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 13	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 12	100.00 1	99.85 25

Gipuma		99.03 66	99.16 51	98.64 188	99.94 2	98.51 104	99.32 23	99.75 36	99.58 29	98.60 220	99.62 37	98.22 83	99.51 345	97.70 152	99.73 148	97.89 375
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 25	99.31 35	99.53 37	99.91 3	98.98 69	99.63 7	99.58 62	99.44 42	99.78 30	99.76 12	96.39 206	99.92 53	99.44 40	99.92 57	99.68 59

pmmvs6		99.67 3	99.70 3	99.60 14	99.90 4	99.27 26	99.53 8	99.76 33	99.64 19	99.84 22	99.83 4	99.50 8	99.87 111	99.36 42	99.92 57	99.64 69

PS-MVSNAJss		99.46 14	99.49 13	99.35 72	99.90 4	98.15 130	99.20 45	99.65 52	99.48 34	99.92 8	99.71 19	98.07 96	99.96 12	99.53 34	100.00 1	99.93 11

testf1		99.25 36	99.16 51	99.51 46	99.89 6	99.63 4	98.71 99	99.69 43	98.90 109	99.43 83	99.35 92	98.86 29	99.67 278	97.81 143	99.81 102	99.24 232

APD_test2		99.25 36	99.16 51	99.51 46	99.89 6	99.63 4	98.71 99	99.69 43	98.90 109	99.43 83	99.35 92	98.86 29	99.67 278	97.81 143	99.81 102	99.24 232

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 45	100.00 1	99.82 30

anonymousdsp		99.51 11	99.47 17	99.62 9	99.88 9	99.08 67	99.34 20	99.69 43	98.93 107	99.65 49	99.72 18	98.93 27	99.95 24	99.11 58	100.00 1	99.82 30

v7n		99.53 9	99.57 10	99.41 62	99.88 9	98.54 102	99.45 11	99.61 58	99.66 17	99.68 43	99.66 29	98.44 64	99.95 24	99.73 21	99.96 26	99.75 49

mvs_tets		99.63 5	99.67 5	99.49 51	99.88 9	98.61 94	99.34 20	99.71 39	99.27 61	99.90 12	99.74 15	99.68 4	99.97 5	99.55 33	99.99 5	99.88 19

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 40	99.98 2	99.75 13	99.80 1	99.97 5	99.82 8	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 51	99.09 89	99.89 15	99.68 22	99.53 7	99.97 5	99.50 37	99.99 5	99.87 20

test_djsdf		99.52 10	99.51 12	99.53 37	99.86 14	98.74 84	99.39 17	99.56 76	99.11 79	99.70 39	99.73 17	99.00 22	99.97 5	99.26 49	99.98 12	99.89 16

MIMVSNet1		99.38 24	99.32 33	99.55 27	99.86 14	99.19 41	99.41 14	99.59 60	99.59 27	99.71 37	99.57 46	97.12 166	99.90 68	99.21 54	99.87 79	99.54 116

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 31	99.63 21	99.78 30	99.67 27	99.48 9	99.81 190	99.30 46	99.97 20	99.77 40
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 62	99.90 3	99.86 19	99.78 10	99.58 6	99.95 24	99.00 67	99.95 33	99.78 38

SixPastTwentyTwo		98.75 103	98.62 113	99.16 107	99.83 18	97.96 157	99.28 37	98.20 329	99.37 49	99.70 39	99.65 33	92.65 309	99.93 44	99.04 64	99.84 88	99.60 82

Baseline_NR-MVSNet		98.98 72	98.86 82	99.36 66	99.82 19	98.55 99	97.47 256	99.57 69	99.37 49	99.21 127	99.61 40	96.76 190	99.83 166	98.06 127	99.83 95	99.71 52

pm-mvs1		99.44 15	99.48 15	99.33 80	99.80 20	98.63 91	99.29 33	99.63 54	99.30 58	99.65 49	99.60 42	99.16 20	99.82 176	99.07 61	99.83 95	99.56 105

TransMVSNet (Re)		99.44 15	99.47 17	99.36 66	99.80 20	98.58 97	99.27 39	99.57 69	99.39 47	99.75 34	99.62 37	99.17 18	99.83 166	99.06 62	99.62 196	99.66 63

K. test v3		98.00 200	97.66 224	99.03 132	99.79 22	97.56 189	99.19 49	92.47 409	99.62 24	99.52 66	99.66 29	89.61 335	99.96 12	99.25 51	99.81 102	99.56 105

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 54	99.97 3	99.66 29	99.71 3	99.96 12	99.79 14	99.99 5	99.96 8

APD_test1		98.83 90	98.66 107	99.34 75	99.78 23	99.47 9	98.42 136	99.45 117	98.28 153	98.98 157	99.19 127	97.76 119	99.58 320	96.57 234	99.55 223	98.97 280

test_vis3_rt		99.14 51	99.17 49	99.07 122	99.78 23	98.38 111	98.92 79	99.94 2	97.80 190	99.91 11	99.67 27	97.15 165	98.91 403	99.76 17	99.56 219	99.92 12

EGC-MVSNET		85.24 388	80.54 391	99.34 75	99.77 26	99.20 38	99.08 58	99.29 188	12.08 426	20.84 427	99.42 80	97.55 137	99.85 131	97.08 187	99.72 156	98.96 282

Anonymous20240521		98.69 114	98.87 79	98.16 251	99.77 26	95.11 293	99.08 58	99.44 121	99.34 53	99.33 103	99.55 54	94.10 285	99.94 37	99.25 51	99.96 26	99.42 171

FC-MVSNet-test		99.27 33	99.25 44	99.34 75	99.77 26	98.37 113	99.30 32	99.57 69	99.61 26	99.40 91	99.50 64	97.12 166	99.85 131	99.02 66	99.94 41	99.80 34

test_vis1_n		98.31 172	98.50 129	97.73 283	99.76 29	94.17 318	98.68 102	99.91 9	96.31 295	99.79 29	99.57 46	92.85 305	99.42 364	99.79 14	99.84 88	99.60 82

test_fmvs3		99.12 57	99.41 21	98.25 243	99.76 29	95.07 294	99.05 64	99.94 2	97.78 192	99.82 24	99.84 3	98.56 55	99.71 258	99.96 1	99.96 26	99.97 4

XXY-MVS		99.14 51	99.15 56	99.10 116	99.76 29	97.74 178	98.85 87	99.62 55	98.48 138	99.37 96	99.49 70	98.75 37	99.86 119	98.20 117	99.80 113	99.71 52

TDRefinement		99.42 20	99.38 24	99.55 27	99.76 29	99.33 20	99.68 6	99.71 39	99.38 48	99.53 64	99.61 40	98.64 45	99.80 197	98.24 114	99.84 88	99.52 127

fmvsm_s_conf0.1_n_a		99.17 46	99.30 38	98.80 163	99.75 33	96.59 242	97.97 192	99.86 16	98.22 156	99.88 17	99.71 19	98.59 51	99.84 149	99.73 21	99.98 12	99.98 3

tt0805		98.69 114	98.62 113	98.90 153	99.75 33	99.30 21	99.15 53	96.97 364	98.86 112	98.87 185	97.62 340	98.63 47	98.96 400	99.41 41	98.29 352	98.45 343

test_vis1_n_1920		98.40 159	98.92 74	96.81 339	99.74 35	90.76 390	98.15 160	99.91 9	98.33 144	99.89 15	99.55 54	95.07 256	99.88 94	99.76 17	99.93 46	99.79 35

FOURS1					99.73 36	99.67 3	99.43 12	99.54 84	99.43 44	99.26 119

PEN-MVS		99.41 21	99.34 30	99.62 9	99.73 36	99.14 56	99.29 33	99.54 84	99.62 24	99.56 56	99.42 80	98.16 91	99.96 12	98.78 81	99.93 46	99.77 40

lessismore_v0				98.97 140	99.73 36	97.53 191		86.71 423		99.37 96	99.52 63	89.93 333	99.92 53	98.99 68	99.72 156	99.44 164

SteuartSystems-ACMMP		98.79 96	98.54 124	99.54 30	99.73 36	99.16 47	98.23 150	99.31 172	97.92 181	98.90 176	98.90 200	98.00 102	99.88 94	96.15 266	99.72 156	99.58 94
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 190	98.15 181	98.22 246	99.73 36	95.15 290	97.36 263	99.68 48	94.45 349	98.99 156	99.27 109	96.87 180	99.94 37	97.13 184	99.91 64	99.57 99

Vis-MVSNet		99.34 26	99.36 27	99.27 90	99.73 36	98.26 120	99.17 50	99.78 31	99.11 79	99.27 115	99.48 71	98.82 32	99.95 24	98.94 71	99.93 46	99.59 88
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
SSC-MVS		98.71 107	98.74 91	98.62 194	99.72 42	96.08 259	98.74 92	98.64 309	99.74 10	99.67 45	99.24 118	94.57 271	99.95 24	99.11 58	99.24 277	99.82 30

test_f		98.67 122	98.87 79	98.05 260	99.72 42	95.59 271	98.51 123	99.81 26	96.30 297	99.78 30	99.82 5	96.14 216	98.63 409	99.82 8	99.93 46	99.95 9

ACMH	96.65 7	99.25 36	99.24 45	99.26 92	99.72 42	98.38 111	99.07 61	99.55 80	98.30 148	99.65 49	99.45 77	99.22 15	99.76 233	98.44 105	99.77 129	99.64 69
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
fmvsm_s_conf0.1_n		99.16 49	99.33 31	98.64 188	99.71 45	96.10 254	97.87 204	99.85 18	98.56 134	99.90 12	99.68 22	98.69 42	99.85 131	99.72 23	99.98 12	99.97 4

PS-CasMVS		99.40 22	99.33 31	99.62 9	99.71 45	99.10 64	99.29 33	99.53 87	99.53 31	99.46 78	99.41 84	98.23 80	99.95 24	98.89 75	99.95 33	99.81 33

DTE-MVSNet		99.43 19	99.35 28	99.66 7	99.71 45	99.30 21	99.31 27	99.51 91	99.64 19	99.56 56	99.46 73	98.23 80	99.97 5	98.78 81	99.93 46	99.72 51

WR-MVS_H		99.33 27	99.22 46	99.65 8	99.71 45	99.24 29	99.32 23	99.55 80	99.46 39	99.50 72	99.34 96	97.30 155	99.93 44	98.90 73	99.93 46	99.77 40

HPM-MVS_fast		99.01 67	98.82 85	99.57 20	99.71 45	99.35 16	99.00 69	99.50 93	97.33 234	98.94 172	98.86 210	98.75 37	99.82 176	97.53 162	99.71 161	99.56 105

ACMH+	96.62 9	99.08 64	99.00 67	99.33 80	99.71 45	98.83 79	98.60 109	99.58 62	99.11 79	99.53 64	99.18 131	98.81 33	99.67 278	96.71 224	99.77 129	99.50 133

PMVS	91.26 20	97.86 213	97.94 203	97.65 287	99.71 45	97.94 159	98.52 118	98.68 305	98.99 100	97.52 310	99.35 92	97.41 150	98.18 414	91.59 379	99.67 182	96.82 403
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FIs		99.14 51	99.09 60	99.29 86	99.70 52	98.28 119	99.13 55	99.52 90	99.48 34	99.24 124	99.41 84	96.79 187	99.82 176	98.69 91	99.88 76	99.76 45

VPNet		98.87 85	98.83 84	99.01 135	99.70 52	97.62 187	98.43 134	99.35 154	99.47 37	99.28 113	99.05 161	96.72 193	99.82 176	98.09 124	99.36 257	99.59 88

fmvsm_s_conf0.1_n_2		99.20 44	99.38 24	98.65 186	99.69 54	96.08 259	97.49 253	99.90 11	99.53 31	99.88 17	99.64 34	98.51 58	99.90 68	99.83 7	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 169	98.68 104	97.27 316	99.69 54	92.29 365	98.03 178	99.85 18	97.62 201	99.96 4	99.62 37	93.98 286	99.74 245	99.52 36	99.86 83	99.79 35

MP-MVS-pluss		98.57 136	98.23 171	99.60 14	99.69 54	99.35 16	97.16 281	99.38 141	94.87 339	98.97 161	98.99 179	98.01 101	99.88 94	97.29 172	99.70 168	99.58 94
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 40	99.32 33	98.96 141	99.68 57	97.35 200	98.84 89	99.48 102	99.69 13	99.63 52	99.68 22	99.03 21	99.96 12	97.97 134	99.92 57	99.57 99

sd_testset		99.28 32	99.31 35	99.19 103	99.68 57	98.06 146	99.41 14	99.30 180	99.69 13	99.63 52	99.68 22	99.25 14	99.96 12	97.25 175	99.92 57	99.57 99

test_fmvs1_n		98.09 194	98.28 163	97.52 302	99.68 57	93.47 344	98.63 105	99.93 5	95.41 328	99.68 43	99.64 34	91.88 318	99.48 352	99.82 8	99.87 79	99.62 73

CHOSEN 1792x2688		97.49 242	97.14 257	98.54 212	99.68 57	96.09 257	96.50 313	99.62 55	91.58 387	98.84 188	98.97 185	92.36 311	99.88 94	96.76 217	99.95 33	99.67 62

tfpnnormal		98.90 82	98.90 76	98.91 150	99.67 61	97.82 170	99.00 69	99.44 121	99.45 40	99.51 71	99.24 118	98.20 86	99.86 119	95.92 275	99.69 171	99.04 267

MTAPA		98.88 84	98.64 110	99.61 12	99.67 61	99.36 15	98.43 134	99.20 211	98.83 116	98.89 178	98.90 200	96.98 176	99.92 53	97.16 179	99.70 168	99.56 105

test_fmvsmvis_n_1920		99.26 35	99.49 13	98.54 212	99.66 63	96.97 222	98.00 184	99.85 18	99.24 63	99.92 8	99.50 64	99.39 11	99.95 24	99.89 3	99.98 12	98.71 320

mvs5depth		99.30 29	99.59 9	98.44 225	99.65 64	95.35 282	99.82 3	99.94 2	99.83 4	99.42 86	99.94 2	98.13 94	99.96 12	99.63 27	99.96 26	100.00 1

fmvsm_l_conf0.5_n_a		99.19 45	99.27 41	98.94 144	99.65 64	97.05 218	97.80 212	99.76 33	98.70 120	99.78 30	99.11 147	98.79 35	99.95 24	99.85 5	99.96 26	99.83 27

WB-MVS		98.52 148	98.55 122	98.43 226	99.65 64	95.59 271	98.52 118	98.77 295	99.65 18	99.52 66	99.00 178	94.34 277	99.93 44	98.65 93	98.83 324	99.76 45

CP-MVSNet		99.21 42	99.09 60	99.56 25	99.65 64	98.96 74	99.13 55	99.34 160	99.42 45	99.33 103	99.26 113	97.01 174	99.94 37	98.74 86	99.93 46	99.79 35

HPM-MVS		98.79 96	98.53 125	99.59 18	99.65 64	99.29 23	99.16 51	99.43 127	96.74 277	98.61 218	98.38 286	98.62 48	99.87 111	96.47 246	99.67 182	99.59 88
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 131	98.36 153	99.42 60	99.65 64	99.42 11	98.55 114	99.57 69	97.72 195	98.90 176	99.26 113	96.12 218	99.52 340	95.72 286	99.71 161	99.32 213

fmvsm_l_conf0.5_n		99.21 42	99.28 40	99.02 134	99.64 70	97.28 204	97.82 209	99.76 33	98.73 117	99.82 24	99.09 153	98.81 33	99.95 24	99.86 4	99.96 26	99.83 27

test_fmvsmconf_n		99.44 15	99.48 15	99.31 85	99.64 70	98.10 136	97.68 227	99.84 21	99.29 59	99.92 8	99.57 46	99.60 5	99.96 12	99.74 20	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 128	98.49 133	99.06 128	99.64 70	97.90 161	98.51 123	98.94 260	96.96 264	99.24 124	98.89 206	97.83 112	99.81 190	96.88 207	99.49 242	99.48 147
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 92	98.72 95	99.12 112	99.64 70	98.54 102	97.98 189	99.68 48	97.62 201	99.34 102	99.18 131	97.54 138	99.77 227	97.79 145	99.74 145	99.04 267

KD-MVS_self_test		99.25 36	99.18 48	99.44 59	99.63 74	99.06 68	98.69 101	99.54 84	99.31 56	99.62 55	99.53 60	97.36 153	99.86 119	99.24 53	99.71 161	99.39 184

EU-MVSNet		97.66 230	98.50 129	95.13 381	99.63 74	85.84 411	98.35 142	98.21 328	98.23 155	99.54 60	99.46 73	95.02 257	99.68 275	98.24 114	99.87 79	99.87 20

HyFIR lowres test		97.19 268	96.60 292	98.96 141	99.62 76	97.28 204	95.17 375	99.50 93	94.21 354	99.01 154	98.32 294	86.61 353	99.99 2	97.10 186	99.84 88	99.60 82

mmtdpeth		99.30 29	99.42 20	98.92 149	99.58 77	96.89 229	99.48 10	99.92 7	99.92 2	98.26 255	99.80 9	98.33 73	99.91 62	99.56 32	99.95 33	99.97 4

ACMMP_NAP		98.75 103	98.48 134	99.57 20	99.58 77	99.29 23	97.82 209	99.25 200	96.94 266	98.78 195	99.12 146	98.02 100	99.84 149	97.13 184	99.67 182	99.59 88

nrg030		99.40 22	99.35 28	99.54 30	99.58 77	99.13 59	98.98 72	99.48 102	99.68 15	99.46 78	99.26 113	98.62 48	99.73 250	99.17 57	99.92 57	99.76 45

VDDNet		98.21 185	97.95 201	99.01 135	99.58 77	97.74 178	99.01 67	97.29 355	99.67 16	98.97 161	99.50 64	90.45 330	99.80 197	97.88 140	99.20 285	99.48 147

COLMAP_ROB	96.50 10	98.99 69	98.85 83	99.41 62	99.58 77	99.10 64	98.74 92	99.56 76	99.09 89	99.33 103	99.19 127	98.40 66	99.72 257	95.98 273	99.76 141	99.42 171
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 82	97.73 180	97.93 193	99.83 23	99.22 64	99.93 6	99.30 104	99.42 10	99.96 12	99.85 5	99.99 5	99.29 222

ZNCC-MVS		98.68 119	98.40 146	99.54 30	99.57 82	99.21 32	98.46 131	99.29 188	97.28 240	98.11 267	98.39 284	98.00 102	99.87 111	96.86 210	99.64 190	99.55 112

MSP-MVS		98.40 159	98.00 196	99.61 12	99.57 82	99.25 28	98.57 112	99.35 154	97.55 211	99.31 111	97.71 333	94.61 270	99.88 94	96.14 267	99.19 288	99.70 57
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		98.32 170	98.39 149	98.13 252	99.57 82	95.54 274	97.78 214	99.49 100	97.37 231	99.19 129	97.65 337	98.96 24	99.49 349	96.50 245	98.99 313	99.34 206

MP-MVS		98.46 153	98.09 186	99.54 30	99.57 82	99.22 31	98.50 125	99.19 215	97.61 204	97.58 304	98.66 247	97.40 151	99.88 94	94.72 312	99.60 203	99.54 116
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 107	98.46 138	99.47 56	99.57 82	98.97 70	98.23 150	99.48 102	96.60 282	99.10 139	99.06 154	98.71 40	99.83 166	95.58 293	99.78 123	99.62 73

LGP-MVS_train				99.47 56	99.57 82	98.97 70		99.48 102	96.60 282	99.10 139	99.06 154	98.71 40	99.83 166	95.58 293	99.78 123	99.62 73

IS-MVSNet		98.19 187	97.90 207	99.08 120	99.57 82	97.97 154	99.31 27	98.32 324	99.01 99	98.98 157	99.03 165	91.59 320	99.79 210	95.49 295	99.80 113	99.48 147

dcpmvs_2		98.78 98	99.11 57	97.78 274	99.56 90	93.67 340	99.06 62	99.86 16	99.50 33	99.66 46	99.26 113	97.21 163	99.99 2	98.00 132	99.91 64	99.68 59

test_0402		98.76 102	98.71 98	98.93 146	99.56 90	98.14 132	98.45 133	99.34 160	99.28 60	98.95 165	98.91 197	98.34 72	99.79 210	95.63 290	99.91 64	98.86 299

EPP-MVSNet		98.30 173	98.04 192	99.07 122	99.56 90	97.83 167	99.29 33	98.07 335	99.03 97	98.59 222	99.13 145	92.16 314	99.90 68	96.87 208	99.68 176	99.49 137

ACMMP		98.75 103	98.50 129	99.52 42	99.56 90	99.16 47	98.87 84	99.37 145	97.16 255	98.82 192	99.01 175	97.71 122	99.87 111	96.29 258	99.69 171	99.54 116
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 59	99.20 47	98.78 169	99.55 94	96.59 242	97.79 213	99.82 25	98.21 157	99.81 27	99.53 60	98.46 62	99.84 149	99.70 24	99.97 20	99.90 15

fmvsm_s_conf0.5_n		99.09 60	99.26 43	98.61 197	99.55 94	96.09 257	97.74 221	99.81 26	98.55 135	99.85 21	99.55 54	98.60 50	99.84 149	99.69 26	99.98 12	99.89 16

FMVSNet1		99.17 46	99.17 49	99.17 104	99.55 94	98.24 122	99.20 45	99.44 121	99.21 66	99.43 83	99.55 54	97.82 115	99.86 119	98.42 107	99.89 74	99.41 174

Vis-MVSNet (Re-imp)		97.46 244	97.16 254	98.34 236	99.55 94	96.10 254	98.94 77	98.44 318	98.32 146	98.16 261	98.62 256	88.76 340	99.73 250	93.88 338	99.79 118	99.18 247

ACMM	96.08 12	98.91 80	98.73 93	99.48 53	99.55 94	99.14 56	98.07 172	99.37 145	97.62 201	99.04 150	98.96 188	98.84 31	99.79 210	97.43 166	99.65 188	99.49 137
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 111	98.97 71	97.89 267	99.54 99	94.05 321	98.55 114	99.92 7	96.78 275	99.72 35	99.78 10	96.60 198	99.67 278	99.91 2	99.90 70	99.94 10

mPP-MVS		98.64 126	98.34 156	99.54 30	99.54 99	99.17 43	98.63 105	99.24 205	97.47 218	98.09 269	98.68 242	97.62 131	99.89 80	96.22 261	99.62 196	99.57 99

XVG-ACMP-BASELINE		98.56 137	98.34 156	99.22 100	99.54 99	98.59 96	97.71 224	99.46 113	97.25 243	98.98 157	98.99 179	97.54 138	99.84 149	95.88 276	99.74 145	99.23 234

region2R		98.69 114	98.40 146	99.54 30	99.53 102	99.17 43	98.52 118	99.31 172	97.46 223	98.44 240	98.51 270	97.83 112	99.88 94	96.46 247	99.58 212	99.58 94

PGM-MVS		98.66 123	98.37 152	99.55 27	99.53 102	99.18 42	98.23 150	99.49 100	97.01 263	98.69 206	98.88 207	98.00 102	99.89 80	95.87 279	99.59 207	99.58 94

Patchmatch-RL test		97.26 261	97.02 262	97.99 264	99.52 104	95.53 275	96.13 336	99.71 39	97.47 218	99.27 115	99.16 137	84.30 374	99.62 303	97.89 137	99.77 129	98.81 306

ACMMPR		98.70 111	98.42 144	99.54 30	99.52 104	99.14 56	98.52 118	99.31 172	97.47 218	98.56 227	98.54 265	97.75 120	99.88 94	96.57 234	99.59 207	99.58 94

GST-MVS		98.61 132	98.30 161	99.52 42	99.51 106	99.20 38	98.26 148	99.25 200	97.44 226	98.67 209	98.39 284	97.68 123	99.85 131	96.00 271	99.51 234	99.52 127

Anonymous20231206		98.21 185	98.21 172	98.20 247	99.51 106	95.43 280	98.13 162	99.32 167	96.16 300	98.93 173	98.82 219	96.00 223	99.83 166	97.32 171	99.73 148	99.36 200

ACMP	95.32 15	98.41 157	98.09 186	99.36 66	99.51 106	98.79 82	97.68 227	99.38 141	95.76 315	98.81 194	98.82 219	98.36 68	99.82 176	94.75 309	99.77 129	99.48 147
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DVP-MVS		98.77 101	98.52 126	99.52 42	99.50 109	99.21 32	98.02 180	98.84 284	97.97 175	99.08 141	99.02 166	97.61 132	99.88 94	96.99 194	99.63 193	99.48 147
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	99.50 109	99.23 30	98.02 180	99.32 167					99.88 94	96.99 194	99.63 193	99.68 59

test0726					99.50 109	99.21 32	98.17 158	99.35 154	97.97 175	99.26 119	99.06 154	97.61 132

AllTest		98.44 155	98.20 173	99.16 107	99.50 109	98.55 99	98.25 149	99.58 62	96.80 273	98.88 181	99.06 154	97.65 126	99.57 322	94.45 319	99.61 201	99.37 193

TestCases				99.16 107	99.50 109	98.55 99		99.58 62	96.80 273	98.88 181	99.06 154	97.65 126	99.57 322	94.45 319	99.61 201	99.37 193

XVG-OURS		98.53 145	98.34 156	99.11 114	99.50 109	98.82 81	95.97 342	99.50 93	97.30 238	99.05 148	98.98 183	99.35 12	99.32 378	95.72 286	99.68 176	99.18 247

EG-PatchMatch MVS		98.99 69	99.01 66	98.94 144	99.50 109	97.47 193	98.04 177	99.59 60	98.15 168	99.40 91	99.36 91	98.58 54	99.76 233	98.78 81	99.68 176	99.59 88

fmvsm_s_conf0.5_n_2		99.14 51	99.31 35	98.63 192	99.49 116	96.08 259	97.38 260	99.81 26	99.48 34	99.84 22	99.57 46	98.46 62	99.89 80	99.82 8	99.97 20	99.91 13

SED-MVS		98.91 80	98.72 95	99.49 51	99.49 116	99.17 43	98.10 168	99.31 172	98.03 171	99.66 46	99.02 166	98.36 68	99.88 94	96.91 200	99.62 196	99.41 174

IU-MVS					99.49 116	99.15 51		98.87 275	92.97 372	99.41 88				96.76 217	99.62 196	99.66 63

test_241102_ONE					99.49 116	99.17 43		99.31 172	97.98 174	99.66 46	98.90 200	98.36 68	99.48 352

UA-Net		99.47 13	99.40 22	99.70 2	99.49 116	99.29 23	99.80 4	99.72 37	99.82 5	99.04 150	99.81 6	98.05 99	99.96 12	98.85 77	99.99 5	99.86 23

HFP-MVS		98.71 107	98.44 141	99.51 46	99.49 116	99.16 47	98.52 118	99.31 172	97.47 218	98.58 224	98.50 274	97.97 106	99.85 131	96.57 234	99.59 207	99.53 124

VPA-MVSNet		99.30 29	99.30 38	99.28 87	99.49 116	98.36 116	99.00 69	99.45 117	99.63 21	99.52 66	99.44 78	98.25 78	99.88 94	99.09 60	99.84 88	99.62 73

XVG-OURS-SEG-HR		98.49 150	98.28 163	99.14 110	99.49 116	98.83 79	96.54 310	99.48 102	97.32 236	99.11 136	98.61 258	99.33 13	99.30 381	96.23 260	98.38 348	99.28 224

114514_t		96.50 301	95.77 309	98.69 183	99.48 124	97.43 197	97.84 208	99.55 80	81.42 419	96.51 361	98.58 262	95.53 243	99.67 278	93.41 351	99.58 212	98.98 277

IterMVS-LS		98.55 141	98.70 101	98.09 253	99.48 124	94.73 302	97.22 276	99.39 139	98.97 103	99.38 94	99.31 103	96.00 223	99.93 44	98.58 96	99.97 20	99.60 82
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v8		99.01 67	99.16 51	98.57 204	99.47 126	96.31 251	98.90 80	99.47 110	99.03 97	99.52 66	99.57 46	96.93 177	99.81 190	99.60 28	99.98 12	99.60 82

fmvsm_s_conf0.5_n_3		99.22 41	99.37 26	98.78 169	99.46 127	96.58 244	97.65 233	99.72 37	99.47 37	99.86 19	99.50 64	98.94 25	99.89 80	99.75 19	99.97 20	99.86 23

XVS		98.72 106	98.45 139	99.53 37	99.46 127	99.21 32	98.65 103	99.34 160	98.62 125	97.54 308	98.63 254	97.50 144	99.83 166	96.79 213	99.53 229	99.56 105

X-MVStestdata		94.32 349	92.59 367	99.53 37	99.46 127	99.21 32	98.65 103	99.34 160	98.62 125	97.54 308	45.85 424	97.50 144	99.83 166	96.79 213	99.53 229	99.56 105

test20.03		98.78 98	98.77 90	98.78 169	99.46 127	97.20 211	97.78 214	99.24 205	99.04 96	99.41 88	98.90 200	97.65 126	99.76 233	97.70 152	99.79 118	99.39 184

CSCG		98.68 119	98.50 129	99.20 101	99.45 131	98.63 91	98.56 113	99.57 69	97.87 185	98.85 186	98.04 315	97.66 125	99.84 149	96.72 222	99.81 102	99.13 256

GeoE		99.05 65	98.99 69	99.25 95	99.44 132	98.35 117	98.73 96	99.56 76	98.42 140	98.91 175	98.81 221	98.94 25	99.91 62	98.35 109	99.73 148	99.49 137

v148		98.45 154	98.60 118	98.00 263	99.44 132	94.98 295	97.44 258	99.06 241	98.30 148	99.32 109	98.97 185	96.65 196	99.62 303	98.37 108	99.85 84	99.39 184

v10		98.97 73	99.11 57	98.55 209	99.44 132	96.21 253	98.90 80	99.55 80	98.73 117	99.48 73	99.60 42	96.63 197	99.83 166	99.70 24	99.99 5	99.61 81

V42		98.78 98	98.78 89	98.76 174	99.44 132	97.04 219	98.27 147	99.19 215	97.87 185	99.25 123	99.16 137	96.84 181	99.78 221	99.21 54	99.84 88	99.46 156

MDA-MVSNet-bldmvs		97.94 204	97.91 206	98.06 258	99.44 132	94.96 296	96.63 308	99.15 231	98.35 142	98.83 189	99.11 147	94.31 278	99.85 131	96.60 231	98.72 330	99.37 193

casdiffmvs_mvg		99.12 57	99.16 51	98.99 137	99.43 137	97.73 180	98.00 184	99.62 55	99.22 64	99.55 59	99.22 123	98.93 27	99.75 240	98.66 92	99.81 102	99.50 133
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		96.49 302	96.82 276	95.52 374	99.42 138	87.08 408	99.22 42	87.14 422	99.11 79	99.46 78	99.58 44	88.69 341	99.86 119	98.80 79	99.95 33	99.62 73

v2v482		98.56 137	98.62 113	98.37 233	99.42 138	95.81 268	97.58 243	99.16 226	97.90 183	99.28 113	99.01 175	95.98 228	99.79 210	99.33 44	99.90 70	99.51 130

OPM-MVS		98.56 137	98.32 160	99.25 95	99.41 140	98.73 87	97.13 283	99.18 219	97.10 258	98.75 201	98.92 196	98.18 87	99.65 294	96.68 226	99.56 219	99.37 193
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 196	98.08 189	98.04 261	99.41 140	94.59 308	94.59 393	99.40 137	97.50 215	98.82 192	98.83 216	96.83 183	99.84 149	97.50 164	99.81 102	99.71 52

test_one_0601					99.39 142	99.20 38		99.31 172	98.49 137	98.66 211	99.02 166	97.64 129

mvsany_test3		98.87 85	98.92 74	98.74 180	99.38 143	96.94 226	98.58 111	99.10 236	96.49 287	99.96 4	99.81 6	98.18 87	99.45 359	98.97 69	99.79 118	99.83 27

patch_mono-2		98.51 149	98.63 111	98.17 249	99.38 143	94.78 299	97.36 263	99.69 43	98.16 167	98.49 236	99.29 106	97.06 169	99.97 5	98.29 113	99.91 64	99.76 45

test2506		92.39 378	91.89 380	93.89 394	99.38 143	82.28 424	99.32 23	66.03 430	99.08 91	98.77 198	99.57 46	66.26 420	99.84 149	98.71 89	99.95 33	99.54 116

ECVR-MVS		96.42 304	96.61 290	95.85 366	99.38 143	88.18 404	99.22 42	86.00 424	99.08 91	99.36 98	99.57 46	88.47 346	99.82 176	98.52 102	99.95 33	99.54 116

casdiffmvs		98.95 76	99.00 67	98.81 161	99.38 143	97.33 201	97.82 209	99.57 69	99.17 75	99.35 100	99.17 135	98.35 71	99.69 266	98.46 104	99.73 148	99.41 174
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 75	99.02 65	98.76 174	99.38 143	97.26 206	98.49 126	99.50 93	98.86 112	99.19 129	99.06 154	98.23 80	99.69 266	98.71 89	99.76 141	99.33 211

TranMVSNet+NR-MVSNet		99.17 46	99.07 63	99.46 58	99.37 149	98.87 77	98.39 138	99.42 130	99.42 45	99.36 98	99.06 154	98.38 67	99.95 24	98.34 110	99.90 70	99.57 99

tttt0517		95.64 328	94.98 338	97.64 289	99.36 150	93.81 335	98.72 97	90.47 417	98.08 170	98.67 209	98.34 291	73.88 407	99.92 53	97.77 147	99.51 234	99.20 239

test_part2					99.36 150	99.10 64				99.05 148

v1144		98.60 133	98.66 107	98.41 228	99.36 150	95.90 264	97.58 243	99.34 160	97.51 214	99.27 115	99.15 141	96.34 211	99.80 197	99.47 39	99.93 46	99.51 130

CP-MVS		98.70 111	98.42 144	99.52 42	99.36 150	99.12 61	98.72 97	99.36 149	97.54 212	98.30 249	98.40 283	97.86 111	99.89 80	96.53 243	99.72 156	99.56 105

Test_1112_low_res		96.99 283	96.55 294	98.31 239	99.35 154	95.47 278	95.84 354	99.53 87	91.51 389	96.80 350	98.48 277	91.36 322	99.83 166	96.58 232	99.53 229	99.62 73

DeepC-MVS	97.60 4	98.97 73	98.93 73	99.10 116	99.35 154	97.98 153	98.01 183	99.46 113	97.56 209	99.54 60	99.50 64	98.97 23	99.84 149	98.06 127	99.92 57	99.49 137
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 260	96.86 272	98.58 201	99.34 156	96.32 250	96.75 302	99.58 62	93.14 370	96.89 345	97.48 347	92.11 315	99.86 119	96.91 200	99.54 225	99.57 99

reproduce_model		99.15 50	98.97 71	99.67 4	99.33 157	99.44 10	98.15 160	99.47 110	99.12 78	99.52 66	99.32 102	98.31 74	99.90 68	97.78 146	99.73 148	99.66 63

MVSMamba_PlusPlus		98.83 90	98.98 70	98.36 234	99.32 158	96.58 244	98.90 80	99.41 134	99.75 8	98.72 204	99.50 64	96.17 215	99.94 37	99.27 48	99.78 123	98.57 336

SF-MVS		98.53 145	98.27 166	99.32 82	99.31 159	98.75 83	98.19 154	99.41 134	96.77 276	98.83 189	98.90 200	97.80 117	99.82 176	95.68 289	99.52 232	99.38 191

CPTT-MVS		97.84 219	97.36 243	99.27 90	99.31 159	98.46 107	98.29 145	99.27 194	94.90 338	97.83 288	98.37 287	94.90 259	99.84 149	93.85 340	99.54 225	99.51 130

UnsupCasMVSNet_eth		97.89 208	97.60 229	98.75 176	99.31 159	97.17 214	97.62 237	99.35 154	98.72 119	98.76 200	98.68 242	92.57 310	99.74 245	97.76 151	95.60 408	99.34 206

pmmvs-eth3d		98.47 152	98.34 156	98.86 155	99.30 162	97.76 176	97.16 281	99.28 191	95.54 321	99.42 86	99.19 127	97.27 158	99.63 300	97.89 137	99.97 20	99.20 239

mamv4		99.44 15	99.39 23	99.58 19	99.30 162	99.74 2	99.04 65	99.81 26	99.77 7	99.82 24	99.57 46	97.82 115	99.98 4	99.53 34	99.89 74	99.01 271

Anonymous20231211		99.27 33	99.27 41	99.26 92	99.29 164	98.18 128	99.49 9	99.51 91	99.70 12	99.80 28	99.68 22	96.84 181	99.83 166	99.21 54	99.91 64	99.77 40

UnsupCasMVSNet_bld		97.30 258	96.92 268	98.45 223	99.28 165	96.78 236	96.20 331	99.27 194	95.42 325	98.28 253	98.30 295	93.16 296	99.71 258	94.99 303	97.37 384	98.87 298

EC-MVSNet		99.09 60	99.05 64	99.20 101	99.28 165	98.93 75	99.24 41	99.84 21	99.08 91	98.12 266	98.37 287	98.72 39	99.90 68	99.05 63	99.77 129	98.77 314

reproduce-ours		99.09 60	98.90 76	99.67 4	99.27 167	99.49 6	98.00 184	99.42 130	99.05 94	99.48 73	99.27 109	98.29 76	99.89 80	97.61 156	99.71 161	99.62 73

our_new_method		99.09 60	98.90 76	99.67 4	99.27 167	99.49 6	98.00 184	99.42 130	99.05 94	99.48 73	99.27 109	98.29 76	99.89 80	97.61 156	99.71 161	99.62 73

DPE-MVS		98.59 135	98.26 167	99.57 20	99.27 167	99.15 51	97.01 286	99.39 139	97.67 197	99.44 82	98.99 179	97.53 140	99.89 80	95.40 297	99.68 176	99.66 63
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 218	98.18 176	96.87 335	99.27 167	91.16 384	95.53 363	99.25 200	99.10 86	99.41 88	99.35 92	93.10 298	99.96 12	98.65 93	99.94 41	99.49 137

v1192		98.60 133	98.66 107	98.41 228	99.27 167	95.88 265	97.52 249	99.36 149	97.41 227	99.33 103	99.20 126	96.37 209	99.82 176	99.57 30	99.92 57	99.55 112

N_pmnet		97.63 232	97.17 253	98.99 137	99.27 167	97.86 164	95.98 341	93.41 406	95.25 330	99.47 77	98.90 200	95.63 240	99.85 131	96.91 200	99.73 148	99.27 225

FPMVS		93.44 365	92.23 371	97.08 324	99.25 173	97.86 164	95.61 360	97.16 359	92.90 374	93.76 408	98.65 249	75.94 405	95.66 421	79.30 421	97.49 377	97.73 385

new-patchmatchnet		98.35 165	98.74 91	97.18 319	99.24 174	92.23 367	96.42 318	99.48 102	98.30 148	99.69 41	99.53 60	97.44 149	99.82 176	98.84 78	99.77 129	99.49 137

MCST-MVS		98.00 200	97.63 227	99.10 116	99.24 174	98.17 129	96.89 295	98.73 302	95.66 316	97.92 279	97.70 335	97.17 164	99.66 289	96.18 265	99.23 280	99.47 154

UniMVSNet (Re)		98.87 85	98.71 98	99.35 72	99.24 174	98.73 87	97.73 223	99.38 141	98.93 107	99.12 135	98.73 233	96.77 188	99.86 119	98.63 95	99.80 113	99.46 156

jason		97.45 246	97.35 244	97.76 278	99.24 174	93.93 329	95.86 351	98.42 320	94.24 353	98.50 235	98.13 305	94.82 263	99.91 62	97.22 176	99.73 148	99.43 168
jason: jason.
IterMVS		97.73 224	98.11 185	96.57 345	99.24 174	90.28 393	95.52 365	99.21 209	98.86 112	99.33 103	99.33 98	93.11 297	99.94 37	98.49 103	99.94 41	99.48 147
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 141	98.62 113	98.32 237	99.22 179	95.58 273	97.51 251	99.45 117	97.16 255	99.45 81	99.24 118	96.12 218	99.85 131	99.60 28	99.88 76	99.55 112

ITE_SJBPF				98.87 154	99.22 179	98.48 106		99.35 154	97.50 215	98.28 253	98.60 260	97.64 129	99.35 374	93.86 339	99.27 272	98.79 312

h-mvs33		97.77 222	97.33 246	99.10 116	99.21 181	97.84 166	98.35 142	98.57 312	99.11 79	98.58 224	99.02 166	88.65 344	99.96 12	98.11 122	96.34 400	99.49 137

v144192		98.54 143	98.57 121	98.45 223	99.21 181	95.98 262	97.63 236	99.36 149	97.15 257	99.32 109	99.18 131	95.84 235	99.84 149	99.50 37	99.91 64	99.54 116

APDe-MVS		98.99 69	98.79 88	99.60 14	99.21 181	99.15 51	98.87 84	99.48 102	97.57 207	99.35 100	99.24 118	97.83 112	99.89 80	97.88 140	99.70 168	99.75 49
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 78	98.81 87	99.28 87	99.21 181	98.45 108	98.46 131	99.33 165	99.63 21	99.48 73	99.15 141	97.23 161	99.75 240	97.17 178	99.66 187	99.63 72

SR-MVS-dyc-post		98.81 94	98.55 122	99.57 20	99.20 185	99.38 12	98.48 129	99.30 180	98.64 121	98.95 165	98.96 188	97.49 147	99.86 119	96.56 238	99.39 253	99.45 160

RE-MVS-def			98.58 120		99.20 185	99.38 12	98.48 129	99.30 180	98.64 121	98.95 165	98.96 188	97.75 120		96.56 238	99.39 253	99.45 160

v1921920		98.54 143	98.60 118	98.38 231	99.20 185	95.76 270	97.56 245	99.36 149	97.23 249	99.38 94	99.17 135	96.02 221	99.84 149	99.57 30	99.90 70	99.54 116

thisisatest0530		95.27 335	94.45 346	97.74 281	99.19 188	94.37 312	97.86 205	90.20 418	97.17 254	98.22 256	97.65 337	73.53 408	99.90 68	96.90 205	99.35 259	98.95 283

Anonymous20240529		98.93 78	98.87 79	99.12 112	99.19 188	98.22 127	99.01 67	98.99 258	99.25 62	99.54 60	99.37 87	97.04 170	99.80 197	97.89 137	99.52 232	99.35 204

APD-MVS_3200maxsize		98.84 89	98.61 117	99.53 37	99.19 188	99.27 26	98.49 126	99.33 165	98.64 121	99.03 153	98.98 183	97.89 109	99.85 131	96.54 242	99.42 250	99.46 156

HQP_MVS		97.99 203	97.67 221	98.93 146	99.19 188	97.65 184	97.77 216	99.27 194	98.20 161	97.79 291	97.98 318	94.90 259	99.70 262	94.42 321	99.51 234	99.45 160

plane_prior7					99.19 188	97.87 163

ab-mvs		98.41 157	98.36 153	98.59 200	99.19 188	97.23 207	99.32 23	98.81 289	97.66 198	98.62 216	99.40 86	96.82 184	99.80 197	95.88 276	99.51 234	98.75 317

F-COLMAP		97.30 258	96.68 285	99.14 110	99.19 188	98.39 110	97.27 272	99.30 180	92.93 373	96.62 356	98.00 316	95.73 238	99.68 275	92.62 367	98.46 347	99.35 204

SR-MVS		98.71 107	98.43 142	99.57 20	99.18 195	99.35 16	98.36 141	99.29 188	98.29 151	98.88 181	98.85 213	97.53 140	99.87 111	96.14 267	99.31 265	99.48 147

UniMVSNet_NR-MVSNet		98.86 88	98.68 104	99.40 64	99.17 196	98.74 84	97.68 227	99.40 137	99.14 77	99.06 143	98.59 261	96.71 194	99.93 44	98.57 98	99.77 129	99.53 124

LF4IMVS		97.90 206	97.69 220	98.52 214	99.17 196	97.66 183	97.19 280	99.47 110	96.31 295	97.85 287	98.20 302	96.71 194	99.52 340	94.62 313	99.72 156	98.38 353

SMA-MVS		98.40 159	98.03 193	99.51 46	99.16 198	99.21 32	98.05 175	99.22 208	94.16 355	98.98 157	99.10 150	97.52 142	99.79 210	96.45 248	99.64 190	99.53 124
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 92	98.63 111	99.39 65	99.16 198	98.74 84	97.54 247	99.25 200	98.84 115	99.06 143	98.76 230	96.76 190	99.93 44	98.57 98	99.77 129	99.50 133

NR-MVSNet		98.95 76	98.82 85	99.36 66	99.16 198	98.72 89	99.22 42	99.20 211	99.10 86	99.72 35	98.76 230	96.38 208	99.86 119	98.00 132	99.82 98	99.50 133

MVS_111021_LR		98.30 173	98.12 184	98.83 158	99.16 198	98.03 148	96.09 338	99.30 180	97.58 206	98.10 268	98.24 298	98.25 78	99.34 375	96.69 225	99.65 188	99.12 257

DSMNet-mixed		97.42 249	97.60 229	96.87 335	99.15 202	91.46 374	98.54 116	99.12 233	92.87 375	97.58 304	99.63 36	96.21 214	99.90 68	95.74 285	99.54 225	99.27 225

D2MVS		97.84 219	97.84 211	97.83 270	99.14 203	94.74 301	96.94 290	98.88 273	95.84 313	98.89 178	98.96 188	94.40 275	99.69 266	97.55 159	99.95 33	99.05 263

pmmvs5		97.64 231	97.49 235	98.08 256	99.14 203	95.12 292	96.70 305	99.05 244	93.77 362	98.62 216	98.83 216	93.23 294	99.75 240	98.33 112	99.76 141	99.36 200

SPE-MVS-test		99.13 55	99.09 60	99.26 92	99.13 205	98.97 70	99.31 27	99.88 14	99.44 42	98.16 261	98.51 270	98.64 45	99.93 44	98.91 72	99.85 84	98.88 297

VDD-MVS		98.56 137	98.39 149	99.07 122	99.13 205	98.07 143	98.59 110	97.01 362	99.59 27	99.11 136	99.27 109	94.82 263	99.79 210	98.34 110	99.63 193	99.34 206

save fliter					99.11 207	97.97 154	96.53 312	99.02 252	98.24 154

APD-MVS		98.10 192	97.67 221	99.42 60	99.11 207	98.93 75	97.76 219	99.28 191	94.97 336	98.72 204	98.77 228	97.04 170	99.85 131	93.79 341	99.54 225	99.49 137
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 114	98.71 98	98.62 194	99.10 209	96.37 248	97.23 273	98.87 275	99.20 68	99.19 129	98.99 179	97.30 155	99.85 131	98.77 84	99.79 118	99.65 68

EI-MVSNet		98.40 159	98.51 127	98.04 261	99.10 209	94.73 302	97.20 277	98.87 275	98.97 103	99.06 143	99.02 166	96.00 223	99.80 197	98.58 96	99.82 98	99.60 82

CVMVSNet		96.25 309	97.21 252	93.38 400	99.10 209	80.56 427	97.20 277	98.19 331	96.94 266	99.00 155	99.02 166	89.50 337	99.80 197	96.36 254	99.59 207	99.78 38

EI-MVSNet-Vis-set		98.68 119	98.70 101	98.63 192	99.09 212	96.40 247	97.23 273	98.86 280	99.20 68	99.18 133	98.97 185	97.29 157	99.85 131	98.72 88	99.78 123	99.64 69

HPM-MVS++		98.10 192	97.64 226	99.48 53	99.09 212	99.13 59	97.52 249	98.75 299	97.46 223	96.90 344	97.83 328	96.01 222	99.84 149	95.82 283	99.35 259	99.46 156

DP-MVS Recon		97.33 256	96.92 268	98.57 204	99.09 212	97.99 150	96.79 298	99.35 154	93.18 369	97.71 295	98.07 313	95.00 258	99.31 379	93.97 334	99.13 296	98.42 350

MVS_111021_HR		98.25 181	98.08 189	98.75 176	99.09 212	97.46 194	95.97 342	99.27 194	97.60 205	97.99 277	98.25 297	98.15 93	99.38 370	96.87 208	99.57 216	99.42 171

BP-MVS1		97.40 251	96.97 264	98.71 182	99.07 216	96.81 232	98.34 144	97.18 357	98.58 130	98.17 258	98.61 258	84.01 376	99.94 37	98.97 69	99.78 123	99.37 193

9.14			97.78 213		99.07 216		97.53 248	99.32 167	95.53 322	98.54 231	98.70 239	97.58 134	99.76 233	94.32 326	99.46 244

PAPM_NR		96.82 290	96.32 301	98.30 240	99.07 216	96.69 240	97.48 254	98.76 296	95.81 314	96.61 357	96.47 372	94.12 284	99.17 392	90.82 393	97.78 372	99.06 262

TAMVS		98.24 182	98.05 191	98.80 163	99.07 216	97.18 213	97.88 201	98.81 289	96.66 281	99.17 134	99.21 124	94.81 265	99.77 227	96.96 198	99.88 76	99.44 164

CLD-MVS		97.49 242	97.16 254	98.48 220	99.07 216	97.03 220	94.71 386	99.21 209	94.46 347	98.06 271	97.16 359	97.57 135	99.48 352	94.46 318	99.78 123	98.95 283
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 55	99.10 59	99.24 97	99.06 221	99.15 51	99.36 19	99.88 14	99.36 52	98.21 257	98.46 278	98.68 43	99.93 44	99.03 65	99.85 84	98.64 329

thres100view900		94.19 352	93.67 356	95.75 369	99.06 221	91.35 377	98.03 178	94.24 401	98.33 144	97.40 320	94.98 401	79.84 392	99.62 303	83.05 414	98.08 364	96.29 407

thres600view7		94.45 347	93.83 353	96.29 353	99.06 221	91.53 373	97.99 188	94.24 401	98.34 143	97.44 318	95.01 399	79.84 392	99.67 278	84.33 412	98.23 353	97.66 388

plane_prior1					99.05 224

YYNet1		97.60 233	97.67 221	97.39 312	99.04 225	93.04 351	95.27 372	98.38 323	97.25 243	98.92 174	98.95 192	95.48 247	99.73 250	96.99 194	98.74 328	99.41 174

MDA-MVSNet_test_wron		97.60 233	97.66 224	97.41 311	99.04 225	93.09 347	95.27 372	98.42 320	97.26 242	98.88 181	98.95 192	95.43 248	99.73 250	97.02 191	98.72 330	99.41 174

MIMVSNet		96.62 297	96.25 305	97.71 284	99.04 225	94.66 305	99.16 51	96.92 368	97.23 249	97.87 284	99.10 150	86.11 359	99.65 294	91.65 377	99.21 284	98.82 302

PatchMatch-RL		97.24 264	96.78 279	98.61 197	99.03 228	97.83 167	96.36 321	99.06 241	93.49 367	97.36 324	97.78 329	95.75 237	99.49 349	93.44 350	98.77 327	98.52 338

GDP-MVS		97.50 239	97.11 258	98.67 185	99.02 229	96.85 230	98.16 159	99.71 39	98.32 146	98.52 234	98.54 265	83.39 380	99.95 24	98.79 80	99.56 219	99.19 244

ZD-MVS					99.01 230	98.84 78		99.07 240	94.10 357	98.05 273	98.12 307	96.36 210	99.86 119	92.70 366	99.19 288

CDPH-MVS		97.26 261	96.66 288	99.07 122	99.00 231	98.15 130	96.03 340	99.01 255	91.21 393	97.79 291	97.85 327	96.89 179	99.69 266	92.75 364	99.38 256	99.39 184

diffmvs		98.22 183	98.24 170	98.17 249	99.00 231	95.44 279	96.38 320	99.58 62	97.79 191	98.53 232	98.50 274	96.76 190	99.74 245	97.95 136	99.64 190	99.34 206
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		98.40 159	98.19 175	99.03 132	99.00 231	97.65 184	96.85 296	98.94 260	98.57 131	98.89 178	98.50 274	95.60 241	99.85 131	97.54 161	99.85 84	99.59 88

plane_prior6					98.99 234	97.70 182						94.90 259

xiu_mvs_v1_base_debu		97.86 213	98.17 177	96.92 332	98.98 235	93.91 330	96.45 315	99.17 223	97.85 187	98.41 243	97.14 361	98.47 59	99.92 53	98.02 129	99.05 302	96.92 400

xiu_mvs_v1_base		97.86 213	98.17 177	96.92 332	98.98 235	93.91 330	96.45 315	99.17 223	97.85 187	98.41 243	97.14 361	98.47 59	99.92 53	98.02 129	99.05 302	96.92 400

xiu_mvs_v1_base_debi		97.86 213	98.17 177	96.92 332	98.98 235	93.91 330	96.45 315	99.17 223	97.85 187	98.41 243	97.14 361	98.47 59	99.92 53	98.02 129	99.05 302	96.92 400

MVP-Stereo		98.08 195	97.92 205	98.57 204	98.96 238	96.79 233	97.90 199	99.18 219	96.41 291	98.46 238	98.95 192	95.93 232	99.60 310	96.51 244	98.98 315	99.31 217
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 159	98.68 104	97.54 300	98.96 238	97.99 150	97.88 201	99.36 149	98.20 161	99.63 52	99.04 163	98.76 36	95.33 423	96.56 238	99.74 145	99.31 217
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	98.94 240	97.76 176		98.76 296	87.58 410	96.75 352	98.10 309	94.80 266	99.78 221	92.73 365	99.00 311	99.20 239

USDC		97.41 250	97.40 239	97.44 309	98.94 240	93.67 340	95.17 375	99.53 87	94.03 359	98.97 161	99.10 150	95.29 250	99.34 375	95.84 282	99.73 148	99.30 220

tfpn200view9		94.03 356	93.44 358	95.78 368	98.93 242	91.44 375	97.60 240	94.29 399	97.94 179	97.10 330	94.31 408	79.67 394	99.62 303	83.05 414	98.08 364	96.29 407

testdata				98.09 253	98.93 242	95.40 281		98.80 291	90.08 401	97.45 317	98.37 287	95.26 251	99.70 262	93.58 346	98.95 318	99.17 251

thres400		94.14 354	93.44 358	96.24 356	98.93 242	91.44 375	97.60 240	94.29 399	97.94 179	97.10 330	94.31 408	79.67 394	99.62 303	83.05 414	98.08 364	97.66 388

TAPA-MVS	96.21 11	96.63 296	95.95 307	98.65 186	98.93 242	98.09 137	96.93 292	99.28 191	83.58 416	98.13 265	97.78 329	96.13 217	99.40 366	93.52 347	99.29 270	98.45 343
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 246	96.93 227	95.54 362	98.78 294	85.72 413	96.86 347	98.11 308	94.43 273			99.10 301	99.23 234

PVSNet_BlendedMVS		97.55 238	97.53 232	97.60 292	98.92 246	93.77 337	96.64 307	99.43 127	94.49 345	97.62 300	99.18 131	96.82 184	99.67 278	94.73 310	99.93 46	99.36 200

PVSNet_Blended		96.88 286	96.68 285	97.47 307	98.92 246	93.77 337	94.71 386	99.43 127	90.98 395	97.62 300	97.36 355	96.82 184	99.67 278	94.73 310	99.56 219	98.98 277

MSDG		97.71 226	97.52 233	98.28 242	98.91 249	96.82 231	94.42 396	99.37 145	97.65 199	98.37 248	98.29 296	97.40 151	99.33 377	94.09 332	99.22 281	98.68 327

Anonymous202405211		97.90 206	97.50 234	99.08 120	98.90 250	98.25 121	98.53 117	96.16 379	98.87 111	99.11 136	98.86 210	90.40 331	99.78 221	97.36 169	99.31 265	99.19 244

原ACMM1				98.35 235	98.90 250	96.25 252		98.83 288	92.48 379	96.07 372	98.10 309	95.39 249	99.71 258	92.61 368	98.99 313	99.08 259

GBi-Net		98.65 124	98.47 136	99.17 104	98.90 250	98.24 122	99.20 45	99.44 121	98.59 127	98.95 165	99.55 54	94.14 281	99.86 119	97.77 147	99.69 171	99.41 174

test1		98.65 124	98.47 136	99.17 104	98.90 250	98.24 122	99.20 45	99.44 121	98.59 127	98.95 165	99.55 54	94.14 281	99.86 119	97.77 147	99.69 171	99.41 174

FMVSNet2		98.49 150	98.40 146	98.75 176	98.90 250	97.14 217	98.61 108	99.13 232	98.59 127	99.19 129	99.28 107	94.14 281	99.82 176	97.97 134	99.80 113	99.29 222

OMC-MVS		97.88 210	97.49 235	99.04 131	98.89 255	98.63 91	96.94 290	99.25 200	95.02 334	98.53 232	98.51 270	97.27 158	99.47 355	93.50 349	99.51 234	99.01 271

MVSFormer		98.26 179	98.43 142	97.77 275	98.88 256	93.89 333	99.39 17	99.56 76	99.11 79	98.16 261	98.13 305	93.81 289	99.97 5	99.26 49	99.57 216	99.43 168

lupinMVS		97.06 276	96.86 272	97.65 287	98.88 256	93.89 333	95.48 366	97.97 337	93.53 365	98.16 261	97.58 341	93.81 289	99.91 62	96.77 216	99.57 216	99.17 251

dmvs_re		95.98 317	95.39 327	97.74 281	98.86 258	97.45 195	98.37 140	95.69 390	97.95 177	96.56 358	95.95 380	90.70 328	97.68 417	88.32 402	96.13 404	98.11 365

DELS-MVS		98.27 177	98.20 173	98.48 220	98.86 258	96.70 239	95.60 361	99.20 211	97.73 194	98.45 239	98.71 236	97.50 144	99.82 176	98.21 116	99.59 207	98.93 288
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		97.89 208	97.98 198	97.60 292	98.86 258	94.35 313	96.21 330	99.44 121	97.45 225	99.06 143	98.88 207	97.99 105	99.28 385	94.38 325	99.58 212	99.18 247

LCM-MVSNet-Re		98.64 126	98.48 134	99.11 114	98.85 261	98.51 104	98.49 126	99.83 23	98.37 141	99.69 41	99.46 73	98.21 85	99.92 53	94.13 331	99.30 268	98.91 292

pmmvs4		97.58 236	97.28 247	98.51 215	98.84 262	96.93 227	95.40 370	98.52 315	93.60 364	98.61 218	98.65 249	95.10 255	99.60 310	96.97 197	99.79 118	98.99 276

NP-MVS					98.84 262	97.39 199					96.84 364

sss		97.21 266	96.93 266	98.06 258	98.83 264	95.22 288	96.75 302	98.48 317	94.49 345	97.27 326	97.90 324	92.77 306	99.80 197	96.57 234	99.32 263	99.16 254

PVSNet	93.40 17	95.67 326	95.70 312	95.57 373	98.83 264	88.57 400	92.50 413	97.72 342	92.69 377	96.49 364	96.44 373	93.72 292	99.43 362	93.61 344	99.28 271	98.71 320

MVE	83.40 22	92.50 377	91.92 379	94.25 388	98.83 264	91.64 372	92.71 412	83.52 426	95.92 311	86.46 424	95.46 393	95.20 252	95.40 422	80.51 419	98.64 339	95.73 415
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ambc				98.24 245	98.82 267	95.97 263	98.62 107	99.00 257		99.27 115	99.21 124	96.99 175	99.50 346	96.55 241	99.50 241	99.26 228

旧先验1					98.82 267	97.45 195		98.76 296			98.34 291	95.50 246			99.01 310	99.23 234

test_vis1_rt		97.75 223	97.72 219	97.83 270	98.81 269	96.35 249	97.30 268	99.69 43	94.61 343	97.87 284	98.05 314	96.26 213	98.32 412	98.74 86	98.18 356	98.82 302

WTY-MVS		96.67 294	96.27 304	97.87 268	98.81 269	94.61 307	96.77 300	97.92 339	94.94 337	97.12 329	97.74 332	91.11 324	99.82 176	93.89 337	98.15 360	99.18 247

3Dnovator+	97.89 3	98.69 114	98.51 127	99.24 97	98.81 269	98.40 109	99.02 66	99.19 215	98.99 100	98.07 270	99.28 107	97.11 168	99.84 149	96.84 211	99.32 263	99.47 154

QAPM		97.31 257	96.81 278	98.82 159	98.80 272	97.49 192	99.06 62	99.19 215	90.22 399	97.69 297	99.16 137	96.91 178	99.90 68	90.89 392	99.41 251	99.07 261

VNet		98.42 156	98.30 161	98.79 166	98.79 273	97.29 203	98.23 150	98.66 306	99.31 56	98.85 186	98.80 222	94.80 266	99.78 221	98.13 121	99.13 296	99.31 217

DPM-MVS		96.32 306	95.59 318	98.51 215	98.76 274	97.21 210	94.54 395	98.26 326	91.94 384	96.37 365	97.25 357	93.06 300	99.43 362	91.42 382	98.74 328	98.89 294

3Dnovator	98.27 2	98.81 94	98.73 93	99.05 129	98.76 274	97.81 173	99.25 40	99.30 180	98.57 131	98.55 229	99.33 98	97.95 107	99.90 68	97.16 179	99.67 182	99.44 164

PLC	94.65 16	96.51 299	95.73 311	98.85 156	98.75 276	97.91 160	96.42 318	99.06 241	90.94 396	95.59 378	97.38 353	94.41 274	99.59 314	90.93 390	98.04 369	99.05 263
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 288	96.75 281	97.08 324	98.74 277	93.33 345	96.71 304	98.26 326	96.72 278	98.44 240	97.37 354	95.20 252	99.47 355	91.89 373	97.43 381	98.44 346

hse-mvs2		97.46 244	97.07 259	98.64 188	98.73 278	97.33 201	97.45 257	97.64 348	99.11 79	98.58 224	97.98 318	88.65 344	99.79 210	98.11 122	97.39 383	98.81 306

CDS-MVSNet		97.69 227	97.35 244	98.69 183	98.73 278	97.02 221	96.92 294	98.75 299	95.89 312	98.59 222	98.67 244	92.08 316	99.74 245	96.72 222	99.81 102	99.32 213
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EIA-MVS		98.00 200	97.74 216	98.80 163	98.72 280	98.09 137	98.05 175	99.60 59	97.39 229	96.63 355	95.55 388	97.68 123	99.80 197	96.73 221	99.27 272	98.52 338

LFMVS		97.20 267	96.72 282	98.64 188	98.72 280	96.95 225	98.93 78	94.14 403	99.74 10	98.78 195	99.01 175	84.45 371	99.73 250	97.44 165	99.27 272	99.25 229

new_pmnet		96.99 283	96.76 280	97.67 285	98.72 280	94.89 297	95.95 346	98.20 329	92.62 378	98.55 229	98.54 265	94.88 262	99.52 340	93.96 335	99.44 249	98.59 335

Fast-Effi-MVS+		97.67 229	97.38 241	98.57 204	98.71 283	97.43 197	97.23 273	99.45 117	94.82 340	96.13 369	96.51 369	98.52 57	99.91 62	96.19 263	98.83 324	98.37 355

TEST9					98.71 283	98.08 141	95.96 344	99.03 249	91.40 390	95.85 375	97.53 343	96.52 201	99.76 233

train_agg		97.10 273	96.45 298	99.07 122	98.71 283	98.08 141	95.96 344	99.03 249	91.64 385	95.85 375	97.53 343	96.47 203	99.76 233	93.67 343	99.16 291	99.36 200

TSAR-MVS + GP.		98.18 188	97.98 198	98.77 173	98.71 283	97.88 162	96.32 324	98.66 306	96.33 293	99.23 126	98.51 270	97.48 148	99.40 366	97.16 179	99.46 244	99.02 270

FA-MVS(test-final)		96.99 283	96.82 276	97.50 304	98.70 287	94.78 299	99.34 20	96.99 363	95.07 333	98.48 237	99.33 98	88.41 347	99.65 294	96.13 269	98.92 321	98.07 368

AUN-MVS		96.24 311	95.45 323	98.60 199	98.70 287	97.22 209	97.38 260	97.65 346	95.95 310	95.53 385	97.96 322	82.11 388	99.79 210	96.31 256	97.44 380	98.80 311

our_test_3		97.39 252	97.73 218	96.34 351	98.70 287	89.78 396	94.61 392	98.97 259	96.50 286	99.04 150	98.85 213	95.98 228	99.84 149	97.26 174	99.67 182	99.41 174

ppachtmachnet_test		97.50 239	97.74 216	96.78 341	98.70 287	91.23 383	94.55 394	99.05 244	96.36 292	99.21 127	98.79 224	96.39 206	99.78 221	96.74 219	99.82 98	99.34 206

PCF-MVS	92.86 18	94.36 348	93.00 365	98.42 227	98.70 287	97.56 189	93.16 411	99.11 235	79.59 420	97.55 307	97.43 350	92.19 313	99.73 250	79.85 420	99.45 246	97.97 374
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 205	98.02 194	97.58 294	98.69 292	94.10 320	98.13 162	98.90 269	97.95 177	97.32 325	99.58 44	95.95 231	98.75 407	96.41 250	99.22 281	99.87 20

ETV-MVS		98.03 197	97.86 210	98.56 208	98.69 292	98.07 143	97.51 251	99.50 93	98.10 169	97.50 312	95.51 389	98.41 65	99.88 94	96.27 259	99.24 277	97.71 387

test_prior				98.95 143	98.69 292	97.95 158		99.03 249					99.59 314			99.30 220

mvsmamba		97.57 237	97.26 248	98.51 215	98.69 292	96.73 238	98.74 92	97.25 356	97.03 262	97.88 283	99.23 122	90.95 325	99.87 111	96.61 230	99.00 311	98.91 292

agg_prior					98.68 296	97.99 150		99.01 255		95.59 378			99.77 227

test_8					98.67 297	98.01 149	95.91 350	99.02 252	91.64 385	95.79 377	97.50 346	96.47 203	99.76 233

HQP-NCC					98.67 297		96.29 326		96.05 303	95.55 381

ACMP_Plane					98.67 297		96.29 326		96.05 303	95.55 381

CNVR-MVS		98.17 190	97.87 209	99.07 122	98.67 297	98.24 122	97.01 286	98.93 263	97.25 243	97.62 300	98.34 291	97.27 158	99.57 322	96.42 249	99.33 262	99.39 184

HQP-MVS		97.00 282	96.49 297	98.55 209	98.67 297	96.79 233	96.29 326	99.04 247	96.05 303	95.55 381	96.84 364	93.84 287	99.54 334	92.82 361	99.26 275	99.32 213

MM		98.22 183	97.99 197	98.91 150	98.66 302	96.97 222	97.89 200	94.44 397	99.54 30	98.95 165	99.14 144	93.50 293	99.92 53	99.80 13	99.96 26	99.85 25

test_fmvs1		97.72 225	97.94 203	97.07 326	98.66 302	92.39 362	97.68 227	99.81 26	95.20 332	99.54 60	99.44 78	91.56 321	99.41 365	99.78 16	99.77 129	99.40 183

balanced_conf03		98.63 128	98.72 95	98.38 231	98.66 302	96.68 241	98.90 80	99.42 130	98.99 100	98.97 161	99.19 127	95.81 236	99.85 131	98.77 84	99.77 129	98.60 332

thres200		93.72 361	93.14 363	95.46 377	98.66 302	91.29 379	96.61 309	94.63 396	97.39 229	96.83 348	93.71 411	79.88 391	99.56 325	82.40 417	98.13 361	95.54 416

wuyk23d		96.06 313	97.62 228	91.38 403	98.65 306	98.57 98	98.85 87	96.95 366	96.86 271	99.90 12	99.16 137	99.18 17	98.40 411	89.23 400	99.77 129	77.18 423

NCCC		97.86 213	97.47 238	99.05 129	98.61 307	98.07 143	96.98 288	98.90 269	97.63 200	97.04 334	97.93 323	95.99 227	99.66 289	95.31 298	98.82 326	99.43 168

DeepC-MVS_fast	96.85 6	98.30 173	98.15 181	98.75 176	98.61 307	97.23 207	97.76 219	99.09 238	97.31 237	98.75 201	98.66 247	97.56 136	99.64 297	96.10 270	99.55 223	99.39 184
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 363	92.09 373	97.75 279	98.60 309	94.40 311	97.32 266	95.26 392	97.56 209	96.79 351	95.50 390	53.57 429	99.77 227	95.26 299	98.97 316	99.08 259

thisisatest0515		94.12 355	93.16 362	96.97 330	98.60 309	92.90 352	93.77 407	90.61 416	94.10 357	96.91 341	95.87 383	74.99 406	99.80 197	94.52 316	99.12 299	98.20 361

GA-MVS		95.86 320	95.32 330	97.49 305	98.60 309	94.15 319	93.83 406	97.93 338	95.49 323	96.68 353	97.42 351	83.21 381	99.30 381	96.22 261	98.55 345	99.01 271

dmvs_testset		92.94 373	92.21 372	95.13 381	98.59 312	90.99 386	97.65 233	92.09 412	96.95 265	94.00 404	93.55 412	92.34 312	96.97 420	72.20 423	92.52 418	97.43 395

OPU-MVS				98.82 159	98.59 312	98.30 118	98.10 168				98.52 269	98.18 87	98.75 407	94.62 313	99.48 243	99.41 174

MSLP-MVS++		98.02 198	98.14 183	97.64 289	98.58 314	95.19 289	97.48 254	99.23 207	97.47 218	97.90 281	98.62 256	97.04 170	98.81 406	97.55 159	99.41 251	98.94 287

test12				98.93 146	98.58 314	97.83 167		98.66 306		96.53 359		95.51 245	99.69 266		99.13 296	99.27 225

CL-MVSNet_self_test		97.44 247	97.22 251	98.08 256	98.57 316	95.78 269	94.30 399	98.79 292	96.58 284	98.60 220	98.19 303	94.74 269	99.64 297	96.41 250	98.84 323	98.82 302

PS-MVSNAJ		97.08 275	97.39 240	96.16 362	98.56 317	92.46 360	95.24 374	98.85 283	97.25 243	97.49 313	95.99 379	98.07 96	99.90 68	96.37 252	98.67 338	96.12 412

CNLPA		97.17 270	96.71 283	98.55 209	98.56 317	98.05 147	96.33 323	98.93 263	96.91 268	97.06 333	97.39 352	94.38 276	99.45 359	91.66 376	99.18 290	98.14 364

xiu_mvs_v2_base		97.16 271	97.49 235	96.17 360	98.54 319	92.46 360	95.45 367	98.84 284	97.25 243	97.48 314	96.49 370	98.31 74	99.90 68	96.34 255	98.68 337	96.15 411

alignmvs		97.35 254	96.88 271	98.78 169	98.54 319	98.09 137	97.71 224	97.69 344	99.20 68	97.59 303	95.90 382	88.12 349	99.55 329	98.18 118	98.96 317	98.70 323

FE-MVS		95.66 327	94.95 340	97.77 275	98.53 321	95.28 285	99.40 16	96.09 381	93.11 371	97.96 278	99.26 113	79.10 398	99.77 227	92.40 370	98.71 332	98.27 359

Effi-MVS+		98.02 198	97.82 212	98.62 194	98.53 321	97.19 212	97.33 265	99.68 48	97.30 238	96.68 353	97.46 349	98.56 55	99.80 197	96.63 228	98.20 355	98.86 299

baseline1		95.96 318	95.44 324	97.52 302	98.51 323	93.99 327	98.39 138	96.09 381	98.21 157	98.40 247	97.76 331	86.88 351	99.63 300	95.42 296	89.27 421	98.95 283

MVS_Test		98.18 188	98.36 153	97.67 285	98.48 324	94.73 302	98.18 155	99.02 252	97.69 196	98.04 274	99.11 147	97.22 162	99.56 325	98.57 98	98.90 322	98.71 320

MGCFI-Net		98.34 166	98.28 163	98.51 215	98.47 325	97.59 188	98.96 74	99.48 102	99.18 74	97.40 320	95.50 390	98.66 44	99.50 346	98.18 118	98.71 332	98.44 346

BH-RMVSNet		96.83 288	96.58 293	97.58 294	98.47 325	94.05 321	96.67 306	97.36 351	96.70 280	97.87 284	97.98 318	95.14 254	99.44 361	90.47 395	98.58 344	99.25 229

sasdasda		98.34 166	98.26 167	98.58 201	98.46 327	97.82 170	98.96 74	99.46 113	99.19 72	97.46 315	95.46 393	98.59 51	99.46 357	98.08 125	98.71 332	98.46 340

canonicalmvs		98.34 166	98.26 167	98.58 201	98.46 327	97.82 170	98.96 74	99.46 113	99.19 72	97.46 315	95.46 393	98.59 51	99.46 357	98.08 125	98.71 332	98.46 340

MVS-HIRNet		94.32 349	95.62 315	90.42 404	98.46 327	75.36 428	96.29 326	89.13 420	95.25 330	95.38 387	99.75 13	92.88 303	99.19 391	94.07 333	99.39 253	96.72 405

PHI-MVS		98.29 176	97.95 201	99.34 75	98.44 330	99.16 47	98.12 165	99.38 141	96.01 307	98.06 271	98.43 281	97.80 117	99.67 278	95.69 288	99.58 212	99.20 239

DVP-MVS++		98.90 82	98.70 101	99.51 46	98.43 331	99.15 51	99.43 12	99.32 167	98.17 164	99.26 119	99.02 166	98.18 87	99.88 94	97.07 188	99.45 246	99.49 137

MSC_two_6792asdad				99.32 82	98.43 331	98.37 113		98.86 280					99.89 80	97.14 182	99.60 203	99.71 52

No_MVS				99.32 82	98.43 331	98.37 113		98.86 280					99.89 80	97.14 182	99.60 203	99.71 52

Fast-Effi-MVS+-dtu		98.27 177	98.09 186	98.81 161	98.43 331	98.11 134	97.61 239	99.50 93	98.64 121	97.39 322	97.52 345	98.12 95	99.95 24	96.90 205	98.71 332	98.38 353

OpenMVS_ROB	95.38 14	95.84 322	95.18 335	97.81 272	98.41 335	97.15 216	97.37 262	98.62 310	83.86 415	98.65 212	98.37 287	94.29 279	99.68 275	88.41 401	98.62 342	96.60 406

DeepPCF-MVS	96.93 5	98.32 170	98.01 195	99.23 99	98.39 336	98.97 70	95.03 379	99.18 219	96.88 269	99.33 103	98.78 226	98.16 91	99.28 385	96.74 219	99.62 196	99.44 164

Patchmatch-test		96.55 298	96.34 300	97.17 321	98.35 337	93.06 348	98.40 137	97.79 340	97.33 234	98.41 243	98.67 244	83.68 379	99.69 266	95.16 301	99.31 265	98.77 314

AdaColmap		97.14 272	96.71 283	98.46 222	98.34 338	97.80 174	96.95 289	98.93 263	95.58 320	96.92 339	97.66 336	95.87 234	99.53 336	90.97 389	99.14 294	98.04 369

OpenMVS	96.65 7	97.09 274	96.68 285	98.32 237	98.32 339	97.16 215	98.86 86	99.37 145	89.48 403	96.29 367	99.15 141	96.56 199	99.90 68	92.90 358	99.20 285	97.89 375

MG-MVS		96.77 291	96.61 290	97.26 317	98.31 340	93.06 348	95.93 347	98.12 334	96.45 290	97.92 279	98.73 233	93.77 291	99.39 368	91.19 387	99.04 305	99.33 211

test_yl		96.69 292	96.29 302	97.90 265	98.28 341	95.24 286	97.29 269	97.36 351	98.21 157	98.17 258	97.86 325	86.27 355	99.55 329	94.87 307	98.32 349	98.89 294

DCV-MVSNet		96.69 292	96.29 302	97.90 265	98.28 341	95.24 286	97.29 269	97.36 351	98.21 157	98.17 258	97.86 325	86.27 355	99.55 329	94.87 307	98.32 349	98.89 294

CHOSEN 280x420		95.51 332	95.47 321	95.65 372	98.25 343	88.27 403	93.25 410	98.88 273	93.53 365	94.65 396	97.15 360	86.17 357	99.93 44	97.41 167	99.93 46	98.73 319

SCA		96.41 305	96.66 288	95.67 370	98.24 344	88.35 402	95.85 353	96.88 369	96.11 301	97.67 298	98.67 244	93.10 298	99.85 131	94.16 327	99.22 281	98.81 306

DeepMVS_CX				93.44 399	98.24 344	94.21 316		94.34 398	64.28 423	91.34 417	94.87 405	89.45 338	92.77 424	77.54 422	93.14 417	93.35 419

MS-PatchMatch		97.68 228	97.75 215	97.45 308	98.23 346	93.78 336	97.29 269	98.84 284	96.10 302	98.64 213	98.65 249	96.04 220	99.36 371	96.84 211	99.14 294	99.20 239

BH-w/o		95.13 338	94.89 342	95.86 365	98.20 347	91.31 378	95.65 359	97.37 350	93.64 363	96.52 360	95.70 386	93.04 301	99.02 397	88.10 403	95.82 407	97.24 398

mvs_anonymous		97.83 221	98.16 180	96.87 335	98.18 348	91.89 369	97.31 267	98.90 269	97.37 231	98.83 189	99.46 73	96.28 212	99.79 210	98.90 73	98.16 359	98.95 283

miper_lstm_enhance		97.18 269	97.16 254	97.25 318	98.16 349	92.85 353	95.15 377	99.31 172	97.25 243	98.74 203	98.78 226	90.07 332	99.78 221	97.19 177	99.80 113	99.11 258

RRT-MVS		97.88 210	97.98 198	97.61 291	98.15 350	93.77 337	98.97 73	99.64 53	99.16 76	98.69 206	99.42 80	91.60 319	99.89 80	97.63 155	98.52 346	99.16 254

ET-MVSNet_ETH3D		94.30 351	93.21 361	97.58 294	98.14 351	94.47 310	94.78 385	93.24 408	94.72 341	89.56 419	95.87 383	78.57 401	99.81 190	96.91 200	97.11 392	98.46 340

ADS-MVSNet2		95.43 333	94.98 338	96.76 342	98.14 351	91.74 370	97.92 196	97.76 341	90.23 397	96.51 361	98.91 197	85.61 362	99.85 131	92.88 359	96.90 393	98.69 324

ADS-MVSNet		95.24 336	94.93 341	96.18 359	98.14 351	90.10 395	97.92 196	97.32 354	90.23 397	96.51 361	98.91 197	85.61 362	99.74 245	92.88 359	96.90 393	98.69 324

c3_l		97.36 253	97.37 242	97.31 313	98.09 354	93.25 346	95.01 380	99.16 226	97.05 259	98.77 198	98.72 235	92.88 303	99.64 297	96.93 199	99.76 141	99.05 263

FMVSNet3		97.50 239	97.24 250	98.29 241	98.08 355	95.83 267	97.86 205	98.91 268	97.89 184	98.95 165	98.95 192	87.06 350	99.81 190	97.77 147	99.69 171	99.23 234

PAPM		91.88 386	90.34 389	96.51 346	98.06 356	92.56 358	92.44 414	97.17 358	86.35 411	90.38 418	96.01 378	86.61 353	99.21 390	70.65 424	95.43 409	97.75 384

Effi-MVS+-dtu		98.26 179	97.90 207	99.35 72	98.02 357	99.49 6	98.02 180	99.16 226	98.29 151	97.64 299	97.99 317	96.44 205	99.95 24	96.66 227	98.93 320	98.60 332

eth_miper_zixun_eth		97.23 265	97.25 249	97.17 321	98.00 358	92.77 355	94.71 386	99.18 219	97.27 241	98.56 227	98.74 232	91.89 317	99.69 266	97.06 190	99.81 102	99.05 263

HY-MVS	95.94 13	95.90 319	95.35 329	97.55 299	97.95 359	94.79 298	98.81 91	96.94 367	92.28 382	95.17 389	98.57 263	89.90 334	99.75 240	91.20 386	97.33 388	98.10 366

UGNet		98.53 145	98.45 139	98.79 166	97.94 360	96.96 224	99.08 58	98.54 313	99.10 86	96.82 349	99.47 72	96.55 200	99.84 149	98.56 101	99.94 41	99.55 112
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
MAR-MVS		96.47 303	95.70 312	98.79 166	97.92 361	99.12 61	98.28 146	98.60 311	92.16 383	95.54 384	96.17 377	94.77 268	99.52 340	89.62 398	98.23 353	97.72 386
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		96.86 287	96.55 294	97.79 273	97.91 362	94.21 316	97.56 245	98.87 275	97.49 217	99.06 143	99.05 161	80.72 389	99.80 197	98.44 105	99.82 98	99.37 193

API-MVS		97.04 278	96.91 270	97.42 310	97.88 363	98.23 126	98.18 155	98.50 316	97.57 207	97.39 322	96.75 366	96.77 188	99.15 394	90.16 396	99.02 309	94.88 417

miper_ehance_all_eth		97.06 276	97.03 261	97.16 323	97.83 364	93.06 348	94.66 389	99.09 238	95.99 308	98.69 206	98.45 279	92.73 308	99.61 309	96.79 213	99.03 306	98.82 302

cl____		97.02 279	96.83 275	97.58 294	97.82 365	94.04 323	94.66 389	99.16 226	97.04 260	98.63 214	98.71 236	88.68 343	99.69 266	97.00 192	99.81 102	99.00 275

DIV-MVS_self_test		97.02 279	96.84 274	97.58 294	97.82 365	94.03 324	94.66 389	99.16 226	97.04 260	98.63 214	98.71 236	88.69 341	99.69 266	97.00 192	99.81 102	99.01 271

CANet		97.87 212	97.76 214	98.19 248	97.75 367	95.51 276	96.76 301	99.05 244	97.74 193	96.93 338	98.21 301	95.59 242	99.89 80	97.86 142	99.93 46	99.19 244

UBG		93.25 368	92.32 369	96.04 364	97.72 368	90.16 394	95.92 349	95.91 385	96.03 306	93.95 406	93.04 416	69.60 412	99.52 340	90.72 394	97.98 370	98.45 343

mvsany_test1		97.60 233	97.54 231	97.77 275	97.72 368	95.35 282	95.36 371	97.13 360	94.13 356	99.71 37	99.33 98	97.93 108	99.30 381	97.60 158	98.94 319	98.67 328

PVSNet_0	89.98 21	91.15 387	90.30 390	93.70 396	97.72 368	84.34 420	90.24 417	97.42 349	90.20 400	93.79 407	93.09 415	90.90 327	98.89 405	86.57 409	72.76 424	97.87 377

CR-MVSNet		96.28 308	95.95 307	97.28 315	97.71 371	94.22 314	98.11 166	98.92 266	92.31 381	96.91 341	99.37 87	85.44 365	99.81 190	97.39 168	97.36 386	97.81 380

RPMNet		97.02 279	96.93 266	97.30 314	97.71 371	94.22 314	98.11 166	99.30 180	99.37 49	96.91 341	99.34 96	86.72 352	99.87 111	97.53 162	97.36 386	97.81 380

ETVMVS		92.60 376	91.08 385	97.18 319	97.70 373	93.65 342	96.54 310	95.70 388	96.51 285	94.68 395	92.39 419	61.80 426	99.50 346	86.97 406	97.41 382	98.40 351

pmmvs3		95.03 340	94.40 347	96.93 331	97.70 373	92.53 359	95.08 378	97.71 343	88.57 407	97.71 295	98.08 312	79.39 396	99.82 176	96.19 263	99.11 300	98.43 348

baseline2		93.73 360	92.83 366	96.42 349	97.70 373	91.28 380	96.84 297	89.77 419	93.96 361	92.44 414	95.93 381	79.14 397	99.77 227	92.94 357	96.76 397	98.21 360

WBMVS		95.18 337	94.78 343	96.37 350	97.68 376	89.74 397	95.80 355	98.73 302	97.54 212	98.30 249	98.44 280	70.06 410	99.82 176	96.62 229	99.87 79	99.54 116

tpm		94.67 345	94.34 349	95.66 371	97.68 376	88.42 401	97.88 201	94.90 393	94.46 347	96.03 374	98.56 264	78.66 399	99.79 210	95.88 276	95.01 411	98.78 313

CANet_DTU		97.26 261	97.06 260	97.84 269	97.57 378	94.65 306	96.19 332	98.79 292	97.23 249	95.14 390	98.24 298	93.22 295	99.84 149	97.34 170	99.84 88	99.04 267

testing11		93.08 371	92.02 375	96.26 355	97.56 379	90.83 389	96.32 324	95.70 388	96.47 289	92.66 413	93.73 410	64.36 424	99.59 314	93.77 342	97.57 375	98.37 355

tpm2		93.09 370	92.58 368	94.62 385	97.56 379	86.53 409	97.66 231	95.79 387	86.15 412	94.07 403	98.23 300	75.95 404	99.53 336	90.91 391	96.86 396	97.81 380

testing91		93.32 366	92.27 370	96.47 348	97.54 381	91.25 381	96.17 335	96.76 371	97.18 253	93.65 409	93.50 413	65.11 423	99.63 300	93.04 356	97.45 379	98.53 337

TR-MVS		95.55 330	95.12 336	96.86 338	97.54 381	93.94 328	96.49 314	96.53 376	94.36 352	97.03 336	96.61 368	94.26 280	99.16 393	86.91 408	96.31 401	97.47 394

testing99		93.04 372	91.98 378	96.23 357	97.53 383	90.70 391	96.35 322	95.94 384	96.87 270	93.41 410	93.43 414	63.84 425	99.59 314	93.24 354	97.19 389	98.40 351

1314		95.74 324	95.60 316	96.17 360	97.53 383	92.75 356	98.07 172	98.31 325	91.22 392	94.25 399	96.68 367	95.53 243	99.03 396	91.64 378	97.18 390	96.74 404

CostFormer		93.97 357	93.78 354	94.51 386	97.53 383	85.83 412	97.98 189	95.96 383	89.29 405	94.99 392	98.63 254	78.63 400	99.62 303	94.54 315	96.50 398	98.09 367

FMVSNet5		96.01 315	95.20 334	98.41 228	97.53 383	96.10 254	98.74 92	99.50 93	97.22 252	98.03 275	99.04 163	69.80 411	99.88 94	97.27 173	99.71 161	99.25 229

PMMVS		96.51 299	95.98 306	98.09 253	97.53 383	95.84 266	94.92 382	98.84 284	91.58 387	96.05 373	95.58 387	95.68 239	99.66 289	95.59 292	98.09 363	98.76 316

reproduce_monomvs		95.00 342	95.25 331	94.22 389	97.51 388	83.34 421	97.86 205	98.44 318	98.51 136	99.29 112	99.30 104	67.68 416	99.56 325	98.89 75	99.81 102	99.77 40

PAPR		95.29 334	94.47 345	97.75 279	97.50 389	95.14 291	94.89 383	98.71 304	91.39 391	95.35 388	95.48 392	94.57 271	99.14 395	84.95 411	97.37 384	98.97 280

testing222		91.96 384	90.37 388	96.72 343	97.47 390	92.59 357	96.11 337	94.76 394	96.83 272	92.90 412	92.87 417	57.92 427	99.55 329	86.93 407	97.52 376	98.00 373

PatchT		96.65 295	96.35 299	97.54 300	97.40 391	95.32 284	97.98 189	96.64 373	99.33 54	96.89 345	99.42 80	84.32 373	99.81 190	97.69 154	97.49 377	97.48 393

tpm cat1		93.29 367	93.13 364	93.75 395	97.39 392	84.74 415	97.39 259	97.65 346	83.39 417	94.16 400	98.41 282	82.86 384	99.39 368	91.56 380	95.35 410	97.14 399

PatchmatchNet		95.58 329	95.67 314	95.30 380	97.34 393	87.32 407	97.65 233	96.65 372	95.30 329	97.07 332	98.69 240	84.77 368	99.75 240	94.97 305	98.64 339	98.83 301
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 254	96.97 264	98.50 219	97.31 394	96.47 246	98.18 155	98.92 266	98.95 106	98.78 195	99.37 87	85.44 365	99.85 131	95.96 274	99.83 95	99.17 251

LS3D		98.63 128	98.38 151	99.36 66	97.25 395	99.38 12	99.12 57	99.32 167	99.21 66	98.44 240	98.88 207	97.31 154	99.80 197	96.58 232	99.34 261	98.92 289

IB-MVS	91.63 19	92.24 382	90.90 386	96.27 354	97.22 396	91.24 382	94.36 398	93.33 407	92.37 380	92.24 415	94.58 407	66.20 421	99.89 80	93.16 355	94.63 413	97.66 388
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		92.38 379	91.76 382	94.21 390	97.16 397	84.65 416	95.42 369	88.45 421	95.96 309	96.17 368	95.84 385	66.36 419	99.71 258	91.87 374	98.64 339	98.28 358

tpmrst		95.07 339	95.46 322	93.91 393	97.11 398	84.36 419	97.62 237	96.96 365	94.98 335	96.35 366	98.80 222	85.46 364	99.59 314	95.60 291	96.23 402	97.79 383

Syy-MVS		96.04 314	95.56 320	97.49 305	97.10 399	94.48 309	96.18 333	96.58 374	95.65 317	94.77 393	92.29 420	91.27 323	99.36 371	98.17 120	98.05 367	98.63 330

myMVS_eth3d		91.92 385	90.45 387	96.30 352	97.10 399	90.90 387	96.18 333	96.58 374	95.65 317	94.77 393	92.29 420	53.88 428	99.36 371	89.59 399	98.05 367	98.63 330

MDTV_nov1_ep13			95.22 333		97.06 401	83.20 422	97.74 221	96.16 379	94.37 351	96.99 337	98.83 216	83.95 377	99.53 336	93.90 336	97.95 371

MVS		93.19 369	92.09 373	96.50 347	96.91 402	94.03 324	98.07 172	98.06 336	68.01 422	94.56 398	96.48 371	95.96 230	99.30 381	83.84 413	96.89 395	96.17 409

E-PMN		94.17 353	94.37 348	93.58 397	96.86 403	85.71 413	90.11 419	97.07 361	98.17 164	97.82 290	97.19 358	84.62 370	98.94 401	89.77 397	97.68 374	96.09 413

JIA-IIPM		95.52 331	95.03 337	97.00 327	96.85 404	94.03 324	96.93 292	95.82 386	99.20 68	94.63 397	99.71 19	83.09 382	99.60 310	94.42 321	94.64 412	97.36 397

EMVS		93.83 359	94.02 351	93.23 401	96.83 405	84.96 414	89.77 420	96.32 378	97.92 181	97.43 319	96.36 376	86.17 357	98.93 402	87.68 404	97.73 373	95.81 414

cl22		95.79 323	95.39 327	96.98 329	96.77 406	92.79 354	94.40 397	98.53 314	94.59 344	97.89 282	98.17 304	82.82 385	99.24 387	96.37 252	99.03 306	98.92 289

WB-MVSnew		95.73 325	95.57 319	96.23 357	96.70 407	90.70 391	96.07 339	93.86 404	95.60 319	97.04 334	95.45 396	96.00 223	99.55 329	91.04 388	98.31 351	98.43 348

dp		93.47 364	93.59 357	93.13 402	96.64 408	81.62 426	97.66 231	96.42 377	92.80 376	96.11 370	98.64 252	78.55 402	99.59 314	93.31 352	92.18 420	98.16 363

MonoMVSNet		96.25 309	96.53 296	95.39 378	96.57 409	91.01 385	98.82 90	97.68 345	98.57 131	98.03 275	99.37 87	90.92 326	97.78 416	94.99 303	93.88 416	97.38 396

test-LLR		93.90 358	93.85 352	94.04 391	96.53 410	84.62 417	94.05 403	92.39 410	96.17 298	94.12 401	95.07 397	82.30 386	99.67 278	95.87 279	98.18 356	97.82 378

test-mter		92.33 381	91.76 382	94.04 391	96.53 410	84.62 417	94.05 403	92.39 410	94.00 360	94.12 401	95.07 397	65.63 422	99.67 278	95.87 279	98.18 356	97.82 378

TESTMET0.1,1		92.19 383	91.77 381	93.46 398	96.48 412	82.80 423	94.05 403	91.52 415	94.45 349	94.00 404	94.88 403	66.65 418	99.56 325	95.78 284	98.11 362	98.02 370

MVS_0304		97.44 247	97.01 263	98.72 181	96.42 413	96.74 237	97.20 277	91.97 413	98.46 139	98.30 249	98.79 224	92.74 307	99.91 62	99.30 46	99.94 41	99.52 127

miper_enhance_ethall		96.01 315	95.74 310	96.81 339	96.41 414	92.27 366	93.69 408	98.89 272	91.14 394	98.30 249	97.35 356	90.58 329	99.58 320	96.31 256	99.03 306	98.60 332

tpmvs		95.02 341	95.25 331	94.33 387	96.39 415	85.87 410	98.08 170	96.83 370	95.46 324	95.51 386	98.69 240	85.91 360	99.53 336	94.16 327	96.23 402	97.58 391

CMPMVS	75.91 23	96.29 307	95.44 324	98.84 157	96.25 416	98.69 90	97.02 285	99.12 233	88.90 406	97.83 288	98.86 210	89.51 336	98.90 404	91.92 372	99.51 234	98.92 289
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 346	93.69 355	96.99 328	96.05 417	93.61 343	94.97 381	93.49 405	96.17 298	97.57 306	94.88 403	82.30 386	99.01 399	93.60 345	94.17 415	98.37 355

EPMVS		93.72 361	93.27 360	95.09 383	96.04 418	87.76 405	98.13 162	85.01 425	94.69 342	96.92 339	98.64 252	78.47 403	99.31 379	95.04 302	96.46 399	98.20 361

cascas		94.79 344	94.33 350	96.15 363	96.02 419	92.36 364	92.34 415	99.26 199	85.34 414	95.08 391	94.96 402	92.96 302	98.53 410	94.41 324	98.59 343	97.56 392

MVStest1		95.86 320	95.60 316	96.63 344	95.87 420	91.70 371	97.93 193	98.94 260	98.03 171	99.56 56	99.66 29	71.83 409	98.26 413	99.35 43	99.24 277	99.91 13

gg-mvs-nofinetune		92.37 380	91.20 384	95.85 366	95.80 421	92.38 363	99.31 27	81.84 427	99.75 8	91.83 416	99.74 15	68.29 413	99.02 397	87.15 405	97.12 391	96.16 410

gm-plane-assit					94.83 422	81.97 425			88.07 409		94.99 400		99.60 310	91.76 375

GG-mvs-BLEND				94.76 384	94.54 423	92.13 368	99.31 27	80.47 428		88.73 422	91.01 422	67.59 417	98.16 415	82.30 418	94.53 414	93.98 418

EPNet_dtu		94.93 343	94.78 343	95.38 379	93.58 424	87.68 406	96.78 299	95.69 390	97.35 233	89.14 421	98.09 311	88.15 348	99.49 349	94.95 306	99.30 268	98.98 277
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 391	75.95 394	77.12 407	92.39 425	67.91 431	90.16 418	59.44 432	82.04 418	89.42 420	94.67 406	49.68 430	81.74 425	48.06 425	77.66 423	81.72 421

KD-MVS_2432*1600		92.87 374	91.99 376	95.51 375	91.37 426	89.27 398	94.07 401	98.14 332	95.42 325	97.25 327	96.44 373	67.86 414	99.24 387	91.28 384	96.08 405	98.02 370

miper_refine_blended		92.87 374	91.99 376	95.51 375	91.37 426	89.27 398	94.07 401	98.14 332	95.42 325	97.25 327	96.44 373	67.86 414	99.24 387	91.28 384	96.08 405	98.02 370

EPNet		96.14 312	95.44 324	98.25 243	90.76 428	95.50 277	97.92 196	94.65 395	98.97 103	92.98 411	98.85 213	89.12 339	99.87 111	95.99 272	99.68 176	99.39 184
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 392	68.95 395	70.34 408	87.68 429	65.00 432	91.11 416	59.90 431	69.02 421	74.46 426	88.89 423	48.58 431	68.03 427	28.61 426	72.33 425	77.99 422

test_method		79.78 389	79.50 392	80.62 405	80.21 430	45.76 433	70.82 421	98.41 322	31.08 425	80.89 425	97.71 333	84.85 367	97.37 418	91.51 381	80.03 422	98.75 317

tmp_tt		78.77 390	78.73 393	78.90 406	58.45 431	74.76 430	94.20 400	78.26 429	39.16 424	86.71 423	92.82 418	80.50 390	75.19 426	86.16 410	92.29 419	86.74 420

testmvs		17.12 394	20.53 397	6.87 410	12.05 432	4.20 435	93.62 409	6.73 433	4.62 428	10.41 428	24.33 425	8.28 433	3.56 429	9.69 428	15.07 426	12.86 425

test123		17.04 395	20.11 398	7.82 409	10.25 433	4.91 434	94.80 384	4.47 434	4.93 427	10.00 429	24.28 426	9.69 432	3.64 428	10.14 427	12.43 427	14.92 424

mmdepth		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

monomultidepth		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

test_blank		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

eth-test2					0.00 434

eth-test					0.00 434

uanet_test		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

DCPMVS		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

cdsmvs_eth3d_5k		24.66 393	32.88 396	0.00 411	0.00 434	0.00 436	0.00 422	99.10 236	0.00 429	0.00 430	97.58 341	99.21 16	0.00 430	0.00 429	0.00 428	0.00 426

pcd_1.5k_mvsjas		8.17 396	10.90 399	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	98.07 96	0.00 430	0.00 429	0.00 428	0.00 426

sosnet-low-res		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

sosnet		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

uncertanet		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

Regformer		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

ab-mvs-re		8.12 397	10.83 400	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	97.48 347	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

uanet		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

WAC-MVS						90.90 387								91.37 383

PC_three_1452									93.27 368	99.40 91	98.54 265	98.22 83	97.00 419	95.17 300	99.45 246	99.49 137

test_241102_TWO								99.30 180	98.03 171	99.26 119	99.02 166	97.51 143	99.88 94	96.91 200	99.60 203	99.66 63

test_0728_THIRD									98.17 164	99.08 141	99.02 166	97.89 109	99.88 94	97.07 188	99.71 161	99.70 57

GSMVS																98.81 306

sam_mvs1												84.74 369				98.81 306

sam_mvs												84.29 375

MTGPA								99.20 211

test_post1							97.59 242				20.48 428	83.07 383	99.66 289	94.16 327

test_post											21.25 427	83.86 378	99.70 262

patchmatchnet-post											98.77 228	84.37 372	99.85 131

MTMP							97.93 193	91.91 414

test9_res														93.28 353	99.15 293	99.38 191

agg_prior2														92.50 369	99.16 291	99.37 193

test_prior4						97.97 154	95.86 351

test_prior2							95.74 357		96.48 288	96.11 370	97.63 339	95.92 233		94.16 327	99.20 285

旧先验2							95.76 356		88.56 408	97.52 310			99.66 289	94.48 317

新几何2							95.93 347

无先验							95.74 357	98.74 301	89.38 404				99.73 250	92.38 371		99.22 238

原ACMM2							95.53 363

testdata2													99.79 210	92.80 363

segment_acmp												97.02 173

testdata1							95.44 368		96.32 294

plane_prior5								99.27 194					99.70 262	94.42 321	99.51 234	99.45 160

plane_prior4											97.98 318

plane_prior3						97.78 175			97.41 227	97.79 291

plane_prior2							97.77 216		98.20 161

plane_prior						97.65 184	97.07 284		96.72 278						99.36 257

n2								0.00 435

nn								0.00 435

door-mid								99.57 69

test11								98.87 275

door								99.41 134

HQP5-MVS						96.79 233

BP-MVS														92.82 361

HQP4-MVS										95.56 380			99.54 334			99.32 213

HQP3-MVS								99.04 247							99.26 275

HQP2-MVS												93.84 287

MDTV_nov1_ep13_2view						74.92 429	97.69 226		90.06 402	97.75 294		85.78 361		93.52 347		98.69 324

ACMMP++_ref															99.77 129

ACMMP++															99.68 176

Test By Simon												96.52 201

High-resolution multi-view benchmark