.15 17	99.74 83	96.50 103	99.62 97	99.42 107

wuyk23d		93.25 313	95.20 226	87.40 407	96.07 363	95.38 107	97.04 129	94.97 351	95.33 185	99.70 7	98.11 172	98.14 18	91.94 425	77.76 415	99.68 86	74.89 425

ACMM	93.33 11	98.05 54	97.79 83	98.85 28	99.15 83	97.55 30	96.68 156	98.83 141	95.21 189	98.36 110	98.13 168	98.13 19	99.62 161	96.04 124	99.54 131	99.39 115
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HPM-MVS		98.11 48	97.83 79	98.92 25	99.42 39	97.46 35	98.57 20	99.05 76	95.43 182	97.41 193	97.50 231	97.98 20	99.79 49	95.58 154	99.57 118	99.50 72
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
testgi		96.07 195	96.50 181	94.80 300	99.26 57	87.69 319	95.96 206	98.58 192	95.08 196	98.02 153	96.25 315	97.92 21	97.60 401	88.68 348	98.74 274	99.11 176

LPG-MVS_test		97.94 67	97.67 95	98.74 38	99.15 83	97.02 46	97.09 126	99.02 86	95.15 193	98.34 114	98.23 157	97.91 22	99.70 118	94.41 218	99.73 71	99.50 72

LGP-MVS_train				98.74 38	99.15 83	97.02 46		99.02 86	95.15 193	98.34 114	98.23 157	97.91 22	99.70 118	94.41 218	99.73 71	99.50 72

SED-MVS		97.94 67	97.90 69	98.07 88	99.22 66	95.35 110	96.79 145	98.83 141	96.11 137	99.08 44	98.24 155	97.87 24	99.72 95	95.44 164	99.51 145	99.14 166

test_241102_ONE					99.22 66	95.35 110		98.83 141	96.04 144	99.08 44	98.13 168	97.87 24	99.33 259

SDMVSNet		97.97 58	98.26 47	97.11 167	99.41 40	92.21 219	96.92 135	98.60 188	98.58 32	98.78 70	99.39 18	97.80 26	99.62 161	94.98 197	99.86 30	99.52 65

testf1		98.57 18	98.45 33	98.93 22	99.79 3	98.78 3	97.69 87	99.42 28	97.69 68	98.92 58	98.77 86	97.80 26	99.25 280	96.27 115	99.69 82	98.76 234

APD_test2		98.57 18	98.45 33	98.93 22	99.79 3	98.78 3	97.69 87	99.42 28	97.69 68	98.92 58	98.77 86	97.80 26	99.25 280	96.27 115	99.69 82	98.76 234

SD-MVS		97.37 127	97.70 90	96.35 223	98.14 227	95.13 124	96.54 161	98.92 112	95.94 152	99.19 38	98.08 174	97.74 29	95.06 419	95.24 176	99.54 131	98.87 220
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 87	97.70 90	98.16 81	98.78 141	95.72 89	96.23 182	99.02 86	93.92 238	98.62 82	98.99 64	97.69 30	99.62 161	96.18 119	99.87 28	99.15 162
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 22	98.62 23	98.32 67	99.22 66	95.66 94	97.90 71	99.08 68	98.31 41	99.02 48	98.74 89	97.68 31	99.61 168	97.77 57	99.85 39	99.70 29

MGCFI-Net		97.20 136	97.23 132	97.08 172	97.68 283	93.71 176	97.79 77	99.09 65	97.40 84	96.59 249	93.96 369	97.67 32	99.35 254	96.43 106	98.50 298	98.17 300

ANet_high		98.31 36	98.94 6	96.41 220	99.33 51	89.64 273	97.92 69	99.56 21	99.27 8	99.66 10	99.50 11	97.67 32	99.83 34	97.55 66	99.98 2	99.77 15

test_fmvsmvis_n_1920		98.08 50	98.47 29	96.93 182	99.03 108	93.29 192	96.32 174	99.65 13	95.59 172	99.71 5	99.01 61	97.66 34	99.60 170	99.44 3	99.83 45	97.90 324

casdiffmvs_mvg		97.83 84	98.11 51	97.00 179	98.57 171	92.10 227	95.97 204	99.18 45	97.67 71	99.00 51	98.48 121	97.64 35	99.50 199	96.96 90	99.54 131	99.40 110
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
sasdasda		97.23 134	97.21 134	97.30 154	97.65 290	94.39 147	97.84 74	99.05 76	97.42 79	96.68 241	93.85 371	97.63 36	99.33 259	96.29 113	98.47 299	98.18 298

canonicalmvs		97.23 134	97.21 134	97.30 154	97.65 290	94.39 147	97.84 74	99.05 76	97.42 79	96.68 241	93.85 371	97.63 36	99.33 259	96.29 113	98.47 299	98.18 298

GeoE		97.75 93	97.70 90	97.89 103	98.88 128	94.53 142	97.10 125	98.98 103	95.75 165	97.62 179	97.59 224	97.61 38	99.77 63	96.34 111	99.44 165	99.36 123

TranMVSNet+NR-MVSNet		98.33 33	98.30 43	98.43 60	99.07 98	95.87 85	96.73 153	99.05 76	98.67 28	98.84 65	98.45 122	97.58 39	99.88 21	96.45 105	99.86 30	99.54 59

cdsmvs_eth3d_5k		24.22 398	32.30 401	0.00 416	0.00 439	0.00 441	0.00 427	98.10 250	0.00 434	0.00 435	95.06 350	97.54 40	0.00 435	0.00 434	0.00 433	0.00 431

ACMP	92.54 13	97.47 118	97.10 139	98.55 53	99.04 107	96.70 55	96.24 181	98.89 115	93.71 242	97.97 158	97.75 212	97.44 41	99.63 156	93.22 260	99.70 81	99.32 127
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_djsdf		98.73 12	98.74 17	98.69 43	99.63 14	96.30 71	98.67 15	99.02 86	96.50 118	99.32 30	99.44 16	97.43 42	99.92 6	98.73 26	99.95 5	99.86 5

TDRefinement		98.90 6	98.86 9	99.02 10	99.54 25	98.06 9	99.34 5	99.44 26	98.85 25	99.00 51	99.20 38	97.42 43	99.59 172	97.21 76	99.76 61	99.40 110

anonymousdsp		98.72 15	98.63 21	98.99 14	99.62 15	97.29 41	98.65 19	99.19 44	95.62 170	99.35 29	99.37 21	97.38 44	99.90 16	98.59 31	99.91 17	99.77 15

PS-CasMVS		98.73 12	98.85 11	98.39 63	99.55 22	95.47 104	98.49 28	99.13 55	99.22 10	99.22 37	98.96 68	97.35 45	99.92 6	97.79 55	99.93 11	99.79 13

COLMAP_ROB	94.48 6	98.25 41	98.11 51	98.64 47	99.21 73	97.35 39	97.96 64	99.16 47	98.34 40	98.78 70	98.52 114	97.32 46	99.45 217	94.08 232	99.67 88	99.13 168
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 98	97.79 83	97.40 148	99.06 100	93.52 184	95.96 206	98.97 106	94.55 218	98.82 67	98.76 88	97.31 47	99.29 272	97.20 78	99.44 165	99.38 117

XXY-MVS		97.54 113	97.70 90	97.07 173	99.46 34	92.21 219	97.22 118	99.00 97	94.93 205	98.58 87	98.92 73	97.31 47	99.41 233	94.44 216	99.43 174	99.59 42

reproduce-ours		98.48 26	98.27 45	99.12 5	98.99 111	98.02 13	96.81 141	99.02 86	98.29 44	98.97 55	98.61 104	97.27 49	99.82 36	96.86 94	99.61 103	99.51 69

our_new_method		98.48 26	98.27 45	99.12 5	98.99 111	98.02 13	96.81 141	99.02 86	98.29 44	98.97 55	98.61 104	97.27 49	99.82 36	96.86 94	99.61 103	99.51 69

PEN-MVS		98.75 11	98.85 11	98.44 59	99.58 18	95.67 93	98.45 31	99.15 51	99.33 6	99.30 31	99.00 62	97.27 49	99.92 6	97.64 64	99.92 14	99.75 23

DTE-MVSNet		98.79 9	98.86 9	98.59 50	99.55 22	96.12 76	98.48 30	99.10 60	99.36 5	99.29 32	99.06 58	97.27 49	99.93 4	97.71 60	99.91 17	99.70 29

ZNCC-MVS		97.92 71	97.62 104	98.83 29	99.32 53	97.24 43	97.45 106	98.84 135	95.76 163	96.93 227	97.43 235	97.26 53	99.79 49	96.06 121	99.53 135	99.45 95

MP-MVS-pluss		97.69 98	97.36 123	98.70 42	99.50 31	96.84 51	95.38 246	98.99 100	92.45 287	98.11 140	98.31 139	97.25 54	99.77 63	96.60 99	99.62 97	99.48 86
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		97.89 77	97.63 102	98.67 44	99.35 49	96.84 51	96.36 171	98.79 151	95.07 197	97.88 167	98.35 134	97.24 55	99.72 95	96.05 123	99.58 115	99.45 95

Effi-MVS+		96.19 191	96.01 200	96.71 200	97.43 310	92.19 223	96.12 190	99.10 60	95.45 179	93.33 364	94.71 357	97.23 56	99.56 182	93.21 261	97.54 345	98.37 274

tt0805		97.44 120	97.56 110	97.11 167	99.55 22	96.36 67	98.66 18	95.66 334	98.31 41	97.09 215	95.45 344	97.17 57	98.50 370	98.67 29	97.45 351	96.48 387

PGM-MVS		97.88 78	97.52 114	98.96 17	99.20 75	97.62 25	97.09 126	99.06 72	95.45 179	97.55 181	97.94 194	97.11 58	99.78 53	94.77 206	99.46 161	99.48 86

test_0728_THIRD									96.62 109	98.40 104	98.28 148	97.10 59	99.71 109	95.70 142	99.62 97	99.58 43

APD-MVS_3200maxsize		98.13 47	97.90 69	98.79 33	98.79 138	97.31 40	97.55 99	98.92 112	97.72 65	98.25 125	98.13 168	97.10 59	99.75 74	95.44 164	99.24 218	99.32 127

fmvsm_s_conf0.5_n_3		97.88 78	98.37 37	96.41 220	98.73 145	89.82 268	95.94 208	99.49 23	96.81 103	99.09 43	99.03 60	97.09 61	99.65 147	99.37 6	99.76 61	99.76 20

OPM-MVS		97.54 113	97.25 130	98.41 61	99.11 92	96.61 60	95.24 259	98.46 201	94.58 217	98.10 142	98.07 176	97.09 61	99.39 239	95.16 182	99.44 165	99.21 152
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HFP-MVS		97.94 67	97.64 100	98.83 29	99.15 83	97.50 33	97.59 96	98.84 135	96.05 142	97.49 186	97.54 227	97.07 63	99.70 118	95.61 151	99.46 161	99.30 132

DVP-MVS		97.78 91	97.65 97	98.16 81	99.24 61	95.51 99	96.74 149	98.23 230	95.92 154	98.40 104	98.28 148	97.06 64	99.71 109	95.48 160	99.52 140	99.26 144
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test0726					99.24 61	95.51 99	96.89 137	98.89 115	95.92 154	98.64 80	98.31 139	97.06 64

test_fmvsm_n_1920		98.08 50	98.29 44	97.43 144	98.88 128	93.95 167	96.17 188	99.57 19	95.66 167	99.52 16	98.71 93	97.04 66	99.64 152	99.21 10	99.87 28	98.69 243

casdiffmvs		97.50 115	97.81 81	96.56 210	98.51 180	91.04 250	95.83 215	99.09 65	97.23 92	98.33 117	98.30 143	97.03 67	99.37 247	96.58 101	99.38 184	99.28 139
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SteuartSystems-ACMMP		98.02 56	97.76 87	98.79 33	99.43 37	97.21 45	97.15 121	98.90 114	96.58 113	98.08 145	97.87 200	97.02 68	99.76 68	95.25 175	99.59 112	99.40 110
Skip Steuart: Steuart Systems R&D Blog.
PC_three_1452									87.24 362	98.37 107	97.44 234	97.00 69	96.78 411	92.01 276	99.25 215	99.21 152

EC-MVSNet		97.90 76	97.94 68	97.79 109	98.66 158	95.14 123	98.31 39	99.66 12	97.57 72	95.95 284	97.01 271	96.99 70	99.82 36	97.66 63	99.64 93	98.39 272

DVP-MVS++		97.96 60	97.90 69	98.12 86	97.75 275	95.40 105	99.03 8	98.89 115	96.62 109	98.62 82	98.30 143	96.97 71	99.75 74	95.70 142	99.25 215	99.21 152

OPU-MVS				97.64 122	98.01 237	95.27 115	96.79 145				97.35 246	96.97 71	98.51 369	91.21 294	99.25 215	99.14 166

RE-MVS-def			97.88 74		98.81 134	98.05 10	97.55 99	98.86 127	97.77 60	98.20 129	98.07 176	96.94 73		95.49 156	99.20 220	99.26 144

APDe-MVS		98.14 44	98.03 59	98.47 58	98.72 148	96.04 79	98.07 58	99.10 60	95.96 149	98.59 86	98.69 96	96.94 73	99.81 41	96.64 97	99.58 115	99.57 50
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
reproduce_model		98.54 22	98.33 40	99.15 4	99.06 100	98.04 12	97.04 129	99.09 65	98.42 37	99.03 47	98.71 93	96.93 75	99.83 34	97.09 83	99.63 95	99.56 54

test_one_0601					99.05 106	95.50 102		98.87 124	97.21 94	98.03 152	98.30 143	96.93 75

GST-MVS		97.82 87	97.49 118	98.81 31	99.23 63	97.25 42	97.16 120	98.79 151	95.96 149	97.53 182	97.40 237	96.93 75	99.77 63	95.04 191	99.35 193	99.42 107

test_241102_TWO								98.83 141	96.11 137	98.62 82	98.24 155	96.92 78	99.72 95	95.44 164	99.49 152	99.49 80

LCM-MVSNet-Re		97.33 130	97.33 125	97.32 153	98.13 230	93.79 173	96.99 132	99.65 13	96.74 106	99.47 19	98.93 71	96.91 79	99.84 32	90.11 325	99.06 243	98.32 281

VPA-MVSNet		98.27 39	98.46 30	97.70 117	99.06 100	93.80 172	97.76 81	99.00 97	98.40 38	99.07 46	98.98 65	96.89 80	99.75 74	97.19 79	99.79 55	99.55 57

ACMMP		98.05 54	97.75 89	98.93 22	99.23 63	97.60 26	98.09 57	98.96 107	95.75 165	97.91 164	98.06 181	96.89 80	99.76 68	95.32 172	99.57 118	99.43 106
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
CS-MVS		98.09 49	98.01 61	98.32 67	98.45 189	96.69 56	98.52 26	99.69 9	98.07 53	96.07 280	97.19 256	96.88 82	99.86 26	97.50 68	99.73 71	98.41 269

PMVS	89.60 17	96.71 169	96.97 148	95.95 244	99.51 28	97.81 20	97.42 110	97.49 287	97.93 56	95.95 284	98.58 107	96.88 82	96.91 408	89.59 334	99.36 188	93.12 417
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
region2R		97.92 71	97.59 107	98.92 25	99.22 66	97.55 30	97.60 94	98.84 135	96.00 147	97.22 199	97.62 222	96.87 84	99.76 68	95.48 160	99.43 174	99.46 91

CP-MVS		97.92 71	97.56 110	98.99 14	98.99 111	97.82 19	97.93 68	98.96 107	96.11 137	96.89 230	97.45 233	96.85 85	99.78 53	95.19 178	99.63 95	99.38 117

DPE-MVS		97.64 103	97.35 124	98.50 55	98.85 132	96.18 73	95.21 261	98.99 100	95.84 160	98.78 70	98.08 174	96.84 86	99.81 41	93.98 238	99.57 118	99.52 65
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_0402		97.84 83	97.97 65	97.47 140	99.19 77	94.07 161	96.71 154	98.73 163	98.66 29	98.56 88	98.41 127	96.84 86	99.69 125	94.82 201	99.81 50	98.64 247

SPE-MVS-test		97.91 74	97.84 76	98.14 84	98.52 178	96.03 81	98.38 34	99.67 10	98.11 51	95.50 304	96.92 277	96.81 88	99.87 24	96.87 93	99.76 61	98.51 261

ACMMPR		97.95 64	97.62 104	98.94 19	99.20 75	97.56 29	97.59 96	98.83 141	96.05 142	97.46 191	97.63 221	96.77 89	99.76 68	95.61 151	99.46 161	99.49 80

Vis-MVSNet		98.27 39	98.34 39	98.07 88	99.33 51	95.21 122	98.04 59	99.46 24	97.32 89	97.82 174	99.11 52	96.75 90	99.86 26	97.84 52	99.36 188	99.15 162
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
Fast-Effi-MVS+		95.49 222	95.07 233	96.75 198	97.67 287	92.82 201	94.22 302	98.60 188	91.61 302	93.42 362	92.90 382	96.73 91	99.70 118	92.60 268	97.89 326	97.74 337

baseline		97.44 120	97.78 86	96.43 217	98.52 178	90.75 257	96.84 138	99.03 84	96.51 117	97.86 171	98.02 185	96.67 92	99.36 250	97.09 83	99.47 158	99.19 156

SR-MVS		98.00 57	97.66 96	99.01 12	98.77 143	97.93 15	97.38 111	98.83 141	97.32 89	98.06 148	97.85 201	96.65 93	99.77 63	95.00 194	99.11 234	99.32 127

tfpnnormal		97.72 96	97.97 65	96.94 181	99.26 57	92.23 218	97.83 76	98.45 202	98.25 46	99.13 41	98.66 98	96.65 93	99.69 125	93.92 240	99.62 97	98.91 210

DeepPCF-MVS	94.58 5	96.90 152	96.43 183	98.31 69	97.48 304	97.23 44	92.56 357	98.60 188	92.84 279	98.54 89	97.40 237	96.64 95	98.78 340	94.40 220	99.41 181	98.93 206

MVS_111021_LR		96.82 160	96.55 175	97.62 123	98.27 205	95.34 112	93.81 324	98.33 220	94.59 216	96.56 252	96.63 295	96.61 96	98.73 345	94.80 202	99.34 196	98.78 230

Gipuma		98.07 52	98.31 41	97.36 150	99.76 7	96.28 72	98.51 27	99.10 60	98.76 27	96.79 233	99.34 26	96.61 96	98.82 336	96.38 108	99.50 149	96.98 366
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
SR-MVS-dyc-post		98.14 44	97.84 76	99.02 10	98.81 134	98.05 10	97.55 99	98.86 127	97.77 60	98.20 129	98.07 176	96.60 98	99.76 68	95.49 156	99.20 220	99.26 144

MVS_111021_HR		96.73 166	96.54 177	97.27 156	98.35 197	93.66 180	93.42 335	98.36 216	94.74 208	96.58 250	96.76 289	96.54 99	98.99 321	94.87 199	99.27 212	99.15 162

SMA-MVS		97.48 117	97.11 138	98.60 49	98.83 133	96.67 57	96.74 149	98.73 163	91.61 302	98.48 96	98.36 133	96.53 100	99.68 130	95.17 180	99.54 131	99.45 95
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
v7n		98.73 12	98.99 5	97.95 100	99.64 13	94.20 158	98.67 15	99.14 54	99.08 14	99.42 22	99.23 35	96.53 100	99.91 14	99.27 8	99.93 11	99.73 25

mPP-MVS		97.91 74	97.53 113	99.04 8	99.22 66	97.87 18	97.74 84	98.78 155	96.04 144	97.10 210	97.73 215	96.53 100	99.78 53	95.16 182	99.50 149	99.46 91

XVS		97.96 60	97.63 102	98.94 19	99.15 83	97.66 23	97.77 79	98.83 141	97.42 79	96.32 264	97.64 220	96.49 103	99.72 95	95.66 147	99.37 185	99.45 95

X-MVStestdata		92.86 318	90.83 347	98.94 19	99.15 83	97.66 23	97.77 79	98.83 141	97.42 79	96.32 264	36.50 429	96.49 103	99.72 95	95.66 147	99.37 185	99.45 95

9.14			96.69 164		98.53 177		96.02 198	98.98 103	93.23 259	97.18 204	97.46 232	96.47 105	99.62 161	92.99 264	99.32 203

UA-Net		98.88 8	98.76 14	99.22 3	99.11 92	97.89 17	99.47 3	99.32 31	99.08 14	97.87 170	99.67 3	96.47 105	99.92 6	97.88 49	99.98 2	99.85 6

fmvsm_l_conf0.5_n		97.68 100	97.81 81	97.27 156	98.92 123	92.71 208	95.89 212	99.41 30	93.36 254	99.00 51	98.44 124	96.46 107	99.65 147	99.09 15	99.76 61	99.45 95

SF-MVS		97.60 107	97.39 121	98.22 77	98.93 121	95.69 91	97.05 128	99.10 60	95.32 186	97.83 173	97.88 199	96.44 108	99.72 95	94.59 215	99.39 183	99.25 148

fmvsm_s_conf0.1_n_a		97.80 89	98.01 61	97.18 162	99.17 79	92.51 211	96.57 159	99.15 51	93.68 245	98.89 61	99.30 29	96.42 109	99.37 247	99.03 17	99.83 45	99.66 33

xiu_mvs_v1_base_debu		95.62 217	95.96 204	94.60 308	98.01 237	88.42 297	93.99 314	98.21 231	92.98 273	95.91 286	94.53 360	96.39 110	99.72 95	95.43 167	98.19 312	95.64 399

xiu_mvs_v1_base		95.62 217	95.96 204	94.60 308	98.01 237	88.42 297	93.99 314	98.21 231	92.98 273	95.91 286	94.53 360	96.39 110	99.72 95	95.43 167	98.19 312	95.64 399

xiu_mvs_v1_base_debi		95.62 217	95.96 204	94.60 308	98.01 237	88.42 297	93.99 314	98.21 231	92.98 273	95.91 286	94.53 360	96.39 110	99.72 95	95.43 167	98.19 312	95.64 399

ETV-MVS		96.13 194	95.90 208	96.82 193	97.76 273	93.89 168	95.40 244	98.95 109	95.87 158	95.58 302	91.00 407	96.36 113	99.72 95	93.36 254	98.83 266	96.85 373

fmvsm_l_conf0.5_n_a		97.60 107	97.76 87	97.11 167	98.92 123	92.28 216	95.83 215	99.32 31	93.22 260	98.91 60	98.49 117	96.31 114	99.64 152	99.07 16	99.76 61	99.40 110

fmvsm_s_conf0.1_n		97.73 94	98.02 60	96.85 190	99.09 95	91.43 244	96.37 170	99.11 57	94.19 228	99.01 49	99.25 32	96.30 115	99.38 242	99.00 18	99.88 25	99.73 25

MP-MVS		97.64 103	97.18 136	99.00 13	99.32 53	97.77 21	97.49 105	98.73 163	96.27 128	95.59 301	97.75 212	96.30 115	99.78 53	93.70 248	99.48 156	99.45 95
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TinyColmap		96.00 200	96.34 187	94.96 291	97.90 248	87.91 312	94.13 309	98.49 199	94.41 221	98.16 135	97.76 209	96.29 117	98.68 354	90.52 318	99.42 177	98.30 285

Fast-Effi-MVS+-dtu		96.44 182	96.12 195	97.39 149	97.18 325	94.39 147	95.46 238	98.73 163	96.03 146	94.72 321	94.92 354	96.28 118	99.69 125	93.81 243	97.98 320	98.09 303

fmvsm_s_conf0.5_n_a		97.65 102	97.83 79	97.13 166	98.80 136	92.51 211	96.25 180	99.06 72	93.67 246	98.64 80	99.00 62	96.23 119	99.36 250	98.99 19	99.80 53	99.53 62

fmvsm_s_conf0.5_n		97.62 105	97.89 72	96.80 194	98.79 138	91.44 243	96.14 189	99.06 72	94.19 228	98.82 67	98.98 65	96.22 120	99.38 242	98.98 20	99.86 30	99.58 43

APD_test1		97.95 64	97.68 94	98.75 35	99.60 16	98.60 6	97.21 119	99.08 68	96.57 116	98.07 147	98.38 131	96.22 120	99.14 298	94.71 210	99.31 206	98.52 260

OMC-MVS		96.48 180	96.00 201	97.91 102	98.30 200	96.01 82	94.86 279	98.60 188	91.88 297	97.18 204	97.21 255	96.11 122	99.04 315	90.49 321	99.34 196	98.69 243

xiu_mvs_v2_base		94.22 281	94.63 259	92.99 357	97.32 320	84.84 363	92.12 370	97.84 267	91.96 295	94.17 334	93.43 373	96.07 123	99.71 109	91.27 291	97.48 348	94.42 409

CSCG		97.40 124	97.30 126	97.69 119	98.95 116	94.83 130	97.28 114	98.99 100	96.35 127	98.13 139	95.95 330	95.99 124	99.66 145	94.36 223	99.73 71	98.59 253

PHI-MVS		96.96 148	96.53 178	98.25 75	97.48 304	96.50 63	96.76 147	98.85 131	93.52 249	96.19 276	96.85 280	95.94 125	99.42 224	93.79 244	99.43 174	98.83 223

mamv4		99.05 5	98.91 8	99.46 2	98.94 119	99.62 2	97.98 63	99.70 8	99.49 3	99.78 2	99.22 36	95.92 126	99.95 3	99.31 7	99.83 45	98.83 223

TSAR-MVS + MP.		97.42 123	97.23 132	98.00 97	99.38 46	95.00 127	97.63 93	98.20 234	93.00 272	98.16 135	98.06 181	95.89 127	99.72 95	95.67 146	99.10 236	99.28 139
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		97.58 111	97.28 129	98.49 56	99.16 80	96.90 50	96.39 166	98.98 103	95.05 199	98.06 148	98.02 185	95.86 128	99.56 182	94.37 221	99.64 93	99.00 192

AllTest		97.20 136	96.92 153	98.06 90	99.08 96	96.16 74	97.14 123	99.16 47	94.35 223	97.78 175	98.07 176	95.84 129	99.12 302	91.41 288	99.42 177	98.91 210

TestCases				98.06 90	99.08 96	96.16 74		99.16 47	94.35 223	97.78 175	98.07 176	95.84 129	99.12 302	91.41 288	99.42 177	98.91 210

APD-MVS		97.00 143	96.53 178	98.41 61	98.55 174	96.31 70	96.32 174	98.77 156	92.96 277	97.44 192	97.58 226	95.84 129	99.74 83	91.96 277	99.35 193	99.19 156
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
pcd_1.5k_mvsjas		7.98 401	10.65 404	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	95.82 132	0.00 435	0.00 434	0.00 433	0.00 431

PS-MVSNAJss		98.53 24	98.63 21	98.21 80	99.68 11	94.82 131	98.10 56	99.21 40	96.91 100	99.75 3	99.45 15	95.82 132	99.92 6	98.80 23	99.96 4	99.89 4

PS-MVSNAJ		94.10 287	94.47 269	93.00 356	97.35 315	84.88 360	91.86 375	97.84 267	91.96 295	94.17 334	92.50 392	95.82 132	99.71 109	91.27 291	97.48 348	94.40 410

3Dnovator	96.53 2	97.61 106	97.64 100	97.50 135	97.74 278	93.65 181	98.49 28	98.88 122	96.86 102	97.11 209	98.55 111	95.82 132	99.73 89	95.94 132	99.42 177	99.13 168

MTAPA		98.14 44	97.84 76	99.06 7	99.44 36	97.90 16	97.25 115	98.73 163	97.69 68	97.90 165	97.96 191	95.81 136	99.82 36	96.13 120	99.61 103	99.45 95

DP-MVS		97.87 80	97.89 72	97.81 108	98.62 165	94.82 131	97.13 124	98.79 151	98.98 21	98.74 77	98.49 117	95.80 137	99.49 204	95.04 191	99.44 165	99.11 176

Anonymous20240529		97.96 60	98.04 58	97.71 115	98.69 155	94.28 156	97.86 73	98.31 224	98.79 26	99.23 36	98.86 81	95.76 138	99.61 168	95.49 156	99.36 188	99.23 150

LS3D		97.77 92	97.50 117	98.57 51	96.24 351	97.58 28	98.45 31	98.85 131	98.58 32	97.51 184	97.94 194	95.74 139	99.63 156	95.19 178	98.97 248	98.51 261

EIA-MVS		96.04 197	95.77 214	96.85 190	97.80 263	92.98 199	96.12 190	99.16 47	94.65 212	93.77 347	91.69 401	95.68 140	99.67 139	94.18 228	98.85 263	97.91 323

CNVR-MVS		96.92 150	96.55 175	98.03 95	98.00 241	95.54 97	94.87 278	98.17 240	94.60 214	96.38 261	97.05 266	95.67 141	99.36 250	95.12 188	99.08 238	99.19 156

CLD-MVS		95.47 225	95.07 233	96.69 202	98.27 205	92.53 210	91.36 384	98.67 178	91.22 312	95.78 294	94.12 367	95.65 142	98.98 323	90.81 304	99.72 75	98.57 254
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 21	98.76 14	97.94 101	98.79 138	94.37 150	98.84 11	99.15 51	99.37 4	99.67 8	99.43 17	95.61 143	99.72 95	98.12 40	99.86 30	99.73 25

EGC-MVSNET		83.08 393	77.93 396	98.53 54	99.57 19	97.55 30	98.33 38	98.57 193	4.71 431	10.38 432	98.90 77	95.60 144	99.50 199	95.69 144	99.61 103	98.55 257

ITE_SJBPF				97.85 106	98.64 159	96.66 58		98.51 198	95.63 169	97.22 199	97.30 250	95.52 145	98.55 366	90.97 299	98.90 256	98.34 280

DeepC-MVS_fast	94.34 7	96.74 164	96.51 180	97.44 143	97.69 282	94.15 159	96.02 198	98.43 205	93.17 267	97.30 195	97.38 243	95.48 146	99.28 274	93.74 245	99.34 196	98.88 218
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 23	98.75 35	99.51 28	96.61 60	98.55 22	99.17 46	99.05 17	99.17 39	98.79 83	95.47 147	99.89 19	97.95 47	99.91 17	99.75 23

FMVSNet1		97.95 64	98.08 53	97.56 126	99.14 90	93.67 177	98.23 46	98.66 180	97.41 83	99.00 51	99.19 39	95.47 147	99.73 89	95.83 139	99.76 61	99.30 132

MIMVSNet1		98.51 25	98.45 33	98.67 44	99.72 8	96.71 54	98.76 13	98.89 115	98.49 35	99.38 25	99.14 50	95.44 149	99.84 32	96.47 104	99.80 53	99.47 89

mmtdpeth		98.33 33	98.53 28	97.71 115	99.07 98	93.44 186	98.80 12	99.78 4	99.10 13	96.61 248	99.63 7	95.42 150	99.73 89	98.53 33	99.86 30	99.95 2

CP-MVSNet		98.42 30	98.46 30	98.30 70	99.46 34	95.22 120	98.27 44	98.84 135	99.05 17	99.01 49	98.65 101	95.37 151	99.90 16	97.57 65	99.91 17	99.77 15

segment_acmp												95.34 152

CDPH-MVS		95.45 227	94.65 256	97.84 107	98.28 203	94.96 128	93.73 326	98.33 220	85.03 387	95.44 305	96.60 296	95.31 153	99.44 220	90.01 327	99.13 230	99.11 176

3Dnovator+	96.13 3	97.73 94	97.59 107	98.15 83	98.11 231	95.60 95	98.04 59	98.70 172	98.13 50	96.93 227	98.45 122	95.30 154	99.62 161	95.64 149	98.96 249	99.24 149

MVS_Test		96.27 188	96.79 161	94.73 304	96.94 335	86.63 337	96.18 184	98.33 220	94.94 203	96.07 280	98.28 148	95.25 155	99.26 278	97.21 76	97.90 325	98.30 285

XVG-OURS		97.12 138	96.74 162	98.26 72	98.99 111	97.45 36	93.82 322	99.05 76	95.19 191	98.32 118	97.70 217	95.22 156	98.41 376	94.27 225	98.13 315	98.93 206

fmvsm_s_conf0.5_n_2		97.59 110	98.07 54	96.17 234	98.78 141	89.10 286	95.33 252	99.55 22	95.96 149	99.41 24	99.10 53	95.18 157	99.59 172	99.43 4	99.86 30	99.81 10

fmvsm_s_conf0.1_n_2		97.68 100	98.18 48	96.20 231	99.06 100	89.08 287	95.51 236	99.72 6	96.06 141	99.48 17	99.24 33	95.18 157	99.60 170	99.45 2	99.88 25	99.94 3

dcpmvs_2		97.12 138	97.99 63	94.51 314	99.11 92	84.00 373	97.75 82	99.65 13	97.38 86	99.14 40	98.42 125	95.16 159	99.96 2	95.52 155	99.78 59	99.58 43

MCST-MVS		96.24 189	95.80 212	97.56 126	98.75 144	94.13 160	94.66 287	98.17 240	90.17 327	96.21 274	96.10 324	95.14 160	99.43 222	94.13 231	98.85 263	99.13 168

EI-MVSNet-Vis-set		97.32 131	97.39 121	97.11 167	97.36 314	92.08 228	95.34 251	97.65 280	97.74 63	98.29 123	98.11 172	95.05 161	99.68 130	97.50 68	99.50 149	99.56 54

EI-MVSNet-UG-set		97.32 131	97.40 120	97.09 171	97.34 317	92.01 230	95.33 252	97.65 280	97.74 63	98.30 122	98.14 166	95.04 162	99.69 125	97.55 66	99.52 140	99.58 43

KD-MVS_self_test		97.86 82	98.07 54	97.25 159	99.22 66	92.81 203	97.55 99	98.94 110	97.10 96	98.85 64	98.88 79	95.03 163	99.67 139	97.39 72	99.65 91	99.26 144

ZD-MVS					98.43 191	95.94 83		98.56 194	90.72 317	96.66 244	97.07 264	95.02 164	99.74 83	91.08 295	98.93 254

DELS-MVS		96.17 192	96.23 191	95.99 240	97.55 300	90.04 264	92.38 366	98.52 196	94.13 230	96.55 254	97.06 265	94.99 165	99.58 175	95.62 150	99.28 210	98.37 274
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
patch_mono-2		96.59 174	96.93 151	95.55 265	98.88 128	87.12 329	94.47 292	99.30 33	94.12 231	96.65 246	98.41 127	94.98 166	99.87 24	95.81 141	99.78 59	99.66 33

ab-mvs		96.59 174	96.59 170	96.60 205	98.64 159	92.21 219	98.35 35	97.67 276	94.45 220	96.99 221	98.79 83	94.96 167	99.49 204	90.39 322	99.07 240	98.08 304

MSLP-MVS++		96.42 184	96.71 163	95.57 262	97.82 258	90.56 261	95.71 220	98.84 135	94.72 209	96.71 240	97.39 241	94.91 168	98.10 392	95.28 173	99.02 245	98.05 313

QAPM		95.88 204	95.57 221	96.80 194	97.90 248	91.84 235	98.18 53	98.73 163	88.41 349	96.42 259	98.13 168	94.73 169	99.75 74	88.72 346	98.94 252	98.81 226

RPSCF		97.87 80	97.51 115	98.95 18	99.15 83	98.43 7	97.56 98	99.06 72	96.19 134	98.48 96	98.70 95	94.72 170	99.24 284	94.37 221	99.33 201	99.17 159

DU-MVS		97.79 90	97.60 106	98.36 65	98.73 145	95.78 87	95.65 228	98.87 124	97.57 72	98.31 120	97.83 202	94.69 171	99.85 29	97.02 88	99.71 78	99.46 91

Baseline_NR-MVSNet		97.72 96	97.79 83	97.50 135	99.56 20	93.29 192	95.44 239	98.86 127	98.20 49	98.37 107	99.24 33	94.69 171	99.55 186	95.98 130	99.79 55	99.65 36

TEST9					97.84 255	95.23 117	93.62 329	98.39 212	86.81 368	93.78 345	95.99 326	94.68 173	99.52 194

UniMVSNet (Re)		97.83 84	97.65 97	98.35 66	98.80 136	95.86 86	95.92 210	99.04 83	97.51 76	98.22 128	97.81 207	94.68 173	99.78 53	97.14 81	99.75 69	99.41 109

UniMVSNet_NR-MVSNet		97.83 84	97.65 97	98.37 64	98.72 148	95.78 87	95.66 226	99.02 86	98.11 51	98.31 120	97.69 218	94.65 175	99.85 29	97.02 88	99.71 78	99.48 86

VPNet		97.26 133	97.49 118	96.59 206	99.47 33	90.58 259	96.27 176	98.53 195	97.77 60	98.46 99	98.41 127	94.59 176	99.68 130	94.61 211	99.29 209	99.52 65

train_agg		95.46 226	94.66 255	97.88 104	97.84 255	95.23 117	93.62 329	98.39 212	87.04 364	93.78 345	95.99 326	94.58 177	99.52 194	91.76 285	98.90 256	98.89 214

test_8					97.81 259	95.07 126	93.54 332	98.38 214	87.04 364	93.71 349	95.96 329	94.58 177	99.52 194

API-MVS		95.09 245	95.01 236	95.31 274	96.61 342	94.02 164	96.83 139	97.18 297	95.60 171	95.79 292	94.33 365	94.54 179	98.37 381	85.70 377	98.52 294	93.52 414

Test By Simon												94.51 180

MSDG		95.33 233	95.13 230	95.94 246	97.40 312	91.85 234	91.02 395	98.37 215	95.30 187	96.31 267	95.99 326	94.51 180	98.38 379	89.59 334	97.65 342	97.60 347

TSAR-MVS + GP.		96.47 181	96.12 195	97.49 138	97.74 278	95.23 117	94.15 306	96.90 309	93.26 258	98.04 151	96.70 291	94.41 182	98.89 331	94.77 206	99.14 228	98.37 274

NR-MVSNet		97.96 60	97.86 75	98.26 72	98.73 145	95.54 97	98.14 54	98.73 163	97.79 59	99.42 22	97.83 202	94.40 183	99.78 53	95.91 134	99.76 61	99.46 91

AdaColmap		95.11 243	94.62 260	96.58 207	97.33 319	94.45 146	94.92 276	98.08 252	93.15 268	93.98 343	95.53 342	94.34 184	99.10 308	85.69 378	98.61 289	96.20 392

FC-MVSNet-test		98.16 43	98.37 37	97.56 126	99.49 32	93.10 197	98.35 35	99.21 40	98.43 36	98.89 61	98.83 82	94.30 185	99.81 41	97.87 50	99.91 17	99.77 15

Effi-MVS+-dtu		96.81 161	96.09 197	98.99 14	96.90 337	98.69 5	96.42 165	98.09 251	95.86 159	95.15 311	95.54 341	94.26 186	99.81 41	94.06 233	98.51 297	98.47 266

ambc				96.56 210	98.23 211	91.68 239	97.88 72	98.13 248		98.42 102	98.56 110	94.22 187	99.04 315	94.05 235	99.35 193	98.95 200

test20.03		96.58 176	96.61 169	96.48 215	98.49 184	91.72 237	95.68 224	97.69 275	96.81 103	98.27 124	97.92 197	94.18 188	98.71 348	90.78 306	99.66 90	99.00 192

HPM-MVS++		96.99 144	96.38 185	98.81 31	98.64 159	97.59 27	95.97 204	98.20 234	95.51 176	95.06 313	96.53 300	94.10 189	99.70 118	94.29 224	99.15 227	99.13 168

test_vis3_rt		97.04 141	96.98 147	97.23 161	98.44 190	95.88 84	96.82 140	99.67 10	90.30 324	99.27 33	99.33 28	94.04 190	96.03 416	97.14 81	97.83 328	99.78 14

test_fmvs3		97.38 125	97.56 110	96.84 192	98.63 163	92.81 203	97.60 94	99.61 18	90.87 315	98.76 75	99.66 4	94.03 191	97.90 395	99.24 9	99.68 86	99.81 10

PM-MVS		97.36 129	97.10 139	98.14 84	98.91 125	96.77 53	96.20 183	98.63 186	93.82 239	98.54 89	98.33 137	93.98 192	99.05 313	95.99 129	99.45 164	98.61 252

mvsany_test3		96.21 190	95.93 207	97.05 174	97.40 312	94.33 152	95.76 219	94.20 360	89.10 338	99.36 28	99.60 8	93.97 193	97.85 396	95.40 171	98.63 287	98.99 195

OpenMVS	94.22 8	95.48 224	95.20 226	96.32 225	97.16 326	91.96 231	97.74 84	98.84 135	87.26 361	94.36 330	98.01 187	93.95 194	99.67 139	90.70 313	98.75 273	97.35 358

v8		97.60 107	98.06 57	96.23 228	98.71 151	89.44 278	97.43 109	98.82 149	97.29 91	98.74 77	99.10 53	93.86 195	99.68 130	98.61 30	99.94 8	99.56 54

diffmvs		96.04 197	96.23 191	95.46 270	97.35 315	88.03 310	93.42 335	99.08 68	94.09 234	96.66 244	96.93 275	93.85 196	99.29 272	96.01 128	98.67 282	99.06 185
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
NCCC		96.52 178	95.99 202	98.10 87	97.81 259	95.68 92	95.00 274	98.20 234	95.39 183	95.40 307	96.36 311	93.81 197	99.45 217	93.55 251	98.42 303	99.17 159

TAPA-MVS	93.32 12	94.93 250	94.23 277	97.04 176	98.18 218	94.51 143	95.22 260	98.73 163	81.22 406	96.25 271	95.95 330	93.80 198	98.98 323	89.89 330	98.87 260	97.62 345
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
FIs		97.93 70	98.07 54	97.48 139	99.38 46	92.95 200	98.03 61	99.11 57	98.04 55	98.62 82	98.66 98	93.75 199	99.78 53	97.23 74	99.84 41	99.73 25

OurMVSNet-221017-0		98.61 17	98.61 25	98.63 48	99.77 5	96.35 68	99.17 7	99.05 76	98.05 54	99.61 14	99.52 9	93.72 200	99.88 21	98.72 28	99.88 25	99.65 36

SSC-MVS3.2		95.75 211	96.56 173	93.34 342	98.69 155	80.75 397	91.60 379	97.43 291	97.37 87	96.99 221	97.02 268	93.69 201	99.71 109	96.32 112	99.89 23	99.55 57

test_prior2							93.33 339		94.21 226	94.02 341	96.25 315	93.64 202		91.90 279	98.96 249

mvsany_test1		93.47 306	93.03 303	94.79 301	94.05 411	92.12 224	90.82 397	90.01 410	85.02 388	97.26 198	98.28 148	93.57 203	97.03 405	92.51 271	95.75 393	95.23 405

旧先验1					97.80 263	93.87 169		97.75 272			97.04 267	93.57 203			98.68 281	98.72 239

v10		97.55 112	97.97 65	96.31 226	98.60 167	89.64 273	97.44 107	99.02 86	96.60 111	98.72 79	99.16 47	93.48 205	99.72 95	98.76 25	99.92 14	99.58 43

v148		96.58 176	96.97 148	95.42 271	98.63 163	87.57 320	95.09 266	97.90 262	95.91 156	98.24 126	97.96 191	93.42 206	99.39 239	96.04 124	99.52 140	99.29 138

V42		97.04 141	97.16 137	96.68 203	98.59 169	91.05 249	96.33 173	98.36 216	94.60 214	97.99 154	98.30 143	93.32 207	99.62 161	97.40 71	99.53 135	99.38 117

new-patchmatchnet		95.67 215	96.58 171	92.94 359	97.48 304	80.21 400	92.96 345	98.19 239	94.83 206	98.82 67	98.79 83	93.31 208	99.51 198	95.83 139	99.04 244	99.12 173

test12				97.46 141	97.61 295	94.07 161		97.78 271		93.57 356		93.31 208	99.42 224		98.78 270	98.89 214

UGNet		96.81 161	96.56 173	97.58 125	96.64 341	93.84 171	97.75 82	97.12 300	96.47 122	93.62 352	98.88 79	93.22 210	99.53 191	95.61 151	99.69 82	99.36 123
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
mvs5depth		98.06 53	98.58 26	96.51 212	98.97 115	89.65 272	99.43 4	99.81 2	99.30 7	98.36 110	99.86 2	93.15 211	99.88 21	98.50 34	99.84 41	99.99 1

pmmvs-eth3d		96.49 179	96.18 194	97.42 146	98.25 208	94.29 153	94.77 283	98.07 256	89.81 331	97.97 158	98.33 137	93.11 212	99.08 310	95.46 163	99.84 41	98.89 214

v1144		96.84 156	97.08 141	96.13 237	98.42 192	89.28 281	95.41 243	98.67 178	94.21 226	97.97 158	98.31 139	93.06 213	99.65 147	98.06 44	99.62 97	99.45 95

MVSMamba_PlusPlus		97.43 122	97.98 64	95.78 252	98.88 128	89.70 270	98.03 61	98.85 131	99.18 11	96.84 232	99.12 51	93.04 214	99.91 14	98.38 36	99.55 127	97.73 338

PVSNet_BlendedMVS		95.02 249	94.93 239	95.27 275	97.79 268	87.40 324	94.14 308	98.68 175	88.94 342	94.51 326	98.01 187	93.04 214	99.30 268	89.77 332	99.49 152	99.11 176

PVSNet_Blended		93.96 293	93.65 293	94.91 292	97.79 268	87.40 324	91.43 383	98.68 175	84.50 394	94.51 326	94.48 363	93.04 214	99.30 268	89.77 332	98.61 289	98.02 316

mvs_anonymous		95.36 230	96.07 199	93.21 349	96.29 350	81.56 390	94.60 289	97.66 278	93.30 257	96.95 226	98.91 76	93.03 217	99.38 242	96.60 99	97.30 356	98.69 243

v1192		96.83 159	97.06 143	96.15 236	98.28 203	89.29 280	95.36 247	98.77 156	93.73 241	98.11 140	98.34 136	93.02 218	99.67 139	98.35 37	99.58 115	99.50 72

F-COLMAP		95.30 235	94.38 274	98.05 94	98.64 159	96.04 79	95.61 232	98.66 180	89.00 341	93.22 365	96.40 309	92.90 219	99.35 254	87.45 366	97.53 346	98.77 233

WR-MVS		96.90 152	96.81 158	97.16 163	98.56 173	92.20 222	94.33 295	98.12 249	97.34 88	98.20 129	97.33 248	92.81 220	99.75 74	94.79 203	99.81 50	99.54 59

v1240		96.74 164	97.02 146	95.91 247	98.18 218	88.52 296	95.39 245	98.88 122	93.15 268	98.46 99	98.40 130	92.80 221	99.71 109	98.45 35	99.49 152	99.49 80

MVE	73.61 22	86.48 390	85.92 389	88.18 404	96.23 353	85.28 354	81.78 425	75.79 429	86.01 374	82.53 425	91.88 398	92.74 222	87.47 428	71.42 424	94.86 401	91.78 419
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DP-MVS Recon		95.55 220	95.13 230	96.80 194	98.51 180	93.99 166	94.60 289	98.69 173	90.20 326	95.78 294	96.21 317	92.73 223	98.98 323	90.58 317	98.86 262	97.42 355

CANet		95.86 205	95.65 218	96.49 214	96.41 348	90.82 254	94.36 294	98.41 209	94.94 203	92.62 381	96.73 290	92.68 224	99.71 109	95.12 188	99.60 109	98.94 202

v1921920		96.72 167	96.96 150	95.99 240	98.21 212	88.79 293	95.42 241	98.79 151	93.22 260	98.19 133	98.26 153	92.68 224	99.70 118	98.34 38	99.55 127	99.49 80

BH-untuned		94.69 263	94.75 253	94.52 313	97.95 246	87.53 321	94.07 311	97.01 305	93.99 236	97.10 210	95.65 337	92.65 226	98.95 328	87.60 361	96.74 369	97.09 363

LF4IMVS		96.07 195	95.63 219	97.36 150	98.19 215	95.55 96	95.44 239	98.82 149	92.29 290	95.70 298	96.55 298	92.63 227	98.69 351	91.75 286	99.33 201	97.85 328

v2v482		96.78 163	97.06 143	95.95 244	98.57 171	88.77 294	95.36 247	98.26 226	95.18 192	97.85 172	98.23 157	92.58 228	99.63 156	97.80 54	99.69 82	99.45 95

WB-MVSnew		91.50 343	91.29 336	92.14 377	94.85 396	80.32 399	93.29 340	88.77 413	88.57 348	94.03 340	92.21 394	92.56 229	98.28 386	80.21 408	97.08 358	97.81 332

EI-MVSNet		96.63 173	96.93 151	95.74 254	97.26 322	88.13 307	95.29 257	97.65 280	96.99 97	97.94 162	98.19 162	92.55 230	99.58 175	96.91 91	99.56 121	99.50 72

IterMVS-LS		96.92 150	97.29 127	95.79 251	98.51 180	88.13 307	95.10 265	98.66 180	96.99 97	98.46 99	98.68 97	92.55 230	99.74 83	96.91 91	99.79 55	99.50 72
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
VDD-MVS		97.37 127	97.25 130	97.74 113	98.69 155	94.50 145	97.04 129	95.61 338	98.59 31	98.51 91	98.72 90	92.54 232	99.58 175	96.02 126	99.49 152	99.12 173

MVS		90.02 357	89.20 364	92.47 371	94.71 399	86.90 333	95.86 213	96.74 316	64.72 426	90.62 394	92.77 386	92.54 232	98.39 378	79.30 410	95.56 395	92.12 418

test_vis1_rt		94.03 292	93.65 293	95.17 280	95.76 378	93.42 188	93.97 317	98.33 220	84.68 391	93.17 366	95.89 332	92.53 234	94.79 420	93.50 252	94.97 399	97.31 360

v144192		96.69 170	96.90 155	96.03 239	98.25 208	88.92 288	95.49 237	98.77 156	93.05 270	98.09 143	98.29 147	92.51 235	99.70 118	98.11 41	99.56 121	99.47 89

原ACMM1				96.58 207	98.16 223	92.12 224		98.15 246	85.90 377	93.49 358	96.43 306	92.47 236	99.38 242	87.66 360	98.62 288	98.23 292

VNet		96.84 156	96.83 157	96.88 188	98.06 233	92.02 229	96.35 172	97.57 286	97.70 67	97.88 167	97.80 208	92.40 237	99.54 189	94.73 208	98.96 249	99.08 181

114514_t		93.96 293	93.22 301	96.19 232	99.06 100	90.97 252	95.99 202	98.94 110	73.88 424	93.43 361	96.93 275	92.38 238	99.37 247	89.09 341	99.28 210	98.25 291

balanced_conf03		96.88 154	97.29 127	95.63 259	97.66 288	89.47 277	97.95 66	98.89 115	95.94 152	97.77 177	98.55 111	92.23 239	99.68 130	97.05 87	99.61 103	97.73 338

CPTT-MVS		96.69 170	96.08 198	98.49 56	98.89 127	96.64 59	97.25 115	98.77 156	92.89 278	96.01 283	97.13 259	92.23 239	99.67 139	92.24 274	99.34 196	99.17 159

MSP-MVS		97.45 119	96.92 153	99.03 9	99.26 57	97.70 22	97.66 90	98.89 115	95.65 168	98.51 91	96.46 304	92.15 241	99.81 41	95.14 185	98.58 292	99.58 43
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
MAR-MVS		94.21 283	93.03 303	97.76 112	96.94 335	97.44 37	96.97 133	97.15 298	87.89 358	92.00 386	92.73 388	92.14 242	99.12 302	83.92 392	97.51 347	96.73 380
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		95.95 201	95.80 212	96.42 218	99.28 55	90.62 258	95.31 255	99.08 68	88.40 350	96.97 225	98.17 165	92.11 243	99.78 53	93.64 249	99.21 219	98.86 221

BH-RMVSNet		94.56 271	94.44 272	94.91 292	97.57 297	87.44 323	93.78 325	96.26 322	93.69 244	96.41 260	96.50 303	92.10 244	99.00 319	85.96 375	97.71 335	98.31 283

新几何1				97.25 159	98.29 201	94.70 135		97.73 273	77.98 417	94.83 320	96.67 293	92.08 245	99.45 217	88.17 355	98.65 286	97.61 346

testdata				95.70 257	98.16 223	90.58 259		97.72 274	80.38 409	95.62 299	97.02 268	92.06 246	98.98 323	89.06 343	98.52 294	97.54 350

YYNet1		94.73 258	94.84 247	94.41 318	97.47 308	85.09 358	90.29 402	95.85 332	92.52 284	97.53 182	97.76 209	91.97 247	99.18 291	93.31 257	96.86 363	98.95 200

Anonymous20231206		95.27 236	95.06 235	95.88 248	98.72 148	89.37 279	95.70 221	97.85 265	88.00 356	96.98 224	97.62 222	91.95 248	99.34 257	89.21 339	99.53 135	98.94 202

MS-PatchMatch		94.83 255	94.91 241	94.57 311	96.81 338	87.10 330	94.23 301	97.34 292	88.74 345	97.14 206	97.11 262	91.94 249	98.23 388	92.99 264	97.92 323	98.37 274

MDA-MVSNet_test_wron		94.73 258	94.83 249	94.42 317	97.48 304	85.15 356	90.28 403	95.87 331	92.52 284	97.48 188	97.76 209	91.92 250	99.17 295	93.32 256	96.80 368	98.94 202

HQP_MVS		96.66 172	96.33 188	97.68 120	98.70 153	94.29 153	96.50 162	98.75 160	96.36 125	96.16 277	96.77 287	91.91 251	99.46 212	92.59 269	99.20 220	99.28 139

plane_prior6					98.38 194	94.37 150						91.91 251

MVP-Stereo		95.69 213	95.28 224	96.92 183	98.15 225	93.03 198	95.64 231	98.20 234	90.39 323	96.63 247	97.73 215	91.63 253	99.10 308	91.84 282	97.31 355	98.63 249
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PatchMatch-RL		94.61 269	93.81 291	97.02 178	98.19 215	95.72 89	93.66 327	97.23 294	88.17 354	94.94 318	95.62 339	91.43 254	98.57 363	87.36 367	97.68 338	96.76 379

MDA-MVSNet-bldmvs		95.69 213	95.67 216	95.74 254	98.48 186	88.76 295	92.84 347	97.25 293	96.00 147	97.59 180	97.95 193	91.38 255	99.46 212	93.16 262	96.35 380	98.99 195

SSC-MVS		95.92 202	97.03 145	92.58 368	99.28 55	78.39 405	96.68 156	95.12 349	98.90 23	99.11 42	98.66 98	91.36 256	99.68 130	95.00 194	99.16 226	99.67 31

PAPR		92.22 328	91.27 338	95.07 284	95.73 380	88.81 292	91.97 373	97.87 264	85.80 378	90.91 393	92.73 388	91.16 257	98.33 383	79.48 409	95.76 392	98.08 304

1314		92.38 325	92.30 320	92.64 367	95.42 387	85.15 356	95.86 213	96.97 307	85.40 383	90.62 394	93.06 380	91.12 258	97.80 398	86.74 372	95.49 396	94.97 407

WB-MVS		95.50 221	96.62 167	92.11 378	99.21 73	77.26 415	96.12 190	95.40 344	98.62 30	98.84 65	98.26 153	91.08 259	99.50 199	93.37 253	98.70 280	99.58 43

ppachtmachnet_test		94.49 275	94.84 247	93.46 341	96.16 357	82.10 385	90.59 399	97.48 288	90.53 321	97.01 220	97.59 224	91.01 260	99.36 250	93.97 239	99.18 224	98.94 202

PLC	91.02 16	94.05 290	92.90 306	97.51 131	98.00 241	95.12 125	94.25 299	98.25 227	86.17 373	91.48 391	95.25 346	91.01 260	99.19 290	85.02 387	96.69 372	98.22 294
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test222					98.17 221	93.24 195	92.74 352	97.61 285	75.17 422	94.65 323	96.69 292	90.96 262			98.66 284	97.66 342

CL-MVSNet_self_test		95.04 246	94.79 252	95.82 250	97.51 302	89.79 269	91.14 392	96.82 312	93.05 270	96.72 239	96.40 309	90.82 263	99.16 296	91.95 278	98.66 284	98.50 264

USDC		94.56 271	94.57 266	94.55 312	97.78 271	86.43 340	92.75 350	98.65 185	85.96 375	96.91 229	97.93 196	90.82 263	98.74 344	90.71 312	99.59 112	98.47 266

PCF-MVS	89.43 18	92.12 331	90.64 351	96.57 209	97.80 263	93.48 185	89.88 409	98.45 202	74.46 423	96.04 282	95.68 336	90.71 265	99.31 265	73.73 420	99.01 247	96.91 370
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PAPM_NR		94.61 269	94.17 281	95.96 242	98.36 196	91.23 247	95.93 209	97.95 259	92.98 273	93.42 362	94.43 364	90.53 266	98.38 379	87.60 361	96.29 382	98.27 289

our_test_3		94.20 285	94.58 264	93.07 352	96.16 357	81.20 394	90.42 401	96.84 310	90.72 317	97.14 206	97.13 259	90.47 267	99.11 305	94.04 236	98.25 310	98.91 210

MM		96.87 155	96.62 167	97.62 123	97.72 280	93.30 191	96.39 166	92.61 380	97.90 58	96.76 238	98.64 102	90.46 268	99.81 41	99.16 12	99.94 8	99.76 20

test_f		95.82 207	95.88 210	95.66 258	97.61 295	93.21 196	95.61 232	98.17 240	86.98 366	98.42 102	99.47 13	90.46 268	94.74 421	97.71 60	98.45 301	99.03 188

OpenMVS_ROB	91.80 14	93.64 302	93.05 302	95.42 271	97.31 321	91.21 248	95.08 268	96.68 319	81.56 403	96.88 231	96.41 307	90.44 270	99.25 280	85.39 383	97.67 339	95.80 397

HQP2-MVS												90.33 271

N_pmnet		95.18 240	94.23 277	98.06 90	97.85 250	96.55 62	92.49 358	91.63 389	89.34 335	98.09 143	97.41 236	90.33 271	99.06 312	91.58 287	99.31 206	98.56 255

HQP-MVS		95.17 242	94.58 264	96.92 183	97.85 250	92.47 213	94.26 296	98.43 205	93.18 264	92.86 372	95.08 348	90.33 271	99.23 286	90.51 319	98.74 274	99.05 187

CNLPA		95.04 246	94.47 269	96.75 198	97.81 259	95.25 116	94.12 310	97.89 263	94.41 221	94.57 324	95.69 335	90.30 274	98.35 382	86.72 373	98.76 272	96.64 381

PMMVS		92.39 324	91.08 341	96.30 227	93.12 418	92.81 203	90.58 400	95.96 328	79.17 414	91.85 388	92.27 393	90.29 275	98.66 356	89.85 331	96.68 373	97.43 354

TR-MVS		92.54 323	92.20 323	93.57 339	96.49 345	86.66 336	93.51 333	94.73 354	89.96 329	94.95 317	93.87 370	90.24 276	98.61 360	81.18 405	94.88 400	95.45 403

TAMVS		95.49 222	94.94 237	97.16 163	98.31 199	93.41 189	95.07 269	96.82 312	91.09 313	97.51 184	97.82 205	89.96 277	99.42 224	88.42 351	99.44 165	98.64 247

DPM-MVS		93.68 300	92.77 313	96.42 218	97.91 247	92.54 209	91.17 391	97.47 289	84.99 389	93.08 368	94.74 356	89.90 278	99.00 319	87.54 363	98.09 317	97.72 340

PMMVS2		93.66 301	94.07 284	92.45 372	97.57 297	80.67 398	86.46 417	96.00 326	93.99 236	97.10 210	97.38 243	89.90 278	97.82 397	88.76 345	99.47 158	98.86 221

BH-w/o		92.14 330	91.94 325	92.73 365	97.13 328	85.30 352	92.46 360	95.64 335	89.33 336	94.21 332	92.74 387	89.60 280	98.24 387	81.68 402	94.66 402	94.66 408

Anonymous20240521		97.07 140	97.51 115	95.76 253	99.35 49	88.18 304	97.78 78	98.40 211	97.11 95	98.34 114	99.04 59	89.58 281	99.79 49	98.09 42	99.93 11	99.30 132

UnsupCasMVSNet_bld		94.72 262	94.26 276	96.08 238	98.62 165	90.54 262	93.38 337	98.05 258	90.30 324	97.02 219	96.80 286	89.54 282	99.16 296	88.44 350	96.18 384	98.56 255

MG-MVS		94.08 289	94.00 286	94.32 322	97.09 329	85.89 345	93.19 343	95.96 328	92.52 284	94.93 319	97.51 230	89.54 282	98.77 341	87.52 365	97.71 335	98.31 283

UnsupCasMVSNet_eth		95.91 203	95.73 215	96.44 216	98.48 186	91.52 241	95.31 255	98.45 202	95.76 163	97.48 188	97.54 227	89.53 284	98.69 351	94.43 217	94.61 403	99.13 168

GBi-Net		96.99 144	96.80 159	97.56 126	97.96 243	93.67 177	98.23 46	98.66 180	95.59 172	97.99 154	99.19 39	89.51 285	99.73 89	94.60 212	99.44 165	99.30 132

test1		96.99 144	96.80 159	97.56 126	97.96 243	93.67 177	98.23 46	98.66 180	95.59 172	97.99 154	99.19 39	89.51 285	99.73 89	94.60 212	99.44 165	99.30 132

FMVSNet2		96.72 167	96.67 166	96.87 189	97.96 243	91.88 233	97.15 121	98.06 257	95.59 172	98.50 93	98.62 103	89.51 285	99.65 147	94.99 196	99.60 109	99.07 183

pmmvs4		94.82 256	94.19 280	96.70 201	97.42 311	92.75 207	92.09 372	96.76 314	86.80 369	95.73 297	97.22 254	89.28 288	98.89 331	93.28 258	99.14 228	98.46 268

cascas		91.89 337	91.35 335	93.51 340	94.27 405	85.60 347	88.86 414	98.61 187	79.32 413	92.16 385	91.44 403	89.22 289	98.12 391	90.80 305	97.47 350	96.82 376

DSMNet-mixed		92.19 329	91.83 327	93.25 346	96.18 356	83.68 376	96.27 176	93.68 365	76.97 421	92.54 382	99.18 43	89.20 290	98.55 366	83.88 393	98.60 291	97.51 351

c3_l		95.20 239	95.32 223	94.83 299	96.19 355	86.43 340	91.83 376	98.35 219	93.47 251	97.36 194	97.26 252	88.69 291	99.28 274	95.41 170	99.36 188	98.78 230

test_fmvs2		96.38 185	96.45 182	96.16 235	97.85 250	91.30 245	96.81 141	99.45 25	89.24 337	98.49 94	99.38 20	88.68 292	97.62 400	98.83 22	99.32 203	99.57 50

CANet_DTU		94.65 267	94.21 279	95.96 242	95.90 367	89.68 271	93.92 319	97.83 269	93.19 263	90.12 403	95.64 338	88.52 293	99.57 181	93.27 259	99.47 158	98.62 250

EPP-MVSNet		96.84 156	96.58 171	97.65 121	99.18 78	93.78 174	98.68 14	96.34 321	97.91 57	97.30 195	98.06 181	88.46 294	99.85 29	93.85 242	99.40 182	99.32 127

SixPastTwentyTwo		97.49 116	97.57 109	97.26 158	99.56 20	92.33 215	98.28 42	96.97 307	98.30 43	99.45 20	99.35 25	88.43 295	99.89 19	98.01 45	99.76 61	99.54 59

miper_ehance_all_eth		94.69 263	94.70 254	94.64 305	95.77 377	86.22 342	91.32 388	98.24 229	91.67 299	97.05 217	96.65 294	88.39 296	99.22 288	94.88 198	98.34 306	98.49 265

MVS_0304		95.71 212	95.18 228	97.33 152	94.85 396	92.82 201	95.36 247	90.89 398	95.51 176	95.61 300	97.82 205	88.39 296	99.78 53	98.23 39	99.91 17	99.40 110

IS-MVSNet		96.93 149	96.68 165	97.70 117	99.25 60	94.00 165	98.57 20	96.74 316	98.36 39	98.14 138	97.98 190	88.23 298	99.71 109	93.10 263	99.72 75	99.38 117

jason		94.39 278	94.04 285	95.41 273	98.29 201	87.85 315	92.74 352	96.75 315	85.38 384	95.29 308	96.15 319	88.21 299	99.65 147	94.24 226	99.34 196	98.74 236
jason: jason.
IterMVS-SCA-FT		95.86 205	96.19 193	94.85 297	97.68 283	85.53 348	92.42 363	97.63 284	96.99 97	98.36 110	98.54 113	87.94 300	99.75 74	97.07 86	99.08 238	99.27 143

SCA		93.38 309	93.52 296	92.96 358	96.24 351	81.40 392	93.24 341	94.00 361	91.58 304	94.57 324	96.97 272	87.94 300	99.42 224	89.47 336	97.66 341	98.06 310

sss		94.22 281	93.72 292	95.74 254	97.71 281	89.95 266	93.84 321	96.98 306	88.38 351	93.75 348	95.74 334	87.94 300	98.89 331	91.02 297	98.10 316	98.37 274

IterMVS		95.42 228	95.83 211	94.20 326	97.52 301	83.78 375	92.41 364	97.47 289	95.49 178	98.06 148	98.49 117	87.94 300	99.58 175	96.02 126	99.02 245	99.23 150
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CHOSEN 1792x2688		94.10 287	93.41 298	96.18 233	99.16 80	90.04 264	92.15 369	98.68 175	79.90 411	96.22 273	97.83 202	87.92 304	99.42 224	89.18 340	99.65 91	99.08 181

VDDNet		96.98 147	96.84 156	97.41 147	99.40 43	93.26 194	97.94 67	95.31 346	99.26 9	98.39 106	99.18 43	87.85 305	99.62 161	95.13 187	99.09 237	99.35 125

pmmvs5		94.63 268	94.34 275	95.50 267	97.63 294	88.34 300	94.02 312	97.13 299	87.15 363	95.22 310	97.15 258	87.50 306	99.27 277	93.99 237	99.26 214	98.88 218

D2MVS		95.18 240	95.17 229	95.21 277	97.76 273	87.76 318	94.15 306	97.94 260	89.77 332	96.99 221	97.68 219	87.45 307	99.14 298	95.03 193	99.81 50	98.74 236

test_vis1_n_1920		95.77 209	96.41 184	93.85 331	98.55 174	84.86 362	95.91 211	99.71 7	92.72 282	97.67 178	98.90 77	87.44 308	98.73 345	97.96 46	98.85 263	97.96 320

PVSNet	86.72 19	91.10 348	90.97 344	91.49 383	97.56 299	78.04 408	87.17 416	94.60 356	84.65 392	92.34 383	92.20 395	87.37 309	98.47 373	85.17 386	97.69 337	97.96 320

Anonymous202405211		96.34 186	95.98 203	97.43 144	98.25 208	93.85 170	96.74 149	94.41 358	97.72 65	98.37 107	98.03 184	87.15 310	99.53 191	94.06 233	99.07 240	98.92 209

MVSFormer		96.14 193	96.36 186	95.49 268	97.68 283	87.81 316	98.67 15	99.02 86	96.50 118	94.48 328	96.15 319	86.90 311	99.92 6	98.73 26	99.13 230	98.74 236

lupinMVS		93.77 296	93.28 299	95.24 276	97.68 283	87.81 316	92.12 370	96.05 324	84.52 393	94.48 328	95.06 350	86.90 311	99.63 156	93.62 250	99.13 230	98.27 289

eth_miper_zixun_eth		94.89 253	94.93 239	94.75 303	95.99 364	86.12 343	91.35 385	98.49 199	93.40 252	97.12 208	97.25 253	86.87 313	99.35 254	95.08 190	98.82 267	98.78 230

test_vis1_n		95.67 215	95.89 209	95.03 286	98.18 218	89.89 267	96.94 134	99.28 35	88.25 353	98.20 129	98.92 73	86.69 314	97.19 403	97.70 62	98.82 267	98.00 318

RRT-MVS		95.78 208	96.25 190	94.35 320	96.68 340	84.47 367	97.72 86	99.11 57	97.23 92	97.27 197	98.72 90	86.39 315	99.79 49	95.49 156	97.67 339	98.80 227

WTY-MVS		93.55 304	93.00 305	95.19 278	97.81 259	87.86 313	93.89 320	96.00 326	89.02 340	94.07 338	95.44 345	86.27 316	99.33 259	87.69 359	96.82 366	98.39 272

CDS-MVSNet		94.88 254	94.12 283	97.14 165	97.64 293	93.57 182	93.96 318	97.06 303	90.05 328	96.30 268	96.55 298	86.10 317	99.47 209	90.10 326	99.31 206	98.40 270
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
1112_ss		94.12 286	93.42 297	96.23 228	98.59 169	90.85 253	94.24 300	98.85 131	85.49 380	92.97 370	94.94 352	86.01 318	99.64 152	91.78 284	97.92 323	98.20 296

dmvs_testset		87.30 387	86.99 384	88.24 403	96.71 339	77.48 412	94.68 286	86.81 420	92.64 283	89.61 408	87.01 423	85.91 319	93.12 424	61.04 427	88.49 420	94.13 411

miper_enhance_ethall		93.14 315	92.78 312	94.20 326	93.65 414	85.29 353	89.97 405	97.85 265	85.05 386	96.15 279	94.56 359	85.74 320	99.14 298	93.74 245	98.34 306	98.17 300

ttmdpeth		94.05 290	94.15 282	93.75 334	95.81 374	85.32 351	96.00 200	94.93 352	92.07 291	94.19 333	99.09 55	85.73 321	96.41 415	90.98 298	98.52 294	99.53 62

new_pmnet		92.34 326	91.69 331	94.32 322	96.23 353	89.16 283	92.27 367	92.88 374	84.39 396	95.29 308	96.35 312	85.66 322	96.74 413	84.53 390	97.56 344	97.05 364

Syy-MVS		92.09 332	91.80 329	92.93 360	95.19 391	82.65 381	92.46 360	91.35 392	90.67 319	91.76 389	87.61 421	85.64 323	98.50 370	94.73 208	96.84 364	97.65 343

alignmvs		96.01 199	95.52 222	97.50 135	97.77 272	94.71 133	96.07 193	96.84 310	97.48 77	96.78 237	94.28 366	85.50 324	99.40 235	96.22 117	98.73 277	98.40 270

lessismore_v0				97.05 174	99.36 48	92.12 224		84.07 423		98.77 74	98.98 65	85.36 325	99.74 83	97.34 73	99.37 185	99.30 132

HY-MVS	91.43 15	92.58 322	91.81 328	94.90 294	96.49 345	88.87 290	97.31 112	94.62 355	85.92 376	90.50 397	96.84 281	85.05 326	99.40 235	83.77 395	95.78 391	96.43 388

EPNet		93.72 298	92.62 317	97.03 177	87.61 432	92.25 217	96.27 176	91.28 394	96.74 106	87.65 417	97.39 241	85.00 327	99.64 152	92.14 275	99.48 156	99.20 155
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_lstm_enhance		94.81 257	94.80 251	94.85 297	96.16 357	86.45 339	91.14 392	98.20 234	93.49 250	97.03 218	97.37 245	84.97 328	99.26 278	95.28 173	99.56 121	98.83 223

Test_1112_low_res		93.53 305	92.86 307	95.54 266	98.60 167	88.86 291	92.75 350	98.69 173	82.66 400	92.65 378	96.92 277	84.75 329	99.56 182	90.94 300	97.76 331	98.19 297

MVS-HIRNet		88.40 376	90.20 357	82.99 408	97.01 331	60.04 433	93.11 344	85.61 422	84.45 395	88.72 413	99.09 55	84.72 330	98.23 388	82.52 399	96.59 375	90.69 423

K. test v3		96.44 182	96.28 189	96.95 180	99.41 40	91.53 240	97.65 91	90.31 406	98.89 24	98.93 57	99.36 23	84.57 331	99.92 6	97.81 53	99.56 121	99.39 115

test_cas_vis1_n_1920		95.34 232	95.67 216	94.35 320	98.21 212	86.83 335	95.61 232	99.26 37	90.45 322	98.17 134	98.96 68	84.43 332	98.31 384	96.74 96	99.17 225	97.90 324

h-mvs33		96.29 187	95.63 219	98.26 72	98.50 183	96.11 77	96.90 136	97.09 301	96.58 113	97.21 201	98.19 162	84.14 333	99.78 53	95.89 135	96.17 385	98.89 214

hse-mvs2		95.77 209	95.09 232	97.79 109	97.84 255	95.51 99	95.66 226	95.43 343	96.58 113	97.21 201	96.16 318	84.14 333	99.54 189	95.89 135	96.92 360	98.32 281

MonoMVSNet		93.30 311	93.96 289	91.33 386	94.14 409	81.33 393	97.68 89	96.69 318	95.38 184	96.32 264	98.42 125	84.12 335	96.76 412	90.78 306	92.12 413	95.89 394

DIV-MVS_self_test		94.73 258	94.64 257	95.01 287	95.86 370	87.00 331	91.33 386	98.08 252	93.34 255	97.10 210	97.34 247	84.02 336	99.31 265	95.15 184	99.55 127	98.72 239

cl____		94.73 258	94.64 257	95.01 287	95.85 371	87.00 331	91.33 386	98.08 252	93.34 255	97.10 210	97.33 248	84.01 337	99.30 268	95.14 185	99.56 121	98.71 242

Vis-MVSNet (Re-imp)		95.11 243	94.85 246	95.87 249	99.12 91	89.17 282	97.54 104	94.92 353	96.50 118	96.58 250	97.27 251	83.64 338	99.48 207	88.42 351	99.67 88	98.97 197

FA-MVS(test-final)		94.91 251	94.89 242	94.99 289	97.51 302	88.11 309	98.27 44	95.20 348	92.40 289	96.68 241	98.60 106	83.44 339	99.28 274	93.34 255	98.53 293	97.59 348

dmvs_re		92.08 333	91.27 338	94.51 314	97.16 326	92.79 206	95.65 228	92.64 379	94.11 232	92.74 375	90.98 408	83.41 340	94.44 423	80.72 406	94.07 406	96.29 390

PVSNet_0	81.89 21	84.49 391	83.21 394	88.34 402	95.76 378	74.97 423	83.49 422	92.70 378	78.47 416	87.94 416	86.90 424	83.38 341	96.63 414	73.44 421	66.86 428	93.40 415

mvsmamba		94.91 251	94.41 273	96.40 222	97.65 290	91.30 245	97.92 69	95.32 345	91.50 305	95.54 303	98.38 131	83.06 342	99.68 130	92.46 272	97.84 327	98.23 292

test_fmvs1_n		95.21 238	95.28 224	94.99 289	98.15 225	89.13 285	96.81 141	99.43 27	86.97 367	97.21 201	98.92 73	83.00 343	97.13 404	98.09 42	98.94 252	98.72 239

CMPMVS	73.10 23	92.74 320	91.39 334	96.77 197	93.57 416	94.67 136	94.21 303	97.67 276	80.36 410	93.61 353	96.60 296	82.85 344	97.35 402	84.86 388	98.78 270	98.29 288
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_fmvs1		94.51 274	94.60 261	94.26 325	95.91 366	87.92 311	95.35 250	99.02 86	86.56 371	96.79 233	98.52 114	82.64 345	97.00 407	97.87 50	98.71 278	97.88 326

EU-MVSNet		94.25 280	94.47 269	93.60 338	98.14 227	82.60 383	97.24 117	92.72 377	85.08 385	98.48 96	98.94 70	82.59 346	98.76 343	97.47 70	99.53 135	99.44 105

baseline1		93.14 315	92.64 316	94.62 307	97.34 317	87.20 328	96.67 158	93.02 372	94.71 210	96.51 256	95.83 333	81.64 347	98.60 362	90.00 328	88.06 421	98.07 306

test1111		94.53 273	94.81 250	93.72 335	99.06 100	81.94 388	98.31 39	83.87 424	96.37 124	98.49 94	99.17 46	81.49 348	99.73 89	96.64 97	99.86 30	99.49 80

CVMVSNet		92.33 327	92.79 310	90.95 388	97.26 322	75.84 419	95.29 257	92.33 383	81.86 401	96.27 269	98.19 162	81.44 349	98.46 374	94.23 227	98.29 309	98.55 257

EPNet_dtu		91.39 345	90.75 348	93.31 344	90.48 428	82.61 382	94.80 280	92.88 374	93.39 253	81.74 426	94.90 355	81.36 350	99.11 305	88.28 353	98.87 260	98.21 295
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ECVR-MVS		94.37 279	94.48 268	94.05 330	98.95 116	83.10 378	98.31 39	82.48 426	96.20 132	98.23 127	99.16 47	81.18 351	99.66 145	95.95 131	99.83 45	99.38 117

test_yl		94.40 276	94.00 286	95.59 260	96.95 333	89.52 275	94.75 284	95.55 340	96.18 135	96.79 233	96.14 321	81.09 352	99.18 291	90.75 308	97.77 329	98.07 306

DCV-MVSNet		94.40 276	94.00 286	95.59 260	96.95 333	89.52 275	94.75 284	95.55 340	96.18 135	96.79 233	96.14 321	81.09 352	99.18 291	90.75 308	97.77 329	98.07 306

MIMVSNet		93.42 307	92.86 307	95.10 283	98.17 221	88.19 303	98.13 55	93.69 363	92.07 291	95.04 316	98.21 161	80.95 354	99.03 318	81.42 403	98.06 318	98.07 306

PAPM		87.64 383	85.84 390	93.04 353	96.54 343	84.99 359	88.42 415	95.57 339	79.52 412	83.82 423	93.05 381	80.57 355	98.41 376	62.29 426	92.79 410	95.71 398

HyFIR lowres test		93.72 298	92.65 315	96.91 185	98.93 121	91.81 236	91.23 390	98.52 196	82.69 399	96.46 258	96.52 302	80.38 356	99.90 16	90.36 323	98.79 269	99.03 188

FMVSNet3		95.26 237	94.94 237	96.22 230	96.53 344	90.06 263	95.99 202	97.66 278	94.11 232	97.99 154	97.91 198	80.22 357	99.63 156	94.60 212	99.44 165	98.96 198

RPMNet		94.68 265	94.60 261	94.90 294	95.44 385	88.15 305	96.18 184	98.86 127	97.43 78	94.10 336	98.49 117	79.40 358	99.76 68	95.69 144	95.81 388	96.81 377

LFMVS		95.32 234	94.88 244	96.62 204	98.03 234	91.47 242	97.65 91	90.72 401	99.11 12	97.89 166	98.31 139	79.20 359	99.48 207	93.91 241	99.12 233	98.93 206

ADS-MVSNet2		91.47 344	90.51 353	94.36 319	95.51 383	85.63 346	95.05 271	95.70 333	83.46 397	92.69 376	96.84 281	79.15 360	99.41 233	85.66 379	90.52 415	98.04 314

ADS-MVSNet		90.95 351	90.26 356	93.04 353	95.51 383	82.37 384	95.05 271	93.41 369	83.46 397	92.69 376	96.84 281	79.15 360	98.70 349	85.66 379	90.52 415	98.04 314

MDTV_nov1_ep13_2view						57.28 434	94.89 277		80.59 408	94.02 341		78.66 362		85.50 381		97.82 330

cl22		93.25 313	92.84 309	94.46 316	94.30 404	86.00 344	91.09 394	96.64 320	90.74 316	95.79 292	96.31 313	78.24 363	98.77 341	94.15 230	98.34 306	98.62 250

PatchmatchNet		91.98 336	91.87 326	92.30 374	94.60 401	79.71 401	95.12 263	93.59 368	89.52 334	93.61 353	97.02 268	77.94 364	99.18 291	90.84 303	94.57 405	98.01 317
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												77.80 365				98.06 310

CR-MVSNet		93.29 312	92.79 310	94.78 302	95.44 385	88.15 305	96.18 184	97.20 295	84.94 390	94.10 336	98.57 108	77.67 366	99.39 239	95.17 180	95.81 388	96.81 377

Patchmtry		95.03 248	94.59 263	96.33 224	94.83 398	90.82 254	96.38 169	97.20 295	96.59 112	97.49 186	98.57 108	77.67 366	99.38 242	92.95 266	99.62 97	98.80 227

tpmrst		90.31 354	90.61 352	89.41 397	94.06 410	72.37 428	95.06 270	93.69 363	88.01 355	92.32 384	96.86 279	77.45 368	98.82 336	91.04 296	87.01 422	97.04 365

sam_mvs												77.38 369

patchmatchnet-post											96.84 281	77.36 370	99.42 224

Patchmatch-RL test		94.66 266	94.49 267	95.19 278	98.54 176	88.91 289	92.57 356	98.74 162	91.46 307	98.32 118	97.75 212	77.31 371	98.81 338	96.06 121	99.61 103	97.85 328

tpmvs		90.79 352	90.87 345	90.57 391	92.75 422	76.30 417	95.79 218	93.64 367	91.04 314	91.91 387	96.26 314	77.19 372	98.86 335	89.38 338	89.85 418	96.56 384

test_post											10.87 432	76.83 373	99.07 311

Patchmatch-test		93.60 303	93.25 300	94.63 306	96.14 361	87.47 322	96.04 196	94.50 357	93.57 247	96.47 257	96.97 272	76.50 374	98.61 360	90.67 315	98.41 304	97.81 332

MDTV_nov1_ep13			91.28 337		94.31 403	73.51 426	94.80 280	93.16 371	86.75 370	93.45 360	97.40 237	76.37 375	98.55 366	88.85 344	96.43 377

EMVS		89.06 370	89.22 362	88.61 401	93.00 419	77.34 413	82.91 424	90.92 397	94.64 213	92.63 380	91.81 399	76.30 376	97.02 406	83.83 394	96.90 362	91.48 421

test_post1							94.98 275				10.37 433	76.21 377	99.04 315	89.47 336

GA-MVS		92.83 319	92.15 324	94.87 296	96.97 332	87.27 327	90.03 404	96.12 323	91.83 298	94.05 339	94.57 358	76.01 378	98.97 327	92.46 272	97.34 354	98.36 279

BP-MVS1		95.36 230	94.86 245	96.89 187	98.35 197	91.72 237	96.76 147	95.21 347	96.48 121	96.23 272	97.19 256	75.97 379	99.80 48	97.91 48	99.60 109	99.15 162

PatchT		93.75 297	93.57 295	94.29 324	95.05 394	87.32 326	96.05 195	92.98 373	97.54 75	94.25 331	98.72 90	75.79 380	99.24 284	95.92 133	95.81 388	96.32 389

E-PMN		89.52 367	89.78 359	88.73 400	93.14 417	77.61 411	83.26 423	92.02 385	94.82 207	93.71 349	93.11 375	75.31 381	96.81 409	85.81 376	96.81 367	91.77 420

DeepMVS_CX				77.17 409	90.94 426	85.28 354		74.08 432	52.51 428	80.87 428	88.03 420	75.25 382	70.63 430	59.23 428	84.94 424	75.62 424

GDP-MVS		95.39 229	94.89 242	96.90 186	98.26 207	91.91 232	96.48 164	99.28 35	95.06 198	96.54 255	97.12 261	74.83 383	99.82 36	97.19 79	99.27 212	98.96 198

AUN-MVS		93.95 295	92.69 314	97.74 113	97.80 263	95.38 107	95.57 235	95.46 342	91.26 311	92.64 379	96.10 324	74.67 384	99.55 186	93.72 247	96.97 359	98.30 285

CHOSEN 280x420		89.98 359	89.19 365	92.37 373	95.60 382	81.13 395	86.22 418	97.09 301	81.44 405	87.44 418	93.15 374	73.99 385	99.47 209	88.69 347	99.07 240	96.52 385

thres200		91.00 350	90.42 354	92.77 364	97.47 308	83.98 374	94.01 313	91.18 396	95.12 195	95.44 305	91.21 405	73.93 386	99.31 265	77.76 415	97.63 343	95.01 406

test-LLR		89.97 360	89.90 358	90.16 392	94.24 406	74.98 421	89.89 406	89.06 411	92.02 293	89.97 404	90.77 409	73.92 387	98.57 363	91.88 280	97.36 352	96.92 368

test0.0.03 1		90.11 355	89.21 363	92.83 362	93.89 412	86.87 334	91.74 377	88.74 414	92.02 293	94.71 322	91.14 406	73.92 387	94.48 422	83.75 396	92.94 409	97.16 362

tpm cat1		88.01 381	87.33 381	90.05 396	94.48 402	76.28 418	94.47 292	94.35 359	73.84 425	89.26 410	95.61 340	73.64 389	98.30 385	84.13 391	86.20 423	95.57 402

tfpn200view9		91.55 342	91.00 342	93.21 349	98.02 235	84.35 369	95.70 221	90.79 399	96.26 129	95.90 289	92.13 396	73.62 390	99.42 224	78.85 412	97.74 332	95.85 395

thres400		91.68 341	91.00 342	93.71 336	98.02 235	84.35 369	95.70 221	90.79 399	96.26 129	95.90 289	92.13 396	73.62 390	99.42 224	78.85 412	97.74 332	97.36 356

test_method		66.88 394	66.13 397	69.11 410	62.68 435	25.73 438	49.76 426	96.04 325	14.32 430	64.27 430	91.69 401	73.45 392	88.05 427	76.06 417	66.94 427	93.54 413

thres100view900		91.76 340	91.26 340	93.26 345	98.21 212	84.50 366	96.39 166	90.39 403	96.87 101	96.33 263	93.08 379	73.44 393	99.42 224	78.85 412	97.74 332	95.85 395

thres600view7		92.03 335	91.43 333	93.82 332	98.19 215	84.61 365	96.27 176	90.39 403	96.81 103	96.37 262	93.11 375	73.44 393	99.49 204	80.32 407	97.95 322	97.36 356

MVSTER		94.21 283	93.93 290	95.05 285	95.83 372	86.46 338	95.18 262	97.65 280	92.41 288	97.94 162	98.00 189	72.39 395	99.58 175	96.36 109	99.56 121	99.12 173

JIA-IIPM		91.79 339	90.69 350	95.11 281	93.80 413	90.98 251	94.16 305	91.78 388	96.38 123	90.30 400	99.30 29	72.02 396	98.90 330	88.28 353	90.17 417	95.45 403

tpm		91.08 349	90.85 346	91.75 381	95.33 389	78.09 407	95.03 273	91.27 395	88.75 344	93.53 357	97.40 237	71.24 397	99.30 268	91.25 293	93.87 407	97.87 327

baseline2		89.65 366	88.44 372	93.25 346	95.62 381	82.71 380	93.82 322	85.94 421	88.89 343	87.35 419	92.54 390	71.23 398	99.33 259	86.01 374	94.60 404	97.72 340

CostFormer		89.75 363	89.25 361	91.26 387	94.69 400	78.00 409	95.32 254	91.98 386	81.50 404	90.55 396	96.96 274	71.06 399	98.89 331	88.59 349	92.63 411	96.87 371

FPMVS		89.92 361	88.63 369	93.82 332	98.37 195	96.94 49	91.58 380	93.34 370	88.00 356	90.32 399	97.10 263	70.87 400	91.13 426	71.91 423	96.16 386	93.39 416

EPMVS		89.26 368	88.55 370	91.39 385	92.36 423	79.11 404	95.65 228	79.86 427	88.60 347	93.12 367	96.53 300	70.73 401	98.10 392	90.75 308	89.32 419	96.98 366

FE-MVS		92.95 317	92.22 322	95.11 281	97.21 324	88.33 301	98.54 23	93.66 366	89.91 330	96.21 274	98.14 166	70.33 402	99.50 199	87.79 357	98.24 311	97.51 351

tmp_tt		57.23 396	62.50 399	41.44 413	34.77 436	49.21 437	83.93 421	60.22 435	15.31 429	71.11 429	79.37 426	70.09 403	44.86 432	64.76 425	82.93 426	30.25 428

ET-MVSNet_ETH3D		91.12 346	89.67 360	95.47 269	96.41 348	89.15 284	91.54 381	90.23 407	89.07 339	86.78 421	92.84 385	69.39 404	99.44 220	94.16 229	96.61 374	97.82 330

dp		88.08 380	88.05 374	88.16 405	92.85 420	68.81 432	94.17 304	92.88 374	85.47 381	91.38 392	96.14 321	68.87 405	98.81 338	86.88 371	83.80 425	96.87 371

tpm2		88.47 375	87.69 379	90.79 389	94.98 395	77.34 413	95.09 266	91.83 387	77.51 420	89.40 409	96.41 307	67.83 406	98.73 345	83.58 397	92.60 412	96.29 390

pmmvs3		90.00 358	88.90 368	93.32 343	94.20 408	85.34 350	91.25 389	92.56 381	78.59 415	93.82 344	95.17 347	67.36 407	98.69 351	89.08 342	98.03 319	95.92 393

thisisatest0515		90.43 353	89.18 366	94.17 328	97.07 330	85.44 349	89.75 410	87.58 416	88.28 352	93.69 351	91.72 400	65.27 408	99.58 175	90.59 316	98.67 282	97.50 353

tttt0517		93.31 310	92.56 318	95.57 262	98.71 151	87.86 313	97.44 107	87.17 418	95.79 162	97.47 190	96.84 281	64.12 409	99.81 41	96.20 118	99.32 203	99.02 191

thisisatest0530		92.71 321	91.76 330	95.56 264	98.42 192	88.23 302	96.03 197	87.35 417	94.04 235	96.56 252	95.47 343	64.03 410	99.77 63	94.78 205	99.11 234	98.68 246

FMVSNet5		93.39 308	92.35 319	96.50 213	95.83 372	90.81 256	97.31 112	98.27 225	92.74 281	96.27 269	98.28 148	62.23 411	99.67 139	90.86 302	99.36 188	99.03 188

UWE-MVS-28		83.78 392	82.36 395	88.03 406	90.72 427	71.58 429	93.64 328	77.87 428	87.62 359	85.91 422	92.89 383	59.94 412	95.99 417	56.06 429	96.56 376	96.52 385

WBMVS		91.11 347	90.72 349	92.26 375	95.99 364	77.98 410	91.47 382	95.90 330	91.63 300	95.90 289	96.45 305	59.60 413	99.46 212	89.97 329	99.59 112	99.33 126

UBG		88.29 378	87.17 382	91.63 382	96.08 362	78.21 406	91.61 378	91.50 391	89.67 333	89.71 407	88.97 418	59.01 414	98.91 329	81.28 404	96.72 371	97.77 335

IB-MVS	85.98 20	88.63 374	86.95 386	93.68 337	95.12 393	84.82 364	90.85 396	90.17 408	87.55 360	88.48 414	91.34 404	58.01 415	99.59 172	87.24 369	93.80 408	96.63 383
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
MVStest1		91.89 337	91.45 332	93.21 349	89.01 429	84.87 361	95.82 217	95.05 350	91.50 305	98.75 76	99.19 39	57.56 416	95.11 418	97.78 56	98.37 305	99.64 39

testing91		89.67 365	88.55 370	93.04 353	95.90 367	81.80 389	92.71 354	93.71 362	93.71 242	90.18 401	90.15 413	57.11 417	99.22 288	87.17 370	96.32 381	98.12 302

gg-mvs-nofinetune		88.28 379	86.96 385	92.23 376	92.84 421	84.44 368	98.19 52	74.60 430	99.08 14	87.01 420	99.47 13	56.93 418	98.23 388	78.91 411	95.61 394	94.01 412

KD-MVS_2432*1600		88.93 371	87.74 376	92.49 369	88.04 430	81.99 386	89.63 411	95.62 336	91.35 309	95.06 313	93.11 375	56.58 419	98.63 358	85.19 384	95.07 397	96.85 373

miper_refine_blended		88.93 371	87.74 376	92.49 369	88.04 430	81.99 386	89.63 411	95.62 336	91.35 309	95.06 313	93.11 375	56.58 419	98.63 358	85.19 384	95.07 397	96.85 373

GG-mvs-BLEND				90.60 390	91.00 425	84.21 372	98.23 46	72.63 433		82.76 424	84.11 425	56.14 421	96.79 410	72.20 422	92.09 414	90.78 422

myMVS_eth3d28		88.32 377	87.73 378	90.11 395	96.42 347	74.96 424	92.21 368	92.37 382	93.56 248	90.14 402	89.61 416	56.13 422	98.05 394	81.84 400	97.26 357	97.33 359

TESTMET0.1,1		87.20 388	86.57 388	89.07 399	93.62 415	72.84 427	89.89 406	87.01 419	85.46 382	89.12 411	90.20 412	56.00 423	97.72 399	90.91 301	96.92 360	96.64 381

testing3-2		90.09 356	90.38 355	89.24 398	98.07 232	69.88 431	95.12 263	90.71 402	96.65 108	93.60 355	94.03 368	55.81 424	99.33 259	90.69 314	98.71 278	98.51 261

reproduce_monomvs		92.05 334	92.26 321	91.43 384	95.42 387	75.72 420	95.68 224	97.05 304	94.47 219	97.95 161	98.35 134	55.58 425	99.05 313	96.36 109	99.44 165	99.51 69

testing99		89.21 369	88.04 375	92.70 366	95.78 376	81.00 396	92.65 355	92.03 384	93.20 262	89.90 406	90.08 415	55.25 426	99.14 298	87.54 363	95.95 387	97.97 319

UWE-MVS		87.57 385	86.72 387	90.13 394	95.21 390	73.56 425	91.94 374	83.78 425	88.73 346	93.00 369	92.87 384	55.22 427	99.25 280	81.74 401	97.96 321	97.59 348

test2506		89.86 362	89.16 367	91.97 379	98.95 116	76.83 416	98.54 23	61.07 434	96.20 132	97.07 216	99.16 47	55.19 428	99.69 125	96.43 106	99.83 45	99.38 117

testing11		88.93 371	87.63 380	92.80 363	95.87 369	81.49 391	92.48 359	91.54 390	91.62 301	88.27 415	90.24 411	55.12 429	99.11 305	87.30 368	96.28 383	97.81 332

test-mter		87.92 382	87.17 382	90.16 392	94.24 406	74.98 421	89.89 406	89.06 411	86.44 372	89.97 404	90.77 409	54.96 430	98.57 363	91.88 280	97.36 352	96.92 368

ETVMVS		87.62 384	85.75 391	93.22 348	96.15 360	83.26 377	92.94 346	90.37 405	91.39 308	90.37 398	88.45 419	51.93 431	98.64 357	73.76 419	96.38 379	97.75 336

testing222		87.35 386	85.50 393	92.93 360	95.79 375	82.83 379	92.40 365	90.10 409	92.80 280	88.87 412	89.02 417	48.34 432	98.70 349	75.40 418	96.74 369	97.27 361

myMVS_eth3d		87.16 389	85.61 392	91.82 380	95.19 391	79.32 402	92.46 360	91.35 392	90.67 319	91.76 389	87.61 421	41.96 433	98.50 370	82.66 398	96.84 364	97.65 343

testing3		89.72 364	88.26 373	94.10 329	97.66 288	84.30 371	94.80 280	88.25 415	94.66 211	95.07 312	92.51 391	41.15 434	99.43 222	91.81 283	98.44 302	98.55 257

dongtai		63.43 395	63.37 398	63.60 411	83.91 433	53.17 435	85.14 419	43.40 437	77.91 419	80.96 427	79.17 427	36.36 435	77.10 429	37.88 430	45.63 429	60.54 426

kuosan		54.81 397	54.94 400	54.42 412	74.43 434	50.03 436	84.98 420	44.27 436	61.80 427	62.49 431	70.43 428	35.16 436	58.04 431	19.30 431	41.61 430	55.19 427

test123		12.59 399	15.49 402	3.87 414	6.07 437	2.55 439	90.75 398	2.59 439	2.52 432	5.20 434	13.02 431	4.96 437	1.85 434	5.20 432	9.09 431	7.23 429

testmvs		12.33 400	15.23 403	3.64 415	5.77 438	2.23 440	88.99 413	3.62 438	2.30 433	5.29 433	13.09 430	4.52 438	1.95 433	5.16 433	8.32 432	6.75 430

mmdepth		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

monomultidepth		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

test_blank		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uanet_test		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

DCPMVS		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

sosnet-low-res		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

sosnet		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uncertanet		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

Regformer		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

ab-mvs-re		7.91 402	10.55 405	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	94.94 352	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uanet		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

WAC-MVS						79.32 402								85.41 382

FOURS1					99.59 17	98.20 8	99.03 8	99.25 38	98.96 22	98.87 63

MSC_two_6792asdad				98.22 77	97.75 275	95.34 112		98.16 244					99.75 74	95.87 137	99.51 145	99.57 50

No_MVS				98.22 77	97.75 275	95.34 112		98.16 244					99.75 74	95.87 137	99.51 145	99.57 50

eth-test2					0.00 439

eth-test					0.00 439

IU-MVS					99.22 66	95.40 105		98.14 247	85.77 379	98.36 110				95.23 177	99.51 145	99.49 80

save fliter					98.48 186	94.71 133	94.53 291	98.41 209	95.02 201

test_0728_SECOND				98.25 75	99.23 63	95.49 103	96.74 149	98.89 115					99.75 74	95.48 160	99.52 140	99.53 62

GSMVS																98.06 310

test_part2					99.03 108	96.07 78				98.08 145

MTGPA								98.73 163

MTMP							96.55 160	74.60 430

gm-plane-assit					91.79 424	71.40 430			81.67 402		90.11 414		98.99 321	84.86 388

test9_res														91.29 290	98.89 259	99.00 192

agg_prior2														90.34 324	98.90 256	99.10 180

agg_prior					97.80 263	94.96 128		98.36 216		93.49 358			99.53 191

test_prior4						95.38 107	93.61 331

test_prior				97.46 141	97.79 268	94.26 157		98.42 208					99.34 257			98.79 229

旧先验2							93.35 338		77.95 418	95.77 296			98.67 355	90.74 311

新几何2							93.43 334

无先验							93.20 342	97.91 261	80.78 407				99.40 235	87.71 358		97.94 322

原ACMM2							92.82 348

testdata2													99.46 212	87.84 356

testdata1							92.77 349		93.78 240

plane_prior7					98.70 153	94.67 136

plane_prior5								98.75 160					99.46 212	92.59 269	99.20 220	99.28 139

plane_prior4											96.77 287

plane_prior3						94.51 143			95.29 188	96.16 277

plane_prior2							96.50 162		96.36 125

plane_prior1					98.49 184

plane_prior						94.29 153	95.42 241		94.31 225						98.93 254

n2								0.00 440

nn								0.00 440

door-mid								98.17 240

test11								98.08 252

door								97.81 270

HQP5-MVS						92.47 213

HQP-NCC					97.85 250		94.26 296		93.18 264	92.86 372

ACMP_Plane					97.85 250		94.26 296		93.18 264	92.86 372

BP-MVS														90.51 319

HQP4-MVS										92.87 371			99.23 286			99.06 185

HQP3-MVS								98.43 205							98.74 274

NP-MVS					98.14 227	93.72 175					95.08 348

ACMMP++_ref															99.52 140

ACMMP++															99.55 127

High-resolution multi-view benchmark