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 5

pmmvs6		99.07 4	99.24 4	98.56 52	99.81 2	96.38 66	98.87 10	99.30 29	99.01 20	99.63 12	99.66 4	99.27 2	99.68 129	97.75 54	99.89 23	99.62 36

UniMVSNet_ETH3D		99.12 3	99.28 3	98.65 46	99.77 5	96.34 69	99.18 6	99.20 38	99.67 2	99.73 4	99.65 6	99.15 3	99.86 26	97.22 71	99.92 14	99.77 13

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	95.44 175	99.64 11	99.52 9	98.96 4	99.74 83	99.38 3	99.86 28	99.81 9

XVG-OURS-SEG-HR		97.38 121	97.07 138	98.30 70	99.01 109	97.41 38	94.66 282	99.02 82	95.20 184	98.15 133	97.52 225	98.83 5	98.43 369	94.87 194	96.41 370	99.07 178

ACMH	93.61 9	98.44 29	98.76 14	97.51 130	99.43 37	93.54 182	98.23 46	99.05 72	97.40 84	99.37 24	99.08 55	98.79 6	99.47 204	97.74 55	99.71 73	99.50 67
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 35	96.23 128	99.71 5	99.48 12	98.77 7	99.93 4	98.89 17	99.95 5	99.84 7

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	95.05 193	99.60 15	99.34 26	98.68 8	99.72 95	99.21 7	99.85 36	99.76 18

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 17	99.02 19	99.62 13	99.36 23	98.53 9	99.52 189	98.58 28	99.95 5	99.66 30
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 35	97.99 98	98.94 118	94.60 140	96.00 199	99.64 15	94.99 196	99.43 20	99.18 42	98.51 10	99.71 109	99.13 10	99.84 38	99.67 28

TransMVSNet (Re)		98.38 32	98.67 19	97.51 130	99.51 28	93.39 189	98.20 51	98.87 120	98.23 47	99.48 17	99.27 31	98.47 11	99.55 181	96.52 98	99.53 130	99.60 37

pm-mvs1		98.47 28	98.67 19	97.86 105	99.52 27	94.58 141	98.28 42	99.00 93	97.57 72	99.27 30	99.22 35	98.32 12	99.50 194	97.09 79	99.75 64	99.50 67

jajsoiax		98.77 10	98.79 13	98.74 38	99.66 12	96.48 64	98.45 31	99.12 52	95.83 155	99.67 8	99.37 21	98.25 13	99.92 6	98.77 20	99.94 8	99.82 8

sd_testset		97.97 57	98.12 47	97.51 130	99.41 40	93.44 185	97.96 64	98.25 223	98.58 32	98.78 66	99.39 18	98.21 14	99.56 177	92.65 262	99.86 28	99.52 60

ACMH+	93.58 10	98.23 41	98.31 39	97.98 99	99.39 44	95.22 120	97.55 99	99.20 38	98.21 48	99.25 32	98.51 112	98.21 14	99.40 230	94.79 198	99.72 70	99.32 122

HPM-MVS_fast		98.32 35	98.13 46	98.88 27	99.54 25	97.48 34	98.35 35	99.03 80	95.88 151	97.88 163	98.22 156	98.15 16	99.74 83	96.50 99	99.62 92	99.42 102

wuyk23d		93.25 308	95.20 221	87.40 399	96.07 356	95.38 107	97.04 129	94.97 346	95.33 179	99.70 7	98.11 168	98.14 17	91.94 417	77.76 408	99.68 81	74.89 417

ACMM	93.33 11	98.05 53	97.79 79	98.85 28	99.15 83	97.55 30	96.68 156	98.83 137	95.21 183	98.36 106	98.13 164	98.13 18	99.62 158	96.04 119	99.54 126	99.39 110
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HPM-MVS		98.11 47	97.83 75	98.92 25	99.42 39	97.46 35	98.57 20	99.05 72	95.43 176	97.41 189	97.50 227	97.98 19	99.79 49	95.58 149	99.57 113	99.50 67
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
testgi		96.07 191	96.50 176	94.80 296	99.26 57	87.69 315	95.96 205	98.58 188	95.08 190	98.02 149	96.25 310	97.92 20	97.60 394	88.68 342	98.74 269	99.11 171

LPG-MVS_test		97.94 66	97.67 91	98.74 38	99.15 83	97.02 46	97.09 126	99.02 82	95.15 187	98.34 110	98.23 153	97.91 21	99.70 117	94.41 213	99.73 66	99.50 67

LGP-MVS_train				98.74 38	99.15 83	97.02 46		99.02 82	95.15 187	98.34 110	98.23 153	97.91 21	99.70 117	94.41 213	99.73 66	99.50 67

SED-MVS		97.94 66	97.90 65	98.07 88	99.22 66	95.35 110	96.79 145	98.83 137	96.11 134	99.08 40	98.24 151	97.87 23	99.72 95	95.44 159	99.51 140	99.14 161

test_241102_ONE					99.22 66	95.35 110		98.83 137	96.04 139	99.08 40	98.13 164	97.87 23	99.33 254

SDMVSNet		97.97 57	98.26 45	97.11 166	99.41 40	92.21 218	96.92 135	98.60 184	98.58 32	98.78 66	99.39 18	97.80 25	99.62 158	94.98 192	99.86 28	99.52 60

testf1		98.57 18	98.45 32	98.93 22	99.79 3	98.78 3	97.69 87	99.42 24	97.69 68	98.92 54	98.77 82	97.80 25	99.25 274	96.27 110	99.69 77	98.76 229

APD_test2		98.57 18	98.45 32	98.93 22	99.79 3	98.78 3	97.69 87	99.42 24	97.69 68	98.92 54	98.77 82	97.80 25	99.25 274	96.27 110	99.69 77	98.76 229

SD-MVS		97.37 123	97.70 86	96.35 221	98.14 222	95.13 124	96.54 161	98.92 108	95.94 146	99.19 35	98.08 170	97.74 28	95.06 411	95.24 171	99.54 126	98.87 215
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 85	97.70 86	98.16 81	98.78 139	95.72 89	96.23 182	99.02 82	93.92 232	98.62 78	98.99 61	97.69 29	99.62 158	96.18 114	99.87 26	99.15 157
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 64	98.31 41	99.02 44	98.74 85	97.68 30	99.61 165	97.77 53	99.85 36	99.70 26

MGCFI-Net		97.20 132	97.23 128	97.08 171	97.68 277	93.71 175	97.79 77	99.09 61	97.40 84	96.59 244	93.96 363	97.67 31	99.35 249	96.43 102	98.50 292	98.17 294

ANet_high		98.31 36	98.94 6	96.41 219	99.33 51	89.64 271	97.92 69	99.56 19	99.27 8	99.66 10	99.50 11	97.67 31	99.83 34	97.55 62	99.98 2	99.77 13

test_fmvsmvis_n_1920		98.08 49	98.47 29	96.93 181	99.03 107	93.29 191	96.32 174	99.65 12	95.59 166	99.71 5	99.01 58	97.66 33	99.60 167	99.44 2	99.83 42	97.90 318

casdiffmvs_mvg		97.83 82	98.11 48	97.00 178	98.57 166	92.10 226	95.97 203	99.18 41	97.67 71	99.00 47	98.48 117	97.64 34	99.50 194	96.96 86	99.54 126	99.40 105
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		97.23 130	97.21 130	97.30 153	97.65 284	94.39 147	97.84 74	99.05 72	97.42 79	96.68 236	93.85 365	97.63 35	99.33 254	96.29 108	98.47 293	98.18 292

canonicalmvs		97.23 130	97.21 130	97.30 153	97.65 284	94.39 147	97.84 74	99.05 72	97.42 79	96.68 236	93.85 365	97.63 35	99.33 254	96.29 108	98.47 293	98.18 292

GeoE		97.75 91	97.70 86	97.89 103	98.88 126	94.53 142	97.10 125	98.98 99	95.75 159	97.62 175	97.59 220	97.61 37	99.77 63	96.34 107	99.44 160	99.36 118

TranMVSNet+NR-MVSNet		98.33 33	98.30 41	98.43 60	99.07 98	95.87 85	96.73 153	99.05 72	98.67 28	98.84 61	98.45 118	97.58 38	99.88 21	96.45 101	99.86 28	99.54 54

cdsmvs_eth3d_5k		24.22 390	32.30 393	0.00 408	0.00 431	0.00 433	0.00 419	98.10 246	0.00 426	0.00 427	95.06 345	97.54 39	0.00 427	0.00 426	0.00 425	0.00 423

ACMP	92.54 13	97.47 114	97.10 135	98.55 53	99.04 106	96.70 55	96.24 181	98.89 111	93.71 236	97.97 154	97.75 208	97.44 40	99.63 153	93.22 255	99.70 76	99.32 122
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 82	96.50 115	99.32 27	99.44 16	97.43 41	99.92 6	98.73 22	99.95 5	99.86 4

TDRefinement		98.90 6	98.86 9	99.02 10	99.54 25	98.06 9	99.34 5	99.44 22	98.85 25	99.00 47	99.20 37	97.42 42	99.59 168	97.21 72	99.76 57	99.40 105

anonymousdsp		98.72 15	98.63 21	98.99 14	99.62 15	97.29 41	98.65 19	99.19 40	95.62 164	99.35 26	99.37 21	97.38 43	99.90 16	98.59 27	99.91 17	99.77 13

PS-CasMVS		98.73 12	98.85 11	98.39 63	99.55 22	95.47 104	98.49 28	99.13 51	99.22 10	99.22 34	98.96 65	97.35 44	99.92 6	97.79 51	99.93 11	99.79 11

COLMAP_ROB	94.48 6	98.25 40	98.11 48	98.64 47	99.21 73	97.35 39	97.96 64	99.16 43	98.34 40	98.78 66	98.52 110	97.32 45	99.45 212	94.08 227	99.67 83	99.13 163
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 96	97.79 79	97.40 147	99.06 100	93.52 183	95.96 205	98.97 102	94.55 212	98.82 63	98.76 84	97.31 46	99.29 266	97.20 74	99.44 160	99.38 112

XXY-MVS		97.54 109	97.70 86	97.07 172	99.46 34	92.21 218	97.22 118	99.00 93	94.93 199	98.58 83	98.92 69	97.31 46	99.41 228	94.44 211	99.43 169	99.59 38

reproduce-ours		98.48 26	98.27 43	99.12 5	98.99 110	98.02 13	96.81 141	99.02 82	98.29 44	98.97 51	98.61 100	97.27 48	99.82 36	96.86 90	99.61 98	99.51 64

our_new_method		98.48 26	98.27 43	99.12 5	98.99 110	98.02 13	96.81 141	99.02 82	98.29 44	98.97 51	98.61 100	97.27 48	99.82 36	96.86 90	99.61 98	99.51 64

PEN-MVS		98.75 11	98.85 11	98.44 59	99.58 18	95.67 93	98.45 31	99.15 47	99.33 6	99.30 28	99.00 59	97.27 48	99.92 6	97.64 60	99.92 14	99.75 20

DTE-MVSNet		98.79 9	98.86 9	98.59 50	99.55 22	96.12 76	98.48 30	99.10 56	99.36 5	99.29 29	99.06 56	97.27 48	99.93 4	97.71 56	99.91 17	99.70 26

ZNCC-MVS		97.92 70	97.62 100	98.83 29	99.32 53	97.24 43	97.45 106	98.84 131	95.76 157	96.93 222	97.43 231	97.26 52	99.79 49	96.06 116	99.53 130	99.45 90

MP-MVS-pluss		97.69 96	97.36 119	98.70 42	99.50 31	96.84 51	95.38 243	98.99 96	92.45 280	98.11 136	98.31 135	97.25 53	99.77 63	96.60 95	99.62 92	99.48 81
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		97.89 76	97.63 98	98.67 44	99.35 49	96.84 51	96.36 171	98.79 147	95.07 191	97.88 163	98.35 130	97.24 54	99.72 95	96.05 118	99.58 110	99.45 90

Effi-MVS+		96.19 187	96.01 195	96.71 199	97.43 304	92.19 222	96.12 190	99.10 56	95.45 173	93.33 358	94.71 352	97.23 55	99.56 177	93.21 256	97.54 339	98.37 268

tt0805		97.44 116	97.56 106	97.11 166	99.55 22	96.36 67	98.66 18	95.66 329	98.31 41	97.09 211	95.45 339	97.17 56	98.50 364	98.67 25	97.45 345	96.48 379

PGM-MVS		97.88 77	97.52 110	98.96 17	99.20 75	97.62 25	97.09 126	99.06 68	95.45 173	97.55 177	97.94 190	97.11 57	99.78 53	94.77 201	99.46 156	99.48 81

test_0728_THIRD									96.62 106	98.40 100	98.28 144	97.10 58	99.71 109	95.70 137	99.62 92	99.58 39

APD-MVS_3200maxsize		98.13 46	97.90 65	98.79 33	98.79 136	97.31 40	97.55 99	98.92 108	97.72 65	98.25 121	98.13 164	97.10 58	99.75 74	95.44 159	99.24 213	99.32 122

OPM-MVS		97.54 109	97.25 126	98.41 61	99.11 92	96.61 60	95.24 255	98.46 197	94.58 211	98.10 138	98.07 172	97.09 60	99.39 234	95.16 177	99.44 160	99.21 147
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HFP-MVS		97.94 66	97.64 96	98.83 29	99.15 83	97.50 33	97.59 96	98.84 131	96.05 137	97.49 182	97.54 223	97.07 61	99.70 117	95.61 146	99.46 156	99.30 127

DVP-MVS		97.78 89	97.65 93	98.16 81	99.24 61	95.51 99	96.74 149	98.23 226	95.92 148	98.40 100	98.28 144	97.06 62	99.71 109	95.48 155	99.52 135	99.26 139
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	98.89 111	95.92 148	98.64 76	98.31 135	97.06 62

test_fmvsm_n_1920		98.08 49	98.29 42	97.43 143	98.88 126	93.95 166	96.17 188	99.57 17	95.66 161	99.52 16	98.71 89	97.04 64	99.64 149	99.21 7	99.87 26	98.69 238

casdiffmvs		97.50 111	97.81 77	96.56 209	98.51 175	91.04 249	95.83 213	99.09 61	97.23 91	98.33 113	98.30 139	97.03 65	99.37 242	96.58 97	99.38 179	99.28 134
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SteuartSystems-ACMMP		98.02 55	97.76 83	98.79 33	99.43 37	97.21 45	97.15 121	98.90 110	96.58 110	98.08 141	97.87 196	97.02 66	99.76 68	95.25 170	99.59 107	99.40 105
Skip Steuart: Steuart Systems R&D Blog.
PC_three_1452									87.24 354	98.37 103	97.44 230	97.00 67	96.78 404	92.01 271	99.25 210	99.21 147

EC-MVSNet		97.90 75	97.94 64	97.79 109	98.66 153	95.14 123	98.31 39	99.66 11	97.57 72	95.95 279	97.01 266	96.99 68	99.82 36	97.66 59	99.64 88	98.39 266

DVP-MVS++		97.96 59	97.90 65	98.12 86	97.75 269	95.40 105	99.03 8	98.89 111	96.62 106	98.62 78	98.30 139	96.97 69	99.75 74	95.70 137	99.25 210	99.21 147

OPU-MVS				97.64 121	98.01 231	95.27 115	96.79 145				97.35 242	96.97 69	98.51 363	91.21 289	99.25 210	99.14 161

RE-MVS-def			97.88 70		98.81 132	98.05 10	97.55 99	98.86 123	97.77 60	98.20 125	98.07 172	96.94 71		95.49 151	99.20 215	99.26 139

APDe-MVS		98.14 43	98.03 55	98.47 58	98.72 144	96.04 79	98.07 58	99.10 56	95.96 144	98.59 82	98.69 92	96.94 71	99.81 41	96.64 93	99.58 110	99.57 46
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 38	99.15 4	99.06 100	98.04 12	97.04 129	99.09 61	98.42 37	99.03 43	98.71 89	96.93 73	99.83 34	97.09 79	99.63 90	99.56 50

test_one_0601					99.05 105	95.50 102		98.87 120	97.21 93	98.03 148	98.30 139	96.93 73

GST-MVS		97.82 85	97.49 114	98.81 31	99.23 63	97.25 42	97.16 120	98.79 147	95.96 144	97.53 178	97.40 233	96.93 73	99.77 63	95.04 186	99.35 188	99.42 102

test_241102_TWO								98.83 137	96.11 134	98.62 78	98.24 151	96.92 76	99.72 95	95.44 159	99.49 147	99.49 75

LCM-MVSNet-Re		97.33 126	97.33 121	97.32 152	98.13 225	93.79 172	96.99 132	99.65 12	96.74 104	99.47 18	98.93 68	96.91 77	99.84 32	90.11 319	99.06 238	98.32 275

VPA-MVSNet		98.27 38	98.46 30	97.70 116	99.06 100	93.80 171	97.76 81	99.00 93	98.40 38	99.07 42	98.98 62	96.89 78	99.75 74	97.19 75	99.79 52	99.55 53

ACMMP		98.05 53	97.75 85	98.93 22	99.23 63	97.60 26	98.09 57	98.96 103	95.75 159	97.91 160	98.06 177	96.89 78	99.76 68	95.32 167	99.57 113	99.43 101
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 48	98.01 57	98.32 67	98.45 184	96.69 56	98.52 26	99.69 8	98.07 53	96.07 275	97.19 252	96.88 80	99.86 26	97.50 64	99.73 66	98.41 263

PMVS	89.60 17	96.71 165	96.97 144	95.95 240	99.51 28	97.81 20	97.42 110	97.49 283	97.93 56	95.95 279	98.58 103	96.88 80	96.91 401	89.59 328	99.36 183	93.12 409
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
region2R		97.92 70	97.59 103	98.92 25	99.22 66	97.55 30	97.60 94	98.84 131	96.00 142	97.22 195	97.62 218	96.87 82	99.76 68	95.48 155	99.43 169	99.46 86

CP-MVS		97.92 70	97.56 106	98.99 14	98.99 110	97.82 19	97.93 68	98.96 103	96.11 134	96.89 225	97.45 229	96.85 83	99.78 53	95.19 173	99.63 90	99.38 112

DPE-MVS		97.64 100	97.35 120	98.50 55	98.85 130	96.18 73	95.21 257	98.99 96	95.84 154	98.78 66	98.08 170	96.84 84	99.81 41	93.98 233	99.57 113	99.52 60
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_0402		97.84 81	97.97 61	97.47 139	99.19 77	94.07 161	96.71 154	98.73 159	98.66 29	98.56 84	98.41 123	96.84 84	99.69 124	94.82 196	99.81 47	98.64 242

SPE-MVS-test		97.91 73	97.84 72	98.14 84	98.52 173	96.03 81	98.38 34	99.67 9	98.11 51	95.50 299	96.92 272	96.81 86	99.87 24	96.87 89	99.76 57	98.51 256

ACMMPR		97.95 63	97.62 100	98.94 19	99.20 75	97.56 29	97.59 96	98.83 137	96.05 137	97.46 187	97.63 217	96.77 87	99.76 68	95.61 146	99.46 156	99.49 75

Vis-MVSNet		98.27 38	98.34 37	98.07 88	99.33 51	95.21 122	98.04 59	99.46 20	97.32 88	97.82 170	99.11 51	96.75 88	99.86 26	97.84 48	99.36 183	99.15 157
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
Fast-Effi-MVS+		95.49 217	95.07 228	96.75 197	97.67 281	92.82 200	94.22 297	98.60 184	91.61 295	93.42 356	92.90 376	96.73 89	99.70 117	92.60 263	97.89 320	97.74 331

baseline		97.44 116	97.78 82	96.43 216	98.52 173	90.75 256	96.84 138	99.03 80	96.51 114	97.86 167	98.02 181	96.67 90	99.36 245	97.09 79	99.47 153	99.19 151

SR-MVS		98.00 56	97.66 92	99.01 12	98.77 140	97.93 15	97.38 111	98.83 137	97.32 88	98.06 144	97.85 197	96.65 91	99.77 63	95.00 189	99.11 229	99.32 122

tfpnnormal		97.72 94	97.97 61	96.94 180	99.26 57	92.23 217	97.83 76	98.45 198	98.25 46	99.13 38	98.66 94	96.65 91	99.69 124	93.92 235	99.62 92	98.91 205

DeepPCF-MVS	94.58 5	96.90 148	96.43 178	98.31 69	97.48 298	97.23 44	92.56 351	98.60 184	92.84 272	98.54 85	97.40 233	96.64 93	98.78 334	94.40 215	99.41 176	98.93 201

MVS_111021_LR		96.82 156	96.55 170	97.62 122	98.27 200	95.34 112	93.81 319	98.33 216	94.59 210	96.56 247	96.63 290	96.61 94	98.73 339	94.80 197	99.34 191	98.78 225

Gipuma		98.07 51	98.31 39	97.36 149	99.76 7	96.28 72	98.51 27	99.10 56	98.76 27	96.79 228	99.34 26	96.61 94	98.82 330	96.38 104	99.50 144	96.98 359
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
SR-MVS-dyc-post		98.14 43	97.84 72	99.02 10	98.81 132	98.05 10	97.55 99	98.86 123	97.77 60	98.20 125	98.07 172	96.60 96	99.76 68	95.49 151	99.20 215	99.26 139

MVS_111021_HR		96.73 162	96.54 172	97.27 155	98.35 192	93.66 179	93.42 329	98.36 212	94.74 202	96.58 245	96.76 284	96.54 97	98.99 315	94.87 194	99.27 207	99.15 157

SMA-MVS		97.48 113	97.11 134	98.60 49	98.83 131	96.67 57	96.74 149	98.73 159	91.61 295	98.48 92	98.36 129	96.53 98	99.68 129	95.17 175	99.54 126	99.45 90
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 50	99.08 14	99.42 21	99.23 34	96.53 98	99.91 14	99.27 5	99.93 11	99.73 22

mPP-MVS		97.91 73	97.53 109	99.04 8	99.22 66	97.87 18	97.74 84	98.78 151	96.04 139	97.10 206	97.73 211	96.53 98	99.78 53	95.16 177	99.50 144	99.46 86

XVS		97.96 59	97.63 98	98.94 19	99.15 83	97.66 23	97.77 79	98.83 137	97.42 79	96.32 259	97.64 216	96.49 101	99.72 95	95.66 142	99.37 180	99.45 90

X-MVStestdata		92.86 313	90.83 342	98.94 19	99.15 83	97.66 23	97.77 79	98.83 137	97.42 79	96.32 259	36.50 421	96.49 101	99.72 95	95.66 142	99.37 180	99.45 90

9.14			96.69 160		98.53 172		96.02 197	98.98 99	93.23 252	97.18 200	97.46 228	96.47 103	99.62 158	92.99 259	99.32 198

UA-Net		98.88 8	98.76 14	99.22 3	99.11 92	97.89 17	99.47 3	99.32 27	99.08 14	97.87 166	99.67 3	96.47 103	99.92 6	97.88 45	99.98 2	99.85 5

fmvsm_l_conf0.5_n		97.68 98	97.81 77	97.27 155	98.92 122	92.71 207	95.89 210	99.41 26	93.36 247	99.00 47	98.44 120	96.46 105	99.65 145	99.09 11	99.76 57	99.45 90

SF-MVS		97.60 104	97.39 117	98.22 77	98.93 120	95.69 91	97.05 128	99.10 56	95.32 180	97.83 169	97.88 195	96.44 106	99.72 95	94.59 210	99.39 178	99.25 143

fmvsm_s_conf0.1_n_a		97.80 87	98.01 57	97.18 161	99.17 79	92.51 210	96.57 159	99.15 47	93.68 239	98.89 57	99.30 29	96.42 107	99.37 242	99.03 13	99.83 42	99.66 30

xiu_mvs_v1_base_debu		95.62 212	95.96 199	94.60 304	98.01 231	88.42 293	93.99 309	98.21 227	92.98 266	95.91 281	94.53 355	96.39 108	99.72 95	95.43 162	98.19 306	95.64 391

xiu_mvs_v1_base		95.62 212	95.96 199	94.60 304	98.01 231	88.42 293	93.99 309	98.21 227	92.98 266	95.91 281	94.53 355	96.39 108	99.72 95	95.43 162	98.19 306	95.64 391

xiu_mvs_v1_base_debi		95.62 212	95.96 199	94.60 304	98.01 231	88.42 293	93.99 309	98.21 227	92.98 266	95.91 281	94.53 355	96.39 108	99.72 95	95.43 162	98.19 306	95.64 391

ETV-MVS		96.13 190	95.90 203	96.82 192	97.76 267	93.89 167	95.40 241	98.95 105	95.87 152	95.58 297	91.00 400	96.36 111	99.72 95	93.36 249	98.83 261	96.85 366

fmvsm_l_conf0.5_n_a		97.60 104	97.76 83	97.11 166	98.92 122	92.28 215	95.83 213	99.32 27	93.22 253	98.91 56	98.49 113	96.31 112	99.64 149	99.07 12	99.76 57	99.40 105

fmvsm_s_conf0.1_n		97.73 92	98.02 56	96.85 189	99.09 95	91.43 243	96.37 170	99.11 53	94.19 222	99.01 45	99.25 32	96.30 113	99.38 237	99.00 14	99.88 24	99.73 22

MP-MVS		97.64 100	97.18 132	99.00 13	99.32 53	97.77 21	97.49 105	98.73 159	96.27 125	95.59 296	97.75 208	96.30 113	99.78 53	93.70 243	99.48 151	99.45 90
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TinyColmap		96.00 196	96.34 182	94.96 287	97.90 242	87.91 308	94.13 304	98.49 195	94.41 215	98.16 131	97.76 205	96.29 115	98.68 348	90.52 312	99.42 172	98.30 279

Fast-Effi-MVS+-dtu		96.44 178	96.12 190	97.39 148	97.18 319	94.39 147	95.46 235	98.73 159	96.03 141	94.72 316	94.92 349	96.28 116	99.69 124	93.81 238	97.98 314	98.09 297

fmvsm_s_conf0.5_n_a		97.65 99	97.83 75	97.13 165	98.80 134	92.51 210	96.25 180	99.06 68	93.67 240	98.64 76	99.00 59	96.23 117	99.36 245	98.99 15	99.80 50	99.53 57

fmvsm_s_conf0.5_n		97.62 102	97.89 68	96.80 193	98.79 136	91.44 242	96.14 189	99.06 68	94.19 222	98.82 63	98.98 62	96.22 118	99.38 237	98.98 16	99.86 28	99.58 39

APD_test1		97.95 63	97.68 90	98.75 35	99.60 16	98.60 6	97.21 119	99.08 64	96.57 113	98.07 143	98.38 127	96.22 118	99.14 292	94.71 205	99.31 201	98.52 255

OMC-MVS		96.48 176	96.00 196	97.91 102	98.30 195	96.01 82	94.86 274	98.60 184	91.88 290	97.18 200	97.21 251	96.11 120	99.04 309	90.49 315	99.34 191	98.69 238

xiu_mvs_v2_base		94.22 276	94.63 254	92.99 352	97.32 314	84.84 359	92.12 363	97.84 263	91.96 288	94.17 329	93.43 367	96.07 121	99.71 109	91.27 286	97.48 342	94.42 401

CSCG		97.40 120	97.30 122	97.69 118	98.95 115	94.83 130	97.28 114	98.99 96	96.35 124	98.13 135	95.95 325	95.99 122	99.66 143	94.36 218	99.73 66	98.59 248

PHI-MVS		96.96 144	96.53 173	98.25 75	97.48 298	96.50 63	96.76 147	98.85 127	93.52 242	96.19 271	96.85 275	95.94 123	99.42 219	93.79 239	99.43 169	98.83 218

mamv4		99.05 5	98.91 8	99.46 2	98.94 118	99.62 2	97.98 63	99.70 7	99.49 3	99.78 2	99.22 35	95.92 124	99.95 3	99.31 4	99.83 42	98.83 218

TSAR-MVS + MP.		97.42 119	97.23 128	98.00 97	99.38 46	95.00 127	97.63 93	98.20 230	93.00 265	98.16 131	98.06 177	95.89 125	99.72 95	95.67 141	99.10 231	99.28 134
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		97.58 107	97.28 125	98.49 56	99.16 80	96.90 50	96.39 166	98.98 99	95.05 193	98.06 144	98.02 181	95.86 126	99.56 177	94.37 216	99.64 88	99.00 187

AllTest		97.20 132	96.92 149	98.06 90	99.08 96	96.16 74	97.14 123	99.16 43	94.35 217	97.78 171	98.07 172	95.84 127	99.12 296	91.41 283	99.42 172	98.91 205

TestCases				98.06 90	99.08 96	96.16 74		99.16 43	94.35 217	97.78 171	98.07 172	95.84 127	99.12 296	91.41 283	99.42 172	98.91 205

APD-MVS		97.00 139	96.53 173	98.41 61	98.55 169	96.31 70	96.32 174	98.77 152	92.96 270	97.44 188	97.58 222	95.84 127	99.74 83	91.96 272	99.35 188	99.19 151
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
pcd_1.5k_mvsjas		7.98 393	10.65 396	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	95.82 130	0.00 427	0.00 426	0.00 425	0.00 423

PS-MVSNAJss		98.53 24	98.63 21	98.21 80	99.68 11	94.82 131	98.10 56	99.21 36	96.91 99	99.75 3	99.45 15	95.82 130	99.92 6	98.80 19	99.96 4	99.89 3

PS-MVSNAJ		94.10 282	94.47 264	93.00 351	97.35 309	84.88 356	91.86 368	97.84 263	91.96 288	94.17 329	92.50 385	95.82 130	99.71 109	91.27 286	97.48 342	94.40 402

3Dnovator	96.53 2	97.61 103	97.64 96	97.50 134	97.74 272	93.65 180	98.49 28	98.88 118	96.86 101	97.11 205	98.55 107	95.82 130	99.73 89	95.94 127	99.42 172	99.13 163

MTAPA		98.14 43	97.84 72	99.06 7	99.44 36	97.90 16	97.25 115	98.73 159	97.69 68	97.90 161	97.96 187	95.81 134	99.82 36	96.13 115	99.61 98	99.45 90

DP-MVS		97.87 78	97.89 68	97.81 108	98.62 160	94.82 131	97.13 124	98.79 147	98.98 21	98.74 73	98.49 113	95.80 135	99.49 199	95.04 186	99.44 160	99.11 171

Anonymous20240529		97.96 59	98.04 54	97.71 114	98.69 151	94.28 156	97.86 73	98.31 220	98.79 26	99.23 33	98.86 77	95.76 136	99.61 165	95.49 151	99.36 183	99.23 145

LS3D		97.77 90	97.50 113	98.57 51	96.24 344	97.58 28	98.45 31	98.85 127	98.58 32	97.51 180	97.94 190	95.74 137	99.63 153	95.19 173	98.97 243	98.51 256

EIA-MVS		96.04 193	95.77 209	96.85 189	97.80 257	92.98 198	96.12 190	99.16 43	94.65 206	93.77 342	91.69 394	95.68 138	99.67 137	94.18 223	98.85 258	97.91 317

CNVR-MVS		96.92 146	96.55 170	98.03 95	98.00 235	95.54 97	94.87 273	98.17 236	94.60 208	96.38 256	97.05 262	95.67 139	99.36 245	95.12 183	99.08 233	99.19 151

CLD-MVS		95.47 220	95.07 228	96.69 201	98.27 200	92.53 209	91.36 376	98.67 174	91.22 305	95.78 289	94.12 362	95.65 140	98.98 317	90.81 299	99.72 70	98.57 249
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	98.79 136	94.37 150	98.84 11	99.15 47	99.37 4	99.67 8	99.43 17	95.61 141	99.72 95	98.12 36	99.86 28	99.73 22

EGC-MVSNET		83.08 385	77.93 388	98.53 54	99.57 19	97.55 30	98.33 38	98.57 189	4.71 423	10.38 424	98.90 73	95.60 142	99.50 194	95.69 139	99.61 98	98.55 252

ITE_SJBPF				97.85 106	98.64 154	96.66 58		98.51 194	95.63 163	97.22 195	97.30 246	95.52 143	98.55 360	90.97 294	98.90 251	98.34 274

DeepC-MVS_fast	94.34 7	96.74 160	96.51 175	97.44 142	97.69 276	94.15 159	96.02 197	98.43 201	93.17 260	97.30 191	97.38 239	95.48 144	99.28 268	93.74 240	99.34 191	98.88 213
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 42	99.05 17	99.17 36	98.79 79	95.47 145	99.89 19	97.95 43	99.91 17	99.75 20

FMVSNet1		97.95 63	98.08 50	97.56 125	99.14 90	93.67 176	98.23 46	98.66 176	97.41 83	99.00 47	99.19 38	95.47 145	99.73 89	95.83 134	99.76 57	99.30 127

MIMVSNet1		98.51 25	98.45 32	98.67 44	99.72 8	96.71 54	98.76 13	98.89 111	98.49 35	99.38 23	99.14 49	95.44 147	99.84 32	96.47 100	99.80 50	99.47 84

mmtdpeth		98.33 33	98.53 28	97.71 114	99.07 98	93.44 185	98.80 12	99.78 4	99.10 13	96.61 243	99.63 7	95.42 148	99.73 89	98.53 29	99.86 28	99.95 2

CP-MVSNet		98.42 30	98.46 30	98.30 70	99.46 34	95.22 120	98.27 44	98.84 131	99.05 17	99.01 45	98.65 97	95.37 149	99.90 16	97.57 61	99.91 17	99.77 13

segment_acmp												95.34 150

CDPH-MVS		95.45 222	94.65 251	97.84 107	98.28 198	94.96 128	93.73 321	98.33 216	85.03 379	95.44 300	96.60 291	95.31 151	99.44 215	90.01 321	99.13 225	99.11 171

3Dnovator+	96.13 3	97.73 92	97.59 103	98.15 83	98.11 226	95.60 95	98.04 59	98.70 168	98.13 50	96.93 222	98.45 118	95.30 152	99.62 158	95.64 144	98.96 244	99.24 144

MVS_Test		96.27 184	96.79 157	94.73 300	96.94 329	86.63 333	96.18 184	98.33 216	94.94 197	96.07 275	98.28 144	95.25 153	99.26 272	97.21 72	97.90 319	98.30 279

XVG-OURS		97.12 134	96.74 158	98.26 72	98.99 110	97.45 36	93.82 317	99.05 72	95.19 185	98.32 114	97.70 213	95.22 154	98.41 370	94.27 220	98.13 309	98.93 201

dcpmvs_2		97.12 134	97.99 59	94.51 310	99.11 92	84.00 369	97.75 82	99.65 12	97.38 86	99.14 37	98.42 121	95.16 155	99.96 2	95.52 150	99.78 55	99.58 39

MCST-MVS		96.24 185	95.80 207	97.56 125	98.75 141	94.13 160	94.66 282	98.17 236	90.17 320	96.21 269	96.10 319	95.14 156	99.43 217	94.13 226	98.85 258	99.13 163

EI-MVSNet-Vis-set		97.32 127	97.39 117	97.11 166	97.36 308	92.08 227	95.34 248	97.65 276	97.74 63	98.29 119	98.11 168	95.05 157	99.68 129	97.50 64	99.50 144	99.56 50

EI-MVSNet-UG-set		97.32 127	97.40 116	97.09 170	97.34 311	92.01 229	95.33 249	97.65 276	97.74 63	98.30 118	98.14 162	95.04 158	99.69 124	97.55 62	99.52 135	99.58 39

KD-MVS_self_test		97.86 80	98.07 51	97.25 158	99.22 66	92.81 202	97.55 99	98.94 106	97.10 95	98.85 60	98.88 75	95.03 159	99.67 137	97.39 68	99.65 86	99.26 139

ZD-MVS					98.43 186	95.94 83		98.56 190	90.72 310	96.66 239	97.07 260	95.02 160	99.74 83	91.08 290	98.93 249

DELS-MVS		96.17 188	96.23 186	95.99 236	97.55 294	90.04 263	92.38 360	98.52 192	94.13 224	96.55 249	97.06 261	94.99 161	99.58 170	95.62 145	99.28 205	98.37 268
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		96.59 170	96.93 147	95.55 261	98.88 126	87.12 325	94.47 287	99.30 29	94.12 225	96.65 241	98.41 123	94.98 162	99.87 24	95.81 136	99.78 55	99.66 30

ab-mvs		96.59 170	96.59 166	96.60 204	98.64 154	92.21 218	98.35 35	97.67 272	94.45 214	96.99 217	98.79 79	94.96 163	99.49 199	90.39 316	99.07 235	98.08 298

MSLP-MVS++		96.42 180	96.71 159	95.57 258	97.82 252	90.56 260	95.71 218	98.84 131	94.72 203	96.71 235	97.39 237	94.91 164	98.10 386	95.28 168	99.02 240	98.05 307

QAPM		95.88 200	95.57 216	96.80 193	97.90 242	91.84 234	98.18 53	98.73 159	88.41 342	96.42 254	98.13 164	94.73 165	99.75 74	88.72 340	98.94 247	98.81 221

RPSCF		97.87 78	97.51 111	98.95 18	99.15 83	98.43 7	97.56 98	99.06 68	96.19 131	98.48 92	98.70 91	94.72 166	99.24 278	94.37 216	99.33 196	99.17 154

DU-MVS		97.79 88	97.60 102	98.36 65	98.73 142	95.78 87	95.65 226	98.87 120	97.57 72	98.31 116	97.83 198	94.69 167	99.85 29	97.02 84	99.71 73	99.46 86

Baseline_NR-MVSNet		97.72 94	97.79 79	97.50 134	99.56 20	93.29 191	95.44 236	98.86 123	98.20 49	98.37 103	99.24 33	94.69 167	99.55 181	95.98 125	99.79 52	99.65 33

TEST9					97.84 249	95.23 117	93.62 323	98.39 208	86.81 360	93.78 340	95.99 321	94.68 169	99.52 189

UniMVSNet (Re)		97.83 82	97.65 93	98.35 66	98.80 134	95.86 86	95.92 208	99.04 79	97.51 76	98.22 124	97.81 203	94.68 169	99.78 53	97.14 77	99.75 64	99.41 104

UniMVSNet_NR-MVSNet		97.83 82	97.65 93	98.37 64	98.72 144	95.78 87	95.66 224	99.02 82	98.11 51	98.31 116	97.69 214	94.65 171	99.85 29	97.02 84	99.71 73	99.48 81

VPNet		97.26 129	97.49 114	96.59 205	99.47 33	90.58 258	96.27 176	98.53 191	97.77 60	98.46 95	98.41 123	94.59 172	99.68 129	94.61 206	99.29 204	99.52 60

train_agg		95.46 221	94.66 250	97.88 104	97.84 249	95.23 117	93.62 323	98.39 208	87.04 356	93.78 340	95.99 321	94.58 173	99.52 189	91.76 280	98.90 251	98.89 209

test_8					97.81 253	95.07 126	93.54 326	98.38 210	87.04 356	93.71 344	95.96 324	94.58 173	99.52 189

API-MVS		95.09 240	95.01 231	95.31 270	96.61 336	94.02 163	96.83 139	97.18 292	95.60 165	95.79 287	94.33 360	94.54 175	98.37 375	85.70 371	98.52 288	93.52 406

Test By Simon												94.51 176

MSDG		95.33 228	95.13 225	95.94 242	97.40 306	91.85 233	91.02 387	98.37 211	95.30 181	96.31 262	95.99 321	94.51 176	98.38 373	89.59 328	97.65 336	97.60 341

TSAR-MVS + GP.		96.47 177	96.12 190	97.49 137	97.74 272	95.23 117	94.15 301	96.90 304	93.26 251	98.04 147	96.70 286	94.41 178	98.89 325	94.77 201	99.14 223	98.37 268

NR-MVSNet		97.96 59	97.86 71	98.26 72	98.73 142	95.54 97	98.14 54	98.73 159	97.79 59	99.42 21	97.83 198	94.40 179	99.78 53	95.91 129	99.76 57	99.46 86

AdaColmap		95.11 238	94.62 255	96.58 206	97.33 313	94.45 146	94.92 271	98.08 248	93.15 261	93.98 338	95.53 337	94.34 180	99.10 302	85.69 372	98.61 283	96.20 384

FC-MVSNet-test		98.16 42	98.37 36	97.56 125	99.49 32	93.10 196	98.35 35	99.21 36	98.43 36	98.89 57	98.83 78	94.30 181	99.81 41	97.87 46	99.91 17	99.77 13

Effi-MVS+-dtu		96.81 157	96.09 192	98.99 14	96.90 331	98.69 5	96.42 165	98.09 247	95.86 153	95.15 306	95.54 336	94.26 182	99.81 41	94.06 228	98.51 291	98.47 260

ambc				96.56 209	98.23 206	91.68 238	97.88 72	98.13 244		98.42 98	98.56 106	94.22 183	99.04 309	94.05 230	99.35 188	98.95 195

test20.03		96.58 172	96.61 165	96.48 214	98.49 179	91.72 236	95.68 222	97.69 271	96.81 102	98.27 120	97.92 193	94.18 184	98.71 342	90.78 301	99.66 85	99.00 187

HPM-MVS++		96.99 140	96.38 180	98.81 31	98.64 154	97.59 27	95.97 203	98.20 230	95.51 170	95.06 308	96.53 295	94.10 185	99.70 117	94.29 219	99.15 222	99.13 163

test_vis3_rt		97.04 137	96.98 143	97.23 160	98.44 185	95.88 84	96.82 140	99.67 9	90.30 317	99.27 30	99.33 28	94.04 186	96.03 409	97.14 77	97.83 322	99.78 12

test_fmvs3		97.38 121	97.56 106	96.84 191	98.63 158	92.81 202	97.60 94	99.61 16	90.87 308	98.76 71	99.66 4	94.03 187	97.90 388	99.24 6	99.68 81	99.81 9

PM-MVS		97.36 125	97.10 135	98.14 84	98.91 124	96.77 53	96.20 183	98.63 182	93.82 233	98.54 85	98.33 133	93.98 188	99.05 307	95.99 124	99.45 159	98.61 247

mvsany_test3		96.21 186	95.93 202	97.05 173	97.40 306	94.33 152	95.76 217	94.20 355	89.10 331	99.36 25	99.60 8	93.97 189	97.85 389	95.40 166	98.63 281	98.99 190

OpenMVS	94.22 8	95.48 219	95.20 221	96.32 223	97.16 320	91.96 230	97.74 84	98.84 131	87.26 353	94.36 325	98.01 183	93.95 190	99.67 137	90.70 308	98.75 268	97.35 352

v8		97.60 104	98.06 53	96.23 226	98.71 147	89.44 276	97.43 109	98.82 145	97.29 90	98.74 73	99.10 52	93.86 191	99.68 129	98.61 26	99.94 8	99.56 50

diffmvs		96.04 193	96.23 186	95.46 266	97.35 309	88.03 306	93.42 329	99.08 64	94.09 228	96.66 239	96.93 270	93.85 192	99.29 266	96.01 123	98.67 276	99.06 180
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		96.52 174	95.99 197	98.10 87	97.81 253	95.68 92	95.00 269	98.20 230	95.39 177	95.40 302	96.36 306	93.81 193	99.45 212	93.55 246	98.42 297	99.17 154

TAPA-MVS	93.32 12	94.93 245	94.23 272	97.04 175	98.18 213	94.51 143	95.22 256	98.73 159	81.22 398	96.25 266	95.95 325	93.80 194	98.98 317	89.89 324	98.87 255	97.62 339
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
FIs		97.93 69	98.07 51	97.48 138	99.38 46	92.95 199	98.03 61	99.11 53	98.04 55	98.62 78	98.66 94	93.75 195	99.78 53	97.23 70	99.84 38	99.73 22

OurMVSNet-221017-0		98.61 17	98.61 25	98.63 48	99.77 5	96.35 68	99.17 7	99.05 72	98.05 54	99.61 14	99.52 9	93.72 196	99.88 21	98.72 24	99.88 24	99.65 33

test_prior2							93.33 333		94.21 220	94.02 336	96.25 310	93.64 197		91.90 274	98.96 244

mvsany_test1		93.47 301	93.03 298	94.79 297	94.05 404	92.12 223	90.82 389	90.01 403	85.02 380	97.26 194	98.28 144	93.57 198	97.03 398	92.51 266	95.75 385	95.23 397

旧先验1					97.80 257	93.87 168		97.75 268			97.04 263	93.57 198			98.68 275	98.72 234

v10		97.55 108	97.97 61	96.31 224	98.60 162	89.64 271	97.44 107	99.02 82	96.60 108	98.72 75	99.16 46	93.48 200	99.72 95	98.76 21	99.92 14	99.58 39

v148		96.58 172	96.97 144	95.42 267	98.63 158	87.57 316	95.09 261	97.90 258	95.91 150	98.24 122	97.96 187	93.42 201	99.39 234	96.04 119	99.52 135	99.29 133

V42		97.04 137	97.16 133	96.68 202	98.59 164	91.05 248	96.33 173	98.36 212	94.60 208	97.99 150	98.30 139	93.32 202	99.62 158	97.40 67	99.53 130	99.38 112

new-patchmatchnet		95.67 210	96.58 167	92.94 354	97.48 298	80.21 395	92.96 339	98.19 235	94.83 200	98.82 63	98.79 79	93.31 203	99.51 193	95.83 134	99.04 239	99.12 168

test12				97.46 140	97.61 289	94.07 161		97.78 267		93.57 350		93.31 203	99.42 219		98.78 265	98.89 209

UGNet		96.81 157	96.56 169	97.58 124	96.64 335	93.84 170	97.75 82	97.12 295	96.47 119	93.62 347	98.88 75	93.22 205	99.53 186	95.61 146	99.69 77	99.36 118
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 52	98.58 26	96.51 211	98.97 114	89.65 270	99.43 4	99.81 2	99.30 7	98.36 106	99.86 2	93.15 206	99.88 21	98.50 30	99.84 38	99.99 1

pmmvs-eth3d		96.49 175	96.18 189	97.42 145	98.25 203	94.29 153	94.77 278	98.07 252	89.81 324	97.97 154	98.33 133	93.11 207	99.08 304	95.46 158	99.84 38	98.89 209

v1144		96.84 152	97.08 137	96.13 233	98.42 187	89.28 279	95.41 240	98.67 174	94.21 220	97.97 154	98.31 135	93.06 208	99.65 145	98.06 40	99.62 92	99.45 90

MVSMamba_PlusPlus		97.43 118	97.98 60	95.78 248	98.88 126	89.70 268	98.03 61	98.85 127	99.18 11	96.84 227	99.12 50	93.04 209	99.91 14	98.38 32	99.55 122	97.73 332

PVSNet_BlendedMVS		95.02 244	94.93 234	95.27 271	97.79 262	87.40 320	94.14 303	98.68 171	88.94 335	94.51 321	98.01 183	93.04 209	99.30 262	89.77 326	99.49 147	99.11 171

PVSNet_Blended		93.96 288	93.65 288	94.91 288	97.79 262	87.40 320	91.43 375	98.68 171	84.50 386	94.51 321	94.48 358	93.04 209	99.30 262	89.77 326	98.61 283	98.02 310

mvs_anonymous		95.36 225	96.07 194	93.21 344	96.29 343	81.56 386	94.60 284	97.66 274	93.30 250	96.95 221	98.91 72	93.03 212	99.38 237	96.60 95	97.30 350	98.69 238

v1192		96.83 155	97.06 139	96.15 232	98.28 198	89.29 278	95.36 244	98.77 152	93.73 235	98.11 136	98.34 132	93.02 213	99.67 137	98.35 33	99.58 110	99.50 67

F-COLMAP		95.30 230	94.38 269	98.05 94	98.64 154	96.04 79	95.61 230	98.66 176	89.00 334	93.22 359	96.40 304	92.90 214	99.35 249	87.45 360	97.53 340	98.77 228

WR-MVS		96.90 148	96.81 154	97.16 162	98.56 168	92.20 221	94.33 290	98.12 245	97.34 87	98.20 125	97.33 244	92.81 215	99.75 74	94.79 198	99.81 47	99.54 54

v1240		96.74 160	97.02 142	95.91 243	98.18 213	88.52 292	95.39 242	98.88 118	93.15 261	98.46 95	98.40 126	92.80 216	99.71 109	98.45 31	99.49 147	99.49 75

MVE	73.61 22	86.48 383	85.92 382	88.18 397	96.23 346	85.28 350	81.78 417	75.79 421	86.01 366	82.53 417	91.88 391	92.74 217	87.47 420	71.42 417	94.86 393	91.78 411
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DP-MVS Recon		95.55 215	95.13 225	96.80 193	98.51 175	93.99 165	94.60 284	98.69 169	90.20 319	95.78 289	96.21 312	92.73 218	98.98 317	90.58 311	98.86 257	97.42 349

CANet		95.86 201	95.65 213	96.49 213	96.41 341	90.82 253	94.36 289	98.41 205	94.94 197	92.62 375	96.73 285	92.68 219	99.71 109	95.12 183	99.60 104	98.94 197

v1921920		96.72 163	96.96 146	95.99 236	98.21 207	88.79 289	95.42 238	98.79 147	93.22 253	98.19 129	98.26 149	92.68 219	99.70 117	98.34 34	99.55 122	99.49 75

BH-untuned		94.69 258	94.75 248	94.52 309	97.95 240	87.53 317	94.07 306	97.01 300	93.99 230	97.10 206	95.65 332	92.65 221	98.95 322	87.60 355	96.74 362	97.09 356

LF4IMVS		96.07 191	95.63 214	97.36 149	98.19 210	95.55 96	95.44 236	98.82 145	92.29 283	95.70 293	96.55 293	92.63 222	98.69 345	91.75 281	99.33 196	97.85 322

v2v482		96.78 159	97.06 139	95.95 240	98.57 166	88.77 290	95.36 244	98.26 222	95.18 186	97.85 168	98.23 153	92.58 223	99.63 153	97.80 50	99.69 77	99.45 90

WB-MVSnew		91.50 338	91.29 331	92.14 372	94.85 389	80.32 394	93.29 334	88.77 406	88.57 341	94.03 335	92.21 387	92.56 224	98.28 380	80.21 401	97.08 351	97.81 326

EI-MVSNet		96.63 169	96.93 147	95.74 250	97.26 316	88.13 303	95.29 253	97.65 276	96.99 96	97.94 158	98.19 158	92.55 225	99.58 170	96.91 87	99.56 116	99.50 67

IterMVS-LS		96.92 146	97.29 123	95.79 247	98.51 175	88.13 303	95.10 260	98.66 176	96.99 96	98.46 95	98.68 93	92.55 225	99.74 83	96.91 87	99.79 52	99.50 67
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
VDD-MVS		97.37 123	97.25 126	97.74 112	98.69 151	94.50 145	97.04 129	95.61 333	98.59 31	98.51 87	98.72 86	92.54 227	99.58 170	96.02 121	99.49 147	99.12 168

MVS		90.02 351	89.20 358	92.47 366	94.71 392	86.90 329	95.86 211	96.74 311	64.72 418	90.62 388	92.77 379	92.54 227	98.39 372	79.30 403	95.56 387	92.12 410

test_vis1_rt		94.03 287	93.65 288	95.17 276	95.76 371	93.42 187	93.97 312	98.33 216	84.68 383	93.17 360	95.89 327	92.53 229	94.79 412	93.50 247	94.97 391	97.31 353

v144192		96.69 166	96.90 151	96.03 235	98.25 203	88.92 284	95.49 234	98.77 152	93.05 263	98.09 139	98.29 143	92.51 230	99.70 117	98.11 37	99.56 116	99.47 84

原ACMM1				96.58 206	98.16 218	92.12 223		98.15 242	85.90 369	93.49 352	96.43 301	92.47 231	99.38 237	87.66 354	98.62 282	98.23 286

VNet		96.84 152	96.83 153	96.88 187	98.06 227	92.02 228	96.35 172	97.57 282	97.70 67	97.88 163	97.80 204	92.40 232	99.54 184	94.73 203	98.96 244	99.08 176

114514_t		93.96 288	93.22 296	96.19 229	99.06 100	90.97 251	95.99 201	98.94 106	73.88 416	93.43 355	96.93 270	92.38 233	99.37 242	89.09 335	99.28 205	98.25 285

balanced_conf03		96.88 150	97.29 123	95.63 255	97.66 282	89.47 275	97.95 66	98.89 111	95.94 146	97.77 173	98.55 107	92.23 234	99.68 129	97.05 83	99.61 98	97.73 332

CPTT-MVS		96.69 166	96.08 193	98.49 56	98.89 125	96.64 59	97.25 115	98.77 152	92.89 271	96.01 278	97.13 255	92.23 234	99.67 137	92.24 269	99.34 191	99.17 154

MSP-MVS		97.45 115	96.92 149	99.03 9	99.26 57	97.70 22	97.66 90	98.89 111	95.65 162	98.51 87	96.46 299	92.15 236	99.81 41	95.14 180	98.58 286	99.58 39
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		94.21 278	93.03 298	97.76 111	96.94 329	97.44 37	96.97 133	97.15 293	87.89 351	92.00 380	92.73 381	92.14 237	99.12 296	83.92 386	97.51 341	96.73 373
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		95.95 197	95.80 207	96.42 217	99.28 55	90.62 257	95.31 251	99.08 64	88.40 343	96.97 220	98.17 161	92.11 238	99.78 53	93.64 244	99.21 214	98.86 216

BH-RMVSNet		94.56 266	94.44 267	94.91 288	97.57 291	87.44 319	93.78 320	96.26 317	93.69 238	96.41 255	96.50 298	92.10 239	99.00 313	85.96 369	97.71 329	98.31 277

新几何1				97.25 158	98.29 196	94.70 135		97.73 269	77.98 409	94.83 315	96.67 288	92.08 240	99.45 212	88.17 349	98.65 280	97.61 340

testdata				95.70 253	98.16 218	90.58 258		97.72 270	80.38 401	95.62 294	97.02 264	92.06 241	98.98 317	89.06 337	98.52 288	97.54 344

YYNet1		94.73 253	94.84 242	94.41 314	97.47 302	85.09 354	90.29 394	95.85 327	92.52 277	97.53 178	97.76 205	91.97 242	99.18 285	93.31 252	96.86 356	98.95 195

Anonymous20231206		95.27 231	95.06 230	95.88 244	98.72 144	89.37 277	95.70 219	97.85 261	88.00 349	96.98 219	97.62 218	91.95 243	99.34 252	89.21 333	99.53 130	98.94 197

MS-PatchMatch		94.83 250	94.91 236	94.57 307	96.81 332	87.10 326	94.23 296	97.34 287	88.74 338	97.14 202	97.11 258	91.94 244	98.23 382	92.99 259	97.92 317	98.37 268

MDA-MVSNet_test_wron		94.73 253	94.83 244	94.42 313	97.48 298	85.15 352	90.28 395	95.87 326	92.52 277	97.48 184	97.76 205	91.92 245	99.17 289	93.32 251	96.80 361	98.94 197

HQP_MVS		96.66 168	96.33 183	97.68 119	98.70 149	94.29 153	96.50 162	98.75 156	96.36 122	96.16 272	96.77 282	91.91 246	99.46 207	92.59 264	99.20 215	99.28 134

plane_prior6					98.38 189	94.37 150						91.91 246

MVP-Stereo		95.69 208	95.28 219	96.92 182	98.15 220	93.03 197	95.64 229	98.20 230	90.39 316	96.63 242	97.73 211	91.63 248	99.10 302	91.84 277	97.31 349	98.63 244
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PatchMatch-RL		94.61 264	93.81 286	97.02 177	98.19 210	95.72 89	93.66 322	97.23 289	88.17 347	94.94 313	95.62 334	91.43 249	98.57 357	87.36 361	97.68 332	96.76 372

MDA-MVSNet-bldmvs		95.69 208	95.67 211	95.74 250	98.48 181	88.76 291	92.84 341	97.25 288	96.00 142	97.59 176	97.95 189	91.38 250	99.46 207	93.16 257	96.35 372	98.99 190

SSC-MVS		95.92 198	97.03 141	92.58 363	99.28 55	78.39 400	96.68 156	95.12 344	98.90 23	99.11 39	98.66 94	91.36 251	99.68 129	95.00 189	99.16 221	99.67 28

PAPR		92.22 323	91.27 333	95.07 280	95.73 373	88.81 288	91.97 366	97.87 260	85.80 370	90.91 387	92.73 381	91.16 252	98.33 377	79.48 402	95.76 384	98.08 298

1314		92.38 320	92.30 315	92.64 362	95.42 380	85.15 352	95.86 211	96.97 302	85.40 375	90.62 388	93.06 374	91.12 253	97.80 391	86.74 366	95.49 388	94.97 399

WB-MVS		95.50 216	96.62 163	92.11 373	99.21 73	77.26 410	96.12 190	95.40 339	98.62 30	98.84 61	98.26 149	91.08 254	99.50 194	93.37 248	98.70 274	99.58 39

ppachtmachnet_test		94.49 270	94.84 242	93.46 337	96.16 350	82.10 381	90.59 391	97.48 284	90.53 314	97.01 216	97.59 220	91.01 255	99.36 245	93.97 234	99.18 219	98.94 197

PLC	91.02 16	94.05 285	92.90 301	97.51 130	98.00 235	95.12 125	94.25 294	98.25 223	86.17 365	91.48 385	95.25 341	91.01 255	99.19 284	85.02 381	96.69 365	98.22 288
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test222					98.17 216	93.24 194	92.74 346	97.61 281	75.17 414	94.65 318	96.69 287	90.96 257			98.66 278	97.66 336

CL-MVSNet_self_test		95.04 241	94.79 247	95.82 246	97.51 296	89.79 267	91.14 384	96.82 307	93.05 263	96.72 234	96.40 304	90.82 258	99.16 290	91.95 273	98.66 278	98.50 258

USDC		94.56 266	94.57 261	94.55 308	97.78 265	86.43 336	92.75 344	98.65 181	85.96 367	96.91 224	97.93 192	90.82 258	98.74 338	90.71 307	99.59 107	98.47 260

PCF-MVS	89.43 18	92.12 326	90.64 346	96.57 208	97.80 257	93.48 184	89.88 401	98.45 198	74.46 415	96.04 277	95.68 331	90.71 260	99.31 259	73.73 413	99.01 242	96.91 363
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PAPM_NR		94.61 264	94.17 276	95.96 238	98.36 191	91.23 246	95.93 207	97.95 255	92.98 266	93.42 356	94.43 359	90.53 261	98.38 373	87.60 355	96.29 374	98.27 283

our_test_3		94.20 280	94.58 259	93.07 347	96.16 350	81.20 390	90.42 393	96.84 305	90.72 310	97.14 202	97.13 255	90.47 262	99.11 299	94.04 231	98.25 304	98.91 205

MM		96.87 151	96.62 163	97.62 122	97.72 274	93.30 190	96.39 166	92.61 375	97.90 58	96.76 233	98.64 98	90.46 263	99.81 41	99.16 9	99.94 8	99.76 18

test_f		95.82 203	95.88 205	95.66 254	97.61 289	93.21 195	95.61 230	98.17 236	86.98 358	98.42 98	99.47 13	90.46 263	94.74 413	97.71 56	98.45 295	99.03 183

OpenMVS_ROB	91.80 14	93.64 297	93.05 297	95.42 267	97.31 315	91.21 247	95.08 263	96.68 314	81.56 395	96.88 226	96.41 302	90.44 265	99.25 274	85.39 377	97.67 333	95.80 389

HQP2-MVS												90.33 266

N_pmnet		95.18 235	94.23 272	98.06 90	97.85 244	96.55 62	92.49 352	91.63 383	89.34 328	98.09 139	97.41 232	90.33 266	99.06 306	91.58 282	99.31 201	98.56 250

HQP-MVS		95.17 237	94.58 259	96.92 182	97.85 244	92.47 212	94.26 291	98.43 201	93.18 257	92.86 366	95.08 343	90.33 266	99.23 280	90.51 313	98.74 269	99.05 182

CNLPA		95.04 241	94.47 264	96.75 197	97.81 253	95.25 116	94.12 305	97.89 259	94.41 215	94.57 319	95.69 330	90.30 269	98.35 376	86.72 367	98.76 267	96.64 374

PMMVS		92.39 319	91.08 336	96.30 225	93.12 411	92.81 202	90.58 392	95.96 323	79.17 406	91.85 382	92.27 386	90.29 270	98.66 350	89.85 325	96.68 366	97.43 348

TR-MVS		92.54 318	92.20 318	93.57 335	96.49 339	86.66 332	93.51 327	94.73 349	89.96 322	94.95 312	93.87 364	90.24 271	98.61 354	81.18 398	94.88 392	95.45 395

TAMVS		95.49 217	94.94 232	97.16 162	98.31 194	93.41 188	95.07 264	96.82 307	91.09 306	97.51 180	97.82 201	89.96 272	99.42 219	88.42 345	99.44 160	98.64 242

DPM-MVS		93.68 295	92.77 308	96.42 217	97.91 241	92.54 208	91.17 383	97.47 285	84.99 381	93.08 362	94.74 351	89.90 273	99.00 313	87.54 357	98.09 311	97.72 334

PMMVS2		93.66 296	94.07 279	92.45 367	97.57 291	80.67 393	86.46 409	96.00 321	93.99 230	97.10 206	97.38 239	89.90 273	97.82 390	88.76 339	99.47 153	98.86 216

BH-w/o		92.14 325	91.94 320	92.73 360	97.13 322	85.30 348	92.46 354	95.64 330	89.33 329	94.21 327	92.74 380	89.60 275	98.24 381	81.68 395	94.66 394	94.66 400

Anonymous20240521		97.07 136	97.51 111	95.76 249	99.35 49	88.18 300	97.78 78	98.40 207	97.11 94	98.34 110	99.04 57	89.58 276	99.79 49	98.09 38	99.93 11	99.30 127

UnsupCasMVSNet_bld		94.72 257	94.26 271	96.08 234	98.62 160	90.54 261	93.38 331	98.05 254	90.30 317	97.02 215	96.80 281	89.54 277	99.16 290	88.44 344	96.18 376	98.56 250

MG-MVS		94.08 284	94.00 281	94.32 318	97.09 323	85.89 341	93.19 337	95.96 323	92.52 277	94.93 314	97.51 226	89.54 277	98.77 335	87.52 359	97.71 329	98.31 277

UnsupCasMVSNet_eth		95.91 199	95.73 210	96.44 215	98.48 181	91.52 240	95.31 251	98.45 198	95.76 157	97.48 184	97.54 223	89.53 279	98.69 345	94.43 212	94.61 395	99.13 163

GBi-Net		96.99 140	96.80 155	97.56 125	97.96 237	93.67 176	98.23 46	98.66 176	95.59 166	97.99 150	99.19 38	89.51 280	99.73 89	94.60 207	99.44 160	99.30 127

test1		96.99 140	96.80 155	97.56 125	97.96 237	93.67 176	98.23 46	98.66 176	95.59 166	97.99 150	99.19 38	89.51 280	99.73 89	94.60 207	99.44 160	99.30 127

FMVSNet2		96.72 163	96.67 162	96.87 188	97.96 237	91.88 232	97.15 121	98.06 253	95.59 166	98.50 89	98.62 99	89.51 280	99.65 145	94.99 191	99.60 104	99.07 178

pmmvs4		94.82 251	94.19 275	96.70 200	97.42 305	92.75 206	92.09 365	96.76 309	86.80 361	95.73 292	97.22 250	89.28 283	98.89 325	93.28 253	99.14 223	98.46 262

cascas		91.89 332	91.35 330	93.51 336	94.27 398	85.60 343	88.86 406	98.61 183	79.32 405	92.16 379	91.44 396	89.22 284	98.12 385	90.80 300	97.47 344	96.82 369

DSMNet-mixed		92.19 324	91.83 322	93.25 341	96.18 349	83.68 372	96.27 176	93.68 360	76.97 413	92.54 376	99.18 42	89.20 285	98.55 360	83.88 387	98.60 285	97.51 345

c3_l		95.20 234	95.32 218	94.83 295	96.19 348	86.43 336	91.83 369	98.35 215	93.47 244	97.36 190	97.26 248	88.69 286	99.28 268	95.41 165	99.36 183	98.78 225

test_fmvs2		96.38 181	96.45 177	96.16 231	97.85 244	91.30 244	96.81 141	99.45 21	89.24 330	98.49 90	99.38 20	88.68 287	97.62 393	98.83 18	99.32 198	99.57 46

CANet_DTU		94.65 262	94.21 274	95.96 238	95.90 360	89.68 269	93.92 314	97.83 265	93.19 256	90.12 396	95.64 333	88.52 288	99.57 176	93.27 254	99.47 153	98.62 245

EPP-MVSNet		96.84 152	96.58 167	97.65 120	99.18 78	93.78 173	98.68 14	96.34 316	97.91 57	97.30 191	98.06 177	88.46 289	99.85 29	93.85 237	99.40 177	99.32 122

SixPastTwentyTwo		97.49 112	97.57 105	97.26 157	99.56 20	92.33 214	98.28 42	96.97 302	98.30 43	99.45 19	99.35 25	88.43 290	99.89 19	98.01 41	99.76 57	99.54 54

miper_ehance_all_eth		94.69 258	94.70 249	94.64 301	95.77 370	86.22 338	91.32 380	98.24 225	91.67 292	97.05 213	96.65 289	88.39 291	99.22 282	94.88 193	98.34 300	98.49 259

MVS_0304		95.71 207	95.18 223	97.33 151	94.85 389	92.82 200	95.36 244	90.89 392	95.51 170	95.61 295	97.82 201	88.39 291	99.78 53	98.23 35	99.91 17	99.40 105

IS-MVSNet		96.93 145	96.68 161	97.70 116	99.25 60	94.00 164	98.57 20	96.74 311	98.36 39	98.14 134	97.98 186	88.23 293	99.71 109	93.10 258	99.72 70	99.38 112

jason		94.39 273	94.04 280	95.41 269	98.29 196	87.85 311	92.74 346	96.75 310	85.38 376	95.29 303	96.15 314	88.21 294	99.65 145	94.24 221	99.34 191	98.74 231
jason: jason.
IterMVS-SCA-FT		95.86 201	96.19 188	94.85 293	97.68 277	85.53 344	92.42 357	97.63 280	96.99 96	98.36 106	98.54 109	87.94 295	99.75 74	97.07 82	99.08 233	99.27 138

SCA		93.38 304	93.52 291	92.96 353	96.24 344	81.40 388	93.24 335	94.00 356	91.58 297	94.57 319	96.97 267	87.94 295	99.42 219	89.47 330	97.66 335	98.06 304

sss		94.22 276	93.72 287	95.74 250	97.71 275	89.95 265	93.84 316	96.98 301	88.38 344	93.75 343	95.74 329	87.94 295	98.89 325	91.02 292	98.10 310	98.37 268

IterMVS		95.42 223	95.83 206	94.20 322	97.52 295	83.78 371	92.41 358	97.47 285	95.49 172	98.06 144	98.49 113	87.94 295	99.58 170	96.02 121	99.02 240	99.23 145
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CHOSEN 1792x2688		94.10 282	93.41 293	96.18 230	99.16 80	90.04 263	92.15 362	98.68 171	79.90 403	96.22 268	97.83 198	87.92 299	99.42 219	89.18 334	99.65 86	99.08 176

VDDNet		96.98 143	96.84 152	97.41 146	99.40 43	93.26 193	97.94 67	95.31 341	99.26 9	98.39 102	99.18 42	87.85 300	99.62 158	95.13 182	99.09 232	99.35 120

pmmvs5		94.63 263	94.34 270	95.50 263	97.63 288	88.34 296	94.02 307	97.13 294	87.15 355	95.22 305	97.15 254	87.50 301	99.27 271	93.99 232	99.26 209	98.88 213

D2MVS		95.18 235	95.17 224	95.21 273	97.76 267	87.76 314	94.15 301	97.94 256	89.77 325	96.99 217	97.68 215	87.45 302	99.14 292	95.03 188	99.81 47	98.74 231

test_vis1_n_1920		95.77 205	96.41 179	93.85 327	98.55 169	84.86 358	95.91 209	99.71 6	92.72 275	97.67 174	98.90 73	87.44 303	98.73 339	97.96 42	98.85 258	97.96 314

PVSNet	86.72 19	91.10 343	90.97 339	91.49 378	97.56 293	78.04 403	87.17 408	94.60 351	84.65 384	92.34 377	92.20 388	87.37 304	98.47 367	85.17 380	97.69 331	97.96 314

Anonymous202405211		96.34 182	95.98 198	97.43 143	98.25 203	93.85 169	96.74 149	94.41 353	97.72 65	98.37 103	98.03 180	87.15 305	99.53 186	94.06 228	99.07 235	98.92 204

MVSFormer		96.14 189	96.36 181	95.49 264	97.68 277	87.81 312	98.67 15	99.02 82	96.50 115	94.48 323	96.15 314	86.90 306	99.92 6	98.73 22	99.13 225	98.74 231

lupinMVS		93.77 291	93.28 294	95.24 272	97.68 277	87.81 312	92.12 363	96.05 319	84.52 385	94.48 323	95.06 345	86.90 306	99.63 153	93.62 245	99.13 225	98.27 283

eth_miper_zixun_eth		94.89 248	94.93 234	94.75 299	95.99 357	86.12 339	91.35 377	98.49 195	93.40 245	97.12 204	97.25 249	86.87 308	99.35 249	95.08 185	98.82 262	98.78 225

test_vis1_n		95.67 210	95.89 204	95.03 282	98.18 213	89.89 266	96.94 134	99.28 31	88.25 346	98.20 125	98.92 69	86.69 309	97.19 396	97.70 58	98.82 262	98.00 312

RRT-MVS		95.78 204	96.25 185	94.35 316	96.68 334	84.47 363	97.72 86	99.11 53	97.23 91	97.27 193	98.72 86	86.39 310	99.79 49	95.49 151	97.67 333	98.80 222

WTY-MVS		93.55 299	93.00 300	95.19 274	97.81 253	87.86 309	93.89 315	96.00 321	89.02 333	94.07 333	95.44 340	86.27 311	99.33 254	87.69 353	96.82 359	98.39 266

CDS-MVSNet		94.88 249	94.12 278	97.14 164	97.64 287	93.57 181	93.96 313	97.06 298	90.05 321	96.30 263	96.55 293	86.10 312	99.47 204	90.10 320	99.31 201	98.40 264
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
1112_ss		94.12 281	93.42 292	96.23 226	98.59 164	90.85 252	94.24 295	98.85 127	85.49 372	92.97 364	94.94 347	86.01 313	99.64 149	91.78 279	97.92 317	98.20 290

dmvs_testset		87.30 380	86.99 377	88.24 396	96.71 333	77.48 407	94.68 281	86.81 413	92.64 276	89.61 401	87.01 415	85.91 314	93.12 416	61.04 420	88.49 412	94.13 403

miper_enhance_ethall		93.14 310	92.78 307	94.20 322	93.65 407	85.29 349	89.97 397	97.85 261	85.05 378	96.15 274	94.56 354	85.74 315	99.14 292	93.74 240	98.34 300	98.17 294

ttmdpeth		94.05 285	94.15 277	93.75 330	95.81 367	85.32 347	96.00 199	94.93 347	92.07 284	94.19 328	99.09 53	85.73 316	96.41 408	90.98 293	98.52 288	99.53 57

new_pmnet		92.34 321	91.69 326	94.32 318	96.23 346	89.16 281	92.27 361	92.88 369	84.39 388	95.29 303	96.35 307	85.66 317	96.74 406	84.53 384	97.56 338	97.05 357

Syy-MVS		92.09 327	91.80 324	92.93 355	95.19 384	82.65 377	92.46 354	91.35 386	90.67 312	91.76 383	87.61 413	85.64 318	98.50 364	94.73 203	96.84 357	97.65 337

alignmvs		96.01 195	95.52 217	97.50 134	97.77 266	94.71 133	96.07 193	96.84 305	97.48 77	96.78 232	94.28 361	85.50 319	99.40 230	96.22 112	98.73 272	98.40 264

lessismore_v0				97.05 173	99.36 48	92.12 223		84.07 416		98.77 70	98.98 62	85.36 320	99.74 83	97.34 69	99.37 180	99.30 127

HY-MVS	91.43 15	92.58 317	91.81 323	94.90 290	96.49 339	88.87 286	97.31 112	94.62 350	85.92 368	90.50 391	96.84 276	85.05 321	99.40 230	83.77 389	95.78 383	96.43 380

EPNet		93.72 293	92.62 312	97.03 176	87.61 424	92.25 216	96.27 176	91.28 388	96.74 104	87.65 410	97.39 237	85.00 322	99.64 149	92.14 270	99.48 151	99.20 150
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_lstm_enhance		94.81 252	94.80 246	94.85 293	96.16 350	86.45 335	91.14 384	98.20 230	93.49 243	97.03 214	97.37 241	84.97 323	99.26 272	95.28 168	99.56 116	98.83 218

Test_1112_low_res		93.53 300	92.86 302	95.54 262	98.60 162	88.86 287	92.75 344	98.69 169	82.66 392	92.65 372	96.92 272	84.75 324	99.56 177	90.94 295	97.76 325	98.19 291

MVS-HIRNet		88.40 370	90.20 351	82.99 400	97.01 325	60.04 425	93.11 338	85.61 415	84.45 387	88.72 406	99.09 53	84.72 325	98.23 382	82.52 393	96.59 368	90.69 415

K. test v3		96.44 178	96.28 184	96.95 179	99.41 40	91.53 239	97.65 91	90.31 399	98.89 24	98.93 53	99.36 23	84.57 326	99.92 6	97.81 49	99.56 116	99.39 110

test_cas_vis1_n_1920		95.34 227	95.67 211	94.35 316	98.21 207	86.83 331	95.61 230	99.26 33	90.45 315	98.17 130	98.96 65	84.43 327	98.31 378	96.74 92	99.17 220	97.90 318

h-mvs33		96.29 183	95.63 214	98.26 72	98.50 178	96.11 77	96.90 136	97.09 296	96.58 110	97.21 197	98.19 158	84.14 328	99.78 53	95.89 130	96.17 377	98.89 209

hse-mvs2		95.77 205	95.09 227	97.79 109	97.84 249	95.51 99	95.66 224	95.43 338	96.58 110	97.21 197	96.16 313	84.14 328	99.54 184	95.89 130	96.92 353	98.32 275

MonoMVSNet		93.30 306	93.96 284	91.33 381	94.14 402	81.33 389	97.68 89	96.69 313	95.38 178	96.32 259	98.42 121	84.12 330	96.76 405	90.78 301	92.12 405	95.89 386

DIV-MVS_self_test		94.73 253	94.64 252	95.01 283	95.86 363	87.00 327	91.33 378	98.08 248	93.34 248	97.10 206	97.34 243	84.02 331	99.31 259	95.15 179	99.55 122	98.72 234

cl____		94.73 253	94.64 252	95.01 283	95.85 364	87.00 327	91.33 378	98.08 248	93.34 248	97.10 206	97.33 244	84.01 332	99.30 262	95.14 180	99.56 116	98.71 237

Vis-MVSNet (Re-imp)		95.11 238	94.85 241	95.87 245	99.12 91	89.17 280	97.54 104	94.92 348	96.50 115	96.58 245	97.27 247	83.64 333	99.48 202	88.42 345	99.67 83	98.97 192

FA-MVS(test-final)		94.91 246	94.89 237	94.99 285	97.51 296	88.11 305	98.27 44	95.20 343	92.40 282	96.68 236	98.60 102	83.44 334	99.28 268	93.34 250	98.53 287	97.59 342

dmvs_re		92.08 328	91.27 333	94.51 310	97.16 320	92.79 205	95.65 226	92.64 374	94.11 226	92.74 369	90.98 401	83.41 335	94.44 415	80.72 399	94.07 398	96.29 382

PVSNet_0	81.89 21	84.49 384	83.21 387	88.34 395	95.76 371	74.97 418	83.49 414	92.70 373	78.47 408	87.94 409	86.90 416	83.38 336	96.63 407	73.44 414	66.86 420	93.40 407

mvsmamba		94.91 246	94.41 268	96.40 220	97.65 284	91.30 244	97.92 69	95.32 340	91.50 298	95.54 298	98.38 127	83.06 337	99.68 129	92.46 267	97.84 321	98.23 286

test_fmvs1_n		95.21 233	95.28 219	94.99 285	98.15 220	89.13 283	96.81 141	99.43 23	86.97 359	97.21 197	98.92 69	83.00 338	97.13 397	98.09 38	98.94 247	98.72 234

CMPMVS	73.10 23	92.74 315	91.39 329	96.77 196	93.57 409	94.67 136	94.21 298	97.67 272	80.36 402	93.61 348	96.60 291	82.85 339	97.35 395	84.86 382	98.78 265	98.29 282
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_fmvs1		94.51 269	94.60 256	94.26 321	95.91 359	87.92 307	95.35 247	99.02 82	86.56 363	96.79 228	98.52 110	82.64 340	97.00 400	97.87 46	98.71 273	97.88 320

EU-MVSNet		94.25 275	94.47 264	93.60 334	98.14 222	82.60 379	97.24 117	92.72 372	85.08 377	98.48 92	98.94 67	82.59 341	98.76 337	97.47 66	99.53 130	99.44 100

baseline1		93.14 310	92.64 311	94.62 303	97.34 311	87.20 324	96.67 158	93.02 367	94.71 204	96.51 251	95.83 328	81.64 342	98.60 356	90.00 322	88.06 413	98.07 300

test1111		94.53 268	94.81 245	93.72 331	99.06 100	81.94 384	98.31 39	83.87 417	96.37 121	98.49 90	99.17 45	81.49 343	99.73 89	96.64 93	99.86 28	99.49 75

CVMVSNet		92.33 322	92.79 305	90.95 383	97.26 316	75.84 414	95.29 253	92.33 377	81.86 393	96.27 264	98.19 158	81.44 344	98.46 368	94.23 222	98.29 303	98.55 252

EPNet_dtu		91.39 340	90.75 343	93.31 339	90.48 420	82.61 378	94.80 275	92.88 369	93.39 246	81.74 418	94.90 350	81.36 345	99.11 299	88.28 347	98.87 255	98.21 289
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ECVR-MVS		94.37 274	94.48 263	94.05 326	98.95 115	83.10 374	98.31 39	82.48 419	96.20 129	98.23 123	99.16 46	81.18 346	99.66 143	95.95 126	99.83 42	99.38 112

test_yl		94.40 271	94.00 281	95.59 256	96.95 327	89.52 273	94.75 279	95.55 335	96.18 132	96.79 228	96.14 316	81.09 347	99.18 285	90.75 303	97.77 323	98.07 300

DCV-MVSNet		94.40 271	94.00 281	95.59 256	96.95 327	89.52 273	94.75 279	95.55 335	96.18 132	96.79 228	96.14 316	81.09 347	99.18 285	90.75 303	97.77 323	98.07 300

MIMVSNet		93.42 302	92.86 302	95.10 279	98.17 216	88.19 299	98.13 55	93.69 358	92.07 284	95.04 311	98.21 157	80.95 349	99.03 312	81.42 396	98.06 312	98.07 300

PAPM		87.64 376	85.84 383	93.04 348	96.54 337	84.99 355	88.42 407	95.57 334	79.52 404	83.82 415	93.05 375	80.57 350	98.41 370	62.29 419	92.79 402	95.71 390

HyFIR lowres test		93.72 293	92.65 310	96.91 184	98.93 120	91.81 235	91.23 382	98.52 192	82.69 391	96.46 253	96.52 297	80.38 351	99.90 16	90.36 317	98.79 264	99.03 183

FMVSNet3		95.26 232	94.94 232	96.22 228	96.53 338	90.06 262	95.99 201	97.66 274	94.11 226	97.99 150	97.91 194	80.22 352	99.63 153	94.60 207	99.44 160	98.96 193

RPMNet		94.68 260	94.60 256	94.90 290	95.44 378	88.15 301	96.18 184	98.86 123	97.43 78	94.10 331	98.49 113	79.40 353	99.76 68	95.69 139	95.81 380	96.81 370

LFMVS		95.32 229	94.88 239	96.62 203	98.03 228	91.47 241	97.65 91	90.72 395	99.11 12	97.89 162	98.31 135	79.20 354	99.48 202	93.91 236	99.12 228	98.93 201

ADS-MVSNet2		91.47 339	90.51 348	94.36 315	95.51 376	85.63 342	95.05 266	95.70 328	83.46 389	92.69 370	96.84 276	79.15 355	99.41 228	85.66 373	90.52 407	98.04 308

ADS-MVSNet		90.95 346	90.26 350	93.04 348	95.51 376	82.37 380	95.05 266	93.41 364	83.46 389	92.69 370	96.84 276	79.15 355	98.70 343	85.66 373	90.52 407	98.04 308

MDTV_nov1_ep13_2view						57.28 426	94.89 272		80.59 400	94.02 336		78.66 357		85.50 375		97.82 324

cl22		93.25 308	92.84 304	94.46 312	94.30 397	86.00 340	91.09 386	96.64 315	90.74 309	95.79 287	96.31 308	78.24 358	98.77 335	94.15 225	98.34 300	98.62 245

PatchmatchNet		91.98 331	91.87 321	92.30 369	94.60 394	79.71 396	95.12 259	93.59 363	89.52 327	93.61 348	97.02 264	77.94 359	99.18 285	90.84 298	94.57 397	98.01 311
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												77.80 360				98.06 304

CR-MVSNet		93.29 307	92.79 305	94.78 298	95.44 378	88.15 301	96.18 184	97.20 290	84.94 382	94.10 331	98.57 104	77.67 361	99.39 234	95.17 175	95.81 380	96.81 370

Patchmtry		95.03 243	94.59 258	96.33 222	94.83 391	90.82 253	96.38 169	97.20 290	96.59 109	97.49 182	98.57 104	77.67 361	99.38 237	92.95 261	99.62 92	98.80 222

tpmrst		90.31 349	90.61 347	89.41 391	94.06 403	72.37 422	95.06 265	93.69 358	88.01 348	92.32 378	96.86 274	77.45 363	98.82 330	91.04 291	87.01 414	97.04 358

sam_mvs												77.38 364

patchmatchnet-post											96.84 276	77.36 365	99.42 219

Patchmatch-RL test		94.66 261	94.49 262	95.19 274	98.54 171	88.91 285	92.57 350	98.74 158	91.46 300	98.32 114	97.75 208	77.31 366	98.81 332	96.06 116	99.61 98	97.85 322

tpmvs		90.79 347	90.87 340	90.57 386	92.75 415	76.30 412	95.79 216	93.64 362	91.04 307	91.91 381	96.26 309	77.19 367	98.86 329	89.38 332	89.85 410	96.56 377

test_post											10.87 424	76.83 368	99.07 305

Patchmatch-test		93.60 298	93.25 295	94.63 302	96.14 354	87.47 318	96.04 195	94.50 352	93.57 241	96.47 252	96.97 267	76.50 369	98.61 354	90.67 309	98.41 298	97.81 326

MDTV_nov1_ep13			91.28 332		94.31 396	73.51 420	94.80 275	93.16 366	86.75 362	93.45 354	97.40 233	76.37 370	98.55 360	88.85 338	96.43 369

EMVS		89.06 364	89.22 356	88.61 394	93.00 412	77.34 408	82.91 416	90.92 391	94.64 207	92.63 374	91.81 392	76.30 371	97.02 399	83.83 388	96.90 355	91.48 413

test_post1							94.98 270				10.37 425	76.21 372	99.04 309	89.47 330

GA-MVS		92.83 314	92.15 319	94.87 292	96.97 326	87.27 323	90.03 396	96.12 318	91.83 291	94.05 334	94.57 353	76.01 373	98.97 321	92.46 267	97.34 348	98.36 273

BP-MVS1		95.36 225	94.86 240	96.89 186	98.35 192	91.72 236	96.76 147	95.21 342	96.48 118	96.23 267	97.19 252	75.97 374	99.80 48	97.91 44	99.60 104	99.15 157

PatchT		93.75 292	93.57 290	94.29 320	95.05 387	87.32 322	96.05 194	92.98 368	97.54 75	94.25 326	98.72 86	75.79 375	99.24 278	95.92 128	95.81 380	96.32 381

E-PMN		89.52 361	89.78 353	88.73 393	93.14 410	77.61 406	83.26 415	92.02 379	94.82 201	93.71 344	93.11 369	75.31 376	96.81 402	85.81 370	96.81 360	91.77 412

DeepMVS_CX				77.17 401	90.94 419	85.28 350		74.08 424	52.51 420	80.87 420	88.03 412	75.25 377	70.63 422	59.23 421	84.94 416	75.62 416

GDP-MVS		95.39 224	94.89 237	96.90 185	98.26 202	91.91 231	96.48 164	99.28 31	95.06 192	96.54 250	97.12 257	74.83 378	99.82 36	97.19 75	99.27 207	98.96 193

AUN-MVS		93.95 290	92.69 309	97.74 112	97.80 257	95.38 107	95.57 233	95.46 337	91.26 304	92.64 373	96.10 319	74.67 379	99.55 181	93.72 242	96.97 352	98.30 279

CHOSEN 280x420		89.98 353	89.19 359	92.37 368	95.60 375	81.13 391	86.22 410	97.09 296	81.44 397	87.44 411	93.15 368	73.99 380	99.47 204	88.69 341	99.07 235	96.52 378

thres200		91.00 345	90.42 349	92.77 359	97.47 302	83.98 370	94.01 308	91.18 390	95.12 189	95.44 300	91.21 398	73.93 381	99.31 259	77.76 408	97.63 337	95.01 398

test-LLR		89.97 354	89.90 352	90.16 387	94.24 399	74.98 416	89.89 398	89.06 404	92.02 286	89.97 397	90.77 402	73.92 382	98.57 357	91.88 275	97.36 346	96.92 361

test0.0.03 1		90.11 350	89.21 357	92.83 357	93.89 405	86.87 330	91.74 370	88.74 407	92.02 286	94.71 317	91.14 399	73.92 382	94.48 414	83.75 390	92.94 401	97.16 355

tpm cat1		88.01 374	87.33 374	90.05 390	94.48 395	76.28 413	94.47 287	94.35 354	73.84 417	89.26 403	95.61 335	73.64 384	98.30 379	84.13 385	86.20 415	95.57 394

tfpn200view9		91.55 337	91.00 337	93.21 344	98.02 229	84.35 365	95.70 219	90.79 393	96.26 126	95.90 284	92.13 389	73.62 385	99.42 219	78.85 405	97.74 326	95.85 387

thres400		91.68 336	91.00 337	93.71 332	98.02 229	84.35 365	95.70 219	90.79 393	96.26 126	95.90 284	92.13 389	73.62 385	99.42 219	78.85 405	97.74 326	97.36 350

test_method		66.88 386	66.13 389	69.11 402	62.68 427	25.73 430	49.76 418	96.04 320	14.32 422	64.27 422	91.69 394	73.45 387	88.05 419	76.06 410	66.94 419	93.54 405

thres100view900		91.76 335	91.26 335	93.26 340	98.21 207	84.50 362	96.39 166	90.39 396	96.87 100	96.33 258	93.08 373	73.44 388	99.42 219	78.85 405	97.74 326	95.85 387

thres600view7		92.03 330	91.43 328	93.82 328	98.19 210	84.61 361	96.27 176	90.39 396	96.81 102	96.37 257	93.11 369	73.44 388	99.49 199	80.32 400	97.95 316	97.36 350

MVSTER		94.21 278	93.93 285	95.05 281	95.83 365	86.46 334	95.18 258	97.65 276	92.41 281	97.94 158	98.00 185	72.39 390	99.58 170	96.36 105	99.56 116	99.12 168

JIA-IIPM		91.79 334	90.69 345	95.11 277	93.80 406	90.98 250	94.16 300	91.78 382	96.38 120	90.30 394	99.30 29	72.02 391	98.90 324	88.28 347	90.17 409	95.45 395

tpm		91.08 344	90.85 341	91.75 376	95.33 382	78.09 402	95.03 268	91.27 389	88.75 337	93.53 351	97.40 233	71.24 392	99.30 262	91.25 288	93.87 399	97.87 321

baseline2		89.65 360	88.44 366	93.25 341	95.62 374	82.71 376	93.82 317	85.94 414	88.89 336	87.35 412	92.54 383	71.23 393	99.33 254	86.01 368	94.60 396	97.72 334

CostFormer		89.75 357	89.25 355	91.26 382	94.69 393	78.00 404	95.32 250	91.98 380	81.50 396	90.55 390	96.96 269	71.06 394	98.89 325	88.59 343	92.63 403	96.87 364

FPMVS		89.92 355	88.63 363	93.82 328	98.37 190	96.94 49	91.58 372	93.34 365	88.00 349	90.32 393	97.10 259	70.87 395	91.13 418	71.91 416	96.16 378	93.39 408

EPMVS		89.26 362	88.55 364	91.39 380	92.36 416	79.11 399	95.65 226	79.86 420	88.60 340	93.12 361	96.53 295	70.73 396	98.10 386	90.75 303	89.32 411	96.98 359

FE-MVS		92.95 312	92.22 317	95.11 277	97.21 318	88.33 297	98.54 23	93.66 361	89.91 323	96.21 269	98.14 162	70.33 397	99.50 194	87.79 351	98.24 305	97.51 345

tmp_tt		57.23 388	62.50 391	41.44 405	34.77 428	49.21 429	83.93 413	60.22 427	15.31 421	71.11 421	79.37 418	70.09 398	44.86 424	64.76 418	82.93 418	30.25 420

ET-MVSNet_ETH3D		91.12 341	89.67 354	95.47 265	96.41 341	89.15 282	91.54 373	90.23 400	89.07 332	86.78 414	92.84 378	69.39 399	99.44 215	94.16 224	96.61 367	97.82 324

dp		88.08 373	88.05 368	88.16 398	92.85 413	68.81 424	94.17 299	92.88 369	85.47 373	91.38 386	96.14 316	68.87 400	98.81 332	86.88 365	83.80 417	96.87 364

tpm2		88.47 369	87.69 372	90.79 384	94.98 388	77.34 408	95.09 261	91.83 381	77.51 412	89.40 402	96.41 302	67.83 401	98.73 339	83.58 391	92.60 404	96.29 382

pmmvs3		90.00 352	88.90 362	93.32 338	94.20 401	85.34 346	91.25 381	92.56 376	78.59 407	93.82 339	95.17 342	67.36 402	98.69 345	89.08 336	98.03 313	95.92 385

thisisatest0515		90.43 348	89.18 360	94.17 324	97.07 324	85.44 345	89.75 402	87.58 409	88.28 345	93.69 346	91.72 393	65.27 403	99.58 170	90.59 310	98.67 276	97.50 347

tttt0517		93.31 305	92.56 313	95.57 258	98.71 147	87.86 309	97.44 107	87.17 411	95.79 156	97.47 186	96.84 276	64.12 404	99.81 41	96.20 113	99.32 198	99.02 186

thisisatest0530		92.71 316	91.76 325	95.56 260	98.42 187	88.23 298	96.03 196	87.35 410	94.04 229	96.56 247	95.47 338	64.03 405	99.77 63	94.78 200	99.11 229	98.68 241

FMVSNet5		93.39 303	92.35 314	96.50 212	95.83 365	90.81 255	97.31 112	98.27 221	92.74 274	96.27 264	98.28 144	62.23 406	99.67 137	90.86 297	99.36 183	99.03 183

WBMVS		91.11 342	90.72 344	92.26 370	95.99 357	77.98 405	91.47 374	95.90 325	91.63 293	95.90 284	96.45 300	59.60 407	99.46 207	89.97 323	99.59 107	99.33 121

UBG		88.29 371	87.17 375	91.63 377	96.08 355	78.21 401	91.61 371	91.50 385	89.67 326	89.71 400	88.97 410	59.01 408	98.91 323	81.28 397	96.72 364	97.77 329

IB-MVS	85.98 20	88.63 368	86.95 379	93.68 333	95.12 386	84.82 360	90.85 388	90.17 401	87.55 352	88.48 407	91.34 397	58.01 409	99.59 168	87.24 363	93.80 400	96.63 376
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		91.89 332	91.45 327	93.21 344	89.01 421	84.87 357	95.82 215	95.05 345	91.50 298	98.75 72	99.19 38	57.56 410	95.11 410	97.78 52	98.37 299	99.64 35

testing91		89.67 359	88.55 364	93.04 348	95.90 360	81.80 385	92.71 348	93.71 357	93.71 236	90.18 395	90.15 406	57.11 411	99.22 282	87.17 364	96.32 373	98.12 296

gg-mvs-nofinetune		88.28 372	86.96 378	92.23 371	92.84 414	84.44 364	98.19 52	74.60 422	99.08 14	87.01 413	99.47 13	56.93 412	98.23 382	78.91 404	95.61 386	94.01 404

KD-MVS_2432*1600		88.93 365	87.74 370	92.49 364	88.04 422	81.99 382	89.63 403	95.62 331	91.35 302	95.06 308	93.11 369	56.58 413	98.63 352	85.19 378	95.07 389	96.85 366

miper_refine_blended		88.93 365	87.74 370	92.49 364	88.04 422	81.99 382	89.63 403	95.62 331	91.35 302	95.06 308	93.11 369	56.58 413	98.63 352	85.19 378	95.07 389	96.85 366

GG-mvs-BLEND				90.60 385	91.00 418	84.21 368	98.23 46	72.63 425		82.76 416	84.11 417	56.14 415	96.79 403	72.20 415	92.09 406	90.78 414

TESTMET0.1,1		87.20 381	86.57 381	89.07 392	93.62 408	72.84 421	89.89 398	87.01 412	85.46 374	89.12 404	90.20 405	56.00 416	97.72 392	90.91 296	96.92 353	96.64 374

reproduce_monomvs		92.05 329	92.26 316	91.43 379	95.42 380	75.72 415	95.68 222	97.05 299	94.47 213	97.95 157	98.35 130	55.58 417	99.05 307	96.36 105	99.44 160	99.51 64

testing99		89.21 363	88.04 369	92.70 361	95.78 369	81.00 392	92.65 349	92.03 378	93.20 255	89.90 399	90.08 408	55.25 418	99.14 292	87.54 357	95.95 379	97.97 313

UWE-MVS		87.57 378	86.72 380	90.13 389	95.21 383	73.56 419	91.94 367	83.78 418	88.73 339	93.00 363	92.87 377	55.22 419	99.25 274	81.74 394	97.96 315	97.59 342

test2506		89.86 356	89.16 361	91.97 374	98.95 115	76.83 411	98.54 23	61.07 426	96.20 129	97.07 212	99.16 46	55.19 420	99.69 124	96.43 102	99.83 42	99.38 112

testing11		88.93 365	87.63 373	92.80 358	95.87 362	81.49 387	92.48 353	91.54 384	91.62 294	88.27 408	90.24 404	55.12 421	99.11 299	87.30 362	96.28 375	97.81 326

test-mter		87.92 375	87.17 375	90.16 387	94.24 399	74.98 416	89.89 398	89.06 404	86.44 364	89.97 397	90.77 402	54.96 422	98.57 357	91.88 275	97.36 346	96.92 361

ETVMVS		87.62 377	85.75 384	93.22 343	96.15 353	83.26 373	92.94 340	90.37 398	91.39 301	90.37 392	88.45 411	51.93 423	98.64 351	73.76 412	96.38 371	97.75 330

testing222		87.35 379	85.50 386	92.93 355	95.79 368	82.83 375	92.40 359	90.10 402	92.80 273	88.87 405	89.02 409	48.34 424	98.70 343	75.40 411	96.74 362	97.27 354

myMVS_eth3d		87.16 382	85.61 385	91.82 375	95.19 384	79.32 397	92.46 354	91.35 386	90.67 312	91.76 383	87.61 413	41.96 425	98.50 364	82.66 392	96.84 357	97.65 337

testing3		89.72 358	88.26 367	94.10 325	97.66 282	84.30 367	94.80 275	88.25 408	94.66 205	95.07 307	92.51 384	41.15 426	99.43 217	91.81 278	98.44 296	98.55 252

dongtai		63.43 387	63.37 390	63.60 403	83.91 425	53.17 427	85.14 411	43.40 429	77.91 411	80.96 419	79.17 419	36.36 427	77.10 421	37.88 422	45.63 421	60.54 418

kuosan		54.81 389	54.94 392	54.42 404	74.43 426	50.03 428	84.98 412	44.27 428	61.80 419	62.49 423	70.43 420	35.16 428	58.04 423	19.30 423	41.61 422	55.19 419

test123		12.59 391	15.49 394	3.87 406	6.07 429	2.55 431	90.75 390	2.59 431	2.52 424	5.20 426	13.02 423	4.96 429	1.85 426	5.20 424	9.09 423	7.23 421

testmvs		12.33 392	15.23 395	3.64 407	5.77 430	2.23 432	88.99 405	3.62 430	2.30 425	5.29 425	13.09 422	4.52 430	1.95 425	5.16 425	8.32 424	6.75 422

mmdepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

monomultidepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

test_blank		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet_test		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

DCPMVS		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

sosnet-low-res		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

sosnet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uncertanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

Regformer		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

ab-mvs-re		7.91 394	10.55 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	94.94 347	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

WAC-MVS						79.32 397								85.41 376

FOURS1					99.59 17	98.20 8	99.03 8	99.25 34	98.96 22	98.87 59

MSC_two_6792asdad				98.22 77	97.75 269	95.34 112		98.16 240					99.75 74	95.87 132	99.51 140	99.57 46

No_MVS				98.22 77	97.75 269	95.34 112		98.16 240					99.75 74	95.87 132	99.51 140	99.57 46

eth-test2					0.00 431

eth-test					0.00 431

IU-MVS					99.22 66	95.40 105		98.14 243	85.77 371	98.36 106				95.23 172	99.51 140	99.49 75

save fliter					98.48 181	94.71 133	94.53 286	98.41 205	95.02 195

test_0728_SECOND				98.25 75	99.23 63	95.49 103	96.74 149	98.89 111					99.75 74	95.48 155	99.52 135	99.53 57

GSMVS																98.06 304

test_part2					99.03 107	96.07 78				98.08 141

MTGPA								98.73 159

MTMP							96.55 160	74.60 422

gm-plane-assit					91.79 417	71.40 423			81.67 394		90.11 407		98.99 315	84.86 382

test9_res														91.29 285	98.89 254	99.00 187

agg_prior2														90.34 318	98.90 251	99.10 175

agg_prior					97.80 257	94.96 128		98.36 212		93.49 352			99.53 186

test_prior4						95.38 107	93.61 325

test_prior				97.46 140	97.79 262	94.26 157		98.42 204					99.34 252			98.79 224

旧先验2							93.35 332		77.95 410	95.77 291			98.67 349	90.74 306

新几何2							93.43 328

无先验							93.20 336	97.91 257	80.78 399				99.40 230	87.71 352		97.94 316

原ACMM2							92.82 342

testdata2													99.46 207	87.84 350

testdata1							92.77 343		93.78 234

plane_prior7					98.70 149	94.67 136

plane_prior5								98.75 156					99.46 207	92.59 264	99.20 215	99.28 134

plane_prior4											96.77 282

plane_prior3						94.51 143			95.29 182	96.16 272

plane_prior2							96.50 162		96.36 122

plane_prior1					98.49 179

plane_prior						94.29 153	95.42 238		94.31 219						98.93 249

n2								0.00 432

nn								0.00 432

door-mid								98.17 236

test11								98.08 248

door								97.81 266

HQP5-MVS						92.47 212

HQP-NCC					97.85 244		94.26 291		93.18 257	92.86 366

ACMP_Plane					97.85 244		94.26 291		93.18 257	92.86 366

BP-MVS														90.51 313

HQP4-MVS										92.87 365			99.23 280			99.06 180

HQP3-MVS								98.43 201							98.74 269

NP-MVS					98.14 222	93.72 174					95.08 343

ACMMP++_ref															99.52 135

ACMMP++															99.55 122

High-resolution multi-view benchmark