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 2	99.97 1	99.97 1	99.95 1	99.74 1	99.98 1	99.56 1	100.00 1	99.85 3

pmmvs6		99.07 4	99.24 4	98.56 48	99.81 2	96.38 62	98.87 9	99.30 26	99.01 16	99.63 11	99.66 3	99.27 2	99.68 124	97.75 51	99.89 26	99.62 36

UniMVSNet_ETH3D		99.12 3	99.28 3	98.65 42	99.77 5	96.34 65	99.18 5	99.20 34	99.67 2	99.73 3	99.65 5	99.15 3	99.86 24	97.22 68	99.92 15	99.77 12

test_fmvsmconf0.01_n		98.57 17	98.74 16	98.06 88	99.39 47	94.63 136	96.70 145	99.82 1	95.44 166	99.64 10	99.52 7	98.96 4	99.74 77	99.38 3	99.86 31	99.81 8

XVG-OURS-SEG-HR		97.38 117	97.07 131	98.30 68	99.01 110	97.41 34	94.66 269	99.02 74	95.20 174	98.15 130	97.52 216	98.83 5	98.43 351	94.87 184	96.41 353	99.07 173

ACMH	93.61 9	98.44 25	98.76 13	97.51 128	99.43 40	93.54 179	98.23 46	99.05 65	97.40 79	99.37 23	99.08 51	98.79 6	99.47 197	97.74 52	99.71 75	99.50 63
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mvs_tets		98.90 5	98.94 6	98.75 31	99.69 10	96.48 60	98.54 23	99.22 31	96.23 121	99.71 4	99.48 10	98.77 7	99.93 3	98.89 17	99.95 5	99.84 5

test_fmvsmconf0.1_n		98.41 27	98.54 25	98.03 93	99.16 83	94.61 137	96.18 174	99.73 3	95.05 182	99.60 14	99.34 25	98.68 8	99.72 88	99.21 7	99.85 38	99.76 17

LTVRE_ROB	96.88 1	99.18 2	99.34 2	98.72 37	99.71 9	96.99 44	99.69 2	99.57 14	99.02 15	99.62 12	99.36 21	98.53 9	99.52 182	98.58 29	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 32	98.41 32	97.99 96	98.94 116	94.60 138	96.00 189	99.64 12	94.99 185	99.43 19	99.18 39	98.51 10	99.71 104	99.13 10	99.84 40	99.67 28

TransMVSNet (Re)		98.38 28	98.67 18	97.51 128	99.51 31	93.39 185	98.20 51	98.87 110	98.23 40	99.48 16	99.27 30	98.47 11	99.55 174	96.52 91	99.53 125	99.60 38

pm-mvs1		98.47 24	98.67 18	97.86 104	99.52 30	94.58 139	98.28 42	99.00 83	97.57 67	99.27 29	99.22 34	98.32 12	99.50 187	97.09 75	99.75 66	99.50 63

jajsoiax		98.77 9	98.79 12	98.74 34	99.66 13	96.48 60	98.45 31	99.12 48	95.83 147	99.67 7	99.37 19	98.25 13	99.92 5	98.77 20	99.94 8	99.82 6

sd_testset		97.97 52	98.12 41	97.51 128	99.41 43	93.44 182	97.96 63	98.25 213	98.58 28	98.78 65	99.39 16	98.21 14	99.56 170	92.65 252	99.86 31	99.52 59

ACMH+	93.58 10	98.23 36	98.31 35	97.98 97	99.39 47	95.22 118	97.55 92	99.20 34	98.21 41	99.25 31	98.51 105	98.21 14	99.40 222	94.79 188	99.72 72	99.32 116

HPM-MVS_fast		98.32 30	98.13 40	98.88 23	99.54 26	97.48 30	98.35 35	99.03 72	95.88 143	97.88 159	98.22 146	98.15 16	99.74 77	96.50 92	99.62 93	99.42 98

wuyk23d		93.25 296	95.20 213	87.40 377	96.07 345	95.38 105	97.04 122	94.97 333	95.33 169	99.70 6	98.11 158	98.14 17	91.94 395	77.76 388	99.68 83	74.89 395

ACMM	93.33 11	98.05 48	97.79 73	98.85 24	99.15 86	97.55 26	96.68 146	98.83 126	95.21 173	98.36 104	98.13 154	98.13 18	99.62 151	96.04 110	99.54 121	99.39 105
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HPM-MVS		98.11 43	97.83 69	98.92 21	99.42 42	97.46 31	98.57 20	99.05 65	95.43 167	97.41 184	97.50 218	97.98 19	99.79 45	95.58 140	99.57 109	99.50 63
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
testgi		96.07 184	96.50 168	94.80 288	99.26 60	87.69 306	95.96 194	98.58 178	95.08 180	98.02 146	96.25 298	97.92 20	97.60 375	88.68 328	98.74 262	99.11 166

LPG-MVS_test		97.94 62	97.67 86	98.74 34	99.15 86	97.02 42	97.09 119	99.02 74	95.15 177	98.34 107	98.23 143	97.91 21	99.70 112	94.41 203	99.73 68	99.50 63

LGP-MVS_train				98.74 34	99.15 86	97.02 42		99.02 74	95.15 177	98.34 107	98.23 143	97.91 21	99.70 112	94.41 203	99.73 68	99.50 63

SED-MVS		97.94 62	97.90 59	98.07 86	99.22 69	95.35 108	96.79 136	98.83 126	96.11 127	99.08 40	98.24 141	97.87 23	99.72 88	95.44 149	99.51 135	99.14 156

test_241102_ONE					99.22 69	95.35 108		98.83 126	96.04 132	99.08 40	98.13 154	97.87 23	99.33 245

SDMVSNet		97.97 52	98.26 39	97.11 163	99.41 43	92.21 214	96.92 127	98.60 173	98.58 28	98.78 65	99.39 16	97.80 25	99.62 151	94.98 182	99.86 31	99.52 59

testf1		98.57 17	98.45 29	98.93 18	99.79 3	98.78 2	97.69 81	99.42 21	97.69 63	98.92 51	98.77 79	97.80 25	99.25 264	96.27 100	99.69 79	98.76 221

APD_test2		98.57 17	98.45 29	98.93 18	99.79 3	98.78 2	97.69 81	99.42 21	97.69 63	98.92 51	98.77 79	97.80 25	99.25 264	96.27 100	99.69 79	98.76 221

SD-MVS		97.37 119	97.70 81	96.35 214	98.14 216	95.13 122	96.54 151	98.92 99	95.94 139	99.19 34	98.08 160	97.74 28	95.06 389	95.24 161	99.54 121	98.87 209
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 81	97.70 81	98.16 79	98.78 135	95.72 86	96.23 172	99.02 74	93.92 220	98.62 76	98.99 57	97.69 29	99.62 151	96.18 105	99.87 29	99.15 153
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 21	98.62 22	98.32 65	99.22 69	95.66 91	97.90 68	99.08 57	98.31 36	99.02 43	98.74 82	97.68 30	99.61 158	97.77 50	99.85 38	99.70 26

ANet_high		98.31 31	98.94 6	96.41 213	99.33 54	89.64 263	97.92 67	99.56 16	99.27 6	99.66 9	99.50 9	97.67 31	99.83 33	97.55 59	99.98 2	99.77 12

test_fmvsmvis_n_1920		98.08 45	98.47 26	96.93 177	99.03 108	93.29 187	96.32 164	99.65 9	95.59 158	99.71 4	99.01 54	97.66 32	99.60 160	99.44 2	99.83 43	97.90 305

casdiffmvs_mvg		97.83 78	98.11 42	97.00 174	98.57 162	92.10 222	95.97 192	99.18 37	97.67 66	99.00 46	98.48 110	97.64 33	99.50 187	96.96 80	99.54 121	99.40 101
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
canonicalmvs		97.23 126	97.21 124	97.30 150	97.65 276	94.39 145	97.84 71	99.05 65	97.42 75	96.68 231	93.85 352	97.63 34	99.33 245	96.29 99	98.47 284	98.18 283

GeoE		97.75 87	97.70 81	97.89 102	98.88 123	94.53 140	97.10 118	98.98 89	95.75 151	97.62 170	97.59 211	97.61 35	99.77 57	96.34 98	99.44 155	99.36 113

TranMVSNet+NR-MVSNet		98.33 29	98.30 37	98.43 57	99.07 101	95.87 81	96.73 143	99.05 65	98.67 24	98.84 59	98.45 111	97.58 36	99.88 20	96.45 94	99.86 31	99.54 54

cdsmvs_eth3d_5k		24.22 365	32.30 368	0.00 384	0.00 406	0.00 409	0.00 395	98.10 237	0.00 402	0.00 403	95.06 333	97.54 37	0.00 403	0.00 402	0.00 401	0.00 399

ACMP	92.54 13	97.47 111	97.10 128	98.55 49	99.04 107	96.70 51	96.24 171	98.89 102	93.71 225	97.97 151	97.75 199	97.44 38	99.63 146	93.22 245	99.70 78	99.32 116
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_djsdf		98.73 11	98.74 16	98.69 39	99.63 15	96.30 67	98.67 15	99.02 74	96.50 109	99.32 26	99.44 14	97.43 39	99.92 5	98.73 22	99.95 5	99.86 2

TDRefinement		98.90 5	98.86 8	99.02 6	99.54 26	98.06 8	99.34 4	99.44 19	98.85 21	99.00 46	99.20 35	97.42 40	99.59 161	97.21 69	99.76 59	99.40 101

anonymousdsp		98.72 14	98.63 20	98.99 10	99.62 16	97.29 37	98.65 19	99.19 36	95.62 156	99.35 25	99.37 19	97.38 41	99.90 14	98.59 28	99.91 18	99.77 12

PS-CasMVS		98.73 11	98.85 10	98.39 61	99.55 23	95.47 102	98.49 28	99.13 47	99.22 8	99.22 33	98.96 61	97.35 42	99.92 5	97.79 49	99.93 11	99.79 10

COLMAP_ROB	94.48 6	98.25 35	98.11 42	98.64 43	99.21 76	97.35 35	97.96 63	99.16 39	98.34 35	98.78 65	98.52 103	97.32 43	99.45 204	94.08 217	99.67 85	99.13 158
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 92	97.79 73	97.40 145	99.06 102	93.52 180	95.96 194	98.97 92	94.55 201	98.82 61	98.76 81	97.31 44	99.29 256	97.20 71	99.44 155	99.38 107

XXY-MVS		97.54 106	97.70 81	97.07 168	99.46 37	92.21 214	97.22 111	99.00 83	94.93 188	98.58 81	98.92 66	97.31 44	99.41 220	94.44 201	99.43 163	99.59 39

PEN-MVS		98.75 10	98.85 10	98.44 55	99.58 19	95.67 90	98.45 31	99.15 43	99.33 5	99.30 27	99.00 55	97.27 46	99.92 5	97.64 57	99.92 15	99.75 19

DTE-MVSNet		98.79 8	98.86 8	98.59 46	99.55 23	96.12 72	98.48 30	99.10 51	99.36 4	99.29 28	99.06 52	97.27 46	99.93 3	97.71 53	99.91 18	99.70 26

ZNCC-MVS		97.92 66	97.62 95	98.83 25	99.32 56	97.24 39	97.45 99	98.84 120	95.76 149	96.93 217	97.43 222	97.26 48	99.79 45	96.06 107	99.53 125	99.45 86

MP-MVS-pluss		97.69 92	97.36 115	98.70 38	99.50 34	96.84 47	95.38 231	98.99 86	92.45 267	98.11 133	98.31 125	97.25 49	99.77 57	96.60 88	99.62 93	99.48 77
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		97.89 72	97.63 93	98.67 40	99.35 52	96.84 47	96.36 161	98.79 136	95.07 181	97.88 159	98.35 121	97.24 50	99.72 88	96.05 109	99.58 106	99.45 86

Effi-MVS+		96.19 180	96.01 187	96.71 193	97.43 294	92.19 218	96.12 180	99.10 51	95.45 164	93.33 343	94.71 340	97.23 51	99.56 170	93.21 246	97.54 325	98.37 260

tt0805		97.44 113	97.56 102	97.11 163	99.55 23	96.36 63	98.66 18	95.66 319	98.31 36	97.09 205	95.45 327	97.17 52	98.50 346	98.67 25	97.45 331	96.48 358

PGM-MVS		97.88 73	97.52 106	98.96 13	99.20 78	97.62 21	97.09 119	99.06 61	95.45 164	97.55 172	97.94 180	97.11 53	99.78 48	94.77 191	99.46 151	99.48 77

test_0728_THIRD									96.62 99	98.40 98	98.28 134	97.10 54	99.71 104	95.70 128	99.62 93	99.58 40

APD-MVS_3200maxsize		98.13 42	97.90 59	98.79 29	98.79 132	97.31 36	97.55 92	98.92 99	97.72 59	98.25 118	98.13 154	97.10 54	99.75 68	95.44 149	99.24 206	99.32 116

OPM-MVS		97.54 106	97.25 121	98.41 59	99.11 95	96.61 56	95.24 242	98.46 187	94.58 200	98.10 135	98.07 162	97.09 56	99.39 226	95.16 167	99.44 155	99.21 141
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HFP-MVS		97.94 62	97.64 91	98.83 25	99.15 86	97.50 29	97.59 89	98.84 120	96.05 130	97.49 177	97.54 214	97.07 57	99.70 112	95.61 137	99.46 151	99.30 121

DVP-MVS		97.78 85	97.65 88	98.16 79	99.24 64	95.51 97	96.74 139	98.23 216	95.92 140	98.40 98	98.28 134	97.06 58	99.71 104	95.48 145	99.52 130	99.26 133
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 64	95.51 97	96.89 129	98.89 102	95.92 140	98.64 74	98.31 125	97.06 58

test_fmvsm_n_1920		98.08 45	98.29 38	97.43 141	98.88 123	93.95 164	96.17 178	99.57 14	95.66 153	99.52 15	98.71 85	97.04 60	99.64 142	99.21 7	99.87 29	98.69 230

casdiffmvs		97.50 108	97.81 71	96.56 203	98.51 171	91.04 242	95.83 203	99.09 56	97.23 85	98.33 110	98.30 129	97.03 61	99.37 234	96.58 90	99.38 173	99.28 128
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 50	97.76 78	98.79 29	99.43 40	97.21 41	97.15 114	98.90 101	96.58 104	98.08 138	97.87 188	97.02 62	99.76 62	95.25 160	99.59 104	99.40 101
Skip Steuart: Steuart Systems R&D Blog.
PC_three_1452									87.24 332	98.37 101	97.44 221	97.00 63	96.78 385	92.01 260	99.25 203	99.21 141

EC-MVSNet		97.90 71	97.94 58	97.79 108	98.66 149	95.14 121	98.31 39	99.66 8	97.57 67	95.95 268	97.01 255	96.99 64	99.82 35	97.66 56	99.64 90	98.39 258

DVP-MVS++		97.96 54	97.90 59	98.12 84	97.75 264	95.40 103	99.03 7	98.89 102	96.62 99	98.62 76	98.30 129	96.97 65	99.75 68	95.70 128	99.25 203	99.21 141

OPU-MVS				97.64 119	98.01 225	95.27 113	96.79 136				97.35 233	96.97 65	98.51 345	91.21 278	99.25 203	99.14 156

RE-MVS-def			97.88 64		98.81 128	98.05 9	97.55 92	98.86 113	97.77 54	98.20 122	98.07 162	96.94 67		95.49 142	99.20 208	99.26 133

APDe-MVS		98.14 39	98.03 50	98.47 54	98.72 140	96.04 75	98.07 58	99.10 51	95.96 137	98.59 80	98.69 87	96.94 67	99.81 37	96.64 86	99.58 106	99.57 47
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test_one_0601					99.05 106	95.50 100		98.87 110	97.21 86	98.03 145	98.30 129	96.93 69

GST-MVS		97.82 81	97.49 110	98.81 27	99.23 66	97.25 38	97.16 113	98.79 136	95.96 137	97.53 173	97.40 224	96.93 69	99.77 57	95.04 176	99.35 182	99.42 98

test_241102_TWO								98.83 126	96.11 127	98.62 76	98.24 141	96.92 71	99.72 88	95.44 149	99.49 142	99.49 71

LCM-MVSNet-Re		97.33 122	97.33 117	97.32 149	98.13 219	93.79 170	96.99 124	99.65 9	96.74 97	99.47 17	98.93 65	96.91 72	99.84 30	90.11 306	99.06 231	98.32 267

VPA-MVSNet		98.27 33	98.46 27	97.70 114	99.06 102	93.80 169	97.76 76	99.00 83	98.40 33	99.07 42	98.98 58	96.89 73	99.75 68	97.19 72	99.79 53	99.55 53

ACMMP		98.05 48	97.75 80	98.93 18	99.23 66	97.60 22	98.09 57	98.96 93	95.75 151	97.91 156	98.06 167	96.89 73	99.76 62	95.32 157	99.57 109	99.43 97
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 44	98.01 52	98.32 65	98.45 180	96.69 52	98.52 26	99.69 5	98.07 46	96.07 264	97.19 243	96.88 75	99.86 24	97.50 61	99.73 68	98.41 255

PMVS	89.60 17	96.71 157	96.97 137	95.95 233	99.51 31	97.81 16	97.42 103	97.49 275	97.93 50	95.95 268	98.58 97	96.88 75	96.91 382	89.59 314	99.36 177	93.12 387
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
region2R		97.92 66	97.59 99	98.92 21	99.22 69	97.55 26	97.60 87	98.84 120	96.00 135	97.22 189	97.62 209	96.87 77	99.76 62	95.48 145	99.43 163	99.46 82

CP-MVS		97.92 66	97.56 102	98.99 10	98.99 111	97.82 15	97.93 66	98.96 93	96.11 127	96.89 220	97.45 220	96.85 78	99.78 48	95.19 163	99.63 92	99.38 107

DPE-MVS		97.64 97	97.35 116	98.50 51	98.85 126	96.18 69	95.21 244	98.99 86	95.84 146	98.78 65	98.08 160	96.84 79	99.81 37	93.98 223	99.57 109	99.52 59
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_0402		97.84 77	97.97 55	97.47 137	99.19 80	94.07 159	96.71 144	98.73 148	98.66 25	98.56 82	98.41 115	96.84 79	99.69 119	94.82 186	99.81 48	98.64 234

CS-MVS-test		97.91 69	97.84 66	98.14 82	98.52 169	96.03 77	98.38 34	99.67 6	98.11 44	95.50 285	96.92 261	96.81 81	99.87 22	96.87 83	99.76 59	98.51 248

ACMMPR		97.95 58	97.62 95	98.94 15	99.20 78	97.56 25	97.59 89	98.83 126	96.05 130	97.46 182	97.63 208	96.77 82	99.76 62	95.61 137	99.46 151	99.49 71

Vis-MVSNet		98.27 33	98.34 34	98.07 86	99.33 54	95.21 120	98.04 60	99.46 17	97.32 82	97.82 166	99.11 47	96.75 83	99.86 24	97.84 46	99.36 177	99.15 153
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
Fast-Effi-MVS+		95.49 208	95.07 219	96.75 191	97.67 274	92.82 196	94.22 284	98.60 173	91.61 279	93.42 341	92.90 362	96.73 84	99.70 112	92.60 253	97.89 308	97.74 314

baseline		97.44 113	97.78 77	96.43 209	98.52 169	90.75 249	96.84 130	99.03 72	96.51 108	97.86 163	98.02 171	96.67 85	99.36 237	97.09 75	99.47 148	99.19 146

SR-MVS		98.00 51	97.66 87	99.01 8	98.77 136	97.93 11	97.38 104	98.83 126	97.32 82	98.06 141	97.85 189	96.65 86	99.77 57	95.00 179	99.11 222	99.32 116

tfpnnormal		97.72 90	97.97 55	96.94 176	99.26 60	92.23 213	97.83 72	98.45 188	98.25 39	99.13 38	98.66 89	96.65 86	99.69 119	93.92 225	99.62 93	98.91 199

DeepPCF-MVS	94.58 5	96.90 142	96.43 170	98.31 67	97.48 288	97.23 40	92.56 334	98.60 173	92.84 259	98.54 83	97.40 224	96.64 88	98.78 318	94.40 205	99.41 170	98.93 195

MVS_111021_LR		96.82 148	96.55 162	97.62 120	98.27 195	95.34 110	93.81 306	98.33 206	94.59 199	96.56 239	96.63 279	96.61 89	98.73 323	94.80 187	99.34 185	98.78 217

Gipuma		98.07 47	98.31 35	97.36 147	99.76 7	96.28 68	98.51 27	99.10 51	98.76 23	96.79 223	99.34 25	96.61 89	98.82 314	96.38 96	99.50 139	96.98 338
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
SR-MVS-dyc-post		98.14 39	97.84 66	99.02 6	98.81 128	98.05 9	97.55 92	98.86 113	97.77 54	98.20 122	98.07 162	96.60 91	99.76 62	95.49 142	99.20 208	99.26 133

MVS_111021_HR		96.73 154	96.54 164	97.27 152	98.35 188	93.66 176	93.42 316	98.36 202	94.74 191	96.58 237	96.76 273	96.54 92	98.99 300	94.87 184	99.27 201	99.15 153

SMA-MVS		97.48 110	97.11 127	98.60 45	98.83 127	96.67 53	96.74 139	98.73 148	91.61 279	98.48 90	98.36 120	96.53 93	99.68 124	95.17 165	99.54 121	99.45 86
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 11	98.99 5	97.95 98	99.64 14	94.20 156	98.67 15	99.14 46	99.08 10	99.42 20	99.23 33	96.53 93	99.91 13	99.27 5	99.93 11	99.73 22

mPP-MVS		97.91 69	97.53 105	99.04 4	99.22 69	97.87 14	97.74 79	98.78 140	96.04 132	97.10 200	97.73 202	96.53 93	99.78 48	95.16 167	99.50 139	99.46 82

XVS		97.96 54	97.63 93	98.94 15	99.15 86	97.66 19	97.77 74	98.83 126	97.42 75	96.32 250	97.64 207	96.49 96	99.72 88	95.66 133	99.37 174	99.45 86

X-MVStestdata		92.86 301	90.83 327	98.94 15	99.15 86	97.66 19	97.77 74	98.83 126	97.42 75	96.32 250	36.50 397	96.49 96	99.72 88	95.66 133	99.37 174	99.45 86

9.14			96.69 153		98.53 168		96.02 187	98.98 89	93.23 240	97.18 194	97.46 219	96.47 98	99.62 151	92.99 249	99.32 192

UA-Net		98.88 7	98.76 13	99.22 2	99.11 95	97.89 13	99.47 3	99.32 24	99.08 10	97.87 162	99.67 2	96.47 98	99.92 5	97.88 43	99.98 2	99.85 3

fmvsm_l_conf0.5_n		97.68 95	97.81 71	97.27 152	98.92 119	92.71 202	95.89 200	99.41 23	93.36 235	99.00 46	98.44 113	96.46 100	99.65 138	99.09 11	99.76 59	99.45 86

SF-MVS		97.60 101	97.39 113	98.22 75	98.93 117	95.69 88	97.05 121	99.10 51	95.32 170	97.83 165	97.88 187	96.44 101	99.72 88	94.59 200	99.39 172	99.25 137

fmvsm_s_conf0.1_n_a		97.80 83	98.01 52	97.18 158	99.17 82	92.51 205	96.57 149	99.15 43	93.68 227	98.89 54	99.30 28	96.42 102	99.37 234	99.03 13	99.83 43	99.66 30

xiu_mvs_v1_base_debu		95.62 203	95.96 191	94.60 296	98.01 225	88.42 284	93.99 296	98.21 218	92.98 253	95.91 270	94.53 343	96.39 103	99.72 88	95.43 152	98.19 295	95.64 369

xiu_mvs_v1_base		95.62 203	95.96 191	94.60 296	98.01 225	88.42 284	93.99 296	98.21 218	92.98 253	95.91 270	94.53 343	96.39 103	99.72 88	95.43 152	98.19 295	95.64 369

xiu_mvs_v1_base_debi		95.62 203	95.96 191	94.60 296	98.01 225	88.42 284	93.99 296	98.21 218	92.98 253	95.91 270	94.53 343	96.39 103	99.72 88	95.43 152	98.19 295	95.64 369

ETV-MVS		96.13 183	95.90 195	96.82 186	97.76 262	93.89 165	95.40 229	98.95 95	95.87 144	95.58 284	91.00 384	96.36 106	99.72 88	93.36 239	98.83 254	96.85 345

fmvsm_l_conf0.5_n_a		97.60 101	97.76 78	97.11 163	98.92 119	92.28 211	95.83 203	99.32 24	93.22 241	98.91 53	98.49 106	96.31 107	99.64 142	99.07 12	99.76 59	99.40 101

fmvsm_s_conf0.1_n		97.73 88	98.02 51	96.85 183	99.09 98	91.43 237	96.37 160	99.11 49	94.19 210	99.01 44	99.25 31	96.30 108	99.38 229	99.00 14	99.88 27	99.73 22

MP-MVS		97.64 97	97.18 125	99.00 9	99.32 56	97.77 17	97.49 98	98.73 148	96.27 118	95.59 283	97.75 199	96.30 108	99.78 48	93.70 233	99.48 146	99.45 86
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TinyColmap		96.00 189	96.34 175	94.96 279	97.90 237	87.91 299	94.13 291	98.49 185	94.41 203	98.16 128	97.76 196	96.29 110	98.68 331	90.52 299	99.42 166	98.30 271

Fast-Effi-MVS+-dtu		96.44 171	96.12 182	97.39 146	97.18 310	94.39 145	95.46 223	98.73 148	96.03 134	94.72 303	94.92 337	96.28 111	99.69 119	93.81 228	97.98 303	98.09 285

fmvsm_s_conf0.5_n_a		97.65 96	97.83 69	97.13 162	98.80 130	92.51 205	96.25 170	99.06 61	93.67 228	98.64 74	99.00 55	96.23 112	99.36 237	98.99 15	99.80 51	99.53 57

fmvsm_s_conf0.5_n		97.62 99	97.89 62	96.80 187	98.79 132	91.44 236	96.14 179	99.06 61	94.19 210	98.82 61	98.98 58	96.22 113	99.38 229	98.98 16	99.86 31	99.58 40

APD_test1		97.95 58	97.68 85	98.75 31	99.60 17	98.60 5	97.21 112	99.08 57	96.57 107	98.07 140	98.38 119	96.22 113	99.14 280	94.71 195	99.31 195	98.52 247

OMC-MVS		96.48 169	96.00 188	97.91 100	98.30 190	96.01 78	94.86 261	98.60 173	91.88 276	97.18 194	97.21 242	96.11 115	99.04 294	90.49 302	99.34 185	98.69 230

xiu_mvs_v2_base		94.22 265	94.63 243	92.99 339	97.32 304	84.84 349	92.12 344	97.84 255	91.96 274	94.17 315	93.43 353	96.07 116	99.71 104	91.27 275	97.48 328	94.42 379

CSCG		97.40 116	97.30 118	97.69 116	98.95 113	94.83 128	97.28 107	98.99 86	96.35 117	98.13 132	95.95 313	95.99 117	99.66 136	94.36 208	99.73 68	98.59 240

PHI-MVS		96.96 138	96.53 165	98.25 73	97.48 288	96.50 59	96.76 138	98.85 117	93.52 230	96.19 260	96.85 264	95.94 118	99.42 211	93.79 229	99.43 163	98.83 212

TSAR-MVS + MP.		97.42 115	97.23 123	98.00 95	99.38 49	95.00 125	97.63 86	98.20 221	93.00 252	98.16 128	98.06 167	95.89 119	99.72 88	95.67 132	99.10 224	99.28 128
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		97.58 104	97.28 120	98.49 52	99.16 83	96.90 46	96.39 156	98.98 89	95.05 182	98.06 141	98.02 171	95.86 120	99.56 170	94.37 206	99.64 90	99.00 182

AllTest		97.20 127	96.92 142	98.06 88	99.08 99	96.16 70	97.14 116	99.16 39	94.35 205	97.78 167	98.07 162	95.84 121	99.12 283	91.41 272	99.42 166	98.91 199

TestCases				98.06 88	99.08 99	96.16 70		99.16 39	94.35 205	97.78 167	98.07 162	95.84 121	99.12 283	91.41 272	99.42 166	98.91 199

APD-MVS		97.00 133	96.53 165	98.41 59	98.55 165	96.31 66	96.32 164	98.77 141	92.96 257	97.44 183	97.58 213	95.84 121	99.74 77	91.96 261	99.35 182	99.19 146
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
pcd_1.5k_mvsjas		7.98 368	10.65 371	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	95.82 124	0.00 403	0.00 402	0.00 401	0.00 399

PS-MVSNAJss		98.53 22	98.63 20	98.21 78	99.68 11	94.82 129	98.10 56	99.21 32	96.91 92	99.75 2	99.45 13	95.82 124	99.92 5	98.80 19	99.96 4	99.89 1

PS-MVSNAJ		94.10 271	94.47 253	93.00 338	97.35 299	84.88 347	91.86 348	97.84 255	91.96 274	94.17 315	92.50 370	95.82 124	99.71 104	91.27 275	97.48 328	94.40 380

3Dnovator	96.53 2	97.61 100	97.64 91	97.50 132	97.74 267	93.65 177	98.49 28	98.88 108	96.86 94	97.11 199	98.55 101	95.82 124	99.73 83	95.94 118	99.42 166	99.13 158

MTAPA		98.14 39	97.84 66	99.06 3	99.44 39	97.90 12	97.25 108	98.73 148	97.69 63	97.90 157	97.96 177	95.81 128	99.82 35	96.13 106	99.61 99	99.45 86

DP-MVS		97.87 74	97.89 62	97.81 107	98.62 156	94.82 129	97.13 117	98.79 136	98.98 17	98.74 71	98.49 106	95.80 129	99.49 192	95.04 176	99.44 155	99.11 166

Anonymous20240529		97.96 54	98.04 49	97.71 113	98.69 147	94.28 153	97.86 70	98.31 210	98.79 22	99.23 32	98.86 74	95.76 130	99.61 158	95.49 142	99.36 177	99.23 139

LS3D		97.77 86	97.50 109	98.57 47	96.24 334	97.58 24	98.45 31	98.85 117	98.58 28	97.51 175	97.94 180	95.74 131	99.63 146	95.19 163	98.97 236	98.51 248

EIA-MVS		96.04 186	95.77 201	96.85 183	97.80 252	92.98 194	96.12 180	99.16 39	94.65 195	93.77 327	91.69 378	95.68 132	99.67 130	94.18 213	98.85 251	97.91 304

CNVR-MVS		96.92 140	96.55 162	98.03 93	98.00 229	95.54 95	94.87 260	98.17 227	94.60 197	96.38 247	97.05 251	95.67 133	99.36 237	95.12 173	99.08 226	99.19 146

CLD-MVS		95.47 211	95.07 219	96.69 195	98.27 195	92.53 204	91.36 354	98.67 163	91.22 286	95.78 277	94.12 350	95.65 134	98.98 302	90.81 287	99.72 72	98.57 241
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 20	98.76 13	97.94 99	98.79 132	94.37 147	98.84 11	99.15 43	99.37 3	99.67 7	99.43 15	95.61 135	99.72 88	98.12 35	99.86 31	99.73 22

EGC-MVSNET		83.08 362	77.93 365	98.53 50	99.57 20	97.55 26	98.33 38	98.57 179	4.71 399	10.38 400	98.90 70	95.60 136	99.50 187	95.69 130	99.61 99	98.55 244

ITE_SJBPF				97.85 105	98.64 150	96.66 54		98.51 184	95.63 155	97.22 189	97.30 237	95.52 137	98.55 342	90.97 282	98.90 244	98.34 266

DeepC-MVS_fast	94.34 7	96.74 152	96.51 167	97.44 140	97.69 270	94.15 157	96.02 187	98.43 191	93.17 247	97.30 186	97.38 230	95.48 138	99.28 258	93.74 230	99.34 185	98.88 207
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 15	98.62 22	98.75 31	99.51 31	96.61 56	98.55 22	99.17 38	99.05 13	99.17 35	98.79 76	95.47 139	99.89 18	97.95 42	99.91 18	99.75 19

FMVSNet1		97.95 58	98.08 44	97.56 123	99.14 93	93.67 173	98.23 46	98.66 165	97.41 78	99.00 46	99.19 36	95.47 139	99.73 83	95.83 125	99.76 59	99.30 121

MIMVSNet1		98.51 23	98.45 29	98.67 40	99.72 8	96.71 50	98.76 12	98.89 102	98.49 31	99.38 22	99.14 46	95.44 141	99.84 30	96.47 93	99.80 51	99.47 80

CP-MVSNet		98.42 26	98.46 27	98.30 68	99.46 37	95.22 118	98.27 44	98.84 120	99.05 13	99.01 44	98.65 92	95.37 142	99.90 14	97.57 58	99.91 18	99.77 12

segment_acmp												95.34 143

CDPH-MVS		95.45 213	94.65 240	97.84 106	98.28 193	94.96 126	93.73 308	98.33 206	85.03 357	95.44 286	96.60 280	95.31 144	99.44 207	90.01 308	99.13 218	99.11 166

3Dnovator+	96.13 3	97.73 88	97.59 99	98.15 81	98.11 220	95.60 92	98.04 60	98.70 157	98.13 43	96.93 217	98.45 111	95.30 145	99.62 151	95.64 135	98.96 237	99.24 138

MVS_Test		96.27 177	96.79 150	94.73 292	96.94 320	86.63 325	96.18 174	98.33 206	94.94 186	96.07 264	98.28 134	95.25 146	99.26 262	97.21 69	97.90 307	98.30 271

XVG-OURS		97.12 128	96.74 151	98.26 70	98.99 111	97.45 32	93.82 304	99.05 65	95.19 175	98.32 111	97.70 204	95.22 147	98.41 352	94.27 210	98.13 298	98.93 195

dcpmvs_2		97.12 128	97.99 54	94.51 302	99.11 95	84.00 358	97.75 77	99.65 9	97.38 80	99.14 37	98.42 114	95.16 148	99.96 2	95.52 141	99.78 56	99.58 40

MCST-MVS		96.24 178	95.80 199	97.56 123	98.75 137	94.13 158	94.66 269	98.17 227	90.17 301	96.21 258	96.10 307	95.14 149	99.43 209	94.13 216	98.85 251	99.13 158

EI-MVSNet-Vis-set		97.32 123	97.39 113	97.11 163	97.36 298	92.08 223	95.34 235	97.65 268	97.74 57	98.29 116	98.11 158	95.05 150	99.68 124	97.50 61	99.50 139	99.56 51

EI-MVSNet-UG-set		97.32 123	97.40 112	97.09 167	97.34 301	92.01 225	95.33 236	97.65 268	97.74 57	98.30 115	98.14 152	95.04 151	99.69 119	97.55 59	99.52 130	99.58 40

KD-MVS_self_test		97.86 76	98.07 45	97.25 155	99.22 69	92.81 197	97.55 92	98.94 96	97.10 88	98.85 57	98.88 72	95.03 152	99.67 130	97.39 65	99.65 88	99.26 133

ZD-MVS					98.43 182	95.94 79		98.56 180	90.72 291	96.66 233	97.07 249	95.02 153	99.74 77	91.08 279	98.93 242

DELS-MVS		96.17 181	96.23 178	95.99 229	97.55 284	90.04 257	92.38 341	98.52 182	94.13 212	96.55 241	97.06 250	94.99 154	99.58 163	95.62 136	99.28 199	98.37 260
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		96.59 163	96.93 140	95.55 252	98.88 123	87.12 317	94.47 274	99.30 26	94.12 213	96.65 235	98.41 115	94.98 155	99.87 22	95.81 127	99.78 56	99.66 30

ab-mvs		96.59 163	96.59 158	96.60 198	98.64 150	92.21 214	98.35 35	97.67 264	94.45 202	96.99 212	98.79 76	94.96 156	99.49 192	90.39 303	99.07 228	98.08 286

MSLP-MVS++		96.42 173	96.71 152	95.57 249	97.82 247	90.56 253	95.71 207	98.84 120	94.72 192	96.71 230	97.39 228	94.91 157	98.10 367	95.28 158	99.02 233	98.05 295

QAPM		95.88 193	95.57 208	96.80 187	97.90 237	91.84 229	98.18 53	98.73 148	88.41 320	96.42 245	98.13 154	94.73 158	99.75 68	88.72 326	98.94 240	98.81 214

RPSCF		97.87 74	97.51 107	98.95 14	99.15 86	98.43 6	97.56 91	99.06 61	96.19 124	98.48 90	98.70 86	94.72 159	99.24 267	94.37 206	99.33 190	99.17 150

DU-MVS		97.79 84	97.60 98	98.36 63	98.73 138	95.78 84	95.65 214	98.87 110	97.57 67	98.31 113	97.83 190	94.69 160	99.85 27	97.02 78	99.71 75	99.46 82

Baseline_NR-MVSNet		97.72 90	97.79 73	97.50 132	99.56 21	93.29 187	95.44 224	98.86 113	98.20 42	98.37 101	99.24 32	94.69 160	99.55 174	95.98 116	99.79 53	99.65 33

TEST9					97.84 244	95.23 115	93.62 310	98.39 198	86.81 338	93.78 325	95.99 309	94.68 162	99.52 182

UniMVSNet (Re)		97.83 78	97.65 88	98.35 64	98.80 130	95.86 83	95.92 198	99.04 71	97.51 72	98.22 121	97.81 194	94.68 162	99.78 48	97.14 73	99.75 66	99.41 100

UniMVSNet_NR-MVSNet		97.83 78	97.65 88	98.37 62	98.72 140	95.78 84	95.66 212	99.02 74	98.11 44	98.31 113	97.69 205	94.65 164	99.85 27	97.02 78	99.71 75	99.48 77

VPNet		97.26 125	97.49 110	96.59 199	99.47 36	90.58 251	96.27 166	98.53 181	97.77 54	98.46 93	98.41 115	94.59 165	99.68 124	94.61 196	99.29 198	99.52 59

train_agg		95.46 212	94.66 239	97.88 103	97.84 244	95.23 115	93.62 310	98.39 198	87.04 334	93.78 325	95.99 309	94.58 166	99.52 182	91.76 269	98.90 244	98.89 203

test_8					97.81 248	95.07 124	93.54 313	98.38 200	87.04 334	93.71 329	95.96 312	94.58 166	99.52 182

API-MVS		95.09 229	95.01 222	95.31 262	96.61 326	94.02 161	96.83 131	97.18 284	95.60 157	95.79 275	94.33 348	94.54 168	98.37 357	85.70 354	98.52 281	93.52 384

Test By Simon												94.51 169

MSDG		95.33 217	95.13 216	95.94 235	97.40 296	91.85 228	91.02 365	98.37 201	95.30 171	96.31 252	95.99 309	94.51 169	98.38 355	89.59 314	97.65 322	97.60 322

TSAR-MVS + GP.		96.47 170	96.12 182	97.49 135	97.74 267	95.23 115	94.15 288	96.90 295	93.26 239	98.04 144	96.70 275	94.41 171	98.89 309	94.77 191	99.14 216	98.37 260

NR-MVSNet		97.96 54	97.86 65	98.26 70	98.73 138	95.54 95	98.14 54	98.73 148	97.79 53	99.42 20	97.83 190	94.40 172	99.78 48	95.91 120	99.76 59	99.46 82

AdaColmap		95.11 227	94.62 244	96.58 200	97.33 303	94.45 144	94.92 258	98.08 240	93.15 248	93.98 323	95.53 325	94.34 173	99.10 288	85.69 355	98.61 276	96.20 363

FC-MVSNet-test		98.16 37	98.37 33	97.56 123	99.49 35	93.10 192	98.35 35	99.21 32	98.43 32	98.89 54	98.83 75	94.30 174	99.81 37	97.87 44	99.91 18	99.77 12

Effi-MVS+-dtu		96.81 149	96.09 184	98.99 10	96.90 322	98.69 4	96.42 155	98.09 239	95.86 145	95.15 293	95.54 324	94.26 175	99.81 37	94.06 218	98.51 283	98.47 252

ambc				96.56 203	98.23 200	91.68 232	97.88 69	98.13 235		98.42 96	98.56 100	94.22 176	99.04 294	94.05 220	99.35 182	98.95 189

test20.03		96.58 165	96.61 157	96.48 207	98.49 175	91.72 231	95.68 211	97.69 263	96.81 95	98.27 117	97.92 183	94.18 177	98.71 326	90.78 289	99.66 87	99.00 182

HPM-MVS++		96.99 134	96.38 173	98.81 27	98.64 150	97.59 23	95.97 192	98.20 221	95.51 162	95.06 295	96.53 284	94.10 178	99.70 112	94.29 209	99.15 215	99.13 158

test_vis3_rt		97.04 131	96.98 136	97.23 157	98.44 181	95.88 80	96.82 132	99.67 6	90.30 298	99.27 29	99.33 27	94.04 179	96.03 388	97.14 73	97.83 309	99.78 11

test_fmvs3		97.38 117	97.56 102	96.84 185	98.63 154	92.81 197	97.60 87	99.61 13	90.87 289	98.76 70	99.66 3	94.03 180	97.90 369	99.24 6	99.68 83	99.81 8

PM-MVS		97.36 121	97.10 128	98.14 82	98.91 121	96.77 49	96.20 173	98.63 171	93.82 222	98.54 83	98.33 123	93.98 181	99.05 293	95.99 115	99.45 154	98.61 239

mvsany_test3		96.21 179	95.93 194	97.05 169	97.40 296	94.33 149	95.76 206	94.20 341	89.10 311	99.36 24	99.60 6	93.97 182	97.85 370	95.40 156	98.63 274	98.99 185

OpenMVS	94.22 8	95.48 210	95.20 213	96.32 216	97.16 311	91.96 226	97.74 79	98.84 120	87.26 331	94.36 312	98.01 173	93.95 183	99.67 130	90.70 295	98.75 261	97.35 332

v8		97.60 101	98.06 47	96.23 219	98.71 143	89.44 267	97.43 102	98.82 134	97.29 84	98.74 71	99.10 48	93.86 184	99.68 124	98.61 27	99.94 8	99.56 51

diffmvs		96.04 186	96.23 178	95.46 257	97.35 299	88.03 297	93.42 316	99.08 57	94.09 216	96.66 233	96.93 259	93.85 185	99.29 256	96.01 114	98.67 269	99.06 175
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
NCCC		96.52 167	95.99 189	98.10 85	97.81 248	95.68 89	95.00 256	98.20 221	95.39 168	95.40 288	96.36 294	93.81 186	99.45 204	93.55 236	98.42 287	99.17 150

TAPA-MVS	93.32 12	94.93 234	94.23 260	97.04 171	98.18 207	94.51 141	95.22 243	98.73 148	81.22 376	96.25 256	95.95 313	93.80 187	98.98 302	89.89 310	98.87 248	97.62 320
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
FIs		97.93 65	98.07 45	97.48 136	99.38 49	92.95 195	98.03 62	99.11 49	98.04 48	98.62 76	98.66 89	93.75 188	99.78 48	97.23 67	99.84 40	99.73 22

OurMVSNet-221017-0		98.61 16	98.61 24	98.63 44	99.77 5	96.35 64	99.17 6	99.05 65	98.05 47	99.61 13	99.52 7	93.72 189	99.88 20	98.72 24	99.88 27	99.65 33

test_prior2							93.33 320		94.21 208	94.02 321	96.25 298	93.64 190		91.90 263	98.96 237

mvsany_test1		93.47 290	93.03 286	94.79 289	94.05 382	92.12 219	90.82 367	90.01 382	85.02 358	97.26 188	98.28 134	93.57 191	97.03 379	92.51 256	95.75 364	95.23 375

旧先验1					97.80 252	93.87 166		97.75 260			97.04 252	93.57 191			98.68 268	98.72 226

v10		97.55 105	97.97 55	96.31 217	98.60 158	89.64 263	97.44 100	99.02 74	96.60 101	98.72 73	99.16 43	93.48 193	99.72 88	98.76 21	99.92 15	99.58 40

v148		96.58 165	96.97 137	95.42 259	98.63 154	87.57 307	95.09 248	97.90 250	95.91 142	98.24 119	97.96 177	93.42 194	99.39 226	96.04 110	99.52 130	99.29 127

V42		97.04 131	97.16 126	96.68 196	98.59 160	91.05 241	96.33 163	98.36 202	94.60 197	97.99 147	98.30 129	93.32 195	99.62 151	97.40 64	99.53 125	99.38 107

new-patchmatchnet		95.67 201	96.58 159	92.94 341	97.48 288	80.21 377	92.96 325	98.19 226	94.83 189	98.82 61	98.79 76	93.31 196	99.51 186	95.83 125	99.04 232	99.12 163

test12				97.46 138	97.61 279	94.07 159		97.78 259		93.57 335		93.31 196	99.42 211		98.78 258	98.89 203

UGNet		96.81 149	96.56 161	97.58 122	96.64 325	93.84 168	97.75 77	97.12 287	96.47 112	93.62 332	98.88 72	93.22 198	99.53 179	95.61 137	99.69 79	99.36 113
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
pmmvs-eth3d		96.49 168	96.18 181	97.42 143	98.25 197	94.29 150	94.77 265	98.07 244	89.81 305	97.97 151	98.33 123	93.11 199	99.08 290	95.46 148	99.84 40	98.89 203

v1144		96.84 144	97.08 130	96.13 226	98.42 183	89.28 270	95.41 228	98.67 163	94.21 208	97.97 151	98.31 125	93.06 200	99.65 138	98.06 39	99.62 93	99.45 86

PVSNet_BlendedMVS		95.02 233	94.93 225	95.27 263	97.79 257	87.40 312	94.14 290	98.68 160	88.94 315	94.51 308	98.01 173	93.04 201	99.30 252	89.77 312	99.49 142	99.11 166

PVSNet_Blended		93.96 276	93.65 275	94.91 280	97.79 257	87.40 312	91.43 353	98.68 160	84.50 364	94.51 308	94.48 346	93.04 201	99.30 252	89.77 312	98.61 276	98.02 298

mvs_anonymous		95.36 215	96.07 186	93.21 333	96.29 333	81.56 372	94.60 271	97.66 266	93.30 238	96.95 216	98.91 69	93.03 203	99.38 229	96.60 88	97.30 336	98.69 230

v1192		96.83 147	97.06 132	96.15 225	98.28 193	89.29 269	95.36 232	98.77 141	93.73 224	98.11 133	98.34 122	93.02 204	99.67 130	98.35 33	99.58 106	99.50 63

F-COLMAP		95.30 219	94.38 257	98.05 92	98.64 150	96.04 75	95.61 218	98.66 165	89.00 314	93.22 344	96.40 292	92.90 205	99.35 241	87.45 345	97.53 326	98.77 220

WR-MVS		96.90 142	96.81 147	97.16 159	98.56 164	92.20 217	94.33 277	98.12 236	97.34 81	98.20 122	97.33 235	92.81 206	99.75 68	94.79 188	99.81 48	99.54 54

v1240		96.74 152	97.02 135	95.91 236	98.18 207	88.52 283	95.39 230	98.88 108	93.15 248	98.46 93	98.40 118	92.80 207	99.71 104	98.45 31	99.49 142	99.49 71

MVS_0304		96.62 162	96.40 172	97.28 151	97.91 235	92.30 210	96.47 154	89.74 383	97.52 71	95.38 289	98.63 94	92.76 208	99.81 37	99.28 4	99.93 11	99.75 19

MVE	73.61 22	86.48 360	85.92 361	88.18 375	96.23 336	85.28 341	81.78 393	75.79 399	86.01 344	82.53 395	91.88 375	92.74 209	87.47 398	71.42 395	94.86 372	91.78 389
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DP-MVS Recon		95.55 206	95.13 216	96.80 187	98.51 171	93.99 163	94.60 271	98.69 158	90.20 300	95.78 277	96.21 300	92.73 210	98.98 302	90.58 298	98.86 250	97.42 329

CANet		95.86 194	95.65 205	96.49 206	96.41 331	90.82 246	94.36 276	98.41 195	94.94 186	92.62 359	96.73 274	92.68 211	99.71 104	95.12 173	99.60 102	98.94 191

v1921920		96.72 155	96.96 139	95.99 229	98.21 201	88.79 280	95.42 226	98.79 136	93.22 241	98.19 126	98.26 139	92.68 211	99.70 112	98.34 34	99.55 118	99.49 71

BH-untuned		94.69 246	94.75 237	94.52 301	97.95 234	87.53 308	94.07 293	97.01 291	93.99 218	97.10 200	95.65 320	92.65 213	98.95 307	87.60 341	96.74 347	97.09 335

LF4IMVS		96.07 184	95.63 206	97.36 147	98.19 204	95.55 94	95.44 224	98.82 134	92.29 270	95.70 281	96.55 282	92.63 214	98.69 328	91.75 270	99.33 190	97.85 309

v2v482		96.78 151	97.06 132	95.95 233	98.57 162	88.77 281	95.36 232	98.26 212	95.18 176	97.85 164	98.23 143	92.58 215	99.63 146	97.80 48	99.69 79	99.45 86

EI-MVSNet		96.63 161	96.93 140	95.74 242	97.26 306	88.13 294	95.29 240	97.65 268	96.99 89	97.94 154	98.19 148	92.55 216	99.58 163	96.91 81	99.56 112	99.50 63

IterMVS-LS		96.92 140	97.29 119	95.79 240	98.51 171	88.13 294	95.10 247	98.66 165	96.99 89	98.46 93	98.68 88	92.55 216	99.74 77	96.91 81	99.79 53	99.50 63
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
VDD-MVS		97.37 119	97.25 121	97.74 111	98.69 147	94.50 143	97.04 122	95.61 323	98.59 27	98.51 85	98.72 83	92.54 218	99.58 163	96.02 112	99.49 142	99.12 163

MVS		90.02 335	89.20 342	92.47 350	94.71 371	86.90 321	95.86 201	96.74 302	64.72 395	90.62 372	92.77 364	92.54 218	98.39 354	79.30 383	95.56 366	92.12 388

test_vis1_rt		94.03 275	93.65 275	95.17 268	95.76 354	93.42 183	93.97 299	98.33 206	84.68 361	93.17 345	95.89 315	92.53 220	94.79 390	93.50 237	94.97 370	97.31 333

v144192		96.69 158	96.90 144	96.03 228	98.25 197	88.92 275	95.49 222	98.77 141	93.05 250	98.09 136	98.29 133	92.51 221	99.70 112	98.11 36	99.56 112	99.47 80

原ACMM1				96.58 200	98.16 212	92.12 219		98.15 233	85.90 347	93.49 337	96.43 289	92.47 222	99.38 229	87.66 340	98.62 275	98.23 278

VNet		96.84 144	96.83 146	96.88 181	98.06 221	92.02 224	96.35 162	97.57 274	97.70 62	97.88 159	97.80 195	92.40 223	99.54 177	94.73 193	98.96 237	99.08 171

114514_t		93.96 276	93.22 283	96.19 222	99.06 102	90.97 244	95.99 190	98.94 96	73.88 393	93.43 340	96.93 259	92.38 224	99.37 234	89.09 321	99.28 199	98.25 277

CPTT-MVS		96.69 158	96.08 185	98.49 52	98.89 122	96.64 55	97.25 108	98.77 141	92.89 258	96.01 267	97.13 245	92.23 225	99.67 130	92.24 258	99.34 185	99.17 150

MSP-MVS		97.45 112	96.92 142	99.03 5	99.26 60	97.70 18	97.66 83	98.89 102	95.65 154	98.51 85	96.46 288	92.15 226	99.81 37	95.14 170	98.58 279	99.58 40
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		94.21 267	93.03 286	97.76 110	96.94 320	97.44 33	96.97 125	97.15 285	87.89 329	92.00 364	92.73 366	92.14 227	99.12 283	83.92 369	97.51 327	96.73 352
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		95.95 190	95.80 199	96.42 211	99.28 58	90.62 250	95.31 238	99.08 57	88.40 321	96.97 215	98.17 151	92.11 228	99.78 48	93.64 234	99.21 207	98.86 210

BH-RMVSNet		94.56 254	94.44 256	94.91 280	97.57 281	87.44 311	93.78 307	96.26 308	93.69 226	96.41 246	96.50 287	92.10 229	99.00 298	85.96 352	97.71 316	98.31 269

新几何1				97.25 155	98.29 191	94.70 133		97.73 261	77.98 387	94.83 302	96.67 277	92.08 230	99.45 204	88.17 335	98.65 273	97.61 321

testdata				95.70 245	98.16 212	90.58 251		97.72 262	80.38 379	95.62 282	97.02 253	92.06 231	98.98 302	89.06 323	98.52 281	97.54 324

YYNet1		94.73 241	94.84 231	94.41 306	97.47 292	85.09 345	90.29 372	95.85 317	92.52 264	97.53 173	97.76 196	91.97 232	99.18 273	93.31 242	96.86 341	98.95 189

Anonymous20231206		95.27 220	95.06 221	95.88 237	98.72 140	89.37 268	95.70 208	97.85 253	88.00 327	96.98 214	97.62 209	91.95 233	99.34 243	89.21 319	99.53 125	98.94 191

MS-PatchMatch		94.83 238	94.91 227	94.57 299	96.81 323	87.10 318	94.23 283	97.34 279	88.74 318	97.14 196	97.11 247	91.94 234	98.23 363	92.99 249	97.92 305	98.37 260

MDA-MVSNet_test_wron		94.73 241	94.83 233	94.42 305	97.48 288	85.15 343	90.28 373	95.87 316	92.52 264	97.48 179	97.76 196	91.92 235	99.17 277	93.32 241	96.80 346	98.94 191

HQP_MVS		96.66 160	96.33 176	97.68 117	98.70 145	94.29 150	96.50 152	98.75 145	96.36 115	96.16 261	96.77 271	91.91 236	99.46 200	92.59 254	99.20 208	99.28 128

plane_prior6					98.38 185	94.37 147						91.91 236

MVP-Stereo		95.69 199	95.28 211	96.92 178	98.15 214	93.03 193	95.64 217	98.20 221	90.39 297	96.63 236	97.73 202	91.63 238	99.10 288	91.84 266	97.31 335	98.63 236
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PatchMatch-RL		94.61 252	93.81 273	97.02 173	98.19 204	95.72 86	93.66 309	97.23 281	88.17 325	94.94 300	95.62 322	91.43 239	98.57 339	87.36 346	97.68 319	96.76 351

MDA-MVSNet-bldmvs		95.69 199	95.67 203	95.74 242	98.48 177	88.76 282	92.84 326	97.25 280	96.00 135	97.59 171	97.95 179	91.38 240	99.46 200	93.16 247	96.35 354	98.99 185

SSC-MVS		95.92 191	97.03 134	92.58 347	99.28 58	78.39 382	96.68 146	95.12 332	98.90 19	99.11 39	98.66 89	91.36 241	99.68 124	95.00 179	99.16 214	99.67 28

mvsmamba		98.16 37	98.06 47	98.44 55	99.53 29	95.87 81	98.70 13	98.94 96	97.71 61	98.85 57	99.10 48	91.35 242	99.83 33	98.47 30	99.90 24	99.64 35

PAPR		92.22 311	91.27 318	95.07 272	95.73 356	88.81 279	91.97 347	97.87 252	85.80 348	90.91 371	92.73 366	91.16 243	98.33 359	79.48 382	95.76 363	98.08 286

1314		92.38 308	92.30 303	92.64 346	95.42 363	85.15 343	95.86 201	96.97 293	85.40 353	90.62 372	93.06 360	91.12 244	97.80 372	86.74 349	95.49 367	94.97 377

WB-MVS		95.50 207	96.62 156	92.11 355	99.21 76	77.26 390	96.12 180	95.40 329	98.62 26	98.84 59	98.26 139	91.08 245	99.50 187	93.37 238	98.70 267	99.58 40

ppachtmachnet_test		94.49 259	94.84 231	93.46 327	96.16 340	82.10 368	90.59 369	97.48 276	90.53 295	97.01 211	97.59 211	91.01 246	99.36 237	93.97 224	99.18 212	98.94 191

PLC	91.02 16	94.05 274	92.90 289	97.51 128	98.00 229	95.12 123	94.25 281	98.25 213	86.17 343	91.48 369	95.25 329	91.01 246	99.19 272	85.02 364	96.69 348	98.22 279
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test222					98.17 210	93.24 190	92.74 331	97.61 273	75.17 391	94.65 305	96.69 276	90.96 248			98.66 271	97.66 317

CL-MVSNet_self_test		95.04 230	94.79 236	95.82 239	97.51 286	89.79 261	91.14 362	96.82 298	93.05 250	96.72 229	96.40 292	90.82 249	99.16 278	91.95 262	98.66 271	98.50 250

USDC		94.56 254	94.57 250	94.55 300	97.78 260	86.43 328	92.75 329	98.65 170	85.96 345	96.91 219	97.93 182	90.82 249	98.74 322	90.71 294	99.59 104	98.47 252

PCF-MVS	89.43 18	92.12 314	90.64 330	96.57 202	97.80 252	93.48 181	89.88 379	98.45 188	74.46 392	96.04 266	95.68 319	90.71 251	99.31 249	73.73 391	99.01 235	96.91 342
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PAPM_NR		94.61 252	94.17 264	95.96 231	98.36 187	91.23 239	95.93 197	97.95 247	92.98 253	93.42 341	94.43 347	90.53 252	98.38 355	87.60 341	96.29 355	98.27 275

our_test_3		94.20 269	94.58 248	93.07 335	96.16 340	81.20 374	90.42 371	96.84 296	90.72 291	97.14 196	97.13 245	90.47 253	99.11 286	94.04 221	98.25 293	98.91 199

MM				97.62 120		93.30 186	96.39 156	92.61 360	97.90 52	96.76 228	98.64 93	90.46 254	99.81 37	99.16 9	99.94 8	99.76 17

test_f		95.82 196	95.88 197	95.66 246	97.61 279	93.21 191	95.61 218	98.17 227	86.98 336	98.42 96	99.47 11	90.46 254	94.74 391	97.71 53	98.45 285	99.03 178

OpenMVS_ROB	91.80 14	93.64 286	93.05 284	95.42 259	97.31 305	91.21 240	95.08 250	96.68 305	81.56 373	96.88 221	96.41 290	90.44 256	99.25 264	85.39 360	97.67 320	95.80 367

HQP2-MVS												90.33 257

N_pmnet		95.18 224	94.23 260	98.06 88	97.85 239	96.55 58	92.49 335	91.63 367	89.34 308	98.09 136	97.41 223	90.33 257	99.06 292	91.58 271	99.31 195	98.56 242

HQP-MVS		95.17 226	94.58 248	96.92 178	97.85 239	92.47 207	94.26 278	98.43 191	93.18 244	92.86 350	95.08 331	90.33 257	99.23 269	90.51 300	98.74 262	99.05 177

CNLPA		95.04 230	94.47 253	96.75 191	97.81 248	95.25 114	94.12 292	97.89 251	94.41 203	94.57 306	95.69 318	90.30 260	98.35 358	86.72 350	98.76 260	96.64 353

PMMVS		92.39 307	91.08 321	96.30 218	93.12 389	92.81 197	90.58 370	95.96 314	79.17 384	91.85 366	92.27 371	90.29 261	98.66 333	89.85 311	96.68 349	97.43 328

TR-MVS		92.54 306	92.20 305	93.57 325	96.49 329	86.66 324	93.51 314	94.73 335	89.96 303	94.95 299	93.87 351	90.24 262	98.61 336	81.18 379	94.88 371	95.45 373

TAMVS		95.49 208	94.94 223	97.16 159	98.31 189	93.41 184	95.07 251	96.82 298	91.09 287	97.51 175	97.82 193	89.96 263	99.42 211	88.42 331	99.44 155	98.64 234

DPM-MVS		93.68 283	92.77 296	96.42 211	97.91 235	92.54 203	91.17 361	97.47 277	84.99 359	93.08 347	94.74 339	89.90 264	99.00 298	87.54 343	98.09 300	97.72 315

PMMVS2		93.66 284	94.07 266	92.45 351	97.57 281	80.67 376	86.46 387	96.00 312	93.99 218	97.10 200	97.38 230	89.90 264	97.82 371	88.76 325	99.47 148	98.86 210

RRT_MVS		97.95 58	97.79 73	98.43 57	99.67 12	95.56 93	98.86 10	96.73 304	97.99 49	99.15 36	99.35 23	89.84 266	99.90 14	98.64 26	99.90 24	99.82 6

bld_raw_dy_0_64		97.69 92	97.61 97	97.91 100	99.54 26	94.27 154	98.06 59	98.60 173	96.60 101	98.79 64	98.95 63	89.62 267	99.84 30	98.43 32	99.91 18	99.62 36

BH-w/o		92.14 313	91.94 307	92.73 345	97.13 313	85.30 339	92.46 336	95.64 320	89.33 309	94.21 314	92.74 365	89.60 268	98.24 362	81.68 377	94.66 373	94.66 378

Anonymous20240521		97.07 130	97.51 107	95.76 241	99.35 52	88.18 291	97.78 73	98.40 197	97.11 87	98.34 107	99.04 53	89.58 269	99.79 45	98.09 37	99.93 11	99.30 121

UnsupCasMVSNet_bld		94.72 245	94.26 259	96.08 227	98.62 156	90.54 254	93.38 318	98.05 246	90.30 298	97.02 210	96.80 270	89.54 270	99.16 278	88.44 330	96.18 356	98.56 242

MG-MVS		94.08 273	94.00 268	94.32 309	97.09 314	85.89 333	93.19 323	95.96 314	92.52 264	94.93 301	97.51 217	89.54 270	98.77 319	87.52 344	97.71 316	98.31 269

UnsupCasMVSNet_eth		95.91 192	95.73 202	96.44 208	98.48 177	91.52 234	95.31 238	98.45 188	95.76 149	97.48 179	97.54 214	89.53 272	98.69 328	94.43 202	94.61 374	99.13 158

GBi-Net		96.99 134	96.80 148	97.56 123	97.96 231	93.67 173	98.23 46	98.66 165	95.59 158	97.99 147	99.19 36	89.51 273	99.73 83	94.60 197	99.44 155	99.30 121

test1		96.99 134	96.80 148	97.56 123	97.96 231	93.67 173	98.23 46	98.66 165	95.59 158	97.99 147	99.19 36	89.51 273	99.73 83	94.60 197	99.44 155	99.30 121

FMVSNet2		96.72 155	96.67 155	96.87 182	97.96 231	91.88 227	97.15 114	98.06 245	95.59 158	98.50 87	98.62 95	89.51 273	99.65 138	94.99 181	99.60 102	99.07 173

pmmvs4		94.82 239	94.19 263	96.70 194	97.42 295	92.75 201	92.09 346	96.76 300	86.80 339	95.73 280	97.22 241	89.28 276	98.89 309	93.28 243	99.14 216	98.46 254

cascas		91.89 319	91.35 316	93.51 326	94.27 377	85.60 335	88.86 384	98.61 172	79.32 383	92.16 363	91.44 380	89.22 277	98.12 366	90.80 288	97.47 330	96.82 348

DSMNet-mixed		92.19 312	91.83 309	93.25 331	96.18 339	83.68 361	96.27 166	93.68 345	76.97 390	92.54 360	99.18 39	89.20 278	98.55 342	83.88 370	98.60 278	97.51 325

c3_l		95.20 223	95.32 210	94.83 287	96.19 338	86.43 328	91.83 349	98.35 205	93.47 232	97.36 185	97.26 239	88.69 279	99.28 258	95.41 155	99.36 177	98.78 217

test_fmvs2		96.38 174	96.45 169	96.16 224	97.85 239	91.30 238	96.81 133	99.45 18	89.24 310	98.49 88	99.38 18	88.68 280	97.62 374	98.83 18	99.32 192	99.57 47

CANet_DTU		94.65 250	94.21 262	95.96 231	95.90 348	89.68 262	93.92 301	97.83 257	93.19 243	90.12 378	95.64 321	88.52 281	99.57 169	93.27 244	99.47 148	98.62 237

EPP-MVSNet		96.84 144	96.58 159	97.65 118	99.18 81	93.78 171	98.68 14	96.34 307	97.91 51	97.30 186	98.06 167	88.46 282	99.85 27	93.85 227	99.40 171	99.32 116

SixPastTwentyTwo		97.49 109	97.57 101	97.26 154	99.56 21	92.33 209	98.28 42	96.97 293	98.30 38	99.45 18	99.35 23	88.43 283	99.89 18	98.01 40	99.76 59	99.54 54

miper_ehance_all_eth		94.69 246	94.70 238	94.64 293	95.77 353	86.22 330	91.32 358	98.24 215	91.67 278	97.05 207	96.65 278	88.39 284	99.22 271	94.88 183	98.34 289	98.49 251

IS-MVSNet		96.93 139	96.68 154	97.70 114	99.25 63	94.00 162	98.57 20	96.74 302	98.36 34	98.14 131	97.98 176	88.23 285	99.71 104	93.10 248	99.72 72	99.38 107

jason		94.39 262	94.04 267	95.41 261	98.29 191	87.85 302	92.74 331	96.75 301	85.38 354	95.29 290	96.15 302	88.21 286	99.65 138	94.24 211	99.34 185	98.74 223
jason: jason.
IterMVS-SCA-FT		95.86 194	96.19 180	94.85 285	97.68 271	85.53 336	92.42 339	97.63 272	96.99 89	98.36 104	98.54 102	87.94 287	99.75 68	97.07 77	99.08 226	99.27 132

SCA		93.38 293	93.52 278	92.96 340	96.24 334	81.40 373	93.24 321	94.00 342	91.58 281	94.57 306	96.97 256	87.94 287	99.42 211	89.47 316	97.66 321	98.06 292

sss		94.22 265	93.72 274	95.74 242	97.71 269	89.95 259	93.84 303	96.98 292	88.38 322	93.75 328	95.74 317	87.94 287	98.89 309	91.02 281	98.10 299	98.37 260

IterMVS		95.42 214	95.83 198	94.20 313	97.52 285	83.78 360	92.41 340	97.47 277	95.49 163	98.06 141	98.49 106	87.94 287	99.58 163	96.02 112	99.02 233	99.23 139
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CHOSEN 1792x2688		94.10 271	93.41 280	96.18 223	99.16 83	90.04 257	92.15 343	98.68 160	79.90 381	96.22 257	97.83 190	87.92 291	99.42 211	89.18 320	99.65 88	99.08 171

VDDNet		96.98 137	96.84 145	97.41 144	99.40 46	93.26 189	97.94 65	95.31 330	99.26 7	98.39 100	99.18 39	87.85 292	99.62 151	95.13 172	99.09 225	99.35 115

pmmvs5		94.63 251	94.34 258	95.50 254	97.63 278	88.34 287	94.02 294	97.13 286	87.15 333	95.22 292	97.15 244	87.50 293	99.27 261	93.99 222	99.26 202	98.88 207

D2MVS		95.18 224	95.17 215	95.21 265	97.76 262	87.76 305	94.15 288	97.94 248	89.77 306	96.99 212	97.68 206	87.45 294	99.14 280	95.03 178	99.81 48	98.74 223

test_vis1_n_1920		95.77 197	96.41 171	93.85 318	98.55 165	84.86 348	95.91 199	99.71 4	92.72 261	97.67 169	98.90 70	87.44 295	98.73 323	97.96 41	98.85 251	97.96 301

PVSNet	86.72 19	91.10 327	90.97 324	91.49 359	97.56 283	78.04 384	87.17 386	94.60 337	84.65 362	92.34 361	92.20 372	87.37 296	98.47 349	85.17 363	97.69 318	97.96 301

Anonymous202405211		96.34 175	95.98 190	97.43 141	98.25 197	93.85 167	96.74 139	94.41 339	97.72 59	98.37 101	98.03 170	87.15 297	99.53 179	94.06 218	99.07 228	98.92 198

MVSFormer		96.14 182	96.36 174	95.49 255	97.68 271	87.81 303	98.67 15	99.02 74	96.50 109	94.48 310	96.15 302	86.90 298	99.92 5	98.73 22	99.13 218	98.74 223

lupinMVS		93.77 279	93.28 281	95.24 264	97.68 271	87.81 303	92.12 344	96.05 310	84.52 363	94.48 310	95.06 333	86.90 298	99.63 146	93.62 235	99.13 218	98.27 275

eth_miper_zixun_eth		94.89 236	94.93 225	94.75 291	95.99 346	86.12 331	91.35 355	98.49 185	93.40 233	97.12 198	97.25 240	86.87 300	99.35 241	95.08 175	98.82 255	98.78 217

test_vis1_n		95.67 201	95.89 196	95.03 274	98.18 207	89.89 260	96.94 126	99.28 28	88.25 324	98.20 122	98.92 66	86.69 301	97.19 377	97.70 55	98.82 255	98.00 300

WTY-MVS		93.55 288	93.00 288	95.19 266	97.81 248	87.86 300	93.89 302	96.00 312	89.02 313	94.07 319	95.44 328	86.27 302	99.33 245	87.69 339	96.82 344	98.39 258

CDS-MVSNet		94.88 237	94.12 265	97.14 161	97.64 277	93.57 178	93.96 300	97.06 290	90.05 302	96.30 253	96.55 282	86.10 303	99.47 197	90.10 307	99.31 195	98.40 256
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
1112_ss		94.12 270	93.42 279	96.23 219	98.59 160	90.85 245	94.24 282	98.85 117	85.49 350	92.97 348	94.94 335	86.01 304	99.64 142	91.78 268	97.92 305	98.20 281

dmvs_testset		87.30 357	86.99 357	88.24 374	96.71 324	77.48 387	94.68 268	86.81 392	92.64 263	89.61 381	87.01 393	85.91 305	93.12 394	61.04 398	88.49 390	94.13 381

miper_enhance_ethall		93.14 298	92.78 295	94.20 313	93.65 385	85.29 340	89.97 375	97.85 253	85.05 356	96.15 263	94.56 342	85.74 306	99.14 280	93.74 230	98.34 289	98.17 284

new_pmnet		92.34 309	91.69 313	94.32 309	96.23 336	89.16 272	92.27 342	92.88 354	84.39 366	95.29 290	96.35 295	85.66 307	96.74 386	84.53 367	97.56 324	97.05 336

Syy-MVS		92.09 315	91.80 311	92.93 342	95.19 365	82.65 364	92.46 336	91.35 368	90.67 293	91.76 367	87.61 391	85.64 308	98.50 346	94.73 193	96.84 342	97.65 318

alignmvs		96.01 188	95.52 209	97.50 132	97.77 261	94.71 131	96.07 183	96.84 296	97.48 73	96.78 227	94.28 349	85.50 309	99.40 222	96.22 102	98.73 265	98.40 256

lessismore_v0				97.05 169	99.36 51	92.12 219		84.07 395		98.77 69	98.98 58	85.36 310	99.74 77	97.34 66	99.37 174	99.30 121

HY-MVS	91.43 15	92.58 305	91.81 310	94.90 282	96.49 329	88.87 277	97.31 105	94.62 336	85.92 346	90.50 375	96.84 265	85.05 311	99.40 222	83.77 372	95.78 362	96.43 359

EPNet		93.72 281	92.62 300	97.03 172	87.61 401	92.25 212	96.27 166	91.28 370	96.74 97	87.65 388	97.39 228	85.00 312	99.64 142	92.14 259	99.48 146	99.20 145
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_lstm_enhance		94.81 240	94.80 235	94.85 285	96.16 340	86.45 327	91.14 362	98.20 221	93.49 231	97.03 209	97.37 232	84.97 313	99.26 262	95.28 158	99.56 112	98.83 212

Test_1112_low_res		93.53 289	92.86 290	95.54 253	98.60 158	88.86 278	92.75 329	98.69 158	82.66 370	92.65 356	96.92 261	84.75 314	99.56 170	90.94 283	97.76 312	98.19 282

MVS-HIRNet		88.40 351	90.20 335	82.99 378	97.01 316	60.04 403	93.11 324	85.61 394	84.45 365	88.72 385	99.09 50	84.72 315	98.23 363	82.52 376	96.59 351	90.69 393

K. test v3		96.44 171	96.28 177	96.95 175	99.41 43	91.53 233	97.65 84	90.31 379	98.89 20	98.93 50	99.36 21	84.57 316	99.92 5	97.81 47	99.56 112	99.39 105

test_cas_vis1_n_1920		95.34 216	95.67 203	94.35 308	98.21 201	86.83 323	95.61 218	99.26 29	90.45 296	98.17 127	98.96 61	84.43 317	98.31 360	96.74 84	99.17 213	97.90 305

h-mvs33		96.29 176	95.63 206	98.26 70	98.50 174	96.11 73	96.90 128	97.09 288	96.58 104	97.21 191	98.19 148	84.14 318	99.78 48	95.89 121	96.17 357	98.89 203

hse-mvs2		95.77 197	95.09 218	97.79 108	97.84 244	95.51 97	95.66 212	95.43 328	96.58 104	97.21 191	96.16 301	84.14 318	99.54 177	95.89 121	96.92 338	98.32 267

DIV-MVS_self_test		94.73 241	94.64 241	95.01 275	95.86 349	87.00 319	91.33 356	98.08 240	93.34 236	97.10 200	97.34 234	84.02 320	99.31 249	95.15 169	99.55 118	98.72 226

cl____		94.73 241	94.64 241	95.01 275	95.85 350	87.00 319	91.33 356	98.08 240	93.34 236	97.10 200	97.33 235	84.01 321	99.30 252	95.14 170	99.56 112	98.71 229

Vis-MVSNet (Re-imp)		95.11 227	94.85 230	95.87 238	99.12 94	89.17 271	97.54 97	94.92 334	96.50 109	96.58 237	97.27 238	83.64 322	99.48 195	88.42 331	99.67 85	98.97 187

FA-MVS(test-final)		94.91 235	94.89 228	94.99 277	97.51 286	88.11 296	98.27 44	95.20 331	92.40 269	96.68 231	98.60 96	83.44 323	99.28 258	93.34 240	98.53 280	97.59 323

dmvs_re		92.08 316	91.27 318	94.51 302	97.16 311	92.79 200	95.65 214	92.64 359	94.11 214	92.74 353	90.98 385	83.41 324	94.44 393	80.72 380	94.07 377	96.29 361

PVSNet_0	81.89 21	84.49 361	83.21 364	88.34 373	95.76 354	74.97 397	83.49 390	92.70 358	78.47 386	87.94 387	86.90 394	83.38 325	96.63 387	73.44 392	66.86 398	93.40 385

test_fmvs1_n		95.21 222	95.28 211	94.99 277	98.15 214	89.13 274	96.81 133	99.43 20	86.97 337	97.21 191	98.92 66	83.00 326	97.13 378	98.09 37	98.94 240	98.72 226

CMPMVS	73.10 23	92.74 303	91.39 315	96.77 190	93.57 387	94.67 134	94.21 285	97.67 264	80.36 380	93.61 333	96.60 280	82.85 327	97.35 376	84.86 365	98.78 258	98.29 274
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_fmvs1		94.51 258	94.60 245	94.26 312	95.91 347	87.92 298	95.35 234	99.02 74	86.56 341	96.79 223	98.52 103	82.64 328	97.00 381	97.87 44	98.71 266	97.88 307

EU-MVSNet		94.25 264	94.47 253	93.60 324	98.14 216	82.60 366	97.24 110	92.72 357	85.08 355	98.48 90	98.94 64	82.59 329	98.76 321	97.47 63	99.53 125	99.44 96

baseline1		93.14 298	92.64 299	94.62 295	97.34 301	87.20 316	96.67 148	93.02 352	94.71 193	96.51 242	95.83 316	81.64 330	98.60 338	90.00 309	88.06 391	98.07 288

test1111		94.53 257	94.81 234	93.72 321	99.06 102	81.94 371	98.31 39	83.87 396	96.37 114	98.49 88	99.17 42	81.49 331	99.73 83	96.64 86	99.86 31	99.49 71

CVMVSNet		92.33 310	92.79 293	90.95 362	97.26 306	75.84 394	95.29 240	92.33 362	81.86 371	96.27 254	98.19 148	81.44 332	98.46 350	94.23 212	98.29 292	98.55 244

EPNet_dtu		91.39 325	90.75 328	93.31 329	90.48 398	82.61 365	94.80 262	92.88 354	93.39 234	81.74 396	94.90 338	81.36 333	99.11 286	88.28 333	98.87 248	98.21 280
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ECVR-MVS		94.37 263	94.48 252	94.05 317	98.95 113	83.10 362	98.31 39	82.48 397	96.20 122	98.23 120	99.16 43	81.18 334	99.66 136	95.95 117	99.83 43	99.38 107

test_yl		94.40 260	94.00 268	95.59 247	96.95 318	89.52 265	94.75 266	95.55 325	96.18 125	96.79 223	96.14 304	81.09 335	99.18 273	90.75 290	97.77 310	98.07 288

DCV-MVSNet		94.40 260	94.00 268	95.59 247	96.95 318	89.52 265	94.75 266	95.55 325	96.18 125	96.79 223	96.14 304	81.09 335	99.18 273	90.75 290	97.77 310	98.07 288

MIMVSNet		93.42 291	92.86 290	95.10 271	98.17 210	88.19 290	98.13 55	93.69 343	92.07 271	95.04 298	98.21 147	80.95 337	99.03 297	81.42 378	98.06 301	98.07 288

PAPM		87.64 356	85.84 362	93.04 336	96.54 327	84.99 346	88.42 385	95.57 324	79.52 382	83.82 393	93.05 361	80.57 338	98.41 352	62.29 397	92.79 381	95.71 368

HyFIR lowres test		93.72 281	92.65 298	96.91 180	98.93 117	91.81 230	91.23 360	98.52 182	82.69 369	96.46 244	96.52 286	80.38 339	99.90 14	90.36 304	98.79 257	99.03 178

FMVSNet3		95.26 221	94.94 223	96.22 221	96.53 328	90.06 256	95.99 190	97.66 266	94.11 214	97.99 147	97.91 184	80.22 340	99.63 146	94.60 197	99.44 155	98.96 188

RPMNet		94.68 248	94.60 245	94.90 282	95.44 361	88.15 292	96.18 174	98.86 113	97.43 74	94.10 317	98.49 106	79.40 341	99.76 62	95.69 130	95.81 359	96.81 349

LFMVS		95.32 218	94.88 229	96.62 197	98.03 222	91.47 235	97.65 84	90.72 376	99.11 9	97.89 158	98.31 125	79.20 342	99.48 195	93.91 226	99.12 221	98.93 195

ADS-MVSNet2		91.47 324	90.51 332	94.36 307	95.51 359	85.63 334	95.05 253	95.70 318	83.46 367	92.69 354	96.84 265	79.15 343	99.41 220	85.66 356	90.52 385	98.04 296

ADS-MVSNet		90.95 330	90.26 334	93.04 336	95.51 359	82.37 367	95.05 253	93.41 349	83.46 367	92.69 354	96.84 265	79.15 343	98.70 327	85.66 356	90.52 385	98.04 296

MDTV_nov1_ep13_2view						57.28 404	94.89 259		80.59 378	94.02 321		78.66 345		85.50 358		97.82 311

cl22		93.25 296	92.84 292	94.46 304	94.30 376	86.00 332	91.09 364	96.64 306	90.74 290	95.79 275	96.31 296	78.24 346	98.77 319	94.15 215	98.34 289	98.62 237

PatchmatchNet		91.98 318	91.87 308	92.30 353	94.60 373	79.71 378	95.12 246	93.59 348	89.52 307	93.61 333	97.02 253	77.94 347	99.18 273	90.84 286	94.57 376	98.01 299
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												77.80 348				98.06 292

CR-MVSNet		93.29 295	92.79 293	94.78 290	95.44 361	88.15 292	96.18 174	97.20 282	84.94 360	94.10 317	98.57 98	77.67 349	99.39 226	95.17 165	95.81 359	96.81 349

Patchmtry		95.03 232	94.59 247	96.33 215	94.83 370	90.82 246	96.38 159	97.20 282	96.59 103	97.49 177	98.57 98	77.67 349	99.38 229	92.95 251	99.62 93	98.80 215

tpmrst		90.31 333	90.61 331	89.41 369	94.06 381	72.37 400	95.06 252	93.69 343	88.01 326	92.32 362	96.86 263	77.45 351	98.82 314	91.04 280	87.01 392	97.04 337

sam_mvs												77.38 352

patchmatchnet-post											96.84 265	77.36 353	99.42 211

Patchmatch-RL test		94.66 249	94.49 251	95.19 266	98.54 167	88.91 276	92.57 333	98.74 147	91.46 282	98.32 111	97.75 199	77.31 354	98.81 316	96.06 107	99.61 99	97.85 309

tpmvs		90.79 331	90.87 325	90.57 365	92.75 393	76.30 392	95.79 205	93.64 347	91.04 288	91.91 365	96.26 297	77.19 355	98.86 313	89.38 318	89.85 388	96.56 356

test_post											10.87 400	76.83 356	99.07 291

Patchmatch-test		93.60 287	93.25 282	94.63 294	96.14 343	87.47 309	96.04 185	94.50 338	93.57 229	96.47 243	96.97 256	76.50 357	98.61 336	90.67 296	98.41 288	97.81 313

MDTV_nov1_ep13			91.28 317		94.31 375	73.51 398	94.80 262	93.16 351	86.75 340	93.45 339	97.40 224	76.37 358	98.55 342	88.85 324	96.43 352

EMVS		89.06 346	89.22 340	88.61 372	93.00 390	77.34 388	82.91 392	90.92 373	94.64 196	92.63 358	91.81 376	76.30 359	97.02 380	83.83 371	96.90 340	91.48 391

test_post1							94.98 257				10.37 401	76.21 360	99.04 294	89.47 316

GA-MVS		92.83 302	92.15 306	94.87 284	96.97 317	87.27 315	90.03 374	96.12 309	91.83 277	94.05 320	94.57 341	76.01 361	98.97 306	92.46 257	97.34 334	98.36 265

PatchT		93.75 280	93.57 277	94.29 311	95.05 368	87.32 314	96.05 184	92.98 353	97.54 70	94.25 313	98.72 83	75.79 362	99.24 267	95.92 119	95.81 359	96.32 360

E-PMN		89.52 344	89.78 337	88.73 371	93.14 388	77.61 386	83.26 391	92.02 363	94.82 190	93.71 329	93.11 355	75.31 363	96.81 383	85.81 353	96.81 345	91.77 390

DeepMVS_CX				77.17 379	90.94 397	85.28 341		74.08 402	52.51 396	80.87 397	88.03 390	75.25 364	70.63 399	59.23 399	84.94 394	75.62 394

AUN-MVS		93.95 278	92.69 297	97.74 111	97.80 252	95.38 105	95.57 221	95.46 327	91.26 285	92.64 357	96.10 307	74.67 365	99.55 174	93.72 232	96.97 337	98.30 271

CHOSEN 280x420		89.98 337	89.19 343	92.37 352	95.60 358	81.13 375	86.22 388	97.09 288	81.44 375	87.44 389	93.15 354	73.99 366	99.47 197	88.69 327	99.07 228	96.52 357

thres200		91.00 329	90.42 333	92.77 344	97.47 292	83.98 359	94.01 295	91.18 372	95.12 179	95.44 286	91.21 382	73.93 367	99.31 249	77.76 388	97.63 323	95.01 376

test-LLR		89.97 338	89.90 336	90.16 366	94.24 378	74.98 395	89.89 376	89.06 384	92.02 272	89.97 379	90.77 386	73.92 368	98.57 339	91.88 264	97.36 332	96.92 340

test0.0.03 1		90.11 334	89.21 341	92.83 343	93.89 383	86.87 322	91.74 350	88.74 386	92.02 272	94.71 304	91.14 383	73.92 368	94.48 392	83.75 373	92.94 380	97.16 334

tpm cat1		88.01 354	87.33 355	90.05 368	94.48 374	76.28 393	94.47 274	94.35 340	73.84 394	89.26 383	95.61 323	73.64 370	98.30 361	84.13 368	86.20 393	95.57 372

tfpn200view9		91.55 323	91.00 322	93.21 333	98.02 223	84.35 354	95.70 208	90.79 374	96.26 119	95.90 273	92.13 373	73.62 371	99.42 211	78.85 385	97.74 313	95.85 365

thres400		91.68 322	91.00 322	93.71 322	98.02 223	84.35 354	95.70 208	90.79 374	96.26 119	95.90 273	92.13 373	73.62 371	99.42 211	78.85 385	97.74 313	97.36 330

test_method		66.88 363	66.13 366	69.11 380	62.68 402	25.73 406	49.76 394	96.04 311	14.32 398	64.27 399	91.69 378	73.45 373	88.05 397	76.06 390	66.94 397	93.54 383

thres100view900		91.76 321	91.26 320	93.26 330	98.21 201	84.50 352	96.39 156	90.39 377	96.87 93	96.33 249	93.08 359	73.44 374	99.42 211	78.85 385	97.74 313	95.85 365

thres600view7		92.03 317	91.43 314	93.82 319	98.19 204	84.61 351	96.27 166	90.39 377	96.81 95	96.37 248	93.11 355	73.44 374	99.49 192	80.32 381	97.95 304	97.36 330

MVSTER		94.21 267	93.93 271	95.05 273	95.83 351	86.46 326	95.18 245	97.65 268	92.41 268	97.94 154	98.00 175	72.39 376	99.58 163	96.36 97	99.56 112	99.12 163

JIA-IIPM		91.79 320	90.69 329	95.11 269	93.80 384	90.98 243	94.16 287	91.78 366	96.38 113	90.30 377	99.30 28	72.02 377	98.90 308	88.28 333	90.17 387	95.45 373

tpm		91.08 328	90.85 326	91.75 358	95.33 364	78.09 383	95.03 255	91.27 371	88.75 317	93.53 336	97.40 224	71.24 378	99.30 252	91.25 277	93.87 378	97.87 308

baseline2		89.65 343	88.44 349	93.25 331	95.62 357	82.71 363	93.82 304	85.94 393	88.89 316	87.35 390	92.54 368	71.23 379	99.33 245	86.01 351	94.60 375	97.72 315

CostFormer		89.75 341	89.25 339	91.26 361	94.69 372	78.00 385	95.32 237	91.98 364	81.50 374	90.55 374	96.96 258	71.06 380	98.89 309	88.59 329	92.63 382	96.87 343

FPMVS		89.92 339	88.63 347	93.82 319	98.37 186	96.94 45	91.58 351	93.34 350	88.00 327	90.32 376	97.10 248	70.87 381	91.13 396	71.91 394	96.16 358	93.39 386

EPMVS		89.26 345	88.55 348	91.39 360	92.36 394	79.11 381	95.65 214	79.86 398	88.60 319	93.12 346	96.53 284	70.73 382	98.10 367	90.75 290	89.32 389	96.98 338

FE-MVS		92.95 300	92.22 304	95.11 269	97.21 309	88.33 288	98.54 23	93.66 346	89.91 304	96.21 258	98.14 152	70.33 383	99.50 187	87.79 337	98.24 294	97.51 325

tmp_tt		57.23 364	62.50 367	41.44 381	34.77 403	49.21 405	83.93 389	60.22 405	15.31 397	71.11 398	79.37 396	70.09 384	44.86 400	64.76 396	82.93 396	30.25 396

ET-MVSNet_ETH3D		91.12 326	89.67 338	95.47 256	96.41 331	89.15 273	91.54 352	90.23 380	89.07 312	86.78 392	92.84 363	69.39 385	99.44 207	94.16 214	96.61 350	97.82 311

dp		88.08 353	88.05 351	88.16 376	92.85 391	68.81 402	94.17 286	92.88 354	85.47 351	91.38 370	96.14 304	68.87 386	98.81 316	86.88 348	83.80 395	96.87 343

iter_conf_final		94.54 256	93.91 272	96.43 209	97.23 308	90.41 255	96.81 133	98.10 237	93.87 221	96.80 222	97.89 185	68.02 387	99.72 88	96.73 85	99.77 58	99.18 149

tpm2		88.47 350	87.69 354	90.79 363	94.98 369	77.34 388	95.09 248	91.83 365	77.51 389	89.40 382	96.41 290	67.83 388	98.73 323	83.58 374	92.60 383	96.29 361

pmmvs3		90.00 336	88.90 346	93.32 328	94.20 380	85.34 338	91.25 359	92.56 361	78.59 385	93.82 324	95.17 330	67.36 389	98.69 328	89.08 322	98.03 302	95.92 364

thisisatest0515		90.43 332	89.18 344	94.17 315	97.07 315	85.44 337	89.75 380	87.58 388	88.28 323	93.69 331	91.72 377	65.27 390	99.58 163	90.59 297	98.67 269	97.50 327

tttt0517		93.31 294	92.56 301	95.57 249	98.71 143	87.86 300	97.44 100	87.17 390	95.79 148	97.47 181	96.84 265	64.12 391	99.81 37	96.20 103	99.32 192	99.02 181

thisisatest0530		92.71 304	91.76 312	95.56 251	98.42 183	88.23 289	96.03 186	87.35 389	94.04 217	96.56 239	95.47 326	64.03 392	99.77 57	94.78 190	99.11 222	98.68 233

iter_conf05		93.65 285	93.05 284	95.46 257	96.13 344	87.45 310	95.95 196	98.22 217	92.66 262	97.04 208	97.89 185	63.52 393	99.72 88	96.19 104	99.82 47	99.21 141

FMVSNet5		93.39 292	92.35 302	96.50 205	95.83 351	90.81 248	97.31 105	98.27 211	92.74 260	96.27 254	98.28 134	62.23 394	99.67 130	90.86 285	99.36 177	99.03 178

IB-MVS	85.98 20	88.63 349	86.95 359	93.68 323	95.12 367	84.82 350	90.85 366	90.17 381	87.55 330	88.48 386	91.34 381	58.01 395	99.59 161	87.24 347	93.80 379	96.63 355
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
gg-mvs-nofinetune		88.28 352	86.96 358	92.23 354	92.84 392	84.44 353	98.19 52	74.60 400	99.08 10	87.01 391	99.47 11	56.93 396	98.23 363	78.91 384	95.61 365	94.01 382

KD-MVS_2432*1600		88.93 347	87.74 352	92.49 348	88.04 399	81.99 369	89.63 381	95.62 321	91.35 283	95.06 295	93.11 355	56.58 397	98.63 334	85.19 361	95.07 368	96.85 345

miper_refine_blended		88.93 347	87.74 352	92.49 348	88.04 399	81.99 369	89.63 381	95.62 321	91.35 283	95.06 295	93.11 355	56.58 397	98.63 334	85.19 361	95.07 368	96.85 345

GG-mvs-BLEND				90.60 364	91.00 396	84.21 357	98.23 46	72.63 403		82.76 394	84.11 395	56.14 399	96.79 384	72.20 393	92.09 384	90.78 392

TESTMET0.1,1		87.20 358	86.57 360	89.07 370	93.62 386	72.84 399	89.89 376	87.01 391	85.46 352	89.12 384	90.20 388	56.00 400	97.72 373	90.91 284	96.92 338	96.64 353

test2506		89.86 340	89.16 345	91.97 356	98.95 113	76.83 391	98.54 23	61.07 404	96.20 122	97.07 206	99.16 43	55.19 401	99.69 119	96.43 95	99.83 43	99.38 107

test-mter		87.92 355	87.17 356	90.16 366	94.24 378	74.98 395	89.89 376	89.06 384	86.44 342	89.97 379	90.77 386	54.96 402	98.57 339	91.88 264	97.36 332	96.92 340

myMVS_eth3d		87.16 359	85.61 363	91.82 357	95.19 365	79.32 379	92.46 336	91.35 368	90.67 293	91.76 367	87.61 391	41.96 403	98.50 346	82.66 375	96.84 342	97.65 318

testing3		89.72 342	88.26 350	94.10 316	97.66 275	84.30 356	94.80 262	88.25 387	94.66 194	95.07 294	92.51 369	41.15 404	99.43 209	91.81 267	98.44 286	98.55 244

test123		12.59 366	15.49 369	3.87 382	6.07 404	2.55 407	90.75 368	2.59 407	2.52 400	5.20 402	13.02 399	4.96 405	1.85 402	5.20 400	9.09 399	7.23 397

testmvs		12.33 367	15.23 370	3.64 383	5.77 405	2.23 408	88.99 383	3.62 406	2.30 401	5.29 401	13.09 398	4.52 406	1.95 401	5.16 401	8.32 400	6.75 398

test_blank		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uanet_test		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

DCPMVS		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

sosnet-low-res		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

sosnet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uncertanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

Regformer		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

ab-mvs-re		7.91 369	10.55 372	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	94.94 335	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

WAC-MVS						79.32 379								85.41 359

FOURS1					99.59 18	98.20 7	99.03 7	99.25 30	98.96 18	98.87 56

MSC_two_6792asdad				98.22 75	97.75 264	95.34 110		98.16 231					99.75 68	95.87 123	99.51 135	99.57 47

No_MVS				98.22 75	97.75 264	95.34 110		98.16 231					99.75 68	95.87 123	99.51 135	99.57 47

eth-test2					0.00 406

eth-test					0.00 406

IU-MVS					99.22 69	95.40 103		98.14 234	85.77 349	98.36 104				95.23 162	99.51 135	99.49 71

save fliter					98.48 177	94.71 131	94.53 273	98.41 195	95.02 184

test_0728_SECOND				98.25 73	99.23 66	95.49 101	96.74 139	98.89 102					99.75 68	95.48 145	99.52 130	99.53 57

GSMVS																98.06 292

test_part2					99.03 108	96.07 74				98.08 138

MTGPA								98.73 148

MTMP							96.55 150	74.60 400

gm-plane-assit					91.79 395	71.40 401			81.67 372		90.11 389		98.99 300	84.86 365

test9_res														91.29 274	98.89 247	99.00 182

agg_prior2														90.34 305	98.90 244	99.10 170

agg_prior					97.80 252	94.96 126		98.36 202		93.49 337			99.53 179

test_prior4						95.38 105	93.61 312

test_prior				97.46 138	97.79 257	94.26 155		98.42 194					99.34 243			98.79 216

旧先验2							93.35 319		77.95 388	95.77 279			98.67 332	90.74 293

新几何2							93.43 315

无先验							93.20 322	97.91 249	80.78 377				99.40 222	87.71 338		97.94 303

原ACMM2							92.82 327

testdata2													99.46 200	87.84 336

testdata1							92.77 328		93.78 223

plane_prior7					98.70 145	94.67 134

plane_prior5								98.75 145					99.46 200	92.59 254	99.20 208	99.28 128

plane_prior4											96.77 271

plane_prior3						94.51 141			95.29 172	96.16 261

plane_prior2							96.50 152		96.36 115

plane_prior1					98.49 175

plane_prior						94.29 150	95.42 226		94.31 207						98.93 242

n2								0.00 408

nn								0.00 408

door-mid								98.17 227

test11								98.08 240

door								97.81 258

HQP5-MVS						92.47 207

HQP-NCC					97.85 239		94.26 278		93.18 244	92.86 350

ACMP_Plane					97.85 239		94.26 278		93.18 244	92.86 350

BP-MVS														90.51 300

HQP4-MVS										92.87 349			99.23 269			99.06 175

HQP3-MVS								98.43 191							98.74 262

NP-MVS					98.14 216	93.72 172					95.08 331

ACMMP++_ref															99.52 130

ACMMP++															99.55 118

High-resolution multi-view benchmark