High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

LCM-MVSNet		99.86 1	99.86 1	99.87 1	99.99 1	99.77 1	99.77 1	99.80 3	99.97 1	99.97 1	99.95 1	99.74 1	99.98 1	99.56 1	100.00 1	99.85 6

pmmvs6		99.07 6	99.24 7	98.56 51	99.81 2	96.38 65	98.87 12	99.30 41	99.01 22	99.63 14	99.66 6	99.27 2	99.68 150	97.75 73	99.89 26	99.62 45

UniMVSNet_ETH3D		99.12 3	99.28 5	98.65 45	99.77 5	96.34 69	99.18 6	99.20 57	99.67 3	99.73 6	99.65 8	99.15 3	99.86 27	97.22 95	99.92 15	99.77 15

test_fmvsmconf0.01_n		98.57 21	98.74 19	98.06 100	99.39 50	94.63 148	96.70 172	99.82 1	95.44 217	99.64 13	99.52 12	98.96 4	99.74 95	99.38 7	99.86 35	99.81 10

XVG-OURS-SEG-HR		97.38 151	97.07 178	98.30 75	99.01 123	97.41 37	94.66 341	99.02 119	95.20 227	98.15 172	97.52 280	98.83 5	98.43 444	94.87 249	96.41 438	99.07 227

ACMH	93.61 9	98.44 32	98.76 16	97.51 143	99.43 43	93.54 194	98.23 50	99.05 106	97.40 92	99.37 32	99.08 60	98.79 6	99.47 245	97.74 74	99.71 91	99.50 88
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mvs_tets		98.90 8	98.94 9	98.75 34	99.69 11	96.48 63	98.54 26	99.22 54	96.23 155	99.71 7	99.48 15	98.77 7	99.93 3	98.89 30	99.95 5	99.84 8

test_fmvsmconf0.1_n		98.41 34	98.54 30	98.03 105	99.16 93	94.61 149	96.18 212	99.73 5	95.05 236	99.60 17	99.34 29	98.68 8	99.72 110	99.21 12	99.85 46	99.76 21

sc_t1		99.09 5	99.28 5	98.53 54	99.72 8	96.21 73	98.87 12	99.19 59	99.71 2	99.76 4	99.65 8	98.64 9	99.79 53	98.07 56	99.90 25	99.58 51

tt0320-xc		99.10 4	99.31 3	98.49 57	99.57 20	96.09 79	98.91 11	99.55 24	99.67 3	99.78 3	99.69 4	98.63 10	99.77 69	98.02 58	99.93 11	99.60 47

LTVRE_ROB	96.88 1	99.18 2	99.34 2	98.72 40	99.71 10	96.99 47	99.69 2	99.57 20	99.02 21	99.62 15	99.36 26	98.53 11	99.52 225	98.58 42	99.95 5	99.66 38
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 40	98.41 39	97.99 108	98.94 136	94.60 150	96.00 232	99.64 15	94.99 241	99.43 27	99.18 45	98.51 12	99.71 126	99.13 20	99.84 49	99.67 36

TransMVSNet (Re)		98.38 35	98.67 21	97.51 143	99.51 32	93.39 203	98.20 55	98.87 165	98.23 53	99.48 21	99.27 34	98.47 13	99.55 216	96.52 126	99.53 164	99.60 47

tt0320		99.07 6	99.29 4	98.43 62	99.55 24	95.92 87	98.97 10	99.53 26	99.67 3	99.79 2	99.71 3	98.33 14	99.78 58	98.11 52	99.92 15	99.57 59

pm-mvs1		98.47 31	98.67 21	97.86 115	99.52 31	94.58 151	98.28 46	99.00 131	97.57 78	99.27 39	99.22 39	98.32 15	99.50 230	97.09 103	99.75 80	99.50 88

fmvsm_l_conf0.5_n_3		98.29 41	98.46 33	97.79 119	98.90 147	94.05 174	96.06 224	99.63 16	96.07 172	99.37 32	98.93 78	98.29 16	99.68 150	99.11 22	99.79 64	99.65 41

jajsoiax		98.77 12	98.79 15	98.74 37	99.66 13	96.48 63	98.45 34	99.12 78	95.83 195	99.67 10	99.37 24	98.25 17	99.92 5	98.77 33	99.94 8	99.82 9

sd_testset		97.97 66	98.12 59	97.51 143	99.41 46	93.44 199	97.96 68	98.25 279	98.58 36	98.78 87	99.39 21	98.21 18	99.56 211	92.65 329	99.86 35	99.52 81

ACMH+	93.58 10	98.23 45	98.31 49	97.98 109	99.39 50	95.22 130	97.55 108	99.20 57	98.21 54	99.25 41	98.51 138	98.21 18	99.40 282	94.79 253	99.72 88	99.32 158

HPM-MVS_fast		98.32 38	98.13 58	98.88 26	99.54 28	97.48 33	98.35 39	99.03 115	95.88 190	97.88 207	98.22 192	98.15 20	99.74 95	96.50 127	99.62 116	99.42 127

wuyk23d		93.25 374	95.20 281	87.40 477	96.07 423	95.38 114	97.04 142	94.97 416	95.33 222	99.70 9	98.11 208	98.14 21	91.94 495	77.76 483	99.68 101	74.89 495

ACMM	93.33 11	98.05 61	97.79 103	98.85 27	99.15 96	97.55 29	96.68 173	98.83 184	95.21 226	98.36 138	98.13 203	98.13 22	99.62 187	96.04 153	99.54 160	99.39 141
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HPM-MVS		98.11 55	97.83 98	98.92 24	99.42 45	97.46 34	98.57 23	99.05 106	95.43 219	97.41 239	97.50 282	97.98 23	99.79 53	95.58 187	99.57 144	99.50 88
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
testgi		96.07 246	96.50 227	94.80 361	99.26 68	87.69 379	95.96 240	98.58 241	95.08 233	98.02 189	96.25 373	97.92 24	97.60 471	88.68 413	98.74 331	99.11 220

LPG-MVS_test		97.94 75	97.67 118	98.74 37	99.15 96	97.02 45	97.09 139	99.02 119	95.15 230	98.34 142	98.23 189	97.91 25	99.70 135	94.41 269	99.73 83	99.50 88

LGP-MVS_train				98.74 37	99.15 96	97.02 45		99.02 119	95.15 230	98.34 142	98.23 189	97.91 25	99.70 135	94.41 269	99.73 83	99.50 88

lecture		98.59 20	98.60 28	98.55 52	99.48 37	96.38 65	98.08 62	99.09 91	98.46 41	98.68 102	98.73 101	97.88 27	99.80 50	97.43 87	99.59 136	99.48 102

SED-MVS		97.94 75	97.90 87	98.07 98	99.22 78	95.35 117	96.79 162	98.83 184	96.11 167	99.08 54	98.24 187	97.87 28	99.72 110	95.44 199	99.51 177	99.14 207

test_241102_ONE					99.22 78	95.35 117		98.83 184	96.04 176	99.08 54	98.13 203	97.87 28	99.33 314

SDMVSNet		97.97 66	98.26 55	97.11 182	99.41 46	92.21 236	96.92 149	98.60 236	98.58 36	98.78 87	99.39 21	97.80 30	99.62 187	94.98 246	99.86 35	99.52 81

testf1		98.57 21	98.45 36	98.93 21	99.79 3	98.78 2	97.69 96	99.42 34	97.69 74	98.92 71	98.77 95	97.80 30	99.25 343	96.27 143	99.69 97	98.76 292

APD_test2		98.57 21	98.45 36	98.93 21	99.79 3	98.78 2	97.69 96	99.42 34	97.69 74	98.92 71	98.77 95	97.80 30	99.25 343	96.27 143	99.69 97	98.76 292

SD-MVS		97.37 153	97.70 113	96.35 260	98.14 275	95.13 134	96.54 180	98.92 150	95.94 185	99.19 45	98.08 212	97.74 33	95.06 489	95.24 216	99.54 160	98.87 272
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 97	97.70 113	98.16 90	98.78 168	95.72 93	96.23 210	99.02 119	93.92 291	98.62 105	98.99 70	97.69 34	99.62 187	96.18 147	99.87 33	99.15 201
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 25	98.62 25	98.32 72	99.22 78	95.66 98	97.90 76	99.08 95	98.31 47	99.02 59	98.74 100	97.68 35	99.61 195	97.77 72	99.85 46	99.70 33

MGCFI-Net		97.20 164	97.23 166	97.08 187	97.68 339	93.71 187	97.79 82	99.09 91	97.40 92	96.59 302	93.96 429	97.67 36	99.35 309	96.43 133	98.50 355	98.17 366

ANet_high		98.31 39	98.94 9	96.41 255	99.33 60	89.64 317	97.92 74	99.56 22	99.27 10	99.66 12	99.50 14	97.67 36	99.83 35	97.55 82	99.98 2	99.77 15

test_fmvsmvis_n_1920		98.08 57	98.47 32	96.93 200	99.03 121	93.29 205	96.32 199	99.65 12	95.59 207	99.71 7	99.01 67	97.66 38	99.60 198	99.44 5	99.83 54	97.90 390

casdiffseed414692147		97.67 115	97.88 92	97.03 193	98.82 157	92.32 231	96.55 178	99.17 64	96.99 109	98.01 190	98.67 114	97.64 39	99.38 295	95.45 198	99.66 107	99.40 134

casdiffmvs_mvg		97.83 94	98.11 61	97.00 196	98.57 209	92.10 244	95.97 238	99.18 61	97.67 77	99.00 62	98.48 143	97.64 39	99.50 230	96.96 110	99.54 160	99.40 134
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
sasdasda		97.23 162	97.21 168	97.30 167	97.65 346	94.39 158	97.84 79	99.05 106	97.42 87	96.68 293	93.85 431	97.63 41	99.33 314	96.29 141	98.47 356	98.18 364

canonicalmvs		97.23 162	97.21 168	97.30 167	97.65 346	94.39 158	97.84 79	99.05 106	97.42 87	96.68 293	93.85 431	97.63 41	99.33 314	96.29 141	98.47 356	98.18 364

GeoE		97.75 104	97.70 113	97.89 113	98.88 149	94.53 153	97.10 138	98.98 138	95.75 200	97.62 221	97.59 272	97.61 43	99.77 69	96.34 138	99.44 200	99.36 151

TranMVSNet+NR-MVSNet		98.33 36	98.30 51	98.43 62	99.07 111	95.87 89	96.73 170	99.05 106	98.67 30	98.84 82	98.45 145	97.58 44	99.88 22	96.45 131	99.86 35	99.54 73

cdsmvs_eth3d_5k		24.22 466	32.30 469	0.00 486	0.00 509	0.00 511	0.00 497	98.10 302	0.00 504	0.00 505	95.06 410	97.54 45	0.00 505	0.00 503	0.00 503	0.00 501

E5new		97.59 126	97.96 84	96.45 244	99.01 123	90.45 294	96.50 181	99.23 50	96.19 161	98.27 152	98.72 102	97.49 46	99.47 245	96.64 117	99.62 116	99.42 127

E6new		97.59 126	97.97 78	96.45 244	99.01 123	90.45 294	96.50 181	99.23 50	96.20 157	98.27 152	98.72 102	97.49 46	99.47 245	96.64 117	99.62 116	99.42 127

E6		97.59 126	97.97 78	96.45 244	99.01 123	90.45 294	96.50 181	99.23 50	96.20 157	98.27 152	98.72 102	97.49 46	99.47 245	96.64 117	99.62 116	99.42 127

E5		97.59 126	97.96 84	96.45 244	99.01 123	90.45 294	96.50 181	99.23 50	96.19 161	98.27 152	98.72 102	97.49 46	99.47 245	96.64 117	99.62 116	99.42 127

ACMP	92.54 13	97.47 140	97.10 175	98.55 52	99.04 120	96.70 54	96.24 209	98.89 156	93.71 295	97.97 198	97.75 258	97.44 50	99.63 182	93.22 320	99.70 95	99.32 158
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_djsdf		98.73 14	98.74 19	98.69 42	99.63 15	96.30 71	98.67 18	99.02 119	96.50 139	99.32 36	99.44 19	97.43 51	99.92 5	98.73 36	99.95 5	99.86 5

TDRefinement		98.90 8	98.86 11	99.02 9	99.54 28	98.06 8	99.34 5	99.44 32	98.85 27	99.00 62	99.20 40	97.42 52	99.59 200	97.21 96	99.76 70	99.40 134

anonymousdsp		98.72 17	98.63 23	98.99 13	99.62 16	97.29 40	98.65 22	99.19 59	95.62 205	99.35 35	99.37 24	97.38 53	99.90 17	98.59 41	99.91 19	99.77 15

PS-CasMVS		98.73 14	98.85 13	98.39 66	99.55 24	95.47 111	98.49 31	99.13 77	99.22 12	99.22 43	98.96 74	97.35 54	99.92 5	97.79 70	99.93 11	99.79 13

COLMAP_ROB	94.48 6	98.25 44	98.11 61	98.64 46	99.21 85	97.35 38	97.96 68	99.16 66	98.34 46	98.78 87	98.52 136	97.32 55	99.45 260	94.08 283	99.67 104	99.13 209
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
EG-PatchMatch MVS		97.69 110	97.79 103	97.40 160	99.06 113	93.52 195	95.96 240	98.97 141	94.55 261	98.82 84	98.76 99	97.31 56	99.29 331	97.20 98	99.44 200	99.38 143

XXY-MVS		97.54 133	97.70 113	97.07 188	99.46 40	92.21 236	97.22 131	99.00 131	94.93 245	98.58 111	98.92 81	97.31 56	99.41 280	94.44 267	99.43 210	99.59 50

reproduce-ours		98.48 29	98.27 53	99.12 4	98.99 128	98.02 12	96.81 158	99.02 119	98.29 50	98.97 66	98.61 122	97.27 58	99.82 38	96.86 114	99.61 126	99.51 85

our_new_method		98.48 29	98.27 53	99.12 4	98.99 128	98.02 12	96.81 158	99.02 119	98.29 50	98.97 66	98.61 122	97.27 58	99.82 38	96.86 114	99.61 126	99.51 85

PEN-MVS		98.75 13	98.85 13	98.44 61	99.58 19	95.67 97	98.45 34	99.15 72	99.33 8	99.30 37	99.00 68	97.27 58	99.92 5	97.64 79	99.92 15	99.75 24

DTE-MVSNet		98.79 11	98.86 11	98.59 49	99.55 24	96.12 77	98.48 33	99.10 86	99.36 7	99.29 38	99.06 61	97.27 58	99.93 3	97.71 75	99.91 19	99.70 33

ZNCC-MVS		97.92 79	97.62 128	98.83 28	99.32 62	97.24 42	97.45 116	98.84 177	95.76 198	96.93 276	97.43 286	97.26 62	99.79 53	96.06 150	99.53 164	99.45 112

MP-MVS-pluss		97.69 110	97.36 155	98.70 41	99.50 35	96.84 50	95.38 287	98.99 135	92.45 344	98.11 175	98.31 169	97.25 63	99.77 69	96.60 123	99.62 116	99.48 102
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		97.89 87	97.63 126	98.67 43	99.35 58	96.84 50	96.36 196	98.79 198	95.07 234	97.88 207	98.35 161	97.24 64	99.72 110	96.05 152	99.58 141	99.45 112

fmvsm_l_conf0.5_n_9		97.92 79	98.37 40	96.57 233	98.94 136	90.54 288	95.39 285	99.58 18	96.82 121	99.56 18	98.77 95	97.23 65	99.61 195	99.17 17	99.86 35	99.57 59

Effi-MVS+		96.19 242	96.01 253	96.71 220	97.43 368	92.19 240	96.12 219	99.10 86	95.45 215	93.33 431	94.71 417	97.23 65	99.56 211	93.21 321	97.54 403	98.37 338

tt0805		97.44 144	97.56 136	97.11 182	99.55 24	96.36 67	98.66 21	95.66 398	98.31 47	97.09 263	95.45 404	97.17 67	98.50 439	98.67 39	97.45 409	96.48 454

PGM-MVS		97.88 88	97.52 142	98.96 16	99.20 87	97.62 24	97.09 139	99.06 100	95.45 215	97.55 225	97.94 234	97.11 68	99.78 58	94.77 256	99.46 194	99.48 102

test_0728_THIRD									96.62 128	98.40 132	98.28 180	97.10 69	99.71 126	95.70 173	99.62 116	99.58 51

APD-MVS_3200maxsize		98.13 54	97.90 87	98.79 32	98.79 164	97.31 39	97.55 108	98.92 150	97.72 71	98.25 160	98.13 203	97.10 69	99.75 85	95.44 199	99.24 262	99.32 158

fmvsm_s_conf0.5_n_3		97.88 88	98.37 40	96.41 255	98.73 174	89.82 311	95.94 242	99.49 29	96.81 122	99.09 53	99.03 65	97.09 71	99.65 171	99.37 8	99.76 70	99.76 21

OPM-MVS		97.54 133	97.25 164	98.41 64	99.11 105	96.61 59	95.24 303	98.46 251	94.58 260	98.10 177	98.07 214	97.09 71	99.39 291	95.16 225	99.44 200	99.21 189
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HFP-MVS		97.94 75	97.64 124	98.83 28	99.15 96	97.50 32	97.59 105	98.84 177	96.05 174	97.49 230	97.54 276	97.07 73	99.70 135	95.61 184	99.46 194	99.30 163

DVP-MVS		97.78 102	97.65 121	98.16 90	99.24 72	95.51 105	96.74 166	98.23 282	95.92 187	98.40 132	98.28 180	97.06 74	99.71 126	95.48 194	99.52 172	99.26 176
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 72	95.51 105	96.89 152	98.89 156	95.92 187	98.64 103	98.31 169	97.06 74

SSM_0407		97.39 150	97.67 118	96.54 238	98.51 218	90.96 275	96.40 189	99.16 66	96.95 114	98.27 152	98.09 210	97.05 76	99.67 160	95.21 218	99.40 218	98.98 245

SSM_0404		97.47 140	97.75 111	96.64 224	98.81 158	91.26 268	96.57 176	99.16 66	96.95 114	98.44 128	98.09 210	97.05 76	99.72 110	95.21 218	99.44 200	98.95 251

test_fmvsm_n_1920		98.08 57	98.29 52	97.43 156	98.88 149	93.95 178	96.17 216	99.57 20	95.66 202	99.52 20	98.71 109	97.04 78	99.64 177	99.21 12	99.87 33	98.69 302

casdiffmvs		97.50 137	97.81 101	96.56 235	98.51 218	91.04 272	95.83 250	99.09 91	97.23 103	98.33 145	98.30 175	97.03 79	99.37 301	96.58 125	99.38 223	99.28 171
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 63	97.76 109	98.79 32	99.43 43	97.21 44	97.15 134	98.90 152	96.58 134	98.08 180	97.87 242	97.02 80	99.76 77	95.25 215	99.59 136	99.40 134
Skip Steuart: Steuart Systems R&D Blog.
PC_three_1452									87.24 429	98.37 135	97.44 285	97.00 81	96.78 481	92.01 338	99.25 259	99.21 189

MED-MVS		98.14 50	98.10 64	98.27 78	99.36 54	95.35 117	97.75 87	99.30 41	97.28 101	98.88 76	98.41 151	96.99 82	99.73 101	95.36 207	99.53 164	99.74 26

EC-MVSNet		97.90 85	97.94 86	97.79 119	98.66 189	95.14 133	98.31 43	99.66 11	97.57 78	95.95 339	97.01 326	96.99 82	99.82 38	97.66 78	99.64 111	98.39 336

DVP-MVS++		97.96 68	97.90 87	98.12 96	97.75 331	95.40 112	99.03 8	98.89 156	96.62 128	98.62 105	98.30 175	96.97 84	99.75 85	95.70 173	99.25 259	99.21 189

OPU-MVS				97.64 134	98.01 286	95.27 125	96.79 162				97.35 297	96.97 84	98.51 438	91.21 358	99.25 259	99.14 207

RE-MVS-def			97.88 92		98.81 158	98.05 9	97.55 108	98.86 168	97.77 66	98.20 164	98.07 214	96.94 86		95.49 190	99.20 264	99.26 176

APDe-MVS		98.14 50	98.03 71	98.47 60	98.72 177	96.04 81	98.07 63	99.10 86	95.96 182	98.59 110	98.69 112	96.94 86	99.81 43	96.64 117	99.58 141	99.57 59
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
reproduce_model		98.54 25	98.33 47	99.15 3	99.06 113	98.04 11	97.04 142	99.09 91	98.42 43	99.03 57	98.71 109	96.93 88	99.83 35	97.09 103	99.63 113	99.56 67

test_one_0601					99.05 119	95.50 108		98.87 165	97.21 105	98.03 187	98.30 175	96.93 88

GST-MVS		97.82 97	97.49 148	98.81 30	99.23 75	97.25 41	97.16 133	98.79 198	95.96 182	97.53 226	97.40 288	96.93 88	99.77 69	95.04 234	99.35 234	99.42 127

test_241102_TWO								98.83 184	96.11 167	98.62 105	98.24 187	96.92 91	99.72 110	95.44 199	99.49 184	99.49 96

viewdifsd2359ckpt07		97.10 173	97.55 139	95.76 300	98.64 190	88.58 348	94.54 345	99.11 81	96.96 113	98.54 114	98.18 198	96.91 92	99.44 263	95.58 187	99.49 184	99.26 176

LCM-MVSNet-Re		97.33 156	97.33 157	97.32 166	98.13 278	93.79 184	96.99 146	99.65 12	96.74 125	99.47 23	98.93 78	96.91 92	99.84 33	90.11 390	99.06 290	98.32 345

viewmacassd2359aftdt		97.25 161	97.52 142	96.43 250	98.83 155	90.49 293	95.45 278	99.18 61	95.44 217	97.98 197	98.47 144	96.90 94	99.37 301	95.93 162	99.55 154	99.43 125

VPA-MVSNet		98.27 42	98.46 33	97.70 127	99.06 113	93.80 183	97.76 86	99.00 131	98.40 44	99.07 56	98.98 71	96.89 95	99.75 85	97.19 99	99.79 64	99.55 71

ACMMP		98.05 61	97.75 111	98.93 21	99.23 75	97.60 25	98.09 61	98.96 142	95.75 200	97.91 204	98.06 219	96.89 95	99.76 77	95.32 212	99.57 144	99.43 125
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 56	98.01 74	98.32 72	98.45 232	96.69 55	98.52 29	99.69 8	98.07 59	96.07 335	97.19 307	96.88 97	99.86 27	97.50 84	99.73 83	98.41 333

PMVS	89.60 17	96.71 209	96.97 184	95.95 291	99.51 32	97.81 19	97.42 120	97.49 344	97.93 62	95.95 339	98.58 128	96.88 97	96.91 478	89.59 399	99.36 229	93.12 487
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
region2R		97.92 79	97.59 133	98.92 24	99.22 78	97.55 29	97.60 103	98.84 177	96.00 179	97.22 247	97.62 270	96.87 99	99.76 77	95.48 194	99.43 210	99.46 108

CP-MVS		97.92 79	97.56 136	98.99 13	98.99 128	97.82 18	97.93 73	98.96 142	96.11 167	96.89 279	97.45 284	96.85 100	99.78 58	95.19 220	99.63 113	99.38 143

DPE-MVS		97.64 118	97.35 156	98.50 56	98.85 154	96.18 74	95.21 305	98.99 135	95.84 194	98.78 87	98.08 212	96.84 101	99.81 43	93.98 291	99.57 144	99.52 81
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_0402		97.84 93	97.97 78	97.47 152	99.19 89	94.07 172	96.71 171	98.73 210	98.66 31	98.56 113	98.41 151	96.84 101	99.69 143	94.82 251	99.81 58	98.64 306

SPE-MVS-test		97.91 83	97.84 95	98.14 94	98.52 216	96.03 84	98.38 38	99.67 9	98.11 57	95.50 363	96.92 333	96.81 103	99.87 25	96.87 113	99.76 70	98.51 325

E4		97.28 159	97.55 139	96.46 243	98.86 153	90.53 290	95.28 301	99.18 61	95.82 196	98.01 190	98.59 127	96.78 104	99.46 252	95.86 169	99.56 147	99.38 143

ACMMPR		97.95 72	97.62 128	98.94 18	99.20 87	97.56 28	97.59 105	98.83 184	96.05 174	97.46 236	97.63 269	96.77 105	99.76 77	95.61 184	99.46 194	99.49 96

Vis-MVSNet		98.27 42	98.34 45	98.07 98	99.33 60	95.21 132	98.04 64	99.46 30	97.32 98	97.82 214	99.11 54	96.75 106	99.86 27	97.84 67	99.36 229	99.15 201
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
Fast-Effi-MVS+		95.49 277	95.07 288	96.75 218	97.67 343	92.82 215	94.22 357	98.60 236	91.61 360	93.42 429	92.90 442	96.73 107	99.70 135	92.60 330	97.89 384	97.74 403

baseline		97.44 144	97.78 107	96.43 250	98.52 216	90.75 283	96.84 155	99.03 115	96.51 138	97.86 211	98.02 224	96.67 108	99.36 305	97.09 103	99.47 191	99.19 193

FE-MVSNET2		97.69 110	97.97 78	96.85 208	99.19 89	91.46 262	97.04 142	99.11 81	95.85 193	98.73 96	99.02 66	96.66 109	99.68 150	96.31 140	99.86 35	99.40 134

viewdifsd2359ckpt11		97.13 168	97.62 128	95.67 309	98.64 190	88.36 355	94.84 332	98.95 144	96.24 153	98.70 99	98.61 122	96.66 109	99.29 331	96.46 129	99.45 197	99.36 151

viewmsd2359difaftdt		97.13 168	97.62 128	95.67 309	98.64 190	88.36 355	94.84 332	98.95 144	96.24 153	98.70 99	98.61 122	96.66 109	99.29 331	96.46 129	99.45 197	99.36 151

SR-MVS		98.00 64	97.66 120	99.01 11	98.77 170	97.93 14	97.38 121	98.83 184	97.32 98	98.06 183	97.85 243	96.65 112	99.77 69	95.00 239	99.11 280	99.32 158

tfpnnormal		97.72 108	97.97 78	96.94 199	99.26 68	92.23 235	97.83 81	98.45 252	98.25 52	99.13 50	98.66 115	96.65 112	99.69 143	93.92 294	99.62 116	98.91 262

DeepPCF-MVS	94.58 5	96.90 188	96.43 230	98.31 74	97.48 362	97.23 43	92.56 415	98.60 236	92.84 336	98.54 114	97.40 288	96.64 114	98.78 408	94.40 271	99.41 217	98.93 258

MVS_111021_LR		96.82 197	96.55 221	97.62 135	98.27 253	95.34 122	93.81 379	98.33 272	94.59 259	96.56 305	96.63 352	96.61 115	98.73 414	94.80 252	99.34 239	98.78 281

Gipuma		98.07 59	98.31 49	97.36 163	99.76 7	96.28 72	98.51 30	99.10 86	98.76 29	96.79 284	99.34 29	96.61 115	98.82 404	96.38 135	99.50 181	96.98 433
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
SR-MVS-dyc-post		98.14 50	97.84 95	99.02 9	98.81 158	98.05 9	97.55 108	98.86 168	97.77 66	98.20 164	98.07 214	96.60 117	99.76 77	95.49 190	99.20 264	99.26 176

mamba_0408		97.17 166	97.38 153	96.55 237	98.51 218	90.96 275	95.19 306	99.06 100	96.60 130	98.27 152	97.78 253	96.58 118	99.72 110	95.04 234	99.40 218	98.98 245

SSM_04072		97.14 167	97.38 153	96.42 252	98.51 218	90.96 275	95.19 306	99.06 100	96.60 130	98.27 152	97.78 253	96.58 118	99.31 323	95.04 234	99.40 218	98.98 245

MVS_111021_HR		96.73 205	96.54 223	97.27 170	98.35 242	93.66 191	93.42 392	98.36 268	94.74 249	96.58 303	96.76 345	96.54 120	98.99 385	94.87 249	99.27 255	99.15 201

SMA-MVS		97.48 139	97.11 174	98.60 48	98.83 155	96.67 56	96.74 166	98.73 210	91.61 360	98.48 122	98.36 159	96.53 121	99.68 150	95.17 223	99.54 160	99.45 112
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 14	98.99 8	97.95 110	99.64 14	94.20 169	98.67 18	99.14 75	99.08 16	99.42 28	99.23 38	96.53 121	99.91 13	99.27 10	99.93 11	99.73 28

mPP-MVS		97.91 83	97.53 141	99.04 7	99.22 78	97.87 17	97.74 93	98.78 202	96.04 176	97.10 258	97.73 262	96.53 121	99.78 58	95.16 225	99.50 181	99.46 108

XVS		97.96 68	97.63 126	98.94 18	99.15 96	97.66 22	97.77 84	98.83 184	97.42 87	96.32 318	97.64 268	96.49 124	99.72 110	95.66 178	99.37 225	99.45 112

X-MVStestdata		92.86 379	90.83 411	98.94 18	99.15 96	97.66 22	97.77 84	98.83 184	97.42 87	96.32 318	36.50 499	96.49 124	99.72 110	95.66 178	99.37 225	99.45 112

9.14			96.69 205		98.53 215		96.02 230	98.98 138	93.23 314	97.18 252	97.46 283	96.47 126	99.62 187	92.99 324	99.32 246

UA-Net		98.88 10	98.76 16	99.22 2	99.11 105	97.89 16	99.47 3	99.32 39	99.08 16	97.87 210	99.67 5	96.47 126	99.92 5	97.88 64	99.98 2	99.85 6

fmvsm_l_conf0.5_n		97.68 113	97.81 101	97.27 170	98.92 142	92.71 222	95.89 246	99.41 37	93.36 309	99.00 62	98.44 147	96.46 128	99.65 171	99.09 23	99.76 70	99.45 112

fmvsm_s_conf0.5_n_5		97.63 120	97.83 98	97.04 191	98.77 170	92.33 229	95.63 270	99.58 18	93.53 302	99.10 52	98.66 115	96.44 129	99.65 171	99.12 21	99.68 101	99.12 215

SF-MVS		97.60 123	97.39 151	98.22 84	98.93 140	95.69 95	97.05 141	99.10 86	95.32 223	97.83 213	97.88 239	96.44 129	99.72 110	94.59 266	99.39 222	99.25 182

fmvsm_s_conf0.1_n_a		97.80 100	98.01 74	97.18 177	99.17 92	92.51 225	96.57 176	99.15 72	93.68 298	98.89 74	99.30 32	96.42 131	99.37 301	99.03 25	99.83 54	99.66 38

xiu_mvs_v1_base_debu		95.62 272	95.96 257	94.60 372	98.01 286	88.42 352	93.99 369	98.21 283	92.98 329	95.91 341	94.53 420	96.39 132	99.72 110	95.43 202	98.19 370	95.64 466

xiu_mvs_v1_base		95.62 272	95.96 257	94.60 372	98.01 286	88.42 352	93.99 369	98.21 283	92.98 329	95.91 341	94.53 420	96.39 132	99.72 110	95.43 202	98.19 370	95.64 466

xiu_mvs_v1_base_debi		95.62 272	95.96 257	94.60 372	98.01 286	88.42 352	93.99 369	98.21 283	92.98 329	95.91 341	94.53 420	96.39 132	99.72 110	95.43 202	98.19 370	95.64 466

ETV-MVS		96.13 245	95.90 261	96.82 212	97.76 329	93.89 179	95.40 284	98.95 144	95.87 191	95.58 360	91.00 467	96.36 135	99.72 110	93.36 314	98.83 318	96.85 440

fmvsm_s_conf0.5_n_11		97.90 85	98.34 45	96.60 228	98.75 172	90.50 292	96.28 201	99.56 22	97.05 108	99.15 48	99.11 54	96.31 136	99.69 143	98.97 29	99.84 49	99.62 45

TestfortrainingZip a		98.22 46	98.18 56	98.33 71	99.36 54	95.49 109	97.75 87	98.86 168	97.28 101	98.87 78	98.41 151	96.31 136	99.77 69	97.40 88	99.38 223	99.74 26

fmvsm_l_conf0.5_n_a		97.60 123	97.76 109	97.11 182	98.92 142	92.28 233	95.83 250	99.32 39	93.22 315	98.91 73	98.49 139	96.31 136	99.64 177	99.07 24	99.76 70	99.40 134

fmvsm_s_conf0.1_n		97.73 106	98.02 72	96.85 208	99.09 108	91.43 265	96.37 195	99.11 81	94.19 279	99.01 60	99.25 35	96.30 139	99.38 295	99.00 26	99.88 28	99.73 28

MP-MVS		97.64 118	97.18 172	99.00 12	99.32 62	97.77 20	97.49 114	98.73 210	96.27 150	95.59 359	97.75 258	96.30 139	99.78 58	93.70 306	99.48 189	99.45 112
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TinyColmap		96.00 252	96.34 237	94.96 352	97.90 299	87.91 372	94.13 364	98.49 249	94.41 271	98.16 170	97.76 255	96.29 141	98.68 423	90.52 383	99.42 213	98.30 350

Fast-Effi-MVS+-dtu		96.44 226	96.12 246	97.39 161	97.18 384	94.39 158	95.46 277	98.73 210	96.03 178	94.72 385	94.92 414	96.28 142	99.69 143	93.81 300	97.98 378	98.09 369

fmvsm_s_conf0.5_n_a		97.65 117	97.83 98	97.13 181	98.80 161	92.51 225	96.25 207	99.06 100	93.67 299	98.64 103	99.00 68	96.23 143	99.36 305	98.99 27	99.80 62	99.53 78

fmvsm_s_conf0.5_n		97.62 121	97.89 90	96.80 214	98.79 164	91.44 264	96.14 218	99.06 100	94.19 279	98.82 84	98.98 71	96.22 144	99.38 295	98.98 28	99.86 35	99.58 51

APD_test1		97.95 72	97.68 117	98.75 34	99.60 17	98.60 5	97.21 132	99.08 95	96.57 137	98.07 182	98.38 157	96.22 144	99.14 361	94.71 260	99.31 249	98.52 324

E2		96.97 182	97.19 170	96.33 261	98.64 190	90.34 298	95.07 316	99.12 78	95.00 239	97.66 219	98.31 169	96.19 146	99.43 266	95.35 210	99.35 234	99.23 185

E3		96.97 182	97.19 170	96.33 261	98.64 190	90.34 298	95.07 316	99.12 78	95.00 239	97.66 219	98.31 169	96.19 146	99.43 266	95.35 210	99.35 234	99.23 185

OMC-MVS		96.48 223	96.00 254	97.91 112	98.30 246	96.01 85	94.86 330	98.60 236	91.88 354	97.18 252	97.21 306	96.11 148	99.04 379	90.49 386	99.34 239	98.69 302

icg_test_0407_2		95.88 256	96.39 233	94.36 385	97.83 310	86.11 406	91.82 439	98.82 192	94.48 264	97.57 223	97.14 310	96.08 149	98.20 460	95.00 239	98.78 322	98.78 281

IMVS_0407		96.35 232	96.88 194	94.74 366	97.83 310	86.11 406	96.25 207	98.82 192	94.48 264	97.57 223	97.14 310	96.08 149	99.33 314	95.00 239	98.78 322	98.78 281

xiu_mvs_v2_base		94.22 338	94.63 314	92.99 425	97.32 378	84.84 430	92.12 431	97.84 321	91.96 352	94.17 399	93.43 433	96.07 151	99.71 126	91.27 355	97.48 406	94.42 478

CSCG		97.40 149	97.30 159	97.69 129	98.95 133	94.83 140	97.28 127	98.99 135	96.35 149	98.13 174	95.95 388	95.99 152	99.66 168	94.36 274	99.73 83	98.59 314

ME-MVS		97.53 136	97.32 158	98.16 90	98.70 183	95.35 117	96.04 227	98.60 236	96.16 166	97.99 192	97.54 276	95.94 153	99.70 135	95.36 207	99.53 164	99.44 122

PHI-MVS		96.96 184	96.53 224	98.25 82	97.48 362	96.50 62	96.76 164	98.85 173	93.52 303	96.19 330	96.85 336	95.94 153	99.42 270	93.79 301	99.43 210	98.83 275

viewmanbaseed2359cas		96.77 201	96.94 187	96.27 267	98.41 238	90.24 301	95.11 311	99.03 115	94.28 276	97.45 237	97.85 243	95.92 155	99.32 322	95.18 222	99.19 268	99.24 183

TSAR-MVS + MP.		97.42 148	97.23 166	98.00 107	99.38 52	95.00 137	97.63 102	98.20 286	93.00 328	98.16 170	98.06 219	95.89 156	99.72 110	95.67 177	99.10 283	99.28 171
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		97.58 131	97.28 162	98.49 57	99.16 93	96.90 49	96.39 191	98.98 138	95.05 236	98.06 183	98.02 224	95.86 157	99.56 211	94.37 272	99.64 111	99.00 238

AllTest		97.20 164	96.92 190	98.06 100	99.08 109	96.16 75	97.14 136	99.16 66	94.35 273	97.78 215	98.07 214	95.84 158	99.12 365	91.41 352	99.42 213	98.91 262

TestCases				98.06 100	99.08 109	96.16 75		99.16 66	94.35 273	97.78 215	98.07 214	95.84 158	99.12 365	91.41 352	99.42 213	98.91 262

APD-MVS		97.00 177	96.53 224	98.41 64	98.55 212	96.31 70	96.32 199	98.77 203	92.96 333	97.44 238	97.58 274	95.84 158	99.74 95	91.96 339	99.35 234	99.19 193
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
pcd_1.5k_mvsjas		7.98 469	10.65 472	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	95.82 161	0.00 505	0.00 503	0.00 503	0.00 501

PS-MVSNAJss		98.53 27	98.63 23	98.21 87	99.68 12	94.82 141	98.10 60	99.21 55	96.91 118	99.75 5	99.45 18	95.82 161	99.92 5	98.80 32	99.96 4	99.89 4

PS-MVSNAJ		94.10 344	94.47 324	93.00 424	97.35 373	84.88 427	91.86 437	97.84 321	91.96 352	94.17 399	92.50 452	95.82 161	99.71 126	91.27 355	97.48 406	94.40 479

3Dnovator	96.53 2	97.61 122	97.64 124	97.50 147	97.74 334	93.65 192	98.49 31	98.88 163	96.86 120	97.11 257	98.55 133	95.82 161	99.73 101	95.94 161	99.42 213	99.13 209

MTAPA		98.14 50	97.84 95	99.06 6	99.44 42	97.90 15	97.25 128	98.73 210	97.69 74	97.90 205	97.96 231	95.81 165	99.82 38	96.13 149	99.61 126	99.45 112

DP-MVS		97.87 90	97.89 90	97.81 118	98.62 201	94.82 141	97.13 137	98.79 198	98.98 23	98.74 94	98.49 139	95.80 166	99.49 236	95.04 234	99.44 200	99.11 220

Anonymous20240529		97.96 68	98.04 70	97.71 125	98.69 186	94.28 167	97.86 78	98.31 276	98.79 28	99.23 42	98.86 89	95.76 167	99.61 195	95.49 190	99.36 229	99.23 185

LS3D		97.77 103	97.50 146	98.57 50	96.24 411	97.58 27	98.45 34	98.85 173	98.58 36	97.51 228	97.94 234	95.74 168	99.63 182	95.19 220	98.97 295	98.51 325

viewcassd2359sk11		96.73 205	96.89 193	96.24 269	98.46 231	90.20 302	94.94 325	99.07 99	94.43 270	97.33 241	98.05 222	95.69 169	99.40 282	94.98 246	99.11 280	99.12 215

fmvsm_s_conf0.5_n_6		97.45 142	97.79 103	96.44 248	98.58 207	90.31 300	95.77 254	99.33 38	94.52 262	98.85 80	98.44 147	95.68 170	99.62 187	99.15 19	99.81 58	99.38 143

EIA-MVS		96.04 248	95.77 269	96.85 208	97.80 319	92.98 212	96.12 219	99.16 66	94.65 255	93.77 413	91.69 461	95.68 170	99.67 160	94.18 279	98.85 315	97.91 389

CNVR-MVS		96.92 186	96.55 221	98.03 105	98.00 290	95.54 103	94.87 329	98.17 292	94.60 257	96.38 315	97.05 321	95.67 172	99.36 305	95.12 231	99.08 285	99.19 193

CLD-MVS		95.47 280	95.07 288	96.69 222	98.27 253	92.53 224	91.36 447	98.67 225	91.22 376	95.78 352	94.12 427	95.65 173	98.98 387	90.81 369	99.72 88	98.57 315
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 24	98.76 16	97.94 111	98.79 164	94.37 161	98.84 14	99.15 72	99.37 6	99.67 10	99.43 20	95.61 174	99.72 110	98.12 51	99.86 35	99.73 28

EGC-MVSNET		83.08 459	77.93 464	98.53 54	99.57 20	97.55 29	98.33 42	98.57 243	4.71 501	10.38 502	98.90 85	95.60 175	99.50 230	95.69 175	99.61 126	98.55 318

fmvsm_s_conf0.5_n_4		97.43 146	97.77 108	96.39 259	98.48 227	89.89 309	95.65 265	99.26 47	94.73 251	98.72 97	98.58 128	95.58 176	99.57 209	99.28 9	99.67 104	99.73 28

usedtu_dtu_shiyan2		97.54 133	97.26 163	98.37 67	99.54 28	96.04 81	97.94 71	98.06 309	97.36 96	98.62 105	98.20 194	95.52 177	99.73 101	90.90 366	99.18 269	99.33 156

ITE_SJBPF				97.85 116	98.64 190	96.66 57		98.51 248	95.63 204	97.22 247	97.30 301	95.52 177	98.55 435	90.97 363	98.90 307	98.34 344

DeepC-MVS_fast	94.34 7	96.74 203	96.51 226	97.44 155	97.69 338	94.15 170	96.02 230	98.43 256	93.17 323	97.30 242	97.38 294	95.48 179	99.28 335	93.74 303	99.34 239	98.88 270
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 18	98.62 25	98.75 34	99.51 32	96.61 59	98.55 25	99.17 64	99.05 19	99.17 46	98.79 91	95.47 180	99.89 20	97.95 62	99.91 19	99.75 24

FMVSNet1		97.95 72	98.08 65	97.56 138	99.14 103	93.67 188	98.23 50	98.66 228	97.41 91	99.00 62	99.19 41	95.47 180	99.73 101	95.83 170	99.76 70	99.30 163

MIMVSNet1		98.51 28	98.45 36	98.67 43	99.72 8	96.71 53	98.76 16	98.89 156	98.49 40	99.38 31	99.14 52	95.44 182	99.84 33	96.47 128	99.80 62	99.47 106

mmtdpeth		98.33 36	98.53 31	97.71 125	99.07 111	93.44 199	98.80 15	99.78 4	99.10 15	96.61 301	99.63 10	95.42 183	99.73 101	98.53 43	99.86 35	99.95 2

IMVS_0403		96.27 236	96.77 202	94.76 364	97.83 310	86.11 406	96.00 232	98.82 192	94.48 264	97.49 230	97.14 310	95.38 184	99.40 282	95.00 239	98.78 322	98.78 281

CP-MVSNet		98.42 33	98.46 33	98.30 75	99.46 40	95.22 130	98.27 48	98.84 177	99.05 19	99.01 60	98.65 119	95.37 185	99.90 17	97.57 81	99.91 19	99.77 15

fmvsm_s_conf0.5_n_9		97.98 65	98.32 48	96.96 197	98.92 142	91.45 263	95.87 247	99.53 26	97.44 85	99.56 18	99.05 62	95.34 186	99.67 160	99.52 2	99.70 95	99.77 15

segment_acmp												95.34 186

CDPH-MVS		95.45 282	94.65 311	97.84 117	98.28 250	94.96 138	93.73 381	98.33 272	85.03 454	95.44 364	96.60 353	95.31 188	99.44 263	90.01 392	99.13 276	99.11 220

3Dnovator+	96.13 3	97.73 106	97.59 133	98.15 93	98.11 279	95.60 99	98.04 64	98.70 219	98.13 56	96.93 276	98.45 145	95.30 189	99.62 187	95.64 180	98.96 298	99.24 183

viewdifsd2359ckpt13		96.47 224	96.42 231	96.61 227	98.35 242	91.50 260	95.31 296	98.84 177	93.21 317	96.73 290	97.58 274	95.28 190	99.26 340	94.02 289	98.45 358	99.07 227

MVS_Test		96.27 236	96.79 201	94.73 367	96.94 394	86.63 398	96.18 212	98.33 272	94.94 243	96.07 335	98.28 180	95.25 191	99.26 340	97.21 96	97.90 383	98.30 350

XVG-OURS		97.12 171	96.74 203	98.26 79	98.99 128	97.45 35	93.82 377	99.05 106	95.19 228	98.32 146	97.70 264	95.22 192	98.41 445	94.27 276	98.13 373	98.93 258

E3new		96.50 220	96.61 211	96.17 277	98.28 250	90.09 303	94.85 331	99.02 119	93.95 290	97.01 268	97.74 261	95.19 193	99.39 291	94.70 261	98.77 328	99.04 233

fmvsm_s_conf0.5_n_2		97.59 126	98.07 66	96.17 277	98.78 168	89.10 334	95.33 293	99.55 24	95.96 182	99.41 30	99.10 56	95.18 194	99.59 200	99.43 6	99.86 35	99.81 10

fmvsm_s_conf0.1_n_2		97.68 113	98.18 56	96.20 273	99.06 113	89.08 335	95.51 275	99.72 6	96.06 173	99.48 21	99.24 36	95.18 194	99.60 198	99.45 4	99.88 28	99.94 3

dcpmvs_2		97.12 171	97.99 76	94.51 379	99.11 105	84.00 442	97.75 87	99.65 12	97.38 94	99.14 49	98.42 149	95.16 196	99.96 2	95.52 189	99.78 68	99.58 51

MCST-MVS		96.24 238	95.80 267	97.56 138	98.75 172	94.13 171	94.66 341	98.17 292	90.17 394	96.21 328	96.10 382	95.14 197	99.43 266	94.13 282	98.85 315	99.13 209

fmvsm_s_conf0.5_n_10		97.74 105	98.11 61	96.62 225	98.72 177	90.95 278	95.99 235	99.50 28	96.22 156	99.20 44	98.93 78	95.13 198	99.77 69	99.49 3	99.76 70	99.15 201

EI-MVSNet-Vis-set		97.32 157	97.39 151	97.11 182	97.36 372	92.08 245	95.34 292	97.65 334	97.74 69	98.29 151	98.11 208	95.05 199	99.68 150	97.50 84	99.50 181	99.56 67

EI-MVSNet-UG-set		97.32 157	97.40 150	97.09 186	97.34 375	92.01 248	95.33 293	97.65 334	97.74 69	98.30 150	98.14 201	95.04 200	99.69 143	97.55 82	99.52 172	99.58 51

KD-MVS_self_test		97.86 92	98.07 66	97.25 173	99.22 78	92.81 217	97.55 108	98.94 147	97.10 107	98.85 80	98.88 87	95.03 201	99.67 160	97.39 90	99.65 109	99.26 176

ZD-MVS					98.43 234	95.94 86		98.56 244	90.72 384	96.66 297	97.07 319	95.02 202	99.74 95	91.08 359	98.93 304

DELS-MVS		96.17 243	96.23 242	95.99 286	97.55 357	90.04 306	92.38 424	98.52 246	94.13 281	96.55 307	97.06 320	94.99 203	99.58 203	95.62 183	99.28 253	98.37 338
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		96.59 214	96.93 188	95.55 322	98.88 149	87.12 390	94.47 347	99.30 41	94.12 282	96.65 299	98.41 151	94.98 204	99.87 25	95.81 172	99.78 68	99.66 38

fmvsm_s_conf0.5_n_7		97.13 168	97.50 146	96.04 284	98.43 234	89.03 338	94.92 326	99.00 131	94.51 263	98.42 129	98.96 74	94.97 205	99.54 219	98.42 46	99.85 46	99.56 67

ab-mvs		96.59 214	96.59 214	96.60 228	98.64 190	92.21 236	98.35 39	97.67 330	94.45 269	96.99 270	98.79 91	94.96 206	99.49 236	90.39 387	99.07 287	98.08 370

MSLP-MVS++		96.42 229	96.71 204	95.57 316	97.82 314	90.56 287	95.71 257	98.84 177	94.72 252	96.71 292	97.39 292	94.91 207	98.10 462	95.28 213	99.02 292	98.05 379

QAPM		95.88 256	95.57 276	96.80 214	97.90 299	91.84 253	98.18 57	98.73 210	88.41 416	96.42 313	98.13 203	94.73 208	99.75 85	88.72 411	98.94 301	98.81 277

RPSCF		97.87 90	97.51 144	98.95 17	99.15 96	98.43 6	97.56 107	99.06 100	96.19 161	98.48 122	98.70 111	94.72 209	99.24 347	94.37 272	99.33 244	99.17 197

viewmambaseed2359dif		95.68 268	95.85 264	95.17 340	97.51 359	87.41 384	93.61 387	98.58 241	91.06 378	96.68 293	97.66 267	94.71 210	99.11 368	93.93 293	98.94 301	98.99 242

DU-MVS		97.79 101	97.60 132	98.36 69	98.73 174	95.78 91	95.65 265	98.87 165	97.57 78	98.31 148	97.83 246	94.69 211	99.85 30	97.02 108	99.71 91	99.46 108

Baseline_NR-MVSNet		97.72 108	97.79 103	97.50 147	99.56 22	93.29 205	95.44 279	98.86 168	98.20 55	98.37 135	99.24 36	94.69 211	99.55 216	95.98 159	99.79 64	99.65 41

TEST9					97.84 307	95.23 127	93.62 385	98.39 263	86.81 435	93.78 411	95.99 384	94.68 213	99.52 225

UniMVSNet (Re)		97.83 94	97.65 121	98.35 70	98.80 161	95.86 90	95.92 244	99.04 114	97.51 82	98.22 163	97.81 251	94.68 213	99.78 58	97.14 101	99.75 80	99.41 133

UniMVSNet_NR-MVSNet		97.83 94	97.65 121	98.37 67	98.72 177	95.78 91	95.66 263	99.02 119	98.11 57	98.31 148	97.69 265	94.65 215	99.85 30	97.02 108	99.71 91	99.48 102

diffmvs_AUTHOR		96.50 220	96.81 197	95.57 316	98.03 282	88.26 359	93.73 381	99.14 75	94.92 246	97.24 246	97.84 245	94.62 216	99.33 314	96.44 132	99.37 225	99.13 209

VPNet		97.26 160	97.49 148	96.59 230	99.47 39	90.58 285	96.27 203	98.53 245	97.77 66	98.46 125	98.41 151	94.59 217	99.68 150	94.61 262	99.29 252	99.52 81

train_agg		95.46 281	94.66 310	97.88 114	97.84 307	95.23 127	93.62 385	98.39 263	87.04 431	93.78 411	95.99 384	94.58 218	99.52 225	91.76 349	98.90 307	98.89 266

test_8					97.81 315	95.07 136	93.54 389	98.38 265	87.04 431	93.71 415	95.96 387	94.58 218	99.52 225

fmvsm_s_conf0.5_n_8		97.66 116	98.12 59	96.27 267	98.79 164	89.43 323	95.76 255	99.42 34	97.49 83	99.16 47	99.04 63	94.56 220	99.69 143	99.18 16	99.73 83	99.70 33

API-MVS		95.09 300	95.01 291	95.31 334	96.61 402	94.02 175	96.83 156	97.18 354	95.60 206	95.79 350	94.33 425	94.54 221	98.37 450	85.70 445	98.52 351	93.52 484

Test By Simon												94.51 222

MSDG		95.33 288	95.13 285	95.94 293	97.40 370	91.85 252	91.02 460	98.37 267	95.30 224	96.31 321	95.99 384	94.51 222	98.38 448	89.59 399	97.65 400	97.60 414

viewdifsd2359ckpt09		96.23 239	96.04 251	96.82 212	98.29 247	92.06 246	95.25 302	99.03 115	91.51 366	96.19 330	97.01 326	94.41 224	99.40 282	93.76 302	98.90 307	99.00 238

TSAR-MVS + GP.		96.47 224	96.12 246	97.49 150	97.74 334	95.23 127	94.15 361	96.90 371	93.26 313	98.04 186	96.70 348	94.41 224	98.89 396	94.77 256	99.14 274	98.37 338

NR-MVSNet		97.96 68	97.86 94	98.26 79	98.73 174	95.54 103	98.14 58	98.73 210	97.79 65	99.42 28	97.83 246	94.40 226	99.78 58	95.91 164	99.76 70	99.46 108

AdaColmap		95.11 298	94.62 315	96.58 231	97.33 377	94.45 157	94.92 326	98.08 304	93.15 324	93.98 409	95.53 402	94.34 227	99.10 372	85.69 446	98.61 346	96.20 459

Elysia		98.19 47	98.37 40	97.66 131	99.28 64	93.52 195	97.35 123	98.90 152	98.63 32	99.45 24	98.32 167	94.31 228	99.91 13	99.19 14	99.88 28	99.54 73

StellarMVS		98.19 47	98.37 40	97.66 131	99.28 64	93.52 195	97.35 123	98.90 152	98.63 32	99.45 24	98.32 167	94.31 228	99.91 13	99.19 14	99.88 28	99.54 73

FC-MVSNet-test		98.16 49	98.37 40	97.56 138	99.49 36	93.10 210	98.35 39	99.21 55	98.43 42	98.89 74	98.83 90	94.30 230	99.81 43	97.87 65	99.91 19	99.77 15

Effi-MVS+-dtu		96.81 198	96.09 248	98.99 13	96.90 396	98.69 4	96.42 188	98.09 303	95.86 192	95.15 372	95.54 401	94.26 231	99.81 43	94.06 284	98.51 354	98.47 330

ambc				96.56 235	98.23 259	91.68 257	97.88 77	98.13 300		98.42 129	98.56 132	94.22 232	99.04 379	94.05 286	99.35 234	98.95 251

test20.03		96.58 217	96.61 211	96.48 242	98.49 225	91.72 255	95.68 261	97.69 329	96.81 122	98.27 152	97.92 237	94.18 233	98.71 417	90.78 371	99.66 107	99.00 238

HPM-MVS++		96.99 178	96.38 235	98.81 30	98.64 190	97.59 26	95.97 238	98.20 286	95.51 212	95.06 374	96.53 357	94.10 234	99.70 135	94.29 275	99.15 273	99.13 209

test_vis3_rt		97.04 175	96.98 183	97.23 176	98.44 233	95.88 88	96.82 157	99.67 9	90.30 391	99.27 39	99.33 31	94.04 235	96.03 486	97.14 101	97.83 386	99.78 14

test_fmvs3		97.38 151	97.56 136	96.84 211	98.63 199	92.81 217	97.60 103	99.61 17	90.87 382	98.76 92	99.66 6	94.03 236	97.90 465	99.24 11	99.68 101	99.81 10

PM-MVS		97.36 155	97.10 175	98.14 94	98.91 145	96.77 52	96.20 211	98.63 234	93.82 292	98.54 114	98.33 164	93.98 237	99.05 377	95.99 158	99.45 197	98.61 313

mvsany_test3		96.21 240	95.93 260	97.05 189	97.40 370	94.33 163	95.76 255	94.20 426	89.10 405	99.36 34	99.60 11	93.97 238	97.85 466	95.40 206	98.63 344	98.99 242

OpenMVS	94.22 8	95.48 279	95.20 281	96.32 264	97.16 385	91.96 249	97.74 93	98.84 177	87.26 428	94.36 394	98.01 226	93.95 239	99.67 160	90.70 378	98.75 330	97.35 425

v8		97.60 123	98.06 69	96.23 270	98.71 181	89.44 322	97.43 119	98.82 192	97.29 100	98.74 94	99.10 56	93.86 240	99.68 150	98.61 40	99.94 8	99.56 67

diffmvs		96.04 248	96.23 242	95.46 327	97.35 373	88.03 370	93.42 392	99.08 95	94.09 285	96.66 297	96.93 331	93.85 241	99.29 331	96.01 157	98.67 339	99.06 230
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		96.52 219	95.99 255	98.10 97	97.81 315	95.68 96	95.00 323	98.20 286	95.39 220	95.40 367	96.36 368	93.81 242	99.45 260	93.55 311	98.42 361	99.17 197

TAPA-MVS	93.32 12	94.93 305	94.23 334	97.04 191	98.18 266	94.51 154	95.22 304	98.73 210	81.22 476	96.25 325	95.95 388	93.80 243	98.98 387	89.89 395	98.87 312	97.62 412
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SD_0403		93.73 356	93.43 354	94.64 368	97.85 301	86.35 403	97.47 115	97.94 313	93.50 304	93.71 415	96.73 346	93.77 244	98.84 402	73.48 489	96.39 439	98.72 297

FIs		97.93 78	98.07 66	97.48 151	99.38 52	92.95 214	98.03 66	99.11 81	98.04 61	98.62 105	98.66 115	93.75 245	99.78 58	97.23 94	99.84 49	99.73 28

OurMVSNet-221017-0		98.61 19	98.61 27	98.63 47	99.77 5	96.35 68	99.17 7	99.05 106	98.05 60	99.61 16	99.52 12	93.72 246	99.88 22	98.72 38	99.88 28	99.65 41

SSC-MVS3.2		95.75 264	96.56 218	93.34 409	98.69 186	80.75 467	91.60 442	97.43 348	97.37 95	96.99 270	97.02 323	93.69 247	99.71 126	96.32 139	99.89 26	99.55 71

test_prior2							93.33 396		94.21 277	94.02 407	96.25 373	93.64 248		91.90 341	98.96 298

mvsany_test1		93.47 365	93.03 362	94.79 362	94.05 478	92.12 241	90.82 464	90.01 477	85.02 455	97.26 245	98.28 180	93.57 249	97.03 475	92.51 333	95.75 459	95.23 472

旧先验1					97.80 319	93.87 180		97.75 326			97.04 322	93.57 249			98.68 338	98.72 297

IMVS_0404		95.66 271	96.03 252	94.55 376	97.83 310	86.11 406	93.24 398	98.82 192	94.48 264	95.51 362	97.14 310	93.49 251	98.78 408	95.00 239	98.78 322	98.78 281

v10		97.55 132	97.97 78	96.31 265	98.60 203	89.64 317	97.44 117	99.02 119	96.60 130	98.72 97	99.16 49	93.48 252	99.72 110	98.76 34	99.92 15	99.58 51

v148		96.58 217	96.97 184	95.42 328	98.63 199	87.57 380	95.09 313	97.90 316	95.91 189	98.24 161	97.96 231	93.42 253	99.39 291	96.04 153	99.52 172	99.29 170

V42		97.04 175	97.16 173	96.68 223	98.59 205	91.05 271	96.33 198	98.36 268	94.60 257	97.99 192	98.30 175	93.32 254	99.62 187	97.40 88	99.53 164	99.38 143

new-patchmatchnet		95.67 269	96.58 215	92.94 427	97.48 362	80.21 470	92.96 403	98.19 291	94.83 247	98.82 84	98.79 91	93.31 255	99.51 229	95.83 170	99.04 291	99.12 215

test12				97.46 153	97.61 351	94.07 172		97.78 325		93.57 423		93.31 255	99.42 270		98.78 322	98.89 266

KinetiMVS		97.82 97	98.02 72	97.24 175	99.24 72	92.32 231	96.92 149	98.38 265	98.56 39	99.03 57	98.33 164	93.22 257	99.83 35	98.74 35	99.71 91	99.57 59

UGNet		96.81 198	96.56 218	97.58 137	96.64 401	93.84 182	97.75 87	97.12 357	96.47 143	93.62 419	98.88 87	93.22 257	99.53 222	95.61 184	99.69 97	99.36 151
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
mvs5depth		98.06 60	98.58 29	96.51 239	98.97 132	89.65 316	99.43 4	99.81 2	99.30 9	98.36 138	99.86 2	93.15 259	99.88 22	98.50 44	99.84 49	99.99 1

pmmvs-eth3d		96.49 222	96.18 245	97.42 158	98.25 256	94.29 164	94.77 337	98.07 308	89.81 398	97.97 198	98.33 164	93.11 260	99.08 374	95.46 197	99.84 49	98.89 266

FE-MVSNET		96.59 214	96.65 208	96.41 255	98.94 136	90.51 291	96.07 222	99.05 106	92.94 334	98.03 187	98.00 228	93.08 261	99.42 270	94.04 287	99.74 82	99.30 163

v1144		96.84 193	97.08 177	96.13 281	98.42 236	89.28 326	95.41 283	98.67 225	94.21 277	97.97 198	98.31 169	93.06 262	99.65 171	98.06 57	99.62 116	99.45 112

MVSMamba_PlusPlus		97.43 146	97.98 77	95.78 299	98.88 149	89.70 313	98.03 66	98.85 173	99.18 13	96.84 283	99.12 53	93.04 263	99.91 13	98.38 47	99.55 154	97.73 404

PVSNet_BlendedMVS		95.02 304	94.93 294	95.27 335	97.79 324	87.40 385	94.14 363	98.68 222	88.94 409	94.51 390	98.01 226	93.04 263	99.30 327	89.77 397	99.49 184	99.11 220

PVSNet_Blended		93.96 350	93.65 350	94.91 353	97.79 324	87.40 385	91.43 446	98.68 222	84.50 461	94.51 390	94.48 423	93.04 263	99.30 327	89.77 397	98.61 346	98.02 382

mvs_anonymous		95.36 285	96.07 250	93.21 416	96.29 410	81.56 460	94.60 343	97.66 332	93.30 312	96.95 275	98.91 84	93.03 266	99.38 295	96.60 123	97.30 414	98.69 302

v1192		96.83 196	97.06 179	96.15 280	98.28 250	89.29 325	95.36 288	98.77 203	93.73 294	98.11 175	98.34 163	93.02 267	99.67 160	98.35 48	99.58 141	99.50 88

F-COLMAP		95.30 290	94.38 329	98.05 104	98.64 190	96.04 81	95.61 271	98.66 228	89.00 408	93.22 432	96.40 366	92.90 268	99.35 309	87.45 431	97.53 404	98.77 290

WR-MVS		96.90 188	96.81 197	97.16 178	98.56 211	92.20 239	94.33 350	98.12 301	97.34 97	98.20 164	97.33 299	92.81 269	99.75 85	94.79 253	99.81 58	99.54 73

v1240		96.74 203	97.02 182	95.91 294	98.18 266	88.52 349	95.39 285	98.88 163	93.15 324	98.46 125	98.40 156	92.80 270	99.71 126	98.45 45	99.49 184	99.49 96

MVE	73.61 22	86.48 455	85.92 454	88.18 474	96.23 413	85.28 421	81.78 495	75.79 499	86.01 441	82.53 492	91.88 458	92.74 271	87.47 498	71.42 493	94.86 467	91.78 489
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DP-MVS Recon		95.55 275	95.13 285	96.80 214	98.51 218	93.99 177	94.60 343	98.69 220	90.20 393	95.78 352	96.21 375	92.73 272	98.98 387	90.58 382	98.86 314	97.42 422

CANet		95.86 258	95.65 273	96.49 241	96.41 408	90.82 280	94.36 349	98.41 260	94.94 243	92.62 448	96.73 346	92.68 273	99.71 126	95.12 231	99.60 133	98.94 254

v1921920		96.72 207	96.96 186	95.99 286	98.21 260	88.79 344	95.42 281	98.79 198	93.22 315	98.19 168	98.26 185	92.68 273	99.70 135	98.34 49	99.55 154	99.49 96

BH-untuned		94.69 318	94.75 308	94.52 378	97.95 295	87.53 381	94.07 366	97.01 367	93.99 288	97.10 258	95.65 397	92.65 275	98.95 392	87.60 426	96.74 428	97.09 430

LF4IMVS		96.07 246	95.63 274	97.36 163	98.19 263	95.55 102	95.44 279	98.82 192	92.29 347	95.70 356	96.55 355	92.63 276	98.69 420	91.75 350	99.33 244	97.85 394

v2v482		96.78 200	97.06 179	95.95 291	98.57 209	88.77 345	95.36 288	98.26 278	95.18 229	97.85 212	98.23 189	92.58 277	99.63 182	97.80 69	99.69 97	99.45 112

TestfortrainingZip				97.39 161	97.24 382	94.58 151	97.75 87	97.64 338	96.08 171	96.48 310	96.31 370	92.56 278	99.27 338		96.62 433	98.31 347

WB-MVSnew		91.50 407	91.29 400	92.14 447	94.85 462	80.32 469	93.29 397	88.77 480	88.57 415	94.03 406	92.21 454	92.56 278	98.28 455	80.21 476	97.08 416	97.81 398

EI-MVSNet		96.63 213	96.93 188	95.74 302	97.26 380	88.13 367	95.29 299	97.65 334	96.99 109	97.94 202	98.19 195	92.55 280	99.58 203	96.91 111	99.56 147	99.50 88

IterMVS-LS		96.92 186	97.29 160	95.79 298	98.51 218	88.13 367	95.10 312	98.66 228	96.99 109	98.46 125	98.68 113	92.55 280	99.74 95	96.91 111	99.79 64	99.50 88
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
VDD-MVS		97.37 153	97.25 164	97.74 123	98.69 186	94.50 156	97.04 142	95.61 402	98.59 35	98.51 117	98.72 102	92.54 282	99.58 203	96.02 155	99.49 184	99.12 215

MVS		90.02 421	89.20 428	92.47 440	94.71 465	86.90 394	95.86 248	96.74 378	64.72 496	90.62 461	92.77 446	92.54 282	98.39 447	79.30 478	95.56 461	92.12 488

test_vis1_rt		94.03 349	93.65 350	95.17 340	95.76 438	93.42 201	93.97 372	98.33 272	84.68 458	93.17 433	95.89 390	92.53 284	94.79 490	93.50 312	94.97 465	97.31 427

v144192		96.69 210	96.90 192	96.03 285	98.25 256	88.92 339	95.49 276	98.77 203	93.05 326	98.09 178	98.29 179	92.51 285	99.70 135	98.11 52	99.56 147	99.47 106

原ACMM1				96.58 231	98.16 271	92.12 241		98.15 298	85.90 444	93.49 425	96.43 363	92.47 286	99.38 295	87.66 425	98.62 345	98.23 358

VNet		96.84 193	96.83 196	96.88 206	98.06 281	92.02 247	96.35 197	97.57 343	97.70 73	97.88 207	97.80 252	92.40 287	99.54 219	94.73 258	98.96 298	99.08 225

114514_t		93.96 350	93.22 359	96.19 275	99.06 113	90.97 274	95.99 235	98.94 147	73.88 494	93.43 428	96.93 331	92.38 288	99.37 301	89.09 406	99.28 253	98.25 357

BridgeMVS		96.88 190	97.29 160	95.63 312	97.66 344	89.47 321	97.95 70	98.89 156	95.94 185	97.77 217	98.55 133	92.23 289	99.68 150	97.05 107	99.61 126	97.73 404

CPTT-MVS		96.69 210	96.08 249	98.49 57	98.89 148	96.64 58	97.25 128	98.77 203	92.89 335	96.01 338	97.13 314	92.23 289	99.67 160	92.24 336	99.34 239	99.17 197

MSP-MVS		97.45 142	96.92 190	99.03 8	99.26 68	97.70 21	97.66 99	98.89 156	95.65 203	98.51 117	96.46 361	92.15 291	99.81 43	95.14 228	98.58 349	99.58 51
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		94.21 340	93.03 362	97.76 122	96.94 394	97.44 36	96.97 147	97.15 355	87.89 425	92.00 453	92.73 448	92.14 292	99.12 365	83.92 460	97.51 405	96.73 447
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		95.95 253	95.80 267	96.42 252	99.28 64	90.62 284	95.31 296	99.08 95	88.40 417	96.97 274	98.17 200	92.11 293	99.78 58	93.64 307	99.21 263	98.86 273

BH-RMVSNet		94.56 328	94.44 327	94.91 353	97.57 354	87.44 383	93.78 380	96.26 385	93.69 297	96.41 314	96.50 360	92.10 294	99.00 383	85.96 443	97.71 393	98.31 347

新几何1				97.25 173	98.29 247	94.70 145		97.73 327	77.98 487	94.83 381	96.67 350	92.08 295	99.45 260	88.17 420	98.65 343	97.61 413

testdata				95.70 308	98.16 271	90.58 285		97.72 328	80.38 479	95.62 357	97.02 323	92.06 296	98.98 387	89.06 408	98.52 351	97.54 417

YYNet1		94.73 313	94.84 302	94.41 384	97.47 366	85.09 425	90.29 469	95.85 396	92.52 341	97.53 226	97.76 255	91.97 297	99.18 354	93.31 317	96.86 421	98.95 251

Anonymous20231206		95.27 291	95.06 290	95.88 295	98.72 177	89.37 324	95.70 258	97.85 319	88.00 423	96.98 273	97.62 270	91.95 298	99.34 312	89.21 404	99.53 164	98.94 254

MS-PatchMatch		94.83 310	94.91 296	94.57 375	96.81 397	87.10 391	94.23 356	97.34 349	88.74 412	97.14 254	97.11 317	91.94 299	98.23 457	92.99 324	97.92 381	98.37 338

MDA-MVSNet_test_wron		94.73 313	94.83 304	94.42 383	97.48 362	85.15 423	90.28 470	95.87 395	92.52 341	97.48 233	97.76 255	91.92 300	99.17 358	93.32 316	96.80 426	98.94 254

HQP_MVS		96.66 212	96.33 238	97.68 130	98.70 183	94.29 164	96.50 181	98.75 207	96.36 147	96.16 332	96.77 343	91.91 301	99.46 252	92.59 331	99.20 264	99.28 171

plane_prior6					98.38 239	94.37 161						91.91 301

MVP-Stereo		95.69 266	95.28 279	96.92 201	98.15 273	93.03 211	95.64 269	98.20 286	90.39 390	96.63 300	97.73 262	91.63 303	99.10 372	91.84 344	97.31 413	98.63 308
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PatchMatch-RL		94.61 324	93.81 348	97.02 195	98.19 263	95.72 93	93.66 383	97.23 351	88.17 421	94.94 379	95.62 399	91.43 304	98.57 432	87.36 432	97.68 396	96.76 446

MDA-MVSNet-bldmvs		95.69 266	95.67 271	95.74 302	98.48 227	88.76 346	92.84 405	97.25 350	96.00 179	97.59 222	97.95 233	91.38 305	99.46 252	93.16 322	96.35 441	98.99 242

SSC-MVS		95.92 254	97.03 181	92.58 437	99.28 64	78.39 475	96.68 173	95.12 414	98.90 25	99.11 51	98.66 115	91.36 306	99.68 150	95.00 239	99.16 272	99.67 36

PAPR		92.22 392	91.27 402	95.07 345	95.73 440	88.81 343	91.97 434	97.87 318	85.80 445	90.91 460	92.73 448	91.16 307	98.33 452	79.48 477	95.76 458	98.08 370

1314		92.38 389	92.30 381	92.64 436	95.42 449	85.15 423	95.86 248	96.97 369	85.40 450	90.62 461	93.06 440	91.12 308	97.80 468	86.74 437	95.49 462	94.97 474

WB-MVS		95.50 276	96.62 209	92.11 448	99.21 85	77.26 485	96.12 219	95.40 408	98.62 34	98.84 82	98.26 185	91.08 309	99.50 230	93.37 313	98.70 337	99.58 51

balanced_ft_v1		96.29 234	96.60 213	95.38 333	96.77 398	88.73 347	98.44 37	98.44 255	94.97 242	95.91 341	98.77 95	91.03 310	99.75 85	96.16 148	98.91 306	97.65 409

ppachtmachnet_test		94.49 332	94.84 302	93.46 408	96.16 417	82.10 455	90.59 466	97.48 345	90.53 388	97.01 268	97.59 272	91.01 311	99.36 305	93.97 292	99.18 269	98.94 254

PLC	91.02 16	94.05 347	92.90 365	97.51 143	98.00 290	95.12 135	94.25 354	98.25 279	86.17 440	91.48 458	95.25 406	91.01 311	99.19 353	85.02 455	96.69 431	98.22 360
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test222					98.17 269	93.24 208	92.74 410	97.61 342	75.17 492	94.65 387	96.69 349	90.96 313			98.66 341	97.66 408

CL-MVSNet_self_test		95.04 301	94.79 307	95.82 297	97.51 359	89.79 312	91.14 457	96.82 374	93.05 326	96.72 291	96.40 366	90.82 314	99.16 359	91.95 340	98.66 341	98.50 328

USDC		94.56 328	94.57 321	94.55 376	97.78 327	86.43 401	92.75 408	98.65 233	85.96 442	96.91 278	97.93 236	90.82 314	98.74 413	90.71 377	99.59 136	98.47 330

PCF-MVS	89.43 18	92.12 395	90.64 415	96.57 233	97.80 319	93.48 198	89.88 476	98.45 252	74.46 493	96.04 337	95.68 396	90.71 316	99.31 323	73.73 488	99.01 294	96.91 437
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PAPM_NR		94.61 324	94.17 338	95.96 289	98.36 241	91.23 269	95.93 243	97.95 312	92.98 329	93.42 429	94.43 424	90.53 317	98.38 448	87.60 426	96.29 443	98.27 354

our_test_3		94.20 342	94.58 319	93.07 420	96.16 417	81.20 464	90.42 468	96.84 372	90.72 384	97.14 254	97.13 314	90.47 318	99.11 368	94.04 287	98.25 368	98.91 262

MM		96.87 191	96.62 209	97.62 135	97.72 336	93.30 204	96.39 191	92.61 447	97.90 64	96.76 289	98.64 120	90.46 319	99.81 43	99.16 18	99.94 8	99.76 21

test_f		95.82 260	95.88 263	95.66 311	97.61 351	93.21 209	95.61 271	98.17 292	86.98 433	98.42 129	99.47 16	90.46 319	94.74 491	97.71 75	98.45 358	99.03 234

OpenMVS_ROB	91.80 14	93.64 361	93.05 361	95.42 328	97.31 379	91.21 270	95.08 315	96.68 381	81.56 473	96.88 280	96.41 364	90.44 321	99.25 343	85.39 451	97.67 397	95.80 464

HQP2-MVS												90.33 322

N_pmnet		95.18 295	94.23 334	98.06 100	97.85 301	96.55 61	92.49 416	91.63 456	89.34 402	98.09 178	97.41 287	90.33 322	99.06 376	91.58 351	99.31 249	98.56 316

HQP-MVS		95.17 297	94.58 319	96.92 201	97.85 301	92.47 227	94.26 351	98.43 256	93.18 320	92.86 439	95.08 408	90.33 322	99.23 349	90.51 384	98.74 331	99.05 232

CNLPA		95.04 301	94.47 324	96.75 218	97.81 315	95.25 126	94.12 365	97.89 317	94.41 271	94.57 388	95.69 395	90.30 325	98.35 451	86.72 438	98.76 329	96.64 448

PMMVS		92.39 388	91.08 405	96.30 266	93.12 485	92.81 217	90.58 467	95.96 392	79.17 484	91.85 455	92.27 453	90.29 326	98.66 425	89.85 396	96.68 432	97.43 421

TR-MVS		92.54 387	92.20 384	93.57 406	96.49 405	86.66 397	93.51 390	94.73 419	89.96 396	94.95 378	93.87 430	90.24 327	98.61 429	81.18 473	94.88 466	95.45 470

TAMVS		95.49 277	94.94 292	97.16 178	98.31 245	93.41 202	95.07 316	96.82 374	91.09 377	97.51 228	97.82 249	89.96 328	99.42 270	88.42 416	99.44 200	98.64 306

DPM-MVS		93.68 359	92.77 372	96.42 252	97.91 298	92.54 223	91.17 456	97.47 346	84.99 456	93.08 435	94.74 416	89.90 329	99.00 383	87.54 428	98.09 375	97.72 406

PMMVS2		93.66 360	94.07 341	92.45 441	97.57 354	80.67 468	86.46 485	96.00 390	93.99 288	97.10 258	97.38 294	89.90 329	97.82 467	88.76 410	99.47 191	98.86 273

BH-w/o		92.14 394	91.94 386	92.73 433	97.13 387	85.30 419	92.46 418	95.64 399	89.33 403	94.21 397	92.74 447	89.60 331	98.24 456	81.68 470	94.66 468	94.66 476

Anonymous20240521		97.07 174	97.51 144	95.76 300	99.35 58	88.18 364	97.78 83	98.40 262	97.11 106	98.34 142	99.04 63	89.58 332	99.79 53	98.09 54	99.93 11	99.30 163

UnsupCasMVSNet_bld		94.72 317	94.26 333	96.08 283	98.62 201	90.54 288	93.38 394	98.05 311	90.30 391	97.02 267	96.80 342	89.54 333	99.16 359	88.44 415	96.18 445	98.56 316

MG-MVS		94.08 346	94.00 343	94.32 389	97.09 388	85.89 411	93.19 401	95.96 392	92.52 341	94.93 380	97.51 281	89.54 333	98.77 410	87.52 430	97.71 393	98.31 347

UnsupCasMVSNet_eth		95.91 255	95.73 270	96.44 248	98.48 227	91.52 259	95.31 296	98.45 252	95.76 198	97.48 233	97.54 276	89.53 335	98.69 420	94.43 268	94.61 469	99.13 209

GBi-Net		96.99 178	96.80 199	97.56 138	97.96 292	93.67 188	98.23 50	98.66 228	95.59 207	97.99 192	99.19 41	89.51 336	99.73 101	94.60 263	99.44 200	99.30 163

test1		96.99 178	96.80 199	97.56 138	97.96 292	93.67 188	98.23 50	98.66 228	95.59 207	97.99 192	99.19 41	89.51 336	99.73 101	94.60 263	99.44 200	99.30 163

FMVSNet2		96.72 207	96.67 207	96.87 207	97.96 292	91.88 251	97.15 134	98.06 309	95.59 207	98.50 119	98.62 121	89.51 336	99.65 171	94.99 245	99.60 133	99.07 227

AstraMVS		96.41 230	96.48 228	96.20 273	98.91 145	89.69 314	96.28 201	93.29 437	96.11 167	98.70 99	98.36 159	89.41 339	99.66 168	97.60 80	99.63 113	99.26 176

pmmvs4		94.82 311	94.19 337	96.70 221	97.42 369	92.75 221	92.09 433	96.76 376	86.80 436	95.73 355	97.22 305	89.28 340	98.89 396	93.28 318	99.14 274	98.46 332

cascas		91.89 401	91.35 399	93.51 407	94.27 472	85.60 413	88.86 481	98.61 235	79.32 483	92.16 452	91.44 463	89.22 341	98.12 461	90.80 370	97.47 408	96.82 443

DSMNet-mixed		92.19 393	91.83 388	93.25 413	96.18 416	83.68 446	96.27 203	93.68 431	76.97 491	92.54 449	99.18 45	89.20 342	98.55 435	83.88 461	98.60 348	97.51 418

c3_l		95.20 294	95.32 278	94.83 360	96.19 415	86.43 401	91.83 438	98.35 271	93.47 306	97.36 240	97.26 303	88.69 343	99.28 335	95.41 205	99.36 229	98.78 281

test_fmvs2		96.38 231	96.45 229	96.16 279	97.85 301	91.30 266	96.81 158	99.45 31	89.24 404	98.49 120	99.38 23	88.68 344	97.62 470	98.83 31	99.32 246	99.57 59

CANet_DTU		94.65 322	94.21 336	95.96 289	95.90 427	89.68 315	93.92 374	97.83 323	93.19 319	90.12 470	95.64 398	88.52 345	99.57 209	93.27 319	99.47 191	98.62 309

EPP-MVSNet		96.84 193	96.58 215	97.65 133	99.18 91	93.78 185	98.68 17	96.34 384	97.91 63	97.30 242	98.06 219	88.46 346	99.85 30	93.85 297	99.40 218	99.32 158

SixPastTwentyTwo		97.49 138	97.57 135	97.26 172	99.56 22	92.33 229	98.28 46	96.97 369	98.30 49	99.45 24	99.35 28	88.43 347	99.89 20	98.01 59	99.76 70	99.54 73

miper_ehance_all_eth		94.69 318	94.70 309	94.64 368	95.77 437	86.22 404	91.32 451	98.24 281	91.67 357	97.05 265	96.65 351	88.39 348	99.22 351	94.88 248	98.34 364	98.49 329

MGCNet		95.71 265	95.18 283	97.33 165	94.85 462	92.82 215	95.36 288	90.89 465	95.51 212	95.61 358	97.82 249	88.39 348	99.78 58	98.23 50	99.91 19	99.40 134

IS-MVSNet		96.93 185	96.68 206	97.70 127	99.25 71	94.00 176	98.57 23	96.74 378	98.36 45	98.14 173	97.98 230	88.23 350	99.71 126	93.10 323	99.72 88	99.38 143

jason		94.39 335	94.04 342	95.41 330	98.29 247	87.85 375	92.74 410	96.75 377	85.38 451	95.29 369	96.15 377	88.21 351	99.65 171	94.24 277	99.34 239	98.74 294
jason: jason.
IterMVS-SCA-FT		95.86 258	96.19 244	94.85 358	97.68 339	85.53 414	92.42 421	97.63 341	96.99 109	98.36 138	98.54 135	87.94 352	99.75 85	97.07 106	99.08 285	99.27 175

SCA		93.38 368	93.52 353	92.96 426	96.24 411	81.40 462	93.24 398	94.00 427	91.58 365	94.57 388	96.97 328	87.94 352	99.42 270	89.47 401	97.66 399	98.06 376

sss		94.22 338	93.72 349	95.74 302	97.71 337	89.95 308	93.84 376	96.98 368	88.38 418	93.75 414	95.74 394	87.94 352	98.89 396	91.02 361	98.10 374	98.37 338

IterMVS		95.42 283	95.83 266	94.20 393	97.52 358	83.78 445	92.41 422	97.47 346	95.49 214	98.06 183	98.49 139	87.94 352	99.58 203	96.02 155	99.02 292	99.23 185
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CHOSEN 1792x2688		94.10 344	93.41 356	96.18 276	99.16 93	90.04 306	92.15 429	98.68 222	79.90 481	96.22 327	97.83 246	87.92 356	99.42 270	89.18 405	99.65 109	99.08 225

VDDNet		96.98 181	96.84 195	97.41 159	99.40 49	93.26 207	97.94 71	95.31 410	99.26 11	98.39 134	99.18 45	87.85 357	99.62 187	95.13 230	99.09 284	99.35 155

LuminaMVS		96.76 202	96.58 215	97.30 167	98.94 136	92.96 213	96.17 216	96.15 386	95.54 211	98.96 68	98.18 198	87.73 358	99.80 50	97.98 60	99.61 126	99.15 201

pmmvs5		94.63 323	94.34 330	95.50 324	97.63 350	88.34 357	94.02 367	97.13 356	87.15 430	95.22 371	97.15 309	87.50 359	99.27 338	93.99 290	99.26 258	98.88 270

D2MVS		95.18 295	95.17 284	95.21 337	97.76 329	87.76 378	94.15 361	97.94 313	89.77 399	96.99 270	97.68 266	87.45 360	99.14 361	95.03 238	99.81 58	98.74 294

test_vis1_n_1920		95.77 262	96.41 232	93.85 398	98.55 212	84.86 429	95.91 245	99.71 7	92.72 339	97.67 218	98.90 85	87.44 361	98.73 414	97.96 61	98.85 315	97.96 386

guyue		96.21 240	96.29 239	95.98 288	98.80 161	89.14 332	96.40 189	94.34 425	95.99 181	98.58 111	98.13 203	87.42 362	99.64 177	97.39 90	99.55 154	99.16 200

PVSNet	86.72 19	91.10 412	90.97 408	91.49 453	97.56 356	78.04 478	87.17 483	94.60 421	84.65 459	92.34 450	92.20 455	87.37 363	98.47 442	85.17 454	97.69 395	97.96 386

Anonymous202405211		96.34 233	95.98 256	97.43 156	98.25 256	93.85 181	96.74 166	94.41 423	97.72 71	98.37 135	98.03 223	87.15 364	99.53 222	94.06 284	99.07 287	98.92 261

VortexMVS		96.04 248	96.56 218	94.49 381	97.60 353	84.36 437	96.05 225	98.67 225	94.74 249	98.95 69	98.78 94	87.13 365	99.50 230	97.37 92	99.76 70	99.60 47

MVSFormer		96.14 244	96.36 236	95.49 325	97.68 339	87.81 376	98.67 18	99.02 119	96.50 139	94.48 392	96.15 377	86.90 366	99.92 5	98.73 36	99.13 276	98.74 294

lupinMVS		93.77 353	93.28 357	95.24 336	97.68 339	87.81 376	92.12 431	96.05 388	84.52 460	94.48 392	95.06 410	86.90 366	99.63 182	93.62 310	99.13 276	98.27 354

eth_miper_zixun_eth		94.89 308	94.93 294	94.75 365	95.99 424	86.12 405	91.35 448	98.49 249	93.40 307	97.12 256	97.25 304	86.87 368	99.35 309	95.08 233	98.82 319	98.78 281

test_vis1_n		95.67 269	95.89 262	95.03 347	98.18 266	89.89 309	96.94 148	99.28 45	88.25 420	98.20 164	98.92 81	86.69 369	97.19 473	97.70 77	98.82 319	98.00 384

usedtu_dtu_shiyan1		94.61 324	94.29 331	95.57 316	97.93 296	88.45 350	91.30 452	97.64 338	91.61 360	95.85 348	95.79 392	86.65 370	99.48 239	92.92 327	98.97 295	98.78 281

FE-MVSNET3		94.61 324	94.29 331	95.57 316	97.93 296	88.45 350	91.30 452	97.64 338	91.61 360	95.85 348	95.79 392	86.65 370	99.48 239	92.92 327	98.97 295	98.78 281

RRT-MVS		95.78 261	96.25 241	94.35 387	96.68 400	84.47 435	97.72 95	99.11 81	97.23 103	97.27 244	98.72 102	86.39 372	99.79 53	95.49 190	97.67 397	98.80 278

WTY-MVS		93.55 363	93.00 364	95.19 338	97.81 315	87.86 373	93.89 375	96.00 390	89.02 407	94.07 404	95.44 405	86.27 373	99.33 314	87.69 424	96.82 424	98.39 336

CDS-MVSNet		94.88 309	94.12 340	97.14 180	97.64 349	93.57 193	93.96 373	97.06 363	90.05 395	96.30 322	96.55 355	86.10 374	99.47 245	90.10 391	99.31 249	98.40 334
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
1112_ss		94.12 343	93.42 355	96.23 270	98.59 205	90.85 279	94.24 355	98.85 173	85.49 447	92.97 437	94.94 412	86.01 375	99.64 177	91.78 348	97.92 381	98.20 362

dmvs_testset		87.30 452	86.99 448	88.24 473	96.71 399	77.48 482	94.68 340	86.81 490	92.64 340	89.61 475	87.01 489	85.91 376	93.12 494	61.04 496	88.49 486	94.13 481

miper_enhance_ethall		93.14 376	92.78 371	94.20 393	93.65 481	85.29 420	89.97 472	97.85 319	85.05 453	96.15 334	94.56 419	85.74 377	99.14 361	93.74 303	98.34 364	98.17 366

ttmdpeth		94.05 347	94.15 339	93.75 401	95.81 434	85.32 418	96.00 232	94.93 417	92.07 348	94.19 398	99.09 58	85.73 378	96.41 485	90.98 362	98.52 351	99.53 78

new_pmnet		92.34 390	91.69 395	94.32 389	96.23 413	89.16 330	92.27 427	92.88 441	84.39 463	95.29 369	96.35 369	85.66 379	96.74 483	84.53 458	97.56 402	97.05 431

Syy-MVS		92.09 396	91.80 390	92.93 428	95.19 454	82.65 451	92.46 418	91.35 459	90.67 386	91.76 456	87.61 483	85.64 380	98.50 439	94.73 258	96.84 422	97.65 409

alignmvs		96.01 251	95.52 277	97.50 147	97.77 328	94.71 143	96.07 222	96.84 372	97.48 84	96.78 288	94.28 426	85.50 381	99.40 282	96.22 145	98.73 334	98.40 334

NormalMVS		96.87 191	96.39 233	98.30 75	99.48 37	95.57 100	96.87 153	98.90 152	96.94 116	96.85 281	97.88 239	85.36 382	99.76 77	95.63 181	99.59 136	99.57 59

SymmetryMVS		96.43 228	95.85 264	98.17 88	98.58 207	95.57 100	96.87 153	95.29 411	96.94 116	96.85 281	97.88 239	85.36 382	99.76 77	95.63 181	99.27 255	99.19 193

lessismore_v0				97.05 189	99.36 54	92.12 241		84.07 493		98.77 91	98.98 71	85.36 382	99.74 95	97.34 93	99.37 225	99.30 163

HY-MVS	91.43 15	92.58 386	91.81 389	94.90 355	96.49 405	88.87 341	97.31 125	94.62 420	85.92 443	90.50 464	96.84 337	85.05 385	99.40 282	83.77 463	95.78 457	96.43 455

EPNet		93.72 357	92.62 376	97.03 193	87.61 502	92.25 234	96.27 203	91.28 461	96.74 125	87.65 484	97.39 292	85.00 386	99.64 177	92.14 337	99.48 189	99.20 192
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_lstm_enhance		94.81 312	94.80 306	94.85 358	96.16 417	86.45 400	91.14 457	98.20 286	93.49 305	97.03 266	97.37 296	84.97 387	99.26 340	95.28 213	99.56 147	98.83 275

Test_1112_low_res		93.53 364	92.86 366	95.54 323	98.60 203	88.86 342	92.75 408	98.69 220	82.66 468	92.65 445	96.92 333	84.75 388	99.56 211	90.94 364	97.76 389	98.19 363

MVS-HIRNet		88.40 441	90.20 421	82.99 478	97.01 390	60.04 503	93.11 402	85.61 492	84.45 462	88.72 480	99.09 58	84.72 389	98.23 457	82.52 467	96.59 435	90.69 493

K. test v3		96.44 226	96.28 240	96.95 198	99.41 46	91.53 258	97.65 100	90.31 473	98.89 26	98.93 70	99.36 26	84.57 390	99.92 5	97.81 68	99.56 147	99.39 141

test_cas_vis1_n_1920		95.34 287	95.67 271	94.35 387	98.21 260	86.83 396	95.61 271	99.26 47	90.45 389	98.17 169	98.96 74	84.43 391	98.31 453	96.74 116	99.17 271	97.90 390

h-mvs33		96.29 234	95.63 274	98.26 79	98.50 224	96.11 78	96.90 151	97.09 361	96.58 134	97.21 249	98.19 195	84.14 392	99.78 58	95.89 165	96.17 446	98.89 266

hse-mvs2		95.77 262	95.09 287	97.79 119	97.84 307	95.51 105	95.66 263	95.43 407	96.58 134	97.21 249	96.16 376	84.14 392	99.54 219	95.89 165	96.92 418	98.32 345

MonoMVSNet		93.30 372	93.96 346	91.33 456	94.14 476	81.33 463	97.68 98	96.69 380	95.38 221	96.32 318	98.42 149	84.12 394	96.76 482	90.78 371	92.12 479	95.89 461

DIV-MVS_self_test		94.73 313	94.64 312	95.01 348	95.86 430	87.00 392	91.33 449	98.08 304	93.34 310	97.10 258	97.34 298	84.02 395	99.31 323	95.15 227	99.55 154	98.72 297

cl____		94.73 313	94.64 312	95.01 348	95.85 431	87.00 392	91.33 449	98.08 304	93.34 310	97.10 258	97.33 299	84.01 396	99.30 327	95.14 228	99.56 147	98.71 301

Vis-MVSNet (Re-imp)		95.11 298	94.85 301	95.87 296	99.12 104	89.17 327	97.54 113	94.92 418	96.50 139	96.58 303	97.27 302	83.64 397	99.48 239	88.42 416	99.67 104	98.97 248

FA-MVS(test-final)		94.91 306	94.89 297	94.99 350	97.51 359	88.11 369	98.27 48	95.20 413	92.40 346	96.68 293	98.60 126	83.44 398	99.28 335	93.34 315	98.53 350	97.59 415

dmvs_re		92.08 397	91.27 402	94.51 379	97.16 385	92.79 220	95.65 265	92.64 446	94.11 283	92.74 442	90.98 468	83.41 399	94.44 493	80.72 474	94.07 472	96.29 457

PVSNet_0	81.89 21	84.49 456	83.21 459	88.34 472	95.76 438	74.97 493	83.49 492	92.70 445	78.47 486	87.94 483	86.90 490	83.38 400	96.63 484	73.44 490	66.86 498	93.40 485

mvsmamba		94.91 306	94.41 328	96.40 258	97.65 346	91.30 266	97.92 74	95.32 409	91.50 367	95.54 361	98.38 157	83.06 401	99.68 150	92.46 334	97.84 385	98.23 358

test_fmvs1_n		95.21 293	95.28 279	94.99 350	98.15 273	89.13 333	96.81 158	99.43 33	86.97 434	97.21 249	98.92 81	83.00 402	97.13 474	98.09 54	98.94 301	98.72 297

CMPMVS	73.10 23	92.74 382	91.39 398	96.77 217	93.57 483	94.67 146	94.21 358	97.67 330	80.36 480	93.61 420	96.60 353	82.85 403	97.35 472	84.86 456	98.78 322	98.29 353
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_fmvs1		94.51 331	94.60 316	94.26 392	95.91 426	87.92 371	95.35 291	99.02 119	86.56 438	96.79 284	98.52 136	82.64 404	97.00 477	97.87 65	98.71 335	97.88 392

EU-MVSNet		94.25 337	94.47 324	93.60 405	98.14 275	82.60 453	97.24 130	92.72 444	85.08 452	98.48 122	98.94 77	82.59 405	98.76 412	97.47 86	99.53 164	99.44 122

blended_shiyan8		93.34 369	92.55 378	95.73 305	95.69 441	89.08 335	92.36 425	97.11 358	91.47 369	95.42 366	88.94 480	82.26 406	99.48 239	93.84 298	95.81 453	98.62 309

blended_shiyan6		93.34 369	92.54 379	95.73 305	95.68 442	89.08 335	92.35 426	97.10 359	91.47 369	95.37 368	88.96 479	82.26 406	99.48 239	93.83 299	95.85 449	98.62 309

baseline1		93.14 376	92.64 375	94.62 371	97.34 375	87.20 389	96.67 175	93.02 439	94.71 253	96.51 309	95.83 391	81.64 408	98.60 431	90.00 393	88.06 487	98.07 372

test1111		94.53 330	94.81 305	93.72 402	99.06 113	81.94 458	98.31 43	83.87 494	96.37 146	98.49 120	99.17 48	81.49 409	99.73 101	96.64 117	99.86 35	99.49 96

CVMVSNet		92.33 391	92.79 369	90.95 458	97.26 380	75.84 489	95.29 299	92.33 450	81.86 471	96.27 323	98.19 195	81.44 410	98.46 443	94.23 278	98.29 367	98.55 318

EPNet_dtu		91.39 409	90.75 412	93.31 411	90.48 495	82.61 452	94.80 334	92.88 441	93.39 308	81.74 493	94.90 415	81.36 411	99.11 368	88.28 418	98.87 312	98.21 361
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ECVR-MVS		94.37 336	94.48 323	94.05 397	98.95 133	83.10 448	98.31 43	82.48 496	96.20 157	98.23 162	99.16 49	81.18 412	99.66 168	95.95 160	99.83 54	99.38 143

test_yl		94.40 333	94.00 343	95.59 314	96.95 392	89.52 319	94.75 338	95.55 404	96.18 164	96.79 284	96.14 379	81.09 413	99.18 354	90.75 373	97.77 387	98.07 372

DCV-MVSNet		94.40 333	94.00 343	95.59 314	96.95 392	89.52 319	94.75 338	95.55 404	96.18 164	96.79 284	96.14 379	81.09 413	99.18 354	90.75 373	97.77 387	98.07 372

MIMVSNet		93.42 366	92.86 366	95.10 344	98.17 269	88.19 361	98.13 59	93.69 429	92.07 348	95.04 377	98.21 193	80.95 415	99.03 382	81.42 471	98.06 376	98.07 372

PAPM		87.64 448	85.84 455	93.04 421	96.54 403	84.99 426	88.42 482	95.57 403	79.52 482	83.82 490	93.05 441	80.57 416	98.41 445	62.29 495	92.79 476	95.71 465

HyFIR lowres test		93.72 357	92.65 374	96.91 203	98.93 140	91.81 254	91.23 455	98.52 246	82.69 467	96.46 312	96.52 359	80.38 417	99.90 17	90.36 388	98.79 321	99.03 234

wanda-best-256-512		92.66 384	91.75 393	95.40 331	94.99 458	88.19 361	90.89 461	97.05 364	91.02 380	94.75 382	87.24 486	80.36 418	99.46 252	93.63 308	95.85 449	98.55 318

FE-blended-shiyan7		92.66 384	91.75 393	95.40 331	94.99 458	88.19 361	90.89 461	97.05 364	91.02 380	94.75 382	87.24 486	80.36 418	99.46 252	93.63 308	95.85 449	98.55 318

usedtu_blend_shiyan5		93.74 355	93.08 360	95.71 307	94.99 458	89.17 327	97.38 121	98.93 149	96.40 144	94.75 382	87.24 486	80.36 418	99.40 282	91.84 344	95.85 449	98.55 318

gbinet_0.2-2-1-0.02		92.86 379	91.78 391	96.13 281	94.34 469	90.06 304	91.90 436	96.63 383	91.73 356	94.24 396	86.22 491	80.26 421	99.56 211	93.87 296	96.80 426	98.77 290

FMVSNet3		95.26 292	94.94 292	96.22 272	96.53 404	90.06 304	95.99 235	97.66 332	94.11 283	97.99 192	97.91 238	80.22 422	99.63 182	94.60 263	99.44 200	98.96 249

RPMNet		94.68 320	94.60 316	94.90 355	95.44 447	88.15 365	96.18 212	98.86 168	97.43 86	94.10 402	98.49 139	79.40 423	99.76 77	95.69 175	95.81 453	96.81 444

LFMVS		95.32 289	94.88 299	96.62 225	98.03 282	91.47 261	97.65 100	90.72 468	99.11 14	97.89 206	98.31 169	79.20 424	99.48 239	93.91 295	99.12 279	98.93 258

ADS-MVSNet2		91.47 408	90.51 417	94.36 385	95.51 445	85.63 412	95.05 320	95.70 397	83.46 465	92.69 443	96.84 337	79.15 425	99.41 280	85.66 447	90.52 481	98.04 380

ADS-MVSNet		90.95 415	90.26 420	93.04 421	95.51 445	82.37 454	95.05 320	93.41 435	83.46 465	92.69 443	96.84 337	79.15 425	98.70 418	85.66 447	90.52 481	98.04 380

MDTV_nov1_ep13_2view						57.28 504	94.89 328		80.59 478	94.02 407		78.66 427		85.50 449		97.82 396

cl22		93.25 374	92.84 368	94.46 382	94.30 471	86.00 410	91.09 459	96.64 382	90.74 383	95.79 350	96.31 370	78.24 428	98.77 410	94.15 281	98.34 364	98.62 309

PatchmatchNet		91.98 400	91.87 387	92.30 444	94.60 467	79.71 471	95.12 309	93.59 434	89.52 401	93.61 420	97.02 323	77.94 429	99.18 354	90.84 368	94.57 471	98.01 383
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												77.80 430				98.06 376

CR-MVSNet		93.29 373	92.79 369	94.78 363	95.44 447	88.15 365	96.18 212	97.20 352	84.94 457	94.10 402	98.57 130	77.67 431	99.39 291	95.17 223	95.81 453	96.81 444

Patchmtry		95.03 303	94.59 318	96.33 261	94.83 464	90.82 280	96.38 194	97.20 352	96.59 133	97.49 230	98.57 130	77.67 431	99.38 295	92.95 326	99.62 116	98.80 278

tpmrst		90.31 418	90.61 416	89.41 467	94.06 477	72.37 498	95.06 319	93.69 429	88.01 422	92.32 451	96.86 335	77.45 433	98.82 404	91.04 360	87.01 488	97.04 432

sam_mvs												77.38 434

patchmatchnet-post											96.84 337	77.36 435	99.42 270

Patchmatch-RL test		94.66 321	94.49 322	95.19 338	98.54 214	88.91 340	92.57 414	98.74 209	91.46 371	98.32 146	97.75 258	77.31 436	98.81 406	96.06 150	99.61 126	97.85 394

tpmvs		90.79 416	90.87 409	90.57 461	92.75 489	76.30 487	95.79 253	93.64 433	91.04 379	91.91 454	96.26 372	77.19 437	98.86 401	89.38 403	89.85 484	96.56 451

test_post											10.87 502	76.83 438	99.07 375

Patchmatch-test		93.60 362	93.25 358	94.63 370	96.14 421	87.47 382	96.04 227	94.50 422	93.57 300	96.47 311	96.97 328	76.50 439	98.61 429	90.67 380	98.41 362	97.81 398

MDTV_nov1_ep13			91.28 401		94.31 470	73.51 496	94.80 334	93.16 438	86.75 437	93.45 427	97.40 288	76.37 440	98.55 435	88.85 409	96.43 437

EMVS		89.06 434	89.22 426	88.61 471	93.00 486	77.34 483	82.91 494	90.92 464	94.64 256	92.63 447	91.81 459	76.30 441	97.02 476	83.83 462	96.90 420	91.48 491

test_post1							94.98 324				10.37 503	76.21 442	99.04 379	89.47 401

GA-MVS		92.83 381	92.15 385	94.87 357	96.97 391	87.27 388	90.03 471	96.12 387	91.83 355	94.05 405	94.57 418	76.01 443	98.97 391	92.46 334	97.34 412	98.36 343

BP-MVS1		95.36 285	94.86 300	96.89 205	98.35 242	91.72 255	96.76 164	95.21 412	96.48 142	96.23 326	97.19 307	75.97 444	99.80 50	97.91 63	99.60 133	99.15 201

PatchT		93.75 354	93.57 352	94.29 391	95.05 457	87.32 387	96.05 225	92.98 440	97.54 81	94.25 395	98.72 102	75.79 445	99.24 347	95.92 163	95.81 453	96.32 456

E-PMN		89.52 431	89.78 423	88.73 470	93.14 484	77.61 481	83.26 493	92.02 452	94.82 248	93.71 415	93.11 435	75.31 446	96.81 479	85.81 444	96.81 425	91.77 490

DeepMVS_CX				77.17 479	90.94 493	85.28 421		74.08 502	52.51 498	80.87 495	88.03 482	75.25 447	70.63 500	59.23 497	84.94 490	75.62 494

GDP-MVS		95.39 284	94.89 297	96.90 204	98.26 255	91.91 250	96.48 187	99.28 45	95.06 235	96.54 308	97.12 316	74.83 448	99.82 38	97.19 99	99.27 255	98.96 249

AUN-MVS		93.95 352	92.69 373	97.74 123	97.80 319	95.38 114	95.57 274	95.46 406	91.26 375	92.64 446	96.10 382	74.67 449	99.55 216	93.72 305	96.97 417	98.30 350

CHOSEN 280x420		89.98 423	89.19 429	92.37 442	95.60 444	81.13 465	86.22 486	97.09 361	81.44 475	87.44 485	93.15 434	73.99 450	99.47 245	88.69 412	99.07 287	96.52 452

thres200		91.00 414	90.42 418	92.77 432	97.47 366	83.98 443	94.01 368	91.18 463	95.12 232	95.44 364	91.21 465	73.93 451	99.31 323	77.76 483	97.63 401	95.01 473

test-LLR		89.97 424	89.90 422	90.16 462	94.24 473	74.98 491	89.89 473	89.06 478	92.02 350	89.97 471	90.77 469	73.92 452	98.57 432	91.88 342	97.36 410	96.92 435

test0.0.03 1		90.11 419	89.21 427	92.83 430	93.89 479	86.87 395	91.74 440	88.74 481	92.02 350	94.71 386	91.14 466	73.92 452	94.48 492	83.75 464	92.94 475	97.16 429

tpm cat1		88.01 446	87.33 445	90.05 466	94.48 468	76.28 488	94.47 347	94.35 424	73.84 495	89.26 477	95.61 400	73.64 454	98.30 454	84.13 459	86.20 489	95.57 469

tfpn200view9		91.55 406	91.00 406	93.21 416	98.02 284	84.35 438	95.70 258	90.79 466	96.26 151	95.90 345	92.13 456	73.62 455	99.42 270	78.85 480	97.74 390	95.85 462

thres400		91.68 405	91.00 406	93.71 403	98.02 284	84.35 438	95.70 258	90.79 466	96.26 151	95.90 345	92.13 456	73.62 455	99.42 270	78.85 480	97.74 390	97.36 423

test_method		66.88 462	66.13 465	69.11 480	62.68 505	25.73 508	49.76 496	96.04 389	14.32 500	64.27 500	91.69 461	73.45 457	88.05 497	76.06 485	66.94 497	93.54 483

thres100view900		91.76 404	91.26 404	93.26 412	98.21 260	84.50 434	96.39 191	90.39 470	96.87 119	96.33 317	93.08 439	73.44 458	99.42 270	78.85 480	97.74 390	95.85 462

thres600view7		92.03 399	91.43 397	93.82 399	98.19 263	84.61 433	96.27 203	90.39 470	96.81 122	96.37 316	93.11 435	73.44 458	99.49 236	80.32 475	97.95 380	97.36 423

MVSTER		94.21 340	93.93 347	95.05 346	95.83 432	86.46 399	95.18 308	97.65 334	92.41 345	97.94 202	98.00 228	72.39 460	99.58 203	96.36 136	99.56 147	99.12 215

JIA-IIPM		91.79 403	90.69 414	95.11 342	93.80 480	90.98 273	94.16 360	91.78 455	96.38 145	90.30 467	99.30 32	72.02 461	98.90 395	88.28 418	90.17 483	95.45 470

tpm		91.08 413	90.85 410	91.75 451	95.33 451	78.09 477	95.03 322	91.27 462	88.75 411	93.53 424	97.40 288	71.24 462	99.30 327	91.25 357	93.87 473	97.87 393

baseline2		89.65 430	88.44 436	93.25 413	95.62 443	82.71 450	93.82 377	85.94 491	88.89 410	87.35 486	92.54 450	71.23 463	99.33 314	86.01 441	94.60 470	97.72 406

CostFormer		89.75 427	89.25 425	91.26 457	94.69 466	78.00 479	95.32 295	91.98 453	81.50 474	90.55 463	96.96 330	71.06 464	98.89 396	88.59 414	92.63 477	96.87 438

FPMVS		89.92 425	88.63 433	93.82 399	98.37 240	96.94 48	91.58 443	93.34 436	88.00 423	90.32 466	97.10 318	70.87 465	91.13 496	71.91 492	96.16 447	93.39 486

EPMVS		89.26 432	88.55 434	91.39 455	92.36 490	79.11 474	95.65 265	79.86 497	88.60 414	93.12 434	96.53 357	70.73 466	98.10 462	90.75 373	89.32 485	96.98 433

FE-MVS		92.95 378	92.22 383	95.11 342	97.21 383	88.33 358	98.54 26	93.66 432	89.91 397	96.21 328	98.14 201	70.33 467	99.50 230	87.79 422	98.24 369	97.51 418

tmp_tt		57.23 464	62.50 467	41.44 483	34.77 506	49.21 507	83.93 490	60.22 505	15.31 499	71.11 499	79.37 493	70.09 468	44.86 502	64.76 494	82.93 492	30.25 498

ET-MVSNet_ETH3D		91.12 410	89.67 424	95.47 326	96.41 408	89.15 331	91.54 444	90.23 474	89.07 406	86.78 488	92.84 445	69.39 469	99.44 263	94.16 280	96.61 434	97.82 396

dp		88.08 445	88.05 438	88.16 475	92.85 487	68.81 502	94.17 359	92.88 441	85.47 448	91.38 459	96.14 379	68.87 470	98.81 406	86.88 436	83.80 491	96.87 438

tpm2		88.47 440	87.69 443	90.79 459	94.98 461	77.34 483	95.09 313	91.83 454	77.51 490	89.40 476	96.41 364	67.83 471	98.73 414	83.58 465	92.60 478	96.29 457

pmmvs3		90.00 422	88.90 432	93.32 410	94.20 475	85.34 417	91.25 454	92.56 448	78.59 485	93.82 410	95.17 407	67.36 472	98.69 420	89.08 407	98.03 377	95.92 460

thisisatest0515		90.43 417	89.18 430	94.17 395	97.07 389	85.44 415	89.75 477	87.58 486	88.28 419	93.69 418	91.72 460	65.27 473	99.58 203	90.59 381	98.67 339	97.50 420

tttt0517		93.31 371	92.56 377	95.57 316	98.71 181	87.86 373	97.44 117	87.17 488	95.79 197	97.47 235	96.84 337	64.12 474	99.81 43	96.20 146	99.32 246	99.02 237

thisisatest0530		92.71 383	91.76 392	95.56 321	98.42 236	88.23 360	96.03 229	87.35 487	94.04 286	96.56 305	95.47 403	64.03 475	99.77 69	94.78 255	99.11 280	98.68 305

FMVSNet5		93.39 367	92.35 380	96.50 240	95.83 432	90.81 282	97.31 125	98.27 277	92.74 338	96.27 323	98.28 180	62.23 476	99.67 160	90.86 367	99.36 229	99.03 234

UWE-MVS-28		83.78 457	82.36 460	88.03 476	90.72 494	71.58 499	93.64 384	77.87 498	87.62 426	85.91 489	92.89 443	59.94 477	95.99 487	56.06 498	96.56 436	96.52 452

WBMVS		91.11 411	90.72 413	92.26 445	95.99 424	77.98 480	91.47 445	95.90 394	91.63 358	95.90 345	96.45 362	59.60 478	99.46 252	89.97 394	99.59 136	99.33 156

UBG		88.29 443	87.17 446	91.63 452	96.08 422	78.21 476	91.61 441	91.50 458	89.67 400	89.71 474	88.97 478	59.01 479	98.91 393	81.28 472	96.72 430	97.77 401

IB-MVS	85.98 20	88.63 439	86.95 450	93.68 404	95.12 456	84.82 431	90.85 463	90.17 475	87.55 427	88.48 481	91.34 464	58.01 480	99.59 200	87.24 434	93.80 474	96.63 450
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
MVStest1		91.89 401	91.45 396	93.21 416	89.01 497	84.87 428	95.82 252	95.05 415	91.50 367	98.75 93	99.19 41	57.56 481	95.11 488	97.78 71	98.37 363	99.64 44

testing91		89.67 429	88.55 434	93.04 421	95.90 427	81.80 459	92.71 412	93.71 428	93.71 295	90.18 468	90.15 473	57.11 482	99.22 351	87.17 435	96.32 442	98.12 368

gg-mvs-nofinetune		88.28 444	86.96 449	92.23 446	92.84 488	84.44 436	98.19 56	74.60 500	99.08 16	87.01 487	99.47 16	56.93 483	98.23 457	78.91 479	95.61 460	94.01 482

KD-MVS_2432*1600		88.93 435	87.74 440	92.49 438	88.04 500	81.99 456	89.63 478	95.62 400	91.35 373	95.06 374	93.11 435	56.58 484	98.63 427	85.19 452	95.07 463	96.85 440

miper_refine_blended		88.93 435	87.74 440	92.49 438	88.04 500	81.99 456	89.63 478	95.62 400	91.35 373	95.06 374	93.11 435	56.58 484	98.63 427	85.19 452	95.07 463	96.85 440

GG-mvs-BLEND				90.60 460	91.00 492	84.21 441	98.23 50	72.63 503		82.76 491	84.11 492	56.14 486	96.79 480	72.20 491	92.09 480	90.78 492

myMVS_eth3d28		88.32 442	87.73 442	90.11 465	96.42 407	74.96 494	92.21 428	92.37 449	93.56 301	90.14 469	89.61 476	56.13 487	98.05 464	81.84 468	97.26 415	97.33 426

TESTMET0.1,1		87.20 453	86.57 452	89.07 469	93.62 482	72.84 497	89.89 473	87.01 489	85.46 449	89.12 478	90.20 472	56.00 488	97.72 469	90.91 365	96.92 418	96.64 448

testing3-2		90.09 420	90.38 419	89.24 468	98.07 280	69.88 501	95.12 309	90.71 469	96.65 127	93.60 422	94.03 428	55.81 489	99.33 314	90.69 379	98.71 335	98.51 325

reproduce_monomvs		92.05 398	92.26 382	91.43 454	95.42 449	75.72 490	95.68 261	97.05 364	94.47 268	97.95 201	98.35 161	55.58 490	99.05 377	96.36 136	99.44 200	99.51 85

testing99		89.21 433	88.04 439	92.70 434	95.78 436	81.00 466	92.65 413	92.03 451	93.20 318	89.90 473	90.08 475	55.25 491	99.14 361	87.54 428	95.95 448	97.97 385

UWE-MVS		87.57 450	86.72 451	90.13 464	95.21 453	73.56 495	91.94 435	83.78 495	88.73 413	93.00 436	92.87 444	55.22 492	99.25 343	81.74 469	97.96 379	97.59 415

test2506		89.86 426	89.16 431	91.97 449	98.95 133	76.83 486	98.54 26	61.07 504	96.20 157	97.07 264	99.16 49	55.19 493	99.69 143	96.43 133	99.83 54	99.38 143

testing11		88.93 435	87.63 444	92.80 431	95.87 429	81.49 461	92.48 417	91.54 457	91.62 359	88.27 482	90.24 471	55.12 494	99.11 368	87.30 433	96.28 444	97.81 398

test-mter		87.92 447	87.17 446	90.16 462	94.24 473	74.98 491	89.89 473	89.06 478	86.44 439	89.97 471	90.77 469	54.96 495	98.57 432	91.88 342	97.36 410	96.92 435

0.4-1-1-0.2		82.53 460	79.25 462	92.37 442	88.10 499	83.96 444	83.72 491	88.15 483	82.14 470	78.97 497	72.49 497	53.22 496	98.84 402	85.99 442	80.50 494	94.30 480

0.4-1-1-0.1		83.64 458	80.50 461	93.08 419	90.32 496	85.42 416	86.48 484	87.71 485	83.60 464	80.38 496	75.45 495	53.19 497	98.91 393	86.46 439	80.88 493	94.93 475

blend_shiyan4		88.73 438	86.43 453	95.61 313	95.31 452	89.17 327	92.13 430	97.10 359	91.59 364	94.15 401	87.38 485	52.97 498	99.40 282	91.84 344	75.42 496	98.27 354

ETVMVS		87.62 449	85.75 456	93.22 415	96.15 420	83.26 447	92.94 404	90.37 472	91.39 372	90.37 465	88.45 481	51.93 499	98.64 426	73.76 487	96.38 440	97.75 402

0.3-1-1-0.015		82.33 461	78.89 463	92.66 435	88.57 498	84.69 432	84.76 489	88.02 484	82.48 469	77.55 498	72.96 496	49.60 500	98.87 400	86.05 440	80.02 495	94.43 477

testing222		87.35 451	85.50 458	92.93 428	95.79 435	82.83 449	92.40 423	90.10 476	92.80 337	88.87 479	89.02 477	48.34 501	98.70 418	75.40 486	96.74 428	97.27 428

myMVS_eth3d		87.16 454	85.61 457	91.82 450	95.19 454	79.32 472	92.46 418	91.35 459	90.67 386	91.76 456	87.61 483	41.96 502	98.50 439	82.66 466	96.84 422	97.65 409

testing3		89.72 428	88.26 437	94.10 396	97.66 344	84.30 440	94.80 334	88.25 482	94.66 254	95.07 373	92.51 451	41.15 503	99.43 266	91.81 347	98.44 360	98.55 318

dongtai		63.43 463	63.37 466	63.60 481	83.91 503	53.17 505	85.14 487	43.40 507	77.91 489	80.96 494	79.17 494	36.36 504	77.10 499	37.88 499	45.63 499	60.54 496

kuosan		54.81 465	54.94 468	54.42 482	74.43 504	50.03 506	84.98 488	44.27 506	61.80 497	62.49 501	70.43 498	35.16 505	58.04 501	19.30 500	41.61 500	55.19 497

test123		12.59 467	15.49 470	3.87 484	6.07 507	2.55 509	90.75 465	2.59 509	2.52 502	5.20 504	13.02 501	4.96 506	1.85 504	5.20 501	9.09 501	7.23 499

testmvs		12.33 468	15.23 471	3.64 485	5.77 508	2.23 510	88.99 480	3.62 508	2.30 503	5.29 503	13.09 500	4.52 507	1.95 503	5.16 502	8.32 502	6.75 500

mmdepth		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

monomultidepth		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

test_blank		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uanet_test		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

DCPMVS		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

sosnet-low-res		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

sosnet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uncertanet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

Regformer		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

ab-mvs-re		7.91 470	10.55 473	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	94.94 412	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uanet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

MED-MVS test				98.17 88	99.36 54	95.35 117	97.75 87	99.30 41	94.02 287	98.88 76	97.54 276		99.73 101	95.36 207	99.53 164	99.44 122

WAC-MVS						79.32 472								85.41 450

FOURS1					99.59 18	98.20 7	99.03 8	99.25 49	98.96 24	98.87 78

MSC_two_6792asdad				98.22 84	97.75 331	95.34 122		98.16 296					99.75 85	95.87 167	99.51 177	99.57 59

No_MVS				98.22 84	97.75 331	95.34 122		98.16 296					99.75 85	95.87 167	99.51 177	99.57 59

eth-test2					0.00 509

eth-test					0.00 509

IU-MVS					99.22 78	95.40 112		98.14 299	85.77 446	98.36 138				95.23 217	99.51 177	99.49 96

save fliter					98.48 227	94.71 143	94.53 346	98.41 260	95.02 238

test_0728_SECOND				98.25 82	99.23 75	95.49 109	96.74 166	98.89 156					99.75 85	95.48 194	99.52 172	99.53 78

GSMVS																98.06 376

test_part2					99.03 121	96.07 80				98.08 180

MTGPA								98.73 210

MTMP							96.55 178	74.60 500

gm-plane-assit					91.79 491	71.40 500			81.67 472		90.11 474		98.99 385	84.86 456

test9_res														91.29 354	98.89 311	99.00 238

agg_prior2														90.34 389	98.90 307	99.10 224

agg_prior					97.80 319	94.96 138		98.36 268		93.49 425			99.53 222

test_prior4						95.38 114	93.61 387

test_prior				97.46 153	97.79 324	94.26 168		98.42 259					99.34 312			98.79 280

旧先验2							93.35 395		77.95 488	95.77 354			98.67 424	90.74 376

新几何2							93.43 391

无先验							93.20 400	97.91 315	80.78 477				99.40 282	87.71 423		97.94 388

原ACMM2							92.82 406

testdata2													99.46 252	87.84 421

testdata1							92.77 407		93.78 293

plane_prior7					98.70 183	94.67 146

plane_prior5								98.75 207					99.46 252	92.59 331	99.20 264	99.28 171

plane_prior4											96.77 343

plane_prior3						94.51 154			95.29 225	96.16 332

plane_prior2							96.50 181		96.36 147

plane_prior1					98.49 225

plane_prior						94.29 164	95.42 281		94.31 275						98.93 304

n2								0.00 510

nn								0.00 510

door-mid								98.17 292

test11								98.08 304

door								97.81 324

HQP5-MVS						92.47 227

HQP-NCC					97.85 301		94.26 351		93.18 320	92.86 439

ACMP_Plane					97.85 301		94.26 351		93.18 320	92.86 439

BP-MVS														90.51 384

HQP4-MVS										92.87 438			99.23 349			99.06 230

HQP3-MVS								98.43 256							98.74 331

NP-MVS					98.14 275	93.72 186					95.08 408

ACMMP++_ref															99.52 172

ACMMP++															99.55 154

High-resolution multi-view benchmark