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 49	99.81 2	96.38 63	98.87 10	99.30 28	99.01 20	99.63 14	99.66 3	99.27 2	99.68 124	97.75 53	99.89 24	99.62 35

UniMVSNet_ETH3D		99.12 3	99.28 3	98.65 43	99.77 5	96.34 66	99.18 6	99.20 37	99.67 2	99.73 5	99.65 5	99.15 3	99.86 27	97.22 70	99.92 15	99.77 11

test_fmvsmconf0.01_n		98.57 18	98.74 17	98.06 88	99.39 45	94.63 136	96.70 149	99.82 1	95.44 170	99.64 13	99.52 7	98.96 4	99.74 79	99.38 3	99.86 30	99.81 7

XVG-OURS-SEG-HR		97.38 119	97.07 135	98.30 68	99.01 109	97.41 35	94.66 272	99.02 80	95.20 178	98.15 131	97.52 217	98.83 5	98.43 360	94.87 187	96.41 359	99.07 170

ACMH	93.61 9	98.44 26	98.76 14	97.51 127	99.43 38	93.54 180	98.23 47	99.05 69	97.40 83	99.37 26	99.08 54	98.79 6	99.47 198	97.74 54	99.71 74	99.50 62
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 32	99.69 10	96.48 61	98.54 24	99.22 34	96.23 125	99.71 7	99.48 10	98.77 7	99.93 4	98.89 18	99.95 5	99.84 5

test_fmvsmconf0.1_n		98.41 28	98.54 27	98.03 93	99.16 82	94.61 137	96.18 178	99.73 3	95.05 186	99.60 17	99.34 24	98.68 8	99.72 90	99.21 8	99.85 37	99.76 16

LTVRE_ROB	96.88 1	99.18 2	99.34 2	98.72 38	99.71 9	96.99 45	99.69 2	99.57 15	99.02 19	99.62 15	99.36 21	98.53 9	99.52 183	98.58 29	99.95 5	99.66 29
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 33	98.41 35	97.99 96	98.94 115	94.60 138	96.00 193	99.64 13	94.99 189	99.43 22	99.18 40	98.51 10	99.71 104	99.13 11	99.84 39	99.67 27

TransMVSNet (Re)		98.38 29	98.67 19	97.51 127	99.51 29	93.39 186	98.20 52	98.87 116	98.23 44	99.48 19	99.27 30	98.47 11	99.55 175	96.52 93	99.53 126	99.60 36

pm-mvs1		98.47 25	98.67 19	97.86 103	99.52 28	94.58 139	98.28 43	99.00 89	97.57 70	99.27 32	99.22 34	98.32 12	99.50 188	97.09 77	99.75 65	99.50 62

jajsoiax		98.77 10	98.79 13	98.74 35	99.66 12	96.48 61	98.45 32	99.12 51	95.83 151	99.67 10	99.37 19	98.25 13	99.92 7	98.77 21	99.94 8	99.82 6

sd_testset		97.97 54	98.12 44	97.51 127	99.41 41	93.44 183	97.96 66	98.25 219	98.58 32	98.78 66	99.39 16	98.21 14	99.56 171	92.65 255	99.86 30	99.52 58

ACMH+	93.58 10	98.23 37	98.31 38	97.98 97	99.39 45	95.22 118	97.55 97	99.20 37	98.21 45	99.25 34	98.51 107	98.21 14	99.40 223	94.79 191	99.72 71	99.32 115

HPM-MVS_fast		98.32 31	98.13 43	98.88 24	99.54 25	97.48 31	98.35 36	99.03 77	95.88 147	97.88 160	98.22 149	98.15 16	99.74 79	96.50 94	99.62 93	99.42 97

wuyk23d		93.25 300	95.20 219	87.40 387	96.07 350	95.38 105	97.04 127	94.97 336	95.33 173	99.70 9	98.11 161	98.14 17	91.94 405	77.76 396	99.68 82	74.89 405

ACMM	93.33 11	98.05 49	97.79 77	98.85 25	99.15 85	97.55 27	96.68 150	98.83 133	95.21 177	98.36 105	98.13 157	98.13 18	99.62 152	96.04 113	99.54 122	99.39 104
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HPM-MVS		98.11 44	97.83 73	98.92 22	99.42 40	97.46 32	98.57 21	99.05 69	95.43 171	97.41 185	97.50 219	97.98 19	99.79 47	95.58 143	99.57 109	99.50 62
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
testgi		96.07 190	96.50 174	94.80 291	99.26 59	87.69 310	95.96 198	98.58 184	95.08 184	98.02 147	96.25 299	97.92 20	97.60 385	88.68 331	98.74 263	99.11 163

LPG-MVS_test		97.94 63	97.67 89	98.74 35	99.15 85	97.02 43	97.09 124	99.02 80	95.15 181	98.34 108	98.23 146	97.91 21	99.70 112	94.41 206	99.73 67	99.50 62

LGP-MVS_train				98.74 35	99.15 85	97.02 43		99.02 80	95.15 181	98.34 108	98.23 146	97.91 21	99.70 112	94.41 206	99.73 67	99.50 62

SED-MVS		97.94 63	97.90 63	98.07 86	99.22 68	95.35 108	96.79 140	98.83 133	96.11 131	99.08 42	98.24 144	97.87 23	99.72 90	95.44 152	99.51 136	99.14 153

test_241102_ONE					99.22 68	95.35 108		98.83 133	96.04 136	99.08 42	98.13 157	97.87 23	99.33 247

SDMVSNet		97.97 54	98.26 42	97.11 163	99.41 41	92.21 216	96.92 132	98.60 180	98.58 32	98.78 66	99.39 16	97.80 25	99.62 152	94.98 185	99.86 30	99.52 58

testf1		98.57 18	98.45 32	98.93 19	99.79 3	98.78 3	97.69 86	99.42 22	97.69 66	98.92 53	98.77 81	97.80 25	99.25 267	96.27 104	99.69 78	98.76 219

APD_test2		98.57 18	98.45 32	98.93 19	99.79 3	98.78 3	97.69 86	99.42 22	97.69 66	98.92 53	98.77 81	97.80 25	99.25 267	96.27 104	99.69 78	98.76 219

SD-MVS		97.37 121	97.70 84	96.35 216	98.14 218	95.13 122	96.54 155	98.92 105	95.94 143	99.19 37	98.08 163	97.74 28	95.06 399	95.24 164	99.54 122	98.87 206
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 83	97.70 84	98.16 79	98.78 137	95.72 87	96.23 176	99.02 80	93.92 225	98.62 77	98.99 60	97.69 29	99.62 152	96.18 108	99.87 27	99.15 150
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 65	99.22 68	95.66 92	97.90 71	99.08 61	98.31 40	99.02 45	98.74 84	97.68 30	99.61 159	97.77 52	99.85 37	99.70 25

MGCFI-Net		97.20 130	97.23 125	97.08 168	97.68 275	93.71 173	97.79 77	99.09 59	97.40 83	96.59 239	93.96 352	97.67 31	99.35 242	96.43 97	98.50 285	98.17 285

ANet_high		98.31 32	98.94 6	96.41 214	99.33 53	89.64 265	97.92 70	99.56 17	99.27 7	99.66 12	99.50 9	97.67 31	99.83 35	97.55 61	99.98 2	99.77 11

test_fmvsmvis_n_1920		98.08 46	98.47 29	96.93 178	99.03 107	93.29 188	96.32 168	99.65 10	95.59 162	99.71 7	99.01 57	97.66 33	99.60 161	99.44 2	99.83 42	97.90 309

casdiffmvs_mvg		97.83 79	98.11 45	97.00 175	98.57 164	92.10 224	95.97 196	99.18 40	97.67 69	99.00 48	98.48 112	97.64 34	99.50 188	96.96 82	99.54 122	99.40 100
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		97.23 128	97.21 127	97.30 149	97.65 281	94.39 145	97.84 74	99.05 69	97.42 78	96.68 232	93.85 354	97.63 35	99.33 247	96.29 102	98.47 286	98.18 283

canonicalmvs		97.23 128	97.21 127	97.30 149	97.65 281	94.39 145	97.84 74	99.05 69	97.42 78	96.68 232	93.85 354	97.63 35	99.33 247	96.29 102	98.47 286	98.18 283

GeoE		97.75 89	97.70 84	97.89 101	98.88 123	94.53 140	97.10 123	98.98 95	95.75 155	97.62 171	97.59 212	97.61 37	99.77 59	96.34 101	99.44 156	99.36 112

TranMVSNet+NR-MVSNet		98.33 30	98.30 40	98.43 58	99.07 100	95.87 82	96.73 147	99.05 69	98.67 28	98.84 61	98.45 113	97.58 38	99.88 23	96.45 96	99.86 30	99.54 53

cdsmvs_eth3d_5k		24.22 378	32.30 381	0.00 396	0.00 419	0.00 421	0.00 407	98.10 242	0.00 414	0.00 415	95.06 334	97.54 39	0.00 415	0.00 414	0.00 413	0.00 411

ACMP	92.54 13	97.47 112	97.10 132	98.55 50	99.04 106	96.70 52	96.24 175	98.89 108	93.71 229	97.97 152	97.75 200	97.44 40	99.63 147	93.22 248	99.70 77	99.32 115
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_djsdf		98.73 12	98.74 17	98.69 40	99.63 14	96.30 68	98.67 16	99.02 80	96.50 113	99.32 29	99.44 14	97.43 41	99.92 7	98.73 23	99.95 5	99.86 2

TDRefinement		98.90 6	98.86 9	99.02 7	99.54 25	98.06 9	99.34 4	99.44 20	98.85 25	99.00 48	99.20 36	97.42 42	99.59 162	97.21 71	99.76 58	99.40 100

anonymousdsp		98.72 15	98.63 21	98.99 11	99.62 15	97.29 38	98.65 20	99.19 39	95.62 160	99.35 28	99.37 19	97.38 43	99.90 18	98.59 28	99.91 18	99.77 11

PS-CasMVS		98.73 12	98.85 11	98.39 61	99.55 22	95.47 102	98.49 29	99.13 50	99.22 10	99.22 36	98.96 64	97.35 44	99.92 7	97.79 51	99.93 11	99.79 9

COLMAP_ROB	94.48 6	98.25 36	98.11 45	98.64 44	99.21 75	97.35 36	97.96 66	99.16 42	98.34 39	98.78 66	98.52 105	97.32 45	99.45 205	94.08 220	99.67 84	99.13 155
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 94	97.79 77	97.40 144	99.06 101	93.52 181	95.96 198	98.97 98	94.55 205	98.82 63	98.76 83	97.31 46	99.29 259	97.20 73	99.44 156	99.38 106

XXY-MVS		97.54 107	97.70 84	97.07 169	99.46 35	92.21 216	97.22 116	99.00 89	94.93 192	98.58 82	98.92 68	97.31 46	99.41 221	94.44 204	99.43 164	99.59 38

PEN-MVS		98.75 11	98.85 11	98.44 56	99.58 18	95.67 91	98.45 32	99.15 46	99.33 6	99.30 30	99.00 58	97.27 48	99.92 7	97.64 59	99.92 15	99.75 18

DTE-MVSNet		98.79 9	98.86 9	98.59 47	99.55 22	96.12 73	98.48 31	99.10 54	99.36 5	99.29 31	99.06 55	97.27 48	99.93 4	97.71 55	99.91 18	99.70 25

ZNCC-MVS		97.92 67	97.62 98	98.83 26	99.32 55	97.24 40	97.45 104	98.84 127	95.76 153	96.93 217	97.43 223	97.26 50	99.79 47	96.06 110	99.53 126	99.45 85

MP-MVS-pluss		97.69 94	97.36 117	98.70 39	99.50 32	96.84 48	95.38 234	98.99 92	92.45 273	98.11 134	98.31 128	97.25 51	99.77 59	96.60 90	99.62 93	99.48 76
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		97.89 73	97.63 96	98.67 41	99.35 50	96.84 48	96.36 165	98.79 143	95.07 185	97.88 160	98.35 124	97.24 52	99.72 90	96.05 112	99.58 106	99.45 85

Effi-MVS+		96.19 186	96.01 193	96.71 195	97.43 300	92.19 220	96.12 184	99.10 54	95.45 168	93.33 347	94.71 341	97.23 53	99.56 171	93.21 249	97.54 329	98.37 259

tt0805		97.44 114	97.56 104	97.11 163	99.55 22	96.36 64	98.66 19	95.66 322	98.31 40	97.09 206	95.45 328	97.17 54	98.50 355	98.67 26	97.45 335	96.48 368

PGM-MVS		97.88 74	97.52 108	98.96 14	99.20 77	97.62 22	97.09 124	99.06 65	95.45 168	97.55 173	97.94 183	97.11 55	99.78 50	94.77 194	99.46 152	99.48 76

test_0728_THIRD									96.62 104	98.40 99	98.28 137	97.10 56	99.71 104	95.70 131	99.62 93	99.58 39

APD-MVS_3200maxsize		98.13 43	97.90 63	98.79 30	98.79 134	97.31 37	97.55 97	98.92 105	97.72 62	98.25 119	98.13 157	97.10 56	99.75 70	95.44 152	99.24 207	99.32 115

OPM-MVS		97.54 107	97.25 123	98.41 59	99.11 94	96.61 57	95.24 245	98.46 193	94.58 204	98.10 136	98.07 165	97.09 58	99.39 227	95.16 170	99.44 156	99.21 140
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HFP-MVS		97.94 63	97.64 94	98.83 26	99.15 85	97.50 30	97.59 94	98.84 127	96.05 134	97.49 178	97.54 215	97.07 59	99.70 112	95.61 140	99.46 152	99.30 120

DVP-MVS		97.78 87	97.65 91	98.16 79	99.24 63	95.51 97	96.74 143	98.23 222	95.92 144	98.40 99	98.28 137	97.06 60	99.71 104	95.48 148	99.52 131	99.26 132
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 63	95.51 97	96.89 134	98.89 108	95.92 144	98.64 75	98.31 128	97.06 60

test_fmvsm_n_1920		98.08 46	98.29 41	97.43 140	98.88 123	93.95 164	96.17 182	99.57 15	95.66 157	99.52 18	98.71 87	97.04 62	99.64 143	99.21 8	99.87 27	98.69 228

casdiffmvs		97.50 109	97.81 75	96.56 205	98.51 173	91.04 244	95.83 206	99.09 59	97.23 90	98.33 111	98.30 132	97.03 63	99.37 235	96.58 92	99.38 174	99.28 127
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 52	97.76 81	98.79 30	99.43 38	97.21 42	97.15 119	98.90 107	96.58 108	98.08 139	97.87 189	97.02 64	99.76 64	95.25 163	99.59 104	99.40 100
Skip Steuart: Steuart Systems R&D Blog.
PC_three_1452									87.24 342	98.37 102	97.44 222	97.00 65	96.78 395	92.01 263	99.25 204	99.21 140

EC-MVSNet		97.90 72	97.94 62	97.79 107	98.66 151	95.14 121	98.31 40	99.66 9	97.57 70	95.95 271	97.01 256	96.99 66	99.82 37	97.66 58	99.64 89	98.39 257

DVP-MVS++		97.96 56	97.90 63	98.12 84	97.75 266	95.40 103	99.03 8	98.89 108	96.62 104	98.62 77	98.30 132	96.97 67	99.75 70	95.70 131	99.25 204	99.21 140

OPU-MVS				97.64 118	98.01 227	95.27 113	96.79 140				97.35 234	96.97 67	98.51 354	91.21 281	99.25 204	99.14 153

RE-MVS-def			97.88 68		98.81 130	98.05 10	97.55 97	98.86 119	97.77 57	98.20 123	98.07 165	96.94 69		95.49 145	99.20 209	99.26 132

APDe-MVS		98.14 40	98.03 53	98.47 55	98.72 142	96.04 76	98.07 59	99.10 54	95.96 141	98.59 81	98.69 89	96.94 69	99.81 39	96.64 88	99.58 106	99.57 46
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test_one_0601					99.05 105	95.50 100		98.87 116	97.21 91	98.03 146	98.30 132	96.93 71

GST-MVS		97.82 83	97.49 112	98.81 28	99.23 65	97.25 39	97.16 118	98.79 143	95.96 141	97.53 174	97.40 225	96.93 71	99.77 59	95.04 179	99.35 183	99.42 97

test_241102_TWO								98.83 133	96.11 131	98.62 77	98.24 144	96.92 73	99.72 90	95.44 152	99.49 143	99.49 70

LCM-MVSNet-Re		97.33 124	97.33 119	97.32 148	98.13 221	93.79 170	96.99 129	99.65 10	96.74 102	99.47 20	98.93 67	96.91 74	99.84 33	90.11 309	99.06 232	98.32 266

VPA-MVSNet		98.27 34	98.46 30	97.70 113	99.06 101	93.80 169	97.76 81	99.00 89	98.40 37	99.07 44	98.98 61	96.89 75	99.75 70	97.19 74	99.79 52	99.55 52

ACMMP		98.05 49	97.75 83	98.93 19	99.23 65	97.60 23	98.09 58	98.96 99	95.75 155	97.91 157	98.06 170	96.89 75	99.76 64	95.32 160	99.57 109	99.43 96
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 45	98.01 55	98.32 65	98.45 182	96.69 53	98.52 27	99.69 6	98.07 50	96.07 267	97.19 244	96.88 77	99.86 27	97.50 63	99.73 67	98.41 254

PMVS	89.60 17	96.71 163	96.97 141	95.95 235	99.51 29	97.81 17	97.42 108	97.49 279	97.93 53	95.95 271	98.58 99	96.88 77	96.91 392	89.59 317	99.36 178	93.12 397
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
region2R		97.92 67	97.59 101	98.92 22	99.22 68	97.55 27	97.60 92	98.84 127	96.00 139	97.22 190	97.62 210	96.87 79	99.76 64	95.48 148	99.43 164	99.46 81

CP-MVS		97.92 67	97.56 104	98.99 11	98.99 110	97.82 16	97.93 69	98.96 99	96.11 131	96.89 220	97.45 221	96.85 80	99.78 50	95.19 166	99.63 91	99.38 106

DPE-MVS		97.64 98	97.35 118	98.50 52	98.85 128	96.18 70	95.21 247	98.99 92	95.84 150	98.78 66	98.08 163	96.84 81	99.81 39	93.98 226	99.57 109	99.52 58
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_0402		97.84 78	97.97 59	97.47 136	99.19 79	94.07 159	96.71 148	98.73 155	98.66 29	98.56 83	98.41 118	96.84 81	99.69 119	94.82 189	99.81 47	98.64 232

CS-MVS-test		97.91 70	97.84 70	98.14 82	98.52 171	96.03 78	98.38 35	99.67 7	98.11 48	95.50 288	96.92 262	96.81 83	99.87 25	96.87 85	99.76 58	98.51 247

ACMMPR		97.95 60	97.62 98	98.94 16	99.20 77	97.56 26	97.59 94	98.83 133	96.05 134	97.46 183	97.63 209	96.77 84	99.76 64	95.61 140	99.46 152	99.49 70

Vis-MVSNet		98.27 34	98.34 37	98.07 86	99.33 53	95.21 120	98.04 60	99.46 18	97.32 87	97.82 167	99.11 50	96.75 85	99.86 27	97.84 48	99.36 178	99.15 150
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
Fast-Effi-MVS+		95.49 214	95.07 225	96.75 192	97.67 279	92.82 197	94.22 287	98.60 180	91.61 286	93.42 345	92.90 365	96.73 86	99.70 112	92.60 256	97.89 312	97.74 321

baseline		97.44 114	97.78 80	96.43 211	98.52 171	90.75 251	96.84 135	99.03 77	96.51 112	97.86 164	98.02 174	96.67 87	99.36 238	97.09 77	99.47 149	99.19 144

SR-MVS		98.00 53	97.66 90	99.01 9	98.77 138	97.93 12	97.38 109	98.83 133	97.32 87	98.06 142	97.85 190	96.65 88	99.77 59	95.00 182	99.11 223	99.32 115

tfpnnormal		97.72 92	97.97 59	96.94 177	99.26 59	92.23 215	97.83 76	98.45 194	98.25 43	99.13 40	98.66 91	96.65 88	99.69 119	93.92 228	99.62 93	98.91 196

DeepPCF-MVS	94.58 5	96.90 146	96.43 176	98.31 67	97.48 294	97.23 41	92.56 341	98.60 180	92.84 265	98.54 84	97.40 225	96.64 90	98.78 325	94.40 208	99.41 171	98.93 192

MVS_111021_LR		96.82 154	96.55 168	97.62 119	98.27 197	95.34 110	93.81 309	98.33 212	94.59 203	96.56 242	96.63 280	96.61 91	98.73 330	94.80 190	99.34 186	98.78 215

Gipuma		98.07 48	98.31 38	97.36 146	99.76 7	96.28 69	98.51 28	99.10 54	98.76 27	96.79 224	99.34 24	96.61 91	98.82 321	96.38 99	99.50 140	96.98 348
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
SR-MVS-dyc-post		98.14 40	97.84 70	99.02 7	98.81 130	98.05 10	97.55 97	98.86 119	97.77 57	98.20 123	98.07 165	96.60 93	99.76 64	95.49 145	99.20 209	99.26 132

MVS_111021_HR		96.73 160	96.54 170	97.27 152	98.35 190	93.66 177	93.42 319	98.36 208	94.74 195	96.58 240	96.76 274	96.54 94	98.99 307	94.87 187	99.27 202	99.15 150

SMA-MVS		97.48 111	97.11 131	98.60 46	98.83 129	96.67 54	96.74 143	98.73 155	91.61 286	98.48 91	98.36 123	96.53 95	99.68 124	95.17 168	99.54 122	99.45 85
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 98	99.64 13	94.20 156	98.67 16	99.14 49	99.08 14	99.42 23	99.23 33	96.53 95	99.91 15	99.27 6	99.93 11	99.73 21

mPP-MVS		97.91 70	97.53 107	99.04 5	99.22 68	97.87 15	97.74 84	98.78 147	96.04 136	97.10 201	97.73 203	96.53 95	99.78 50	95.16 170	99.50 140	99.46 81

XVS		97.96 56	97.63 96	98.94 16	99.15 85	97.66 20	97.77 79	98.83 133	97.42 78	96.32 253	97.64 208	96.49 98	99.72 90	95.66 136	99.37 175	99.45 85

X-MVStestdata		92.86 305	90.83 332	98.94 16	99.15 85	97.66 20	97.77 79	98.83 133	97.42 78	96.32 253	36.50 409	96.49 98	99.72 90	95.66 136	99.37 175	99.45 85

9.14			96.69 158		98.53 170		96.02 191	98.98 95	93.23 245	97.18 195	97.46 220	96.47 100	99.62 152	92.99 252	99.32 193

UA-Net		98.88 8	98.76 14	99.22 3	99.11 94	97.89 14	99.47 3	99.32 26	99.08 14	97.87 163	99.67 2	96.47 100	99.92 7	97.88 45	99.98 2	99.85 3

fmvsm_l_conf0.5_n		97.68 96	97.81 75	97.27 152	98.92 119	92.71 203	95.89 203	99.41 25	93.36 240	99.00 48	98.44 115	96.46 102	99.65 138	99.09 12	99.76 58	99.45 85

SF-MVS		97.60 102	97.39 115	98.22 75	98.93 117	95.69 89	97.05 126	99.10 54	95.32 174	97.83 166	97.88 188	96.44 103	99.72 90	94.59 203	99.39 173	99.25 136

fmvsm_s_conf0.1_n_a		97.80 85	98.01 55	97.18 158	99.17 81	92.51 206	96.57 153	99.15 46	93.68 232	98.89 56	99.30 28	96.42 104	99.37 235	99.03 14	99.83 42	99.66 29

xiu_mvs_v1_base_debu		95.62 209	95.96 197	94.60 299	98.01 227	88.42 288	93.99 299	98.21 223	92.98 259	95.91 273	94.53 344	96.39 105	99.72 90	95.43 155	98.19 298	95.64 379

xiu_mvs_v1_base		95.62 209	95.96 197	94.60 299	98.01 227	88.42 288	93.99 299	98.21 223	92.98 259	95.91 273	94.53 344	96.39 105	99.72 90	95.43 155	98.19 298	95.64 379

xiu_mvs_v1_base_debi		95.62 209	95.96 197	94.60 299	98.01 227	88.42 288	93.99 299	98.21 223	92.98 259	95.91 273	94.53 344	96.39 105	99.72 90	95.43 155	98.19 298	95.64 379

ETV-MVS		96.13 189	95.90 201	96.82 187	97.76 264	93.89 165	95.40 232	98.95 101	95.87 148	95.58 287	91.00 389	96.36 108	99.72 90	93.36 242	98.83 255	96.85 355

fmvsm_l_conf0.5_n_a		97.60 102	97.76 81	97.11 163	98.92 119	92.28 213	95.83 206	99.32 26	93.22 246	98.91 55	98.49 108	96.31 109	99.64 143	99.07 13	99.76 58	99.40 100

fmvsm_s_conf0.1_n		97.73 90	98.02 54	96.85 184	99.09 97	91.43 239	96.37 164	99.11 52	94.19 215	99.01 46	99.25 31	96.30 110	99.38 230	99.00 15	99.88 25	99.73 21

MP-MVS		97.64 98	97.18 129	99.00 10	99.32 55	97.77 18	97.49 103	98.73 155	96.27 122	95.59 286	97.75 200	96.30 110	99.78 50	93.70 236	99.48 147	99.45 85
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TinyColmap		96.00 195	96.34 181	94.96 282	97.90 239	87.91 303	94.13 294	98.49 191	94.41 207	98.16 129	97.76 197	96.29 112	98.68 339	90.52 302	99.42 167	98.30 270

Fast-Effi-MVS+-dtu		96.44 177	96.12 188	97.39 145	97.18 315	94.39 145	95.46 226	98.73 155	96.03 138	94.72 306	94.92 338	96.28 113	99.69 119	93.81 231	97.98 306	98.09 288

fmvsm_s_conf0.5_n_a		97.65 97	97.83 73	97.13 162	98.80 132	92.51 206	96.25 174	99.06 65	93.67 233	98.64 75	99.00 58	96.23 114	99.36 238	98.99 16	99.80 50	99.53 56

fmvsm_s_conf0.5_n		97.62 100	97.89 66	96.80 188	98.79 134	91.44 238	96.14 183	99.06 65	94.19 215	98.82 63	98.98 61	96.22 115	99.38 230	98.98 17	99.86 30	99.58 39

APD_test1		97.95 60	97.68 88	98.75 32	99.60 16	98.60 6	97.21 117	99.08 61	96.57 111	98.07 141	98.38 122	96.22 115	99.14 285	94.71 198	99.31 196	98.52 246

OMC-MVS		96.48 175	96.00 194	97.91 100	98.30 192	96.01 79	94.86 264	98.60 180	91.88 282	97.18 195	97.21 243	96.11 117	99.04 301	90.49 305	99.34 186	98.69 228

xiu_mvs_v2_base		94.22 270	94.63 249	92.99 344	97.32 310	84.84 352	92.12 353	97.84 259	91.96 280	94.17 318	93.43 356	96.07 118	99.71 104	91.27 278	97.48 332	94.42 389

CSCG		97.40 118	97.30 120	97.69 115	98.95 112	94.83 128	97.28 112	98.99 92	96.35 121	98.13 133	95.95 314	95.99 119	99.66 136	94.36 211	99.73 67	98.59 238

PHI-MVS		96.96 142	96.53 171	98.25 73	97.48 294	96.50 60	96.76 142	98.85 123	93.52 235	96.19 263	96.85 265	95.94 120	99.42 212	93.79 232	99.43 164	98.83 209

mamv4		99.05 5	98.91 8	99.46 2	98.94 115	99.62 2	97.98 65	99.70 5	99.49 3	99.78 2	99.22 34	95.92 121	99.95 3	99.31 4	99.83 42	98.83 209

TSAR-MVS + MP.		97.42 117	97.23 125	98.00 95	99.38 47	95.00 125	97.63 91	98.20 226	93.00 258	98.16 129	98.06 170	95.89 122	99.72 90	95.67 135	99.10 225	99.28 127
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		97.58 105	97.28 122	98.49 53	99.16 82	96.90 47	96.39 160	98.98 95	95.05 186	98.06 142	98.02 174	95.86 123	99.56 171	94.37 209	99.64 89	99.00 179

AllTest		97.20 130	96.92 146	98.06 88	99.08 98	96.16 71	97.14 121	99.16 42	94.35 209	97.78 168	98.07 165	95.84 124	99.12 289	91.41 275	99.42 167	98.91 196

TestCases				98.06 88	99.08 98	96.16 71		99.16 42	94.35 209	97.78 168	98.07 165	95.84 124	99.12 289	91.41 275	99.42 167	98.91 196

APD-MVS		97.00 137	96.53 171	98.41 59	98.55 167	96.31 67	96.32 168	98.77 148	92.96 263	97.44 184	97.58 214	95.84 124	99.74 79	91.96 264	99.35 183	99.19 144
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
pcd_1.5k_mvsjas		7.98 381	10.65 384	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	95.82 127	0.00 415	0.00 414	0.00 413	0.00 411

PS-MVSNAJss		98.53 23	98.63 21	98.21 78	99.68 11	94.82 129	98.10 57	99.21 35	96.91 97	99.75 3	99.45 13	95.82 127	99.92 7	98.80 20	99.96 4	99.89 1

PS-MVSNAJ		94.10 276	94.47 259	93.00 343	97.35 305	84.88 350	91.86 358	97.84 259	91.96 280	94.17 318	92.50 374	95.82 127	99.71 104	91.27 278	97.48 332	94.40 390

3Dnovator	96.53 2	97.61 101	97.64 94	97.50 131	97.74 269	93.65 178	98.49 29	98.88 114	96.86 99	97.11 200	98.55 103	95.82 127	99.73 85	95.94 121	99.42 167	99.13 155

MTAPA		98.14 40	97.84 70	99.06 4	99.44 37	97.90 13	97.25 113	98.73 155	97.69 66	97.90 158	97.96 180	95.81 131	99.82 37	96.13 109	99.61 99	99.45 85

DP-MVS		97.87 75	97.89 66	97.81 106	98.62 158	94.82 129	97.13 122	98.79 143	98.98 21	98.74 72	98.49 108	95.80 132	99.49 193	95.04 179	99.44 156	99.11 163

Anonymous20240529		97.96 56	98.04 52	97.71 112	98.69 149	94.28 154	97.86 73	98.31 216	98.79 26	99.23 35	98.86 76	95.76 133	99.61 159	95.49 145	99.36 178	99.23 138

LS3D		97.77 88	97.50 111	98.57 48	96.24 339	97.58 25	98.45 32	98.85 123	98.58 32	97.51 176	97.94 183	95.74 134	99.63 147	95.19 166	98.97 237	98.51 247

EIA-MVS		96.04 192	95.77 207	96.85 184	97.80 254	92.98 195	96.12 184	99.16 42	94.65 199	93.77 331	91.69 383	95.68 135	99.67 130	94.18 216	98.85 252	97.91 308

CNVR-MVS		96.92 144	96.55 168	98.03 93	98.00 231	95.54 95	94.87 263	98.17 232	94.60 201	96.38 250	97.05 252	95.67 136	99.36 238	95.12 176	99.08 227	99.19 144

CLD-MVS		95.47 217	95.07 225	96.69 197	98.27 197	92.53 205	91.36 364	98.67 170	91.22 294	95.78 280	94.12 351	95.65 137	98.98 309	90.81 290	99.72 71	98.57 240
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 99	98.79 134	94.37 148	98.84 12	99.15 46	99.37 4	99.67 10	99.43 15	95.61 138	99.72 90	98.12 37	99.86 30	99.73 21

EGC-MVSNET		83.08 373	77.93 376	98.53 51	99.57 19	97.55 27	98.33 39	98.57 185	4.71 411	10.38 412	98.90 72	95.60 139	99.50 188	95.69 133	99.61 99	98.55 243

ITE_SJBPF				97.85 104	98.64 152	96.66 55		98.51 190	95.63 159	97.22 190	97.30 238	95.52 140	98.55 351	90.97 285	98.90 245	98.34 265

DeepC-MVS_fast	94.34 7	96.74 158	96.51 173	97.44 139	97.69 274	94.15 157	96.02 191	98.43 197	93.17 253	97.30 187	97.38 231	95.48 141	99.28 261	93.74 233	99.34 186	98.88 204
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 32	99.51 29	96.61 57	98.55 23	99.17 41	99.05 17	99.17 38	98.79 78	95.47 142	99.89 21	97.95 44	99.91 18	99.75 18

FMVSNet1		97.95 60	98.08 47	97.56 122	99.14 92	93.67 174	98.23 47	98.66 172	97.41 82	99.00 48	99.19 37	95.47 142	99.73 85	95.83 128	99.76 58	99.30 120

MIMVSNet1		98.51 24	98.45 32	98.67 41	99.72 8	96.71 51	98.76 13	98.89 108	98.49 35	99.38 25	99.14 47	95.44 144	99.84 33	96.47 95	99.80 50	99.47 79

CP-MVSNet		98.42 27	98.46 30	98.30 68	99.46 35	95.22 118	98.27 45	98.84 127	99.05 17	99.01 46	98.65 94	95.37 145	99.90 18	97.57 60	99.91 18	99.77 11

segment_acmp												95.34 146

CDPH-MVS		95.45 219	94.65 246	97.84 105	98.28 195	94.96 126	93.73 311	98.33 212	85.03 367	95.44 289	96.60 281	95.31 147	99.44 208	90.01 311	99.13 219	99.11 163

3Dnovator+	96.13 3	97.73 90	97.59 101	98.15 81	98.11 222	95.60 93	98.04 60	98.70 164	98.13 47	96.93 217	98.45 113	95.30 148	99.62 152	95.64 138	98.96 238	99.24 137

MVS_Test		96.27 183	96.79 155	94.73 295	96.94 325	86.63 328	96.18 178	98.33 212	94.94 190	96.07 267	98.28 137	95.25 149	99.26 265	97.21 71	97.90 311	98.30 270

XVG-OURS		97.12 132	96.74 156	98.26 70	98.99 110	97.45 33	93.82 307	99.05 69	95.19 179	98.32 112	97.70 205	95.22 150	98.41 361	94.27 213	98.13 301	98.93 192

dcpmvs_2		97.12 132	97.99 57	94.51 305	99.11 94	84.00 361	97.75 82	99.65 10	97.38 85	99.14 39	98.42 117	95.16 151	99.96 2	95.52 144	99.78 55	99.58 39

MCST-MVS		96.24 184	95.80 205	97.56 122	98.75 139	94.13 158	94.66 272	98.17 232	90.17 309	96.21 261	96.10 308	95.14 152	99.43 210	94.13 219	98.85 252	99.13 155

EI-MVSNet-Vis-set		97.32 125	97.39 115	97.11 163	97.36 304	92.08 225	95.34 238	97.65 272	97.74 60	98.29 117	98.11 161	95.05 153	99.68 124	97.50 63	99.50 140	99.56 50

EI-MVSNet-UG-set		97.32 125	97.40 114	97.09 167	97.34 307	92.01 227	95.33 239	97.65 272	97.74 60	98.30 116	98.14 155	95.04 154	99.69 119	97.55 61	99.52 131	99.58 39

KD-MVS_self_test		97.86 77	98.07 48	97.25 155	99.22 68	92.81 198	97.55 97	98.94 102	97.10 93	98.85 59	98.88 74	95.03 155	99.67 130	97.39 67	99.65 87	99.26 132

ZD-MVS					98.43 184	95.94 80		98.56 186	90.72 299	96.66 235	97.07 250	95.02 156	99.74 79	91.08 282	98.93 243

DELS-MVS		96.17 187	96.23 184	95.99 231	97.55 290	90.04 258	92.38 350	98.52 188	94.13 217	96.55 244	97.06 251	94.99 157	99.58 164	95.62 139	99.28 200	98.37 259
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		96.59 169	96.93 144	95.55 256	98.88 123	87.12 320	94.47 277	99.30 28	94.12 218	96.65 237	98.41 118	94.98 158	99.87 25	95.81 130	99.78 55	99.66 29

ab-mvs		96.59 169	96.59 164	96.60 200	98.64 152	92.21 216	98.35 36	97.67 268	94.45 206	96.99 212	98.79 78	94.96 159	99.49 193	90.39 306	99.07 229	98.08 289

MSLP-MVS++		96.42 179	96.71 157	95.57 253	97.82 249	90.56 255	95.71 210	98.84 127	94.72 196	96.71 231	97.39 229	94.91 160	98.10 377	95.28 161	99.02 234	98.05 298

QAPM		95.88 199	95.57 214	96.80 188	97.90 239	91.84 231	98.18 54	98.73 155	88.41 330	96.42 248	98.13 157	94.73 161	99.75 70	88.72 329	98.94 241	98.81 212

RPSCF		97.87 75	97.51 109	98.95 15	99.15 85	98.43 7	97.56 96	99.06 65	96.19 128	98.48 91	98.70 88	94.72 162	99.24 271	94.37 209	99.33 191	99.17 147

DU-MVS		97.79 86	97.60 100	98.36 63	98.73 140	95.78 85	95.65 217	98.87 116	97.57 70	98.31 114	97.83 191	94.69 163	99.85 30	97.02 80	99.71 74	99.46 81

Baseline_NR-MVSNet		97.72 92	97.79 77	97.50 131	99.56 20	93.29 188	95.44 227	98.86 119	98.20 46	98.37 102	99.24 32	94.69 163	99.55 175	95.98 119	99.79 52	99.65 32

TEST9					97.84 246	95.23 115	93.62 313	98.39 204	86.81 348	93.78 329	95.99 310	94.68 165	99.52 183

UniMVSNet (Re)		97.83 79	97.65 91	98.35 64	98.80 132	95.86 84	95.92 201	99.04 76	97.51 75	98.22 122	97.81 195	94.68 165	99.78 50	97.14 75	99.75 65	99.41 99

UniMVSNet_NR-MVSNet		97.83 79	97.65 91	98.37 62	98.72 142	95.78 85	95.66 215	99.02 80	98.11 48	98.31 114	97.69 206	94.65 167	99.85 30	97.02 80	99.71 74	99.48 76

VPNet		97.26 127	97.49 112	96.59 201	99.47 34	90.58 253	96.27 170	98.53 187	97.77 57	98.46 94	98.41 118	94.59 168	99.68 124	94.61 199	99.29 199	99.52 58

train_agg		95.46 218	94.66 245	97.88 102	97.84 246	95.23 115	93.62 313	98.39 204	87.04 344	93.78 329	95.99 310	94.58 169	99.52 183	91.76 272	98.90 245	98.89 200

test_8					97.81 250	95.07 124	93.54 316	98.38 206	87.04 344	93.71 333	95.96 313	94.58 169	99.52 183

API-MVS		95.09 235	95.01 228	95.31 265	96.61 331	94.02 161	96.83 136	97.18 288	95.60 161	95.79 278	94.33 349	94.54 171	98.37 366	85.70 360	98.52 282	93.52 394

Test By Simon												94.51 172

MSDG		95.33 223	95.13 222	95.94 237	97.40 302	91.85 230	91.02 375	98.37 207	95.30 175	96.31 255	95.99 310	94.51 172	98.38 364	89.59 317	97.65 326	97.60 330

TSAR-MVS + GP.		96.47 176	96.12 188	97.49 134	97.74 269	95.23 115	94.15 291	96.90 299	93.26 244	98.04 145	96.70 276	94.41 174	98.89 316	94.77 194	99.14 217	98.37 259

NR-MVSNet		97.96 56	97.86 69	98.26 70	98.73 140	95.54 95	98.14 55	98.73 155	97.79 56	99.42 23	97.83 191	94.40 175	99.78 50	95.91 123	99.76 58	99.46 81

AdaColmap		95.11 233	94.62 250	96.58 202	97.33 309	94.45 144	94.92 261	98.08 244	93.15 254	93.98 327	95.53 326	94.34 176	99.10 295	85.69 361	98.61 277	96.20 373

FC-MVSNet-test		98.16 38	98.37 36	97.56 122	99.49 33	93.10 193	98.35 36	99.21 35	98.43 36	98.89 56	98.83 77	94.30 177	99.81 39	97.87 46	99.91 18	99.77 11

Effi-MVS+-dtu		96.81 155	96.09 190	98.99 11	96.90 327	98.69 5	96.42 159	98.09 243	95.86 149	95.15 296	95.54 325	94.26 178	99.81 39	94.06 221	98.51 284	98.47 251

ambc				96.56 205	98.23 202	91.68 234	97.88 72	98.13 240		98.42 97	98.56 102	94.22 179	99.04 301	94.05 223	99.35 183	98.95 186

test20.03		96.58 171	96.61 163	96.48 209	98.49 177	91.72 233	95.68 214	97.69 267	96.81 100	98.27 118	97.92 186	94.18 180	98.71 333	90.78 292	99.66 86	99.00 179

HPM-MVS++		96.99 138	96.38 179	98.81 28	98.64 152	97.59 24	95.97 196	98.20 226	95.51 166	95.06 298	96.53 285	94.10 181	99.70 112	94.29 212	99.15 216	99.13 155

test_vis3_rt		97.04 135	96.98 140	97.23 157	98.44 183	95.88 81	96.82 137	99.67 7	90.30 306	99.27 32	99.33 27	94.04 182	96.03 398	97.14 75	97.83 313	99.78 10

test_fmvs3		97.38 119	97.56 104	96.84 186	98.63 156	92.81 198	97.60 92	99.61 14	90.87 297	98.76 71	99.66 3	94.03 183	97.90 379	99.24 7	99.68 82	99.81 7

PM-MVS		97.36 123	97.10 132	98.14 82	98.91 121	96.77 50	96.20 177	98.63 178	93.82 226	98.54 84	98.33 126	93.98 184	99.05 300	95.99 118	99.45 155	98.61 237

mvsany_test3		96.21 185	95.93 200	97.05 170	97.40 302	94.33 150	95.76 209	94.20 344	89.10 319	99.36 27	99.60 6	93.97 185	97.85 380	95.40 159	98.63 275	98.99 182

OpenMVS	94.22 8	95.48 216	95.20 219	96.32 218	97.16 316	91.96 228	97.74 84	98.84 127	87.26 341	94.36 315	98.01 176	93.95 186	99.67 130	90.70 298	98.75 262	97.35 341

v8		97.60 102	98.06 50	96.23 221	98.71 145	89.44 270	97.43 107	98.82 141	97.29 89	98.74 72	99.10 51	93.86 187	99.68 124	98.61 27	99.94 8	99.56 50

diffmvs		96.04 192	96.23 184	95.46 261	97.35 305	88.03 301	93.42 319	99.08 61	94.09 221	96.66 235	96.93 260	93.85 188	99.29 259	96.01 117	98.67 270	99.06 172
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		96.52 173	95.99 195	98.10 85	97.81 250	95.68 90	95.00 259	98.20 226	95.39 172	95.40 291	96.36 295	93.81 189	99.45 205	93.55 239	98.42 290	99.17 147

TAPA-MVS	93.32 12	94.93 240	94.23 266	97.04 172	98.18 209	94.51 141	95.22 246	98.73 155	81.22 386	96.25 259	95.95 314	93.80 190	98.98 309	89.89 313	98.87 249	97.62 328
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
FIs		97.93 66	98.07 48	97.48 135	99.38 47	92.95 196	98.03 62	99.11 52	98.04 52	98.62 77	98.66 91	93.75 191	99.78 50	97.23 69	99.84 39	99.73 21

OurMVSNet-221017-0		98.61 17	98.61 25	98.63 45	99.77 5	96.35 65	99.17 7	99.05 69	98.05 51	99.61 16	99.52 7	93.72 192	99.88 23	98.72 25	99.88 25	99.65 32

test_prior2							93.33 323		94.21 213	94.02 325	96.25 299	93.64 193		91.90 266	98.96 238

mvsany_test1		93.47 294	93.03 290	94.79 292	94.05 393	92.12 221	90.82 377	90.01 390	85.02 368	97.26 189	98.28 137	93.57 194	97.03 389	92.51 259	95.75 374	95.23 385

旧先验1					97.80 254	93.87 166		97.75 264			97.04 253	93.57 194			98.68 269	98.72 224

v10		97.55 106	97.97 59	96.31 219	98.60 160	89.64 265	97.44 105	99.02 80	96.60 106	98.72 74	99.16 44	93.48 196	99.72 90	98.76 22	99.92 15	99.58 39

v148		96.58 171	96.97 141	95.42 262	98.63 156	87.57 311	95.09 251	97.90 254	95.91 146	98.24 120	97.96 180	93.42 197	99.39 227	96.04 113	99.52 131	99.29 126

V42		97.04 135	97.16 130	96.68 198	98.59 162	91.05 243	96.33 167	98.36 208	94.60 201	97.99 148	98.30 132	93.32 198	99.62 152	97.40 66	99.53 126	99.38 106

new-patchmatchnet		95.67 207	96.58 165	92.94 346	97.48 294	80.21 386	92.96 329	98.19 231	94.83 193	98.82 63	98.79 78	93.31 199	99.51 187	95.83 128	99.04 233	99.12 160

test12				97.46 137	97.61 285	94.07 159		97.78 263		93.57 339		93.31 199	99.42 212		98.78 259	98.89 200

UGNet		96.81 155	96.56 167	97.58 121	96.64 330	93.84 168	97.75 82	97.12 291	96.47 116	93.62 336	98.88 74	93.22 201	99.53 180	95.61 140	99.69 78	99.36 112
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		96.49 174	96.18 187	97.42 142	98.25 199	94.29 151	94.77 268	98.07 248	89.81 313	97.97 152	98.33 126	93.11 202	99.08 297	95.46 151	99.84 39	98.89 200

v1144		96.84 150	97.08 134	96.13 228	98.42 185	89.28 273	95.41 231	98.67 170	94.21 213	97.97 152	98.31 128	93.06 203	99.65 138	98.06 41	99.62 93	99.45 85

MVSMamba_PlusPlus		97.43 116	97.98 58	95.78 244	98.88 123	89.70 263	98.03 62	98.85 123	99.18 11	96.84 222	99.12 48	93.04 204	99.91 15	98.38 32	99.55 118	97.73 322

iter_conf05		97.83 79	98.49 28	95.84 241	98.88 123	89.05 278	98.87 10	99.42 22	99.18 11	99.73 5	99.12 48	93.04 204	99.91 15	98.38 32	99.78 55	98.58 239

PVSNet_BlendedMVS		95.02 239	94.93 231	95.27 266	97.79 259	87.40 315	94.14 293	98.68 167	88.94 323	94.51 311	98.01 176	93.04 204	99.30 255	89.77 315	99.49 143	99.11 163

PVSNet_Blended		93.96 281	93.65 280	94.91 283	97.79 259	87.40 315	91.43 363	98.68 167	84.50 374	94.51 311	94.48 347	93.04 204	99.30 255	89.77 315	98.61 277	98.02 301

mvs_anonymous		95.36 221	96.07 192	93.21 337	96.29 338	81.56 378	94.60 274	97.66 270	93.30 243	96.95 216	98.91 71	93.03 208	99.38 230	96.60 90	97.30 340	98.69 228

v1192		96.83 153	97.06 136	96.15 227	98.28 195	89.29 272	95.36 235	98.77 148	93.73 228	98.11 134	98.34 125	93.02 209	99.67 130	98.35 34	99.58 106	99.50 62

F-COLMAP		95.30 225	94.38 263	98.05 92	98.64 152	96.04 76	95.61 221	98.66 172	89.00 322	93.22 348	96.40 293	92.90 210	99.35 242	87.45 349	97.53 330	98.77 218

bld_raw_dy_0_64		98.03 51	98.57 26	96.38 215	99.35 50	89.63 267	99.26 5	99.26 31	99.27 7	99.74 4	99.34 24	92.88 211	99.93 4	98.20 36	99.87 27	99.60 36

WR-MVS		96.90 146	96.81 152	97.16 159	98.56 166	92.20 219	94.33 280	98.12 241	97.34 86	98.20 123	97.33 236	92.81 212	99.75 70	94.79 191	99.81 47	99.54 53

v1240		96.74 158	97.02 139	95.91 238	98.18 209	88.52 287	95.39 233	98.88 114	93.15 254	98.46 94	98.40 121	92.80 213	99.71 104	98.45 31	99.49 143	99.49 70

MVS_0304		96.62 168	96.40 178	97.28 151	97.91 237	92.30 212	96.47 158	89.74 391	97.52 74	95.38 292	98.63 96	92.76 214	99.81 39	99.28 5	99.93 11	99.75 18

MVE	73.61 22	86.48 371	85.92 370	88.18 385	96.23 341	85.28 344	81.78 405	75.79 409	86.01 354	82.53 405	91.88 380	92.74 215	87.47 408	71.42 405	94.86 382	91.78 399
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DP-MVS Recon		95.55 212	95.13 222	96.80 188	98.51 173	93.99 163	94.60 274	98.69 165	90.20 308	95.78 280	96.21 301	92.73 216	98.98 309	90.58 301	98.86 251	97.42 338

CANet		95.86 200	95.65 211	96.49 208	96.41 336	90.82 248	94.36 279	98.41 201	94.94 190	92.62 364	96.73 275	92.68 217	99.71 104	95.12 176	99.60 102	98.94 188

v1921920		96.72 161	96.96 143	95.99 231	98.21 203	88.79 284	95.42 229	98.79 143	93.22 246	98.19 127	98.26 142	92.68 217	99.70 112	98.34 35	99.55 118	99.49 70

BH-untuned		94.69 252	94.75 243	94.52 304	97.95 236	87.53 312	94.07 296	97.01 295	93.99 223	97.10 201	95.65 321	92.65 219	98.95 314	87.60 344	96.74 352	97.09 345

LF4IMVS		96.07 190	95.63 212	97.36 146	98.19 206	95.55 94	95.44 227	98.82 141	92.29 276	95.70 284	96.55 283	92.63 220	98.69 336	91.75 273	99.33 191	97.85 313

v2v482		96.78 157	97.06 136	95.95 235	98.57 164	88.77 285	95.36 235	98.26 218	95.18 180	97.85 165	98.23 146	92.58 221	99.63 147	97.80 50	99.69 78	99.45 85

WB-MVSnew		91.50 328	91.29 321	92.14 363	94.85 380	80.32 385	93.29 324	88.77 394	88.57 329	94.03 324	92.21 376	92.56 222	98.28 371	80.21 389	97.08 341	97.81 317

EI-MVSNet		96.63 167	96.93 144	95.74 246	97.26 312	88.13 298	95.29 243	97.65 272	96.99 94	97.94 155	98.19 151	92.55 223	99.58 164	96.91 83	99.56 112	99.50 62

IterMVS-LS		96.92 144	97.29 121	95.79 243	98.51 173	88.13 298	95.10 250	98.66 172	96.99 94	98.46 94	98.68 90	92.55 223	99.74 79	96.91 83	99.79 52	99.50 62
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
VDD-MVS		97.37 121	97.25 123	97.74 110	98.69 149	94.50 143	97.04 127	95.61 326	98.59 31	98.51 86	98.72 85	92.54 225	99.58 164	96.02 115	99.49 143	99.12 160

MVS		90.02 340	89.20 347	92.47 358	94.71 382	86.90 324	95.86 204	96.74 306	64.72 406	90.62 377	92.77 368	92.54 225	98.39 363	79.30 391	95.56 376	92.12 398

test_vis1_rt		94.03 280	93.65 280	95.17 271	95.76 363	93.42 184	93.97 302	98.33 212	84.68 371	93.17 349	95.89 316	92.53 227	94.79 400	93.50 240	94.97 380	97.31 342

v144192		96.69 164	96.90 149	96.03 230	98.25 199	88.92 279	95.49 225	98.77 148	93.05 256	98.09 137	98.29 136	92.51 228	99.70 112	98.11 38	99.56 112	99.47 79

原ACMM1				96.58 202	98.16 214	92.12 221		98.15 238	85.90 357	93.49 341	96.43 290	92.47 229	99.38 230	87.66 343	98.62 276	98.23 277

VNet		96.84 150	96.83 151	96.88 182	98.06 223	92.02 226	96.35 166	97.57 278	97.70 65	97.88 160	97.80 196	92.40 230	99.54 178	94.73 196	98.96 238	99.08 168

114514_t		93.96 281	93.22 288	96.19 224	99.06 101	90.97 246	95.99 194	98.94 102	73.88 404	93.43 344	96.93 260	92.38 231	99.37 235	89.09 324	99.28 200	98.25 276

CPTT-MVS		96.69 164	96.08 191	98.49 53	98.89 122	96.64 56	97.25 113	98.77 148	92.89 264	96.01 270	97.13 246	92.23 232	99.67 130	92.24 261	99.34 186	99.17 147

MSP-MVS		97.45 113	96.92 146	99.03 6	99.26 59	97.70 19	97.66 88	98.89 108	95.65 158	98.51 86	96.46 289	92.15 233	99.81 39	95.14 173	98.58 280	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		94.21 272	93.03 290	97.76 109	96.94 325	97.44 34	96.97 130	97.15 289	87.89 339	92.00 369	92.73 370	92.14 234	99.12 289	83.92 375	97.51 331	96.73 362
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		95.95 196	95.80 205	96.42 212	99.28 57	90.62 252	95.31 241	99.08 61	88.40 331	96.97 215	98.17 154	92.11 235	99.78 50	93.64 237	99.21 208	98.86 207

BH-RMVSNet		94.56 260	94.44 262	94.91 283	97.57 287	87.44 314	93.78 310	96.26 311	93.69 231	96.41 249	96.50 288	92.10 236	99.00 305	85.96 358	97.71 320	98.31 268

新几何1				97.25 155	98.29 193	94.70 133		97.73 265	77.98 397	94.83 305	96.67 278	92.08 237	99.45 205	88.17 338	98.65 274	97.61 329

testdata				95.70 249	98.16 214	90.58 253		97.72 266	80.38 389	95.62 285	97.02 254	92.06 238	98.98 309	89.06 326	98.52 282	97.54 333

YYNet1		94.73 247	94.84 237	94.41 309	97.47 298	85.09 348	90.29 382	95.85 320	92.52 270	97.53 174	97.76 197	91.97 239	99.18 278	93.31 245	96.86 346	98.95 186

Anonymous20231206		95.27 226	95.06 227	95.88 239	98.72 142	89.37 271	95.70 211	97.85 257	88.00 337	96.98 214	97.62 210	91.95 240	99.34 245	89.21 322	99.53 126	98.94 188

MS-PatchMatch		94.83 244	94.91 233	94.57 302	96.81 328	87.10 321	94.23 286	97.34 283	88.74 326	97.14 197	97.11 248	91.94 241	98.23 373	92.99 252	97.92 309	98.37 259

MDA-MVSNet_test_wron		94.73 247	94.83 239	94.42 308	97.48 294	85.15 346	90.28 383	95.87 319	92.52 270	97.48 180	97.76 197	91.92 242	99.17 282	93.32 244	96.80 351	98.94 188

HQP_MVS		96.66 166	96.33 182	97.68 116	98.70 147	94.29 151	96.50 156	98.75 152	96.36 119	96.16 264	96.77 272	91.91 243	99.46 201	92.59 257	99.20 209	99.28 127

plane_prior6					98.38 187	94.37 148						91.91 243

iter_conf05_11		96.88 148	96.92 146	96.75 192	97.70 273	92.38 210	98.03 62	99.03 77	94.26 212	96.84 222	98.43 116	91.72 245	99.65 138	96.67 87	99.63 91	98.20 280

MVP-Stereo		95.69 205	95.28 217	96.92 179	98.15 216	93.03 194	95.64 220	98.20 226	90.39 305	96.63 238	97.73 203	91.63 246	99.10 295	91.84 269	97.31 339	98.63 234
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PatchMatch-RL		94.61 258	93.81 278	97.02 174	98.19 206	95.72 87	93.66 312	97.23 285	88.17 335	94.94 303	95.62 323	91.43 247	98.57 348	87.36 350	97.68 323	96.76 361

MDA-MVSNet-bldmvs		95.69 205	95.67 209	95.74 246	98.48 179	88.76 286	92.84 331	97.25 284	96.00 139	97.59 172	97.95 182	91.38 248	99.46 201	93.16 250	96.35 361	98.99 182

SSC-MVS		95.92 197	97.03 138	92.58 355	99.28 57	78.39 391	96.68 150	95.12 335	98.90 23	99.11 41	98.66 91	91.36 249	99.68 124	95.00 182	99.16 215	99.67 27

mvsmamba		98.16 38	98.06 50	98.44 56	99.53 27	95.87 82	98.70 14	98.94 102	97.71 64	98.85 59	99.10 51	91.35 250	99.83 35	98.47 30	99.90 23	99.64 34

PAPR		92.22 315	91.27 323	95.07 275	95.73 365	88.81 283	91.97 356	97.87 256	85.80 358	90.91 376	92.73 370	91.16 251	98.33 368	79.48 390	95.76 373	98.08 289

1314		92.38 312	92.30 307	92.64 354	95.42 372	85.15 346	95.86 204	96.97 297	85.40 363	90.62 377	93.06 363	91.12 252	97.80 382	86.74 355	95.49 377	94.97 387

WB-MVS		95.50 213	96.62 161	92.11 364	99.21 75	77.26 399	96.12 184	95.40 332	98.62 30	98.84 61	98.26 142	91.08 253	99.50 188	93.37 241	98.70 268	99.58 39

ppachtmachnet_test		94.49 264	94.84 237	93.46 330	96.16 345	82.10 373	90.59 379	97.48 280	90.53 303	97.01 211	97.59 212	91.01 254	99.36 238	93.97 227	99.18 213	98.94 188

PLC	91.02 16	94.05 279	92.90 293	97.51 127	98.00 231	95.12 123	94.25 284	98.25 219	86.17 353	91.48 374	95.25 330	91.01 254	99.19 277	85.02 370	96.69 354	98.22 278
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test222					98.17 212	93.24 191	92.74 336	97.61 277	75.17 402	94.65 308	96.69 277	90.96 256			98.66 272	97.66 325

CL-MVSNet_self_test		95.04 236	94.79 242	95.82 242	97.51 292	89.79 262	91.14 372	96.82 302	93.05 256	96.72 230	96.40 293	90.82 257	99.16 283	91.95 265	98.66 272	98.50 249

USDC		94.56 260	94.57 256	94.55 303	97.78 262	86.43 331	92.75 334	98.65 177	85.96 355	96.91 219	97.93 185	90.82 257	98.74 329	90.71 297	99.59 104	98.47 251

PCF-MVS	89.43 18	92.12 318	90.64 335	96.57 204	97.80 254	93.48 182	89.88 389	98.45 194	74.46 403	96.04 269	95.68 320	90.71 259	99.31 252	73.73 401	99.01 236	96.91 352
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PAPM_NR		94.61 258	94.17 270	95.96 233	98.36 189	91.23 241	95.93 200	97.95 251	92.98 259	93.42 345	94.43 348	90.53 260	98.38 364	87.60 344	96.29 363	98.27 274

our_test_3		94.20 274	94.58 254	93.07 339	96.16 345	81.20 381	90.42 381	96.84 300	90.72 299	97.14 197	97.13 246	90.47 261	99.11 292	94.04 224	98.25 296	98.91 196

MM		96.87 149	96.62 161	97.62 119	97.72 271	93.30 187	96.39 160	92.61 364	97.90 55	96.76 229	98.64 95	90.46 262	99.81 39	99.16 10	99.94 8	99.76 16

test_f		95.82 202	95.88 203	95.66 250	97.61 285	93.21 192	95.61 221	98.17 232	86.98 346	98.42 97	99.47 11	90.46 262	94.74 401	97.71 55	98.45 288	99.03 175

OpenMVS_ROB	91.80 14	93.64 290	93.05 289	95.42 262	97.31 311	91.21 242	95.08 253	96.68 308	81.56 383	96.88 221	96.41 291	90.44 264	99.25 267	85.39 366	97.67 324	95.80 377

HQP2-MVS												90.33 265

N_pmnet		95.18 230	94.23 266	98.06 88	97.85 241	96.55 59	92.49 342	91.63 372	89.34 316	98.09 137	97.41 224	90.33 265	99.06 299	91.58 274	99.31 196	98.56 241

HQP-MVS		95.17 232	94.58 254	96.92 179	97.85 241	92.47 208	94.26 281	98.43 197	93.18 250	92.86 355	95.08 332	90.33 265	99.23 273	90.51 303	98.74 263	99.05 174

CNLPA		95.04 236	94.47 259	96.75 192	97.81 250	95.25 114	94.12 295	97.89 255	94.41 207	94.57 309	95.69 319	90.30 268	98.35 367	86.72 356	98.76 261	96.64 363

PMMVS		92.39 311	91.08 326	96.30 220	93.12 400	92.81 198	90.58 380	95.96 317	79.17 394	91.85 371	92.27 375	90.29 269	98.66 341	89.85 314	96.68 355	97.43 337

TR-MVS		92.54 310	92.20 309	93.57 328	96.49 334	86.66 327	93.51 317	94.73 338	89.96 311	94.95 302	93.87 353	90.24 270	98.61 345	81.18 386	94.88 381	95.45 383

TAMVS		95.49 214	94.94 229	97.16 159	98.31 191	93.41 185	95.07 254	96.82 302	91.09 295	97.51 176	97.82 194	89.96 271	99.42 212	88.42 334	99.44 156	98.64 232

DPM-MVS		93.68 288	92.77 300	96.42 212	97.91 237	92.54 204	91.17 371	97.47 281	84.99 369	93.08 351	94.74 340	89.90 272	99.00 305	87.54 346	98.09 303	97.72 323

PMMVS2		93.66 289	94.07 272	92.45 359	97.57 287	80.67 384	86.46 397	96.00 315	93.99 223	97.10 201	97.38 231	89.90 272	97.82 381	88.76 328	99.47 149	98.86 207

BH-w/o		92.14 317	91.94 311	92.73 352	97.13 318	85.30 342	92.46 344	95.64 323	89.33 317	94.21 317	92.74 369	89.60 274	98.24 372	81.68 384	94.66 383	94.66 388

Anonymous20240521		97.07 134	97.51 109	95.76 245	99.35 50	88.18 295	97.78 78	98.40 203	97.11 92	98.34 108	99.04 56	89.58 275	99.79 47	98.09 39	99.93 11	99.30 120

UnsupCasMVSNet_bld		94.72 251	94.26 265	96.08 229	98.62 158	90.54 256	93.38 321	98.05 250	90.30 306	97.02 210	96.80 271	89.54 276	99.16 283	88.44 333	96.18 365	98.56 241

MG-MVS		94.08 278	94.00 274	94.32 312	97.09 319	85.89 336	93.19 327	95.96 317	92.52 270	94.93 304	97.51 218	89.54 276	98.77 326	87.52 348	97.71 320	98.31 268

UnsupCasMVSNet_eth		95.91 198	95.73 208	96.44 210	98.48 179	91.52 236	95.31 241	98.45 194	95.76 153	97.48 180	97.54 215	89.53 278	98.69 336	94.43 205	94.61 384	99.13 155

GBi-Net		96.99 138	96.80 153	97.56 122	97.96 233	93.67 174	98.23 47	98.66 172	95.59 162	97.99 148	99.19 37	89.51 279	99.73 85	94.60 200	99.44 156	99.30 120

test1		96.99 138	96.80 153	97.56 122	97.96 233	93.67 174	98.23 47	98.66 172	95.59 162	97.99 148	99.19 37	89.51 279	99.73 85	94.60 200	99.44 156	99.30 120

FMVSNet2		96.72 161	96.67 160	96.87 183	97.96 233	91.88 229	97.15 119	98.06 249	95.59 162	98.50 88	98.62 97	89.51 279	99.65 138	94.99 184	99.60 102	99.07 170

pmmvs4		94.82 245	94.19 269	96.70 196	97.42 301	92.75 202	92.09 355	96.76 304	86.80 349	95.73 283	97.22 242	89.28 282	98.89 316	93.28 246	99.14 217	98.46 253

cascas		91.89 323	91.35 320	93.51 329	94.27 388	85.60 338	88.86 394	98.61 179	79.32 393	92.16 368	91.44 385	89.22 283	98.12 376	90.80 291	97.47 334	96.82 358

DSMNet-mixed		92.19 316	91.83 313	93.25 334	96.18 344	83.68 364	96.27 170	93.68 349	76.97 401	92.54 365	99.18 40	89.20 284	98.55 351	83.88 376	98.60 279	97.51 334

c3_l		95.20 229	95.32 216	94.83 290	96.19 343	86.43 331	91.83 359	98.35 211	93.47 237	97.36 186	97.26 240	88.69 285	99.28 261	95.41 158	99.36 178	98.78 215

test_fmvs2		96.38 180	96.45 175	96.16 226	97.85 241	91.30 240	96.81 138	99.45 19	89.24 318	98.49 89	99.38 18	88.68 286	97.62 384	98.83 19	99.32 193	99.57 46

CANet_DTU		94.65 256	94.21 268	95.96 233	95.90 353	89.68 264	93.92 304	97.83 261	93.19 249	90.12 385	95.64 322	88.52 287	99.57 170	93.27 247	99.47 149	98.62 235

EPP-MVSNet		96.84 150	96.58 165	97.65 117	99.18 80	93.78 171	98.68 15	96.34 310	97.91 54	97.30 187	98.06 170	88.46 288	99.85 30	93.85 230	99.40 172	99.32 115

SixPastTwentyTwo		97.49 110	97.57 103	97.26 154	99.56 20	92.33 211	98.28 43	96.97 297	98.30 42	99.45 21	99.35 23	88.43 289	99.89 21	98.01 42	99.76 58	99.54 53

miper_ehance_all_eth		94.69 252	94.70 244	94.64 296	95.77 362	86.22 333	91.32 368	98.24 221	91.67 284	97.05 208	96.65 279	88.39 290	99.22 275	94.88 186	98.34 292	98.49 250

IS-MVSNet		96.93 143	96.68 159	97.70 113	99.25 62	94.00 162	98.57 21	96.74 306	98.36 38	98.14 132	97.98 179	88.23 291	99.71 104	93.10 251	99.72 71	99.38 106

jason		94.39 267	94.04 273	95.41 264	98.29 193	87.85 306	92.74 336	96.75 305	85.38 364	95.29 293	96.15 303	88.21 292	99.65 138	94.24 214	99.34 186	98.74 221
jason: jason.
IterMVS-SCA-FT		95.86 200	96.19 186	94.85 288	97.68 275	85.53 339	92.42 347	97.63 276	96.99 94	98.36 105	98.54 104	87.94 293	99.75 70	97.07 79	99.08 227	99.27 131

SCA		93.38 297	93.52 283	92.96 345	96.24 339	81.40 380	93.24 325	94.00 345	91.58 288	94.57 309	96.97 257	87.94 293	99.42 212	89.47 319	97.66 325	98.06 295

sss		94.22 270	93.72 279	95.74 246	97.71 272	89.95 260	93.84 306	96.98 296	88.38 332	93.75 332	95.74 318	87.94 293	98.89 316	91.02 284	98.10 302	98.37 259

IterMVS		95.42 220	95.83 204	94.20 316	97.52 291	83.78 363	92.41 348	97.47 281	95.49 167	98.06 142	98.49 108	87.94 293	99.58 164	96.02 115	99.02 234	99.23 138
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CHOSEN 1792x2688		94.10 276	93.41 285	96.18 225	99.16 82	90.04 258	92.15 352	98.68 167	79.90 391	96.22 260	97.83 191	87.92 297	99.42 212	89.18 323	99.65 87	99.08 168

VDDNet		96.98 141	96.84 150	97.41 143	99.40 44	93.26 190	97.94 68	95.31 333	99.26 9	98.39 101	99.18 40	87.85 298	99.62 152	95.13 175	99.09 226	99.35 114

pmmvs5		94.63 257	94.34 264	95.50 258	97.63 284	88.34 291	94.02 297	97.13 290	87.15 343	95.22 295	97.15 245	87.50 299	99.27 264	93.99 225	99.26 203	98.88 204

D2MVS		95.18 230	95.17 221	95.21 268	97.76 264	87.76 309	94.15 291	97.94 252	89.77 314	96.99 212	97.68 207	87.45 300	99.14 285	95.03 181	99.81 47	98.74 221

test_vis1_n_1920		95.77 203	96.41 177	93.85 321	98.55 167	84.86 351	95.91 202	99.71 4	92.72 268	97.67 170	98.90 72	87.44 301	98.73 330	97.96 43	98.85 252	97.96 305

PVSNet	86.72 19	91.10 332	90.97 329	91.49 368	97.56 289	78.04 393	87.17 396	94.60 340	84.65 372	92.34 366	92.20 377	87.37 302	98.47 358	85.17 369	97.69 322	97.96 305

Anonymous202405211		96.34 181	95.98 196	97.43 140	98.25 199	93.85 167	96.74 143	94.41 342	97.72 62	98.37 102	98.03 173	87.15 303	99.53 180	94.06 221	99.07 229	98.92 195

MVSFormer		96.14 188	96.36 180	95.49 259	97.68 275	87.81 307	98.67 16	99.02 80	96.50 113	94.48 313	96.15 303	86.90 304	99.92 7	98.73 23	99.13 219	98.74 221

lupinMVS		93.77 284	93.28 286	95.24 267	97.68 275	87.81 307	92.12 353	96.05 313	84.52 373	94.48 313	95.06 334	86.90 304	99.63 147	93.62 238	99.13 219	98.27 274

eth_miper_zixun_eth		94.89 242	94.93 231	94.75 294	95.99 351	86.12 334	91.35 365	98.49 191	93.40 238	97.12 199	97.25 241	86.87 306	99.35 242	95.08 178	98.82 256	98.78 215

test_vis1_n		95.67 207	95.89 202	95.03 277	98.18 209	89.89 261	96.94 131	99.28 30	88.25 334	98.20 123	98.92 68	86.69 307	97.19 387	97.70 57	98.82 256	98.00 303

WTY-MVS		93.55 292	93.00 292	95.19 269	97.81 250	87.86 304	93.89 305	96.00 315	89.02 321	94.07 322	95.44 329	86.27 308	99.33 247	87.69 342	96.82 349	98.39 257

CDS-MVSNet		94.88 243	94.12 271	97.14 161	97.64 283	93.57 179	93.96 303	97.06 294	90.05 310	96.30 256	96.55 283	86.10 309	99.47 198	90.10 310	99.31 196	98.40 255
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
1112_ss		94.12 275	93.42 284	96.23 221	98.59 162	90.85 247	94.24 285	98.85 123	85.49 360	92.97 353	94.94 336	86.01 310	99.64 143	91.78 271	97.92 309	98.20 280

dmvs_testset		87.30 368	86.99 365	88.24 384	96.71 329	77.48 396	94.68 271	86.81 401	92.64 269	89.61 389	87.01 403	85.91 311	93.12 404	61.04 408	88.49 400	94.13 391

miper_enhance_ethall		93.14 302	92.78 299	94.20 316	93.65 396	85.29 343	89.97 385	97.85 257	85.05 366	96.15 266	94.56 343	85.74 312	99.14 285	93.74 233	98.34 292	98.17 285

new_pmnet		92.34 313	91.69 317	94.32 312	96.23 341	89.16 275	92.27 351	92.88 358	84.39 376	95.29 293	96.35 296	85.66 313	96.74 396	84.53 373	97.56 328	97.05 346

Syy-MVS		92.09 319	91.80 315	92.93 347	95.19 375	82.65 369	92.46 344	91.35 374	90.67 301	91.76 372	87.61 401	85.64 314	98.50 355	94.73 196	96.84 347	97.65 326

alignmvs		96.01 194	95.52 215	97.50 131	97.77 263	94.71 131	96.07 187	96.84 300	97.48 76	96.78 228	94.28 350	85.50 315	99.40 223	96.22 106	98.73 266	98.40 255

lessismore_v0				97.05 170	99.36 49	92.12 221		84.07 404		98.77 70	98.98 61	85.36 316	99.74 79	97.34 68	99.37 175	99.30 120

HY-MVS	91.43 15	92.58 309	91.81 314	94.90 285	96.49 334	88.87 281	97.31 110	94.62 339	85.92 356	90.50 380	96.84 266	85.05 317	99.40 223	83.77 378	95.78 372	96.43 369

EPNet		93.72 286	92.62 304	97.03 173	87.61 412	92.25 214	96.27 170	91.28 376	96.74 102	87.65 398	97.39 229	85.00 318	99.64 143	92.14 262	99.48 147	99.20 143
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_lstm_enhance		94.81 246	94.80 241	94.85 288	96.16 345	86.45 330	91.14 372	98.20 226	93.49 236	97.03 209	97.37 233	84.97 319	99.26 265	95.28 161	99.56 112	98.83 209

Test_1112_low_res		93.53 293	92.86 294	95.54 257	98.60 160	88.86 282	92.75 334	98.69 165	82.66 380	92.65 361	96.92 262	84.75 320	99.56 171	90.94 286	97.76 316	98.19 282

MVS-HIRNet		88.40 359	90.20 340	82.99 388	97.01 321	60.04 413	93.11 328	85.61 403	84.45 375	88.72 394	99.09 53	84.72 321	98.23 373	82.52 382	96.59 357	90.69 403

K. test v3		96.44 177	96.28 183	96.95 176	99.41 41	91.53 235	97.65 89	90.31 386	98.89 24	98.93 52	99.36 21	84.57 322	99.92 7	97.81 49	99.56 112	99.39 104

test_cas_vis1_n_1920		95.34 222	95.67 209	94.35 311	98.21 203	86.83 326	95.61 221	99.26 31	90.45 304	98.17 128	98.96 64	84.43 323	98.31 369	96.74 86	99.17 214	97.90 309

h-mvs33		96.29 182	95.63 212	98.26 70	98.50 176	96.11 74	96.90 133	97.09 292	96.58 108	97.21 192	98.19 151	84.14 324	99.78 50	95.89 124	96.17 366	98.89 200

hse-mvs2		95.77 203	95.09 224	97.79 107	97.84 246	95.51 97	95.66 215	95.43 331	96.58 108	97.21 192	96.16 302	84.14 324	99.54 178	95.89 124	96.92 343	98.32 266

DIV-MVS_self_test		94.73 247	94.64 247	95.01 278	95.86 356	87.00 322	91.33 366	98.08 244	93.34 241	97.10 201	97.34 235	84.02 326	99.31 252	95.15 172	99.55 118	98.72 224

cl____		94.73 247	94.64 247	95.01 278	95.85 357	87.00 322	91.33 366	98.08 244	93.34 241	97.10 201	97.33 236	84.01 327	99.30 255	95.14 173	99.56 112	98.71 227

Vis-MVSNet (Re-imp)		95.11 233	94.85 236	95.87 240	99.12 93	89.17 274	97.54 102	94.92 337	96.50 113	96.58 240	97.27 239	83.64 328	99.48 196	88.42 334	99.67 84	98.97 184

FA-MVS(test-final)		94.91 241	94.89 234	94.99 280	97.51 292	88.11 300	98.27 45	95.20 334	92.40 275	96.68 232	98.60 98	83.44 329	99.28 261	93.34 243	98.53 281	97.59 331

dmvs_re		92.08 320	91.27 323	94.51 305	97.16 316	92.79 201	95.65 217	92.64 363	94.11 219	92.74 358	90.98 390	83.41 330	94.44 403	80.72 387	94.07 387	96.29 371

PVSNet_0	81.89 21	84.49 372	83.21 375	88.34 383	95.76 363	74.97 406	83.49 402	92.70 362	78.47 396	87.94 397	86.90 404	83.38 331	96.63 397	73.44 402	66.86 408	93.40 395

test_fmvs1_n		95.21 228	95.28 217	94.99 280	98.15 216	89.13 277	96.81 138	99.43 21	86.97 347	97.21 192	98.92 68	83.00 332	97.13 388	98.09 39	98.94 241	98.72 224

CMPMVS	73.10 23	92.74 307	91.39 319	96.77 191	93.57 398	94.67 134	94.21 288	97.67 268	80.36 390	93.61 337	96.60 281	82.85 333	97.35 386	84.86 371	98.78 259	98.29 273
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_fmvs1		94.51 263	94.60 251	94.26 315	95.91 352	87.92 302	95.35 237	99.02 80	86.56 351	96.79 224	98.52 105	82.64 334	97.00 391	97.87 46	98.71 267	97.88 311

EU-MVSNet		94.25 269	94.47 259	93.60 327	98.14 218	82.60 371	97.24 115	92.72 361	85.08 365	98.48 91	98.94 66	82.59 335	98.76 328	97.47 65	99.53 126	99.44 95

baseline1		93.14 302	92.64 303	94.62 298	97.34 307	87.20 319	96.67 152	93.02 356	94.71 197	96.51 245	95.83 317	81.64 336	98.60 347	90.00 312	88.06 401	98.07 291

test1111		94.53 262	94.81 240	93.72 324	99.06 101	81.94 376	98.31 40	83.87 405	96.37 118	98.49 89	99.17 43	81.49 337	99.73 85	96.64 88	99.86 30	99.49 70

CVMVSNet		92.33 314	92.79 297	90.95 371	97.26 312	75.84 403	95.29 243	92.33 366	81.86 381	96.27 257	98.19 151	81.44 338	98.46 359	94.23 215	98.29 295	98.55 243

EPNet_dtu		91.39 330	90.75 333	93.31 332	90.48 409	82.61 370	94.80 265	92.88 358	93.39 239	81.74 406	94.90 339	81.36 339	99.11 292	88.28 336	98.87 249	98.21 279
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ECVR-MVS		94.37 268	94.48 258	94.05 320	98.95 112	83.10 366	98.31 40	82.48 407	96.20 126	98.23 121	99.16 44	81.18 340	99.66 136	95.95 120	99.83 42	99.38 106

test_yl		94.40 265	94.00 274	95.59 251	96.95 323	89.52 268	94.75 269	95.55 328	96.18 129	96.79 224	96.14 305	81.09 341	99.18 278	90.75 293	97.77 314	98.07 291

DCV-MVSNet		94.40 265	94.00 274	95.59 251	96.95 323	89.52 268	94.75 269	95.55 328	96.18 129	96.79 224	96.14 305	81.09 341	99.18 278	90.75 293	97.77 314	98.07 291

MIMVSNet		93.42 295	92.86 294	95.10 274	98.17 212	88.19 294	98.13 56	93.69 347	92.07 277	95.04 301	98.21 150	80.95 343	99.03 304	81.42 385	98.06 304	98.07 291

PAPM		87.64 364	85.84 371	93.04 340	96.54 332	84.99 349	88.42 395	95.57 327	79.52 392	83.82 403	93.05 364	80.57 344	98.41 361	62.29 407	92.79 391	95.71 378

HyFIR lowres test		93.72 286	92.65 302	96.91 181	98.93 117	91.81 232	91.23 370	98.52 188	82.69 379	96.46 247	96.52 287	80.38 345	99.90 18	90.36 307	98.79 258	99.03 175

FMVSNet3		95.26 227	94.94 229	96.22 223	96.53 333	90.06 257	95.99 194	97.66 270	94.11 219	97.99 148	97.91 187	80.22 346	99.63 147	94.60 200	99.44 156	98.96 185

RPMNet		94.68 254	94.60 251	94.90 285	95.44 370	88.15 296	96.18 178	98.86 119	97.43 77	94.10 320	98.49 108	79.40 347	99.76 64	95.69 133	95.81 369	96.81 359

LFMVS		95.32 224	94.88 235	96.62 199	98.03 224	91.47 237	97.65 89	90.72 382	99.11 13	97.89 159	98.31 128	79.20 348	99.48 196	93.91 229	99.12 222	98.93 192

ADS-MVSNet2		91.47 329	90.51 337	94.36 310	95.51 368	85.63 337	95.05 256	95.70 321	83.46 377	92.69 359	96.84 266	79.15 349	99.41 221	85.66 362	90.52 395	98.04 299

ADS-MVSNet		90.95 335	90.26 339	93.04 340	95.51 368	82.37 372	95.05 256	93.41 353	83.46 377	92.69 359	96.84 266	79.15 349	98.70 334	85.66 362	90.52 395	98.04 299

MDTV_nov1_ep13_2view						57.28 414	94.89 262		80.59 388	94.02 325		78.66 351		85.50 364		97.82 315

cl22		93.25 300	92.84 296	94.46 307	94.30 387	86.00 335	91.09 374	96.64 309	90.74 298	95.79 278	96.31 297	78.24 352	98.77 326	94.15 218	98.34 292	98.62 235

PatchmatchNet		91.98 322	91.87 312	92.30 361	94.60 384	79.71 387	95.12 249	93.59 352	89.52 315	93.61 337	97.02 254	77.94 353	99.18 278	90.84 289	94.57 386	98.01 302
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												77.80 354				98.06 295

CR-MVSNet		93.29 299	92.79 297	94.78 293	95.44 370	88.15 296	96.18 178	97.20 286	84.94 370	94.10 320	98.57 100	77.67 355	99.39 227	95.17 168	95.81 369	96.81 359

Patchmtry		95.03 238	94.59 253	96.33 217	94.83 381	90.82 248	96.38 163	97.20 286	96.59 107	97.49 178	98.57 100	77.67 355	99.38 230	92.95 254	99.62 93	98.80 213

tpmrst		90.31 338	90.61 336	89.41 379	94.06 392	72.37 410	95.06 255	93.69 347	88.01 336	92.32 367	96.86 264	77.45 357	98.82 321	91.04 283	87.01 402	97.04 347

sam_mvs												77.38 358

patchmatchnet-post											96.84 266	77.36 359	99.42 212

Patchmatch-RL test		94.66 255	94.49 257	95.19 269	98.54 169	88.91 280	92.57 340	98.74 154	91.46 289	98.32 112	97.75 200	77.31 360	98.81 323	96.06 110	99.61 99	97.85 313

tpmvs		90.79 336	90.87 330	90.57 374	92.75 404	76.30 401	95.79 208	93.64 351	91.04 296	91.91 370	96.26 298	77.19 361	98.86 320	89.38 321	89.85 398	96.56 366

test_post											10.87 412	76.83 362	99.07 298

Patchmatch-test		93.60 291	93.25 287	94.63 297	96.14 349	87.47 313	96.04 189	94.50 341	93.57 234	96.47 246	96.97 257	76.50 363	98.61 345	90.67 299	98.41 291	97.81 317

MDTV_nov1_ep13			91.28 322		94.31 386	73.51 408	94.80 265	93.16 355	86.75 350	93.45 343	97.40 225	76.37 364	98.55 351	88.85 327	96.43 358

EMVS		89.06 353	89.22 345	88.61 382	93.00 401	77.34 397	82.91 404	90.92 379	94.64 200	92.63 363	91.81 381	76.30 365	97.02 390	83.83 377	96.90 345	91.48 401

test_post1							94.98 260				10.37 413	76.21 366	99.04 301	89.47 319

GA-MVS		92.83 306	92.15 310	94.87 287	96.97 322	87.27 318	90.03 384	96.12 312	91.83 283	94.05 323	94.57 342	76.01 367	98.97 313	92.46 260	97.34 338	98.36 264

PatchT		93.75 285	93.57 282	94.29 314	95.05 378	87.32 317	96.05 188	92.98 357	97.54 73	94.25 316	98.72 85	75.79 368	99.24 271	95.92 122	95.81 369	96.32 370

E-PMN		89.52 350	89.78 342	88.73 381	93.14 399	77.61 395	83.26 403	92.02 368	94.82 194	93.71 333	93.11 358	75.31 369	96.81 393	85.81 359	96.81 350	91.77 400

DeepMVS_CX				77.17 389	90.94 408	85.28 344		74.08 412	52.51 408	80.87 408	88.03 400	75.25 370	70.63 410	59.23 409	84.94 404	75.62 404

AUN-MVS		93.95 283	92.69 301	97.74 110	97.80 254	95.38 105	95.57 224	95.46 330	91.26 293	92.64 362	96.10 308	74.67 371	99.55 175	93.72 235	96.97 342	98.30 270

CHOSEN 280x420		89.98 342	89.19 348	92.37 360	95.60 367	81.13 382	86.22 398	97.09 292	81.44 385	87.44 399	93.15 357	73.99 372	99.47 198	88.69 330	99.07 229	96.52 367

thres200		91.00 334	90.42 338	92.77 351	97.47 298	83.98 362	94.01 298	91.18 378	95.12 183	95.44 289	91.21 387	73.93 373	99.31 252	77.76 396	97.63 327	95.01 386

test-LLR		89.97 343	89.90 341	90.16 375	94.24 389	74.98 404	89.89 386	89.06 392	92.02 278	89.97 386	90.77 391	73.92 374	98.57 348	91.88 267	97.36 336	96.92 350

test0.0.03 1		90.11 339	89.21 346	92.83 349	93.89 394	86.87 325	91.74 360	88.74 395	92.02 278	94.71 307	91.14 388	73.92 374	94.48 402	83.75 379	92.94 390	97.16 344

tpm cat1		88.01 362	87.33 363	90.05 378	94.48 385	76.28 402	94.47 277	94.35 343	73.84 405	89.26 391	95.61 324	73.64 376	98.30 370	84.13 374	86.20 403	95.57 382

tfpn200view9		91.55 327	91.00 327	93.21 337	98.02 225	84.35 357	95.70 211	90.79 380	96.26 123	95.90 276	92.13 378	73.62 377	99.42 212	78.85 393	97.74 317	95.85 375

thres400		91.68 326	91.00 327	93.71 325	98.02 225	84.35 357	95.70 211	90.79 380	96.26 123	95.90 276	92.13 378	73.62 377	99.42 212	78.85 393	97.74 317	97.36 339

test_method		66.88 374	66.13 377	69.11 390	62.68 415	25.73 418	49.76 406	96.04 314	14.32 410	64.27 410	91.69 383	73.45 379	88.05 407	76.06 398	66.94 407	93.54 393

thres100view900		91.76 325	91.26 325	93.26 333	98.21 203	84.50 355	96.39 160	90.39 383	96.87 98	96.33 252	93.08 362	73.44 380	99.42 212	78.85 393	97.74 317	95.85 375

thres600view7		92.03 321	91.43 318	93.82 322	98.19 206	84.61 354	96.27 170	90.39 383	96.81 100	96.37 251	93.11 358	73.44 380	99.49 193	80.32 388	97.95 308	97.36 339

MVSTER		94.21 272	93.93 277	95.05 276	95.83 358	86.46 329	95.18 248	97.65 272	92.41 274	97.94 155	98.00 178	72.39 382	99.58 164	96.36 100	99.56 112	99.12 160

JIA-IIPM		91.79 324	90.69 334	95.11 272	93.80 395	90.98 245	94.16 290	91.78 371	96.38 117	90.30 383	99.30 28	72.02 383	98.90 315	88.28 336	90.17 397	95.45 383

tpm		91.08 333	90.85 331	91.75 367	95.33 373	78.09 392	95.03 258	91.27 377	88.75 325	93.53 340	97.40 225	71.24 384	99.30 255	91.25 280	93.87 388	97.87 312

baseline2		89.65 349	88.44 355	93.25 334	95.62 366	82.71 368	93.82 307	85.94 402	88.89 324	87.35 400	92.54 372	71.23 385	99.33 247	86.01 357	94.60 385	97.72 323

CostFormer		89.75 346	89.25 344	91.26 370	94.69 383	78.00 394	95.32 240	91.98 369	81.50 384	90.55 379	96.96 259	71.06 386	98.89 316	88.59 332	92.63 392	96.87 353

FPMVS		89.92 344	88.63 352	93.82 322	98.37 188	96.94 46	91.58 361	93.34 354	88.00 337	90.32 382	97.10 249	70.87 387	91.13 406	71.91 404	96.16 367	93.39 396

EPMVS		89.26 351	88.55 353	91.39 369	92.36 405	79.11 390	95.65 217	79.86 408	88.60 328	93.12 350	96.53 285	70.73 388	98.10 377	90.75 293	89.32 399	96.98 348

FE-MVS		92.95 304	92.22 308	95.11 272	97.21 314	88.33 292	98.54 24	93.66 350	89.91 312	96.21 261	98.14 155	70.33 389	99.50 188	87.79 340	98.24 297	97.51 334

tmp_tt		57.23 376	62.50 379	41.44 393	34.77 416	49.21 417	83.93 401	60.22 415	15.31 409	71.11 409	79.37 406	70.09 390	44.86 412	64.76 406	82.93 406	30.25 408

ET-MVSNet_ETH3D		91.12 331	89.67 343	95.47 260	96.41 336	89.15 276	91.54 362	90.23 387	89.07 320	86.78 402	92.84 367	69.39 391	99.44 208	94.16 217	96.61 356	97.82 315

dp		88.08 361	88.05 357	88.16 386	92.85 402	68.81 412	94.17 289	92.88 358	85.47 361	91.38 375	96.14 305	68.87 392	98.81 323	86.88 354	83.80 405	96.87 353

tpm2		88.47 358	87.69 361	90.79 372	94.98 379	77.34 397	95.09 251	91.83 370	77.51 400	89.40 390	96.41 291	67.83 393	98.73 330	83.58 380	92.60 393	96.29 371

pmmvs3		90.00 341	88.90 351	93.32 331	94.20 391	85.34 341	91.25 369	92.56 365	78.59 395	93.82 328	95.17 331	67.36 394	98.69 336	89.08 325	98.03 305	95.92 374

thisisatest0515		90.43 337	89.18 349	94.17 318	97.07 320	85.44 340	89.75 390	87.58 397	88.28 333	93.69 335	91.72 382	65.27 395	99.58 164	90.59 300	98.67 270	97.50 336

tttt0517		93.31 298	92.56 305	95.57 253	98.71 145	87.86 304	97.44 105	87.17 399	95.79 152	97.47 182	96.84 266	64.12 396	99.81 39	96.20 107	99.32 193	99.02 178

thisisatest0530		92.71 308	91.76 316	95.56 255	98.42 185	88.23 293	96.03 190	87.35 398	94.04 222	96.56 242	95.47 327	64.03 397	99.77 59	94.78 193	99.11 223	98.68 231

FMVSNet5		93.39 296	92.35 306	96.50 207	95.83 358	90.81 250	97.31 110	98.27 217	92.74 267	96.27 257	98.28 137	62.23 398	99.67 130	90.86 288	99.36 178	99.03 175

IB-MVS	85.98 20	88.63 357	86.95 367	93.68 326	95.12 377	84.82 353	90.85 376	90.17 388	87.55 340	88.48 395	91.34 386	58.01 399	99.59 162	87.24 352	93.80 389	96.63 365
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
testing91		89.67 348	88.55 353	93.04 340	95.90 353	81.80 377	92.71 338	93.71 346	93.71 229	90.18 384	90.15 395	57.11 400	99.22 275	87.17 353	96.32 362	98.12 287

gg-mvs-nofinetune		88.28 360	86.96 366	92.23 362	92.84 403	84.44 356	98.19 53	74.60 410	99.08 14	87.01 401	99.47 11	56.93 401	98.23 373	78.91 392	95.61 375	94.01 392

KD-MVS_2432*1600		88.93 354	87.74 359	92.49 356	88.04 410	81.99 374	89.63 391	95.62 324	91.35 291	95.06 298	93.11 358	56.58 402	98.63 343	85.19 367	95.07 378	96.85 355

miper_refine_blended		88.93 354	87.74 359	92.49 356	88.04 410	81.99 374	89.63 391	95.62 324	91.35 291	95.06 298	93.11 358	56.58 402	98.63 343	85.19 367	95.07 378	96.85 355

GG-mvs-BLEND				90.60 373	91.00 407	84.21 360	98.23 47	72.63 413		82.76 404	84.11 405	56.14 404	96.79 394	72.20 403	92.09 394	90.78 402

TESTMET0.1,1		87.20 369	86.57 369	89.07 380	93.62 397	72.84 409	89.89 386	87.01 400	85.46 362	89.12 392	90.20 394	56.00 405	97.72 383	90.91 287	96.92 343	96.64 363

testing99		89.21 352	88.04 358	92.70 353	95.78 361	81.00 383	92.65 339	92.03 367	93.20 248	89.90 388	90.08 397	55.25 406	99.14 285	87.54 346	95.95 368	97.97 304

UWE-MVS		87.57 366	86.72 368	90.13 377	95.21 374	73.56 407	91.94 357	83.78 406	88.73 327	93.00 352	92.87 366	55.22 407	99.25 267	81.74 383	97.96 307	97.59 331

test2506		89.86 345	89.16 350	91.97 365	98.95 112	76.83 400	98.54 24	61.07 414	96.20 126	97.07 207	99.16 44	55.19 408	99.69 119	96.43 97	99.83 42	99.38 106

testing11		88.93 354	87.63 362	92.80 350	95.87 355	81.49 379	92.48 343	91.54 373	91.62 285	88.27 396	90.24 393	55.12 409	99.11 292	87.30 351	96.28 364	97.81 317

test-mter		87.92 363	87.17 364	90.16 375	94.24 389	74.98 404	89.89 386	89.06 392	86.44 352	89.97 386	90.77 391	54.96 410	98.57 348	91.88 267	97.36 336	96.92 350

ETVMVS		87.62 365	85.75 372	93.22 336	96.15 348	83.26 365	92.94 330	90.37 385	91.39 290	90.37 381	88.45 399	51.93 411	98.64 342	73.76 400	96.38 360	97.75 320

testing222		87.35 367	85.50 374	92.93 347	95.79 360	82.83 367	92.40 349	90.10 389	92.80 266	88.87 393	89.02 398	48.34 412	98.70 334	75.40 399	96.74 352	97.27 343

myMVS_eth3d		87.16 370	85.61 373	91.82 366	95.19 375	79.32 388	92.46 344	91.35 374	90.67 301	91.76 372	87.61 401	41.96 413	98.50 355	82.66 381	96.84 347	97.65 326

testing3		89.72 347	88.26 356	94.10 319	97.66 280	84.30 359	94.80 265	88.25 396	94.66 198	95.07 297	92.51 373	41.15 414	99.43 210	91.81 270	98.44 289	98.55 243

dongtai		63.43 375	63.37 378	63.60 391	83.91 413	53.17 415	85.14 399	43.40 417	77.91 399	80.96 407	79.17 407	36.36 415	77.10 409	37.88 410	45.63 409	60.54 406

kuosan		54.81 377	54.94 380	54.42 392	74.43 414	50.03 416	84.98 400	44.27 416	61.80 407	62.49 411	70.43 408	35.16 416	58.04 411	19.30 411	41.61 410	55.19 407

test123		12.59 379	15.49 382	3.87 394	6.07 417	2.55 419	90.75 378	2.59 419	2.52 412	5.20 414	13.02 411	4.96 417	1.85 414	5.20 412	9.09 411	7.23 409

testmvs		12.33 380	15.23 383	3.64 395	5.77 418	2.23 420	88.99 393	3.62 418	2.30 413	5.29 413	13.09 410	4.52 418	1.95 413	5.16 413	8.32 412	6.75 410

test_blank		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet_test		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

DCPMVS		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

sosnet-low-res		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

sosnet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uncertanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

Regformer		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

ab-mvs-re		7.91 382	10.55 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	94.94 336	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

WAC-MVS						79.32 388								85.41 365

FOURS1					99.59 17	98.20 8	99.03 8	99.25 33	98.96 22	98.87 58

MSC_two_6792asdad				98.22 75	97.75 266	95.34 110		98.16 236					99.75 70	95.87 126	99.51 136	99.57 46

No_MVS				98.22 75	97.75 266	95.34 110		98.16 236					99.75 70	95.87 126	99.51 136	99.57 46

eth-test2					0.00 419

eth-test					0.00 419

IU-MVS					99.22 68	95.40 103		98.14 239	85.77 359	98.36 105				95.23 165	99.51 136	99.49 70

save fliter					98.48 179	94.71 131	94.53 276	98.41 201	95.02 188

test_0728_SECOND				98.25 73	99.23 65	95.49 101	96.74 143	98.89 108					99.75 70	95.48 148	99.52 131	99.53 56

GSMVS																98.06 295

test_part2					99.03 107	96.07 75				98.08 139

MTGPA								98.73 155

MTMP							96.55 154	74.60 410

gm-plane-assit					91.79 406	71.40 411			81.67 382		90.11 396		98.99 307	84.86 371

test9_res														91.29 277	98.89 248	99.00 179

agg_prior2														90.34 308	98.90 245	99.10 167

agg_prior					97.80 254	94.96 126		98.36 208		93.49 341			99.53 180

test_prior4						95.38 105	93.61 315

test_prior				97.46 137	97.79 259	94.26 155		98.42 200					99.34 245			98.79 214

旧先验2							93.35 322		77.95 398	95.77 282			98.67 340	90.74 296

新几何2							93.43 318

无先验							93.20 326	97.91 253	80.78 387				99.40 223	87.71 341		97.94 307

原ACMM2							92.82 332

testdata2													99.46 201	87.84 339

testdata1							92.77 333		93.78 227

plane_prior7					98.70 147	94.67 134

plane_prior5								98.75 152					99.46 201	92.59 257	99.20 209	99.28 127

plane_prior4											96.77 272

plane_prior3						94.51 141			95.29 176	96.16 264

plane_prior2							96.50 156		96.36 119

plane_prior1					98.49 177

plane_prior						94.29 151	95.42 229		94.31 211						98.93 243

n2								0.00 420

nn								0.00 420

door-mid								98.17 232

test11								98.08 244

door								97.81 262

HQP5-MVS						92.47 208

HQP-NCC					97.85 241		94.26 281		93.18 250	92.86 355

ACMP_Plane					97.85 241		94.26 281		93.18 250	92.86 355

BP-MVS														90.51 303

HQP4-MVS										92.87 354			99.23 273			99.06 172

HQP3-MVS								98.43 197							98.74 263

NP-MVS					98.14 218	93.72 172					95.08 332

ACMMP++_ref															99.52 131

ACMMP++															99.55 118

High-resolution multi-view benchmark