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.

test_vis1_n		97.92 234	97.44 269	99.34 142	99.53 167	98.08 238	99.74 46	99.49 148	99.15 20	100.00 1	99.94 6	79.51 396	99.98 13	99.88 14	99.76 115	99.97 4

fmvsm_s_conf0.1_n_a		99.26 73	99.06 87	99.85 28	99.52 172	99.62 65	99.54 139	99.62 41	98.69 79	99.99 2	99.96 1	94.47 241	99.94 69	99.88 14	99.92 29	99.98 2

fmvsm_s_conf0.1_n		99.29 67	99.10 80	99.86 21	99.70 102	99.65 57	99.53 147	99.62 41	98.74 75	99.99 2	99.95 3	94.53 239	99.94 69	99.89 13	99.96 14	99.97 4

test_vis1_n_1920		98.63 164	98.40 170	99.31 149	99.86 20	97.94 250	99.67 66	99.62 41	99.43 7	99.99 2	99.91 22	87.29 368	100.00 1	99.92 12	99.92 29	99.98 2

test_fmvs1_n		98.41 175	98.14 186	99.21 169	99.82 42	97.71 263	99.74 46	99.49 148	99.32 14	99.99 2	99.95 3	85.32 377	99.97 21	99.82 16	99.84 82	99.96 7

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 28	99.86 20	99.61 67	99.56 123	99.63 39	99.48 3	99.98 6	99.83 71	98.75 55	99.99 4	99.97 1	99.96 14	99.94 11

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 28	99.84 32	99.63 64	99.56 123	99.63 39	99.47 4	99.98 6	99.82 79	98.75 55	99.99 4	99.97 1	99.97 8	99.94 11

fmvsm_s_conf0.5_n_a		99.56 13	99.47 17	99.85 28	99.83 39	99.64 63	99.52 148	99.65 33	99.10 27	99.98 6	99.92 15	97.35 125	99.96 30	99.94 10	99.92 29	99.95 9

fmvsm_s_conf0.5_n		99.51 18	99.40 27	99.85 28	99.84 32	99.65 57	99.51 156	99.67 23	99.13 22	99.98 6	99.92 15	96.60 152	99.96 30	99.95 8	99.96 14	99.95 9

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 52	99.84 32	99.44 97	99.58 110	99.69 18	99.43 7	99.98 6	99.91 22	98.62 70	100.00 1	99.97 1	99.95 20	99.90 17

test_fmvs1		98.88 131	98.79 133	99.16 174	99.69 107	97.61 266	99.55 135	99.49 148	99.32 14	99.98 6	99.91 22	91.41 323	99.96 30	99.82 16	99.92 29	99.90 17

dcpmvs_2		99.23 79	99.58 7	98.16 299	99.83 39	94.68 360	99.76 37	99.52 104	99.07 35	99.98 6	99.88 39	98.56 74	99.93 87	99.67 22	99.98 4	99.87 31

test_cas_vis1_n_1920		99.16 88	99.01 100	99.61 87	99.81 46	98.86 179	99.65 77	99.64 36	99.39 10	99.97 13	99.94 6	93.20 276	99.98 13	99.55 34	99.91 36	99.99 1

mvsany_test1		99.50 20	99.46 20	99.62 86	99.61 145	99.09 142	98.94 341	99.48 160	99.10 27	99.96 14	99.91 22	98.85 39	99.96 30	99.72 18	99.58 142	99.82 54

iter_conf05		99.48 26	99.40 27	99.71 67	99.68 111	99.61 67	99.49 174	99.58 62	98.27 117	99.95 15	99.92 15	98.09 101	99.94 69	99.65 24	99.96 14	99.58 154

mamv4		99.33 61	99.42 22	99.07 183	99.67 114	97.73 258	99.42 206	99.60 54	98.15 135	99.94 16	99.91 22	98.42 85	99.94 69	99.72 18	99.96 14	99.54 164

test_fmvsmconf_n		99.70 3	99.64 4	99.87 11	99.80 52	99.66 53	99.48 179	99.64 36	99.45 5	99.92 17	99.92 15	98.62 70	99.99 4	99.96 7	99.99 1	99.96 7

SED-MVS		99.61 7	99.52 11	99.88 5	99.84 32	99.90 2	99.60 96	99.48 160	99.08 33	99.91 18	99.81 93	99.20 7	99.96 30	98.91 102	99.85 74	99.79 74

test_241102_ONE					99.84 32	99.90 2		99.48 160	99.07 35	99.91 18	99.74 144	99.20 7	99.76 203

EI-MVSNet-UG-set		99.58 9	99.57 8	99.64 79	99.78 56	99.14 137	99.60 96	99.45 200	99.01 40	99.90 20	99.83 71	98.98 23	99.93 87	99.59 28	99.95 20	99.86 33

EI-MVSNet-Vis-set		99.58 9	99.56 10	99.64 79	99.78 56	99.15 136	99.61 95	99.45 200	99.01 40	99.89 21	99.82 79	99.01 18	99.92 98	99.56 32	99.95 20	99.85 36

DVP-MVS++		99.59 8	99.50 13	99.88 5	99.51 175	99.88 8	99.87 8	99.51 119	98.99 45	99.88 22	99.81 93	99.27 5	99.96 30	98.85 115	99.80 102	99.81 61

test_241102_TWO								99.48 160	99.08 33	99.88 22	99.81 93	98.94 29	99.96 30	98.91 102	99.84 82	99.88 26

DPE-MVS		99.46 32	99.32 43	99.91 2	99.78 56	99.88 8	99.36 233	99.51 119	98.73 76	99.88 22	99.84 67	98.72 61	99.96 30	98.16 196	99.87 59	99.88 26
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SD-MVS		99.41 49	99.52 11	99.05 187	99.74 80	99.68 48	99.46 188	99.52 104	99.11 26	99.88 22	99.91 22	99.43 1	97.70 388	98.72 133	99.93 27	99.77 82
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
APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 62	99.89 4	99.75 41	99.56 71	99.02 38	99.88 22	99.85 56	99.18 10	99.96 30	99.22 73	99.92 29	99.90 17
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MVSMamba_PlusPlus		99.46 32	99.41 26	99.64 79	99.68 111	99.50 88	99.75 41	99.50 139	98.27 117	99.87 27	99.92 15	98.09 101	99.94 69	99.65 24	99.95 20	99.47 189

test_fmvsmconf0.1_n		99.55 14	99.45 21	99.86 21	99.44 201	99.65 57	99.50 163	99.61 48	99.45 5	99.87 27	99.92 15	97.31 126	99.97 21	99.95 8	99.99 1	99.97 4

test_fmvsmvis_n_1920		99.65 6	99.61 6	99.77 55	99.38 219	99.37 103	99.58 110	99.62 41	99.41 9	99.87 27	99.92 15	98.81 44	100.00 1	99.97 1	99.93 27	99.94 11

iter_conf05_11		99.40 52	99.32 43	99.63 85	99.53 167	99.47 93	99.75 41	99.52 104	98.11 143	99.87 27	99.85 56	97.72 115	99.89 131	99.56 32	99.97 8	99.53 170

test0726					99.85 26	99.89 4	99.62 89	99.50 139	99.10 27	99.86 31	99.82 79	98.94 29

Vis-MVSNet		99.12 100	98.97 106	99.56 98	99.78 56	99.10 141	99.68 63	99.66 28	98.49 95	99.86 31	99.87 47	94.77 222	99.84 158	99.19 75	99.41 153	99.74 92
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PC_three_1452									98.18 133	99.84 33	99.70 159	99.31 3	98.52 371	98.30 187	99.80 102	99.81 61

IU-MVS					99.84 32	99.88 8		99.32 271	98.30 114	99.84 33				98.86 113	99.85 74	99.89 20

xiu_mvs_v1_base_debu		99.29 67	99.27 62	99.34 142	99.63 135	98.97 159	99.12 298	99.51 119	98.86 60	99.84 33	99.47 256	98.18 97	99.99 4	99.50 41	99.31 162	99.08 236

xiu_mvs_v1_base		99.29 67	99.27 62	99.34 142	99.63 135	98.97 159	99.12 298	99.51 119	98.86 60	99.84 33	99.47 256	98.18 97	99.99 4	99.50 41	99.31 162	99.08 236

xiu_mvs_v1_base_debi		99.29 67	99.27 62	99.34 142	99.63 135	98.97 159	99.12 298	99.51 119	98.86 60	99.84 33	99.47 256	98.18 97	99.99 4	99.50 41	99.31 162	99.08 236

DeepPCF-MVS	98.18 3	98.81 146	99.37 33	97.12 346	99.60 150	91.75 386	98.61 371	99.44 208	99.35 12	99.83 38	99.85 56	98.70 63	99.81 183	99.02 90	99.91 36	99.81 61

MVS_0304		99.42 44	99.32 43	99.72 65	99.70 102	99.27 118	99.52 148	97.57 390	99.51 2	99.82 39	99.78 124	98.09 101	99.96 30	99.97 1	99.97 8	99.94 11

TSAR-MVS + GP.		99.36 58	99.36 35	99.36 141	99.67 114	98.61 203	99.07 308	99.33 261	99.00 43	99.82 39	99.81 93	99.06 16	99.84 158	99.09 84	99.42 152	99.65 129

FOURS1					99.91 1	99.93 1	99.87 8	99.56 71	99.10 27	99.81 41

DVP-MVS		99.57 12	99.47 17	99.88 5	99.85 26	99.89 4	99.57 117	99.37 243	99.10 27	99.81 41	99.80 106	98.94 29	99.96 30	98.93 99	99.86 67	99.81 61
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_THIRD									98.99 45	99.81 41	99.80 106	99.09 14	99.96 30	98.85 115	99.90 44	99.88 26

MVSFormer		99.17 86	99.12 78	99.29 157	99.51 175	98.94 169	99.88 3	99.46 189	97.55 209	99.80 44	99.65 187	97.39 121	99.28 302	99.03 88	99.85 74	99.65 129

lupinMVS		99.13 94	99.01 100	99.46 128	99.51 175	98.94 169	99.05 313	99.16 304	97.86 171	99.80 44	99.56 224	97.39 121	99.86 145	98.94 97	99.85 74	99.58 154

tttt0517		98.42 173	98.14 186	99.28 161	99.66 124	98.38 225	99.74 46	96.85 394	97.68 196	99.79 46	99.74 144	91.39 324	99.89 131	98.83 121	99.56 143	99.57 158

APD-MVS_3200maxsize		99.48 26	99.35 37	99.85 28	99.76 65	99.83 16	99.63 84	99.54 88	98.36 108	99.79 46	99.82 79	98.86 38	99.95 59	98.62 146	99.81 98	99.78 80

jason		99.13 94	99.03 92	99.45 129	99.46 195	98.87 176	99.12 298	99.26 288	98.03 160	99.79 46	99.65 187	97.02 139	99.85 151	99.02 90	99.90 44	99.65 129
jason: jason.
SteuartSystems-ACMMP		99.54 15	99.42 22	99.87 11	99.82 42	99.81 25	99.59 102	99.51 119	98.62 84	99.79 46	99.83 71	99.28 4	99.97 21	98.48 168	99.90 44	99.84 40
Skip Steuart: Steuart Systems R&D Blog.
DeepC-MVS_fast	98.69 1	99.49 22	99.39 30	99.77 55	99.63 135	99.59 71	99.36 233	99.46 189	99.07 35	99.79 46	99.82 79	98.85 39	99.92 98	98.68 140	99.87 59	99.82 54
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_fmvsmconf0.01_n		99.22 80	99.03 92	99.79 49	98.42 368	99.48 91	99.55 135	99.51 119	99.39 10	99.78 51	99.93 10	94.80 217	99.95 59	99.93 11	99.95 20	99.94 11

CS-MVS		99.50 20	99.48 15	99.54 101	99.76 65	99.42 99	99.90 1	99.55 79	98.56 89	99.78 51	99.70 159	98.65 68	99.79 192	99.65 24	99.78 109	99.41 203

SMA-MVS		99.44 39	99.30 53	99.85 28	99.73 88	99.83 16	99.56 123	99.47 180	97.45 222	99.78 51	99.82 79	99.18 10	99.91 109	98.79 126	99.89 53	99.81 61
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
TSAR-MVS + MP.		99.58 9	99.50 13	99.81 44	99.91 1	99.66 53	99.63 84	99.39 227	98.91 58	99.78 51	99.85 56	99.36 2	99.94 69	98.84 118	99.88 56	99.82 54
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test2506		96.81 317	96.65 313	97.29 342	99.74 80	92.21 385	99.60 96	85.06 416	99.13 22	99.77 55	99.93 10	87.82 366	99.85 151	99.38 53	99.38 154	99.80 70

test_part2					99.81 46	99.83 16				99.77 55

MSP-MVS		99.42 44	99.27 62	99.88 5	99.89 8	99.80 27	99.67 66	99.50 139	98.70 78	99.77 55	99.49 248	98.21 95	99.95 59	98.46 172	99.77 112	99.88 26
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
UA-Net		99.42 44	99.29 57	99.80 46	99.62 141	99.55 78	99.50 163	99.70 15	98.79 70	99.77 55	99.96 1	97.45 120	99.96 30	98.92 101	99.90 44	99.89 20

APD-MVS		99.27 71	99.08 85	99.84 39	99.75 73	99.79 30	99.50 163	99.50 139	97.16 249	99.77 55	99.82 79	98.78 48	99.94 69	97.56 253	99.86 67	99.80 70
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SR-MVS-dyc-post		99.45 35	99.31 51	99.85 28	99.76 65	99.82 22	99.63 84	99.52 104	98.38 104	99.76 60	99.82 79	98.53 76	99.95 59	98.61 149	99.81 98	99.77 82

RE-MVS-def			99.34 39		99.76 65	99.82 22	99.63 84	99.52 104	98.38 104	99.76 60	99.82 79	98.75 55		98.61 149	99.81 98	99.77 82

ACMMP_NAP		99.47 30	99.34 39	99.88 5	99.87 15	99.86 13	99.47 185	99.48 160	98.05 157	99.76 60	99.86 51	98.82 43	99.93 87	98.82 125	99.91 36	99.84 40

HPM-MVS_fast		99.51 18	99.40 27	99.85 28	99.91 1	99.79 30	99.76 37	99.56 71	97.72 190	99.76 60	99.75 139	99.13 12	99.92 98	99.07 86	99.92 29	99.85 36

MM		99.40 52	99.28 59	99.74 61	99.67 114	99.31 111	99.52 148	98.87 344	99.55 1	99.74 64	99.80 106	96.47 157	99.98 13	99.97 1	99.97 8	99.94 11

VNet		99.11 104	98.90 115	99.73 64	99.52 172	99.56 76	99.41 210	99.39 227	99.01 40	99.74 64	99.78 124	95.56 190	99.92 98	99.52 39	98.18 238	99.72 103

patch_mono-2		99.26 73	99.62 5	98.16 299	99.81 46	94.59 362	99.52 148	99.64 36	99.33 13	99.73 66	99.90 29	99.00 22	99.99 4	99.69 20	99.98 4	99.89 20

SR-MVS		99.43 42	99.29 57	99.86 21	99.75 73	99.83 16	99.59 102	99.62 41	98.21 128	99.73 66	99.79 118	98.68 64	99.96 30	98.44 174	99.77 112	99.79 74

thisisatest0530		98.35 181	98.03 201	99.31 149	99.63 135	98.56 205	99.54 139	96.75 396	97.53 213	99.73 66	99.65 187	91.25 327	99.89 131	98.62 146	99.56 143	99.48 183

CS-MVS-test		99.49 22	99.48 15	99.54 101	99.78 56	99.30 114	99.89 2	99.58 62	98.56 89	99.73 66	99.69 169	98.55 75	99.82 178	99.69 20	99.85 74	99.48 183

EC-MVSNet		99.44 39	99.39 30	99.58 94	99.56 160	99.49 89	99.88 3	99.58 62	98.38 104	99.73 66	99.69 169	98.20 96	99.70 230	99.64 27	99.82 95	99.54 164

diffmvs		99.14 92	99.02 96	99.51 117	99.61 145	98.96 163	99.28 259	99.49 148	98.46 97	99.72 71	99.71 155	96.50 156	99.88 137	99.31 63	99.11 176	99.67 122
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SF-MVS		99.38 56	99.24 67	99.79 49	99.79 54	99.68 48	99.57 117	99.54 88	97.82 181	99.71 72	99.80 106	98.95 27	99.93 87	98.19 192	99.84 82	99.74 92

xiu_mvs_v2_base		99.26 73	99.25 66	99.29 157	99.53 167	98.91 173	99.02 321	99.45 200	98.80 69	99.71 72	99.26 311	98.94 29	99.98 13	99.34 60	99.23 166	98.98 250

PS-MVSNAJ		99.32 63	99.32 43	99.30 154	99.57 156	98.94 169	98.97 335	99.46 189	98.92 57	99.71 72	99.24 313	99.01 18	99.98 13	99.35 56	99.66 133	98.97 251

PGM-MVS		99.45 35	99.31 51	99.86 21	99.87 15	99.78 36	99.58 110	99.65 33	97.84 176	99.71 72	99.80 106	99.12 13	99.97 21	98.33 183	99.87 59	99.83 49

114514_t		98.93 127	98.67 143	99.72 65	99.85 26	99.53 83	99.62 89	99.59 58	92.65 381	99.71 72	99.78 124	98.06 105	99.90 120	98.84 118	99.91 36	99.74 92

PVSNet_Blended_VisFu		99.36 58	99.28 59	99.61 87	99.86 20	99.07 147	99.47 185	99.93 2	97.66 199	99.71 72	99.86 51	97.73 114	99.96 30	99.47 48	99.82 95	99.79 74

MTAPA		99.52 17	99.39 30	99.89 4	99.90 4	99.86 13	99.66 71	99.47 180	98.79 70	99.68 78	99.81 93	98.43 83	99.97 21	98.88 105	99.90 44	99.83 49

HFP-MVS		99.49 22	99.37 33	99.86 21	99.87 15	99.80 27	99.66 71	99.67 23	98.15 135	99.68 78	99.69 169	99.06 16	99.96 30	98.69 138	99.87 59	99.84 40

VDDNet		97.55 285	97.02 304	99.16 174	99.49 186	98.12 237	99.38 227	99.30 279	95.35 346	99.68 78	99.90 29	82.62 389	99.93 87	99.31 63	98.13 242	99.42 201

HPM-MVS		99.42 44	99.28 59	99.83 40	99.90 4	99.72 42	99.81 20	99.54 88	97.59 203	99.68 78	99.63 199	98.91 34	99.94 69	98.58 155	99.91 36	99.84 40
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
VDD-MVS		97.73 265	97.35 281	98.88 216	99.47 194	97.12 282	99.34 241	98.85 346	98.19 130	99.67 82	99.85 56	82.98 387	99.92 98	99.49 45	98.32 229	99.60 146

ACMMPR		99.49 22	99.36 35	99.86 21	99.87 15	99.79 30	99.66 71	99.67 23	98.15 135	99.67 82	99.69 169	98.95 27	99.96 30	98.69 138	99.87 59	99.84 40

PVSNet_BlendedMVS		98.86 135	98.80 130	99.03 189	99.76 65	98.79 188	99.28 259	99.91 3	97.42 227	99.67 82	99.37 282	97.53 118	99.88 137	98.98 93	97.29 289	98.42 347

PVSNet_Blended		99.08 110	98.97 106	99.42 134	99.76 65	98.79 188	98.78 357	99.91 3	96.74 282	99.67 82	99.49 248	97.53 118	99.88 137	98.98 93	99.85 74	99.60 146

sss		99.17 86	99.05 88	99.53 109	99.62 141	98.97 159	99.36 233	99.62 41	97.83 177	99.67 82	99.65 187	97.37 124	99.95 59	99.19 75	99.19 169	99.68 119

ECVR-MVS		98.04 214	98.05 199	98.00 311	99.74 80	94.37 365	99.59 102	94.98 404	99.13 22	99.66 87	99.93 10	90.67 333	99.84 158	99.40 52	99.38 154	99.80 70

h-mvs33		97.70 271	97.28 292	98.97 197	99.70 102	97.27 274	99.36 233	99.45 200	98.94 54	99.66 87	99.64 193	94.93 209	99.99 4	99.48 46	84.36 395	99.65 129

hse-mvs2		97.50 290	97.14 298	98.59 250	99.49 186	97.05 289	99.28 259	99.22 295	98.94 54	99.66 87	99.42 266	94.93 209	99.65 246	99.48 46	83.80 397	99.08 236

region2R		99.48 26	99.35 37	99.87 11	99.88 11	99.80 27	99.65 77	99.66 28	98.13 140	99.66 87	99.68 175	98.96 24	99.96 30	98.62 146	99.87 59	99.84 40

RPSCF		98.22 189	98.62 153	96.99 348	99.82 42	91.58 387	99.72 51	99.44 208	96.61 294	99.66 87	99.89 33	95.92 177	99.82 178	97.46 263	99.10 179	99.57 158

OMC-MVS		99.08 110	99.04 90	99.20 170	99.67 114	98.22 231	99.28 259	99.52 104	98.07 152	99.66 87	99.81 93	97.79 112	99.78 197	97.79 227	99.81 98	99.60 146

test1111		98.04 214	98.11 190	97.83 322	99.74 80	93.82 370	99.58 110	95.40 403	99.12 25	99.65 93	99.93 10	90.73 332	99.84 158	99.43 51	99.38 154	99.82 54

test_one_0601					99.81 46	99.88 8		99.49 148	98.97 51	99.65 93	99.81 93	99.09 14

LFMVS		97.90 237	97.35 281	99.54 101	99.52 172	99.01 154	99.39 222	98.24 378	97.10 257	99.65 93	99.79 118	84.79 380	99.91 109	99.28 67	98.38 222	99.69 115

MVS_111021_LR		99.41 49	99.33 41	99.65 74	99.77 62	99.51 87	98.94 341	99.85 6	98.82 65	99.65 93	99.74 144	98.51 78	99.80 189	98.83 121	99.89 53	99.64 136

SDMVSNet		99.11 104	98.90 115	99.75 58	99.81 46	99.59 71	99.81 20	99.65 33	98.78 73	99.64 97	99.88 39	94.56 235	99.93 87	99.67 22	98.26 231	99.72 103

sd_testset		98.75 153	98.57 160	99.29 157	99.81 46	98.26 229	99.56 123	99.62 41	98.78 73	99.64 97	99.88 39	92.02 307	99.88 137	99.54 35	98.26 231	99.72 103

9.14			99.10 80		99.72 92		99.40 218	99.51 119	97.53 213	99.64 97	99.78 124	98.84 41	99.91 109	97.63 244	99.82 95

GST-MVS		99.40 52	99.24 67	99.85 28	99.86 20	99.79 30	99.60 96	99.67 23	97.97 163	99.63 100	99.68 175	98.52 77	99.95 59	98.38 177	99.86 67	99.81 61

CPTT-MVS		99.11 104	98.90 115	99.74 61	99.80 52	99.46 95	99.59 102	99.49 148	97.03 265	99.63 100	99.69 169	97.27 129	99.96 30	97.82 225	99.84 82	99.81 61

ACMMP		99.45 35	99.32 43	99.82 41	99.89 8	99.67 51	99.62 89	99.69 18	98.12 141	99.63 100	99.84 67	98.73 60	99.96 30	98.55 164	99.83 91	99.81 61
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
DeepC-MVS	98.35 2	99.30 65	99.19 72	99.64 79	99.82 42	99.23 124	99.62 89	99.55 79	98.94 54	99.63 100	99.95 3	95.82 182	99.94 69	99.37 55	99.97 8	99.73 97
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
FE-MVS		98.48 168	98.17 182	99.40 136	99.54 166	98.96 163	99.68 63	98.81 351	95.54 344	99.62 104	99.70 159	93.82 264	99.93 87	97.35 271	99.46 149	99.32 217

CHOSEN 280x420		99.12 100	99.13 77	99.08 181	99.66 124	97.89 251	98.43 381	99.71 13	98.88 59	99.62 104	99.76 136	96.63 151	99.70 230	99.46 49	99.99 1	99.66 125

PHI-MVS		99.30 65	99.17 74	99.70 68	99.56 160	99.52 86	99.58 110	99.80 8	97.12 253	99.62 104	99.73 150	98.58 72	99.90 120	98.61 149	99.91 36	99.68 119

test_yl		98.86 135	98.63 148	99.54 101	99.49 186	99.18 128	99.50 163	99.07 316	98.22 126	99.61 107	99.51 242	95.37 196	99.84 158	98.60 152	98.33 225	99.59 150

DCV-MVSNet		98.86 135	98.63 148	99.54 101	99.49 186	99.18 128	99.50 163	99.07 316	98.22 126	99.61 107	99.51 242	95.37 196	99.84 158	98.60 152	98.33 225	99.59 150

MG-MVS		99.13 94	99.02 96	99.45 129	99.57 156	98.63 200	99.07 308	99.34 254	98.99 45	99.61 107	99.82 79	97.98 108	99.87 142	97.00 290	99.80 102	99.85 36

MP-MVS-pluss		99.37 57	99.20 71	99.88 5	99.90 4	99.87 12	99.30 249	99.52 104	97.18 247	99.60 110	99.79 118	98.79 47	99.95 59	98.83 121	99.91 36	99.83 49
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
CDPH-MVS		99.13 94	98.91 114	99.80 46	99.75 73	99.71 44	99.15 292	99.41 218	96.60 296	99.60 110	99.55 227	98.83 42	99.90 120	97.48 260	99.83 91	99.78 80

EPP-MVSNet		99.13 94	98.99 102	99.53 109	99.65 130	99.06 148	99.81 20	99.33 261	97.43 225	99.60 110	99.88 39	97.14 131	99.84 158	99.13 80	98.94 190	99.69 115

bld_raw_dy_0_64		99.22 80	99.09 83	99.60 90	99.74 80	99.31 111	99.42 206	99.55 79	96.02 339	99.59 113	99.94 6	98.03 106	99.92 98	99.58 30	99.98 4	99.56 160

HyFIR lowres test		99.11 104	98.92 112	99.65 74	99.90 4	99.37 103	99.02 321	99.91 3	97.67 198	99.59 113	99.75 139	95.90 179	99.73 214	99.53 37	99.02 187	99.86 33

FA-MVS(test-final)		98.75 153	98.53 164	99.41 135	99.55 164	99.05 150	99.80 25	99.01 322	96.59 298	99.58 115	99.59 213	95.39 195	99.90 120	97.78 228	99.49 148	99.28 220

MVS_Test		99.10 108	98.97 106	99.48 123	99.49 186	99.14 137	99.67 66	99.34 254	97.31 236	99.58 115	99.76 136	97.65 117	99.82 178	98.87 108	99.07 182	99.46 194

MDTV_nov1_ep13_2view						95.18 353	99.35 238		96.84 278	99.58 115		95.19 205		97.82 225		99.46 194

DELS-MVS		99.48 26	99.42 22	99.65 74	99.72 92	99.40 102	99.05 313	99.66 28	99.14 21	99.57 118	99.80 106	98.46 81	99.94 69	99.57 31	99.84 82	99.60 146
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
ZD-MVS					99.71 97	99.79 30		99.61 48	96.84 278	99.56 119	99.54 232	98.58 72	99.96 30	96.93 297	99.75 117

CR-MVSNet		98.17 196	97.93 213	98.87 220	99.18 269	98.49 216	99.22 282	99.33 261	96.96 269	99.56 119	99.38 279	94.33 245	99.00 346	94.83 349	98.58 212	99.14 228

RPMNet		96.72 318	95.90 330	99.19 171	99.18 269	98.49 216	99.22 282	99.52 104	88.72 395	99.56 119	97.38 389	94.08 255	99.95 59	86.87 397	98.58 212	99.14 228

IS-MVSNet		99.05 113	98.87 120	99.57 96	99.73 88	99.32 107	99.75 41	99.20 299	98.02 161	99.56 119	99.86 51	96.54 155	99.67 238	98.09 199	99.13 175	99.73 97

ZNCC-MVS		99.47 30	99.33 41	99.87 11	99.87 15	99.81 25	99.64 80	99.67 23	98.08 151	99.55 123	99.64 193	98.91 34	99.96 30	98.72 133	99.90 44	99.82 54

thisisatest0515		98.14 199	97.79 224	99.19 171	99.50 184	98.50 215	98.61 371	96.82 395	96.95 271	99.54 124	99.43 264	91.66 319	99.86 145	98.08 203	99.51 147	99.22 225

MVS_111021_HR		99.41 49	99.32 43	99.66 70	99.72 92	99.47 93	98.95 339	99.85 6	98.82 65	99.54 124	99.73 150	98.51 78	99.74 208	98.91 102	99.88 56	99.77 82

CP-MVS		99.45 35	99.32 43	99.85 28	99.83 39	99.75 39	99.69 57	99.52 104	98.07 152	99.53 126	99.63 199	98.93 33	99.97 21	98.74 130	99.91 36	99.83 49

WTY-MVS		99.06 112	98.88 119	99.61 87	99.62 141	99.16 131	99.37 229	99.56 71	98.04 158	99.53 126	99.62 204	96.84 144	99.94 69	98.85 115	98.49 220	99.72 103

MCST-MVS		99.43 42	99.30 53	99.82 41	99.79 54	99.74 41	99.29 254	99.40 224	98.79 70	99.52 128	99.62 204	98.91 34	99.90 120	98.64 144	99.75 117	99.82 54

PatchT		97.03 313	96.44 318	98.79 235	98.99 311	98.34 226	99.16 289	99.07 316	92.13 382	99.52 128	97.31 392	94.54 238	98.98 348	88.54 390	98.73 206	99.03 244

CANet		99.25 77	99.14 76	99.59 91	99.41 209	99.16 131	99.35 238	99.57 66	98.82 65	99.51 130	99.61 208	96.46 158	99.95 59	99.59 28	99.98 4	99.65 129

mPP-MVS		99.44 39	99.30 53	99.86 21	99.88 11	99.79 30	99.69 57	99.48 160	98.12 141	99.50 131	99.75 139	98.78 48	99.97 21	98.57 158	99.89 53	99.83 49

PatchMatch-RL		98.84 145	98.62 153	99.52 115	99.71 97	99.28 116	99.06 311	99.77 9	97.74 189	99.50 131	99.53 236	95.41 194	99.84 158	97.17 284	99.64 136	99.44 199

PVSNet	96.02 17	98.85 142	98.84 127	98.89 214	99.73 88	97.28 273	98.32 387	99.60 54	97.86 171	99.50 131	99.57 221	96.75 148	99.86 145	98.56 161	99.70 127	99.54 164

LS3D		99.27 71	99.12 78	99.74 61	99.18 269	99.75 39	99.56 123	99.57 66	98.45 98	99.49 134	99.85 56	97.77 113	99.94 69	98.33 183	99.84 82	99.52 172

MP-MVS		99.33 61	99.15 75	99.87 11	99.88 11	99.82 22	99.66 71	99.46 189	98.09 147	99.48 135	99.74 144	98.29 92	99.96 30	97.93 214	99.87 59	99.82 54
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
旧先验2							98.96 336		96.70 285	99.47 136			99.94 69	98.19 192

MSDG		98.98 123	98.80 130	99.53 109	99.76 65	99.19 126	98.75 360	99.55 79	97.25 241	99.47 136	99.77 132	97.82 111	99.87 142	96.93 297	99.90 44	99.54 164

CDS-MVSNet		99.09 109	99.03 92	99.25 164	99.42 204	98.73 192	99.45 189	99.46 189	98.11 143	99.46 138	99.77 132	98.01 107	99.37 284	98.70 135	98.92 193	99.66 125
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MSLP-MVS++		99.46 32	99.47 17	99.44 133	99.60 150	99.16 131	99.41 210	99.71 13	98.98 48	99.45 139	99.78 124	99.19 9	99.54 263	99.28 67	99.84 82	99.63 140

XVG-OURS		98.73 156	98.68 142	98.88 216	99.70 102	97.73 258	98.92 343	99.55 79	98.52 93	99.45 139	99.84 67	95.27 200	99.91 109	98.08 203	98.84 199	99.00 247

casdiffmvs_mvg		99.15 90	99.02 96	99.55 100	99.66 124	99.09 142	99.64 80	99.56 71	98.26 120	99.45 139	99.87 47	96.03 171	99.81 183	99.54 35	99.15 173	99.73 97
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
tpmrst		98.33 182	98.48 166	97.90 317	99.16 279	94.78 358	99.31 247	99.11 309	97.27 239	99.45 139	99.59 213	95.33 198	99.84 158	98.48 168	98.61 209	99.09 235

TAMVS		99.12 100	99.08 85	99.24 166	99.46 195	98.55 206	99.51 156	99.46 189	98.09 147	99.45 139	99.82 79	98.34 90	99.51 264	98.70 135	98.93 191	99.67 122

ETV-MVS		99.26 73	99.21 70	99.40 136	99.46 195	99.30 114	99.56 123	99.52 104	98.52 93	99.44 144	99.27 309	98.41 87	99.86 145	99.10 83	99.59 141	99.04 243

CANet_DTU		98.97 125	98.87 120	99.25 164	99.33 231	98.42 224	99.08 307	99.30 279	99.16 19	99.43 145	99.75 139	95.27 200	99.97 21	98.56 161	99.95 20	99.36 211

SCA		98.19 193	98.16 183	98.27 294	99.30 239	95.55 341	99.07 308	98.97 326	97.57 206	99.43 145	99.57 221	92.72 287	99.74 208	97.58 248	99.20 168	99.52 172

testdata				99.54 101	99.75 73	98.95 166		99.51 119	97.07 259	99.43 145	99.70 159	98.87 37	99.94 69	97.76 232	99.64 136	99.72 103

DPM-MVS		98.95 126	98.71 139	99.66 70	99.63 135	99.55 78	98.64 370	99.10 310	97.93 166	99.42 148	99.55 227	98.67 66	99.80 189	95.80 328	99.68 131	99.61 144

XVG-OURS-SEG-HR		98.69 158	98.62 153	98.89 214	99.71 97	97.74 257	99.12 298	99.54 88	98.44 101	99.42 148	99.71 155	94.20 249	99.92 98	98.54 165	98.90 195	99.00 247

baseline		99.15 90	99.02 96	99.53 109	99.66 124	99.14 137	99.72 51	99.48 160	98.35 109	99.42 148	99.84 67	96.07 169	99.79 192	99.51 40	99.14 174	99.67 122

DP-MVS Recon		99.12 100	98.95 110	99.65 74	99.74 80	99.70 46	99.27 264	99.57 66	96.40 312	99.42 148	99.68 175	98.75 55	99.80 189	97.98 211	99.72 123	99.44 199

Effi-MVS+-dtu		98.78 150	98.89 118	98.47 270	99.33 231	96.91 302	99.57 117	99.30 279	98.47 96	99.41 152	98.99 340	96.78 146	99.74 208	98.73 132	99.38 154	98.74 272

casdiffmvs		99.13 94	98.98 105	99.56 98	99.65 130	99.16 131	99.56 123	99.50 139	98.33 112	99.41 152	99.86 51	95.92 177	99.83 171	99.45 50	99.16 170	99.70 113
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MIMVSNet		97.73 265	97.45 264	98.57 254	99.45 200	97.50 268	99.02 321	98.98 325	96.11 332	99.41 152	99.14 324	90.28 335	98.74 366	95.74 329	98.93 191	99.47 189

CSCG		99.32 63	99.32 43	99.32 148	99.85 26	98.29 227	99.71 53	99.66 28	98.11 143	99.41 152	99.80 106	98.37 89	99.96 30	98.99 92	99.96 14	99.72 103

F-COLMAP		99.19 82	99.04 90	99.64 79	99.78 56	99.27 118	99.42 206	99.54 88	97.29 238	99.41 152	99.59 213	98.42 85	99.93 87	98.19 192	99.69 128	99.73 97

EIA-MVS		99.18 84	99.09 83	99.45 129	99.49 186	99.18 128	99.67 66	99.53 99	97.66 199	99.40 157	99.44 262	98.10 100	99.81 183	98.94 97	99.62 139	99.35 212

mvsmamba		98.92 128	98.87 120	99.08 181	99.07 297	99.16 131	99.88 3	99.51 119	98.15 135	99.40 157	99.89 33	97.12 132	99.33 294	99.38 53	97.40 285	98.73 274

MDTV_nov1_ep13			98.32 175		99.11 287	94.44 364	99.27 264	98.74 358	97.51 216	99.40 157	99.62 204	94.78 219	99.76 203	97.59 247	98.81 203

CVMVSNet		98.57 166	98.67 143	98.30 289	99.35 226	95.59 340	99.50 163	99.55 79	98.60 86	99.39 160	99.83 71	94.48 240	99.45 268	98.75 129	98.56 215	99.85 36

CNVR-MVS		99.42 44	99.30 53	99.78 52	99.62 141	99.71 44	99.26 273	99.52 104	98.82 65	99.39 160	99.71 155	98.96 24	99.85 151	98.59 154	99.80 102	99.77 82

Effi-MVS+		98.81 146	98.59 159	99.48 123	99.46 195	99.12 140	98.08 394	99.50 139	97.50 217	99.38 162	99.41 270	96.37 162	99.81 183	99.11 82	98.54 217	99.51 178

mvs_anonymous		99.03 116	98.99 102	99.16 174	99.38 219	98.52 212	99.51 156	99.38 235	97.79 182	99.38 162	99.81 93	97.30 127	99.45 268	99.35 56	98.99 188	99.51 178

XVS		99.53 16	99.42 22	99.87 11	99.85 26	99.83 16	99.69 57	99.68 20	98.98 48	99.37 164	99.74 144	98.81 44	99.94 69	98.79 126	99.86 67	99.84 40

X-MVStestdata		96.55 320	95.45 338	99.87 11	99.85 26	99.83 16	99.69 57	99.68 20	98.98 48	99.37 164	64.01 412	98.81 44	99.94 69	98.79 126	99.86 67	99.84 40

PatchmatchNet		98.31 183	98.36 171	98.19 297	99.16 279	95.32 349	99.27 264	98.92 333	97.37 231	99.37 164	99.58 217	94.90 212	99.70 230	97.43 266	99.21 167	99.54 164
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
AllTest		98.87 132	98.72 137	99.31 149	99.86 20	98.48 218	99.56 123	99.61 48	97.85 174	99.36 167	99.85 56	95.95 174	99.85 151	96.66 310	99.83 91	99.59 150

TestCases				99.31 149	99.86 20	98.48 218		99.61 48	97.85 174	99.36 167	99.85 56	95.95 174	99.85 151	96.66 310	99.83 91	99.59 150

Vis-MVSNet (Re-imp)		98.87 132	98.72 137	99.31 149	99.71 97	98.88 175	99.80 25	99.44 208	97.91 168	99.36 167	99.78 124	95.49 193	99.43 277	97.91 215	99.11 176	99.62 142

alignmvs		98.81 146	98.56 162	99.58 94	99.43 202	99.42 99	99.51 156	98.96 328	98.61 85	99.35 170	98.92 350	94.78 219	99.77 199	99.35 56	98.11 243	99.54 164

VPA-MVSNet		98.29 186	97.95 210	99.30 154	99.16 279	99.54 80	99.50 163	99.58 62	98.27 117	99.35 170	99.37 282	92.53 296	99.65 246	99.35 56	94.46 349	98.72 275

AdaColmap		99.01 121	98.80 130	99.66 70	99.56 160	99.54 80	99.18 287	99.70 15	98.18 133	99.35 170	99.63 199	96.32 163	99.90 120	97.48 260	99.77 112	99.55 162

test222					99.75 73	99.49 89	98.91 345	99.49 148	96.42 310	99.34 173	99.65 187	98.28 93			99.69 128	99.72 103

API-MVS		99.04 114	99.03 92	99.06 185	99.40 214	99.31 111	99.55 135	99.56 71	98.54 91	99.33 174	99.39 277	98.76 52	99.78 197	96.98 292	99.78 109	98.07 366

v144192		97.92 234	97.60 249	98.87 220	98.83 332	98.65 198	99.55 135	99.34 254	96.20 323	99.32 175	99.40 273	94.36 244	99.26 306	96.37 318	95.03 340	98.70 281

sasdasda		99.02 117	98.86 123	99.51 117	99.42 204	99.32 107	99.80 25	99.48 160	98.63 82	99.31 176	98.81 355	97.09 134	99.75 206	99.27 69	97.90 249	99.47 189

GeoE		98.85 142	98.62 153	99.53 109	99.61 145	99.08 145	99.80 25	99.51 119	97.10 257	99.31 176	99.78 124	95.23 204	99.77 199	98.21 190	99.03 185	99.75 88

canonicalmvs		99.02 117	98.86 123	99.51 117	99.42 204	99.32 107	99.80 25	99.48 160	98.63 82	99.31 176	98.81 355	97.09 134	99.75 206	99.27 69	97.90 249	99.47 189

V42		98.06 208	97.79 224	98.86 223	98.98 314	98.84 181	99.69 57	99.34 254	96.53 300	99.30 179	99.37 282	94.67 230	99.32 297	97.57 252	94.66 346	98.42 347

ab-mvs		98.86 135	98.63 148	99.54 101	99.64 132	99.19 126	99.44 195	99.54 88	97.77 185	99.30 179	99.81 93	94.20 249	99.93 87	99.17 78	98.82 201	99.49 182

TAPA-MVS	97.07 15	97.74 264	97.34 284	98.94 201	99.70 102	97.53 267	99.25 275	99.51 119	91.90 383	99.30 179	99.63 199	98.78 48	99.64 249	88.09 392	99.87 59	99.65 129
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
新几何1				99.75 58	99.75 73	99.59 71		99.54 88	96.76 281	99.29 182	99.64 193	98.43 83	99.94 69	96.92 299	99.66 133	99.72 103

MGCFI-Net		99.01 121	98.85 125	99.50 122	99.42 204	99.26 120	99.82 16	99.48 160	98.60 86	99.28 183	98.81 355	97.04 138	99.76 203	99.29 66	97.87 252	99.47 189

test_fmvs2		97.25 305	97.30 289	97.09 347	99.43 202	93.31 378	99.73 49	98.87 344	98.83 64	99.28 183	99.80 106	84.45 382	99.66 241	97.88 217	97.45 279	98.30 355

VPNet		97.84 246	97.44 269	99.01 191	99.21 261	98.94 169	99.48 179	99.57 66	98.38 104	99.28 183	99.73 150	88.89 350	99.39 280	99.19 75	93.27 367	98.71 277

HY-MVS	97.30 7	98.85 142	98.64 147	99.47 126	99.42 204	99.08 145	99.62 89	99.36 244	97.39 230	99.28 183	99.68 175	96.44 160	99.92 98	98.37 179	98.22 233	99.40 205

PAPM_NR		99.04 114	98.84 127	99.66 70	99.74 80	99.44 97	99.39 222	99.38 235	97.70 194	99.28 183	99.28 306	98.34 90	99.85 151	96.96 294	99.45 150	99.69 115

HPM-MVS++		99.39 55	99.23 69	99.87 11	99.75 73	99.84 15	99.43 199	99.51 119	98.68 81	99.27 188	99.53 236	98.64 69	99.96 30	98.44 174	99.80 102	99.79 74

v1240		97.69 272	97.32 287	98.79 235	98.85 330	98.43 222	99.48 179	99.36 244	96.11 332	99.27 188	99.36 285	93.76 267	99.24 309	94.46 352	95.23 335	98.70 281

thres600view7		97.86 242	97.51 257	98.92 205	99.72 92	97.95 248	99.59 102	98.74 358	97.94 165	99.27 188	98.62 363	91.75 313	99.86 145	93.73 361	98.19 237	98.96 253

PLC	97.94 4	99.02 117	98.85 125	99.53 109	99.66 124	99.01 154	99.24 277	99.52 104	96.85 277	99.27 188	99.48 253	98.25 94	99.91 109	97.76 232	99.62 139	99.65 129
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
thres100view900		97.76 258	97.45 264	98.69 244	99.72 92	97.86 254	99.59 102	98.74 358	97.93 166	99.26 192	98.62 363	91.75 313	99.83 171	93.22 366	98.18 238	98.37 353

EPMVS		97.82 251	97.65 243	98.35 284	98.88 323	95.98 333	99.49 174	94.71 406	97.57 206	99.26 192	99.48 253	92.46 301	99.71 224	97.87 219	99.08 181	99.35 212

Fast-Effi-MVS+-dtu		98.77 152	98.83 129	98.60 249	99.41 209	96.99 296	99.52 148	99.49 148	98.11 143	99.24 194	99.34 292	96.96 142	99.79 192	97.95 213	99.45 150	99.02 246

v1921920		97.80 255	97.45 264	98.84 227	98.80 333	98.53 208	99.52 148	99.34 254	96.15 329	99.24 194	99.47 256	93.98 258	99.29 301	95.40 339	95.13 338	98.69 285

LPG-MVS_test		98.22 189	98.13 188	98.49 263	99.33 231	97.05 289	99.58 110	99.55 79	97.46 219	99.24 194	99.83 71	92.58 294	99.72 218	98.09 199	97.51 272	98.68 290

LGP-MVS_train				98.49 263	99.33 231	97.05 289		99.55 79	97.46 219	99.24 194	99.83 71	92.58 294	99.72 218	98.09 199	97.51 272	98.68 290

v1144		97.98 225	97.69 239	98.85 226	98.87 326	98.66 197	99.54 139	99.35 250	96.27 318	99.23 198	99.35 288	94.67 230	99.23 310	96.73 305	95.16 337	98.68 290

Anonymous20240529		98.09 204	97.68 240	99.34 142	99.66 124	98.44 221	99.40 218	99.43 214	93.67 370	99.22 199	99.89 33	90.23 339	99.93 87	99.26 71	98.33 225	99.66 125

OPM-MVS		98.19 193	98.10 191	98.45 272	98.88 323	97.07 287	99.28 259	99.38 235	98.57 88	99.22 199	99.81 93	92.12 305	99.66 241	98.08 203	97.54 270	98.61 327
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
test_djsdf		98.67 160	98.57 160	98.98 195	98.70 350	98.91 173	99.88 3	99.46 189	97.55 209	99.22 199	99.88 39	95.73 185	99.28 302	99.03 88	97.62 263	98.75 269

test12				99.75 58	99.64 132	99.61 67		99.29 283		99.21 202		98.38 88	99.89 131		99.74 120	99.74 92

NCCC		99.34 60	99.19 72	99.79 49	99.61 145	99.65 57	99.30 249	99.48 160	98.86 60	99.21 202	99.63 199	98.72 61	99.90 120	98.25 188	99.63 138	99.80 70

PMMVS		98.80 149	98.62 153	99.34 142	99.27 248	98.70 194	98.76 359	99.31 275	97.34 233	99.21 202	99.07 330	97.20 130	99.82 178	98.56 161	98.87 196	99.52 172

v1192		97.81 253	97.44 269	98.91 209	98.88 323	98.68 195	99.51 156	99.34 254	96.18 325	99.20 205	99.34 292	94.03 256	99.36 288	95.32 341	95.18 336	98.69 285

EI-MVSNet		98.67 160	98.67 143	98.68 245	99.35 226	97.97 244	99.50 163	99.38 235	96.93 274	99.20 205	99.83 71	97.87 109	99.36 288	98.38 177	97.56 268	98.71 277

MVSTER		98.49 167	98.32 175	99.00 193	99.35 226	99.02 152	99.54 139	99.38 235	97.41 228	99.20 205	99.73 150	93.86 263	99.36 288	98.87 108	97.56 268	98.62 318

UWE-MVS		97.58 284	97.29 291	98.48 265	99.09 293	96.25 328	99.01 326	96.61 399	97.86 171	99.19 208	99.01 338	88.72 351	99.90 120	97.38 269	98.69 207	99.28 220

Anonymous202405211		98.30 185	97.98 206	99.26 163	99.57 156	98.16 233	99.41 210	98.55 371	96.03 337	99.19 208	99.74 144	91.87 310	99.92 98	99.16 79	98.29 230	99.70 113

v2v482		98.06 208	97.77 229	98.92 205	98.90 321	98.82 185	99.57 117	99.36 244	96.65 289	99.19 208	99.35 288	94.20 249	99.25 307	97.72 238	94.97 341	98.69 285

CNLPA		99.14 92	98.99 102	99.59 91	99.58 154	99.41 101	99.16 289	99.44 208	98.45 98	99.19 208	99.49 248	98.08 104	99.89 131	97.73 236	99.75 117	99.48 183

UGNet		98.87 132	98.69 141	99.40 136	99.22 260	98.72 193	99.44 195	99.68 20	99.24 17	99.18 212	99.42 266	92.74 286	99.96 30	99.34 60	99.94 26	99.53 170
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
tfpn200view9		97.72 267	97.38 277	98.72 240	99.69 107	97.96 246	99.50 163	98.73 363	97.83 177	99.17 213	98.45 368	91.67 317	99.83 171	93.22 366	98.18 238	98.37 353

thres400		97.77 257	97.38 277	98.92 205	99.69 107	97.96 246	99.50 163	98.73 363	97.83 177	99.17 213	98.45 368	91.67 317	99.83 171	93.22 366	98.18 238	98.96 253

Test_1112_low_res		98.89 130	98.66 146	99.57 96	99.69 107	98.95 166	99.03 318	99.47 180	96.98 267	99.15 215	99.23 314	96.77 147	99.89 131	98.83 121	98.78 204	99.86 33

baseline1		98.31 183	97.95 210	99.38 140	99.50 184	98.74 191	99.59 102	98.93 330	98.41 102	99.14 216	99.60 211	94.59 233	99.79 192	98.48 168	93.29 366	99.61 144

1112_ss		98.98 123	98.77 134	99.59 91	99.68 111	99.02 152	99.25 275	99.48 160	97.23 244	99.13 217	99.58 217	96.93 143	99.90 120	98.87 108	98.78 204	99.84 40

CLD-MVS		98.16 197	98.10 191	98.33 285	99.29 243	96.82 307	98.75 360	99.44 208	97.83 177	99.13 217	99.55 227	92.92 280	99.67 238	98.32 185	97.69 259	98.48 339
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
原ACMM1				99.65 74	99.73 88	99.33 106		99.47 180	97.46 219	99.12 219	99.66 186	98.67 66	99.91 109	97.70 241	99.69 128	99.71 112

tpm		97.67 277	97.55 251	98.03 306	99.02 306	95.01 355	99.43 199	98.54 372	96.44 308	99.12 219	99.34 292	91.83 312	99.60 257	97.75 234	96.46 305	99.48 183

HQP_MVS		98.27 188	98.22 181	98.44 275	99.29 243	96.97 298	99.39 222	99.47 180	98.97 51	99.11 221	99.61 208	92.71 289	99.69 235	97.78 228	97.63 261	98.67 297

plane_prior3						97.00 295			98.69 79	99.11 221

CHOSEN 1792x2688		99.19 82	99.10 80	99.45 129	99.89 8	98.52 212	99.39 222	99.94 1	98.73 76	99.11 221	99.89 33	95.50 192	99.94 69	99.50 41	99.97 8	99.89 20

v8		97.95 230	97.63 247	98.93 203	98.95 318	98.81 187	99.80 25	99.41 218	96.03 337	99.10 224	99.42 266	94.92 211	99.30 300	96.94 296	94.08 357	98.66 305

ADS-MVSNet2		98.02 218	98.07 198	97.87 318	99.33 231	95.19 352	99.23 278	99.08 313	96.24 320	99.10 224	99.67 181	94.11 253	98.93 358	96.81 302	99.05 183	99.48 183

ADS-MVSNet		98.20 192	98.08 195	98.56 257	99.33 231	96.48 320	99.23 278	99.15 305	96.24 320	99.10 224	99.67 181	94.11 253	99.71 224	96.81 302	99.05 183	99.48 183

thres200		97.61 282	97.28 292	98.62 248	99.64 132	98.03 240	99.26 273	98.74 358	97.68 196	99.09 227	98.32 374	91.66 319	99.81 183	92.88 371	98.22 233	98.03 369

dp		97.75 262	97.80 223	97.59 334	99.10 290	93.71 373	99.32 244	98.88 342	96.48 305	99.08 228	99.55 227	92.67 292	99.82 178	96.52 313	98.58 212	99.24 224

WB-MVSnew		97.65 279	97.65 243	97.63 331	98.78 337	97.62 265	99.13 295	98.33 375	97.36 232	99.07 229	98.94 346	95.64 189	99.15 323	92.95 370	98.68 208	96.12 397

GBi-Net		97.68 274	97.48 259	98.29 290	99.51 175	97.26 276	99.43 199	99.48 160	96.49 302	99.07 229	99.32 299	90.26 336	98.98 348	97.10 285	96.65 300	98.62 318

test1		97.68 274	97.48 259	98.29 290	99.51 175	97.26 276	99.43 199	99.48 160	96.49 302	99.07 229	99.32 299	90.26 336	98.98 348	97.10 285	96.65 300	98.62 318

FMVSNet3		98.03 216	97.76 233	98.84 227	99.39 217	98.98 156	99.40 218	99.38 235	96.67 287	99.07 229	99.28 306	92.93 279	98.98 348	97.10 285	96.65 300	98.56 334

IterMVS-LS		98.46 170	98.42 168	98.58 253	99.59 152	98.00 242	99.37 229	99.43 214	96.94 273	99.07 229	99.59 213	97.87 109	99.03 341	98.32 185	95.62 327	98.71 277
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dmvs_re		98.08 206	98.16 183	97.85 319	99.55 164	94.67 361	99.70 54	98.92 333	98.15 135	99.06 234	99.35 288	93.67 269	99.25 307	97.77 231	97.25 290	99.64 136

pmmvs4		98.13 200	97.90 215	98.81 232	98.61 359	98.87 176	98.99 329	99.21 298	96.44 308	99.06 234	99.58 217	95.90 179	99.11 332	97.18 283	96.11 313	98.46 344

XVG-ACMP-BASELINE		97.83 248	97.71 238	98.20 296	99.11 287	96.33 325	99.41 210	99.52 104	98.06 156	99.05 236	99.50 245	89.64 345	99.73 214	97.73 236	97.38 287	98.53 335

CostFormer		97.72 267	97.73 236	97.71 329	99.15 283	94.02 369	99.54 139	99.02 321	94.67 361	99.04 237	99.35 288	92.35 304	99.77 199	98.50 167	97.94 248	99.34 215

DP-MVS		99.16 88	98.95 110	99.78 52	99.77 62	99.53 83	99.41 210	99.50 139	97.03 265	99.04 237	99.88 39	97.39 121	99.92 98	98.66 142	99.90 44	99.87 31

ACMM	97.58 5	98.37 180	98.34 173	98.48 265	99.41 209	97.10 283	99.56 123	99.45 200	98.53 92	99.04 237	99.85 56	93.00 278	99.71 224	98.74 130	97.45 279	98.64 309
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Fast-Effi-MVS+		98.70 157	98.43 167	99.51 117	99.51 175	99.28 116	99.52 148	99.47 180	96.11 332	99.01 240	99.34 292	96.20 167	99.84 158	97.88 217	98.82 201	99.39 206

nrg030		98.64 163	98.42 168	99.28 161	99.05 303	99.69 47	99.81 20	99.46 189	98.04 158	99.01 240	99.82 79	96.69 150	99.38 281	99.34 60	94.59 348	98.78 262

test_prior2							98.96 336		98.34 110	99.01 240	99.52 239	98.68 64		97.96 212	99.74 120

MAR-MVS		98.86 135	98.63 148	99.54 101	99.37 222	99.66 53	99.45 189	99.54 88	96.61 294	99.01 240	99.40 273	97.09 134	99.86 145	97.68 243	99.53 146	99.10 231
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
PS-MVSNAJss		98.92 128	98.92 112	98.90 211	98.78 337	98.53 208	99.78 32	99.54 88	98.07 152	99.00 244	99.76 136	99.01 18	99.37 284	99.13 80	97.23 291	98.81 260

PAPR		98.63 164	98.34 173	99.51 117	99.40 214	99.03 151	98.80 355	99.36 244	96.33 313	99.00 244	99.12 328	98.46 81	99.84 158	95.23 343	99.37 161	99.66 125

D2MVS		98.41 175	98.50 165	98.15 302	99.26 250	96.62 315	99.40 218	99.61 48	97.71 191	98.98 246	99.36 285	96.04 170	99.67 238	98.70 135	97.41 284	98.15 363

v10		97.85 243	97.52 255	98.86 223	98.99 311	98.67 196	99.75 41	99.41 218	95.70 342	98.98 246	99.41 270	94.75 224	99.23 310	96.01 324	94.63 347	98.67 297

miper_enhance_ethall		98.16 197	98.08 195	98.41 278	98.96 317	97.72 260	98.45 380	99.32 271	96.95 271	98.97 248	99.17 320	97.06 137	99.22 313	97.86 220	95.99 316	98.29 356

UniMVSNet (Re)		98.29 186	98.00 204	99.13 179	99.00 308	99.36 105	99.49 174	99.51 119	97.95 164	98.97 248	99.13 325	96.30 164	99.38 281	98.36 181	93.34 365	98.66 305

TEST9					99.67 114	99.65 57	99.05 313	99.41 218	96.22 322	98.95 250	99.49 248	98.77 51	99.91 109

train_agg		99.02 117	98.77 134	99.77 55	99.67 114	99.65 57	99.05 313	99.41 218	96.28 316	98.95 250	99.49 248	98.76 52	99.91 109	97.63 244	99.72 123	99.75 88

BH-RMVSNet		98.41 175	98.08 195	99.40 136	99.41 209	98.83 184	99.30 249	98.77 354	97.70 194	98.94 252	99.65 187	92.91 282	99.74 208	96.52 313	99.55 145	99.64 136

test_8					99.67 114	99.61 67	99.03 318	99.41 218	96.28 316	98.93 253	99.48 253	98.76 52	99.91 109

3Dnovator	97.25 9	99.24 78	99.05 88	99.81 44	99.12 285	99.66 53	99.84 12	99.74 10	99.09 32	98.92 254	99.90 29	95.94 176	99.98 13	98.95 96	99.92 29	99.79 74

v7n		97.87 240	97.52 255	98.92 205	98.76 343	98.58 204	99.84 12	99.46 189	96.20 323	98.91 255	99.70 159	94.89 213	99.44 273	96.03 322	93.89 360	98.75 269

JIA-IIPM		97.50 290	97.02 304	98.93 203	98.73 345	97.80 256	99.30 249	98.97 326	91.73 384	98.91 255	94.86 399	95.10 206	99.71 224	97.58 248	97.98 246	99.28 220

v148		97.79 256	97.55 251	98.50 262	98.74 344	97.72 260	99.54 139	99.33 261	96.26 319	98.90 257	99.51 242	94.68 229	99.14 324	97.83 224	93.15 369	98.63 316

GA-MVS		97.85 243	97.47 261	99.00 193	99.38 219	97.99 243	98.57 374	99.15 305	97.04 264	98.90 257	99.30 302	89.83 342	99.38 281	96.70 307	98.33 225	99.62 142

tpm2		97.44 297	97.34 284	97.74 328	99.15 283	94.36 366	99.45 189	98.94 329	93.45 375	98.90 257	99.44 262	91.35 325	99.59 258	97.31 272	98.07 244	99.29 219

tt0805		97.97 228	97.77 229	98.57 254	99.59 152	96.61 316	99.45 189	99.08 313	98.21 128	98.88 260	99.80 106	88.66 354	99.70 230	98.58 155	97.72 258	99.39 206

miper_ehance_all_eth		98.18 195	98.10 191	98.41 278	99.23 256	97.72 260	98.72 363	99.31 275	96.60 296	98.88 260	99.29 304	97.29 128	99.13 327	97.60 246	95.99 316	98.38 352

eth_miper_zixun_eth		98.05 213	97.96 208	98.33 285	99.26 250	97.38 271	98.56 376	99.31 275	96.65 289	98.88 260	99.52 239	96.58 153	99.12 331	97.39 268	95.53 330	98.47 341

cl22		97.85 243	97.64 246	98.48 265	99.09 293	97.87 252	98.60 373	99.33 261	97.11 256	98.87 263	99.22 315	92.38 303	99.17 322	98.21 190	95.99 316	98.42 347

agg_prior					99.67 114	99.62 65		99.40 224		98.87 263			99.91 109

anonymousdsp		98.44 171	98.28 178	98.94 201	98.50 365	98.96 163	99.77 34	99.50 139	97.07 259	98.87 263	99.77 132	94.76 223	99.28 302	98.66 142	97.60 264	98.57 333

DSMNet-mixed		97.25 305	97.35 281	96.95 351	97.84 376	93.61 376	99.57 117	96.63 398	96.13 331	98.87 263	98.61 365	94.59 233	97.70 388	95.08 345	98.86 197	99.55 162

FMVSNet2		97.72 267	97.36 279	98.80 234	99.51 175	98.84 181	99.45 189	99.42 216	96.49 302	98.86 267	99.29 304	90.26 336	98.98 348	96.44 315	96.56 303	98.58 332

c3_l		98.12 202	98.04 200	98.38 282	99.30 239	97.69 264	98.81 354	99.33 261	96.67 287	98.83 268	99.34 292	97.11 133	98.99 347	97.58 248	95.34 333	98.48 339

ITE_SJBPF				98.08 304	99.29 243	96.37 323		98.92 333	98.34 110	98.83 268	99.75 139	91.09 328	99.62 255	95.82 326	97.40 285	98.25 359

Anonymous20231211		97.88 238	97.54 254	98.90 211	99.71 97	98.53 208	99.48 179	99.57 66	94.16 366	98.81 270	99.68 175	93.23 273	99.42 278	98.84 118	94.42 351	98.76 267

Patchmtry		97.75 262	97.40 276	98.81 232	99.10 290	98.87 176	99.11 304	99.33 261	94.83 358	98.81 270	99.38 279	94.33 245	99.02 343	96.10 320	95.57 328	98.53 335

miper_lstm_enhance		98.00 223	97.91 214	98.28 293	99.34 230	97.43 270	98.88 347	99.36 244	96.48 305	98.80 272	99.55 227	95.98 172	98.91 359	97.27 274	95.50 331	98.51 337

BH-untuned		98.42 173	98.36 171	98.59 250	99.49 186	96.70 310	99.27 264	99.13 308	97.24 243	98.80 272	99.38 279	95.75 184	99.74 208	97.07 288	99.16 170	99.33 216

FIs		98.78 150	98.63 148	99.23 168	99.18 269	99.54 80	99.83 15	99.59 58	98.28 115	98.79 274	99.81 93	96.75 148	99.37 284	99.08 85	96.38 307	98.78 262

OurMVSNet-221017-0		97.88 238	97.77 229	98.19 297	98.71 349	96.53 318	99.88 3	99.00 323	97.79 182	98.78 275	99.94 6	91.68 316	99.35 291	97.21 277	96.99 298	98.69 285

MVS-HIRNet		95.75 336	95.16 341	97.51 336	99.30 239	93.69 374	98.88 347	95.78 401	85.09 398	98.78 275	92.65 401	91.29 326	99.37 284	94.85 348	99.85 74	99.46 194

tpmvs		97.98 225	98.02 203	97.84 321	99.04 304	94.73 359	99.31 247	99.20 299	96.10 336	98.76 277	99.42 266	94.94 208	99.81 183	96.97 293	98.45 221	98.97 251

Patchmatch-test		97.93 231	97.65 243	98.77 237	99.18 269	97.07 287	99.03 318	99.14 307	96.16 327	98.74 278	99.57 221	94.56 235	99.72 218	93.36 365	99.11 176	99.52 172

QAPM		98.67 160	98.30 177	99.80 46	99.20 263	99.67 51	99.77 34	99.72 11	94.74 360	98.73 279	99.90 29	95.78 183	99.98 13	96.96 294	99.88 56	99.76 87

3Dnovator+	97.12 13	99.18 84	98.97 106	99.82 41	99.17 277	99.68 48	99.81 20	99.51 119	99.20 18	98.72 280	99.89 33	95.68 187	99.97 21	98.86 113	99.86 67	99.81 61

IterMVS-SCA-FT		97.82 251	97.75 234	98.06 305	99.57 156	96.36 324	99.02 321	99.49 148	97.18 247	98.71 281	99.72 154	92.72 287	99.14 324	97.44 265	95.86 321	98.67 297

UniMVSNet_NR-MVSNet		98.22 189	97.97 207	98.96 198	98.92 320	98.98 156	99.48 179	99.53 99	97.76 186	98.71 281	99.46 260	96.43 161	99.22 313	98.57 158	92.87 372	98.69 285

DU-MVS		98.08 206	97.79 224	98.96 198	98.87 326	98.98 156	99.41 210	99.45 200	97.87 170	98.71 281	99.50 245	94.82 215	99.22 313	98.57 158	92.87 372	98.68 290

tpm cat1		97.39 299	97.36 279	97.50 337	99.17 277	93.73 372	99.43 199	99.31 275	91.27 385	98.71 281	99.08 329	94.31 247	99.77 199	96.41 317	98.50 219	99.00 247

XXY-MVS		98.38 179	98.09 194	99.24 166	99.26 250	99.32 107	99.56 123	99.55 79	97.45 222	98.71 281	99.83 71	93.23 273	99.63 254	98.88 105	96.32 309	98.76 267

IterMVS		97.83 248	97.77 229	98.02 308	99.58 154	96.27 327	99.02 321	99.48 160	97.22 245	98.71 281	99.70 159	92.75 284	99.13 327	97.46 263	96.00 315	98.67 297
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FC-MVSNet-test		98.75 153	98.62 153	99.15 178	99.08 296	99.45 96	99.86 11	99.60 54	98.23 125	98.70 287	99.82 79	96.80 145	99.22 313	99.07 86	96.38 307	98.79 261

COLMAP_ROB	97.56 6	98.86 135	98.75 136	99.17 173	99.88 11	98.53 208	99.34 241	99.59 58	97.55 209	98.70 287	99.89 33	95.83 181	99.90 120	98.10 198	99.90 44	99.08 236
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TR-MVS		97.76 258	97.41 275	98.82 229	99.06 300	97.87 252	98.87 349	98.56 370	96.63 293	98.68 289	99.22 315	92.49 297	99.65 246	95.40 339	97.79 256	98.95 255

WR-MVS		98.06 208	97.73 236	99.06 185	98.86 329	99.25 122	99.19 285	99.35 250	97.30 237	98.66 290	99.43 264	93.94 259	99.21 318	98.58 155	94.28 353	98.71 277

HQP-NCC					99.19 266		98.98 332		98.24 122	98.66 290

ACMP_Plane					99.19 266		98.98 332		98.24 122	98.66 290

HQP4-MVS										98.66 290			99.64 249			98.64 309

HQP-MVS		98.02 218	97.90 215	98.37 283	99.19 266	96.83 305	98.98 332	99.39 227	98.24 122	98.66 290	99.40 273	92.47 298	99.64 249	97.19 281	97.58 266	98.64 309

LF4IMVS		97.52 287	97.46 263	97.70 330	98.98 314	95.55 341	99.29 254	98.82 349	98.07 152	98.66 290	99.64 193	89.97 341	99.61 256	97.01 289	96.68 299	97.94 376

mvs_tets		98.40 178	98.23 180	98.91 209	98.67 353	98.51 214	99.66 71	99.53 99	98.19 130	98.65 296	99.81 93	92.75 284	99.44 273	99.31 63	97.48 278	98.77 265

TESTMET0.1,1		97.55 285	97.27 295	98.40 280	98.93 319	96.53 318	98.67 366	97.61 389	96.96 269	98.64 297	99.28 306	88.63 356	99.45 268	97.30 273	99.38 154	99.21 226

jajsoiax		98.43 172	98.28 178	98.88 216	98.60 360	98.43 222	99.82 16	99.53 99	98.19 130	98.63 298	99.80 106	93.22 275	99.44 273	99.22 73	97.50 274	98.77 265

Baseline_NR-MVSNet		97.76 258	97.45 264	98.68 245	99.09 293	98.29 227	99.41 210	98.85 346	95.65 343	98.63 298	99.67 181	94.82 215	99.10 334	98.07 206	92.89 371	98.64 309

EPNet		98.86 135	98.71 139	99.30 154	97.20 388	98.18 232	99.62 89	98.91 337	99.28 16	98.63 298	99.81 93	95.96 173	99.99 4	99.24 72	99.72 123	99.73 97
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test-LLR		98.06 208	97.90 215	98.55 259	98.79 334	97.10 283	98.67 366	97.75 386	97.34 233	98.61 301	98.85 352	94.45 242	99.45 268	97.25 275	99.38 154	99.10 231

test-mter		97.49 295	97.13 300	98.55 259	98.79 334	97.10 283	98.67 366	97.75 386	96.65 289	98.61 301	98.85 352	88.23 360	99.45 268	97.25 275	99.38 154	99.10 231

DIV-MVS_self_test		98.01 221	97.85 221	98.48 265	99.24 255	97.95 248	98.71 364	99.35 250	96.50 301	98.60 303	99.54 232	95.72 186	99.03 341	97.21 277	95.77 322	98.46 344

cl____		98.01 221	97.84 222	98.55 259	99.25 254	97.97 244	98.71 364	99.34 254	96.47 307	98.59 304	99.54 232	95.65 188	99.21 318	97.21 277	95.77 322	98.46 344

ETVMVS		97.50 290	96.90 308	99.29 157	99.23 256	98.78 190	99.32 244	98.90 339	97.52 215	98.56 305	98.09 383	84.72 381	99.69 235	97.86 220	97.88 251	99.39 206

FMVSNet1		96.84 316	96.36 320	98.29 290	99.32 237	97.26 276	99.43 199	99.48 160	95.11 350	98.55 306	99.32 299	83.95 384	98.98 348	95.81 327	96.26 310	98.62 318

UniMVSNet_ETH3D		97.32 302	96.81 310	98.87 220	99.40 214	97.46 269	99.51 156	99.53 99	95.86 341	98.54 307	99.77 132	82.44 390	99.66 241	98.68 140	97.52 271	99.50 181

AUN-MVS		96.88 315	96.31 321	98.59 250	99.48 193	97.04 292	99.27 264	99.22 295	97.44 224	98.51 308	99.41 270	91.97 308	99.66 241	97.71 239	83.83 396	99.07 241

PCF-MVS	97.08 14	97.66 278	97.06 303	99.47 126	99.61 145	99.09 142	98.04 395	99.25 290	91.24 386	98.51 308	99.70 159	94.55 237	99.91 109	92.76 374	99.85 74	99.42 201
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TranMVSNet+NR-MVSNet		97.93 231	97.66 242	98.76 238	98.78 337	98.62 201	99.65 77	99.49 148	97.76 186	98.49 310	99.60 211	94.23 248	98.97 355	98.00 210	92.90 370	98.70 281

CP-MVSNet		98.09 204	97.78 227	99.01 191	98.97 316	99.24 123	99.67 66	99.46 189	97.25 241	98.48 311	99.64 193	93.79 265	99.06 337	98.63 145	94.10 356	98.74 272

ACMP	97.20 11	98.06 208	97.94 212	98.45 272	99.37 222	97.01 294	99.44 195	99.49 148	97.54 212	98.45 312	99.79 118	91.95 309	99.72 218	97.91 215	97.49 277	98.62 318
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
cascas		97.69 272	97.43 273	98.48 265	98.60 360	97.30 272	98.18 392	99.39 227	92.96 378	98.41 313	98.78 359	93.77 266	99.27 305	98.16 196	98.61 209	98.86 257

WR-MVS_H		98.13 200	97.87 220	98.90 211	99.02 306	98.84 181	99.70 54	99.59 58	97.27 239	98.40 314	99.19 319	95.53 191	99.23 310	98.34 182	93.78 362	98.61 327

BH-w/o		98.00 223	97.89 219	98.32 287	99.35 226	96.20 330	99.01 326	98.90 339	96.42 310	98.38 315	99.00 339	95.26 202	99.72 218	96.06 321	98.61 209	99.03 244

pmmvs5		97.52 287	97.30 289	98.16 299	98.57 362	96.73 309	99.27 264	98.90 339	96.14 330	98.37 316	99.53 236	91.54 322	99.14 324	97.51 257	95.87 320	98.63 316

EU-MVSNet		97.98 225	98.03 201	97.81 325	98.72 347	96.65 314	99.66 71	99.66 28	98.09 147	98.35 317	99.82 79	95.25 203	98.01 381	97.41 267	95.30 334	98.78 262

FMVSNet5		96.43 324	96.19 323	97.15 343	99.11 287	95.89 335	99.32 244	99.52 104	94.47 365	98.34 318	99.07 330	87.54 367	97.07 393	92.61 375	95.72 325	98.47 341

testing91		97.44 297	97.02 304	98.71 242	99.18 269	96.89 304	99.19 285	99.04 319	97.78 184	98.31 319	98.29 375	85.41 376	99.85 151	98.01 209	97.95 247	99.39 206

PS-CasMVS		97.93 231	97.59 250	98.95 200	98.99 311	99.06 148	99.68 63	99.52 104	97.13 251	98.31 319	99.68 175	92.44 302	99.05 338	98.51 166	94.08 357	98.75 269

USDC		97.34 301	97.20 296	97.75 327	99.07 297	95.20 351	98.51 378	99.04 319	97.99 162	98.31 319	99.86 51	89.02 348	99.55 262	95.67 333	97.36 288	98.49 338

PEN-MVS		97.76 258	97.44 269	98.72 240	98.77 342	98.54 207	99.78 32	99.51 119	97.06 261	98.29 322	99.64 193	92.63 293	98.89 361	98.09 199	93.16 368	98.72 275

tfpnnormal		97.84 246	97.47 261	98.98 195	99.20 263	99.22 125	99.64 80	99.61 48	96.32 314	98.27 323	99.70 159	93.35 272	99.44 273	95.69 331	95.40 332	98.27 357

testing99		97.36 300	96.94 307	98.63 247	99.18 269	96.70 310	99.30 249	98.93 330	97.71 191	98.23 324	98.26 376	84.92 379	99.84 158	98.04 208	97.85 254	99.35 212

testing222		97.16 308	96.50 316	99.16 174	99.16 279	98.47 220	99.27 264	98.66 367	97.71 191	98.23 324	98.15 378	82.28 392	99.84 158	97.36 270	97.66 260	99.18 227

ppachtmachnet_test		97.49 295	97.45 264	97.61 333	98.62 357	95.24 350	98.80 355	99.46 189	96.11 332	98.22 326	99.62 204	96.45 159	98.97 355	93.77 360	95.97 319	98.61 327

testing11		97.50 290	97.10 301	98.71 242	99.20 263	96.91 302	99.29 254	98.82 349	97.89 169	98.21 327	98.40 370	85.63 374	99.83 171	98.45 173	98.04 245	99.37 210

our_test_3		97.65 279	97.68 240	97.55 335	98.62 357	94.97 356	98.84 351	99.30 279	96.83 280	98.19 328	99.34 292	97.01 140	99.02 343	95.00 347	96.01 314	98.64 309

LTVRE_ROB	97.16 12	98.02 218	97.90 215	98.40 280	99.23 256	96.80 308	99.70 54	99.60 54	97.12 253	98.18 329	99.70 159	91.73 315	99.72 218	98.39 176	97.45 279	98.68 290
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
ACMH	97.28 8	98.10 203	97.99 205	98.44 275	99.41 209	96.96 300	99.60 96	99.56 71	98.09 147	98.15 330	99.91 22	90.87 331	99.70 230	98.88 105	97.45 279	98.67 297
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MS-PatchMatch		97.24 307	97.32 287	96.99 348	98.45 367	93.51 377	98.82 353	99.32 271	97.41 228	98.13 331	99.30 302	88.99 349	99.56 260	95.68 332	99.80 102	97.90 379

MVS		97.28 303	96.55 315	99.48 123	98.78 337	98.95 166	99.27 264	99.39 227	83.53 399	98.08 332	99.54 232	96.97 141	99.87 142	94.23 356	99.16 170	99.63 140

PAPM		97.59 283	97.09 302	99.07 183	99.06 300	98.26 229	98.30 388	99.10 310	94.88 356	98.08 332	99.34 292	96.27 165	99.64 249	89.87 385	98.92 193	99.31 218

OpenMVS	96.50 16	98.47 169	98.12 189	99.52 115	99.04 304	99.53 83	99.82 16	99.72 11	94.56 363	98.08 332	99.88 39	94.73 225	99.98 13	97.47 262	99.76 115	99.06 242

gg-mvs-nofinetune		96.17 329	95.32 340	98.73 239	98.79 334	98.14 235	99.38 227	94.09 407	91.07 388	98.07 335	91.04 405	89.62 346	99.35 291	96.75 304	99.09 180	98.68 290

test0.0.03 1		97.71 270	97.42 274	98.56 257	98.41 369	97.82 255	98.78 357	98.63 368	97.34 233	98.05 336	98.98 342	94.45 242	98.98 348	95.04 346	97.15 295	98.89 256

APD_test1		95.87 333	96.49 317	94.00 368	99.53 167	84.01 397	99.54 139	99.32 271	95.91 340	97.99 337	99.85 56	85.49 375	99.88 137	91.96 377	98.84 199	98.12 364

1314		98.68 159	98.54 163	99.11 180	98.89 322	98.65 198	99.27 264	99.49 148	96.89 275	97.99 337	99.56 224	97.72 115	99.83 171	97.74 235	99.27 165	98.84 259

DTE-MVSNet		97.51 289	97.19 297	98.46 271	98.63 356	98.13 236	99.84 12	99.48 160	96.68 286	97.97 339	99.67 181	92.92 280	98.56 370	96.88 301	92.60 375	98.70 281

SixPastTwentyTwo		97.50 290	97.33 286	98.03 306	98.65 354	96.23 329	99.77 34	98.68 366	97.14 250	97.90 340	99.93 10	90.45 334	99.18 321	97.00 290	96.43 306	98.67 297

testing3		97.28 303	96.76 312	98.82 229	99.37 222	98.07 239	99.45 189	99.36 244	97.56 208	97.89 341	98.95 345	83.70 385	98.82 362	96.03 322	98.56 215	99.58 154

pm-mvs1		97.68 274	97.28 292	98.88 216	99.06 300	98.62 201	99.50 163	99.45 200	96.32 314	97.87 342	99.79 118	92.47 298	99.35 291	97.54 255	93.54 364	98.67 297

testgi		97.65 279	97.50 258	98.13 303	99.36 225	96.45 321	99.42 206	99.48 160	97.76 186	97.87 342	99.45 261	91.09 328	98.81 363	94.53 351	98.52 218	99.13 230

EPNet_dtu		98.03 216	97.96 208	98.23 295	98.27 370	95.54 343	99.23 278	98.75 355	99.02 38	97.82 344	99.71 155	96.11 168	99.48 265	93.04 369	99.65 135	99.69 115
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TinyColmap		97.12 310	96.89 309	97.83 322	99.07 297	95.52 344	98.57 374	98.74 358	97.58 205	97.81 345	99.79 118	88.16 361	99.56 260	95.10 344	97.21 292	98.39 351

ACMH+	97.24 10	97.92 234	97.78 227	98.32 287	99.46 195	96.68 313	99.56 123	99.54 88	98.41 102	97.79 346	99.87 47	90.18 340	99.66 241	98.05 207	97.18 294	98.62 318

N_pmnet		94.95 345	95.83 332	92.31 375	98.47 366	79.33 407	99.12 298	92.81 413	93.87 368	97.68 347	99.13 325	93.87 262	99.01 345	91.38 380	96.19 311	98.59 331

KD-MVS_2432*1600		94.62 346	93.72 354	97.31 340	97.19 389	95.82 336	98.34 384	99.20 299	95.00 354	97.57 348	98.35 372	87.95 363	98.10 378	92.87 372	77.00 403	98.01 370

miper_refine_blended		94.62 346	93.72 354	97.31 340	97.19 389	95.82 336	98.34 384	99.20 299	95.00 354	97.57 348	98.35 372	87.95 363	98.10 378	92.87 372	77.00 403	98.01 370

PVSNet_0	94.43 19	96.09 331	95.47 337	97.94 314	99.31 238	94.34 367	97.81 396	99.70 15	97.12 253	97.46 350	98.75 360	89.71 343	99.79 192	97.69 242	81.69 399	99.68 119

Syy-MVS		97.09 312	97.14 298	96.95 351	99.00 308	92.73 382	99.29 254	99.39 227	97.06 261	97.41 351	98.15 378	93.92 261	98.68 368	91.71 378	98.34 223	99.45 197

myMVS_eth3d		96.89 314	96.37 319	98.43 277	99.00 308	97.16 280	99.29 254	99.39 227	97.06 261	97.41 351	98.15 378	83.46 386	98.68 368	95.27 342	98.34 223	99.45 197

pmmvs6		96.53 321	96.09 326	97.82 324	98.69 351	95.47 345	99.37 229	99.47 180	93.46 374	97.41 351	99.78 124	87.06 369	99.33 294	96.92 299	92.70 374	98.65 307

new_pmnet		96.38 325	96.03 327	97.41 338	98.13 373	95.16 354	99.05 313	99.20 299	93.94 367	97.39 354	98.79 358	91.61 321	99.04 339	90.43 383	95.77 322	98.05 368

CL-MVSNet_self_test		94.49 348	93.97 352	96.08 362	96.16 393	93.67 375	98.33 386	99.38 235	95.13 348	97.33 355	98.15 378	92.69 291	96.57 396	88.67 389	79.87 401	97.99 373

IB-MVS	95.67 18	96.22 326	95.44 339	98.57 254	99.21 261	96.70 310	98.65 369	97.74 388	96.71 284	97.27 356	98.54 366	86.03 371	99.92 98	98.47 171	86.30 393	99.10 231
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
GG-mvs-BLEND				98.45 272	98.55 363	98.16 233	99.43 199	93.68 408		97.23 357	98.46 367	89.30 347	99.22 313	95.43 338	98.22 233	97.98 374

MVP-Stereo		97.81 253	97.75 234	97.99 312	97.53 381	96.60 317	98.96 336	98.85 346	97.22 245	97.23 357	99.36 285	95.28 199	99.46 267	95.51 335	99.78 109	97.92 378
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Anonymous20240521		96.20 328	95.89 331	97.13 345	97.72 380	94.96 357	99.79 31	99.29 283	93.01 377	97.20 359	99.03 335	89.69 344	98.36 374	91.16 381	96.13 312	98.07 366

TransMVSNet (Re)		97.15 309	96.58 314	98.86 223	99.12 285	98.85 180	99.49 174	98.91 337	95.48 345	97.16 360	99.80 106	93.38 271	99.11 332	94.16 358	91.73 377	98.62 318

KD-MVS_self_test		95.00 343	94.34 348	96.96 350	97.07 391	95.39 348	99.56 123	99.44 208	95.11 350	97.13 361	97.32 391	91.86 311	97.27 392	90.35 384	81.23 400	98.23 361

NR-MVSNet		97.97 228	97.61 248	99.02 190	98.87 326	99.26 120	99.47 185	99.42 216	97.63 201	97.08 362	99.50 245	95.07 207	99.13 327	97.86 220	93.59 363	98.68 290

Anonymous20231206		96.22 326	96.03 327	96.79 356	97.31 386	94.14 368	99.63 84	99.08 313	96.17 326	97.04 363	99.06 332	93.94 259	97.76 387	86.96 396	95.06 339	98.47 341

test_0402		96.64 319	96.24 322	97.85 319	98.85 330	96.43 322	99.44 195	99.26 288	93.52 372	96.98 364	99.52 239	88.52 357	99.20 320	92.58 376	97.50 274	97.93 377

MIMVSNet1		95.51 337	95.04 342	96.92 353	97.38 383	95.60 339	99.52 148	99.50 139	93.65 371	96.97 365	99.17 320	85.28 378	96.56 397	88.36 391	95.55 329	98.60 330

dongtai		93.26 355	92.93 359	94.25 367	99.39 217	85.68 395	97.68 398	93.27 409	92.87 379	96.85 366	99.39 277	82.33 391	97.48 390	76.78 403	97.80 255	99.58 154

TDRefinement		95.42 339	94.57 346	97.97 313	89.83 409	96.11 332	99.48 179	98.75 355	96.74 282	96.68 367	99.88 39	88.65 355	99.71 224	98.37 179	82.74 398	98.09 365

baseline2		97.87 240	97.55 251	98.82 229	99.18 269	98.02 241	99.41 210	96.58 400	96.97 268	96.51 368	99.17 320	93.43 270	99.57 259	97.71 239	99.03 185	98.86 257

pmmvs3		94.09 352	93.25 358	96.60 358	94.76 403	94.49 363	98.92 343	98.18 381	89.66 389	96.48 369	98.06 384	86.28 370	97.33 391	89.68 386	87.20 392	97.97 375

DeepMVS_CX				93.34 371	99.29 243	82.27 400		99.22 295	85.15 397	96.33 370	99.05 333	90.97 330	99.73 214	93.57 363	97.77 257	98.01 370

LCM-MVSNet-Re		97.83 248	98.15 185	96.87 354	99.30 239	92.25 384	99.59 102	98.26 376	97.43 225	96.20 371	99.13 325	96.27 165	98.73 367	98.17 195	98.99 188	99.64 136

test20.03		96.12 330	95.96 329	96.63 357	97.44 382	95.45 346	99.51 156	99.38 235	96.55 299	96.16 372	99.25 312	93.76 267	96.17 398	87.35 395	94.22 354	98.27 357

K. test v3		97.10 311	96.79 311	98.01 309	98.72 347	96.33 325	99.87 8	97.05 393	97.59 203	96.16 372	99.80 106	88.71 352	99.04 339	96.69 308	96.55 304	98.65 307

UnsupCasMVSNet_eth		96.44 323	96.12 324	97.40 339	98.65 354	95.65 338	99.36 233	99.51 119	97.13 251	96.04 374	98.99 340	88.40 358	98.17 377	96.71 306	90.27 385	98.40 350

test_method		91.10 361	91.36 363	90.31 381	95.85 394	73.72 414	94.89 402	99.25 290	68.39 405	95.82 375	99.02 337	80.50 395	98.95 357	93.64 362	94.89 345	98.25 359

lessismore_v0				97.79 326	98.69 351	95.44 347		94.75 405		95.71 376	99.87 47	88.69 353	99.32 297	95.89 325	94.93 343	98.62 318

test_vis1_rt		95.81 335	95.65 335	96.32 361	99.67 114	91.35 388	99.49 174	96.74 397	98.25 121	95.24 377	98.10 382	74.96 397	99.90 120	99.53 37	98.85 198	97.70 382

dmvs_testset		95.02 342	96.12 324	91.72 377	99.10 290	80.43 405	99.58 110	97.87 385	97.47 218	95.22 378	98.82 354	93.99 257	95.18 402	88.09 392	94.91 344	99.56 160

Patchmatch-RL test		95.84 334	95.81 333	95.95 363	95.61 396	90.57 389	98.24 389	98.39 374	95.10 352	95.20 379	98.67 362	94.78 219	97.77 386	96.28 319	90.02 386	99.51 178

test_fmvs3		92.10 359	91.77 362	93.08 373	96.19 392	86.25 393	99.82 16	98.62 369	96.65 289	95.19 380	96.90 393	55.05 408	95.93 400	96.63 312	90.92 383	97.06 389

ambc				93.06 374	92.68 405	82.36 399	98.47 379	98.73 363		95.09 381	97.41 388	55.55 406	99.10 334	96.42 316	91.32 378	97.71 380

PM-MVS		92.96 357	92.23 361	95.14 365	95.61 396	89.98 391	99.37 229	98.21 379	94.80 359	95.04 382	97.69 386	65.06 401	97.90 384	94.30 353	89.98 387	97.54 386

OpenMVS_ROB	92.34 20	94.38 350	93.70 356	96.41 360	97.38 383	93.17 379	99.06 311	98.75 355	86.58 396	94.84 383	98.26 376	81.53 393	99.32 297	89.01 388	97.87 252	96.76 390

mvsany_test3		93.77 353	93.45 357	94.74 366	95.78 395	88.01 392	99.64 80	98.25 377	98.28 115	94.31 384	97.97 385	68.89 400	98.51 372	97.50 258	90.37 384	97.71 380

EG-PatchMatch MVS		95.97 332	95.69 334	96.81 355	97.78 377	92.79 381	99.16 289	98.93 330	96.16 327	94.08 385	99.22 315	82.72 388	99.47 266	95.67 333	97.50 274	98.17 362

test_f		91.90 360	91.26 364	93.84 369	95.52 399	85.92 394	99.69 57	98.53 373	95.31 347	93.87 386	96.37 396	55.33 407	98.27 375	95.70 330	90.98 382	97.32 388

pmmvs-eth3d		95.34 341	94.73 344	97.15 343	95.53 398	95.94 334	99.35 238	99.10 310	95.13 348	93.55 387	97.54 387	88.15 362	97.91 383	94.58 350	89.69 388	97.61 383

new-patchmatchnet		94.48 349	94.08 350	95.67 364	95.08 401	92.41 383	99.18 287	99.28 285	94.55 364	93.49 388	97.37 390	87.86 365	97.01 394	91.57 379	88.36 389	97.61 383

UnsupCasMVSNet_bld		93.53 354	92.51 360	96.58 359	97.38 383	93.82 370	98.24 389	99.48 160	91.10 387	93.10 389	96.66 394	74.89 398	98.37 373	94.03 359	87.71 391	97.56 385

WB-MVS		93.10 356	94.10 349	90.12 382	95.51 400	81.88 402	99.73 49	99.27 287	95.05 353	93.09 390	98.91 351	94.70 228	91.89 406	76.62 404	94.02 359	96.58 392

SSC-MVS		92.73 358	93.73 353	89.72 383	95.02 402	81.38 403	99.76 37	99.23 293	94.87 357	92.80 391	98.93 347	94.71 227	91.37 407	74.49 406	93.80 361	96.42 393

Gipuma		90.99 362	90.15 367	93.51 370	98.73 345	90.12 390	93.98 403	99.45 200	79.32 401	92.28 392	94.91 398	69.61 399	97.98 382	87.42 394	95.67 326	92.45 401
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
kuosan		90.92 363	90.11 368	93.34 371	98.78 337	85.59 396	98.15 393	93.16 411	89.37 392	92.07 393	98.38 371	81.48 394	95.19 401	62.54 410	97.04 296	99.25 223

CMPMVS	69.68 23	94.13 351	94.90 343	91.84 376	97.24 387	80.01 406	98.52 377	99.48 160	89.01 393	91.99 394	99.67 181	85.67 373	99.13 327	95.44 337	97.03 297	96.39 394
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testf1		90.42 364	90.68 365	89.65 384	97.78 377	73.97 412	99.13 295	98.81 351	89.62 390	91.80 395	98.93 347	62.23 404	98.80 364	86.61 398	91.17 379	96.19 395

APD_test2		90.42 364	90.68 365	89.65 384	97.78 377	73.97 412	99.13 295	98.81 351	89.62 390	91.80 395	98.93 347	62.23 404	98.80 364	86.61 398	91.17 379	96.19 395

PMMVS2		86.87 367	85.37 371	91.35 379	90.21 408	83.80 398	98.89 346	97.45 392	83.13 400	91.67 397	95.03 397	48.49 410	94.70 403	85.86 400	77.62 402	95.54 398

LCM-MVSNet		86.80 368	85.22 372	91.53 378	87.81 410	80.96 404	98.23 391	98.99 324	71.05 403	90.13 398	96.51 395	48.45 411	96.88 395	90.51 382	85.30 394	96.76 390

ET-MVSNet_ETH3D		96.49 322	95.64 336	99.05 187	99.53 167	98.82 185	98.84 351	97.51 391	97.63 201	84.77 399	99.21 318	92.09 306	98.91 359	98.98 93	92.21 376	99.41 203

E-PMN		80.61 372	79.88 374	82.81 389	90.75 407	76.38 410	97.69 397	95.76 402	66.44 407	83.52 400	92.25 402	62.54 403	87.16 409	68.53 408	61.40 406	84.89 407

FPMVS		84.93 369	85.65 370	82.75 390	86.77 411	63.39 416	98.35 383	98.92 333	74.11 402	83.39 401	98.98 342	50.85 409	92.40 405	84.54 401	94.97 341	92.46 400

EMVS		80.02 373	79.22 375	82.43 391	91.19 406	76.40 409	97.55 400	92.49 414	66.36 408	83.01 402	91.27 404	64.63 402	85.79 410	65.82 409	60.65 407	85.08 406

test_vis3_rt		87.04 366	85.81 369	90.73 380	93.99 404	81.96 401	99.76 37	90.23 415	92.81 380	81.35 403	91.56 403	40.06 412	99.07 336	94.27 355	88.23 390	91.15 403

YYNet1		95.36 340	94.51 347	97.92 315	97.89 375	97.10 283	99.10 306	99.23 293	93.26 376	80.77 404	99.04 334	92.81 283	98.02 380	94.30 353	94.18 355	98.64 309

MDA-MVSNet_test_wron		95.45 338	94.60 345	98.01 309	98.16 372	97.21 279	99.11 304	99.24 292	93.49 373	80.73 405	98.98 342	93.02 277	98.18 376	94.22 357	94.45 350	98.64 309

MDA-MVSNet-bldmvs		94.96 344	93.98 351	97.92 315	98.24 371	97.27 274	99.15 292	99.33 261	93.80 369	80.09 406	99.03 335	88.31 359	97.86 385	93.49 364	94.36 352	98.62 318

tmp_tt		82.80 370	81.52 373	86.66 386	66.61 416	68.44 415	92.79 405	97.92 383	68.96 404	80.04 407	99.85 56	85.77 372	96.15 399	97.86 220	43.89 409	95.39 399

MVE	76.82 21	76.91 375	74.31 379	84.70 387	85.38 413	76.05 411	96.88 401	93.17 410	67.39 406	71.28 408	89.01 407	21.66 418	87.69 408	71.74 407	72.29 405	90.35 404
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		77.30 374	74.86 378	84.62 388	75.88 414	77.61 408	97.63 399	93.15 412	88.81 394	64.27 409	89.29 406	36.51 413	83.93 411	75.89 405	52.31 408	92.33 402

PMVS	70.75 22	75.98 376	74.97 377	79.01 392	70.98 415	55.18 417	93.37 404	98.21 379	65.08 409	61.78 410	93.83 400	21.74 417	92.53 404	78.59 402	91.12 381	89.34 405
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test123		39.01 379	42.50 381	28.53 394	39.17 417	20.91 419	98.75 360	19.17 419	19.83 412	38.57 411	66.67 409	33.16 414	15.42 413	37.50 413	29.66 411	49.26 408

testmvs		39.17 378	43.78 380	25.37 395	36.04 418	16.84 420	98.36 382	26.56 417	20.06 411	38.51 412	67.32 408	29.64 415	15.30 414	37.59 412	39.90 410	43.98 409

wuyk23d		40.18 377	41.29 382	36.84 393	86.18 412	49.12 418	79.73 406	22.81 418	27.64 410	25.46 413	28.45 413	21.98 416	48.89 412	55.80 411	23.56 412	12.51 410

EGC-MVSNET		82.80 370	77.86 376	97.62 332	97.91 374	96.12 331	99.33 243	99.28 285	8.40 413	25.05 414	99.27 309	84.11 383	99.33 294	89.20 387	98.22 233	97.42 387

test_blank		0.13 383	0.17 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	1.57 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet_test		0.02 384	0.03 387	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.27 415	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

DCPMVS		0.02 384	0.03 387	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.27 415	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

cdsmvs_eth3d_5k		24.64 380	32.85 383	0.00 396	0.00 419	0.00 421	0.00 407	99.51 119	0.00 414	0.00 415	99.56 224	96.58 153	0.00 415	0.00 414	0.00 413	0.00 411

pcd_1.5k_mvsjas		8.27 382	11.03 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.27 415	99.01 18	0.00 415	0.00 414	0.00 413	0.00 411

sosnet-low-res		0.02 384	0.03 387	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.27 415	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

sosnet		0.02 384	0.03 387	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.27 415	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uncertanet		0.02 384	0.03 387	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.27 415	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

Regformer		0.02 384	0.03 387	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.27 415	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

ab-mvs-re		8.30 381	11.06 384	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	99.58 217	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet		0.02 384	0.03 387	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.27 415	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

WAC-MVS						97.16 280								95.47 336

MSC_two_6792asdad				99.87 11	99.51 175	99.76 37		99.33 261					99.96 30	98.87 108	99.84 82	99.89 20

No_MVS				99.87 11	99.51 175	99.76 37		99.33 261					99.96 30	98.87 108	99.84 82	99.89 20

eth-test2					0.00 419

eth-test					0.00 419

OPU-MVS				99.64 79	99.56 160	99.72 42	99.60 96				99.70 159	99.27 5	99.42 278	98.24 189	99.80 102	99.79 74

save fliter					99.76 65	99.59 71	99.14 294	99.40 224	99.00 43

test_0728_SECOND				99.91 2	99.84 32	99.89 4	99.57 117	99.51 119					99.96 30	98.93 99	99.86 67	99.88 26

GSMVS																99.52 172

sam_mvs1												94.86 214				99.52 172

sam_mvs												94.72 226

MTGPA								99.47 180

test_post1							99.23 278				65.14 411	94.18 252	99.71 224	97.58 248

test_post											65.99 410	94.65 232	99.73 214

patchmatchnet-post											98.70 361	94.79 218	99.74 208

MTMP							99.54 139	98.88 342

gm-plane-assit					98.54 364	92.96 380			94.65 362		99.15 323		99.64 249	97.56 253

test9_res														97.49 259	99.72 123	99.75 88

agg_prior2														97.21 277	99.73 122	99.75 88

test_prior4						99.56 76	98.99 329

test_prior				99.68 69	99.67 114	99.48 91		99.56 71					99.83 171			99.74 92

新几何2							99.01 326

旧先验1					99.74 80	99.59 71		99.54 88			99.69 169	98.47 80			99.68 131	99.73 97

无先验							98.99 329	99.51 119	96.89 275				99.93 87	97.53 256		99.72 103

原ACMM2							98.95 339

testdata2													99.95 59	96.67 309

segment_acmp												98.96 24

testdata1							98.85 350		98.32 113

plane_prior7					99.29 243	97.03 293

plane_prior6					99.27 248	96.98 297						92.71 289

plane_prior5								99.47 180					99.69 235	97.78 228	97.63 261	98.67 297

plane_prior4											99.61 208

plane_prior2							99.39 222		98.97 51

plane_prior1					99.26 250

plane_prior						96.97 298	99.21 284		98.45 98						97.60 264

n2								0.00 420

nn								0.00 420

door-mid								98.05 382

test11								99.35 250

door								97.92 383

HQP5-MVS						96.83 305

BP-MVS														97.19 281

HQP3-MVS								99.39 227							97.58 266

HQP2-MVS												92.47 298

NP-MVS					99.23 256	96.92 301					99.40 273

ACMMP++_ref															97.19 293

ACMMP++															97.43 283

Test By Simon												98.75 55

High-resolution multi-view benchmark