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		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 12	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 10	100.00 1	99.85 22

Gipuma		99.03 63	99.16 48	98.64 186	99.94 2	98.51 104	99.32 23	99.75 34	99.58 29	98.60 217	99.62 36	98.22 80	99.51 342	97.70 149	99.73 145	97.89 372
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 25	99.31 33	99.53 37	99.91 3	98.98 69	99.63 7	99.58 59	99.44 39	99.78 27	99.76 12	96.39 203	99.92 53	99.44 37	99.92 54	99.68 56

pmmvs6		99.67 3	99.70 3	99.60 14	99.90 4	99.27 26	99.53 8	99.76 31	99.64 19	99.84 20	99.83 4	99.50 8	99.87 108	99.36 39	99.92 54	99.64 66

PS-MVSNAJss		99.46 14	99.49 13	99.35 72	99.90 4	98.15 130	99.20 45	99.65 49	99.48 33	99.92 8	99.71 19	98.07 93	99.96 12	99.53 31	100.00 1	99.93 10

testf1		99.25 36	99.16 48	99.51 46	99.89 6	99.63 4	98.71 99	99.69 40	98.90 106	99.43 80	99.35 89	98.86 28	99.67 275	97.81 140	99.81 99	99.24 229

APD_test2		99.25 36	99.16 48	99.51 46	99.89 6	99.63 4	98.71 99	99.69 40	98.90 106	99.43 80	99.35 89	98.86 28	99.67 275	97.81 140	99.81 99	99.24 229

ANet_high		99.57 7	99.67 5	99.28 87	99.89 6	98.09 137	99.14 54	99.93 5	99.82 5	99.93 6	99.81 6	99.17 18	99.94 37	99.31 42	100.00 1	99.82 27

anonymousdsp		99.51 11	99.47 17	99.62 9	99.88 9	99.08 67	99.34 20	99.69 40	98.93 104	99.65 46	99.72 18	98.93 26	99.95 24	99.11 55	100.00 1	99.82 27

v7n		99.53 9	99.57 10	99.41 62	99.88 9	98.54 102	99.45 11	99.61 55	99.66 17	99.68 40	99.66 29	98.44 61	99.95 24	99.73 18	99.96 23	99.75 46

mvs_tets		99.63 5	99.67 5	99.49 51	99.88 9	98.61 94	99.34 20	99.71 36	99.27 58	99.90 12	99.74 15	99.68 4	99.97 5	99.55 30	99.99 5	99.88 17

test_fmvsmconf0.01_n		99.57 7	99.63 7	99.36 66	99.87 12	98.13 133	98.08 170	99.95 1	99.45 37	99.98 2	99.75 13	99.80 1	99.97 5	99.82 7	99.99 5	99.99 2

jajsoiax		99.58 6	99.61 8	99.48 53	99.87 12	98.61 94	99.28 37	99.66 48	99.09 86	99.89 15	99.68 22	99.53 7	99.97 5	99.50 34	99.99 5	99.87 18

test_djsdf		99.52 10	99.51 12	99.53 37	99.86 14	98.74 84	99.39 17	99.56 73	99.11 76	99.70 36	99.73 17	99.00 22	99.97 5	99.26 46	99.98 12	99.89 14

MIMVSNet1		99.38 24	99.32 31	99.55 27	99.86 14	99.19 41	99.41 14	99.59 57	99.59 27	99.71 34	99.57 45	97.12 163	99.90 68	99.21 51	99.87 76	99.54 113

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 25	99.85 16	99.11 63	99.90 1	99.78 29	99.63 21	99.78 27	99.67 27	99.48 9	99.81 187	99.30 43	99.97 19	99.77 37
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
UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 17	99.34 19	99.69 5	99.58 59	99.90 3	99.86 18	99.78 10	99.58 6	99.95 24	99.00 64	99.95 30	99.78 35

SixPastTwentyTwo		98.75 100	98.62 110	99.16 107	99.83 18	97.96 157	99.28 37	98.20 326	99.37 46	99.70 36	99.65 33	92.65 306	99.93 44	99.04 61	99.84 85	99.60 79

Baseline_NR-MVSNet		98.98 69	98.86 79	99.36 66	99.82 19	98.55 99	97.47 254	99.57 66	99.37 46	99.21 124	99.61 39	96.76 187	99.83 163	98.06 124	99.83 92	99.71 49

pm-mvs1		99.44 15	99.48 15	99.33 80	99.80 20	98.63 91	99.29 33	99.63 51	99.30 55	99.65 46	99.60 41	99.16 20	99.82 173	99.07 58	99.83 92	99.56 102

TransMVSNet (Re)		99.44 15	99.47 17	99.36 66	99.80 20	98.58 97	99.27 39	99.57 66	99.39 44	99.75 31	99.62 36	99.17 18	99.83 163	99.06 59	99.62 193	99.66 60

K. test v3		98.00 197	97.66 221	99.03 132	99.79 22	97.56 189	99.19 49	92.47 406	99.62 24	99.52 63	99.66 29	89.61 332	99.96 12	99.25 48	99.81 99	99.56 102

test_fmvsmconf0.1_n		99.49 12	99.54 11	99.34 75	99.78 23	98.11 134	97.77 216	99.90 11	99.33 51	99.97 3	99.66 29	99.71 3	99.96 12	99.79 12	99.99 5	99.96 7

APD_test1		98.83 87	98.66 104	99.34 75	99.78 23	99.47 9	98.42 136	99.45 114	98.28 150	98.98 154	99.19 124	97.76 116	99.58 317	96.57 231	99.55 220	98.97 277

test_vis3_rt		99.14 49	99.17 46	99.07 122	99.78 23	98.38 111	98.92 79	99.94 2	97.80 187	99.91 11	99.67 27	97.15 162	98.91 400	99.76 15	99.56 216	99.92 11

EGC-MVSNET		85.24 385	80.54 388	99.34 75	99.77 26	99.20 38	99.08 58	99.29 185	12.08 423	20.84 424	99.42 77	97.55 134	99.85 128	97.08 184	99.72 153	98.96 279

Anonymous20240521		98.69 111	98.87 76	98.16 248	99.77 26	95.11 290	99.08 58	99.44 118	99.34 50	99.33 100	99.55 52	94.10 282	99.94 37	99.25 48	99.96 23	99.42 168

FC-MVSNet-test		99.27 33	99.25 41	99.34 75	99.77 26	98.37 113	99.30 32	99.57 66	99.61 26	99.40 88	99.50 62	97.12 163	99.85 128	99.02 63	99.94 38	99.80 31

test_vis1_n		98.31 169	98.50 126	97.73 280	99.76 29	94.17 315	98.68 102	99.91 9	96.31 292	99.79 26	99.57 45	92.85 302	99.42 361	99.79 12	99.84 85	99.60 79

test_fmvs3		99.12 54	99.41 21	98.25 240	99.76 29	95.07 291	99.05 64	99.94 2	97.78 189	99.82 21	99.84 3	98.56 54	99.71 255	99.96 1	99.96 23	99.97 4

XXY-MVS		99.14 49	99.15 53	99.10 116	99.76 29	97.74 178	98.85 87	99.62 52	98.48 135	99.37 93	99.49 67	98.75 36	99.86 116	98.20 114	99.80 110	99.71 49

TDRefinement		99.42 20	99.38 24	99.55 27	99.76 29	99.33 20	99.68 6	99.71 36	99.38 45	99.53 61	99.61 39	98.64 44	99.80 194	98.24 111	99.84 85	99.52 124

fmvsm_s_conf0.1_n_a		99.17 44	99.30 35	98.80 163	99.75 33	96.59 242	97.97 192	99.86 15	98.22 153	99.88 17	99.71 19	98.59 50	99.84 146	99.73 18	99.98 12	99.98 3

tt0805		98.69 111	98.62 110	98.90 153	99.75 33	99.30 21	99.15 53	96.97 361	98.86 109	98.87 182	97.62 337	98.63 46	98.96 397	99.41 38	98.29 349	98.45 340

test_vis1_n_1920		98.40 156	98.92 71	96.81 336	99.74 35	90.76 387	98.15 160	99.91 9	98.33 141	99.89 15	99.55 52	95.07 253	99.88 91	99.76 15	99.93 43	99.79 32

FOURS1					99.73 36	99.67 3	99.43 12	99.54 81	99.43 41	99.26 116

PEN-MVS		99.41 21	99.34 28	99.62 9	99.73 36	99.14 56	99.29 33	99.54 81	99.62 24	99.56 53	99.42 77	98.16 88	99.96 12	98.78 78	99.93 43	99.77 37

lessismore_v0				98.97 140	99.73 36	97.53 191		86.71 420		99.37 93	99.52 61	89.93 330	99.92 53	98.99 65	99.72 153	99.44 161

SteuartSystems-ACMMP		98.79 93	98.54 121	99.54 30	99.73 36	99.16 47	98.23 150	99.31 169	97.92 178	98.90 173	98.90 197	98.00 99	99.88 91	96.15 263	99.72 153	99.58 91
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 187	98.15 178	98.22 243	99.73 36	95.15 287	97.36 260	99.68 45	94.45 346	98.99 153	99.27 106	96.87 177	99.94 37	97.13 181	99.91 61	99.57 96

Vis-MVSNet		99.34 26	99.36 25	99.27 90	99.73 36	98.26 120	99.17 50	99.78 29	99.11 76	99.27 112	99.48 68	98.82 31	99.95 24	98.94 68	99.93 43	99.59 85
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
SSC-MVS		98.71 104	98.74 88	98.62 191	99.72 42	96.08 258	98.74 92	98.64 306	99.74 10	99.67 42	99.24 115	94.57 268	99.95 24	99.11 55	99.24 274	99.82 27

test_f		98.67 119	98.87 76	98.05 257	99.72 42	95.59 268	98.51 123	99.81 25	96.30 294	99.78 27	99.82 5	96.14 213	98.63 406	99.82 7	99.93 43	99.95 8

ACMH	96.65 7	99.25 36	99.24 42	99.26 92	99.72 42	98.38 111	99.07 61	99.55 77	98.30 145	99.65 46	99.45 74	99.22 15	99.76 230	98.44 102	99.77 126	99.64 66
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
fmvsm_s_conf0.1_n		99.16 47	99.33 29	98.64 186	99.71 45	96.10 253	97.87 204	99.85 17	98.56 131	99.90 12	99.68 22	98.69 41	99.85 128	99.72 20	99.98 12	99.97 4

PS-CasMVS		99.40 22	99.33 29	99.62 9	99.71 45	99.10 64	99.29 33	99.53 84	99.53 31	99.46 75	99.41 81	98.23 77	99.95 24	98.89 72	99.95 30	99.81 30

DTE-MVSNet		99.43 19	99.35 26	99.66 7	99.71 45	99.30 21	99.31 27	99.51 88	99.64 19	99.56 53	99.46 70	98.23 77	99.97 5	98.78 78	99.93 43	99.72 48

WR-MVS_H		99.33 27	99.22 43	99.65 8	99.71 45	99.24 29	99.32 23	99.55 77	99.46 36	99.50 69	99.34 93	97.30 152	99.93 44	98.90 70	99.93 43	99.77 37

HPM-MVS_fast		99.01 64	98.82 82	99.57 20	99.71 45	99.35 16	99.00 69	99.50 90	97.33 231	98.94 169	98.86 207	98.75 36	99.82 173	97.53 159	99.71 158	99.56 102

ACMH+	96.62 9	99.08 61	99.00 64	99.33 80	99.71 45	98.83 79	98.60 109	99.58 59	99.11 76	99.53 61	99.18 128	98.81 32	99.67 275	96.71 221	99.77 126	99.50 130

PMVS	91.26 20	97.86 210	97.94 200	97.65 284	99.71 45	97.94 159	98.52 118	98.68 302	98.99 97	97.52 307	99.35 89	97.41 147	98.18 411	91.59 376	99.67 179	96.82 400
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FIs		99.14 49	99.09 57	99.29 86	99.70 52	98.28 119	99.13 55	99.52 87	99.48 33	99.24 121	99.41 81	96.79 184	99.82 173	98.69 88	99.88 73	99.76 42

VPNet		98.87 82	98.83 81	99.01 135	99.70 52	97.62 187	98.43 134	99.35 151	99.47 35	99.28 110	99.05 158	96.72 190	99.82 173	98.09 121	99.36 254	99.59 85

test_cas_vis1_n_1920		98.33 166	98.68 101	97.27 313	99.69 54	92.29 362	98.03 178	99.85 17	97.62 198	99.96 4	99.62 36	93.98 283	99.74 242	99.52 33	99.86 80	99.79 32

MP-MVS-pluss		98.57 133	98.23 168	99.60 14	99.69 54	99.35 16	97.16 278	99.38 138	94.87 336	98.97 158	98.99 176	98.01 98	99.88 91	97.29 169	99.70 165	99.58 91
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 40	99.32 31	98.96 141	99.68 56	97.35 200	98.84 89	99.48 99	99.69 13	99.63 49	99.68 22	99.03 21	99.96 12	97.97 131	99.92 54	99.57 96

sd_testset		99.28 32	99.31 33	99.19 103	99.68 56	98.06 146	99.41 14	99.30 177	99.69 13	99.63 49	99.68 22	99.25 14	99.96 12	97.25 172	99.92 54	99.57 96

test_fmvs1_n		98.09 191	98.28 160	97.52 299	99.68 56	93.47 341	98.63 105	99.93 5	95.41 325	99.68 40	99.64 34	91.88 315	99.48 349	99.82 7	99.87 76	99.62 70

CHOSEN 1792x2688		97.49 239	97.14 254	98.54 209	99.68 56	96.09 256	96.50 310	99.62 52	91.58 384	98.84 185	98.97 182	92.36 308	99.88 91	96.76 214	99.95 30	99.67 59

tfpnnormal		98.90 79	98.90 73	98.91 150	99.67 60	97.82 170	99.00 69	99.44 118	99.45 37	99.51 68	99.24 115	98.20 83	99.86 116	95.92 272	99.69 168	99.04 264

MTAPA		98.88 81	98.64 107	99.61 12	99.67 60	99.36 15	98.43 134	99.20 208	98.83 113	98.89 175	98.90 197	96.98 173	99.92 53	97.16 176	99.70 165	99.56 102

test_fmvsmvis_n_1920		99.26 35	99.49 13	98.54 209	99.66 62	96.97 222	98.00 184	99.85 17	99.24 60	99.92 8	99.50 62	99.39 11	99.95 24	99.89 3	99.98 12	98.71 317

mvs5depth		99.30 29	99.59 9	98.44 222	99.65 63	95.35 279	99.82 3	99.94 2	99.83 4	99.42 83	99.94 2	98.13 91	99.96 12	99.63 24	99.96 23	100.00 1

fmvsm_l_conf0.5_n_a		99.19 43	99.27 38	98.94 144	99.65 63	97.05 218	97.80 212	99.76 31	98.70 117	99.78 27	99.11 144	98.79 34	99.95 24	99.85 5	99.96 23	99.83 24

WB-MVS		98.52 145	98.55 119	98.43 223	99.65 63	95.59 268	98.52 118	98.77 292	99.65 18	99.52 63	99.00 175	94.34 274	99.93 44	98.65 90	98.83 321	99.76 42

CP-MVSNet		99.21 41	99.09 57	99.56 25	99.65 63	98.96 74	99.13 55	99.34 157	99.42 42	99.33 100	99.26 110	97.01 171	99.94 37	98.74 83	99.93 43	99.79 32

HPM-MVS		98.79 93	98.53 122	99.59 18	99.65 63	99.29 23	99.16 51	99.43 124	96.74 274	98.61 215	98.38 283	98.62 47	99.87 108	96.47 243	99.67 179	99.59 85
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 128	98.36 150	99.42 60	99.65 63	99.42 11	98.55 114	99.57 66	97.72 192	98.90 173	99.26 110	96.12 215	99.52 337	95.72 283	99.71 158	99.32 210

fmvsm_l_conf0.5_n		99.21 41	99.28 37	99.02 134	99.64 69	97.28 204	97.82 209	99.76 31	98.73 114	99.82 21	99.09 150	98.81 32	99.95 24	99.86 4	99.96 23	99.83 24

test_fmvsmconf_n		99.44 15	99.48 15	99.31 85	99.64 69	98.10 136	97.68 227	99.84 20	99.29 56	99.92 8	99.57 45	99.60 5	99.96 12	99.74 17	99.98 12	99.89 14

TSAR-MVS + MP.		98.63 125	98.49 130	99.06 128	99.64 69	97.90 161	98.51 123	98.94 257	96.96 261	99.24 121	98.89 203	97.83 109	99.81 187	96.88 204	99.49 239	99.48 144
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 89	98.72 92	99.12 112	99.64 69	98.54 102	97.98 189	99.68 45	97.62 198	99.34 99	99.18 128	97.54 135	99.77 224	97.79 142	99.74 142	99.04 264

KD-MVS_self_test		99.25 36	99.18 45	99.44 59	99.63 73	99.06 68	98.69 101	99.54 81	99.31 53	99.62 52	99.53 58	97.36 150	99.86 116	99.24 50	99.71 158	99.39 181

EU-MVSNet		97.66 227	98.50 126	95.13 378	99.63 73	85.84 408	98.35 142	98.21 325	98.23 152	99.54 57	99.46 70	95.02 254	99.68 272	98.24 111	99.87 76	99.87 18

HyFIR lowres test		97.19 265	96.60 289	98.96 141	99.62 75	97.28 204	95.17 372	99.50 90	94.21 351	99.01 151	98.32 291	86.61 350	99.99 2	97.10 183	99.84 85	99.60 79

mmtdpeth		99.30 29	99.42 20	98.92 149	99.58 76	96.89 229	99.48 10	99.92 7	99.92 2	98.26 252	99.80 9	98.33 70	99.91 62	99.56 29	99.95 30	99.97 4

ACMMP_NAP		98.75 100	98.48 131	99.57 20	99.58 76	99.29 23	97.82 209	99.25 197	96.94 263	98.78 192	99.12 143	98.02 97	99.84 146	97.13 181	99.67 179	99.59 85

nrg030		99.40 22	99.35 26	99.54 30	99.58 76	99.13 59	98.98 72	99.48 99	99.68 15	99.46 75	99.26 110	98.62 47	99.73 247	99.17 54	99.92 54	99.76 42

VDDNet		98.21 182	97.95 198	99.01 135	99.58 76	97.74 178	99.01 67	97.29 352	99.67 16	98.97 158	99.50 62	90.45 327	99.80 194	97.88 137	99.20 282	99.48 144

COLMAP_ROB	96.50 10	98.99 66	98.85 80	99.41 62	99.58 76	99.10 64	98.74 92	99.56 73	99.09 86	99.33 100	99.19 124	98.40 63	99.72 254	95.98 270	99.76 138	99.42 168
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvsm_n_1920		99.33 27	99.45 19	98.99 137	99.57 81	97.73 180	97.93 193	99.83 22	99.22 61	99.93 6	99.30 101	99.42 10	99.96 12	99.85 5	99.99 5	99.29 219

ZNCC-MVS		98.68 116	98.40 143	99.54 30	99.57 81	99.21 32	98.46 131	99.29 185	97.28 237	98.11 264	98.39 281	98.00 99	99.87 108	96.86 207	99.64 187	99.55 109

MSP-MVS		98.40 156	98.00 193	99.61 12	99.57 81	99.25 28	98.57 112	99.35 151	97.55 208	99.31 108	97.71 330	94.61 267	99.88 91	96.14 264	99.19 285	99.70 54
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
testgi		98.32 167	98.39 146	98.13 249	99.57 81	95.54 271	97.78 214	99.49 97	97.37 228	99.19 126	97.65 334	98.96 24	99.49 346	96.50 242	98.99 310	99.34 203

MP-MVS		98.46 150	98.09 183	99.54 30	99.57 81	99.22 31	98.50 125	99.19 212	97.61 201	97.58 301	98.66 244	97.40 148	99.88 91	94.72 309	99.60 200	99.54 113
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 104	98.46 135	99.47 56	99.57 81	98.97 70	98.23 150	99.48 99	96.60 279	99.10 136	99.06 151	98.71 39	99.83 163	95.58 290	99.78 120	99.62 70

LGP-MVS_train				99.47 56	99.57 81	98.97 70		99.48 99	96.60 279	99.10 136	99.06 151	98.71 39	99.83 163	95.58 290	99.78 120	99.62 70

IS-MVSNet		98.19 184	97.90 204	99.08 120	99.57 81	97.97 154	99.31 27	98.32 321	99.01 96	98.98 154	99.03 162	91.59 317	99.79 207	95.49 292	99.80 110	99.48 144

dcpmvs_2		98.78 95	99.11 54	97.78 271	99.56 89	93.67 337	99.06 62	99.86 15	99.50 32	99.66 43	99.26 110	97.21 160	99.99 2	98.00 129	99.91 61	99.68 56

test_0402		98.76 99	98.71 95	98.93 146	99.56 89	98.14 132	98.45 133	99.34 157	99.28 57	98.95 162	98.91 194	98.34 69	99.79 207	95.63 287	99.91 61	98.86 296

EPP-MVSNet		98.30 170	98.04 189	99.07 122	99.56 89	97.83 167	99.29 33	98.07 332	99.03 94	98.59 219	99.13 142	92.16 311	99.90 68	96.87 205	99.68 173	99.49 134

ACMMP		98.75 100	98.50 126	99.52 42	99.56 89	99.16 47	98.87 84	99.37 142	97.16 252	98.82 189	99.01 172	97.71 119	99.87 108	96.29 255	99.69 168	99.54 113
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
fmvsm_s_conf0.5_n_a		99.10 56	99.20 44	98.78 169	99.55 93	96.59 242	97.79 213	99.82 24	98.21 154	99.81 24	99.53 58	98.46 60	99.84 146	99.70 21	99.97 19	99.90 13

fmvsm_s_conf0.5_n		99.09 57	99.26 40	98.61 194	99.55 93	96.09 256	97.74 221	99.81 25	98.55 132	99.85 19	99.55 52	98.60 49	99.84 146	99.69 23	99.98 12	99.89 14

FMVSNet1		99.17 44	99.17 46	99.17 104	99.55 93	98.24 122	99.20 45	99.44 118	99.21 63	99.43 80	99.55 52	97.82 112	99.86 116	98.42 104	99.89 71	99.41 171

Vis-MVSNet (Re-imp)		97.46 241	97.16 251	98.34 233	99.55 93	96.10 253	98.94 77	98.44 315	98.32 143	98.16 258	98.62 253	88.76 337	99.73 247	93.88 335	99.79 115	99.18 244

ACMM	96.08 12	98.91 77	98.73 90	99.48 53	99.55 93	99.14 56	98.07 172	99.37 142	97.62 198	99.04 147	98.96 185	98.84 30	99.79 207	97.43 163	99.65 185	99.49 134
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 108	98.97 68	97.89 264	99.54 98	94.05 318	98.55 114	99.92 7	96.78 272	99.72 32	99.78 10	96.60 195	99.67 275	99.91 2	99.90 67	99.94 9

mPP-MVS		98.64 123	98.34 153	99.54 30	99.54 98	99.17 43	98.63 105	99.24 202	97.47 215	98.09 266	98.68 239	97.62 128	99.89 79	96.22 258	99.62 193	99.57 96

XVG-ACMP-BASELINE		98.56 134	98.34 153	99.22 100	99.54 98	98.59 96	97.71 224	99.46 110	97.25 240	98.98 154	98.99 176	97.54 135	99.84 146	95.88 273	99.74 142	99.23 231

region2R		98.69 111	98.40 143	99.54 30	99.53 101	99.17 43	98.52 118	99.31 169	97.46 220	98.44 237	98.51 267	97.83 109	99.88 91	96.46 244	99.58 209	99.58 91

PGM-MVS		98.66 120	98.37 149	99.55 27	99.53 101	99.18 42	98.23 150	99.49 97	97.01 260	98.69 203	98.88 204	98.00 99	99.89 79	95.87 276	99.59 204	99.58 91

Patchmatch-RL test		97.26 258	97.02 259	97.99 261	99.52 103	95.53 272	96.13 333	99.71 36	97.47 215	99.27 112	99.16 134	84.30 371	99.62 300	97.89 134	99.77 126	98.81 303

ACMMPR		98.70 108	98.42 141	99.54 30	99.52 103	99.14 56	98.52 118	99.31 169	97.47 215	98.56 224	98.54 262	97.75 117	99.88 91	96.57 231	99.59 204	99.58 91

GST-MVS		98.61 129	98.30 158	99.52 42	99.51 105	99.20 38	98.26 148	99.25 197	97.44 223	98.67 206	98.39 281	97.68 120	99.85 128	96.00 268	99.51 231	99.52 124

Anonymous20231206		98.21 182	98.21 169	98.20 244	99.51 105	95.43 277	98.13 162	99.32 164	96.16 297	98.93 170	98.82 216	96.00 220	99.83 163	97.32 168	99.73 145	99.36 197

ACMP	95.32 15	98.41 154	98.09 183	99.36 66	99.51 105	98.79 82	97.68 227	99.38 138	95.76 312	98.81 191	98.82 216	98.36 65	99.82 173	94.75 306	99.77 126	99.48 144
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DVP-MVS		98.77 98	98.52 123	99.52 42	99.50 108	99.21 32	98.02 180	98.84 281	97.97 172	99.08 138	99.02 163	97.61 129	99.88 91	96.99 191	99.63 190	99.48 144
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_SECOND				99.60 14	99.50 108	99.23 30	98.02 180	99.32 164					99.88 91	96.99 191	99.63 190	99.68 56

test0726					99.50 108	99.21 32	98.17 158	99.35 151	97.97 172	99.26 116	99.06 151	97.61 129

AllTest		98.44 152	98.20 170	99.16 107	99.50 108	98.55 99	98.25 149	99.58 59	96.80 270	98.88 178	99.06 151	97.65 123	99.57 319	94.45 316	99.61 198	99.37 190

TestCases				99.16 107	99.50 108	98.55 99		99.58 59	96.80 270	98.88 178	99.06 151	97.65 123	99.57 319	94.45 316	99.61 198	99.37 190

XVG-OURS		98.53 142	98.34 153	99.11 114	99.50 108	98.82 81	95.97 339	99.50 90	97.30 235	99.05 145	98.98 180	99.35 12	99.32 375	95.72 283	99.68 173	99.18 244

EG-PatchMatch MVS		98.99 66	99.01 63	98.94 144	99.50 108	97.47 193	98.04 177	99.59 57	98.15 165	99.40 88	99.36 88	98.58 53	99.76 230	98.78 78	99.68 173	99.59 85

SED-MVS		98.91 77	98.72 92	99.49 51	99.49 115	99.17 43	98.10 168	99.31 169	98.03 168	99.66 43	99.02 163	98.36 65	99.88 91	96.91 197	99.62 193	99.41 171

IU-MVS					99.49 115	99.15 51		98.87 272	92.97 369	99.41 85				96.76 214	99.62 193	99.66 60

test_241102_ONE					99.49 115	99.17 43		99.31 169	97.98 171	99.66 43	98.90 197	98.36 65	99.48 349

UA-Net		99.47 13	99.40 22	99.70 2	99.49 115	99.29 23	99.80 4	99.72 35	99.82 5	99.04 147	99.81 6	98.05 96	99.96 12	98.85 74	99.99 5	99.86 21

HFP-MVS		98.71 104	98.44 138	99.51 46	99.49 115	99.16 47	98.52 118	99.31 169	97.47 215	98.58 221	98.50 271	97.97 103	99.85 128	96.57 231	99.59 204	99.53 121

VPA-MVSNet		99.30 29	99.30 35	99.28 87	99.49 115	98.36 116	99.00 69	99.45 114	99.63 21	99.52 63	99.44 75	98.25 75	99.88 91	99.09 57	99.84 85	99.62 70

XVG-OURS-SEG-HR		98.49 147	98.28 160	99.14 110	99.49 115	98.83 79	96.54 307	99.48 99	97.32 233	99.11 133	98.61 255	99.33 13	99.30 378	96.23 257	98.38 345	99.28 221

114514_t		96.50 298	95.77 306	98.69 182	99.48 122	97.43 197	97.84 208	99.55 77	81.42 416	96.51 358	98.58 259	95.53 240	99.67 275	93.41 348	99.58 209	98.98 274

IterMVS-LS		98.55 138	98.70 98	98.09 250	99.48 122	94.73 299	97.22 273	99.39 136	98.97 100	99.38 91	99.31 100	96.00 220	99.93 44	98.58 93	99.97 19	99.60 79
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v8		99.01 64	99.16 48	98.57 201	99.47 124	96.31 250	98.90 80	99.47 107	99.03 94	99.52 63	99.57 45	96.93 174	99.81 187	99.60 25	99.98 12	99.60 79

XVS		98.72 103	98.45 136	99.53 37	99.46 125	99.21 32	98.65 103	99.34 157	98.62 122	97.54 305	98.63 251	97.50 141	99.83 163	96.79 210	99.53 226	99.56 102

X-MVStestdata		94.32 346	92.59 364	99.53 37	99.46 125	99.21 32	98.65 103	99.34 157	98.62 122	97.54 305	45.85 421	97.50 141	99.83 163	96.79 210	99.53 226	99.56 102

test20.03		98.78 95	98.77 87	98.78 169	99.46 125	97.20 211	97.78 214	99.24 202	99.04 93	99.41 85	98.90 197	97.65 123	99.76 230	97.70 149	99.79 115	99.39 181

CSCG		98.68 116	98.50 126	99.20 101	99.45 128	98.63 91	98.56 113	99.57 66	97.87 182	98.85 183	98.04 312	97.66 122	99.84 146	96.72 219	99.81 99	99.13 253

GeoE		99.05 62	98.99 66	99.25 95	99.44 129	98.35 117	98.73 96	99.56 73	98.42 137	98.91 172	98.81 218	98.94 25	99.91 62	98.35 106	99.73 145	99.49 134

v148		98.45 151	98.60 115	98.00 260	99.44 129	94.98 292	97.44 256	99.06 238	98.30 145	99.32 106	98.97 182	96.65 193	99.62 300	98.37 105	99.85 81	99.39 181

v10		98.97 70	99.11 54	98.55 206	99.44 129	96.21 252	98.90 80	99.55 77	98.73 114	99.48 70	99.60 41	96.63 194	99.83 163	99.70 21	99.99 5	99.61 78

V42		98.78 95	98.78 86	98.76 173	99.44 129	97.04 219	98.27 147	99.19 212	97.87 182	99.25 120	99.16 134	96.84 178	99.78 218	99.21 51	99.84 85	99.46 153

MDA-MVSNet-bldmvs		97.94 201	97.91 203	98.06 255	99.44 129	94.96 293	96.63 305	99.15 228	98.35 139	98.83 186	99.11 144	94.31 275	99.85 128	96.60 228	98.72 327	99.37 190

casdiffmvs_mvg		99.12 54	99.16 48	98.99 137	99.43 134	97.73 180	98.00 184	99.62 52	99.22 61	99.55 56	99.22 120	98.93 26	99.75 237	98.66 89	99.81 99	99.50 130
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test1111		96.49 299	96.82 273	95.52 371	99.42 135	87.08 405	99.22 42	87.14 419	99.11 76	99.46 75	99.58 43	88.69 338	99.86 116	98.80 76	99.95 30	99.62 70

v2v482		98.56 134	98.62 110	98.37 230	99.42 135	95.81 265	97.58 242	99.16 223	97.90 180	99.28 110	99.01 172	95.98 225	99.79 207	99.33 41	99.90 67	99.51 127

OPM-MVS		98.56 134	98.32 157	99.25 95	99.41 137	98.73 87	97.13 280	99.18 216	97.10 255	98.75 198	98.92 193	98.18 84	99.65 291	96.68 223	99.56 216	99.37 190
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 193	98.08 186	98.04 258	99.41 137	94.59 305	94.59 390	99.40 134	97.50 212	98.82 189	98.83 213	96.83 180	99.84 146	97.50 161	99.81 99	99.71 49

test_one_0601					99.39 139	99.20 38		99.31 169	98.49 134	98.66 208	99.02 163	97.64 126

mvsany_test3		98.87 82	98.92 71	98.74 179	99.38 140	96.94 226	98.58 111	99.10 233	96.49 284	99.96 4	99.81 6	98.18 84	99.45 356	98.97 66	99.79 115	99.83 24

patch_mono-2		98.51 146	98.63 108	98.17 246	99.38 140	94.78 296	97.36 260	99.69 40	98.16 164	98.49 233	99.29 103	97.06 166	99.97 5	98.29 110	99.91 61	99.76 42

test2506		92.39 375	91.89 377	93.89 391	99.38 140	82.28 421	99.32 23	66.03 427	99.08 88	98.77 195	99.57 45	66.26 417	99.84 146	98.71 86	99.95 30	99.54 113

ECVR-MVS		96.42 301	96.61 287	95.85 363	99.38 140	88.18 401	99.22 42	86.00 421	99.08 88	99.36 95	99.57 45	88.47 343	99.82 173	98.52 99	99.95 30	99.54 113

casdiffmvs		98.95 73	99.00 64	98.81 161	99.38 140	97.33 201	97.82 209	99.57 66	99.17 72	99.35 97	99.17 132	98.35 68	99.69 263	98.46 101	99.73 145	99.41 171
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		98.96 72	99.02 62	98.76 173	99.38 140	97.26 206	98.49 126	99.50 90	98.86 109	99.19 126	99.06 151	98.23 77	99.69 263	98.71 86	99.76 138	99.33 208

TranMVSNet+NR-MVSNet		99.17 44	99.07 60	99.46 58	99.37 146	98.87 77	98.39 138	99.42 127	99.42 42	99.36 95	99.06 151	98.38 64	99.95 24	98.34 107	99.90 67	99.57 96

tttt0517		95.64 325	94.98 335	97.64 286	99.36 147	93.81 332	98.72 97	90.47 414	98.08 167	98.67 206	98.34 288	73.88 404	99.92 53	97.77 144	99.51 231	99.20 236

test_part2					99.36 147	99.10 64				99.05 145

v1144		98.60 130	98.66 104	98.41 225	99.36 147	95.90 261	97.58 242	99.34 157	97.51 211	99.27 112	99.15 138	96.34 208	99.80 194	99.47 36	99.93 43	99.51 127

CP-MVS		98.70 108	98.42 141	99.52 42	99.36 147	99.12 61	98.72 97	99.36 146	97.54 209	98.30 246	98.40 280	97.86 108	99.89 79	96.53 240	99.72 153	99.56 102

Test_1112_low_res		96.99 280	96.55 291	98.31 236	99.35 151	95.47 275	95.84 351	99.53 84	91.51 386	96.80 347	98.48 274	91.36 319	99.83 163	96.58 229	99.53 226	99.62 70

DeepC-MVS	97.60 4	98.97 70	98.93 70	99.10 116	99.35 151	97.98 153	98.01 183	99.46 110	97.56 206	99.54 57	99.50 62	98.97 23	99.84 146	98.06 124	99.92 54	99.49 134
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 257	96.86 269	98.58 198	99.34 153	96.32 249	96.75 299	99.58 59	93.14 367	96.89 342	97.48 344	92.11 312	99.86 116	96.91 197	99.54 222	99.57 96

reproduce_model		99.15 48	98.97 68	99.67 4	99.33 154	99.44 10	98.15 160	99.47 107	99.12 75	99.52 63	99.32 99	98.31 71	99.90 68	97.78 143	99.73 145	99.66 60

MVSMamba_PlusPlus		98.83 87	98.98 67	98.36 231	99.32 155	96.58 244	98.90 80	99.41 131	99.75 8	98.72 201	99.50 62	96.17 212	99.94 37	99.27 45	99.78 120	98.57 333

SF-MVS		98.53 142	98.27 163	99.32 82	99.31 156	98.75 83	98.19 154	99.41 131	96.77 273	98.83 186	98.90 197	97.80 114	99.82 173	95.68 286	99.52 229	99.38 188

CPTT-MVS		97.84 216	97.36 240	99.27 90	99.31 156	98.46 107	98.29 145	99.27 191	94.90 335	97.83 285	98.37 284	94.90 256	99.84 146	93.85 337	99.54 222	99.51 127

UnsupCasMVSNet_eth		97.89 205	97.60 226	98.75 175	99.31 156	97.17 214	97.62 236	99.35 151	98.72 116	98.76 197	98.68 239	92.57 307	99.74 242	97.76 148	95.60 405	99.34 203

pmmvs-eth3d		98.47 149	98.34 153	98.86 155	99.30 159	97.76 176	97.16 278	99.28 188	95.54 318	99.42 83	99.19 124	97.27 155	99.63 297	97.89 134	99.97 19	99.20 236

mamv4		99.44 15	99.39 23	99.58 19	99.30 159	99.74 2	99.04 65	99.81 25	99.77 7	99.82 21	99.57 45	97.82 112	99.98 4	99.53 31	99.89 71	99.01 268

Anonymous20231211		99.27 33	99.27 38	99.26 92	99.29 161	98.18 128	99.49 9	99.51 88	99.70 12	99.80 25	99.68 22	96.84 178	99.83 163	99.21 51	99.91 61	99.77 37

UnsupCasMVSNet_bld		97.30 255	96.92 265	98.45 220	99.28 162	96.78 236	96.20 328	99.27 191	95.42 322	98.28 250	98.30 292	93.16 293	99.71 255	94.99 300	97.37 381	98.87 295

EC-MVSNet		99.09 57	99.05 61	99.20 101	99.28 162	98.93 75	99.24 41	99.84 20	99.08 88	98.12 263	98.37 284	98.72 38	99.90 68	99.05 60	99.77 126	98.77 311

reproduce-ours		99.09 57	98.90 73	99.67 4	99.27 164	99.49 6	98.00 184	99.42 127	99.05 91	99.48 70	99.27 106	98.29 73	99.89 79	97.61 153	99.71 158	99.62 70

our_new_method		99.09 57	98.90 73	99.67 4	99.27 164	99.49 6	98.00 184	99.42 127	99.05 91	99.48 70	99.27 106	98.29 73	99.89 79	97.61 153	99.71 158	99.62 70

DPE-MVS		98.59 132	98.26 164	99.57 20	99.27 164	99.15 51	97.01 283	99.39 136	97.67 194	99.44 79	98.99 176	97.53 137	99.89 79	95.40 294	99.68 173	99.66 60
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 215	98.18 173	96.87 332	99.27 164	91.16 381	95.53 360	99.25 197	99.10 83	99.41 85	99.35 89	93.10 295	99.96 12	98.65 90	99.94 38	99.49 134

v1192		98.60 130	98.66 104	98.41 225	99.27 164	95.88 262	97.52 248	99.36 146	97.41 224	99.33 100	99.20 123	96.37 206	99.82 173	99.57 27	99.92 54	99.55 109

N_pmnet		97.63 229	97.17 250	98.99 137	99.27 164	97.86 164	95.98 338	93.41 403	95.25 327	99.47 74	98.90 197	95.63 237	99.85 128	96.91 197	99.73 145	99.27 222

FPMVS		93.44 362	92.23 368	97.08 321	99.25 170	97.86 164	95.61 357	97.16 356	92.90 371	93.76 405	98.65 246	75.94 402	95.66 418	79.30 418	97.49 374	97.73 382

new-patchmatchnet		98.35 162	98.74 88	97.18 316	99.24 171	92.23 364	96.42 315	99.48 99	98.30 145	99.69 38	99.53 58	97.44 146	99.82 173	98.84 75	99.77 126	99.49 134

MCST-MVS		98.00 197	97.63 224	99.10 116	99.24 171	98.17 129	96.89 292	98.73 299	95.66 313	97.92 276	97.70 332	97.17 161	99.66 286	96.18 262	99.23 277	99.47 151

UniMVSNet (Re)		98.87 82	98.71 95	99.35 72	99.24 171	98.73 87	97.73 223	99.38 138	98.93 104	99.12 132	98.73 230	96.77 185	99.86 116	98.63 92	99.80 110	99.46 153

jason		97.45 243	97.35 241	97.76 275	99.24 171	93.93 326	95.86 348	98.42 317	94.24 350	98.50 232	98.13 302	94.82 260	99.91 62	97.22 173	99.73 145	99.43 165
jason: jason.
IterMVS		97.73 221	98.11 182	96.57 342	99.24 171	90.28 390	95.52 362	99.21 206	98.86 109	99.33 100	99.33 95	93.11 294	99.94 37	98.49 100	99.94 38	99.48 144
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 138	98.62 110	98.32 234	99.22 176	95.58 270	97.51 250	99.45 114	97.16 252	99.45 78	99.24 115	96.12 215	99.85 128	99.60 25	99.88 73	99.55 109

ITE_SJBPF				98.87 154	99.22 176	98.48 106		99.35 151	97.50 212	98.28 250	98.60 257	97.64 126	99.35 371	93.86 336	99.27 269	98.79 309

h-mvs33		97.77 219	97.33 243	99.10 116	99.21 178	97.84 166	98.35 142	98.57 309	99.11 76	98.58 221	99.02 163	88.65 341	99.96 12	98.11 119	96.34 397	99.49 134

v144192		98.54 140	98.57 118	98.45 220	99.21 178	95.98 259	97.63 235	99.36 146	97.15 254	99.32 106	99.18 128	95.84 232	99.84 146	99.50 34	99.91 61	99.54 113

APDe-MVS		98.99 66	98.79 85	99.60 14	99.21 178	99.15 51	98.87 84	99.48 99	97.57 204	99.35 97	99.24 115	97.83 109	99.89 79	97.88 137	99.70 165	99.75 46
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 75	98.81 84	99.28 87	99.21 178	98.45 108	98.46 131	99.33 162	99.63 21	99.48 70	99.15 138	97.23 158	99.75 237	97.17 175	99.66 184	99.63 69

SR-MVS-dyc-post		98.81 91	98.55 119	99.57 20	99.20 182	99.38 12	98.48 129	99.30 177	98.64 118	98.95 162	98.96 185	97.49 144	99.86 116	96.56 235	99.39 250	99.45 157

RE-MVS-def			98.58 117		99.20 182	99.38 12	98.48 129	99.30 177	98.64 118	98.95 162	98.96 185	97.75 117		96.56 235	99.39 250	99.45 157

v1921920		98.54 140	98.60 115	98.38 228	99.20 182	95.76 267	97.56 244	99.36 146	97.23 246	99.38 91	99.17 132	96.02 218	99.84 146	99.57 27	99.90 67	99.54 113

thisisatest0530		95.27 332	94.45 343	97.74 278	99.19 185	94.37 309	97.86 205	90.20 415	97.17 251	98.22 253	97.65 334	73.53 405	99.90 68	96.90 202	99.35 256	98.95 280

Anonymous20240529		98.93 75	98.87 76	99.12 112	99.19 185	98.22 127	99.01 67	98.99 255	99.25 59	99.54 57	99.37 84	97.04 167	99.80 194	97.89 134	99.52 229	99.35 201

APD-MVS_3200maxsize		98.84 86	98.61 114	99.53 37	99.19 185	99.27 26	98.49 126	99.33 162	98.64 118	99.03 150	98.98 180	97.89 106	99.85 128	96.54 239	99.42 247	99.46 153

HQP_MVS		97.99 200	97.67 218	98.93 146	99.19 185	97.65 184	97.77 216	99.27 191	98.20 158	97.79 288	97.98 315	94.90 256	99.70 259	94.42 318	99.51 231	99.45 157

plane_prior7					99.19 185	97.87 163

ab-mvs		98.41 154	98.36 150	98.59 197	99.19 185	97.23 207	99.32 23	98.81 286	97.66 195	98.62 213	99.40 83	96.82 181	99.80 194	95.88 273	99.51 231	98.75 314

F-COLMAP		97.30 255	96.68 282	99.14 110	99.19 185	98.39 110	97.27 269	99.30 177	92.93 370	96.62 353	98.00 313	95.73 235	99.68 272	92.62 364	98.46 344	99.35 201

SR-MVS		98.71 104	98.43 139	99.57 20	99.18 192	99.35 16	98.36 141	99.29 185	98.29 148	98.88 178	98.85 210	97.53 137	99.87 108	96.14 264	99.31 262	99.48 144

UniMVSNet_NR-MVSNet		98.86 85	98.68 101	99.40 64	99.17 193	98.74 84	97.68 227	99.40 134	99.14 74	99.06 140	98.59 258	96.71 191	99.93 44	98.57 95	99.77 126	99.53 121

LF4IMVS		97.90 203	97.69 217	98.52 211	99.17 193	97.66 183	97.19 277	99.47 107	96.31 292	97.85 284	98.20 299	96.71 191	99.52 337	94.62 310	99.72 153	98.38 350

SMA-MVS		98.40 156	98.03 190	99.51 46	99.16 195	99.21 32	98.05 175	99.22 205	94.16 352	98.98 154	99.10 147	97.52 139	99.79 207	96.45 245	99.64 187	99.53 121
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
DU-MVS		98.82 89	98.63 108	99.39 65	99.16 195	98.74 84	97.54 246	99.25 197	98.84 112	99.06 140	98.76 227	96.76 187	99.93 44	98.57 95	99.77 126	99.50 130

NR-MVSNet		98.95 73	98.82 82	99.36 66	99.16 195	98.72 89	99.22 42	99.20 208	99.10 83	99.72 32	98.76 227	96.38 205	99.86 116	98.00 129	99.82 95	99.50 130

MVS_111021_LR		98.30 170	98.12 181	98.83 158	99.16 195	98.03 148	96.09 335	99.30 177	97.58 203	98.10 265	98.24 295	98.25 75	99.34 372	96.69 222	99.65 185	99.12 254

DSMNet-mixed		97.42 246	97.60 226	96.87 332	99.15 199	91.46 371	98.54 116	99.12 230	92.87 372	97.58 301	99.63 35	96.21 211	99.90 68	95.74 282	99.54 222	99.27 222

D2MVS		97.84 216	97.84 208	97.83 267	99.14 200	94.74 298	96.94 287	98.88 270	95.84 310	98.89 175	98.96 185	94.40 272	99.69 263	97.55 156	99.95 30	99.05 260

pmmvs5		97.64 228	97.49 232	98.08 253	99.14 200	95.12 289	96.70 302	99.05 241	93.77 359	98.62 213	98.83 213	93.23 291	99.75 237	98.33 109	99.76 138	99.36 197

SPE-MVS-test		99.13 52	99.09 57	99.26 92	99.13 202	98.97 70	99.31 27	99.88 13	99.44 39	98.16 258	98.51 267	98.64 44	99.93 44	98.91 69	99.85 81	98.88 294

VDD-MVS		98.56 134	98.39 146	99.07 122	99.13 202	98.07 143	98.59 110	97.01 359	99.59 27	99.11 133	99.27 106	94.82 260	99.79 207	98.34 107	99.63 190	99.34 203

save fliter					99.11 204	97.97 154	96.53 309	99.02 249	98.24 151

APD-MVS		98.10 189	97.67 218	99.42 60	99.11 204	98.93 75	97.76 219	99.28 188	94.97 333	98.72 201	98.77 225	97.04 167	99.85 128	93.79 338	99.54 222	99.49 134
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 111	98.71 95	98.62 191	99.10 206	96.37 247	97.23 270	98.87 272	99.20 65	99.19 126	98.99 176	97.30 152	99.85 128	98.77 81	99.79 115	99.65 65

EI-MVSNet		98.40 156	98.51 124	98.04 258	99.10 206	94.73 299	97.20 274	98.87 272	98.97 100	99.06 140	99.02 163	96.00 220	99.80 194	98.58 93	99.82 95	99.60 79

CVMVSNet		96.25 306	97.21 249	93.38 397	99.10 206	80.56 424	97.20 274	98.19 328	96.94 263	99.00 152	99.02 163	89.50 334	99.80 194	96.36 251	99.59 204	99.78 35

EI-MVSNet-Vis-set		98.68 116	98.70 98	98.63 190	99.09 209	96.40 246	97.23 270	98.86 277	99.20 65	99.18 130	98.97 182	97.29 154	99.85 128	98.72 85	99.78 120	99.64 66

HPM-MVS++		98.10 189	97.64 223	99.48 53	99.09 209	99.13 59	97.52 248	98.75 296	97.46 220	96.90 341	97.83 325	96.01 219	99.84 146	95.82 280	99.35 256	99.46 153

DP-MVS Recon		97.33 253	96.92 265	98.57 201	99.09 209	97.99 150	96.79 295	99.35 151	93.18 366	97.71 292	98.07 310	95.00 255	99.31 376	93.97 331	99.13 293	98.42 347

MVS_111021_HR		98.25 178	98.08 186	98.75 175	99.09 209	97.46 194	95.97 339	99.27 191	97.60 202	97.99 274	98.25 294	98.15 90	99.38 367	96.87 205	99.57 213	99.42 168

BP-MVS1		97.40 248	96.97 261	98.71 181	99.07 213	96.81 232	98.34 144	97.18 354	98.58 127	98.17 255	98.61 255	84.01 373	99.94 37	98.97 66	99.78 120	99.37 190

9.14			97.78 210		99.07 213		97.53 247	99.32 164	95.53 319	98.54 228	98.70 236	97.58 131	99.76 230	94.32 323	99.46 241

PAPM_NR		96.82 287	96.32 298	98.30 237	99.07 213	96.69 240	97.48 252	98.76 293	95.81 311	96.61 354	96.47 369	94.12 281	99.17 389	90.82 390	97.78 369	99.06 259

TAMVS		98.24 179	98.05 188	98.80 163	99.07 213	97.18 213	97.88 201	98.81 286	96.66 278	99.17 131	99.21 121	94.81 262	99.77 224	96.96 195	99.88 73	99.44 161

CLD-MVS		97.49 239	97.16 251	98.48 217	99.07 213	97.03 220	94.71 383	99.21 206	94.46 344	98.06 268	97.16 356	97.57 132	99.48 349	94.46 315	99.78 120	98.95 280
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CS-MVS		99.13 52	99.10 56	99.24 97	99.06 218	99.15 51	99.36 19	99.88 13	99.36 49	98.21 254	98.46 275	98.68 42	99.93 44	99.03 62	99.85 81	98.64 326

thres100view900		94.19 349	93.67 353	95.75 366	99.06 218	91.35 374	98.03 178	94.24 398	98.33 141	97.40 317	94.98 398	79.84 389	99.62 300	83.05 411	98.08 361	96.29 404

thres600view7		94.45 344	93.83 350	96.29 350	99.06 218	91.53 370	97.99 188	94.24 398	98.34 140	97.44 315	95.01 396	79.84 389	99.67 275	84.33 409	98.23 350	97.66 385

plane_prior1					99.05 221

YYNet1		97.60 230	97.67 218	97.39 309	99.04 222	93.04 348	95.27 369	98.38 320	97.25 240	98.92 171	98.95 189	95.48 244	99.73 247	96.99 191	98.74 325	99.41 171

MDA-MVSNet_test_wron		97.60 230	97.66 221	97.41 308	99.04 222	93.09 344	95.27 369	98.42 317	97.26 239	98.88 178	98.95 189	95.43 245	99.73 247	97.02 188	98.72 327	99.41 171

MIMVSNet		96.62 294	96.25 302	97.71 281	99.04 222	94.66 302	99.16 51	96.92 365	97.23 246	97.87 281	99.10 147	86.11 356	99.65 291	91.65 374	99.21 281	98.82 299

PatchMatch-RL		97.24 261	96.78 276	98.61 194	99.03 225	97.83 167	96.36 318	99.06 238	93.49 364	97.36 321	97.78 326	95.75 234	99.49 346	93.44 347	98.77 324	98.52 335

GDP-MVS		97.50 236	97.11 255	98.67 184	99.02 226	96.85 230	98.16 159	99.71 36	98.32 143	98.52 231	98.54 262	83.39 377	99.95 24	98.79 77	99.56 216	99.19 241

ZD-MVS					99.01 227	98.84 78		99.07 237	94.10 354	98.05 270	98.12 304	96.36 207	99.86 116	92.70 363	99.19 285

CDPH-MVS		97.26 258	96.66 285	99.07 122	99.00 228	98.15 130	96.03 337	99.01 252	91.21 390	97.79 288	97.85 324	96.89 176	99.69 263	92.75 361	99.38 253	99.39 181

diffmvs		98.22 180	98.24 167	98.17 246	99.00 228	95.44 276	96.38 317	99.58 59	97.79 188	98.53 229	98.50 271	96.76 187	99.74 242	97.95 133	99.64 187	99.34 203
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WR-MVS		98.40 156	98.19 172	99.03 132	99.00 228	97.65 184	96.85 293	98.94 257	98.57 128	98.89 175	98.50 271	95.60 238	99.85 128	97.54 158	99.85 81	99.59 85

plane_prior6					98.99 231	97.70 182						94.90 256

xiu_mvs_v1_base_debu		97.86 210	98.17 174	96.92 329	98.98 232	93.91 327	96.45 312	99.17 220	97.85 184	98.41 240	97.14 358	98.47 57	99.92 53	98.02 126	99.05 299	96.92 397

xiu_mvs_v1_base		97.86 210	98.17 174	96.92 329	98.98 232	93.91 327	96.45 312	99.17 220	97.85 184	98.41 240	97.14 358	98.47 57	99.92 53	98.02 126	99.05 299	96.92 397

xiu_mvs_v1_base_debi		97.86 210	98.17 174	96.92 329	98.98 232	93.91 327	96.45 312	99.17 220	97.85 184	98.41 240	97.14 358	98.47 57	99.92 53	98.02 126	99.05 299	96.92 397

MVP-Stereo		98.08 192	97.92 202	98.57 201	98.96 235	96.79 233	97.90 199	99.18 216	96.41 288	98.46 235	98.95 189	95.93 229	99.60 307	96.51 241	98.98 312	99.31 214
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 156	98.68 101	97.54 297	98.96 235	97.99 150	97.88 201	99.36 146	98.20 158	99.63 49	99.04 160	98.76 35	95.33 420	96.56 235	99.74 142	99.31 214
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
新几何1				98.91 150	98.94 237	97.76 176		98.76 293	87.58 407	96.75 349	98.10 306	94.80 263	99.78 218	92.73 362	99.00 308	99.20 236

USDC		97.41 247	97.40 236	97.44 306	98.94 237	93.67 337	95.17 372	99.53 84	94.03 356	98.97 158	99.10 147	95.29 247	99.34 372	95.84 279	99.73 145	99.30 217

tfpn200view9		94.03 353	93.44 355	95.78 365	98.93 239	91.44 372	97.60 239	94.29 396	97.94 176	97.10 327	94.31 405	79.67 391	99.62 300	83.05 411	98.08 361	96.29 404

testdata				98.09 250	98.93 239	95.40 278		98.80 288	90.08 398	97.45 314	98.37 284	95.26 248	99.70 259	93.58 343	98.95 315	99.17 248

thres400		94.14 351	93.44 355	96.24 353	98.93 239	91.44 372	97.60 239	94.29 396	97.94 176	97.10 327	94.31 405	79.67 391	99.62 300	83.05 411	98.08 361	97.66 385

TAPA-MVS	96.21 11	96.63 293	95.95 304	98.65 185	98.93 239	98.09 137	96.93 289	99.28 188	83.58 413	98.13 262	97.78 326	96.13 214	99.40 363	93.52 344	99.29 267	98.45 340
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 243	96.93 227	95.54 359	98.78 291	85.72 410	96.86 344	98.11 305	94.43 270			99.10 298	99.23 231

PVSNet_BlendedMVS		97.55 235	97.53 229	97.60 289	98.92 243	93.77 334	96.64 304	99.43 124	94.49 342	97.62 297	99.18 128	96.82 181	99.67 275	94.73 307	99.93 43	99.36 197

PVSNet_Blended		96.88 283	96.68 282	97.47 304	98.92 243	93.77 334	94.71 383	99.43 124	90.98 392	97.62 297	97.36 352	96.82 181	99.67 275	94.73 307	99.56 216	98.98 274

MSDG		97.71 223	97.52 230	98.28 239	98.91 246	96.82 231	94.42 393	99.37 142	97.65 196	98.37 245	98.29 293	97.40 148	99.33 374	94.09 329	99.22 278	98.68 324

Anonymous202405211		97.90 203	97.50 231	99.08 120	98.90 247	98.25 121	98.53 117	96.16 376	98.87 108	99.11 133	98.86 207	90.40 328	99.78 218	97.36 166	99.31 262	99.19 241

原ACMM1				98.35 232	98.90 247	96.25 251		98.83 285	92.48 376	96.07 369	98.10 306	95.39 246	99.71 255	92.61 365	98.99 310	99.08 256

GBi-Net		98.65 121	98.47 133	99.17 104	98.90 247	98.24 122	99.20 45	99.44 118	98.59 124	98.95 162	99.55 52	94.14 278	99.86 116	97.77 144	99.69 168	99.41 171

test1		98.65 121	98.47 133	99.17 104	98.90 247	98.24 122	99.20 45	99.44 118	98.59 124	98.95 162	99.55 52	94.14 278	99.86 116	97.77 144	99.69 168	99.41 171

FMVSNet2		98.49 147	98.40 143	98.75 175	98.90 247	97.14 217	98.61 108	99.13 229	98.59 124	99.19 126	99.28 104	94.14 278	99.82 173	97.97 131	99.80 110	99.29 219

OMC-MVS		97.88 207	97.49 232	99.04 131	98.89 252	98.63 91	96.94 287	99.25 197	95.02 331	98.53 229	98.51 267	97.27 155	99.47 352	93.50 346	99.51 231	99.01 268

MVSFormer		98.26 176	98.43 139	97.77 272	98.88 253	93.89 330	99.39 17	99.56 73	99.11 76	98.16 258	98.13 302	93.81 286	99.97 5	99.26 46	99.57 213	99.43 165

lupinMVS		97.06 273	96.86 269	97.65 284	98.88 253	93.89 330	95.48 363	97.97 334	93.53 362	98.16 258	97.58 338	93.81 286	99.91 62	96.77 213	99.57 213	99.17 248

dmvs_re		95.98 314	95.39 324	97.74 278	98.86 255	97.45 195	98.37 140	95.69 387	97.95 174	96.56 355	95.95 377	90.70 325	97.68 414	88.32 399	96.13 401	98.11 362

DELS-MVS		98.27 174	98.20 170	98.48 217	98.86 255	96.70 239	95.60 358	99.20 208	97.73 191	98.45 236	98.71 233	97.50 141	99.82 173	98.21 113	99.59 204	98.93 285
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
TinyColmap		97.89 205	97.98 195	97.60 289	98.86 255	94.35 310	96.21 327	99.44 118	97.45 222	99.06 140	98.88 204	97.99 102	99.28 382	94.38 322	99.58 209	99.18 244

LCM-MVSNet-Re		98.64 123	98.48 131	99.11 114	98.85 258	98.51 104	98.49 126	99.83 22	98.37 138	99.69 38	99.46 70	98.21 82	99.92 53	94.13 328	99.30 265	98.91 289

pmmvs4		97.58 233	97.28 244	98.51 212	98.84 259	96.93 227	95.40 367	98.52 312	93.60 361	98.61 215	98.65 246	95.10 252	99.60 307	96.97 194	99.79 115	98.99 273

NP-MVS					98.84 259	97.39 199					96.84 361

sss		97.21 263	96.93 263	98.06 255	98.83 261	95.22 285	96.75 299	98.48 314	94.49 342	97.27 323	97.90 321	92.77 303	99.80 194	96.57 231	99.32 260	99.16 251

PVSNet	93.40 17	95.67 323	95.70 309	95.57 370	98.83 261	88.57 397	92.50 410	97.72 339	92.69 374	96.49 361	96.44 370	93.72 289	99.43 359	93.61 341	99.28 268	98.71 317

MVE	83.40 22	92.50 374	91.92 376	94.25 385	98.83 261	91.64 369	92.71 409	83.52 423	95.92 308	86.46 421	95.46 390	95.20 249	95.40 419	80.51 416	98.64 336	95.73 412
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ambc				98.24 242	98.82 264	95.97 260	98.62 107	99.00 254		99.27 112	99.21 121	96.99 172	99.50 343	96.55 238	99.50 238	99.26 225

旧先验1					98.82 264	97.45 195		98.76 293			98.34 288	95.50 243			99.01 307	99.23 231

test_vis1_rt		97.75 220	97.72 216	97.83 267	98.81 266	96.35 248	97.30 265	99.69 40	94.61 340	97.87 281	98.05 311	96.26 210	98.32 409	98.74 83	98.18 353	98.82 299

WTY-MVS		96.67 291	96.27 301	97.87 265	98.81 266	94.61 304	96.77 297	97.92 336	94.94 334	97.12 326	97.74 329	91.11 321	99.82 173	93.89 334	98.15 357	99.18 244

3Dnovator+	97.89 3	98.69 111	98.51 124	99.24 97	98.81 266	98.40 109	99.02 66	99.19 212	98.99 97	98.07 267	99.28 104	97.11 165	99.84 146	96.84 208	99.32 260	99.47 151

QAPM		97.31 254	96.81 275	98.82 159	98.80 269	97.49 192	99.06 62	99.19 212	90.22 396	97.69 294	99.16 134	96.91 175	99.90 68	90.89 389	99.41 248	99.07 258

VNet		98.42 153	98.30 158	98.79 166	98.79 270	97.29 203	98.23 150	98.66 303	99.31 53	98.85 183	98.80 219	94.80 263	99.78 218	98.13 118	99.13 293	99.31 214

DPM-MVS		96.32 303	95.59 315	98.51 212	98.76 271	97.21 210	94.54 392	98.26 323	91.94 381	96.37 362	97.25 354	93.06 297	99.43 359	91.42 379	98.74 325	98.89 291

3Dnovator	98.27 2	98.81 91	98.73 90	99.05 129	98.76 271	97.81 173	99.25 40	99.30 177	98.57 128	98.55 226	99.33 95	97.95 104	99.90 68	97.16 176	99.67 179	99.44 161

PLC	94.65 16	96.51 296	95.73 308	98.85 156	98.75 273	97.91 160	96.42 315	99.06 238	90.94 393	95.59 375	97.38 350	94.41 271	99.59 311	90.93 387	98.04 366	99.05 260
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 285	96.75 278	97.08 321	98.74 274	93.33 342	96.71 301	98.26 323	96.72 275	98.44 237	97.37 351	95.20 249	99.47 352	91.89 370	97.43 378	98.44 343

hse-mvs2		97.46 241	97.07 256	98.64 186	98.73 275	97.33 201	97.45 255	97.64 345	99.11 76	98.58 221	97.98 315	88.65 341	99.79 207	98.11 119	97.39 380	98.81 303

CDS-MVSNet		97.69 224	97.35 241	98.69 182	98.73 275	97.02 221	96.92 291	98.75 296	95.89 309	98.59 219	98.67 241	92.08 313	99.74 242	96.72 219	99.81 99	99.32 210
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EIA-MVS		98.00 197	97.74 213	98.80 163	98.72 277	98.09 137	98.05 175	99.60 56	97.39 226	96.63 352	95.55 385	97.68 120	99.80 194	96.73 218	99.27 269	98.52 335

LFMVS		97.20 264	96.72 279	98.64 186	98.72 277	96.95 225	98.93 78	94.14 400	99.74 10	98.78 192	99.01 172	84.45 368	99.73 247	97.44 162	99.27 269	99.25 226

new_pmnet		96.99 280	96.76 277	97.67 282	98.72 277	94.89 294	95.95 343	98.20 326	92.62 375	98.55 226	98.54 262	94.88 259	99.52 337	93.96 332	99.44 246	98.59 332

Fast-Effi-MVS+		97.67 226	97.38 238	98.57 201	98.71 280	97.43 197	97.23 270	99.45 114	94.82 337	96.13 366	96.51 366	98.52 56	99.91 62	96.19 260	98.83 321	98.37 352

TEST9					98.71 280	98.08 141	95.96 341	99.03 246	91.40 387	95.85 372	97.53 340	96.52 198	99.76 230

train_agg		97.10 270	96.45 295	99.07 122	98.71 280	98.08 141	95.96 341	99.03 246	91.64 382	95.85 372	97.53 340	96.47 200	99.76 230	93.67 340	99.16 288	99.36 197

TSAR-MVS + GP.		98.18 185	97.98 195	98.77 172	98.71 280	97.88 162	96.32 321	98.66 303	96.33 290	99.23 123	98.51 267	97.48 145	99.40 363	97.16 176	99.46 241	99.02 267

FA-MVS(test-final)		96.99 280	96.82 273	97.50 301	98.70 284	94.78 296	99.34 20	96.99 360	95.07 330	98.48 234	99.33 95	88.41 344	99.65 291	96.13 266	98.92 318	98.07 365

AUN-MVS		96.24 308	95.45 320	98.60 196	98.70 284	97.22 209	97.38 258	97.65 343	95.95 307	95.53 382	97.96 319	82.11 385	99.79 207	96.31 253	97.44 377	98.80 308

our_test_3		97.39 249	97.73 215	96.34 348	98.70 284	89.78 393	94.61 389	98.97 256	96.50 283	99.04 147	98.85 210	95.98 225	99.84 146	97.26 171	99.67 179	99.41 171

ppachtmachnet_test		97.50 236	97.74 213	96.78 338	98.70 284	91.23 380	94.55 391	99.05 241	96.36 289	99.21 124	98.79 221	96.39 203	99.78 218	96.74 216	99.82 95	99.34 203

PCF-MVS	92.86 18	94.36 345	93.00 362	98.42 224	98.70 284	97.56 189	93.16 408	99.11 232	79.59 417	97.55 304	97.43 347	92.19 310	99.73 247	79.85 417	99.45 243	97.97 371
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 202	98.02 191	97.58 291	98.69 289	94.10 317	98.13 162	98.90 266	97.95 174	97.32 322	99.58 43	95.95 228	98.75 404	96.41 247	99.22 278	99.87 18

ETV-MVS		98.03 194	97.86 207	98.56 205	98.69 289	98.07 143	97.51 250	99.50 90	98.10 166	97.50 309	95.51 386	98.41 62	99.88 91	96.27 256	99.24 274	97.71 384

test_prior				98.95 143	98.69 289	97.95 158		99.03 246					99.59 311			99.30 217

mvsmamba		97.57 234	97.26 245	98.51 212	98.69 289	96.73 238	98.74 92	97.25 353	97.03 259	97.88 280	99.23 119	90.95 322	99.87 108	96.61 227	99.00 308	98.91 289

agg_prior					98.68 293	97.99 150		99.01 252		95.59 375			99.77 224

test_8					98.67 294	98.01 149	95.91 347	99.02 249	91.64 382	95.79 374	97.50 343	96.47 200	99.76 230

HQP-NCC					98.67 294		96.29 323		96.05 300	95.55 378

ACMP_Plane					98.67 294		96.29 323		96.05 300	95.55 378

CNVR-MVS		98.17 187	97.87 206	99.07 122	98.67 294	98.24 122	97.01 283	98.93 260	97.25 240	97.62 297	98.34 288	97.27 155	99.57 319	96.42 246	99.33 259	99.39 181

HQP-MVS		97.00 279	96.49 294	98.55 206	98.67 294	96.79 233	96.29 323	99.04 244	96.05 300	95.55 378	96.84 361	93.84 284	99.54 331	92.82 358	99.26 272	99.32 210

MM		98.22 180	97.99 194	98.91 150	98.66 299	96.97 222	97.89 200	94.44 394	99.54 30	98.95 162	99.14 141	93.50 290	99.92 53	99.80 11	99.96 23	99.85 22

test_fmvs1		97.72 222	97.94 200	97.07 323	98.66 299	92.39 359	97.68 227	99.81 25	95.20 329	99.54 57	99.44 75	91.56 318	99.41 362	99.78 14	99.77 126	99.40 180

balanced_conf03		98.63 125	98.72 92	98.38 228	98.66 299	96.68 241	98.90 80	99.42 127	98.99 97	98.97 158	99.19 124	95.81 233	99.85 128	98.77 81	99.77 126	98.60 329

thres200		93.72 358	93.14 360	95.46 374	98.66 299	91.29 376	96.61 306	94.63 393	97.39 226	96.83 345	93.71 408	79.88 388	99.56 322	82.40 414	98.13 358	95.54 413

wuyk23d		96.06 310	97.62 225	91.38 400	98.65 303	98.57 98	98.85 87	96.95 363	96.86 268	99.90 12	99.16 134	99.18 17	98.40 408	89.23 397	99.77 126	77.18 420

NCCC		97.86 210	97.47 235	99.05 129	98.61 304	98.07 143	96.98 285	98.90 266	97.63 197	97.04 331	97.93 320	95.99 224	99.66 286	95.31 295	98.82 323	99.43 165

DeepC-MVS_fast	96.85 6	98.30 170	98.15 178	98.75 175	98.61 304	97.23 207	97.76 219	99.09 235	97.31 234	98.75 198	98.66 244	97.56 133	99.64 294	96.10 267	99.55 220	99.39 181
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 360	92.09 370	97.75 276	98.60 306	94.40 308	97.32 263	95.26 389	97.56 206	96.79 348	95.50 387	53.57 426	99.77 224	95.26 296	98.97 313	99.08 256

thisisatest0515		94.12 352	93.16 359	96.97 327	98.60 306	92.90 349	93.77 404	90.61 413	94.10 354	96.91 338	95.87 380	74.99 403	99.80 194	94.52 313	99.12 296	98.20 358

GA-MVS		95.86 317	95.32 327	97.49 302	98.60 306	94.15 316	93.83 403	97.93 335	95.49 320	96.68 350	97.42 348	83.21 378	99.30 378	96.22 258	98.55 342	99.01 268

dmvs_testset		92.94 370	92.21 369	95.13 378	98.59 309	90.99 383	97.65 233	92.09 409	96.95 262	94.00 401	93.55 409	92.34 309	96.97 417	72.20 420	92.52 415	97.43 392

OPU-MVS				98.82 159	98.59 309	98.30 118	98.10 168				98.52 266	98.18 84	98.75 404	94.62 310	99.48 240	99.41 171

MSLP-MVS++		98.02 195	98.14 180	97.64 286	98.58 311	95.19 286	97.48 252	99.23 204	97.47 215	97.90 278	98.62 253	97.04 167	98.81 403	97.55 156	99.41 248	98.94 284

test12				98.93 146	98.58 311	97.83 167		98.66 303		96.53 356		95.51 242	99.69 263		99.13 293	99.27 222

CL-MVSNet_self_test		97.44 244	97.22 248	98.08 253	98.57 313	95.78 266	94.30 396	98.79 289	96.58 281	98.60 217	98.19 300	94.74 266	99.64 294	96.41 247	98.84 320	98.82 299

PS-MVSNAJ		97.08 272	97.39 237	96.16 359	98.56 314	92.46 357	95.24 371	98.85 280	97.25 240	97.49 310	95.99 376	98.07 93	99.90 68	96.37 249	98.67 335	96.12 409

CNLPA		97.17 267	96.71 280	98.55 206	98.56 314	98.05 147	96.33 320	98.93 260	96.91 265	97.06 330	97.39 349	94.38 273	99.45 356	91.66 373	99.18 287	98.14 361

xiu_mvs_v2_base		97.16 268	97.49 232	96.17 357	98.54 316	92.46 357	95.45 364	98.84 281	97.25 240	97.48 311	96.49 367	98.31 71	99.90 68	96.34 252	98.68 334	96.15 408

alignmvs		97.35 251	96.88 268	98.78 169	98.54 316	98.09 137	97.71 224	97.69 341	99.20 65	97.59 300	95.90 379	88.12 346	99.55 326	98.18 115	98.96 314	98.70 320

FE-MVS		95.66 324	94.95 337	97.77 272	98.53 318	95.28 282	99.40 16	96.09 378	93.11 368	97.96 275	99.26 110	79.10 395	99.77 224	92.40 367	98.71 329	98.27 356

Effi-MVS+		98.02 195	97.82 209	98.62 191	98.53 318	97.19 212	97.33 262	99.68 45	97.30 235	96.68 350	97.46 346	98.56 54	99.80 194	96.63 225	98.20 352	98.86 296

baseline1		95.96 315	95.44 321	97.52 299	98.51 320	93.99 324	98.39 138	96.09 378	98.21 154	98.40 244	97.76 328	86.88 348	99.63 297	95.42 293	89.27 418	98.95 280

MVS_Test		98.18 185	98.36 150	97.67 282	98.48 321	94.73 299	98.18 155	99.02 249	97.69 193	98.04 271	99.11 144	97.22 159	99.56 322	98.57 95	98.90 319	98.71 317

MGCFI-Net		98.34 163	98.28 160	98.51 212	98.47 322	97.59 188	98.96 74	99.48 99	99.18 71	97.40 317	95.50 387	98.66 43	99.50 343	98.18 115	98.71 329	98.44 343

BH-RMVSNet		96.83 285	96.58 290	97.58 291	98.47 322	94.05 318	96.67 303	97.36 348	96.70 277	97.87 281	97.98 315	95.14 251	99.44 358	90.47 392	98.58 341	99.25 226

sasdasda		98.34 163	98.26 164	98.58 198	98.46 324	97.82 170	98.96 74	99.46 110	99.19 69	97.46 312	95.46 390	98.59 50	99.46 354	98.08 122	98.71 329	98.46 337

canonicalmvs		98.34 163	98.26 164	98.58 198	98.46 324	97.82 170	98.96 74	99.46 110	99.19 69	97.46 312	95.46 390	98.59 50	99.46 354	98.08 122	98.71 329	98.46 337

MVS-HIRNet		94.32 346	95.62 312	90.42 401	98.46 324	75.36 425	96.29 323	89.13 417	95.25 327	95.38 384	99.75 13	92.88 300	99.19 388	94.07 330	99.39 250	96.72 402

PHI-MVS		98.29 173	97.95 198	99.34 75	98.44 327	99.16 47	98.12 165	99.38 138	96.01 304	98.06 268	98.43 278	97.80 114	99.67 275	95.69 285	99.58 209	99.20 236

DVP-MVS++		98.90 79	98.70 98	99.51 46	98.43 328	99.15 51	99.43 12	99.32 164	98.17 161	99.26 116	99.02 163	98.18 84	99.88 91	97.07 185	99.45 243	99.49 134

MSC_two_6792asdad				99.32 82	98.43 328	98.37 113		98.86 277					99.89 79	97.14 179	99.60 200	99.71 49

No_MVS				99.32 82	98.43 328	98.37 113		98.86 277					99.89 79	97.14 179	99.60 200	99.71 49

Fast-Effi-MVS+-dtu		98.27 174	98.09 183	98.81 161	98.43 328	98.11 134	97.61 238	99.50 90	98.64 118	97.39 319	97.52 342	98.12 92	99.95 24	96.90 202	98.71 329	98.38 350

OpenMVS_ROB	95.38 14	95.84 319	95.18 332	97.81 269	98.41 332	97.15 216	97.37 259	98.62 307	83.86 412	98.65 209	98.37 284	94.29 276	99.68 272	88.41 398	98.62 339	96.60 403

DeepPCF-MVS	96.93 5	98.32 167	98.01 192	99.23 99	98.39 333	98.97 70	95.03 376	99.18 216	96.88 266	99.33 100	98.78 223	98.16 88	99.28 382	96.74 216	99.62 193	99.44 161

Patchmatch-test		96.55 295	96.34 297	97.17 318	98.35 334	93.06 345	98.40 137	97.79 337	97.33 231	98.41 240	98.67 241	83.68 376	99.69 263	95.16 298	99.31 262	98.77 311

AdaColmap		97.14 269	96.71 280	98.46 219	98.34 335	97.80 174	96.95 286	98.93 260	95.58 317	96.92 336	97.66 333	95.87 231	99.53 333	90.97 386	99.14 291	98.04 366

OpenMVS	96.65 7	97.09 271	96.68 282	98.32 234	98.32 336	97.16 215	98.86 86	99.37 142	89.48 400	96.29 364	99.15 138	96.56 196	99.90 68	92.90 355	99.20 282	97.89 372

MG-MVS		96.77 288	96.61 287	97.26 314	98.31 337	93.06 345	95.93 344	98.12 331	96.45 287	97.92 276	98.73 230	93.77 288	99.39 365	91.19 384	99.04 302	99.33 208

test_yl		96.69 289	96.29 299	97.90 262	98.28 338	95.24 283	97.29 266	97.36 348	98.21 154	98.17 255	97.86 322	86.27 352	99.55 326	94.87 304	98.32 346	98.89 291

DCV-MVSNet		96.69 289	96.29 299	97.90 262	98.28 338	95.24 283	97.29 266	97.36 348	98.21 154	98.17 255	97.86 322	86.27 352	99.55 326	94.87 304	98.32 346	98.89 291

CHOSEN 280x420		95.51 329	95.47 318	95.65 369	98.25 340	88.27 400	93.25 407	98.88 270	93.53 362	94.65 393	97.15 357	86.17 354	99.93 44	97.41 164	99.93 43	98.73 316

SCA		96.41 302	96.66 285	95.67 367	98.24 341	88.35 399	95.85 350	96.88 366	96.11 298	97.67 295	98.67 241	93.10 295	99.85 128	94.16 324	99.22 278	98.81 303

DeepMVS_CX				93.44 396	98.24 341	94.21 313		94.34 395	64.28 420	91.34 414	94.87 402	89.45 335	92.77 421	77.54 419	93.14 414	93.35 416

MS-PatchMatch		97.68 225	97.75 212	97.45 305	98.23 343	93.78 333	97.29 266	98.84 281	96.10 299	98.64 210	98.65 246	96.04 217	99.36 368	96.84 208	99.14 291	99.20 236

BH-w/o		95.13 335	94.89 339	95.86 362	98.20 344	91.31 375	95.65 356	97.37 347	93.64 360	96.52 357	95.70 383	93.04 298	99.02 394	88.10 400	95.82 404	97.24 395

mvs_anonymous		97.83 218	98.16 177	96.87 332	98.18 345	91.89 366	97.31 264	98.90 266	97.37 228	98.83 186	99.46 70	96.28 209	99.79 207	98.90 70	98.16 356	98.95 280

miper_lstm_enhance		97.18 266	97.16 251	97.25 315	98.16 346	92.85 350	95.15 374	99.31 169	97.25 240	98.74 200	98.78 223	90.07 329	99.78 218	97.19 174	99.80 110	99.11 255

RRT-MVS		97.88 207	97.98 195	97.61 288	98.15 347	93.77 334	98.97 73	99.64 50	99.16 73	98.69 203	99.42 77	91.60 316	99.89 79	97.63 152	98.52 343	99.16 251

ET-MVSNet_ETH3D		94.30 348	93.21 358	97.58 291	98.14 348	94.47 307	94.78 382	93.24 405	94.72 338	89.56 416	95.87 380	78.57 398	99.81 187	96.91 197	97.11 389	98.46 337

ADS-MVSNet2		95.43 330	94.98 335	96.76 339	98.14 348	91.74 367	97.92 196	97.76 338	90.23 394	96.51 358	98.91 194	85.61 359	99.85 128	92.88 356	96.90 390	98.69 321

ADS-MVSNet		95.24 333	94.93 338	96.18 356	98.14 348	90.10 392	97.92 196	97.32 351	90.23 394	96.51 358	98.91 194	85.61 359	99.74 242	92.88 356	96.90 390	98.69 321

c3_l		97.36 250	97.37 239	97.31 310	98.09 351	93.25 343	95.01 377	99.16 223	97.05 256	98.77 195	98.72 232	92.88 300	99.64 294	96.93 196	99.76 138	99.05 260

FMVSNet3		97.50 236	97.24 247	98.29 238	98.08 352	95.83 264	97.86 205	98.91 265	97.89 181	98.95 162	98.95 189	87.06 347	99.81 187	97.77 144	99.69 168	99.23 231

PAPM		91.88 383	90.34 386	96.51 343	98.06 353	92.56 355	92.44 411	97.17 355	86.35 408	90.38 415	96.01 375	86.61 350	99.21 387	70.65 421	95.43 406	97.75 381

Effi-MVS+-dtu		98.26 176	97.90 204	99.35 72	98.02 354	99.49 6	98.02 180	99.16 223	98.29 148	97.64 296	97.99 314	96.44 202	99.95 24	96.66 224	98.93 317	98.60 329

eth_miper_zixun_eth		97.23 262	97.25 246	97.17 318	98.00 355	92.77 352	94.71 383	99.18 216	97.27 238	98.56 224	98.74 229	91.89 314	99.69 263	97.06 187	99.81 99	99.05 260

HY-MVS	95.94 13	95.90 316	95.35 326	97.55 296	97.95 356	94.79 295	98.81 91	96.94 364	92.28 379	95.17 386	98.57 260	89.90 331	99.75 237	91.20 383	97.33 385	98.10 363

UGNet		98.53 142	98.45 136	98.79 166	97.94 357	96.96 224	99.08 58	98.54 310	99.10 83	96.82 346	99.47 69	96.55 197	99.84 146	98.56 98	99.94 38	99.55 109
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
MAR-MVS		96.47 300	95.70 309	98.79 166	97.92 358	99.12 61	98.28 146	98.60 308	92.16 380	95.54 381	96.17 374	94.77 265	99.52 337	89.62 395	98.23 350	97.72 383
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
MVSTER		96.86 284	96.55 291	97.79 270	97.91 359	94.21 313	97.56 244	98.87 272	97.49 214	99.06 140	99.05 158	80.72 386	99.80 194	98.44 102	99.82 95	99.37 190

API-MVS		97.04 275	96.91 267	97.42 307	97.88 360	98.23 126	98.18 155	98.50 313	97.57 204	97.39 319	96.75 363	96.77 185	99.15 391	90.16 393	99.02 306	94.88 414

miper_ehance_all_eth		97.06 273	97.03 258	97.16 320	97.83 361	93.06 345	94.66 386	99.09 235	95.99 305	98.69 203	98.45 276	92.73 305	99.61 306	96.79 210	99.03 303	98.82 299

cl____		97.02 276	96.83 272	97.58 291	97.82 362	94.04 320	94.66 386	99.16 223	97.04 257	98.63 211	98.71 233	88.68 340	99.69 263	97.00 189	99.81 99	99.00 272

DIV-MVS_self_test		97.02 276	96.84 271	97.58 291	97.82 362	94.03 321	94.66 386	99.16 223	97.04 257	98.63 211	98.71 233	88.69 338	99.69 263	97.00 189	99.81 99	99.01 268

CANet		97.87 209	97.76 211	98.19 245	97.75 364	95.51 273	96.76 298	99.05 241	97.74 190	96.93 335	98.21 298	95.59 239	99.89 79	97.86 139	99.93 43	99.19 241

UBG		93.25 365	92.32 366	96.04 361	97.72 365	90.16 391	95.92 346	95.91 382	96.03 303	93.95 403	93.04 413	69.60 409	99.52 337	90.72 391	97.98 367	98.45 340

mvsany_test1		97.60 230	97.54 228	97.77 272	97.72 365	95.35 279	95.36 368	97.13 357	94.13 353	99.71 34	99.33 95	97.93 105	99.30 378	97.60 155	98.94 316	98.67 325

PVSNet_0	89.98 21	91.15 384	90.30 387	93.70 393	97.72 365	84.34 417	90.24 414	97.42 346	90.20 397	93.79 404	93.09 412	90.90 324	98.89 402	86.57 406	72.76 421	97.87 374

CR-MVSNet		96.28 305	95.95 304	97.28 312	97.71 368	94.22 311	98.11 166	98.92 263	92.31 378	96.91 338	99.37 84	85.44 362	99.81 187	97.39 165	97.36 383	97.81 377

RPMNet		97.02 276	96.93 263	97.30 311	97.71 368	94.22 311	98.11 166	99.30 177	99.37 46	96.91 338	99.34 93	86.72 349	99.87 108	97.53 159	97.36 383	97.81 377

ETVMVS		92.60 373	91.08 382	97.18 316	97.70 370	93.65 339	96.54 307	95.70 385	96.51 282	94.68 392	92.39 416	61.80 423	99.50 343	86.97 403	97.41 379	98.40 348

pmmvs3		95.03 337	94.40 344	96.93 328	97.70 370	92.53 356	95.08 375	97.71 340	88.57 404	97.71 292	98.08 309	79.39 393	99.82 173	96.19 260	99.11 297	98.43 345

baseline2		93.73 357	92.83 363	96.42 346	97.70 370	91.28 377	96.84 294	89.77 416	93.96 358	92.44 411	95.93 378	79.14 394	99.77 224	92.94 354	96.76 394	98.21 357

WBMVS		95.18 334	94.78 340	96.37 347	97.68 373	89.74 394	95.80 352	98.73 299	97.54 209	98.30 246	98.44 277	70.06 407	99.82 173	96.62 226	99.87 76	99.54 113

tpm		94.67 342	94.34 346	95.66 368	97.68 373	88.42 398	97.88 201	94.90 390	94.46 344	96.03 371	98.56 261	78.66 396	99.79 207	95.88 273	95.01 408	98.78 310

CANet_DTU		97.26 258	97.06 257	97.84 266	97.57 375	94.65 303	96.19 329	98.79 289	97.23 246	95.14 387	98.24 295	93.22 292	99.84 146	97.34 167	99.84 85	99.04 264

testing11		93.08 368	92.02 372	96.26 352	97.56 376	90.83 386	96.32 321	95.70 385	96.47 286	92.66 410	93.73 407	64.36 421	99.59 311	93.77 339	97.57 372	98.37 352

tpm2		93.09 367	92.58 365	94.62 382	97.56 376	86.53 406	97.66 231	95.79 384	86.15 409	94.07 400	98.23 297	75.95 401	99.53 333	90.91 388	96.86 393	97.81 377

testing91		93.32 363	92.27 367	96.47 345	97.54 378	91.25 378	96.17 332	96.76 368	97.18 250	93.65 406	93.50 410	65.11 420	99.63 297	93.04 353	97.45 376	98.53 334

TR-MVS		95.55 327	95.12 333	96.86 335	97.54 378	93.94 325	96.49 311	96.53 373	94.36 349	97.03 333	96.61 365	94.26 277	99.16 390	86.91 405	96.31 398	97.47 391

testing99		93.04 369	91.98 375	96.23 354	97.53 380	90.70 388	96.35 319	95.94 381	96.87 267	93.41 407	93.43 411	63.84 422	99.59 311	93.24 351	97.19 386	98.40 348

1314		95.74 321	95.60 313	96.17 357	97.53 380	92.75 353	98.07 172	98.31 322	91.22 389	94.25 396	96.68 364	95.53 240	99.03 393	91.64 375	97.18 387	96.74 401

CostFormer		93.97 354	93.78 351	94.51 383	97.53 380	85.83 409	97.98 189	95.96 380	89.29 402	94.99 389	98.63 251	78.63 397	99.62 300	94.54 312	96.50 395	98.09 364

FMVSNet5		96.01 312	95.20 331	98.41 225	97.53 380	96.10 253	98.74 92	99.50 90	97.22 249	98.03 272	99.04 160	69.80 408	99.88 91	97.27 170	99.71 158	99.25 226

PMMVS		96.51 296	95.98 303	98.09 250	97.53 380	95.84 263	94.92 379	98.84 281	91.58 384	96.05 370	95.58 384	95.68 236	99.66 286	95.59 289	98.09 360	98.76 313

reproduce_monomvs		95.00 339	95.25 328	94.22 386	97.51 385	83.34 418	97.86 205	98.44 315	98.51 133	99.29 109	99.30 101	67.68 413	99.56 322	98.89 72	99.81 99	99.77 37

PAPR		95.29 331	94.47 342	97.75 276	97.50 386	95.14 288	94.89 380	98.71 301	91.39 388	95.35 385	95.48 389	94.57 268	99.14 392	84.95 408	97.37 381	98.97 277

testing222		91.96 381	90.37 385	96.72 340	97.47 387	92.59 354	96.11 334	94.76 391	96.83 269	92.90 409	92.87 414	57.92 424	99.55 326	86.93 404	97.52 373	98.00 370

PatchT		96.65 292	96.35 296	97.54 297	97.40 388	95.32 281	97.98 189	96.64 370	99.33 51	96.89 342	99.42 77	84.32 370	99.81 187	97.69 151	97.49 374	97.48 390

tpm cat1		93.29 364	93.13 361	93.75 392	97.39 389	84.74 412	97.39 257	97.65 343	83.39 414	94.16 397	98.41 279	82.86 381	99.39 365	91.56 377	95.35 407	97.14 396

PatchmatchNet		95.58 326	95.67 311	95.30 377	97.34 390	87.32 404	97.65 233	96.65 369	95.30 326	97.07 329	98.69 237	84.77 365	99.75 237	94.97 302	98.64 336	98.83 298
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 251	96.97 261	98.50 216	97.31 391	96.47 245	98.18 155	98.92 263	98.95 103	98.78 192	99.37 84	85.44 362	99.85 128	95.96 271	99.83 92	99.17 248

LS3D		98.63 125	98.38 148	99.36 66	97.25 392	99.38 12	99.12 57	99.32 164	99.21 63	98.44 237	98.88 204	97.31 151	99.80 194	96.58 229	99.34 258	98.92 286

IB-MVS	91.63 19	92.24 379	90.90 383	96.27 351	97.22 393	91.24 379	94.36 395	93.33 404	92.37 377	92.24 412	94.58 404	66.20 418	99.89 79	93.16 352	94.63 410	97.66 385
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
UWE-MVS		92.38 376	91.76 379	94.21 387	97.16 394	84.65 413	95.42 366	88.45 418	95.96 306	96.17 365	95.84 382	66.36 416	99.71 255	91.87 371	98.64 336	98.28 355

tpmrst		95.07 336	95.46 319	93.91 390	97.11 395	84.36 416	97.62 236	96.96 362	94.98 332	96.35 363	98.80 219	85.46 361	99.59 311	95.60 288	96.23 399	97.79 380

Syy-MVS		96.04 311	95.56 317	97.49 302	97.10 396	94.48 306	96.18 330	96.58 371	95.65 314	94.77 390	92.29 417	91.27 320	99.36 368	98.17 117	98.05 364	98.63 327

myMVS_eth3d		91.92 382	90.45 384	96.30 349	97.10 396	90.90 384	96.18 330	96.58 371	95.65 314	94.77 390	92.29 417	53.88 425	99.36 368	89.59 396	98.05 364	98.63 327

MDTV_nov1_ep13			95.22 330		97.06 398	83.20 419	97.74 221	96.16 376	94.37 348	96.99 334	98.83 213	83.95 374	99.53 333	93.90 333	97.95 368

MVS		93.19 366	92.09 370	96.50 344	96.91 399	94.03 321	98.07 172	98.06 333	68.01 419	94.56 395	96.48 368	95.96 227	99.30 378	83.84 410	96.89 392	96.17 406

E-PMN		94.17 350	94.37 345	93.58 394	96.86 400	85.71 410	90.11 416	97.07 358	98.17 161	97.82 287	97.19 355	84.62 367	98.94 398	89.77 394	97.68 371	96.09 410

JIA-IIPM		95.52 328	95.03 334	97.00 324	96.85 401	94.03 321	96.93 289	95.82 383	99.20 65	94.63 394	99.71 19	83.09 379	99.60 307	94.42 318	94.64 409	97.36 394

EMVS		93.83 356	94.02 348	93.23 398	96.83 402	84.96 411	89.77 417	96.32 375	97.92 178	97.43 316	96.36 373	86.17 354	98.93 399	87.68 401	97.73 370	95.81 411

cl22		95.79 320	95.39 324	96.98 326	96.77 403	92.79 351	94.40 394	98.53 311	94.59 341	97.89 279	98.17 301	82.82 382	99.24 384	96.37 249	99.03 303	98.92 286

WB-MVSnew		95.73 322	95.57 316	96.23 354	96.70 404	90.70 388	96.07 336	93.86 401	95.60 316	97.04 331	95.45 393	96.00 220	99.55 326	91.04 385	98.31 348	98.43 345

dp		93.47 361	93.59 354	93.13 399	96.64 405	81.62 423	97.66 231	96.42 374	92.80 373	96.11 367	98.64 249	78.55 399	99.59 311	93.31 349	92.18 417	98.16 360

MonoMVSNet		96.25 306	96.53 293	95.39 375	96.57 406	91.01 382	98.82 90	97.68 342	98.57 128	98.03 272	99.37 84	90.92 323	97.78 413	94.99 300	93.88 413	97.38 393

test-LLR		93.90 355	93.85 349	94.04 388	96.53 407	84.62 414	94.05 400	92.39 407	96.17 295	94.12 398	95.07 394	82.30 383	99.67 275	95.87 276	98.18 353	97.82 375

test-mter		92.33 378	91.76 379	94.04 388	96.53 407	84.62 414	94.05 400	92.39 407	94.00 357	94.12 398	95.07 394	65.63 419	99.67 275	95.87 276	98.18 353	97.82 375

TESTMET0.1,1		92.19 380	91.77 378	93.46 395	96.48 409	82.80 420	94.05 400	91.52 412	94.45 346	94.00 401	94.88 400	66.65 415	99.56 322	95.78 281	98.11 359	98.02 367

MVS_0304		97.44 244	97.01 260	98.72 180	96.42 410	96.74 237	97.20 274	91.97 410	98.46 136	98.30 246	98.79 221	92.74 304	99.91 62	99.30 43	99.94 38	99.52 124

miper_enhance_ethall		96.01 312	95.74 307	96.81 336	96.41 411	92.27 363	93.69 405	98.89 269	91.14 391	98.30 246	97.35 353	90.58 326	99.58 317	96.31 253	99.03 303	98.60 329

tpmvs		95.02 338	95.25 328	94.33 384	96.39 412	85.87 407	98.08 170	96.83 367	95.46 321	95.51 383	98.69 237	85.91 357	99.53 333	94.16 324	96.23 399	97.58 388

CMPMVS	75.91 23	96.29 304	95.44 321	98.84 157	96.25 413	98.69 90	97.02 282	99.12 230	88.90 403	97.83 285	98.86 207	89.51 333	98.90 401	91.92 369	99.51 231	98.92 286
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 343	93.69 352	96.99 325	96.05 414	93.61 340	94.97 378	93.49 402	96.17 295	97.57 303	94.88 400	82.30 383	99.01 396	93.60 342	94.17 412	98.37 352

EPMVS		93.72 358	93.27 357	95.09 380	96.04 415	87.76 402	98.13 162	85.01 422	94.69 339	96.92 336	98.64 249	78.47 400	99.31 376	95.04 299	96.46 396	98.20 358

cascas		94.79 341	94.33 347	96.15 360	96.02 416	92.36 361	92.34 412	99.26 196	85.34 411	95.08 388	94.96 399	92.96 299	98.53 407	94.41 321	98.59 340	97.56 389

MVStest1		95.86 317	95.60 313	96.63 341	95.87 417	91.70 368	97.93 193	98.94 257	98.03 168	99.56 53	99.66 29	71.83 406	98.26 410	99.35 40	99.24 274	99.91 12

gg-mvs-nofinetune		92.37 377	91.20 381	95.85 363	95.80 418	92.38 360	99.31 27	81.84 424	99.75 8	91.83 413	99.74 15	68.29 410	99.02 394	87.15 402	97.12 388	96.16 407

gm-plane-assit					94.83 419	81.97 422			88.07 406		94.99 397		99.60 307	91.76 372

GG-mvs-BLEND				94.76 381	94.54 420	92.13 365	99.31 27	80.47 425		88.73 419	91.01 419	67.59 414	98.16 412	82.30 415	94.53 411	93.98 415

EPNet_dtu		94.93 340	94.78 340	95.38 376	93.58 421	87.68 403	96.78 296	95.69 387	97.35 230	89.14 418	98.09 308	88.15 345	99.49 346	94.95 303	99.30 265	98.98 274
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 388	75.95 391	77.12 404	92.39 422	67.91 428	90.16 415	59.44 429	82.04 415	89.42 417	94.67 403	49.68 427	81.74 422	48.06 422	77.66 420	81.72 418

KD-MVS_2432*1600		92.87 371	91.99 373	95.51 372	91.37 423	89.27 395	94.07 398	98.14 329	95.42 322	97.25 324	96.44 370	67.86 411	99.24 384	91.28 381	96.08 402	98.02 367

miper_refine_blended		92.87 371	91.99 373	95.51 372	91.37 423	89.27 395	94.07 398	98.14 329	95.42 322	97.25 324	96.44 370	67.86 411	99.24 384	91.28 381	96.08 402	98.02 367

EPNet		96.14 309	95.44 321	98.25 240	90.76 425	95.50 274	97.92 196	94.65 392	98.97 100	92.98 408	98.85 210	89.12 336	99.87 108	95.99 269	99.68 173	99.39 181
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 389	68.95 392	70.34 405	87.68 426	65.00 429	91.11 413	59.90 428	69.02 418	74.46 423	88.89 420	48.58 428	68.03 424	28.61 423	72.33 422	77.99 419

test_method		79.78 386	79.50 389	80.62 402	80.21 427	45.76 430	70.82 418	98.41 319	31.08 422	80.89 422	97.71 330	84.85 364	97.37 415	91.51 378	80.03 419	98.75 314

tmp_tt		78.77 387	78.73 390	78.90 403	58.45 428	74.76 427	94.20 397	78.26 426	39.16 421	86.71 420	92.82 415	80.50 387	75.19 423	86.16 407	92.29 416	86.74 417

testmvs		17.12 391	20.53 394	6.87 407	12.05 429	4.20 432	93.62 406	6.73 430	4.62 425	10.41 425	24.33 422	8.28 430	3.56 426	9.69 425	15.07 423	12.86 422

test123		17.04 392	20.11 395	7.82 406	10.25 430	4.91 431	94.80 381	4.47 431	4.93 424	10.00 426	24.28 423	9.69 429	3.64 425	10.14 424	12.43 424	14.92 421

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

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

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

eth-test2					0.00 431

eth-test					0.00 431

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

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

cdsmvs_eth3d_5k		24.66 390	32.88 393	0.00 408	0.00 431	0.00 433	0.00 419	99.10 233	0.00 426	0.00 427	97.58 338	99.21 16	0.00 427	0.00 426	0.00 425	0.00 423

pcd_1.5k_mvsjas		8.17 393	10.90 396	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	98.07 93	0.00 427	0.00 426	0.00 425	0.00 423

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

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

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

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

ab-mvs-re		8.12 394	10.83 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	97.48 344	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

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

WAC-MVS						90.90 384								91.37 380

PC_three_1452									93.27 365	99.40 88	98.54 262	98.22 80	97.00 416	95.17 297	99.45 243	99.49 134

test_241102_TWO								99.30 177	98.03 168	99.26 116	99.02 163	97.51 140	99.88 91	96.91 197	99.60 200	99.66 60

test_0728_THIRD									98.17 161	99.08 138	99.02 163	97.89 106	99.88 91	97.07 185	99.71 158	99.70 54

GSMVS																98.81 303

sam_mvs1												84.74 366				98.81 303

sam_mvs												84.29 372

MTGPA								99.20 208

test_post1							97.59 241				20.48 425	83.07 380	99.66 286	94.16 324

test_post											21.25 424	83.86 375	99.70 259

patchmatchnet-post											98.77 225	84.37 369	99.85 128

MTMP							97.93 193	91.91 411

test9_res														93.28 350	99.15 290	99.38 188

agg_prior2														92.50 366	99.16 288	99.37 190

test_prior4						97.97 154	95.86 348

test_prior2							95.74 354		96.48 285	96.11 367	97.63 336	95.92 230		94.16 324	99.20 282

旧先验2							95.76 353		88.56 405	97.52 307			99.66 286	94.48 314

新几何2							95.93 344

无先验							95.74 354	98.74 298	89.38 401				99.73 247	92.38 368		99.22 235

原ACMM2							95.53 360

testdata2													99.79 207	92.80 360

segment_acmp												97.02 170

testdata1							95.44 365		96.32 291

plane_prior5								99.27 191					99.70 259	94.42 318	99.51 231	99.45 157

plane_prior4											97.98 315

plane_prior3						97.78 175			97.41 224	97.79 288

plane_prior2							97.77 216		98.20 158

plane_prior						97.65 184	97.07 281		96.72 275						99.36 254

n2								0.00 432

nn								0.00 432

door-mid								99.57 66

test11								98.87 272

door								99.41 131

HQP5-MVS						96.79 233

BP-MVS														92.82 358

HQP4-MVS										95.56 377			99.54 331			99.32 210

HQP3-MVS								99.04 244							99.26 272

HQP2-MVS												93.84 284

MDTV_nov1_ep13_2view						74.92 426	97.69 226		90.06 399	97.75 291		85.78 358		93.52 344		98.69 321

ACMMP++_ref															99.77 126

ACMMP++															99.68 173

Test By Simon												96.52 198

High-resolution multi-view benchmark