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

PS-MVSNAJss		98.53 22	98.63 20	98.21 78	99.68 11	94.82 129	98.10 56	99.21 33	96.91 93	99.75 2	99.45 13	95.82 125	99.92 5	98.80 19	99.96 4	99.89 1

UniMVSNet_ETH3D		99.12 3	99.28 3	98.65 42	99.77 5	96.34 65	99.18 5	99.20 35	99.67 2	99.73 3	99.65 5	99.15 3	99.86 24	97.22 67	99.92 16	99.77 12

test_fmvsmvis_n_1920		98.08 45	98.47 26	96.93 177	99.03 107	93.29 187	96.32 164	99.65 9	95.59 158	99.71 4	99.01 54	97.66 32	99.60 158	99.44 2	99.83 43	97.90 306

mvs_tets		98.90 5	98.94 6	98.75 31	99.69 10	96.48 60	98.54 23	99.22 32	96.23 121	99.71 4	99.48 10	98.77 7	99.93 3	98.89 17	99.95 5	99.84 5

wuyk23d		93.25 298	95.20 214	87.40 385	96.07 348	95.38 105	97.04 122	94.97 334	95.33 169	99.70 6	98.11 157	98.14 17	91.94 403	77.76 394	99.68 82	74.89 403

Anonymous20231211		98.55 20	98.76 13	97.94 99	98.79 131	94.37 148	98.84 11	99.15 44	99.37 3	99.67 7	99.43 15	95.61 136	99.72 87	98.12 34	99.86 31	99.73 22

jajsoiax		98.77 9	98.79 12	98.74 34	99.66 13	96.48 60	98.45 31	99.12 49	95.83 147	99.67 7	99.37 19	98.25 13	99.92 5	98.77 20	99.94 8	99.82 6

ANet_high		98.31 31	98.94 6	96.41 212	99.33 53	89.64 262	97.92 66	99.56 16	99.27 6	99.66 9	99.50 9	97.67 31	99.83 32	97.55 58	99.98 2	99.77 12

test_fmvsmconf0.01_n		98.57 17	98.74 16	98.06 88	99.39 46	94.63 136	96.70 144	99.82 1	95.44 166	99.64 10	99.52 7	98.96 4	99.74 76	99.38 3	99.86 31	99.81 8

pmmvs6		99.07 4	99.24 4	98.56 48	99.81 2	96.38 62	98.87 9	99.30 27	99.01 16	99.63 11	99.66 3	99.27 2	99.68 122	97.75 50	99.89 26	99.62 36

LTVRE_ROB	96.88 1	99.18 2	99.34 2	98.72 37	99.71 9	96.99 44	99.69 2	99.57 14	99.02 15	99.62 12	99.36 21	98.53 9	99.52 181	98.58 29	99.95 5	99.66 30
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
OurMVSNet-221017-0		98.61 16	98.61 24	98.63 44	99.77 5	96.35 64	99.17 6	99.05 66	98.05 47	99.61 13	99.52 7	93.72 190	99.88 20	98.72 24	99.88 27	99.65 33

test_fmvsmconf0.1_n		98.41 27	98.54 25	98.03 93	99.16 82	94.61 137	96.18 174	99.73 3	95.05 182	99.60 14	99.34 25	98.68 8	99.72 87	99.21 7	99.85 38	99.76 17

test_fmvsm_n_1920		98.08 45	98.29 38	97.43 140	98.88 122	93.95 164	96.17 178	99.57 14	95.66 153	99.52 15	98.71 84	97.04 61	99.64 140	99.21 7	99.87 29	98.69 228

TransMVSNet (Re)		98.38 28	98.67 18	97.51 127	99.51 30	93.39 185	98.20 51	98.87 112	98.23 40	99.48 16	99.27 30	98.47 11	99.55 173	96.52 89	99.53 125	99.60 37

LCM-MVSNet-Re		97.33 121	97.33 116	97.32 148	98.13 218	93.79 170	96.99 124	99.65 9	96.74 98	99.47 17	98.93 64	96.91 73	99.84 30	90.11 307	99.06 231	98.32 265

SixPastTwentyTwo		97.49 108	97.57 100	97.26 154	99.56 21	92.33 209	98.28 42	96.97 293	98.30 38	99.45 18	99.35 23	88.43 285	99.89 18	98.01 39	99.76 58	99.54 53

test_fmvsmconf_n		98.30 32	98.41 32	97.99 96	98.94 115	94.60 138	96.00 189	99.64 12	94.99 185	99.43 19	99.18 39	98.51 10	99.71 102	99.13 10	99.84 40	99.67 28

v7n		98.73 11	98.99 5	97.95 98	99.64 14	94.20 156	98.67 15	99.14 47	99.08 10	99.42 20	99.23 33	96.53 94	99.91 13	99.27 5	99.93 11	99.73 22

NR-MVSNet		97.96 54	97.86 65	98.26 70	98.73 137	95.54 95	98.14 54	98.73 150	97.79 53	99.42 20	97.83 188	94.40 173	99.78 47	95.91 119	99.76 58	99.46 81

MIMVSNet1		98.51 23	98.45 29	98.67 40	99.72 8	96.71 50	98.76 12	98.89 104	98.49 31	99.38 22	99.14 46	95.44 142	99.84 30	96.47 91	99.80 51	99.47 79

ACMH	93.61 9	98.44 25	98.76 13	97.51 127	99.43 39	93.54 179	98.23 46	99.05 66	97.40 80	99.37 23	99.08 51	98.79 6	99.47 196	97.74 51	99.71 74	99.50 62
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mvsany_test3		96.21 180	95.93 195	97.05 169	97.40 297	94.33 150	95.76 206	94.20 342	89.10 317	99.36 24	99.60 6	93.97 183	97.85 378	95.40 155	98.63 274	98.99 183

anonymousdsp		98.72 14	98.63 20	98.99 10	99.62 16	97.29 37	98.65 19	99.19 37	95.62 156	99.35 25	99.37 19	97.38 42	99.90 14	98.59 28	99.91 19	99.77 12

test_djsdf		98.73 11	98.74 16	98.69 39	99.63 15	96.30 67	98.67 15	99.02 76	96.50 109	99.32 26	99.44 14	97.43 40	99.92 5	98.73 22	99.95 5	99.86 2

PEN-MVS		98.75 10	98.85 10	98.44 55	99.58 19	95.67 90	98.45 31	99.15 44	99.33 5	99.30 27	99.00 55	97.27 47	99.92 5	97.64 56	99.92 16	99.75 19

DTE-MVSNet		98.79 8	98.86 8	98.59 46	99.55 23	96.12 72	98.48 30	99.10 52	99.36 4	99.29 28	99.06 52	97.27 47	99.93 3	97.71 52	99.91 19	99.70 26

test_vis3_rt		97.04 131	96.98 136	97.23 157	98.44 180	95.88 80	96.82 132	99.67 6	90.30 302	99.27 29	99.33 27	94.04 180	96.03 396	97.14 72	97.83 311	99.78 11

pm-mvs1		98.47 24	98.67 18	97.86 103	99.52 29	94.58 139	98.28 42	99.00 85	97.57 67	99.27 29	99.22 34	98.32 12	99.50 186	97.09 74	99.75 65	99.50 62

ACMH+	93.58 10	98.23 36	98.31 35	97.98 97	99.39 46	95.22 118	97.55 92	99.20 35	98.21 41	99.25 31	98.51 104	98.21 14	99.40 221	94.79 187	99.72 71	99.32 115

Anonymous20240529		97.96 54	98.04 49	97.71 112	98.69 146	94.28 154	97.86 69	98.31 211	98.79 22	99.23 32	98.86 73	95.76 131	99.61 156	95.49 141	99.36 177	99.23 138

PS-CasMVS		98.73 11	98.85 10	98.39 61	99.55 23	95.47 102	98.49 28	99.13 48	99.22 8	99.22 33	98.96 61	97.35 43	99.92 5	97.79 48	99.93 11	99.79 10

SD-MVS		97.37 118	97.70 81	96.35 213	98.14 215	95.13 122	96.54 151	98.92 101	95.94 139	99.19 34	98.08 159	97.74 28	95.06 397	95.24 160	99.54 121	98.87 207
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
WR-MVS_H		98.65 15	98.62 22	98.75 31	99.51 30	96.61 56	98.55 22	99.17 39	99.05 13	99.17 35	98.79 75	95.47 140	99.89 18	97.95 41	99.91 19	99.75 19

RRT_MVS		97.95 58	97.79 73	98.43 57	99.67 12	95.56 93	98.86 10	96.73 304	97.99 49	99.15 36	99.35 23	89.84 268	99.90 14	98.64 26	99.90 24	99.82 6

dcpmvs_2		97.12 128	97.99 54	94.51 303	99.11 94	84.00 359	97.75 77	99.65 9	97.38 81	99.14 37	98.42 113	95.16 149	99.96 2	95.52 140	99.78 56	99.58 39

tfpnnormal		97.72 90	97.97 55	96.94 176	99.26 59	92.23 213	97.83 72	98.45 189	98.25 39	99.13 38	98.66 88	96.65 87	99.69 117	93.92 224	99.62 92	98.91 197

SSC-MVS		95.92 192	97.03 134	92.58 353	99.28 57	78.39 389	96.68 145	95.12 332	98.90 19	99.11 39	98.66 88	91.36 243	99.68 122	95.00 178	99.16 214	99.67 28

SED-MVS		97.94 62	97.90 59	98.07 86	99.22 68	95.35 108	96.79 135	98.83 128	96.11 127	99.08 40	98.24 140	97.87 23	99.72 87	95.44 148	99.51 135	99.14 154

test_241102_ONE					99.22 68	95.35 108		98.83 128	96.04 132	99.08 40	98.13 153	97.87 23	99.33 245

VPA-MVSNet		98.27 33	98.46 27	97.70 113	99.06 101	93.80 169	97.76 76	99.00 85	98.40 33	99.07 42	98.98 58	96.89 74	99.75 67	97.19 71	99.79 53	99.55 52

nrg030		98.54 21	98.62 22	98.32 65	99.22 68	95.66 91	97.90 67	99.08 58	98.31 36	99.02 43	98.74 81	97.68 30	99.61 156	97.77 49	99.85 38	99.70 26

fmvsm_s_conf0.1_n		97.73 88	98.02 51	96.85 183	99.09 97	91.43 237	96.37 160	99.11 50	94.19 210	99.01 44	99.25 31	96.30 109	99.38 228	99.00 14	99.88 27	99.73 22

CP-MVSNet		98.42 26	98.46 27	98.30 68	99.46 36	95.22 118	98.27 44	98.84 122	99.05 13	99.01 44	98.65 91	95.37 143	99.90 14	97.57 57	99.91 19	99.77 12

fmvsm_l_conf0.5_n		97.68 94	97.81 71	97.27 152	98.92 118	92.71 202	95.89 200	99.41 24	93.36 235	99.00 46	98.44 112	96.46 101	99.65 136	99.09 11	99.76 58	99.45 85

casdiffmvs_mvg		97.83 78	98.11 42	97.00 174	98.57 161	92.10 222	95.97 192	99.18 38	97.67 66	99.00 46	98.48 109	97.64 33	99.50 186	96.96 79	99.54 121	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
FMVSNet1		97.95 58	98.08 44	97.56 122	99.14 92	93.67 173	98.23 46	98.66 167	97.41 79	99.00 46	99.19 36	95.47 140	99.73 82	95.83 124	99.76 58	99.30 120

TDRefinement		98.90 5	98.86 8	99.02 6	99.54 26	98.06 8	99.34 4	99.44 20	98.85 21	99.00 46	99.20 35	97.42 41	99.59 159	97.21 68	99.76 58	99.40 100

K. test v3		96.44 172	96.28 178	96.95 175	99.41 42	91.53 233	97.65 84	90.31 384	98.89 20	98.93 50	99.36 21	84.57 319	99.92 5	97.81 46	99.56 111	99.39 104

testf1		98.57 17	98.45 29	98.93 18	99.79 3	98.78 2	97.69 81	99.42 22	97.69 63	98.92 51	98.77 78	97.80 25	99.25 265	96.27 99	99.69 78	98.76 219

APD_test2		98.57 17	98.45 29	98.93 18	99.79 3	98.78 2	97.69 81	99.42 22	97.69 63	98.92 51	98.77 78	97.80 25	99.25 265	96.27 99	99.69 78	98.76 219

fmvsm_l_conf0.5_n_a		97.60 100	97.76 78	97.11 163	98.92 118	92.28 211	95.83 203	99.32 25	93.22 241	98.91 53	98.49 105	96.31 108	99.64 140	99.07 12	99.76 58	99.40 100

fmvsm_s_conf0.1_n_a		97.80 83	98.01 52	97.18 158	99.17 81	92.51 205	96.57 149	99.15 44	93.68 227	98.89 54	99.30 28	96.42 103	99.37 234	99.03 13	99.83 43	99.66 30

FC-MVSNet-test		98.16 37	98.37 33	97.56 122	99.49 34	93.10 192	98.35 35	99.21 33	98.43 32	98.89 54	98.83 74	94.30 175	99.81 36	97.87 43	99.91 19	99.77 12

FOURS1					99.59 18	98.20 7	99.03 7	99.25 31	98.96 18	98.87 56

KD-MVS_self_test		97.86 76	98.07 45	97.25 155	99.22 68	92.81 197	97.55 92	98.94 98	97.10 89	98.85 57	98.88 71	95.03 153	99.67 128	97.39 64	99.65 87	99.26 132

mvsmamba		98.16 37	98.06 47	98.44 55	99.53 28	95.87 81	98.70 13	98.94 98	97.71 61	98.85 57	99.10 48	91.35 244	99.83 32	98.47 30	99.90 24	99.64 35

WB-MVS		95.50 208	96.62 156	92.11 362	99.21 75	77.26 397	96.12 180	95.40 329	98.62 26	98.84 59	98.26 138	91.08 247	99.50 186	93.37 237	98.70 267	99.58 39

TranMVSNet+NR-MVSNet		98.33 29	98.30 37	98.43 57	99.07 100	95.87 81	96.73 142	99.05 66	98.67 24	98.84 59	98.45 110	97.58 37	99.88 20	96.45 92	99.86 31	99.54 53

fmvsm_s_conf0.5_n		97.62 98	97.89 62	96.80 187	98.79 131	91.44 236	96.14 179	99.06 62	94.19 210	98.82 61	98.98 58	96.22 114	99.38 228	98.98 16	99.86 31	99.58 39

new-patchmatchnet		95.67 202	96.58 160	92.94 344	97.48 289	80.21 384	92.96 326	98.19 227	94.83 189	98.82 61	98.79 75	93.31 197	99.51 185	95.83 124	99.04 232	99.12 161

EG-PatchMatch MVS		97.69 92	97.79 73	97.40 144	99.06 101	93.52 180	95.96 194	98.97 94	94.55 201	98.82 61	98.76 80	97.31 45	99.29 257	97.20 70	99.44 155	99.38 106

SDMVSNet		97.97 52	98.26 39	97.11 163	99.41 42	92.21 214	96.92 127	98.60 175	98.58 28	98.78 64	99.39 16	97.80 25	99.62 149	94.98 181	99.86 31	99.52 58

sd_testset		97.97 52	98.12 41	97.51 127	99.41 42	93.44 182	97.96 62	98.25 214	98.58 28	98.78 64	99.39 16	98.21 14	99.56 168	92.65 251	99.86 31	99.52 58

DPE-MVS		97.64 96	97.35 115	98.50 51	98.85 125	96.18 69	95.21 244	98.99 88	95.84 146	98.78 64	98.08 159	96.84 80	99.81 36	93.98 222	99.57 108	99.52 58
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
COLMAP_ROB	94.48 6	98.25 35	98.11 42	98.64 43	99.21 75	97.35 35	97.96 62	99.16 40	98.34 35	98.78 64	98.52 102	97.32 44	99.45 203	94.08 216	99.67 84	99.13 156
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
lessismore_v0				97.05 169	99.36 50	92.12 219		84.07 402		98.77 68	98.98 58	85.36 313	99.74 76	97.34 65	99.37 174	99.30 120

test_fmvs3		97.38 116	97.56 101	96.84 185	98.63 153	92.81 197	97.60 87	99.61 13	90.87 293	98.76 69	99.66 3	94.03 181	97.90 377	99.24 6	99.68 82	99.81 8

v8		97.60 100	98.06 47	96.23 218	98.71 142	89.44 266	97.43 102	98.82 136	97.29 85	98.74 70	99.10 48	93.86 185	99.68 122	98.61 27	99.94 8	99.56 50

DP-MVS		97.87 74	97.89 62	97.81 106	98.62 155	94.82 129	97.13 117	98.79 138	98.98 17	98.74 70	98.49 105	95.80 130	99.49 191	95.04 175	99.44 155	99.11 164

bld_raw_dy_0_64		95.16 228	95.16 217	95.15 269	96.54 327	89.06 275	96.63 148	99.54 17	89.68 312	98.72 72	94.50 344	88.64 282	99.38 228	92.24 257	99.93 11	97.03 344

v10		97.55 104	97.97 55	96.31 216	98.60 157	89.64 262	97.44 100	99.02 76	96.60 102	98.72 72	99.16 43	93.48 194	99.72 87	98.76 21	99.92 16	99.58 39

fmvsm_s_conf0.5_n_a		97.65 95	97.83 69	97.13 162	98.80 129	92.51 205	96.25 170	99.06 62	93.67 228	98.64 74	99.00 55	96.23 113	99.36 237	98.99 15	99.80 51	99.53 56

test0726					99.24 63	95.51 97	96.89 129	98.89 104	95.92 140	98.64 74	98.31 124	97.06 59

DVP-MVS++		97.96 54	97.90 59	98.12 84	97.75 263	95.40 103	99.03 7	98.89 104	96.62 100	98.62 76	98.30 128	96.97 66	99.75 67	95.70 127	99.25 203	99.21 140

test_241102_TWO								98.83 128	96.11 127	98.62 76	98.24 140	96.92 72	99.72 87	95.44 148	99.49 142	99.49 70

FIs		97.93 65	98.07 45	97.48 135	99.38 48	92.95 195	98.03 61	99.11 50	98.04 48	98.62 76	98.66 88	93.75 189	99.78 47	97.23 66	99.84 40	99.73 22

DeepC-MVS	95.41 4	97.82 81	97.70 81	98.16 79	98.78 134	95.72 86	96.23 172	99.02 76	93.92 220	98.62 76	98.99 57	97.69 29	99.62 149	96.18 104	99.87 29	99.15 151
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
APDe-MVS		98.14 39	98.03 50	98.47 54	98.72 139	96.04 75	98.07 58	99.10 52	95.96 137	98.59 80	98.69 86	96.94 68	99.81 36	96.64 84	99.58 105	99.57 46
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
XXY-MVS		97.54 105	97.70 81	97.07 168	99.46 36	92.21 214	97.22 111	99.00 85	94.93 188	98.58 81	98.92 65	97.31 45	99.41 219	94.44 200	99.43 163	99.59 38

test_0402		97.84 77	97.97 55	97.47 136	99.19 79	94.07 159	96.71 143	98.73 150	98.66 25	98.56 82	98.41 114	96.84 80	99.69 117	94.82 185	99.81 48	98.64 232

PM-MVS		97.36 120	97.10 128	98.14 82	98.91 120	96.77 49	96.20 173	98.63 173	93.82 221	98.54 83	98.33 122	93.98 182	99.05 298	95.99 114	99.45 154	98.61 237

DeepPCF-MVS	94.58 5	96.90 142	96.43 171	98.31 67	97.48 289	97.23 40	92.56 338	98.60 175	92.84 260	98.54 83	97.40 222	96.64 89	98.78 323	94.40 204	99.41 170	98.93 193

MSP-MVS		97.45 111	96.92 142	99.03 5	99.26 59	97.70 18	97.66 83	98.89 104	95.65 154	98.51 85	96.46 286	92.15 228	99.81 36	95.14 169	98.58 279	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
VDD-MVS		97.37 118	97.25 120	97.74 110	98.69 146	94.50 143	97.04 122	95.61 323	98.59 27	98.51 85	98.72 82	92.54 220	99.58 161	96.02 111	99.49 142	99.12 161

FMVSNet2		96.72 156	96.67 155	96.87 182	97.96 230	91.88 227	97.15 114	98.06 245	95.59 158	98.50 87	98.62 94	89.51 274	99.65 136	94.99 180	99.60 101	99.07 171

test_fmvs2		96.38 175	96.45 170	96.16 223	97.85 238	91.30 238	96.81 133	99.45 19	89.24 316	98.49 88	99.38 18	88.68 281	97.62 382	98.83 18	99.32 192	99.57 46

test1111		94.53 258	94.81 236	93.72 322	99.06 101	81.94 374	98.31 39	83.87 403	96.37 114	98.49 88	99.17 42	81.49 334	99.73 82	96.64 84	99.86 31	99.49 70

SMA-MVS		97.48 109	97.11 127	98.60 45	98.83 126	96.67 53	96.74 138	98.73 150	91.61 282	98.48 90	98.36 119	96.53 94	99.68 122	95.17 164	99.54 121	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
EU-MVSNet		94.25 265	94.47 255	93.60 325	98.14 215	82.60 369	97.24 110	92.72 359	85.08 363	98.48 90	98.94 63	82.59 332	98.76 326	97.47 62	99.53 125	99.44 95

RPSCF		97.87 74	97.51 106	98.95 14	99.15 85	98.43 6	97.56 91	99.06 62	96.19 124	98.48 90	98.70 85	94.72 160	99.24 269	94.37 205	99.33 190	99.17 148

v1240		96.74 153	97.02 135	95.91 235	98.18 206	88.52 284	95.39 230	98.88 110	93.15 249	98.46 93	98.40 117	92.80 208	99.71 102	98.45 31	99.49 142	99.49 70

VPNet		97.26 124	97.49 109	96.59 199	99.47 35	90.58 251	96.27 166	98.53 182	97.77 54	98.46 93	98.41 114	94.59 166	99.68 122	94.61 195	99.29 198	99.52 58

IterMVS-LS		96.92 140	97.29 118	95.79 239	98.51 170	88.13 295	95.10 247	98.66 167	96.99 90	98.46 93	98.68 87	92.55 218	99.74 76	96.91 80	99.79 53	99.50 62
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test_f		95.82 197	95.88 198	95.66 245	97.61 280	93.21 191	95.61 218	98.17 228	86.98 344	98.42 96	99.47 11	90.46 256	94.74 399	97.71 52	98.45 286	99.03 176

ambc				96.56 203	98.23 199	91.68 232	97.88 68	98.13 236		98.42 96	98.56 99	94.22 177	99.04 299	94.05 219	99.35 182	98.95 187

DVP-MVS		97.78 85	97.65 88	98.16 79	99.24 63	95.51 97	96.74 138	98.23 217	95.92 140	98.40 98	98.28 133	97.06 59	99.71 102	95.48 144	99.52 130	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
test_0728_THIRD									96.62 100	98.40 98	98.28 133	97.10 55	99.71 102	95.70 127	99.62 92	99.58 39

VDDNet		96.98 137	96.84 145	97.41 143	99.40 45	93.26 189	97.94 64	95.31 330	99.26 7	98.39 100	99.18 39	87.85 294	99.62 149	95.13 171	99.09 225	99.35 114

PC_three_1452									87.24 340	98.37 101	97.44 219	97.00 64	96.78 393	92.01 261	99.25 203	99.21 140

Anonymous202405211		96.34 176	95.98 191	97.43 140	98.25 196	93.85 167	96.74 138	94.41 340	97.72 59	98.37 101	98.03 169	87.15 300	99.53 178	94.06 217	99.07 228	98.92 196

Baseline_NR-MVSNet		97.72 90	97.79 73	97.50 131	99.56 21	93.29 187	95.44 224	98.86 115	98.20 42	98.37 101	99.24 32	94.69 161	99.55 173	95.98 115	99.79 53	99.65 33

IU-MVS					99.22 68	95.40 103		98.14 235	85.77 357	98.36 104				95.23 161	99.51 135	99.49 70

IterMVS-SCA-FT		95.86 195	96.19 181	94.85 286	97.68 271	85.53 337	92.42 344	97.63 272	96.99 90	98.36 104	98.54 101	87.94 289	99.75 67	97.07 76	99.08 226	99.27 131

ACMM	93.33 11	98.05 48	97.79 73	98.85 24	99.15 85	97.55 26	96.68 145	98.83 128	95.21 173	98.36 104	98.13 153	98.13 18	99.62 149	96.04 109	99.54 121	99.39 104
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240521		97.07 130	97.51 106	95.76 240	99.35 51	88.18 292	97.78 73	98.40 198	97.11 88	98.34 107	99.04 53	89.58 270	99.79 44	98.09 36	99.93 11	99.30 120

LPG-MVS_test		97.94 62	97.67 86	98.74 34	99.15 85	97.02 42	97.09 119	99.02 76	95.15 177	98.34 107	98.23 142	97.91 21	99.70 110	94.41 202	99.73 67	99.50 62

LGP-MVS_train				98.74 34	99.15 85	97.02 42		99.02 76	95.15 177	98.34 107	98.23 142	97.91 21	99.70 110	94.41 202	99.73 67	99.50 62

casdiffmvs		97.50 107	97.81 71	96.56 203	98.51 170	91.04 242	95.83 203	99.09 57	97.23 86	98.33 110	98.30 128	97.03 62	99.37 234	96.58 88	99.38 173	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
Patchmatch-RL test		94.66 251	94.49 253	95.19 266	98.54 166	88.91 277	92.57 337	98.74 149	91.46 285	98.32 111	97.75 197	77.31 357	98.81 321	96.06 106	99.61 98	97.85 310

XVG-OURS		97.12 128	96.74 151	98.26 70	98.99 110	97.45 32	93.82 304	99.05 66	95.19 175	98.32 111	97.70 202	95.22 148	98.41 359	94.27 209	98.13 299	98.93 193

UniMVSNet_NR-MVSNet		97.83 78	97.65 88	98.37 62	98.72 139	95.78 84	95.66 212	99.02 76	98.11 44	98.31 113	97.69 203	94.65 165	99.85 27	97.02 77	99.71 74	99.48 76

DU-MVS		97.79 84	97.60 97	98.36 63	98.73 137	95.78 84	95.65 214	98.87 112	97.57 67	98.31 113	97.83 188	94.69 161	99.85 27	97.02 77	99.71 74	99.46 81

EI-MVSNet-UG-set		97.32 122	97.40 111	97.09 167	97.34 302	92.01 225	95.33 236	97.65 268	97.74 57	98.30 115	98.14 151	95.04 152	99.69 117	97.55 58	99.52 130	99.58 39

EI-MVSNet-Vis-set		97.32 122	97.39 112	97.11 163	97.36 299	92.08 223	95.34 235	97.65 268	97.74 57	98.29 116	98.11 157	95.05 151	99.68 122	97.50 60	99.50 139	99.56 50

test20.03		96.58 166	96.61 158	96.48 207	98.49 174	91.72 231	95.68 211	97.69 263	96.81 96	98.27 117	97.92 182	94.18 178	98.71 331	90.78 290	99.66 86	99.00 180

APD-MVS_3200maxsize		98.13 42	97.90 59	98.79 29	98.79 131	97.31 36	97.55 92	98.92 101	97.72 59	98.25 118	98.13 153	97.10 55	99.75 67	95.44 148	99.24 206	99.32 115

v148		96.58 166	96.97 137	95.42 258	98.63 153	87.57 308	95.09 248	97.90 250	95.91 142	98.24 119	97.96 176	93.42 195	99.39 225	96.04 109	99.52 130	99.29 126

ECVR-MVS		94.37 264	94.48 254	94.05 318	98.95 112	83.10 364	98.31 39	82.48 405	96.20 122	98.23 120	99.16 43	81.18 337	99.66 134	95.95 116	99.83 43	99.38 106

UniMVSNet (Re)		97.83 78	97.65 88	98.35 64	98.80 129	95.86 83	95.92 198	99.04 73	97.51 72	98.22 121	97.81 192	94.68 163	99.78 47	97.14 72	99.75 65	99.41 99

test_vis1_n		95.67 202	95.89 197	95.03 275	98.18 206	89.89 259	96.94 126	99.28 29	88.25 332	98.20 122	98.92 65	86.69 304	97.19 385	97.70 54	98.82 255	98.00 300

SR-MVS-dyc-post		98.14 39	97.84 66	99.02 6	98.81 127	98.05 9	97.55 92	98.86 115	97.77 54	98.20 122	98.07 161	96.60 92	99.76 61	95.49 141	99.20 208	99.26 132

RE-MVS-def			97.88 64		98.81 127	98.05 9	97.55 92	98.86 115	97.77 54	98.20 122	98.07 161	96.94 68		95.49 141	99.20 208	99.26 132

WR-MVS		96.90 142	96.81 147	97.16 159	98.56 163	92.20 217	94.33 277	98.12 237	97.34 82	98.20 122	97.33 233	92.81 207	99.75 67	94.79 187	99.81 48	99.54 53

v1921920		96.72 156	96.96 139	95.99 228	98.21 200	88.79 281	95.42 226	98.79 138	93.22 241	98.19 126	98.26 138	92.68 212	99.70 110	98.34 33	99.55 118	99.49 70

test_cas_vis1_n_1920		95.34 217	95.67 204	94.35 309	98.21 200	86.83 324	95.61 218	99.26 30	90.45 300	98.17 127	98.96 61	84.43 320	98.31 367	96.74 83	99.17 213	97.90 306

TSAR-MVS + MP.		97.42 114	97.23 122	98.00 95	99.38 48	95.00 125	97.63 86	98.20 222	93.00 253	98.16 128	98.06 166	95.89 120	99.72 87	95.67 131	99.10 224	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
TinyColmap		96.00 190	96.34 176	94.96 280	97.90 236	87.91 300	94.13 291	98.49 186	94.41 203	98.16 128	97.76 194	96.29 111	98.68 337	90.52 300	99.42 166	98.30 269

XVG-OURS-SEG-HR		97.38 116	97.07 131	98.30 68	99.01 109	97.41 34	94.66 269	99.02 76	95.20 174	98.15 130	97.52 214	98.83 5	98.43 358	94.87 183	96.41 357	99.07 171

IS-MVSNet		96.93 139	96.68 154	97.70 113	99.25 62	94.00 162	98.57 20	96.74 302	98.36 34	98.14 131	97.98 175	88.23 287	99.71 102	93.10 247	99.72 71	99.38 106

CSCG		97.40 115	97.30 117	97.69 115	98.95 112	94.83 128	97.28 107	98.99 88	96.35 117	98.13 132	95.95 311	95.99 118	99.66 134	94.36 207	99.73 67	98.59 238

MP-MVS-pluss		97.69 92	97.36 114	98.70 38	99.50 33	96.84 47	95.38 231	98.99 88	92.45 269	98.11 133	98.31 124	97.25 50	99.77 56	96.60 86	99.62 92	99.48 76
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
v1192		96.83 148	97.06 132	96.15 224	98.28 192	89.29 268	95.36 232	98.77 143	93.73 223	98.11 133	98.34 121	93.02 205	99.67 128	98.35 32	99.58 105	99.50 62

OPM-MVS		97.54 105	97.25 120	98.41 59	99.11 94	96.61 56	95.24 242	98.46 188	94.58 200	98.10 135	98.07 161	97.09 57	99.39 225	95.16 166	99.44 155	99.21 140
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v144192		96.69 159	96.90 144	96.03 227	98.25 196	88.92 276	95.49 222	98.77 143	93.05 251	98.09 136	98.29 132	92.51 223	99.70 110	98.11 35	99.56 111	99.47 79

N_pmnet		95.18 225	94.23 262	98.06 88	97.85 238	96.55 58	92.49 339	91.63 370	89.34 314	98.09 136	97.41 221	90.33 259	99.06 297	91.58 272	99.31 195	98.56 240

test_part2					99.03 107	96.07 74				98.08 138

SteuartSystems-ACMMP		98.02 50	97.76 78	98.79 29	99.43 39	97.21 41	97.15 114	98.90 103	96.58 104	98.08 138	97.87 186	97.02 63	99.76 61	95.25 159	99.59 103	99.40 100
Skip Steuart: Steuart Systems R&D Blog.
APD_test1		97.95 58	97.68 85	98.75 31	99.60 17	98.60 5	97.21 112	99.08 58	96.57 107	98.07 140	98.38 118	96.22 114	99.14 283	94.71 194	99.31 195	98.52 245

SR-MVS		98.00 51	97.66 87	99.01 8	98.77 135	97.93 11	97.38 104	98.83 128	97.32 83	98.06 141	97.85 187	96.65 87	99.77 56	95.00 178	99.11 222	99.32 115

XVG-ACMP-BASELINE		97.58 103	97.28 119	98.49 52	99.16 82	96.90 46	96.39 156	98.98 91	95.05 182	98.06 141	98.02 170	95.86 121	99.56 168	94.37 205	99.64 89	99.00 180

IterMVS		95.42 215	95.83 199	94.20 314	97.52 286	83.78 361	92.41 345	97.47 277	95.49 163	98.06 141	98.49 105	87.94 289	99.58 161	96.02 111	99.02 233	99.23 138
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TSAR-MVS + GP.		96.47 171	96.12 183	97.49 134	97.74 266	95.23 115	94.15 288	96.90 295	93.26 239	98.04 144	96.70 273	94.41 172	98.89 314	94.77 190	99.14 216	98.37 258

test_one_0601					99.05 105	95.50 100		98.87 112	97.21 87	98.03 145	98.30 128	96.93 70

testgi		96.07 185	96.50 169	94.80 289	99.26 59	87.69 307	95.96 194	98.58 179	95.08 180	98.02 146	96.25 296	97.92 20	97.60 383	88.68 329	98.74 262	99.11 164

V42		97.04 131	97.16 126	96.68 196	98.59 159	91.05 241	96.33 163	98.36 203	94.60 197	97.99 147	98.30 128	93.32 196	99.62 149	97.40 63	99.53 125	99.38 106

GBi-Net		96.99 134	96.80 148	97.56 122	97.96 230	93.67 173	98.23 46	98.66 167	95.59 158	97.99 147	99.19 36	89.51 274	99.73 82	94.60 196	99.44 155	99.30 120

test1		96.99 134	96.80 148	97.56 122	97.96 230	93.67 173	98.23 46	98.66 167	95.59 158	97.99 147	99.19 36	89.51 274	99.73 82	94.60 196	99.44 155	99.30 120

FMVSNet3		95.26 222	94.94 225	96.22 220	96.53 330	90.06 255	95.99 190	97.66 266	94.11 214	97.99 147	97.91 183	80.22 343	99.63 144	94.60 196	99.44 155	98.96 186

pmmvs-eth3d		96.49 169	96.18 182	97.42 142	98.25 196	94.29 151	94.77 265	98.07 244	89.81 310	97.97 151	98.33 122	93.11 200	99.08 295	95.46 147	99.84 40	98.89 201

v1144		96.84 145	97.08 130	96.13 225	98.42 182	89.28 269	95.41 228	98.67 165	94.21 208	97.97 151	98.31 124	93.06 201	99.65 136	98.06 38	99.62 92	99.45 85

ACMP	92.54 13	97.47 110	97.10 128	98.55 49	99.04 106	96.70 51	96.24 171	98.89 104	93.71 224	97.97 151	97.75 197	97.44 39	99.63 144	93.22 244	99.70 77	99.32 115
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
EI-MVSNet		96.63 162	96.93 140	95.74 241	97.26 307	88.13 295	95.29 240	97.65 268	96.99 90	97.94 154	98.19 147	92.55 218	99.58 161	96.91 80	99.56 111	99.50 62

MVSTER		94.21 268	93.93 273	95.05 274	95.83 356	86.46 327	95.18 245	97.65 268	92.41 270	97.94 154	98.00 174	72.39 379	99.58 161	96.36 95	99.56 111	99.12 161

ACMMP		98.05 48	97.75 80	98.93 18	99.23 65	97.60 22	98.09 57	98.96 95	95.75 151	97.91 156	98.06 166	96.89 74	99.76 61	95.32 156	99.57 108	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
MTAPA		98.14 39	97.84 66	99.06 3	99.44 38	97.90 12	97.25 108	98.73 150	97.69 63	97.90 157	97.96 176	95.81 129	99.82 34	96.13 105	99.61 98	99.45 85

LFMVS		95.32 219	94.88 231	96.62 197	98.03 221	91.47 235	97.65 84	90.72 380	99.11 9	97.89 158	98.31 124	79.20 345	99.48 194	93.91 225	99.12 221	98.93 193

ACMMP_NAP		97.89 72	97.63 93	98.67 40	99.35 51	96.84 47	96.36 161	98.79 138	95.07 181	97.88 159	98.35 120	97.24 51	99.72 87	96.05 108	99.58 105	99.45 85

VNet		96.84 145	96.83 146	96.88 181	98.06 220	92.02 224	96.35 162	97.57 274	97.70 62	97.88 159	97.80 193	92.40 225	99.54 176	94.73 192	98.96 237	99.08 169

HPM-MVS_fast		98.32 30	98.13 40	98.88 23	99.54 26	97.48 30	98.35 35	99.03 74	95.88 143	97.88 159	98.22 145	98.15 16	99.74 76	96.50 90	99.62 92	99.42 97

UA-Net		98.88 7	98.76 13	99.22 2	99.11 94	97.89 13	99.47 3	99.32 25	99.08 10	97.87 162	99.67 2	96.47 99	99.92 5	97.88 42	99.98 2	99.85 3

baseline		97.44 112	97.78 77	96.43 209	98.52 168	90.75 249	96.84 130	99.03 74	96.51 108	97.86 163	98.02 170	96.67 86	99.36 237	97.09 74	99.47 148	99.19 145

v2v482		96.78 152	97.06 132	95.95 232	98.57 161	88.77 282	95.36 232	98.26 213	95.18 176	97.85 164	98.23 142	92.58 216	99.63 144	97.80 47	99.69 78	99.45 85

SF-MVS		97.60 100	97.39 112	98.22 75	98.93 116	95.69 88	97.05 121	99.10 52	95.32 170	97.83 165	97.88 185	96.44 102	99.72 87	94.59 199	99.39 172	99.25 136

Vis-MVSNet		98.27 33	98.34 34	98.07 86	99.33 53	95.21 120	98.04 59	99.46 18	97.32 83	97.82 166	99.11 47	96.75 84	99.86 24	97.84 45	99.36 177	99.15 151
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
AllTest		97.20 127	96.92 142	98.06 88	99.08 98	96.16 70	97.14 116	99.16 40	94.35 205	97.78 167	98.07 161	95.84 122	99.12 287	91.41 273	99.42 166	98.91 197

TestCases				98.06 88	99.08 98	96.16 70		99.16 40	94.35 205	97.78 167	98.07 161	95.84 122	99.12 287	91.41 273	99.42 166	98.91 197

test_vis1_n_1920		95.77 198	96.41 172	93.85 319	98.55 164	84.86 349	95.91 199	99.71 4	92.72 263	97.67 169	98.90 69	87.44 297	98.73 328	97.96 40	98.85 251	97.96 302

GeoE		97.75 87	97.70 81	97.89 101	98.88 122	94.53 140	97.10 118	98.98 91	95.75 151	97.62 170	97.59 209	97.61 36	99.77 56	96.34 96	99.44 155	99.36 112

MDA-MVSNet-bldmvs		95.69 200	95.67 204	95.74 241	98.48 176	88.76 283	92.84 328	97.25 280	96.00 135	97.59 171	97.95 178	91.38 242	99.46 199	93.16 246	96.35 359	98.99 183

PGM-MVS		97.88 73	97.52 105	98.96 13	99.20 77	97.62 21	97.09 119	99.06 62	95.45 164	97.55 172	97.94 179	97.11 54	99.78 47	94.77 190	99.46 151	99.48 76

GST-MVS		97.82 81	97.49 109	98.81 27	99.23 65	97.25 38	97.16 113	98.79 138	95.96 137	97.53 173	97.40 222	96.93 70	99.77 56	95.04 175	99.35 182	99.42 97

YYNet1		94.73 243	94.84 233	94.41 307	97.47 293	85.09 346	90.29 380	95.85 317	92.52 266	97.53 173	97.76 194	91.97 234	99.18 276	93.31 241	96.86 344	98.95 187

TAMVS		95.49 209	94.94 225	97.16 159	98.31 188	93.41 184	95.07 251	96.82 298	91.09 291	97.51 175	97.82 191	89.96 265	99.42 210	88.42 332	99.44 155	98.64 232

LS3D		97.77 86	97.50 108	98.57 47	96.24 336	97.58 24	98.45 31	98.85 119	98.58 28	97.51 175	97.94 179	95.74 132	99.63 144	95.19 162	98.97 236	98.51 246

HFP-MVS		97.94 62	97.64 91	98.83 25	99.15 85	97.50 29	97.59 89	98.84 122	96.05 130	97.49 177	97.54 212	97.07 58	99.70 110	95.61 136	99.46 151	99.30 120

Patchmtry		95.03 234	94.59 249	96.33 214	94.83 379	90.82 246	96.38 159	97.20 282	96.59 103	97.49 177	98.57 97	77.67 352	99.38 228	92.95 250	99.62 92	98.80 213

MDA-MVSNet_test_wron		94.73 243	94.83 235	94.42 306	97.48 289	85.15 344	90.28 381	95.87 316	92.52 266	97.48 179	97.76 194	91.92 237	99.17 280	93.32 240	96.80 349	98.94 189

UnsupCasMVSNet_eth		95.91 193	95.73 203	96.44 208	98.48 176	91.52 234	95.31 238	98.45 189	95.76 149	97.48 179	97.54 212	89.53 273	98.69 334	94.43 201	94.61 382	99.13 156

tttt0517		93.31 296	92.56 303	95.57 248	98.71 142	87.86 301	97.44 100	87.17 397	95.79 148	97.47 181	96.84 263	64.12 393	99.81 36	96.20 102	99.32 192	99.02 179

ACMMPR		97.95 58	97.62 95	98.94 15	99.20 77	97.56 25	97.59 89	98.83 128	96.05 130	97.46 182	97.63 206	96.77 83	99.76 61	95.61 136	99.46 151	99.49 70

APD-MVS		97.00 133	96.53 166	98.41 59	98.55 164	96.31 66	96.32 164	98.77 143	92.96 258	97.44 183	97.58 211	95.84 122	99.74 76	91.96 262	99.35 182	99.19 145
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
HPM-MVS		98.11 43	97.83 69	98.92 21	99.42 41	97.46 31	98.57 20	99.05 66	95.43 167	97.41 184	97.50 216	97.98 19	99.79 44	95.58 139	99.57 108	99.50 62
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
c3_l		95.20 224	95.32 211	94.83 288	96.19 340	86.43 329	91.83 356	98.35 206	93.47 232	97.36 185	97.26 237	88.69 280	99.28 259	95.41 154	99.36 177	98.78 215

EPP-MVSNet		96.84 145	96.58 160	97.65 117	99.18 80	93.78 171	98.68 14	96.34 307	97.91 51	97.30 186	98.06 166	88.46 284	99.85 27	93.85 226	99.40 171	99.32 115

DeepC-MVS_fast	94.34 7	96.74 153	96.51 168	97.44 139	97.69 270	94.15 157	96.02 187	98.43 192	93.17 248	97.30 186	97.38 228	95.48 139	99.28 259	93.74 229	99.34 185	98.88 205
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
mvsany_test1		93.47 292	93.03 288	94.79 290	94.05 391	92.12 219	90.82 375	90.01 388	85.02 366	97.26 188	98.28 133	93.57 192	97.03 387	92.51 255	95.75 372	95.23 383

region2R		97.92 66	97.59 98	98.92 21	99.22 68	97.55 26	97.60 87	98.84 122	96.00 135	97.22 189	97.62 207	96.87 78	99.76 61	95.48 144	99.43 163	99.46 81

ITE_SJBPF				97.85 104	98.64 149	96.66 54		98.51 185	95.63 155	97.22 189	97.30 235	95.52 138	98.55 349	90.97 283	98.90 244	98.34 264

test_fmvs1_n		95.21 223	95.28 212	94.99 278	98.15 213	89.13 274	96.81 133	99.43 21	86.97 345	97.21 191	98.92 65	83.00 329	97.13 386	98.09 36	98.94 240	98.72 224

h-mvs33		96.29 177	95.63 207	98.26 70	98.50 173	96.11 73	96.90 128	97.09 288	96.58 104	97.21 191	98.19 147	84.14 321	99.78 47	95.89 120	96.17 364	98.89 201

hse-mvs2		95.77 198	95.09 220	97.79 107	97.84 243	95.51 97	95.66 212	95.43 328	96.58 104	97.21 191	96.16 299	84.14 321	99.54 176	95.89 120	96.92 341	98.32 265

9.14			96.69 153		98.53 167		96.02 187	98.98 91	93.23 240	97.18 194	97.46 217	96.47 99	99.62 149	92.99 248	99.32 192

OMC-MVS		96.48 170	96.00 189	97.91 100	98.30 189	96.01 78	94.86 261	98.60 175	91.88 278	97.18 194	97.21 240	96.11 116	99.04 299	90.49 303	99.34 185	98.69 228

our_test_3		94.20 270	94.58 250	93.07 337	96.16 342	81.20 379	90.42 379	96.84 296	90.72 295	97.14 196	97.13 243	90.47 255	99.11 290	94.04 220	98.25 294	98.91 197

MS-PatchMatch		94.83 240	94.91 229	94.57 300	96.81 323	87.10 319	94.23 283	97.34 279	88.74 324	97.14 196	97.11 245	91.94 236	98.23 371	92.99 248	97.92 307	98.37 258

eth_miper_zixun_eth		94.89 238	94.93 227	94.75 292	95.99 349	86.12 332	91.35 363	98.49 186	93.40 233	97.12 198	97.25 238	86.87 303	99.35 241	95.08 174	98.82 255	98.78 215

3Dnovator	96.53 2	97.61 99	97.64 91	97.50 131	97.74 266	93.65 177	98.49 28	98.88 110	96.86 95	97.11 199	98.55 100	95.82 125	99.73 82	95.94 117	99.42 166	99.13 156

cl____		94.73 243	94.64 243	95.01 276	95.85 355	87.00 320	91.33 364	98.08 240	93.34 236	97.10 200	97.33 233	84.01 324	99.30 253	95.14 169	99.56 111	98.71 227

DIV-MVS_self_test		94.73 243	94.64 243	95.01 276	95.86 354	87.00 320	91.33 364	98.08 240	93.34 236	97.10 200	97.34 232	84.02 323	99.31 250	95.15 168	99.55 118	98.72 224

PMMVS2		93.66 286	94.07 268	92.45 357	97.57 282	80.67 382	86.46 395	96.00 312	93.99 218	97.10 200	97.38 228	89.90 266	97.82 379	88.76 326	99.47 148	98.86 208

mPP-MVS		97.91 69	97.53 104	99.04 4	99.22 68	97.87 14	97.74 79	98.78 142	96.04 132	97.10 200	97.73 200	96.53 94	99.78 47	95.16 166	99.50 139	99.46 81

BH-untuned		94.69 248	94.75 239	94.52 302	97.95 233	87.53 309	94.07 293	97.01 291	93.99 218	97.10 200	95.65 318	92.65 214	98.95 312	87.60 342	96.74 350	97.09 341

tt0805		97.44 112	97.56 101	97.11 163	99.55 23	96.36 63	98.66 18	95.66 319	98.31 36	97.09 205	95.45 325	97.17 53	98.50 353	98.67 25	97.45 333	96.48 366

test2506		89.86 343	89.16 348	91.97 363	98.95 112	76.83 398	98.54 23	61.07 412	96.20 122	97.07 206	99.16 43	55.19 406	99.69 117	96.43 93	99.83 43	99.38 106

miper_ehance_all_eth		94.69 248	94.70 240	94.64 294	95.77 360	86.22 331	91.32 366	98.24 216	91.67 280	97.05 207	96.65 276	88.39 286	99.22 273	94.88 182	98.34 290	98.49 249

iter_conf05		93.65 287	93.05 286	95.46 256	96.13 347	87.45 311	95.95 196	98.22 218	92.66 264	97.04 208	97.89 184	63.52 395	99.72 87	96.19 103	99.82 47	99.21 140

miper_lstm_enhance		94.81 242	94.80 237	94.85 286	96.16 342	86.45 328	91.14 370	98.20 222	93.49 231	97.03 209	97.37 230	84.97 316	99.26 263	95.28 157	99.56 111	98.83 210

UnsupCasMVSNet_bld		94.72 247	94.26 261	96.08 226	98.62 155	90.54 254	93.38 318	98.05 246	90.30 302	97.02 210	96.80 268	89.54 271	99.16 281	88.44 331	96.18 363	98.56 240

ppachtmachnet_test		94.49 260	94.84 233	93.46 328	96.16 342	82.10 371	90.59 377	97.48 276	90.53 299	97.01 211	97.59 209	91.01 248	99.36 237	93.97 223	99.18 212	98.94 189

D2MVS		95.18 225	95.17 216	95.21 265	97.76 261	87.76 306	94.15 288	97.94 248	89.77 311	96.99 212	97.68 204	87.45 296	99.14 283	95.03 177	99.81 48	98.74 221

ab-mvs		96.59 164	96.59 159	96.60 198	98.64 149	92.21 214	98.35 35	97.67 264	94.45 202	96.99 212	98.79 75	94.96 157	99.49 191	90.39 304	99.07 228	98.08 286

Anonymous20231206		95.27 221	95.06 223	95.88 236	98.72 139	89.37 267	95.70 208	97.85 253	88.00 335	96.98 214	97.62 207	91.95 235	99.34 243	89.21 320	99.53 125	98.94 189

PVSNet_Blended_VisFu		95.95 191	95.80 200	96.42 210	99.28 57	90.62 250	95.31 238	99.08 58	88.40 329	96.97 215	98.17 150	92.11 230	99.78 47	93.64 233	99.21 207	98.86 208

mvs_anonymous		95.36 216	96.07 187	93.21 335	96.29 335	81.56 376	94.60 271	97.66 266	93.30 238	96.95 216	98.91 68	93.03 204	99.38 228	96.60 86	97.30 338	98.69 228

ZNCC-MVS		97.92 66	97.62 95	98.83 25	99.32 55	97.24 39	97.45 99	98.84 122	95.76 149	96.93 217	97.43 220	97.26 49	99.79 44	96.06 106	99.53 125	99.45 85

3Dnovator+	96.13 3	97.73 88	97.59 98	98.15 81	98.11 219	95.60 92	98.04 59	98.70 159	98.13 43	96.93 217	98.45 110	95.30 146	99.62 149	95.64 134	98.96 237	99.24 137

USDC		94.56 256	94.57 252	94.55 301	97.78 259	86.43 329	92.75 331	98.65 172	85.96 353	96.91 219	97.93 181	90.82 251	98.74 327	90.71 295	99.59 103	98.47 250

CP-MVS		97.92 66	97.56 101	98.99 10	98.99 110	97.82 15	97.93 65	98.96 95	96.11 127	96.89 220	97.45 218	96.85 79	99.78 47	95.19 162	99.63 91	99.38 106

OpenMVS_ROB	91.80 14	93.64 288	93.05 286	95.42 258	97.31 306	91.21 240	95.08 250	96.68 305	81.56 381	96.88 221	96.41 288	90.44 258	99.25 265	85.39 364	97.67 322	95.80 375

test_fmvs1		94.51 259	94.60 247	94.26 313	95.91 350	87.92 299	95.35 234	99.02 76	86.56 349	96.79 222	98.52 102	82.64 331	97.00 389	97.87 43	98.71 266	97.88 308

test_yl		94.40 261	94.00 270	95.59 246	96.95 318	89.52 264	94.75 266	95.55 325	96.18 125	96.79 222	96.14 302	81.09 338	99.18 276	90.75 291	97.77 312	98.07 288

DCV-MVSNet		94.40 261	94.00 270	95.59 246	96.95 318	89.52 264	94.75 266	95.55 325	96.18 125	96.79 222	96.14 302	81.09 338	99.18 276	90.75 291	97.77 312	98.07 288

Gipuma		98.07 47	98.31 35	97.36 146	99.76 7	96.28 68	98.51 27	99.10 52	98.76 23	96.79 222	99.34 25	96.61 90	98.82 319	96.38 94	99.50 139	96.98 346
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
alignmvs		96.01 189	95.52 210	97.50 131	97.77 260	94.71 131	96.07 183	96.84 296	97.48 73	96.78 226	94.28 348	85.50 312	99.40 221	96.22 101	98.73 265	98.40 254

MM		96.87 144	96.62 156	97.62 119	97.72 268	93.30 186	96.39 156	92.61 362	97.90 52	96.76 227	98.64 92	90.46 256	99.81 36	99.16 9	99.94 8	99.76 17

CL-MVSNet_self_test		95.04 232	94.79 238	95.82 238	97.51 287	89.79 260	91.14 370	96.82 298	93.05 251	96.72 228	96.40 290	90.82 251	99.16 281	91.95 263	98.66 271	98.50 248

MSLP-MVS++		96.42 174	96.71 152	95.57 248	97.82 246	90.56 253	95.71 207	98.84 122	94.72 192	96.71 229	97.39 226	94.91 158	98.10 375	95.28 157	99.02 233	98.05 295

MGCFI-Net		97.23 125	97.21 123	97.30 149	97.65 276	94.39 145	97.84 70	99.05 66	97.42 75	96.68 230	93.85 352	97.63 34	99.33 245	96.29 97	98.47 284	98.18 281

FA-MVS(test-final)		94.91 237	94.89 230	94.99 278	97.51 287	88.11 297	98.27 44	95.20 331	92.40 271	96.68 230	98.60 95	83.44 326	99.28 259	93.34 239	98.53 280	97.59 327

canonicalmvs		97.23 125	97.21 123	97.30 149	97.65 276	94.39 145	97.84 70	99.05 66	97.42 75	96.68 230	93.85 352	97.63 34	99.33 245	96.29 97	98.47 284	98.18 281

ZD-MVS					98.43 181	95.94 79		98.56 181	90.72 295	96.66 233	97.07 247	95.02 154	99.74 76	91.08 280	98.93 242

diffmvs		96.04 187	96.23 179	95.46 256	97.35 300	88.03 298	93.42 316	99.08 58	94.09 216	96.66 233	96.93 257	93.85 186	99.29 257	96.01 113	98.67 269	99.06 173
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
patch_mono-2		96.59 164	96.93 140	95.55 251	98.88 122	87.12 318	94.47 274	99.30 27	94.12 213	96.65 235	98.41 114	94.98 156	99.87 22	95.81 126	99.78 56	99.66 30

MVP-Stereo		95.69 200	95.28 212	96.92 178	98.15 213	93.03 193	95.64 217	98.20 222	90.39 301	96.63 236	97.73 200	91.63 240	99.10 293	91.84 267	97.31 337	98.63 234
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Vis-MVSNet (Re-imp)		95.11 229	94.85 232	95.87 237	99.12 93	89.17 270	97.54 97	94.92 335	96.50 109	96.58 237	97.27 236	83.64 325	99.48 194	88.42 332	99.67 84	98.97 185

MVS_111021_HR		96.73 155	96.54 165	97.27 152	98.35 187	93.66 176	93.42 316	98.36 203	94.74 191	96.58 237	96.76 271	96.54 93	98.99 305	94.87 183	99.27 201	99.15 151

thisisatest0530		92.71 306	91.76 314	95.56 250	98.42 182	88.23 290	96.03 186	87.35 396	94.04 217	96.56 239	95.47 324	64.03 394	99.77 56	94.78 189	99.11 222	98.68 231

MVS_111021_LR		96.82 149	96.55 163	97.62 119	98.27 194	95.34 110	93.81 306	98.33 207	94.59 199	96.56 239	96.63 277	96.61 90	98.73 328	94.80 186	99.34 185	98.78 215

DELS-MVS		96.17 182	96.23 179	95.99 228	97.55 285	90.04 256	92.38 347	98.52 183	94.13 212	96.55 241	97.06 248	94.99 155	99.58 161	95.62 135	99.28 199	98.37 258
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
baseline1		93.14 300	92.64 301	94.62 296	97.34 302	87.20 317	96.67 147	93.02 354	94.71 193	96.51 242	95.83 314	81.64 333	98.60 345	90.00 310	88.06 399	98.07 288

Patchmatch-test		93.60 289	93.25 284	94.63 295	96.14 346	87.47 310	96.04 185	94.50 339	93.57 229	96.47 243	96.97 254	76.50 360	98.61 343	90.67 297	98.41 289	97.81 314

HyFIR lowres test		93.72 283	92.65 300	96.91 180	98.93 116	91.81 230	91.23 368	98.52 183	82.69 377	96.46 244	96.52 284	80.38 342	99.90 14	90.36 305	98.79 257	99.03 176

QAPM		95.88 194	95.57 209	96.80 187	97.90 236	91.84 229	98.18 53	98.73 150	88.41 328	96.42 245	98.13 153	94.73 159	99.75 67	88.72 327	98.94 240	98.81 212

BH-RMVSNet		94.56 256	94.44 258	94.91 281	97.57 282	87.44 312	93.78 307	96.26 308	93.69 226	96.41 246	96.50 285	92.10 231	99.00 303	85.96 356	97.71 318	98.31 267

CNVR-MVS		96.92 140	96.55 163	98.03 93	98.00 228	95.54 95	94.87 260	98.17 228	94.60 197	96.38 247	97.05 249	95.67 134	99.36 237	95.12 172	99.08 226	99.19 145

thres600view7		92.03 319	91.43 316	93.82 320	98.19 203	84.61 352	96.27 166	90.39 381	96.81 96	96.37 248	93.11 356	73.44 377	99.49 191	80.32 386	97.95 306	97.36 335

thres100view900		91.76 323	91.26 323	93.26 331	98.21 200	84.50 353	96.39 156	90.39 381	96.87 94	96.33 249	93.08 360	73.44 377	99.42 210	78.85 391	97.74 315	95.85 373

XVS		97.96 54	97.63 93	98.94 15	99.15 85	97.66 19	97.77 74	98.83 128	97.42 75	96.32 250	97.64 205	96.49 97	99.72 87	95.66 132	99.37 174	99.45 85

X-MVStestdata		92.86 303	90.83 330	98.94 15	99.15 85	97.66 19	97.77 74	98.83 128	97.42 75	96.32 250	36.50 405	96.49 97	99.72 87	95.66 132	99.37 174	99.45 85

MSDG		95.33 218	95.13 218	95.94 234	97.40 297	91.85 228	91.02 373	98.37 202	95.30 171	96.31 252	95.99 307	94.51 170	98.38 362	89.59 315	97.65 324	97.60 326

CDS-MVSNet		94.88 239	94.12 267	97.14 161	97.64 278	93.57 178	93.96 300	97.06 290	90.05 307	96.30 253	96.55 280	86.10 306	99.47 196	90.10 308	99.31 195	98.40 254
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CVMVSNet		92.33 312	92.79 295	90.95 369	97.26 307	75.84 401	95.29 240	92.33 364	81.86 379	96.27 254	98.19 147	81.44 335	98.46 357	94.23 211	98.29 293	98.55 242

FMVSNet5		93.39 294	92.35 304	96.50 205	95.83 356	90.81 248	97.31 105	98.27 212	92.74 262	96.27 254	98.28 133	62.23 396	99.67 128	90.86 286	99.36 177	99.03 176

TAPA-MVS	93.32 12	94.93 236	94.23 262	97.04 171	98.18 206	94.51 141	95.22 243	98.73 150	81.22 384	96.25 256	95.95 311	93.80 188	98.98 307	89.89 311	98.87 248	97.62 324
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CHOSEN 1792x2688		94.10 272	93.41 281	96.18 222	99.16 82	90.04 256	92.15 349	98.68 162	79.90 389	96.22 257	97.83 188	87.92 293	99.42 210	89.18 321	99.65 87	99.08 169

FE-MVS		92.95 302	92.22 306	95.11 270	97.21 309	88.33 289	98.54 23	93.66 348	89.91 309	96.21 258	98.14 151	70.33 386	99.50 186	87.79 338	98.24 295	97.51 330

MCST-MVS		96.24 179	95.80 200	97.56 122	98.75 136	94.13 158	94.66 269	98.17 228	90.17 305	96.21 258	96.10 305	95.14 150	99.43 208	94.13 215	98.85 251	99.13 156

PHI-MVS		96.96 138	96.53 166	98.25 73	97.48 289	96.50 59	96.76 137	98.85 119	93.52 230	96.19 260	96.85 262	95.94 119	99.42 210	93.79 228	99.43 163	98.83 210

HQP_MVS		96.66 161	96.33 177	97.68 116	98.70 144	94.29 151	96.50 152	98.75 147	96.36 115	96.16 261	96.77 269	91.91 238	99.46 199	92.59 253	99.20 208	99.28 127

plane_prior3						94.51 141			95.29 172	96.16 261

miper_enhance_ethall		93.14 300	92.78 297	94.20 314	93.65 394	85.29 341	89.97 383	97.85 253	85.05 364	96.15 263	94.56 340	85.74 309	99.14 283	93.74 229	98.34 290	98.17 283

CS-MVS		98.09 44	98.01 52	98.32 65	98.45 179	96.69 52	98.52 26	99.69 5	98.07 46	96.07 264	97.19 241	96.88 76	99.86 24	97.50 60	99.73 67	98.41 253

MVS_Test		96.27 178	96.79 150	94.73 293	96.94 320	86.63 326	96.18 174	98.33 207	94.94 186	96.07 264	98.28 133	95.25 147	99.26 263	97.21 68	97.90 309	98.30 269

PCF-MVS	89.43 18	92.12 316	90.64 333	96.57 202	97.80 251	93.48 181	89.88 387	98.45 189	74.46 400	96.04 266	95.68 317	90.71 253	99.31 250	73.73 399	99.01 235	96.91 350
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CPTT-MVS		96.69 159	96.08 186	98.49 52	98.89 121	96.64 55	97.25 108	98.77 143	92.89 259	96.01 267	97.13 243	92.23 227	99.67 128	92.24 257	99.34 185	99.17 148

EC-MVSNet		97.90 71	97.94 58	97.79 107	98.66 148	95.14 121	98.31 39	99.66 8	97.57 67	95.95 268	97.01 253	96.99 65	99.82 34	97.66 55	99.64 89	98.39 256

PMVS	89.60 17	96.71 158	96.97 137	95.95 232	99.51 30	97.81 16	97.42 103	97.49 275	97.93 50	95.95 268	98.58 96	96.88 76	96.91 390	89.59 315	99.36 177	93.12 395
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
xiu_mvs_v1_base_debu		95.62 204	95.96 192	94.60 297	98.01 224	88.42 285	93.99 296	98.21 219	92.98 254	95.91 270	94.53 341	96.39 104	99.72 87	95.43 151	98.19 296	95.64 377

xiu_mvs_v1_base		95.62 204	95.96 192	94.60 297	98.01 224	88.42 285	93.99 296	98.21 219	92.98 254	95.91 270	94.53 341	96.39 104	99.72 87	95.43 151	98.19 296	95.64 377

xiu_mvs_v1_base_debi		95.62 204	95.96 192	94.60 297	98.01 224	88.42 285	93.99 296	98.21 219	92.98 254	95.91 270	94.53 341	96.39 104	99.72 87	95.43 151	98.19 296	95.64 377

tfpn200view9		91.55 325	91.00 325	93.21 335	98.02 222	84.35 355	95.70 208	90.79 378	96.26 119	95.90 273	92.13 376	73.62 374	99.42 210	78.85 391	97.74 315	95.85 373

thres400		91.68 324	91.00 325	93.71 323	98.02 222	84.35 355	95.70 208	90.79 378	96.26 119	95.90 273	92.13 376	73.62 374	99.42 210	78.85 391	97.74 315	97.36 335

cl22		93.25 298	92.84 294	94.46 305	94.30 385	86.00 333	91.09 372	96.64 306	90.74 294	95.79 275	96.31 294	78.24 349	98.77 324	94.15 214	98.34 290	98.62 235

API-MVS		95.09 231	95.01 224	95.31 261	96.61 326	94.02 161	96.83 131	97.18 284	95.60 157	95.79 275	94.33 347	94.54 169	98.37 364	85.70 358	98.52 281	93.52 392

DP-MVS Recon		95.55 207	95.13 218	96.80 187	98.51 170	93.99 163	94.60 271	98.69 160	90.20 304	95.78 277	96.21 298	92.73 211	98.98 307	90.58 299	98.86 250	97.42 334

CLD-MVS		95.47 212	95.07 221	96.69 195	98.27 194	92.53 204	91.36 362	98.67 165	91.22 290	95.78 277	94.12 349	95.65 135	98.98 307	90.81 288	99.72 71	98.57 239
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
旧先验2							93.35 319		77.95 396	95.77 279			98.67 338	90.74 294

pmmvs4		94.82 241	94.19 265	96.70 194	97.42 296	92.75 201	92.09 352	96.76 300	86.80 347	95.73 280	97.22 239	89.28 277	98.89 314	93.28 242	99.14 216	98.46 252

LF4IMVS		96.07 185	95.63 207	97.36 146	98.19 203	95.55 94	95.44 224	98.82 136	92.29 272	95.70 281	96.55 280	92.63 215	98.69 334	91.75 271	99.33 190	97.85 310

testdata				95.70 244	98.16 211	90.58 251		97.72 262	80.38 387	95.62 282	97.02 251	92.06 233	98.98 307	89.06 324	98.52 281	97.54 329

MP-MVS		97.64 96	97.18 125	99.00 9	99.32 55	97.77 17	97.49 98	98.73 150	96.27 118	95.59 283	97.75 197	96.30 109	99.78 47	93.70 232	99.48 146	99.45 85
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ETV-MVS		96.13 184	95.90 196	96.82 186	97.76 261	93.89 165	95.40 229	98.95 97	95.87 144	95.58 284	91.00 387	96.36 107	99.72 87	93.36 238	98.83 254	96.85 353

CS-MVS-test		97.91 69	97.84 66	98.14 82	98.52 168	96.03 77	98.38 34	99.67 6	98.11 44	95.50 285	96.92 259	96.81 82	99.87 22	96.87 82	99.76 58	98.51 246

thres200		91.00 332	90.42 336	92.77 349	97.47 293	83.98 360	94.01 295	91.18 376	95.12 179	95.44 286	91.21 385	73.93 370	99.31 250	77.76 394	97.63 325	95.01 384

CDPH-MVS		95.45 214	94.65 242	97.84 105	98.28 192	94.96 126	93.73 308	98.33 207	85.03 365	95.44 286	96.60 278	95.31 145	99.44 206	90.01 309	99.13 218	99.11 164

NCCC		96.52 168	95.99 190	98.10 85	97.81 247	95.68 89	95.00 256	98.20 222	95.39 168	95.40 288	96.36 292	93.81 187	99.45 203	93.55 235	98.42 288	99.17 148

MVS_0304		96.62 163	96.40 173	97.28 151	97.91 234	92.30 210	96.47 154	89.74 389	97.52 71	95.38 289	98.63 93	92.76 209	99.81 36	99.28 4	99.93 11	99.75 19

jason		94.39 263	94.04 269	95.41 260	98.29 190	87.85 303	92.74 333	96.75 301	85.38 362	95.29 290	96.15 300	88.21 288	99.65 136	94.24 210	99.34 185	98.74 221
jason: jason.
new_pmnet		92.34 311	91.69 315	94.32 310	96.23 338	89.16 271	92.27 348	92.88 356	84.39 374	95.29 290	96.35 293	85.66 310	96.74 394	84.53 371	97.56 326	97.05 342

pmmvs5		94.63 253	94.34 260	95.50 253	97.63 279	88.34 288	94.02 294	97.13 286	87.15 341	95.22 292	97.15 242	87.50 295	99.27 262	93.99 221	99.26 202	98.88 205

Effi-MVS+-dtu		96.81 150	96.09 185	98.99 10	96.90 322	98.69 4	96.42 155	98.09 239	95.86 145	95.15 293	95.54 322	94.26 176	99.81 36	94.06 217	98.51 283	98.47 250

testing3		89.72 345	88.26 354	94.10 317	97.66 275	84.30 357	94.80 262	88.25 394	94.66 194	95.07 294	92.51 371	41.15 412	99.43 208	91.81 268	98.44 287	98.55 242

KD-MVS_2432*1600		88.93 352	87.74 357	92.49 354	88.04 408	81.99 372	89.63 389	95.62 321	91.35 287	95.06 295	93.11 356	56.58 400	98.63 341	85.19 365	95.07 376	96.85 353

miper_refine_blended		88.93 352	87.74 357	92.49 354	88.04 408	81.99 372	89.63 389	95.62 321	91.35 287	95.06 295	93.11 356	56.58 400	98.63 341	85.19 365	95.07 376	96.85 353

HPM-MVS++		96.99 134	96.38 174	98.81 27	98.64 149	97.59 23	95.97 192	98.20 222	95.51 162	95.06 295	96.53 282	94.10 179	99.70 110	94.29 208	99.15 215	99.13 156

MIMVSNet		93.42 293	92.86 292	95.10 272	98.17 209	88.19 291	98.13 55	93.69 345	92.07 273	95.04 298	98.21 146	80.95 340	99.03 302	81.42 383	98.06 302	98.07 288

TR-MVS		92.54 308	92.20 307	93.57 326	96.49 331	86.66 325	93.51 314	94.73 336	89.96 308	94.95 299	93.87 351	90.24 264	98.61 343	81.18 384	94.88 379	95.45 381

PatchMatch-RL		94.61 254	93.81 274	97.02 173	98.19 203	95.72 86	93.66 309	97.23 281	88.17 333	94.94 300	95.62 320	91.43 241	98.57 346	87.36 348	97.68 321	96.76 359

MG-MVS		94.08 274	94.00 270	94.32 310	97.09 314	85.89 334	93.19 324	95.96 314	92.52 266	94.93 301	97.51 215	89.54 271	98.77 324	87.52 346	97.71 318	98.31 267

新几何1				97.25 155	98.29 190	94.70 133		97.73 261	77.98 395	94.83 302	96.67 275	92.08 232	99.45 203	88.17 336	98.65 273	97.61 325

Fast-Effi-MVS+-dtu		96.44 172	96.12 183	97.39 145	97.18 310	94.39 145	95.46 223	98.73 150	96.03 134	94.72 303	94.92 335	96.28 112	99.69 117	93.81 227	97.98 304	98.09 285

test0.0.03 1		90.11 337	89.21 344	92.83 347	93.89 392	86.87 323	91.74 357	88.74 393	92.02 274	94.71 304	91.14 386	73.92 371	94.48 400	83.75 377	92.94 388	97.16 340

test222					98.17 209	93.24 190	92.74 333	97.61 273	75.17 399	94.65 305	96.69 274	90.96 250			98.66 271	97.66 321

SCA		93.38 295	93.52 279	92.96 343	96.24 336	81.40 378	93.24 322	94.00 343	91.58 284	94.57 306	96.97 254	87.94 289	99.42 210	89.47 317	97.66 323	98.06 292

CNLPA		95.04 232	94.47 255	96.75 191	97.81 247	95.25 114	94.12 292	97.89 251	94.41 203	94.57 306	95.69 316	90.30 262	98.35 365	86.72 354	98.76 260	96.64 361

PVSNet_BlendedMVS		95.02 235	94.93 227	95.27 262	97.79 256	87.40 313	94.14 290	98.68 162	88.94 321	94.51 308	98.01 172	93.04 202	99.30 253	89.77 313	99.49 142	99.11 164

PVSNet_Blended		93.96 277	93.65 276	94.91 281	97.79 256	87.40 313	91.43 361	98.68 162	84.50 372	94.51 308	94.48 345	93.04 202	99.30 253	89.77 313	98.61 276	98.02 298

MVSFormer		96.14 183	96.36 175	95.49 254	97.68 271	87.81 304	98.67 15	99.02 76	96.50 109	94.48 310	96.15 300	86.90 301	99.92 5	98.73 22	99.13 218	98.74 221

lupinMVS		93.77 280	93.28 283	95.24 263	97.68 271	87.81 304	92.12 350	96.05 310	84.52 371	94.48 310	95.06 331	86.90 301	99.63 144	93.62 234	99.13 218	98.27 273

OpenMVS	94.22 8	95.48 211	95.20 214	96.32 215	97.16 311	91.96 226	97.74 79	98.84 122	87.26 339	94.36 312	98.01 172	93.95 184	99.67 128	90.70 296	98.75 261	97.35 337

PatchT		93.75 282	93.57 278	94.29 312	95.05 376	87.32 315	96.05 184	92.98 355	97.54 70	94.25 313	98.72 82	75.79 365	99.24 269	95.92 118	95.81 367	96.32 368

BH-w/o		92.14 315	91.94 309	92.73 350	97.13 313	85.30 340	92.46 341	95.64 320	89.33 315	94.21 314	92.74 367	89.60 269	98.24 370	81.68 382	94.66 381	94.66 386

xiu_mvs_v2_base		94.22 266	94.63 245	92.99 342	97.32 305	84.84 350	92.12 350	97.84 255	91.96 276	94.17 315	93.43 354	96.07 117	99.71 102	91.27 276	97.48 330	94.42 387

PS-MVSNAJ		94.10 272	94.47 255	93.00 341	97.35 300	84.88 348	91.86 355	97.84 255	91.96 276	94.17 315	92.50 372	95.82 125	99.71 102	91.27 276	97.48 330	94.40 388

CR-MVSNet		93.29 297	92.79 295	94.78 291	95.44 368	88.15 293	96.18 174	97.20 282	84.94 368	94.10 317	98.57 97	77.67 352	99.39 225	95.17 164	95.81 367	96.81 357

RPMNet		94.68 250	94.60 247	94.90 283	95.44 368	88.15 293	96.18 174	98.86 115	97.43 74	94.10 317	98.49 105	79.40 344	99.76 61	95.69 129	95.81 367	96.81 357

WTY-MVS		93.55 290	93.00 290	95.19 266	97.81 247	87.86 301	93.89 302	96.00 312	89.02 319	94.07 319	95.44 326	86.27 305	99.33 245	87.69 340	96.82 347	98.39 256

GA-MVS		92.83 304	92.15 308	94.87 285	96.97 317	87.27 316	90.03 382	96.12 309	91.83 279	94.05 320	94.57 339	76.01 364	98.97 311	92.46 256	97.34 336	98.36 263

WB-MVSnew		91.50 326	91.29 319	92.14 361	94.85 378	80.32 383	93.29 321	88.77 392	88.57 327	94.03 321	92.21 374	92.56 217	98.28 369	80.21 387	97.08 339	97.81 314

test_prior2							93.33 320		94.21 208	94.02 322	96.25 296	93.64 191		91.90 264	98.96 237

MDTV_nov1_ep13_2view						57.28 412	94.89 259		80.59 386	94.02 322		78.66 348		85.50 362		97.82 312

AdaColmap		95.11 229	94.62 246	96.58 200	97.33 304	94.45 144	94.92 258	98.08 240	93.15 249	93.98 324	95.53 323	94.34 174	99.10 293	85.69 359	98.61 276	96.20 371

pmmvs3		90.00 339	88.90 349	93.32 329	94.20 389	85.34 339	91.25 367	92.56 363	78.59 393	93.82 325	95.17 328	67.36 391	98.69 334	89.08 323	98.03 303	95.92 372

TEST9					97.84 243	95.23 115	93.62 310	98.39 199	86.81 346	93.78 326	95.99 307	94.68 163	99.52 181

train_agg		95.46 213	94.66 241	97.88 102	97.84 243	95.23 115	93.62 310	98.39 199	87.04 342	93.78 326	95.99 307	94.58 167	99.52 181	91.76 270	98.90 244	98.89 201

EIA-MVS		96.04 187	95.77 202	96.85 183	97.80 251	92.98 194	96.12 180	99.16 40	94.65 195	93.77 328	91.69 381	95.68 133	99.67 128	94.18 212	98.85 251	97.91 305

sss		94.22 266	93.72 275	95.74 241	97.71 269	89.95 258	93.84 303	96.98 292	88.38 330	93.75 329	95.74 315	87.94 289	98.89 314	91.02 282	98.10 300	98.37 258

test_8					97.81 247	95.07 124	93.54 313	98.38 201	87.04 342	93.71 330	95.96 310	94.58 167	99.52 181

E-PMN		89.52 348	89.78 340	88.73 379	93.14 397	77.61 393	83.26 399	92.02 366	94.82 190	93.71 330	93.11 356	75.31 366	96.81 391	85.81 357	96.81 348	91.77 398

thisisatest0515		90.43 335	89.18 347	94.17 316	97.07 315	85.44 338	89.75 388	87.58 395	88.28 331	93.69 332	91.72 380	65.27 392	99.58 161	90.59 298	98.67 269	97.50 332

UGNet		96.81 150	96.56 162	97.58 121	96.64 325	93.84 168	97.75 77	97.12 287	96.47 112	93.62 333	98.88 71	93.22 199	99.53 178	95.61 136	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
PatchmatchNet		91.98 320	91.87 310	92.30 359	94.60 382	79.71 385	95.12 246	93.59 350	89.52 313	93.61 334	97.02 251	77.94 350	99.18 276	90.84 287	94.57 384	98.01 299
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CMPMVS	73.10 23	92.74 305	91.39 317	96.77 190	93.57 396	94.67 134	94.21 285	97.67 264	80.36 388	93.61 334	96.60 278	82.85 330	97.35 384	84.86 369	98.78 258	98.29 272
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test12				97.46 137	97.61 280	94.07 159		97.78 259		93.57 336		93.31 197	99.42 210		98.78 258	98.89 201

tpm		91.08 331	90.85 329	91.75 365	95.33 371	78.09 390	95.03 255	91.27 375	88.75 323	93.53 337	97.40 222	71.24 381	99.30 253	91.25 278	93.87 386	97.87 309

agg_prior					97.80 251	94.96 126		98.36 203		93.49 338			99.53 178

原ACMM1				96.58 200	98.16 211	92.12 219		98.15 234	85.90 355	93.49 338	96.43 287	92.47 224	99.38 228	87.66 341	98.62 275	98.23 276

MDTV_nov1_ep13			91.28 320		94.31 384	73.51 406	94.80 262	93.16 353	86.75 348	93.45 340	97.40 222	76.37 361	98.55 349	88.85 325	96.43 356

114514_t		93.96 277	93.22 285	96.19 221	99.06 101	90.97 244	95.99 190	98.94 98	73.88 401	93.43 341	96.93 257	92.38 226	99.37 234	89.09 322	99.28 199	98.25 275

Fast-Effi-MVS+		95.49 209	95.07 221	96.75 191	97.67 274	92.82 196	94.22 284	98.60 175	91.61 282	93.42 342	92.90 363	96.73 85	99.70 110	92.60 252	97.89 310	97.74 318

PAPM_NR		94.61 254	94.17 266	95.96 230	98.36 186	91.23 239	95.93 197	97.95 247	92.98 254	93.42 342	94.43 346	90.53 254	98.38 362	87.60 342	96.29 361	98.27 273

Effi-MVS+		96.19 181	96.01 188	96.71 193	97.43 295	92.19 218	96.12 180	99.10 52	95.45 164	93.33 344	94.71 338	97.23 52	99.56 168	93.21 245	97.54 327	98.37 258

F-COLMAP		95.30 220	94.38 259	98.05 92	98.64 149	96.04 75	95.61 218	98.66 167	89.00 320	93.22 345	96.40 290	92.90 206	99.35 241	87.45 347	97.53 328	98.77 218

iter_conf05_11		93.77 280	93.29 282	95.24 263	96.54 327	89.14 273	91.55 359	95.02 333	90.16 306	93.21 346	93.94 350	87.37 298	99.56 168	92.24 257	99.56 111	97.03 344

test_vis1_rt		94.03 276	93.65 276	95.17 268	95.76 361	93.42 183	93.97 299	98.33 207	84.68 369	93.17 347	95.89 313	92.53 222	94.79 398	93.50 236	94.97 378	97.31 338

EPMVS		89.26 349	88.55 351	91.39 367	92.36 403	79.11 388	95.65 214	79.86 406	88.60 326	93.12 348	96.53 282	70.73 385	98.10 375	90.75 291	89.32 397	96.98 346

DPM-MVS		93.68 285	92.77 298	96.42 210	97.91 234	92.54 203	91.17 369	97.47 277	84.99 367	93.08 349	94.74 337	89.90 266	99.00 303	87.54 344	98.09 301	97.72 319

UWE-MVS		87.57 364	86.72 366	90.13 375	95.21 372	73.56 405	91.94 354	83.78 404	88.73 325	93.00 350	92.87 364	55.22 405	99.25 265	81.74 381	97.96 305	97.59 327

1112_ss		94.12 271	93.42 280	96.23 218	98.59 159	90.85 245	94.24 282	98.85 119	85.49 358	92.97 351	94.94 333	86.01 307	99.64 140	91.78 269	97.92 307	98.20 279

HQP4-MVS										92.87 352			99.23 271			99.06 173

HQP-NCC					97.85 238		94.26 278		93.18 245	92.86 353

ACMP_Plane					97.85 238		94.26 278		93.18 245	92.86 353

HQP-MVS		95.17 227	94.58 250	96.92 178	97.85 238	92.47 207	94.26 278	98.43 192	93.18 245	92.86 353	95.08 329	90.33 259	99.23 271	90.51 301	98.74 262	99.05 175

dmvs_re		92.08 318	91.27 321	94.51 303	97.16 311	92.79 200	95.65 214	92.64 361	94.11 214	92.74 356	90.98 388	83.41 327	94.44 401	80.72 385	94.07 385	96.29 369

ADS-MVSNet2		91.47 327	90.51 335	94.36 308	95.51 366	85.63 335	95.05 253	95.70 318	83.46 375	92.69 357	96.84 263	79.15 346	99.41 219	85.66 360	90.52 393	98.04 296

ADS-MVSNet		90.95 333	90.26 337	93.04 338	95.51 366	82.37 370	95.05 253	93.41 351	83.46 375	92.69 357	96.84 263	79.15 346	98.70 332	85.66 360	90.52 393	98.04 296

Test_1112_low_res		93.53 291	92.86 292	95.54 252	98.60 157	88.86 279	92.75 331	98.69 160	82.66 378	92.65 359	96.92 259	84.75 317	99.56 168	90.94 284	97.76 314	98.19 280

AUN-MVS		93.95 279	92.69 299	97.74 110	97.80 251	95.38 105	95.57 221	95.46 327	91.26 289	92.64 360	96.10 305	74.67 368	99.55 173	93.72 231	96.97 340	98.30 269

EMVS		89.06 351	89.22 343	88.61 380	93.00 399	77.34 395	82.91 400	90.92 377	94.64 196	92.63 361	91.81 379	76.30 362	97.02 388	83.83 375	96.90 343	91.48 399

CANet		95.86 195	95.65 206	96.49 206	96.41 333	90.82 246	94.36 276	98.41 196	94.94 186	92.62 362	96.73 272	92.68 212	99.71 102	95.12 172	99.60 101	98.94 189

DSMNet-mixed		92.19 314	91.83 311	93.25 332	96.18 341	83.68 362	96.27 166	93.68 347	76.97 398	92.54 363	99.18 39	89.20 279	98.55 349	83.88 374	98.60 278	97.51 330

PVSNet	86.72 19	91.10 330	90.97 327	91.49 366	97.56 284	78.04 391	87.17 394	94.60 338	84.65 370	92.34 364	92.20 375	87.37 298	98.47 356	85.17 367	97.69 320	97.96 302

tpmrst		90.31 336	90.61 334	89.41 377	94.06 390	72.37 408	95.06 252	93.69 345	88.01 334	92.32 365	96.86 261	77.45 354	98.82 319	91.04 281	87.01 400	97.04 343

cascas		91.89 321	91.35 318	93.51 327	94.27 386	85.60 336	88.86 392	98.61 174	79.32 391	92.16 366	91.44 383	89.22 278	98.12 374	90.80 289	97.47 332	96.82 356

MAR-MVS		94.21 268	93.03 288	97.76 109	96.94 320	97.44 33	96.97 125	97.15 285	87.89 337	92.00 367	92.73 368	92.14 229	99.12 287	83.92 373	97.51 329	96.73 360
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
tpmvs		90.79 334	90.87 328	90.57 372	92.75 402	76.30 399	95.79 205	93.64 349	91.04 292	91.91 368	96.26 295	77.19 358	98.86 318	89.38 319	89.85 396	96.56 364

PMMVS		92.39 309	91.08 324	96.30 217	93.12 398	92.81 197	90.58 378	95.96 314	79.17 392	91.85 369	92.27 373	90.29 263	98.66 339	89.85 312	96.68 353	97.43 333

Syy-MVS		92.09 317	91.80 313	92.93 345	95.19 373	82.65 367	92.46 341	91.35 372	90.67 297	91.76 370	87.61 399	85.64 311	98.50 353	94.73 192	96.84 345	97.65 322

myMVS_eth3d		87.16 368	85.61 371	91.82 364	95.19 373	79.32 386	92.46 341	91.35 372	90.67 297	91.76 370	87.61 399	41.96 411	98.50 353	82.66 379	96.84 345	97.65 322

PLC	91.02 16	94.05 275	92.90 291	97.51 127	98.00 228	95.12 123	94.25 281	98.25 214	86.17 351	91.48 372	95.25 327	91.01 248	99.19 275	85.02 368	96.69 352	98.22 277
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
dp		88.08 359	88.05 355	88.16 384	92.85 400	68.81 410	94.17 286	92.88 356	85.47 359	91.38 373	96.14 302	68.87 389	98.81 321	86.88 352	83.80 403	96.87 351

PAPR		92.22 313	91.27 321	95.07 273	95.73 363	88.81 280	91.97 353	97.87 252	85.80 356	90.91 374	92.73 368	91.16 245	98.33 366	79.48 388	95.76 371	98.08 286

1314		92.38 310	92.30 305	92.64 352	95.42 370	85.15 344	95.86 201	96.97 293	85.40 361	90.62 375	93.06 361	91.12 246	97.80 380	86.74 353	95.49 375	94.97 385

MVS		90.02 338	89.20 345	92.47 356	94.71 380	86.90 322	95.86 201	96.74 302	64.72 403	90.62 375	92.77 366	92.54 220	98.39 361	79.30 389	95.56 374	92.12 396

CostFormer		89.75 344	89.25 342	91.26 368	94.69 381	78.00 392	95.32 237	91.98 367	81.50 382	90.55 377	96.96 256	71.06 383	98.89 314	88.59 330	92.63 390	96.87 351

HY-MVS	91.43 15	92.58 307	91.81 312	94.90 283	96.49 331	88.87 278	97.31 105	94.62 337	85.92 354	90.50 378	96.84 263	85.05 314	99.40 221	83.77 376	95.78 370	96.43 367

ETVMVS		87.62 363	85.75 370	93.22 334	96.15 345	83.26 363	92.94 327	90.37 383	91.39 286	90.37 379	88.45 397	51.93 409	98.64 340	73.76 398	96.38 358	97.75 317

FPMVS		89.92 342	88.63 350	93.82 320	98.37 185	96.94 45	91.58 358	93.34 352	88.00 335	90.32 380	97.10 246	70.87 384	91.13 404	71.91 402	96.16 365	93.39 394

JIA-IIPM		91.79 322	90.69 332	95.11 270	93.80 393	90.98 243	94.16 287	91.78 369	96.38 113	90.30 381	99.30 28	72.02 380	98.90 313	88.28 334	90.17 395	95.45 381

testing91		89.67 346	88.55 351	93.04 338	95.90 351	81.80 375	92.71 335	93.71 344	93.71 224	90.18 382	90.15 393	57.11 398	99.22 273	87.17 351	96.32 360	98.12 284

CANet_DTU		94.65 252	94.21 264	95.96 230	95.90 351	89.68 261	93.92 301	97.83 257	93.19 244	90.12 383	95.64 319	88.52 283	99.57 167	93.27 243	99.47 148	98.62 235

test-LLR		89.97 341	89.90 339	90.16 373	94.24 387	74.98 402	89.89 384	89.06 390	92.02 274	89.97 384	90.77 389	73.92 371	98.57 346	91.88 265	97.36 334	96.92 348

test-mter		87.92 361	87.17 362	90.16 373	94.24 387	74.98 402	89.89 384	89.06 390	86.44 350	89.97 384	90.77 389	54.96 408	98.57 346	91.88 265	97.36 334	96.92 348

testing99		89.21 350	88.04 356	92.70 351	95.78 359	81.00 381	92.65 336	92.03 365	93.20 243	89.90 386	90.08 395	55.25 404	99.14 283	87.54 344	95.95 366	97.97 301

dmvs_testset		87.30 366	86.99 363	88.24 382	96.71 324	77.48 394	94.68 268	86.81 399	92.64 265	89.61 387	87.01 401	85.91 308	93.12 402	61.04 406	88.49 398	94.13 389

tpm2		88.47 356	87.69 359	90.79 370	94.98 377	77.34 395	95.09 248	91.83 368	77.51 397	89.40 388	96.41 288	67.83 390	98.73 328	83.58 378	92.60 391	96.29 369

tpm cat1		88.01 360	87.33 361	90.05 376	94.48 383	76.28 400	94.47 274	94.35 341	73.84 402	89.26 389	95.61 321	73.64 373	98.30 368	84.13 372	86.20 401	95.57 380

TESTMET0.1,1		87.20 367	86.57 367	89.07 378	93.62 395	72.84 407	89.89 384	87.01 398	85.46 360	89.12 390	90.20 392	56.00 403	97.72 381	90.91 285	96.92 341	96.64 361

testing222		87.35 365	85.50 372	92.93 345	95.79 358	82.83 365	92.40 346	90.10 387	92.80 261	88.87 391	89.02 396	48.34 410	98.70 332	75.40 397	96.74 350	97.27 339

MVS-HIRNet		88.40 357	90.20 338	82.99 386	97.01 316	60.04 411	93.11 325	85.61 401	84.45 373	88.72 392	99.09 50	84.72 318	98.23 371	82.52 380	96.59 355	90.69 401

IB-MVS	85.98 20	88.63 355	86.95 365	93.68 324	95.12 375	84.82 351	90.85 374	90.17 386	87.55 338	88.48 393	91.34 384	58.01 397	99.59 159	87.24 350	93.80 387	96.63 363
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
testing11		88.93 352	87.63 360	92.80 348	95.87 353	81.49 377	92.48 340	91.54 371	91.62 281	88.27 394	90.24 391	55.12 407	99.11 290	87.30 349	96.28 362	97.81 314

PVSNet_0	81.89 21	84.49 370	83.21 373	88.34 381	95.76 361	74.97 404	83.49 398	92.70 360	78.47 394	87.94 395	86.90 402	83.38 328	96.63 395	73.44 400	66.86 406	93.40 393

EPNet		93.72 283	92.62 302	97.03 172	87.61 410	92.25 212	96.27 166	91.28 374	96.74 98	87.65 396	97.39 226	85.00 315	99.64 140	92.14 260	99.48 146	99.20 144
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CHOSEN 280x420		89.98 340	89.19 346	92.37 358	95.60 365	81.13 380	86.22 396	97.09 288	81.44 383	87.44 397	93.15 355	73.99 369	99.47 196	88.69 328	99.07 228	96.52 365

baseline2		89.65 347	88.44 353	93.25 332	95.62 364	82.71 366	93.82 304	85.94 400	88.89 322	87.35 398	92.54 370	71.23 382	99.33 245	86.01 355	94.60 383	97.72 319

gg-mvs-nofinetune		88.28 358	86.96 364	92.23 360	92.84 401	84.44 354	98.19 52	74.60 408	99.08 10	87.01 399	99.47 11	56.93 399	98.23 371	78.91 390	95.61 373	94.01 390

ET-MVSNet_ETH3D		91.12 329	89.67 341	95.47 255	96.41 333	89.15 272	91.54 360	90.23 385	89.07 318	86.78 400	92.84 365	69.39 388	99.44 206	94.16 213	96.61 354	97.82 312

PAPM		87.64 362	85.84 369	93.04 338	96.54 327	84.99 347	88.42 393	95.57 324	79.52 390	83.82 401	93.05 362	80.57 341	98.41 359	62.29 405	92.79 389	95.71 376

GG-mvs-BLEND				90.60 371	91.00 405	84.21 358	98.23 46	72.63 411		82.76 402	84.11 403	56.14 402	96.79 392	72.20 401	92.09 392	90.78 400

MVE	73.61 22	86.48 369	85.92 368	88.18 383	96.23 338	85.28 342	81.78 401	75.79 407	86.01 352	82.53 403	91.88 378	92.74 210	87.47 406	71.42 403	94.86 380	91.78 397
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EPNet_dtu		91.39 328	90.75 331	93.31 330	90.48 407	82.61 368	94.80 262	92.88 356	93.39 234	81.74 404	94.90 336	81.36 336	99.11 290	88.28 334	98.87 248	98.21 278
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepMVS_CX				77.17 387	90.94 406	85.28 342		74.08 410	52.51 404	80.87 405	88.03 398	75.25 367	70.63 407	59.23 407	84.94 402	75.62 402

tmp_tt		57.23 373	62.50 376	41.44 389	34.77 412	49.21 413	83.93 397	60.22 413	15.31 405	71.11 406	79.37 404	70.09 387	44.86 408	64.76 404	82.93 404	30.25 404

test_method		66.88 372	66.13 375	69.11 388	62.68 411	25.73 414	49.76 402	96.04 311	14.32 406	64.27 407	91.69 381	73.45 376	88.05 405	76.06 396	66.94 405	93.54 391

EGC-MVSNET		83.08 371	77.93 374	98.53 50	99.57 20	97.55 26	98.33 38	98.57 180	4.71 407	10.38 408	98.90 69	95.60 137	99.50 186	95.69 129	99.61 98	98.55 242

testmvs		12.33 376	15.23 379	3.64 391	5.77 414	2.23 416	88.99 391	3.62 414	2.30 409	5.29 409	13.09 406	4.52 414	1.95 409	5.16 409	8.32 408	6.75 406

test123		12.59 375	15.49 378	3.87 390	6.07 413	2.55 415	90.75 376	2.59 415	2.52 408	5.20 410	13.02 407	4.96 413	1.85 410	5.20 408	9.09 407	7.23 405

test_blank		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 410	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

uanet_test		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 410	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

DCPMVS		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 410	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

cdsmvs_eth3d_5k		24.22 374	32.30 377	0.00 392	0.00 415	0.00 417	0.00 403	98.10 238	0.00 410	0.00 411	95.06 331	97.54 38	0.00 411	0.00 410	0.00 409	0.00 407

pcd_1.5k_mvsjas		7.98 377	10.65 380	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 410	95.82 125	0.00 411	0.00 410	0.00 409	0.00 407

sosnet-low-res		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 410	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

sosnet		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 410	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

uncertanet		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 410	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

Regformer		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 410	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

ab-mvs-re		7.91 378	10.55 381	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	94.94 333	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

uanet		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 410	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

WAC-MVS						79.32 386								85.41 363

MSC_two_6792asdad				98.22 75	97.75 263	95.34 110		98.16 232					99.75 67	95.87 122	99.51 135	99.57 46

No_MVS				98.22 75	97.75 263	95.34 110		98.16 232					99.75 67	95.87 122	99.51 135	99.57 46

eth-test2					0.00 415

eth-test					0.00 415

OPU-MVS				97.64 118	98.01 224	95.27 113	96.79 135				97.35 231	96.97 66	98.51 352	91.21 279	99.25 203	99.14 154

save fliter					98.48 176	94.71 131	94.53 273	98.41 196	95.02 184

test_0728_SECOND				98.25 73	99.23 65	95.49 101	96.74 138	98.89 104					99.75 67	95.48 144	99.52 130	99.53 56

GSMVS																98.06 292

sam_mvs1												77.80 351				98.06 292

sam_mvs												77.38 355

MTGPA								98.73 150

test_post1							94.98 257				10.37 409	76.21 363	99.04 299	89.47 317

test_post											10.87 408	76.83 359	99.07 296

patchmatchnet-post											96.84 263	77.36 356	99.42 210

MTMP							96.55 150	74.60 408

gm-plane-assit					91.79 404	71.40 409			81.67 380		90.11 394		98.99 305	84.86 369

test9_res														91.29 275	98.89 247	99.00 180

agg_prior2														90.34 306	98.90 244	99.10 168

test_prior4						95.38 105	93.61 312

test_prior				97.46 137	97.79 256	94.26 155		98.42 195					99.34 243			98.79 214

新几何2							93.43 315

旧先验1					97.80 251	93.87 166		97.75 260			97.04 250	93.57 192			98.68 268	98.72 224

无先验							93.20 323	97.91 249	80.78 385				99.40 221	87.71 339		97.94 304

原ACMM2							92.82 329

testdata2													99.46 199	87.84 337

segment_acmp												95.34 144

testdata1							92.77 330		93.78 222

plane_prior7					98.70 144	94.67 134

plane_prior6					98.38 184	94.37 148						91.91 238

plane_prior5								98.75 147					99.46 199	92.59 253	99.20 208	99.28 127

plane_prior4											96.77 269

plane_prior2							96.50 152		96.36 115

plane_prior1					98.49 174

plane_prior						94.29 151	95.42 226		94.31 207						98.93 242

n2								0.00 416

nn								0.00 416

door-mid								98.17 228

test11								98.08 240

door								97.81 258

HQP5-MVS						92.47 207

BP-MVS														90.51 301

HQP3-MVS								98.43 192							98.74 262

HQP2-MVS												90.33 259

NP-MVS					98.14 215	93.72 172					95.08 329

ACMMP++_ref															99.52 130

ACMMP++															99.55 118

Test By Simon												94.51 170

High-resolution multi-view benchmark