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		97.92 233	97.44 268	99.34 140	99.53 163	98.08 238	99.74 45	99.49 143	99.15 20	100.00 1	99.94 6	79.51 393	99.98 13	99.88 14	99.76 111	99.97 4

fmvsm_s_conf0.1_n_a		99.26 69	99.06 82	99.85 28	99.52 167	99.62 65	99.54 140	99.62 41	98.69 79	99.99 2	99.96 1	94.47 237	99.94 69	99.88 14	99.92 25	99.98 2

fmvsm_s_conf0.1_n		99.29 63	99.10 76	99.86 21	99.70 101	99.65 57	99.53 148	99.62 41	98.74 75	99.99 2	99.95 3	94.53 235	99.94 69	99.89 13	99.96 12	99.97 4

test_vis1_n_1920		98.63 160	98.40 167	99.31 147	99.86 20	97.94 250	99.67 65	99.62 41	99.43 7	99.99 2	99.91 20	87.29 367	100.00 1	99.92 12	99.92 25	99.98 2

test_fmvs1_n		98.41 172	98.14 183	99.21 167	99.82 42	97.71 262	99.74 45	99.49 143	99.32 14	99.99 2	99.95 3	85.32 376	99.97 21	99.82 16	99.84 78	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 67	98.75 55	99.99 4	99.97 1	99.96 12	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 75	98.75 55	99.99 4	99.97 1	99.97 7	99.94 11

fmvsm_s_conf0.5_n_a		99.56 13	99.47 17	99.85 28	99.83 39	99.64 63	99.52 149	99.65 33	99.10 27	99.98 6	99.92 14	97.35 120	99.96 30	99.94 10	99.92 25	99.95 9

fmvsm_s_conf0.5_n		99.51 18	99.40 25	99.85 28	99.84 32	99.65 57	99.51 157	99.67 23	99.13 22	99.98 6	99.92 14	96.60 148	99.96 30	99.95 8	99.96 12	99.95 9

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 52	99.84 32	99.44 94	99.58 110	99.69 18	99.43 7	99.98 6	99.91 20	98.62 70	100.00 1	99.97 1	99.95 16	99.90 17

test_fmvs1		98.88 126	98.79 128	99.16 172	99.69 106	97.61 265	99.55 135	99.49 143	99.32 14	99.98 6	99.91 20	91.41 320	99.96 30	99.82 16	99.92 25	99.90 17

dcpmvs_2		99.23 75	99.58 7	98.16 298	99.83 39	94.68 359	99.76 38	99.52 101	99.07 35	99.98 6	99.88 36	98.56 74	99.93 84	99.67 21	99.98 4	99.87 31

test_cas_vis1_n_1920		99.16 83	99.01 95	99.61 84	99.81 46	98.86 177	99.65 76	99.64 36	99.39 10	99.97 13	99.94 6	93.20 273	99.98 13	99.55 29	99.91 32	99.99 1

mvsany_test1		99.50 20	99.46 20	99.62 83	99.61 141	99.09 139	98.94 340	99.48 155	99.10 27	99.96 14	99.91 20	98.85 39	99.96 30	99.72 18	99.58 138	99.82 54

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 15	99.92 14	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	99.48 155	99.08 33	99.91 16	99.81 89	99.20 7	99.96 30	98.91 101	99.85 70	99.79 74

test_241102_ONE					99.84 32	99.90 2		99.48 155	99.07 35	99.91 16	99.74 141	99.20 7	99.76 200

EI-MVSNet-UG-set		99.58 9	99.57 8	99.64 78	99.78 56	99.14 133	99.60 96	99.45 195	99.01 40	99.90 18	99.83 67	98.98 23	99.93 84	99.59 25	99.95 16	99.86 33

EI-MVSNet-Vis-set		99.58 9	99.56 10	99.64 78	99.78 56	99.15 132	99.61 95	99.45 195	99.01 40	99.89 19	99.82 75	99.01 18	99.92 95	99.56 28	99.95 16	99.85 36

DVP-MVS++		99.59 8	99.50 13	99.88 5	99.51 170	99.88 8	99.87 9	99.51 115	98.99 45	99.88 20	99.81 89	99.27 5	99.96 30	98.85 114	99.80 98	99.81 61

test_241102_TWO								99.48 155	99.08 33	99.88 20	99.81 89	98.94 29	99.96 30	98.91 101	99.84 78	99.88 26

DPE-MVS		99.46 31	99.32 40	99.91 2	99.78 56	99.88 8	99.36 231	99.51 115	98.73 76	99.88 20	99.84 63	98.72 61	99.96 30	98.16 195	99.87 55	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 47	99.52 11	99.05 184	99.74 80	99.68 48	99.46 188	99.52 101	99.11 26	99.88 20	99.91 20	99.43 1	97.70 387	98.72 132	99.93 23	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 42	99.56 69	99.02 38	99.88 20	99.85 53	99.18 10	99.96 30	99.22 70	99.92 25	99.90 17
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test_fmvsmconf0.1_n		99.55 14	99.45 21	99.86 21	99.44 196	99.65 57	99.50 164	99.61 48	99.45 5	99.87 25	99.92 14	97.31 121	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	99.38 213	99.37 100	99.58 110	99.62 41	99.41 9	99.87 25	99.92 14	98.81 44	100.00 1	99.97 1	99.93 23	99.94 11

test0726					99.85 26	99.89 4	99.62 88	99.50 135	99.10 27	99.86 27	99.82 75	98.94 29

Vis-MVSNet		99.12 95	98.97 101	99.56 94	99.78 56	99.10 138	99.68 62	99.66 28	98.49 97	99.86 27	99.87 44	94.77 218	99.84 155	99.19 72	99.41 149	99.74 92
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PC_three_1452									98.18 134	99.84 29	99.70 156	99.31 3	98.52 370	98.30 186	99.80 98	99.81 61

IU-MVS					99.84 32	99.88 8		99.32 267	98.30 116	99.84 29				98.86 112	99.85 70	99.89 20

xiu_mvs_v1_base_debu		99.29 63	99.27 58	99.34 140	99.63 131	98.97 157	99.12 296	99.51 115	98.86 60	99.84 29	99.47 254	98.18 96	99.99 4	99.50 36	99.31 158	99.08 231

xiu_mvs_v1_base		99.29 63	99.27 58	99.34 140	99.63 131	98.97 157	99.12 296	99.51 115	98.86 60	99.84 29	99.47 254	98.18 96	99.99 4	99.50 36	99.31 158	99.08 231

xiu_mvs_v1_base_debi		99.29 63	99.27 58	99.34 140	99.63 131	98.97 157	99.12 296	99.51 115	98.86 60	99.84 29	99.47 254	98.18 96	99.99 4	99.50 36	99.31 158	99.08 231

DeepPCF-MVS	98.18 3	98.81 141	99.37 30	97.12 345	99.60 146	91.75 385	98.61 370	99.44 203	99.35 12	99.83 34	99.85 53	98.70 63	99.81 180	99.02 87	99.91 32	99.81 61

MVS_0304		99.42 42	99.32 40	99.72 65	99.70 101	99.27 114	99.52 149	97.57 389	99.51 2	99.82 35	99.78 120	98.09 100	99.96 30	99.97 1	99.97 7	99.94 11

TSAR-MVS + GP.		99.36 55	99.36 32	99.36 139	99.67 111	98.61 201	99.07 306	99.33 257	99.00 43	99.82 35	99.81 89	99.06 16	99.84 155	99.09 81	99.42 148	99.65 129

FOURS1					99.91 1	99.93 1	99.87 9	99.56 69	99.10 27	99.81 37

DVP-MVS		99.57 12	99.47 17	99.88 5	99.85 26	99.89 4	99.57 117	99.37 239	99.10 27	99.81 37	99.80 102	98.94 29	99.96 30	98.93 98	99.86 63	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 37	99.80 102	99.09 14	99.96 30	98.85 114	99.90 40	99.88 26

MVSFormer		99.17 81	99.12 74	99.29 155	99.51 170	98.94 167	99.88 4	99.46 184	97.55 209	99.80 40	99.65 184	97.39 116	99.28 300	99.03 85	99.85 70	99.65 129

lupinMVS		99.13 89	99.01 95	99.46 124	99.51 170	98.94 167	99.05 311	99.16 301	97.86 170	99.80 40	99.56 221	97.39 116	99.86 142	98.94 96	99.85 70	99.58 154

tttt0517		98.42 170	98.14 183	99.28 159	99.66 120	98.38 225	99.74 45	96.85 393	97.68 196	99.79 42	99.74 141	91.39 321	99.89 127	98.83 120	99.56 139	99.57 156

APD-MVS_3200maxsize		99.48 26	99.35 34	99.85 28	99.76 65	99.83 16	99.63 83	99.54 85	98.36 110	99.79 42	99.82 75	98.86 38	99.95 59	98.62 145	99.81 94	99.78 80

jason		99.13 89	99.03 87	99.45 125	99.46 190	98.87 174	99.12 296	99.26 285	98.03 159	99.79 42	99.65 184	97.02 134	99.85 148	99.02 87	99.90 40	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	99.51 115	98.62 84	99.79 42	99.83 67	99.28 4	99.97 21	98.48 167	99.90 40	99.84 40
Skip Steuart: Steuart Systems R&D Blog.
DeepC-MVS_fast	98.69 1	99.49 22	99.39 27	99.77 55	99.63 131	99.59 70	99.36 231	99.46 184	99.07 35	99.79 42	99.82 75	98.85 39	99.92 95	98.68 139	99.87 55	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 76	99.03 87	99.79 49	98.42 365	99.48 89	99.55 135	99.51 115	99.39 10	99.78 47	99.93 9	94.80 213	99.95 59	99.93 11	99.95 16	99.94 11

CS-MVS		99.50 20	99.48 15	99.54 97	99.76 65	99.42 96	99.90 1	99.55 77	98.56 89	99.78 47	99.70 156	98.65 68	99.79 189	99.65 23	99.78 105	99.41 197

SMA-MVS		99.44 37	99.30 49	99.85 28	99.73 87	99.83 16	99.56 123	99.47 175	97.45 222	99.78 47	99.82 75	99.18 10	99.91 105	98.79 125	99.89 49	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 83	99.39 223	98.91 58	99.78 47	99.85 53	99.36 2	99.94 69	98.84 117	99.88 52	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		96.81 316	96.65 312	97.29 341	99.74 80	92.21 384	99.60 96	85.06 413	99.13 22	99.77 51	99.93 9	87.82 365	99.85 148	99.38 48	99.38 150	99.80 70

test_part2					99.81 46	99.83 16				99.77 51

MSP-MVS		99.42 42	99.27 58	99.88 5	99.89 8	99.80 27	99.67 65	99.50 135	98.70 78	99.77 51	99.49 246	98.21 94	99.95 59	98.46 171	99.77 108	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 42	99.29 53	99.80 46	99.62 137	99.55 77	99.50 164	99.70 15	98.79 70	99.77 51	99.96 1	97.45 115	99.96 30	98.92 100	99.90 40	99.89 20

APD-MVS		99.27 67	99.08 80	99.84 39	99.75 73	99.79 30	99.50 164	99.50 135	97.16 249	99.77 51	99.82 75	98.78 48	99.94 69	97.56 252	99.86 63	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 33	99.31 47	99.85 28	99.76 65	99.82 22	99.63 83	99.52 101	98.38 106	99.76 56	99.82 75	98.53 76	99.95 59	98.61 148	99.81 94	99.77 82

RE-MVS-def			99.34 36		99.76 65	99.82 22	99.63 83	99.52 101	98.38 106	99.76 56	99.82 75	98.75 55		98.61 148	99.81 94	99.77 82

ACMMP_NAP		99.47 29	99.34 36	99.88 5	99.87 15	99.86 13	99.47 185	99.48 155	98.05 156	99.76 56	99.86 48	98.82 43	99.93 84	98.82 124	99.91 32	99.84 40

HPM-MVS_fast		99.51 18	99.40 25	99.85 28	99.91 1	99.79 30	99.76 38	99.56 69	97.72 190	99.76 56	99.75 136	99.13 12	99.92 95	99.07 83	99.92 25	99.85 36

MM		99.40 50	99.28 55	99.74 61	99.67 111	99.31 108	99.52 149	98.87 342	99.55 1	99.74 60	99.80 102	96.47 153	99.98 13	99.97 1	99.97 7	99.94 11

VNet		99.11 99	98.90 110	99.73 64	99.52 167	99.56 75	99.41 208	99.39 223	99.01 40	99.74 60	99.78 120	95.56 186	99.92 95	99.52 34	98.18 234	99.72 103

patch_mono-2		99.26 69	99.62 5	98.16 298	99.81 46	94.59 361	99.52 149	99.64 36	99.33 13	99.73 62	99.90 26	99.00 22	99.99 4	99.69 19	99.98 4	99.89 20

SR-MVS		99.43 40	99.29 53	99.86 21	99.75 73	99.83 16	99.59 102	99.62 41	98.21 128	99.73 62	99.79 114	98.68 64	99.96 30	98.44 173	99.77 108	99.79 74

thisisatest0530		98.35 178	98.03 198	99.31 147	99.63 131	98.56 204	99.54 140	96.75 395	97.53 213	99.73 62	99.65 184	91.25 324	99.89 127	98.62 145	99.56 139	99.48 178

CS-MVS-test		99.49 22	99.48 15	99.54 97	99.78 56	99.30 110	99.89 2	99.58 61	98.56 89	99.73 62	99.69 166	98.55 75	99.82 175	99.69 19	99.85 70	99.48 178

EC-MVSNet		99.44 37	99.39 27	99.58 90	99.56 156	99.49 87	99.88 4	99.58 61	98.38 106	99.73 62	99.69 166	98.20 95	99.70 227	99.64 24	99.82 91	99.54 161

diffmvs		99.14 87	99.02 91	99.51 113	99.61 141	98.96 161	99.28 257	99.49 143	98.46 99	99.72 67	99.71 152	96.50 152	99.88 133	99.31 58	99.11 172	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 53	99.24 63	99.79 49	99.79 54	99.68 48	99.57 117	99.54 85	97.82 180	99.71 68	99.80 102	98.95 27	99.93 84	98.19 191	99.84 78	99.74 92

xiu_mvs_v2_base		99.26 69	99.25 62	99.29 155	99.53 163	98.91 171	99.02 319	99.45 195	98.80 69	99.71 68	99.26 309	98.94 29	99.98 13	99.34 55	99.23 162	98.98 245

PS-MVSNAJ		99.32 59	99.32 40	99.30 152	99.57 152	98.94 167	98.97 333	99.46 184	98.92 57	99.71 68	99.24 311	99.01 18	99.98 13	99.35 51	99.66 129	98.97 246

PGM-MVS		99.45 33	99.31 47	99.86 21	99.87 15	99.78 36	99.58 110	99.65 33	97.84 175	99.71 68	99.80 102	99.12 13	99.97 21	98.33 182	99.87 55	99.83 49

114514_t		98.93 122	98.67 138	99.72 65	99.85 26	99.53 82	99.62 88	99.59 57	92.65 379	99.71 68	99.78 120	98.06 102	99.90 116	98.84 117	99.91 32	99.74 92

PVSNet_Blended_VisFu		99.36 55	99.28 55	99.61 84	99.86 20	99.07 145	99.47 185	99.93 2	97.66 199	99.71 68	99.86 48	97.73 110	99.96 30	99.47 43	99.82 91	99.79 74

MTAPA		99.52 17	99.39 27	99.89 4	99.90 4	99.86 13	99.66 70	99.47 175	98.79 70	99.68 74	99.81 89	98.43 83	99.97 21	98.88 104	99.90 40	99.83 49

HFP-MVS		99.49 22	99.37 30	99.86 21	99.87 15	99.80 27	99.66 70	99.67 23	98.15 136	99.68 74	99.69 166	99.06 16	99.96 30	98.69 137	99.87 55	99.84 40

VDDNet		97.55 284	97.02 303	99.16 172	99.49 181	98.12 237	99.38 225	99.30 275	95.35 345	99.68 74	99.90 26	82.62 388	99.93 84	99.31 58	98.13 238	99.42 195

HPM-MVS		99.42 42	99.28 55	99.83 40	99.90 4	99.72 42	99.81 21	99.54 85	97.59 203	99.68 74	99.63 196	98.91 34	99.94 69	98.58 154	99.91 32	99.84 40
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
VDD-MVS		97.73 264	97.35 280	98.88 213	99.47 189	97.12 281	99.34 239	98.85 344	98.19 131	99.67 78	99.85 53	82.98 386	99.92 95	99.49 40	98.32 225	99.60 146

ACMMPR		99.49 22	99.36 32	99.86 21	99.87 15	99.79 30	99.66 70	99.67 23	98.15 136	99.67 78	99.69 166	98.95 27	99.96 30	98.69 137	99.87 55	99.84 40

PVSNet_BlendedMVS		98.86 130	98.80 125	99.03 186	99.76 65	98.79 186	99.28 257	99.91 3	97.42 227	99.67 78	99.37 280	97.53 113	99.88 133	98.98 92	97.29 286	98.42 344

PVSNet_Blended		99.08 105	98.97 101	99.42 130	99.76 65	98.79 186	98.78 356	99.91 3	96.74 282	99.67 78	99.49 246	97.53 113	99.88 133	98.98 92	99.85 70	99.60 146

sss		99.17 81	99.05 83	99.53 105	99.62 137	98.97 157	99.36 231	99.62 41	97.83 176	99.67 78	99.65 184	97.37 119	99.95 59	99.19 72	99.19 165	99.68 119

ECVR-MVS		98.04 213	98.05 196	98.00 310	99.74 80	94.37 364	99.59 102	94.98 403	99.13 22	99.66 83	99.93 9	90.67 330	99.84 155	99.40 47	99.38 150	99.80 70

h-mvs33		97.70 270	97.28 291	98.97 194	99.70 101	97.27 273	99.36 231	99.45 195	98.94 54	99.66 83	99.64 190	94.93 205	99.99 4	99.48 41	84.36 392	99.65 129

hse-mvs2		97.50 289	97.14 297	98.59 249	99.49 181	97.05 288	99.28 257	99.22 292	98.94 54	99.66 83	99.42 265	94.93 205	99.65 243	99.48 41	83.80 394	99.08 231

region2R		99.48 26	99.35 34	99.87 11	99.88 11	99.80 27	99.65 76	99.66 28	98.13 140	99.66 83	99.68 172	98.96 24	99.96 30	98.62 145	99.87 55	99.84 40

RPSCF		98.22 188	98.62 149	96.99 347	99.82 42	91.58 386	99.72 50	99.44 203	96.61 294	99.66 83	99.89 30	95.92 173	99.82 175	97.46 262	99.10 175	99.57 156

OMC-MVS		99.08 105	99.04 85	99.20 168	99.67 111	98.22 231	99.28 257	99.52 101	98.07 151	99.66 83	99.81 89	97.79 108	99.78 194	97.79 226	99.81 94	99.60 146

test1111		98.04 213	98.11 187	97.83 321	99.74 80	93.82 369	99.58 110	95.40 402	99.12 25	99.65 89	99.93 9	90.73 329	99.84 155	99.43 46	99.38 150	99.82 54

test_one_0601					99.81 46	99.88 8		99.49 143	98.97 51	99.65 89	99.81 89	99.09 14

LFMVS		97.90 236	97.35 280	99.54 97	99.52 167	99.01 152	99.39 220	98.24 376	97.10 257	99.65 89	99.79 114	84.79 379	99.91 105	99.28 63	98.38 218	99.69 115

MVS_111021_LR		99.41 47	99.33 38	99.65 73	99.77 62	99.51 86	98.94 340	99.85 6	98.82 65	99.65 89	99.74 141	98.51 78	99.80 186	98.83 120	99.89 49	99.64 136

SDMVSNet		99.11 99	98.90 110	99.75 58	99.81 46	99.59 70	99.81 21	99.65 33	98.78 73	99.64 93	99.88 36	94.56 231	99.93 84	99.67 21	98.26 227	99.72 103

sd_testset		98.75 148	98.57 156	99.29 155	99.81 46	98.26 229	99.56 123	99.62 41	98.78 73	99.64 93	99.88 36	92.02 304	99.88 133	99.54 30	98.26 227	99.72 103

9.14			99.10 76		99.72 91		99.40 216	99.51 115	97.53 213	99.64 93	99.78 120	98.84 41	99.91 105	97.63 243	99.82 91

iter_conf05_11		98.35 178	97.99 202	99.41 131	99.37 216	99.13 136	98.96 334	98.23 377	98.50 96	99.63 96	99.46 258	88.83 349	99.87 138	99.00 89	99.95 16	99.23 218

GST-MVS		99.40 50	99.24 63	99.85 28	99.86 20	99.79 30	99.60 96	99.67 23	97.97 162	99.63 96	99.68 172	98.52 77	99.95 59	98.38 176	99.86 63	99.81 61

CPTT-MVS		99.11 99	98.90 110	99.74 61	99.80 52	99.46 92	99.59 102	99.49 143	97.03 265	99.63 96	99.69 166	97.27 124	99.96 30	97.82 224	99.84 78	99.81 61

ACMMP		99.45 33	99.32 40	99.82 41	99.89 8	99.67 51	99.62 88	99.69 18	98.12 141	99.63 96	99.84 63	98.73 60	99.96 30	98.55 163	99.83 87	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 61	99.19 68	99.64 78	99.82 42	99.23 120	99.62 88	99.55 77	98.94 54	99.63 96	99.95 3	95.82 178	99.94 69	99.37 50	99.97 7	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		98.48 165	98.17 179	99.40 133	99.54 162	98.96 161	99.68 62	98.81 349	95.54 343	99.62 101	99.70 156	93.82 260	99.93 84	97.35 270	99.46 145	99.32 211

CHOSEN 280x420		99.12 95	99.13 73	99.08 179	99.66 120	97.89 251	98.43 380	99.71 13	98.88 59	99.62 101	99.76 133	96.63 147	99.70 227	99.46 44	99.99 1	99.66 125

PHI-MVS		99.30 61	99.17 70	99.70 67	99.56 156	99.52 85	99.58 110	99.80 8	97.12 253	99.62 101	99.73 147	98.58 72	99.90 116	98.61 148	99.91 32	99.68 119

test_yl		98.86 130	98.63 144	99.54 97	99.49 181	99.18 124	99.50 164	99.07 313	98.22 126	99.61 104	99.51 239	95.37 192	99.84 155	98.60 151	98.33 221	99.59 150

DCV-MVSNet		98.86 130	98.63 144	99.54 97	99.49 181	99.18 124	99.50 164	99.07 313	98.22 126	99.61 104	99.51 239	95.37 192	99.84 155	98.60 151	98.33 221	99.59 150

MG-MVS		99.13 89	99.02 91	99.45 125	99.57 152	98.63 198	99.07 306	99.34 250	98.99 45	99.61 104	99.82 75	97.98 104	99.87 138	97.00 289	99.80 98	99.85 36

MP-MVS-pluss		99.37 54	99.20 67	99.88 5	99.90 4	99.87 12	99.30 247	99.52 101	97.18 247	99.60 107	99.79 114	98.79 47	99.95 59	98.83 120	99.91 32	99.83 49
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
CDPH-MVS		99.13 89	98.91 109	99.80 46	99.75 73	99.71 44	99.15 290	99.41 214	96.60 296	99.60 107	99.55 224	98.83 42	99.90 116	97.48 259	99.83 87	99.78 80

EPP-MVSNet		99.13 89	98.99 97	99.53 105	99.65 126	99.06 146	99.81 21	99.33 257	97.43 225	99.60 107	99.88 36	97.14 126	99.84 155	99.13 77	98.94 186	99.69 115

HyFIR lowres test		99.11 99	98.92 107	99.65 73	99.90 4	99.37 100	99.02 319	99.91 3	97.67 198	99.59 110	99.75 136	95.90 175	99.73 211	99.53 32	99.02 183	99.86 33

FA-MVS(test-final)		98.75 148	98.53 160	99.41 131	99.55 160	99.05 148	99.80 26	99.01 319	96.59 298	99.58 111	99.59 210	95.39 191	99.90 116	97.78 227	99.49 144	99.28 214

MVS_Test		99.10 103	98.97 101	99.48 119	99.49 181	99.14 133	99.67 65	99.34 250	97.31 236	99.58 111	99.76 133	97.65 112	99.82 175	98.87 107	99.07 178	99.46 188

MDTV_nov1_ep13_2view						95.18 352	99.35 236		96.84 278	99.58 111		95.19 201		97.82 224		99.46 188

DELS-MVS		99.48 26	99.42 22	99.65 73	99.72 91	99.40 99	99.05 311	99.66 28	99.14 21	99.57 114	99.80 102	98.46 81	99.94 69	99.57 27	99.84 78	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 96	99.79 30		99.61 48	96.84 278	99.56 115	99.54 229	98.58 72	99.96 30	96.93 296	99.75 113

CR-MVSNet		98.17 195	97.93 211	98.87 217	99.18 266	98.49 215	99.22 280	99.33 257	96.96 269	99.56 115	99.38 277	94.33 241	99.00 345	94.83 348	98.58 208	99.14 223

RPMNet		96.72 317	95.90 329	99.19 169	99.18 266	98.49 215	99.22 280	99.52 101	88.72 392	99.56 115	97.38 386	94.08 251	99.95 59	86.87 396	98.58 208	99.14 223

IS-MVSNet		99.05 108	98.87 115	99.57 92	99.73 87	99.32 104	99.75 42	99.20 296	98.02 160	99.56 115	99.86 48	96.54 151	99.67 235	98.09 198	99.13 171	99.73 97

ZNCC-MVS		99.47 29	99.33 38	99.87 11	99.87 15	99.81 25	99.64 79	99.67 23	98.08 150	99.55 119	99.64 190	98.91 34	99.96 30	98.72 132	99.90 40	99.82 54

thisisatest0515		98.14 198	97.79 223	99.19 169	99.50 179	98.50 214	98.61 370	96.82 394	96.95 271	99.54 120	99.43 263	91.66 316	99.86 142	98.08 202	99.51 143	99.22 220

MVS_111021_HR		99.41 47	99.32 40	99.66 69	99.72 91	99.47 91	98.95 338	99.85 6	98.82 65	99.54 120	99.73 147	98.51 78	99.74 205	98.91 101	99.88 52	99.77 82

CP-MVS		99.45 33	99.32 40	99.85 28	99.83 39	99.75 39	99.69 56	99.52 101	98.07 151	99.53 122	99.63 196	98.93 33	99.97 21	98.74 129	99.91 32	99.83 49

WTY-MVS		99.06 107	98.88 114	99.61 84	99.62 137	99.16 127	99.37 227	99.56 69	98.04 157	99.53 122	99.62 201	96.84 140	99.94 69	98.85 114	98.49 216	99.72 103

MCST-MVS		99.43 40	99.30 49	99.82 41	99.79 54	99.74 41	99.29 252	99.40 220	98.79 70	99.52 124	99.62 201	98.91 34	99.90 116	98.64 143	99.75 113	99.82 54

PatchT		97.03 312	96.44 317	98.79 234	98.99 308	98.34 226	99.16 287	99.07 313	92.13 380	99.52 124	97.31 389	94.54 234	98.98 347	88.54 389	98.73 202	99.03 239

CANet		99.25 73	99.14 72	99.59 87	99.41 204	99.16 127	99.35 236	99.57 64	98.82 65	99.51 126	99.61 205	96.46 154	99.95 59	99.59 25	99.98 4	99.65 129

mPP-MVS		99.44 37	99.30 49	99.86 21	99.88 11	99.79 30	99.69 56	99.48 155	98.12 141	99.50 127	99.75 136	98.78 48	99.97 21	98.57 157	99.89 49	99.83 49

PatchMatch-RL		98.84 140	98.62 149	99.52 111	99.71 96	99.28 112	99.06 309	99.77 9	97.74 189	99.50 127	99.53 233	95.41 190	99.84 155	97.17 283	99.64 132	99.44 193

PVSNet	96.02 17	98.85 137	98.84 122	98.89 211	99.73 87	97.28 272	98.32 386	99.60 54	97.86 170	99.50 127	99.57 218	96.75 144	99.86 142	98.56 160	99.70 123	99.54 161

LS3D		99.27 67	99.12 74	99.74 61	99.18 266	99.75 39	99.56 123	99.57 64	98.45 100	99.49 130	99.85 53	97.77 109	99.94 69	98.33 182	99.84 78	99.52 167

MP-MVS		99.33 58	99.15 71	99.87 11	99.88 11	99.82 22	99.66 70	99.46 184	98.09 146	99.48 131	99.74 141	98.29 91	99.96 30	97.93 213	99.87 55	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							98.96 334		96.70 285	99.47 132			99.94 69	98.19 191

MSDG		98.98 118	98.80 125	99.53 105	99.76 65	99.19 122	98.75 359	99.55 77	97.25 241	99.47 132	99.77 128	97.82 107	99.87 138	96.93 296	99.90 40	99.54 161

CDS-MVSNet		99.09 104	99.03 87	99.25 162	99.42 199	98.73 190	99.45 189	99.46 184	98.11 143	99.46 134	99.77 128	98.01 103	99.37 282	98.70 134	98.92 189	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 31	99.47 17	99.44 129	99.60 146	99.16 127	99.41 208	99.71 13	98.98 48	99.45 135	99.78 120	99.19 9	99.54 260	99.28 63	99.84 78	99.63 140

XVG-OURS		98.73 151	98.68 137	98.88 213	99.70 101	97.73 258	98.92 342	99.55 77	98.52 94	99.45 135	99.84 63	95.27 196	99.91 105	98.08 202	98.84 195	99.00 242

casdiffmvs_mvg		99.15 85	99.02 91	99.55 96	99.66 120	99.09 139	99.64 79	99.56 69	98.26 120	99.45 135	99.87 44	96.03 167	99.81 180	99.54 30	99.15 169	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		98.33 180	98.48 162	97.90 316	99.16 276	94.78 357	99.31 245	99.11 306	97.27 239	99.45 135	99.59 210	95.33 194	99.84 155	98.48 167	98.61 205	99.09 230

TAMVS		99.12 95	99.08 80	99.24 164	99.46 190	98.55 205	99.51 157	99.46 184	98.09 146	99.45 135	99.82 75	98.34 89	99.51 261	98.70 134	98.93 187	99.67 122

ETV-MVS		99.26 69	99.21 66	99.40 133	99.46 190	99.30 110	99.56 123	99.52 101	98.52 94	99.44 140	99.27 307	98.41 86	99.86 142	99.10 80	99.59 137	99.04 238

CANet_DTU		98.97 120	98.87 115	99.25 162	99.33 228	98.42 224	99.08 305	99.30 275	99.16 19	99.43 141	99.75 136	95.27 196	99.97 21	98.56 160	99.95 16	99.36 205

SCA		98.19 192	98.16 180	98.27 293	99.30 236	95.55 340	99.07 306	98.97 323	97.57 206	99.43 141	99.57 218	92.72 284	99.74 205	97.58 247	99.20 164	99.52 167

testdata				99.54 97	99.75 73	98.95 164		99.51 115	97.07 259	99.43 141	99.70 156	98.87 37	99.94 69	97.76 231	99.64 132	99.72 103

DPM-MVS		98.95 121	98.71 134	99.66 69	99.63 131	99.55 77	98.64 369	99.10 307	97.93 165	99.42 144	99.55 224	98.67 66	99.80 186	95.80 327	99.68 127	99.61 144

XVG-OURS-SEG-HR		98.69 154	98.62 149	98.89 211	99.71 96	97.74 257	99.12 296	99.54 85	98.44 103	99.42 144	99.71 152	94.20 245	99.92 95	98.54 164	98.90 191	99.00 242

baseline		99.15 85	99.02 91	99.53 105	99.66 120	99.14 133	99.72 50	99.48 155	98.35 111	99.42 144	99.84 63	96.07 165	99.79 189	99.51 35	99.14 170	99.67 122

DP-MVS Recon		99.12 95	98.95 105	99.65 73	99.74 80	99.70 46	99.27 262	99.57 64	96.40 312	99.42 144	99.68 172	98.75 55	99.80 186	97.98 210	99.72 119	99.44 193

Effi-MVS+-dtu		98.78 145	98.89 113	98.47 269	99.33 228	96.91 301	99.57 117	99.30 275	98.47 98	99.41 148	98.99 338	96.78 142	99.74 205	98.73 131	99.38 150	98.74 268

casdiffmvs		99.13 89	98.98 100	99.56 94	99.65 126	99.16 127	99.56 123	99.50 135	98.33 114	99.41 148	99.86 48	95.92 173	99.83 168	99.45 45	99.16 166	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		97.73 264	97.45 263	98.57 253	99.45 195	97.50 267	99.02 319	98.98 322	96.11 332	99.41 148	99.14 322	90.28 332	98.74 365	95.74 328	98.93 187	99.47 184

CSCG		99.32 59	99.32 40	99.32 146	99.85 26	98.29 227	99.71 52	99.66 28	98.11 143	99.41 148	99.80 102	98.37 88	99.96 30	98.99 91	99.96 12	99.72 103

F-COLMAP		99.19 77	99.04 85	99.64 78	99.78 56	99.27 114	99.42 206	99.54 85	97.29 238	99.41 148	99.59 210	98.42 85	99.93 84	98.19 191	99.69 124	99.73 97

bld_raw_dy_0_64		98.26 187	97.88 218	99.40 133	99.37 216	99.09 139	99.62 88	98.94 326	98.53 92	99.40 153	99.51 239	88.93 347	99.89 127	99.00 89	97.64 256	99.23 218

EIA-MVS		99.18 79	99.09 79	99.45 125	99.49 181	99.18 124	99.67 65	99.53 96	97.66 199	99.40 153	99.44 261	98.10 99	99.81 180	98.94 96	99.62 135	99.35 206

mvsmamba		98.92 123	98.87 115	99.08 179	99.07 294	99.16 127	99.88 4	99.51 115	98.15 136	99.40 153	99.89 30	97.12 127	99.33 292	99.38 48	97.40 282	98.73 270

MDTV_nov1_ep13			98.32 172		99.11 284	94.44 363	99.27 262	98.74 356	97.51 216	99.40 153	99.62 201	94.78 215	99.76 200	97.59 246	98.81 199

CVMVSNet		98.57 162	98.67 138	98.30 288	99.35 222	95.59 339	99.50 164	99.55 77	98.60 86	99.39 157	99.83 67	94.48 236	99.45 265	98.75 128	98.56 211	99.85 36

CNVR-MVS		99.42 42	99.30 49	99.78 52	99.62 137	99.71 44	99.26 271	99.52 101	98.82 65	99.39 157	99.71 152	98.96 24	99.85 148	98.59 153	99.80 98	99.77 82

Effi-MVS+		98.81 141	98.59 155	99.48 119	99.46 190	99.12 137	98.08 392	99.50 135	97.50 217	99.38 159	99.41 269	96.37 158	99.81 180	99.11 79	98.54 213	99.51 173

mvs_anonymous		99.03 111	98.99 97	99.16 172	99.38 213	98.52 211	99.51 157	99.38 231	97.79 181	99.38 159	99.81 89	97.30 122	99.45 265	99.35 51	98.99 184	99.51 173

iter_conf05		98.55 163	98.44 163	98.87 217	99.34 226	98.60 202	99.55 135	99.42 211	98.21 128	99.37 161	99.77 128	93.55 266	99.38 278	99.30 61	97.48 274	98.63 312

XVS		99.53 16	99.42 22	99.87 11	99.85 26	99.83 16	99.69 56	99.68 20	98.98 48	99.37 161	99.74 141	98.81 44	99.94 69	98.79 125	99.86 63	99.84 40

X-MVStestdata		96.55 319	95.45 337	99.87 11	99.85 26	99.83 16	99.69 56	99.68 20	98.98 48	99.37 161	64.01 409	98.81 44	99.94 69	98.79 125	99.86 63	99.84 40

PatchmatchNet		98.31 181	98.36 168	98.19 296	99.16 276	95.32 348	99.27 262	98.92 331	97.37 231	99.37 161	99.58 214	94.90 208	99.70 227	97.43 265	99.21 163	99.54 161
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
AllTest		98.87 127	98.72 132	99.31 147	99.86 20	98.48 217	99.56 123	99.61 48	97.85 173	99.36 165	99.85 53	95.95 170	99.85 148	96.66 309	99.83 87	99.59 150

TestCases				99.31 147	99.86 20	98.48 217		99.61 48	97.85 173	99.36 165	99.85 53	95.95 170	99.85 148	96.66 309	99.83 87	99.59 150

Vis-MVSNet (Re-imp)		98.87 127	98.72 132	99.31 147	99.71 96	98.88 173	99.80 26	99.44 203	97.91 167	99.36 165	99.78 120	95.49 189	99.43 274	97.91 214	99.11 172	99.62 142

alignmvs		98.81 141	98.56 158	99.58 90	99.43 197	99.42 96	99.51 157	98.96 325	98.61 85	99.35 168	98.92 348	94.78 215	99.77 196	99.35 51	98.11 239	99.54 161

VPA-MVSNet		98.29 184	97.95 208	99.30 152	99.16 276	99.54 79	99.50 164	99.58 61	98.27 119	99.35 168	99.37 280	92.53 293	99.65 243	99.35 51	94.46 346	98.72 271

AdaColmap		99.01 116	98.80 125	99.66 69	99.56 156	99.54 79	99.18 285	99.70 15	98.18 134	99.35 168	99.63 196	96.32 159	99.90 116	97.48 259	99.77 108	99.55 159

test222					99.75 73	99.49 87	98.91 344	99.49 143	96.42 310	99.34 171	99.65 184	98.28 92			99.69 124	99.72 103

API-MVS		99.04 109	99.03 87	99.06 182	99.40 209	99.31 108	99.55 135	99.56 69	98.54 91	99.33 172	99.39 276	98.76 52	99.78 194	96.98 291	99.78 105	98.07 363

v144192		97.92 233	97.60 248	98.87 217	98.83 330	98.65 196	99.55 135	99.34 250	96.20 323	99.32 173	99.40 272	94.36 240	99.26 304	96.37 317	95.03 337	98.70 277

sasdasda		99.02 112	98.86 118	99.51 113	99.42 199	99.32 104	99.80 26	99.48 155	98.63 82	99.31 174	98.81 353	97.09 129	99.75 203	99.27 66	97.90 245	99.47 184

GeoE		98.85 137	98.62 149	99.53 105	99.61 141	99.08 143	99.80 26	99.51 115	97.10 257	99.31 174	99.78 120	95.23 200	99.77 196	98.21 189	99.03 181	99.75 88

canonicalmvs		99.02 112	98.86 118	99.51 113	99.42 199	99.32 104	99.80 26	99.48 155	98.63 82	99.31 174	98.81 353	97.09 129	99.75 203	99.27 66	97.90 245	99.47 184

V42		98.06 207	97.79 223	98.86 221	98.98 311	98.84 179	99.69 56	99.34 250	96.53 300	99.30 177	99.37 280	94.67 226	99.32 295	97.57 251	94.66 343	98.42 344

ab-mvs		98.86 130	98.63 144	99.54 97	99.64 128	99.19 122	99.44 195	99.54 85	97.77 184	99.30 177	99.81 89	94.20 245	99.93 84	99.17 75	98.82 197	99.49 177

TAPA-MVS	97.07 15	97.74 263	97.34 283	98.94 198	99.70 101	97.53 266	99.25 273	99.51 115	91.90 381	99.30 177	99.63 196	98.78 48	99.64 246	88.09 391	99.87 55	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 70		99.54 85	96.76 281	99.29 180	99.64 190	98.43 83	99.94 69	96.92 298	99.66 129	99.72 103

MGCFI-Net		99.01 116	98.85 120	99.50 118	99.42 199	99.26 116	99.82 17	99.48 155	98.60 86	99.28 181	98.81 353	97.04 133	99.76 200	99.29 62	97.87 248	99.47 184

test_fmvs2		97.25 304	97.30 288	97.09 346	99.43 197	93.31 377	99.73 48	98.87 342	98.83 64	99.28 181	99.80 102	84.45 381	99.66 238	97.88 216	97.45 276	98.30 352

VPNet		97.84 245	97.44 268	99.01 188	99.21 258	98.94 167	99.48 179	99.57 64	98.38 106	99.28 181	99.73 147	88.89 348	99.39 277	99.19 72	93.27 364	98.71 273

HY-MVS	97.30 7	98.85 137	98.64 143	99.47 122	99.42 199	99.08 143	99.62 88	99.36 240	97.39 230	99.28 181	99.68 172	96.44 156	99.92 95	98.37 178	98.22 229	99.40 199

PAPM_NR		99.04 109	98.84 122	99.66 69	99.74 80	99.44 94	99.39 220	99.38 231	97.70 194	99.28 181	99.28 304	98.34 89	99.85 148	96.96 293	99.45 146	99.69 115

HPM-MVS++		99.39 52	99.23 65	99.87 11	99.75 73	99.84 15	99.43 199	99.51 115	98.68 81	99.27 186	99.53 233	98.64 69	99.96 30	98.44 173	99.80 98	99.79 74

v1240		97.69 271	97.32 286	98.79 234	98.85 328	98.43 222	99.48 179	99.36 240	96.11 332	99.27 186	99.36 283	93.76 263	99.24 308	94.46 351	95.23 332	98.70 277

thres600view7		97.86 241	97.51 256	98.92 202	99.72 91	97.95 248	99.59 102	98.74 356	97.94 164	99.27 186	98.62 361	91.75 310	99.86 142	93.73 360	98.19 233	98.96 248

PLC	97.94 4	99.02 112	98.85 120	99.53 105	99.66 120	99.01 152	99.24 275	99.52 101	96.85 277	99.27 186	99.48 251	98.25 93	99.91 105	97.76 231	99.62 135	99.65 129
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
thres100view900		97.76 257	97.45 263	98.69 243	99.72 91	97.86 254	99.59 102	98.74 356	97.93 165	99.26 190	98.62 361	91.75 310	99.83 168	93.22 365	98.18 234	98.37 350

EPMVS		97.82 250	97.65 242	98.35 283	98.88 321	95.98 332	99.49 175	94.71 405	97.57 206	99.26 190	99.48 251	92.46 298	99.71 221	97.87 218	99.08 177	99.35 206

Fast-Effi-MVS+-dtu		98.77 147	98.83 124	98.60 248	99.41 204	96.99 295	99.52 149	99.49 143	98.11 143	99.24 192	99.34 290	96.96 138	99.79 189	97.95 212	99.45 146	99.02 241

v1921920		97.80 254	97.45 263	98.84 225	98.80 331	98.53 207	99.52 149	99.34 250	96.15 329	99.24 192	99.47 254	93.98 254	99.29 299	95.40 338	95.13 335	98.69 281

LPG-MVS_test		98.22 188	98.13 185	98.49 262	99.33 228	97.05 288	99.58 110	99.55 77	97.46 219	99.24 192	99.83 67	92.58 291	99.72 215	98.09 198	97.51 268	98.68 286

LGP-MVS_train				98.49 262	99.33 228	97.05 288		99.55 77	97.46 219	99.24 192	99.83 67	92.58 291	99.72 215	98.09 198	97.51 268	98.68 286

v1144		97.98 224	97.69 238	98.85 224	98.87 324	98.66 195	99.54 140	99.35 246	96.27 318	99.23 196	99.35 286	94.67 226	99.23 309	96.73 304	95.16 334	98.68 286

Anonymous20240529		98.09 203	97.68 239	99.34 140	99.66 120	98.44 221	99.40 216	99.43 209	93.67 369	99.22 197	99.89 30	90.23 336	99.93 84	99.26 68	98.33 221	99.66 125

OPM-MVS		98.19 192	98.10 188	98.45 271	98.88 321	97.07 286	99.28 257	99.38 231	98.57 88	99.22 197	99.81 89	92.12 302	99.66 238	98.08 202	97.54 266	98.61 324
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
test_djsdf		98.67 156	98.57 156	98.98 192	98.70 347	98.91 171	99.88 4	99.46 184	97.55 209	99.22 197	99.88 36	95.73 181	99.28 300	99.03 85	97.62 259	98.75 265

test12				99.75 58	99.64 128	99.61 67		99.29 279		99.21 200		98.38 87	99.89 127		99.74 116	99.74 92

NCCC		99.34 57	99.19 68	99.79 49	99.61 141	99.65 57	99.30 247	99.48 155	98.86 60	99.21 200	99.63 196	98.72 61	99.90 116	98.25 187	99.63 134	99.80 70

PMMVS		98.80 144	98.62 149	99.34 140	99.27 245	98.70 192	98.76 358	99.31 271	97.34 233	99.21 200	99.07 328	97.20 125	99.82 175	98.56 160	98.87 192	99.52 167

v1192		97.81 252	97.44 268	98.91 206	98.88 321	98.68 193	99.51 157	99.34 250	96.18 325	99.20 203	99.34 290	94.03 252	99.36 286	95.32 340	95.18 333	98.69 281

EI-MVSNet		98.67 156	98.67 138	98.68 244	99.35 222	97.97 244	99.50 164	99.38 231	96.93 274	99.20 203	99.83 67	97.87 105	99.36 286	98.38 176	97.56 264	98.71 273

MVSTER		98.49 164	98.32 172	99.00 190	99.35 222	99.02 150	99.54 140	99.38 231	97.41 228	99.20 203	99.73 147	93.86 259	99.36 286	98.87 107	97.56 264	98.62 315

UWE-MVS		97.58 283	97.29 290	98.48 264	99.09 290	96.25 327	99.01 324	96.61 398	97.86 170	99.19 206	99.01 336	88.72 350	99.90 116	97.38 268	98.69 203	99.28 214

Anonymous202405211		98.30 183	97.98 204	99.26 161	99.57 152	98.16 233	99.41 208	98.55 369	96.03 337	99.19 206	99.74 141	91.87 307	99.92 95	99.16 76	98.29 226	99.70 113

v2v482		98.06 207	97.77 228	98.92 202	98.90 318	98.82 183	99.57 117	99.36 240	96.65 289	99.19 206	99.35 286	94.20 245	99.25 305	97.72 237	94.97 338	98.69 281

CNLPA		99.14 87	98.99 97	99.59 87	99.58 150	99.41 98	99.16 287	99.44 203	98.45 100	99.19 206	99.49 246	98.08 101	99.89 127	97.73 235	99.75 113	99.48 178

UGNet		98.87 127	98.69 136	99.40 133	99.22 257	98.72 191	99.44 195	99.68 20	99.24 17	99.18 210	99.42 265	92.74 283	99.96 30	99.34 55	99.94 22	99.53 166
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		97.72 266	97.38 276	98.72 239	99.69 106	97.96 246	99.50 164	98.73 361	97.83 176	99.17 211	98.45 366	91.67 314	99.83 168	93.22 365	98.18 234	98.37 350

thres400		97.77 256	97.38 276	98.92 202	99.69 106	97.96 246	99.50 164	98.73 361	97.83 176	99.17 211	98.45 366	91.67 314	99.83 168	93.22 365	98.18 234	98.96 248

Test_1112_low_res		98.89 125	98.66 141	99.57 92	99.69 106	98.95 164	99.03 316	99.47 175	96.98 267	99.15 213	99.23 312	96.77 143	99.89 127	98.83 120	98.78 200	99.86 33

baseline1		98.31 181	97.95 208	99.38 138	99.50 179	98.74 189	99.59 102	98.93 328	98.41 104	99.14 214	99.60 208	94.59 229	99.79 189	98.48 167	93.29 363	99.61 144

1112_ss		98.98 118	98.77 129	99.59 87	99.68 110	99.02 150	99.25 273	99.48 155	97.23 244	99.13 215	99.58 214	96.93 139	99.90 116	98.87 107	98.78 200	99.84 40

CLD-MVS		98.16 196	98.10 188	98.33 284	99.29 240	96.82 306	98.75 359	99.44 203	97.83 176	99.13 215	99.55 224	92.92 277	99.67 235	98.32 184	97.69 254	98.48 336
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 73	99.73 87	99.33 103		99.47 175	97.46 219	99.12 217	99.66 183	98.67 66	99.91 105	97.70 240	99.69 124	99.71 112

tpm		97.67 276	97.55 250	98.03 305	99.02 303	95.01 354	99.43 199	98.54 370	96.44 308	99.12 217	99.34 290	91.83 309	99.60 254	97.75 233	96.46 302	99.48 178

HQP_MVS		98.27 186	98.22 178	98.44 274	99.29 240	96.97 297	99.39 220	99.47 175	98.97 51	99.11 219	99.61 205	92.71 286	99.69 232	97.78 227	97.63 257	98.67 293

plane_prior3						97.00 294			98.69 79	99.11 219

CHOSEN 1792x2688		99.19 77	99.10 76	99.45 125	99.89 8	98.52 211	99.39 220	99.94 1	98.73 76	99.11 219	99.89 30	95.50 188	99.94 69	99.50 36	99.97 7	99.89 20

v8		97.95 229	97.63 246	98.93 200	98.95 315	98.81 185	99.80 26	99.41 214	96.03 337	99.10 222	99.42 265	94.92 207	99.30 298	96.94 295	94.08 354	98.66 301

ADS-MVSNet2		98.02 217	98.07 195	97.87 317	99.33 228	95.19 351	99.23 276	99.08 310	96.24 320	99.10 222	99.67 178	94.11 249	98.93 357	96.81 301	99.05 179	99.48 178

ADS-MVSNet		98.20 191	98.08 192	98.56 256	99.33 228	96.48 319	99.23 276	99.15 302	96.24 320	99.10 222	99.67 178	94.11 249	99.71 221	96.81 301	99.05 179	99.48 178

thres200		97.61 281	97.28 291	98.62 247	99.64 128	98.03 240	99.26 271	98.74 356	97.68 196	99.09 225	98.32 371	91.66 316	99.81 180	92.88 370	98.22 229	98.03 366

dp		97.75 261	97.80 222	97.59 333	99.10 287	93.71 372	99.32 242	98.88 340	96.48 305	99.08 226	99.55 224	92.67 289	99.82 175	96.52 312	98.58 208	99.24 217

WB-MVSnew		97.65 278	97.65 242	97.63 330	98.78 335	97.62 264	99.13 293	98.33 373	97.36 232	99.07 227	98.94 344	95.64 185	99.15 322	92.95 369	98.68 204	96.12 394

GBi-Net		97.68 273	97.48 258	98.29 289	99.51 170	97.26 275	99.43 199	99.48 155	96.49 302	99.07 227	99.32 297	90.26 333	98.98 347	97.10 284	96.65 297	98.62 315

test1		97.68 273	97.48 258	98.29 289	99.51 170	97.26 275	99.43 199	99.48 155	96.49 302	99.07 227	99.32 297	90.26 333	98.98 347	97.10 284	96.65 297	98.62 315

FMVSNet3		98.03 215	97.76 232	98.84 225	99.39 212	98.98 154	99.40 216	99.38 231	96.67 287	99.07 227	99.28 304	92.93 276	98.98 347	97.10 284	96.65 297	98.56 331

IterMVS-LS		98.46 167	98.42 165	98.58 252	99.59 148	98.00 242	99.37 227	99.43 209	96.94 273	99.07 227	99.59 210	97.87 105	99.03 340	98.32 184	95.62 324	98.71 273
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dmvs_re		98.08 205	98.16 180	97.85 318	99.55 160	94.67 360	99.70 53	98.92 331	98.15 136	99.06 232	99.35 286	93.67 265	99.25 305	97.77 230	97.25 287	99.64 136

pmmvs4		98.13 199	97.90 213	98.81 231	98.61 356	98.87 174	98.99 327	99.21 295	96.44 308	99.06 232	99.58 214	95.90 175	99.11 331	97.18 282	96.11 310	98.46 341

XVG-ACMP-BASELINE		97.83 247	97.71 237	98.20 295	99.11 284	96.33 324	99.41 208	99.52 101	98.06 155	99.05 234	99.50 243	89.64 342	99.73 211	97.73 235	97.38 284	98.53 332

CostFormer		97.72 266	97.73 235	97.71 328	99.15 280	94.02 368	99.54 140	99.02 318	94.67 360	99.04 235	99.35 286	92.35 301	99.77 196	98.50 166	97.94 244	99.34 209

DP-MVS		99.16 83	98.95 105	99.78 52	99.77 62	99.53 82	99.41 208	99.50 135	97.03 265	99.04 235	99.88 36	97.39 116	99.92 95	98.66 141	99.90 40	99.87 31

ACMM	97.58 5	98.37 177	98.34 170	98.48 264	99.41 204	97.10 282	99.56 123	99.45 195	98.53 92	99.04 235	99.85 53	93.00 275	99.71 221	98.74 129	97.45 276	98.64 305
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Fast-Effi-MVS+		98.70 152	98.43 164	99.51 113	99.51 170	99.28 112	99.52 149	99.47 175	96.11 332	99.01 238	99.34 290	96.20 163	99.84 155	97.88 216	98.82 197	99.39 200

nrg030		98.64 159	98.42 165	99.28 159	99.05 300	99.69 47	99.81 21	99.46 184	98.04 157	99.01 238	99.82 75	96.69 146	99.38 278	99.34 55	94.59 345	98.78 258

test_prior2							98.96 334		98.34 112	99.01 238	99.52 236	98.68 64		97.96 211	99.74 116

MAR-MVS		98.86 130	98.63 144	99.54 97	99.37 216	99.66 53	99.45 189	99.54 85	96.61 294	99.01 238	99.40 272	97.09 129	99.86 142	97.68 242	99.53 142	99.10 226
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		98.92 123	98.92 107	98.90 208	98.78 335	98.53 207	99.78 33	99.54 85	98.07 151	99.00 242	99.76 133	99.01 18	99.37 282	99.13 77	97.23 288	98.81 255

PAPR		98.63 160	98.34 170	99.51 113	99.40 209	99.03 149	98.80 354	99.36 240	96.33 313	99.00 242	99.12 326	98.46 81	99.84 155	95.23 342	99.37 157	99.66 125

D2MVS		98.41 172	98.50 161	98.15 301	99.26 247	96.62 314	99.40 216	99.61 48	97.71 191	98.98 244	99.36 283	96.04 166	99.67 235	98.70 134	97.41 281	98.15 360

v10		97.85 242	97.52 254	98.86 221	98.99 308	98.67 194	99.75 42	99.41 214	95.70 341	98.98 244	99.41 269	94.75 220	99.23 309	96.01 323	94.63 344	98.67 293

miper_enhance_ethall		98.16 196	98.08 192	98.41 277	98.96 314	97.72 259	98.45 379	99.32 267	96.95 271	98.97 246	99.17 318	97.06 132	99.22 312	97.86 219	95.99 313	98.29 353

UniMVSNet (Re)		98.29 184	98.00 201	99.13 177	99.00 305	99.36 102	99.49 175	99.51 115	97.95 163	98.97 246	99.13 323	96.30 160	99.38 278	98.36 180	93.34 362	98.66 301

TEST9					99.67 111	99.65 57	99.05 311	99.41 214	96.22 322	98.95 248	99.49 246	98.77 51	99.91 105

train_agg		99.02 112	98.77 129	99.77 55	99.67 111	99.65 57	99.05 311	99.41 214	96.28 316	98.95 248	99.49 246	98.76 52	99.91 105	97.63 243	99.72 119	99.75 88

RRT_MVS		98.70 152	98.66 141	98.83 227	98.90 318	98.45 220	99.89 2	99.28 281	97.76 185	98.94 250	99.92 14	96.98 136	99.25 305	99.28 63	97.00 294	98.80 256

BH-RMVSNet		98.41 172	98.08 192	99.40 133	99.41 204	98.83 182	99.30 247	98.77 352	97.70 194	98.94 250	99.65 184	92.91 279	99.74 205	96.52 312	99.55 141	99.64 136

test_8					99.67 111	99.61 67	99.03 316	99.41 214	96.28 316	98.93 252	99.48 251	98.76 52	99.91 105

3Dnovator	97.25 9	99.24 74	99.05 83	99.81 44	99.12 282	99.66 53	99.84 13	99.74 10	99.09 32	98.92 253	99.90 26	95.94 172	99.98 13	98.95 95	99.92 25	99.79 74

v7n		97.87 239	97.52 254	98.92 202	98.76 340	98.58 203	99.84 13	99.46 184	96.20 323	98.91 254	99.70 156	94.89 209	99.44 270	96.03 321	93.89 357	98.75 265

JIA-IIPM		97.50 289	97.02 303	98.93 200	98.73 342	97.80 256	99.30 247	98.97 323	91.73 382	98.91 254	94.86 396	95.10 202	99.71 221	97.58 247	97.98 242	99.28 214

v148		97.79 255	97.55 250	98.50 261	98.74 341	97.72 259	99.54 140	99.33 257	96.26 319	98.90 256	99.51 239	94.68 225	99.14 323	97.83 223	93.15 366	98.63 312

GA-MVS		97.85 242	97.47 260	99.00 190	99.38 213	97.99 243	98.57 373	99.15 302	97.04 264	98.90 256	99.30 300	89.83 339	99.38 278	96.70 306	98.33 221	99.62 142

tpm2		97.44 296	97.34 283	97.74 327	99.15 280	94.36 365	99.45 189	98.94 326	93.45 374	98.90 256	99.44 261	91.35 322	99.59 255	97.31 271	98.07 240	99.29 213

tt0805		97.97 227	97.77 228	98.57 253	99.59 148	96.61 315	99.45 189	99.08 310	98.21 128	98.88 259	99.80 102	88.66 353	99.70 227	98.58 154	97.72 253	99.39 200

miper_ehance_all_eth		98.18 194	98.10 188	98.41 277	99.23 253	97.72 259	98.72 362	99.31 271	96.60 296	98.88 259	99.29 302	97.29 123	99.13 326	97.60 245	95.99 313	98.38 349

eth_miper_zixun_eth		98.05 212	97.96 206	98.33 284	99.26 247	97.38 270	98.56 375	99.31 271	96.65 289	98.88 259	99.52 236	96.58 149	99.12 330	97.39 267	95.53 327	98.47 338

cl22		97.85 242	97.64 245	98.48 264	99.09 290	97.87 252	98.60 372	99.33 257	97.11 256	98.87 262	99.22 313	92.38 300	99.17 321	98.21 189	95.99 313	98.42 344

agg_prior					99.67 111	99.62 65		99.40 220		98.87 262			99.91 105

anonymousdsp		98.44 168	98.28 175	98.94 198	98.50 362	98.96 161	99.77 35	99.50 135	97.07 259	98.87 262	99.77 128	94.76 219	99.28 300	98.66 141	97.60 260	98.57 330

DSMNet-mixed		97.25 304	97.35 280	96.95 350	97.84 373	93.61 375	99.57 117	96.63 397	96.13 331	98.87 262	98.61 363	94.59 229	97.70 387	95.08 344	98.86 193	99.55 159

FMVSNet2		97.72 266	97.36 278	98.80 233	99.51 170	98.84 179	99.45 189	99.42 211	96.49 302	98.86 266	99.29 302	90.26 333	98.98 347	96.44 314	96.56 300	98.58 329

c3_l		98.12 201	98.04 197	98.38 281	99.30 236	97.69 263	98.81 353	99.33 257	96.67 287	98.83 267	99.34 290	97.11 128	98.99 346	97.58 247	95.34 330	98.48 336

ITE_SJBPF				98.08 303	99.29 240	96.37 322		98.92 331	98.34 112	98.83 267	99.75 136	91.09 325	99.62 252	95.82 325	97.40 282	98.25 356

Anonymous20231211		97.88 237	97.54 253	98.90 208	99.71 96	98.53 207	99.48 179	99.57 64	94.16 365	98.81 269	99.68 172	93.23 270	99.42 275	98.84 117	94.42 348	98.76 263

Patchmtry		97.75 261	97.40 275	98.81 231	99.10 287	98.87 174	99.11 302	99.33 257	94.83 357	98.81 269	99.38 277	94.33 241	99.02 342	96.10 319	95.57 325	98.53 332

miper_lstm_enhance		98.00 222	97.91 212	98.28 292	99.34 226	97.43 269	98.88 346	99.36 240	96.48 305	98.80 271	99.55 224	95.98 168	98.91 358	97.27 273	95.50 328	98.51 334

BH-untuned		98.42 170	98.36 168	98.59 249	99.49 181	96.70 309	99.27 262	99.13 305	97.24 243	98.80 271	99.38 277	95.75 180	99.74 205	97.07 287	99.16 166	99.33 210

FIs		98.78 145	98.63 144	99.23 166	99.18 266	99.54 79	99.83 16	99.59 57	98.28 117	98.79 273	99.81 89	96.75 144	99.37 282	99.08 82	96.38 304	98.78 258

OurMVSNet-221017-0		97.88 237	97.77 228	98.19 296	98.71 346	96.53 317	99.88 4	99.00 320	97.79 181	98.78 274	99.94 6	91.68 313	99.35 289	97.21 276	96.99 295	98.69 281

MVS-HIRNet		95.75 335	95.16 340	97.51 335	99.30 236	93.69 373	98.88 346	95.78 400	85.09 395	98.78 274	92.65 398	91.29 323	99.37 282	94.85 347	99.85 70	99.46 188

tpmvs		97.98 224	98.02 200	97.84 320	99.04 301	94.73 358	99.31 245	99.20 296	96.10 336	98.76 276	99.42 265	94.94 204	99.81 180	96.97 292	98.45 217	98.97 246

Patchmatch-test		97.93 230	97.65 242	98.77 236	99.18 266	97.07 286	99.03 316	99.14 304	96.16 327	98.74 277	99.57 218	94.56 231	99.72 215	93.36 364	99.11 172	99.52 167

QAPM		98.67 156	98.30 174	99.80 46	99.20 260	99.67 51	99.77 35	99.72 11	94.74 359	98.73 278	99.90 26	95.78 179	99.98 13	96.96 293	99.88 52	99.76 87

3Dnovator+	97.12 13	99.18 79	98.97 101	99.82 41	99.17 274	99.68 48	99.81 21	99.51 115	99.20 18	98.72 279	99.89 30	95.68 183	99.97 21	98.86 112	99.86 63	99.81 61

IterMVS-SCA-FT		97.82 250	97.75 233	98.06 304	99.57 152	96.36 323	99.02 319	99.49 143	97.18 247	98.71 280	99.72 151	92.72 284	99.14 323	97.44 264	95.86 318	98.67 293

UniMVSNet_NR-MVSNet		98.22 188	97.97 205	98.96 195	98.92 317	98.98 154	99.48 179	99.53 96	97.76 185	98.71 280	99.46 258	96.43 157	99.22 312	98.57 157	92.87 369	98.69 281

DU-MVS		98.08 205	97.79 223	98.96 195	98.87 324	98.98 154	99.41 208	99.45 195	97.87 169	98.71 280	99.50 243	94.82 211	99.22 312	98.57 157	92.87 369	98.68 286

tpm cat1		97.39 298	97.36 278	97.50 336	99.17 274	93.73 371	99.43 199	99.31 271	91.27 383	98.71 280	99.08 327	94.31 243	99.77 196	96.41 316	98.50 215	99.00 242

XXY-MVS		98.38 176	98.09 191	99.24 164	99.26 247	99.32 104	99.56 123	99.55 77	97.45 222	98.71 280	99.83 67	93.23 270	99.63 251	98.88 104	96.32 306	98.76 263

IterMVS		97.83 247	97.77 228	98.02 307	99.58 150	96.27 326	99.02 319	99.48 155	97.22 245	98.71 280	99.70 156	92.75 281	99.13 326	97.46 262	96.00 312	98.67 293
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FC-MVSNet-test		98.75 148	98.62 149	99.15 176	99.08 293	99.45 93	99.86 12	99.60 54	98.23 125	98.70 286	99.82 75	96.80 141	99.22 312	99.07 83	96.38 304	98.79 257

COLMAP_ROB	97.56 6	98.86 130	98.75 131	99.17 171	99.88 11	98.53 207	99.34 239	99.59 57	97.55 209	98.70 286	99.89 30	95.83 177	99.90 116	98.10 197	99.90 40	99.08 231
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TR-MVS		97.76 257	97.41 274	98.82 228	99.06 297	97.87 252	98.87 348	98.56 368	96.63 293	98.68 288	99.22 313	92.49 294	99.65 243	95.40 338	97.79 251	98.95 250

WR-MVS		98.06 207	97.73 235	99.06 182	98.86 327	99.25 118	99.19 283	99.35 246	97.30 237	98.66 289	99.43 263	93.94 255	99.21 317	98.58 154	94.28 350	98.71 273

HQP-NCC					99.19 263		98.98 330		98.24 122	98.66 289

ACMP_Plane					99.19 263		98.98 330		98.24 122	98.66 289

HQP4-MVS										98.66 289			99.64 246			98.64 305

HQP-MVS		98.02 217	97.90 213	98.37 282	99.19 263	96.83 304	98.98 330	99.39 223	98.24 122	98.66 289	99.40 272	92.47 295	99.64 246	97.19 280	97.58 262	98.64 305

LF4IMVS		97.52 286	97.46 262	97.70 329	98.98 311	95.55 340	99.29 252	98.82 347	98.07 151	98.66 289	99.64 190	89.97 338	99.61 253	97.01 288	96.68 296	97.94 373

mvs_tets		98.40 175	98.23 177	98.91 206	98.67 350	98.51 213	99.66 70	99.53 96	98.19 131	98.65 295	99.81 89	92.75 281	99.44 270	99.31 58	97.48 274	98.77 261

TESTMET0.1,1		97.55 284	97.27 294	98.40 279	98.93 316	96.53 317	98.67 365	97.61 388	96.96 269	98.64 296	99.28 304	88.63 355	99.45 265	97.30 272	99.38 150	99.21 221

jajsoiax		98.43 169	98.28 175	98.88 213	98.60 357	98.43 222	99.82 17	99.53 96	98.19 131	98.63 297	99.80 102	93.22 272	99.44 270	99.22 70	97.50 270	98.77 261

Baseline_NR-MVSNet		97.76 257	97.45 263	98.68 244	99.09 290	98.29 227	99.41 208	98.85 344	95.65 342	98.63 297	99.67 178	94.82 211	99.10 333	98.07 205	92.89 368	98.64 305

EPNet		98.86 130	98.71 134	99.30 152	97.20 385	98.18 232	99.62 88	98.91 335	99.28 16	98.63 297	99.81 89	95.96 169	99.99 4	99.24 69	99.72 119	99.73 97
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test-LLR		98.06 207	97.90 213	98.55 258	98.79 332	97.10 282	98.67 365	97.75 385	97.34 233	98.61 300	98.85 350	94.45 238	99.45 265	97.25 274	99.38 150	99.10 226

test-mter		97.49 294	97.13 299	98.55 258	98.79 332	97.10 282	98.67 365	97.75 385	96.65 289	98.61 300	98.85 350	88.23 359	99.45 265	97.25 274	99.38 150	99.10 226

DIV-MVS_self_test		98.01 220	97.85 220	98.48 264	99.24 252	97.95 248	98.71 363	99.35 246	96.50 301	98.60 302	99.54 229	95.72 182	99.03 340	97.21 276	95.77 319	98.46 341

cl____		98.01 220	97.84 221	98.55 258	99.25 251	97.97 244	98.71 363	99.34 250	96.47 307	98.59 303	99.54 229	95.65 184	99.21 317	97.21 276	95.77 319	98.46 341

ETVMVS		97.50 289	96.90 307	99.29 155	99.23 253	98.78 188	99.32 242	98.90 337	97.52 215	98.56 304	98.09 380	84.72 380	99.69 232	97.86 219	97.88 247	99.39 200

FMVSNet1		96.84 315	96.36 319	98.29 289	99.32 234	97.26 275	99.43 199	99.48 155	95.11 349	98.55 305	99.32 297	83.95 383	98.98 347	95.81 326	96.26 307	98.62 315

UniMVSNet_ETH3D		97.32 301	96.81 309	98.87 217	99.40 209	97.46 268	99.51 157	99.53 96	95.86 340	98.54 306	99.77 128	82.44 389	99.66 238	98.68 139	97.52 267	99.50 176

AUN-MVS		96.88 314	96.31 320	98.59 249	99.48 188	97.04 291	99.27 262	99.22 292	97.44 224	98.51 307	99.41 269	91.97 305	99.66 238	97.71 238	83.83 393	99.07 236

PCF-MVS	97.08 14	97.66 277	97.06 302	99.47 122	99.61 141	99.09 139	98.04 393	99.25 287	91.24 384	98.51 307	99.70 156	94.55 233	99.91 105	92.76 373	99.85 70	99.42 195
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TranMVSNet+NR-MVSNet		97.93 230	97.66 241	98.76 237	98.78 335	98.62 199	99.65 76	99.49 143	97.76 185	98.49 309	99.60 208	94.23 244	98.97 354	98.00 209	92.90 367	98.70 277

CP-MVSNet		98.09 203	97.78 226	99.01 188	98.97 313	99.24 119	99.67 65	99.46 184	97.25 241	98.48 310	99.64 190	93.79 261	99.06 336	98.63 144	94.10 353	98.74 268

ACMP	97.20 11	98.06 207	97.94 210	98.45 271	99.37 216	97.01 293	99.44 195	99.49 143	97.54 212	98.45 311	99.79 114	91.95 306	99.72 215	97.91 214	97.49 273	98.62 315
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
cascas		97.69 271	97.43 272	98.48 264	98.60 357	97.30 271	98.18 391	99.39 223	92.96 377	98.41 312	98.78 357	93.77 262	99.27 303	98.16 195	98.61 205	98.86 252

WR-MVS_H		98.13 199	97.87 219	98.90 208	99.02 303	98.84 179	99.70 53	99.59 57	97.27 239	98.40 313	99.19 317	95.53 187	99.23 309	98.34 181	93.78 359	98.61 324

BH-w/o		98.00 222	97.89 217	98.32 286	99.35 222	96.20 329	99.01 324	98.90 337	96.42 310	98.38 314	99.00 337	95.26 198	99.72 215	96.06 320	98.61 205	99.03 239

pmmvs5		97.52 286	97.30 288	98.16 298	98.57 359	96.73 308	99.27 262	98.90 337	96.14 330	98.37 315	99.53 233	91.54 319	99.14 323	97.51 256	95.87 317	98.63 312

EU-MVSNet		97.98 224	98.03 198	97.81 324	98.72 344	96.65 313	99.66 70	99.66 28	98.09 146	98.35 316	99.82 75	95.25 199	98.01 380	97.41 266	95.30 331	98.78 258

FMVSNet5		96.43 323	96.19 322	97.15 342	99.11 284	95.89 334	99.32 242	99.52 101	94.47 364	98.34 317	99.07 328	87.54 366	97.07 391	92.61 374	95.72 322	98.47 338

testing91		97.44 296	97.02 303	98.71 241	99.18 266	96.89 303	99.19 283	99.04 316	97.78 183	98.31 318	98.29 372	85.41 375	99.85 148	98.01 208	97.95 243	99.39 200

PS-CasMVS		97.93 230	97.59 249	98.95 197	98.99 308	99.06 146	99.68 62	99.52 101	97.13 251	98.31 318	99.68 172	92.44 299	99.05 337	98.51 165	94.08 354	98.75 265

USDC		97.34 300	97.20 295	97.75 326	99.07 294	95.20 350	98.51 377	99.04 316	97.99 161	98.31 318	99.86 48	89.02 345	99.55 259	95.67 332	97.36 285	98.49 335

PEN-MVS		97.76 257	97.44 268	98.72 239	98.77 339	98.54 206	99.78 33	99.51 115	97.06 261	98.29 321	99.64 190	92.63 290	98.89 360	98.09 198	93.16 365	98.72 271

tfpnnormal		97.84 245	97.47 260	98.98 192	99.20 260	99.22 121	99.64 79	99.61 48	96.32 314	98.27 322	99.70 156	93.35 269	99.44 270	95.69 330	95.40 329	98.27 354

testing99		97.36 299	96.94 306	98.63 246	99.18 266	96.70 309	99.30 247	98.93 328	97.71 191	98.23 323	98.26 373	84.92 378	99.84 155	98.04 207	97.85 250	99.35 206

testing222		97.16 307	96.50 315	99.16 172	99.16 276	98.47 219	99.27 262	98.66 365	97.71 191	98.23 323	98.15 375	82.28 390	99.84 155	97.36 269	97.66 255	99.18 222

ppachtmachnet_test		97.49 294	97.45 263	97.61 332	98.62 354	95.24 349	98.80 354	99.46 184	96.11 332	98.22 325	99.62 201	96.45 155	98.97 354	93.77 359	95.97 316	98.61 324

testing11		97.50 289	97.10 300	98.71 241	99.20 260	96.91 301	99.29 252	98.82 347	97.89 168	98.21 326	98.40 368	85.63 373	99.83 168	98.45 172	98.04 241	99.37 204

our_test_3		97.65 278	97.68 239	97.55 334	98.62 354	94.97 355	98.84 350	99.30 275	96.83 280	98.19 327	99.34 290	97.01 135	99.02 342	95.00 346	96.01 311	98.64 305

LTVRE_ROB	97.16 12	98.02 217	97.90 213	98.40 279	99.23 253	96.80 307	99.70 53	99.60 54	97.12 253	98.18 328	99.70 156	91.73 312	99.72 215	98.39 175	97.45 276	98.68 286
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	98.10 202	97.99 202	98.44 274	99.41 204	96.96 299	99.60 96	99.56 69	98.09 146	98.15 329	99.91 20	90.87 328	99.70 227	98.88 104	97.45 276	98.67 293
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MS-PatchMatch		97.24 306	97.32 286	96.99 347	98.45 364	93.51 376	98.82 352	99.32 267	97.41 228	98.13 330	99.30 300	88.99 346	99.56 257	95.68 331	99.80 98	97.90 376

MVS		97.28 302	96.55 314	99.48 119	98.78 335	98.95 164	99.27 262	99.39 223	83.53 396	98.08 331	99.54 229	96.97 137	99.87 138	94.23 355	99.16 166	99.63 140

PAPM		97.59 282	97.09 301	99.07 181	99.06 297	98.26 229	98.30 387	99.10 307	94.88 355	98.08 331	99.34 290	96.27 161	99.64 246	89.87 384	98.92 189	99.31 212

OpenMVS	96.50 16	98.47 166	98.12 186	99.52 111	99.04 301	99.53 82	99.82 17	99.72 11	94.56 362	98.08 331	99.88 36	94.73 221	99.98 13	97.47 261	99.76 111	99.06 237

gg-mvs-nofinetune		96.17 328	95.32 339	98.73 238	98.79 332	98.14 235	99.38 225	94.09 406	91.07 386	98.07 334	91.04 402	89.62 343	99.35 289	96.75 303	99.09 176	98.68 286

test0.0.03 1		97.71 269	97.42 273	98.56 256	98.41 366	97.82 255	98.78 356	98.63 366	97.34 233	98.05 335	98.98 340	94.45 238	98.98 347	95.04 345	97.15 292	98.89 251

APD_test1		95.87 332	96.49 316	94.00 366	99.53 163	84.01 394	99.54 140	99.32 267	95.91 339	97.99 336	99.85 53	85.49 374	99.88 133	91.96 376	98.84 195	98.12 361

1314		98.68 155	98.54 159	99.11 178	98.89 320	98.65 196	99.27 262	99.49 143	96.89 275	97.99 336	99.56 221	97.72 111	99.83 168	97.74 234	99.27 161	98.84 254

DTE-MVSNet		97.51 288	97.19 296	98.46 270	98.63 353	98.13 236	99.84 13	99.48 155	96.68 286	97.97 338	99.67 178	92.92 277	98.56 369	96.88 300	92.60 372	98.70 277

SixPastTwentyTwo		97.50 289	97.33 285	98.03 305	98.65 351	96.23 328	99.77 35	98.68 364	97.14 250	97.90 339	99.93 9	90.45 331	99.18 320	97.00 289	96.43 303	98.67 293

testing3		97.28 302	96.76 311	98.82 228	99.37 216	98.07 239	99.45 189	99.36 240	97.56 208	97.89 340	98.95 343	83.70 384	98.82 361	96.03 321	98.56 211	99.58 154

pm-mvs1		97.68 273	97.28 291	98.88 213	99.06 297	98.62 199	99.50 164	99.45 195	96.32 314	97.87 341	99.79 114	92.47 295	99.35 289	97.54 254	93.54 361	98.67 293

testgi		97.65 278	97.50 257	98.13 302	99.36 221	96.45 320	99.42 206	99.48 155	97.76 185	97.87 341	99.45 260	91.09 325	98.81 362	94.53 350	98.52 214	99.13 225

EPNet_dtu		98.03 215	97.96 206	98.23 294	98.27 367	95.54 342	99.23 276	98.75 353	99.02 38	97.82 343	99.71 152	96.11 164	99.48 262	93.04 368	99.65 131	99.69 115
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TinyColmap		97.12 309	96.89 308	97.83 321	99.07 294	95.52 343	98.57 373	98.74 356	97.58 205	97.81 344	99.79 114	88.16 360	99.56 257	95.10 343	97.21 289	98.39 348

ACMH+	97.24 10	97.92 233	97.78 226	98.32 286	99.46 190	96.68 312	99.56 123	99.54 85	98.41 104	97.79 345	99.87 44	90.18 337	99.66 238	98.05 206	97.18 291	98.62 315

N_pmnet		94.95 344	95.83 331	92.31 372	98.47 363	79.33 404	99.12 296	92.81 410	93.87 367	97.68 346	99.13 323	93.87 258	99.01 344	91.38 379	96.19 308	98.59 328

KD-MVS_2432*1600		94.62 345	93.72 353	97.31 339	97.19 386	95.82 335	98.34 383	99.20 296	95.00 353	97.57 347	98.35 369	87.95 362	98.10 377	92.87 371	77.00 400	98.01 367

miper_refine_blended		94.62 345	93.72 353	97.31 339	97.19 386	95.82 335	98.34 383	99.20 296	95.00 353	97.57 347	98.35 369	87.95 362	98.10 377	92.87 371	77.00 400	98.01 367

PVSNet_0	94.43 19	96.09 330	95.47 336	97.94 313	99.31 235	94.34 366	97.81 394	99.70 15	97.12 253	97.46 349	98.75 358	89.71 340	99.79 189	97.69 241	81.69 396	99.68 119

Syy-MVS		97.09 311	97.14 297	96.95 350	99.00 305	92.73 381	99.29 252	99.39 223	97.06 261	97.41 350	98.15 375	93.92 257	98.68 367	91.71 377	98.34 219	99.45 191

myMVS_eth3d		96.89 313	96.37 318	98.43 276	99.00 305	97.16 279	99.29 252	99.39 223	97.06 261	97.41 350	98.15 375	83.46 385	98.68 367	95.27 341	98.34 219	99.45 191

pmmvs6		96.53 320	96.09 325	97.82 323	98.69 348	95.47 344	99.37 227	99.47 175	93.46 373	97.41 350	99.78 120	87.06 368	99.33 292	96.92 298	92.70 371	98.65 303

new_pmnet		96.38 324	96.03 326	97.41 337	98.13 370	95.16 353	99.05 311	99.20 296	93.94 366	97.39 353	98.79 356	91.61 318	99.04 338	90.43 382	95.77 319	98.05 365

CL-MVSNet_self_test		94.49 347	93.97 351	96.08 361	96.16 390	93.67 374	98.33 385	99.38 231	95.13 347	97.33 354	98.15 375	92.69 288	96.57 394	88.67 388	79.87 398	97.99 370

IB-MVS	95.67 18	96.22 325	95.44 338	98.57 253	99.21 258	96.70 309	98.65 368	97.74 387	96.71 284	97.27 355	98.54 364	86.03 370	99.92 95	98.47 170	86.30 390	99.10 226
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				98.45 271	98.55 360	98.16 233	99.43 199	93.68 407		97.23 356	98.46 365	89.30 344	99.22 312	95.43 337	98.22 229	97.98 371

MVP-Stereo		97.81 252	97.75 233	97.99 311	97.53 378	96.60 316	98.96 334	98.85 344	97.22 245	97.23 356	99.36 283	95.28 195	99.46 264	95.51 334	99.78 105	97.92 375
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Anonymous20240521		96.20 327	95.89 330	97.13 344	97.72 377	94.96 356	99.79 32	99.29 279	93.01 376	97.20 358	99.03 333	89.69 341	98.36 373	91.16 380	96.13 309	98.07 363

TransMVSNet (Re)		97.15 308	96.58 313	98.86 221	99.12 282	98.85 178	99.49 175	98.91 335	95.48 344	97.16 359	99.80 102	93.38 268	99.11 331	94.16 357	91.73 374	98.62 315

KD-MVS_self_test		95.00 342	94.34 347	96.96 349	97.07 388	95.39 347	99.56 123	99.44 203	95.11 349	97.13 360	97.32 388	91.86 308	97.27 390	90.35 383	81.23 397	98.23 358

NR-MVSNet		97.97 227	97.61 247	99.02 187	98.87 324	99.26 116	99.47 185	99.42 211	97.63 201	97.08 361	99.50 243	95.07 203	99.13 326	97.86 219	93.59 360	98.68 286

Anonymous20231206		96.22 325	96.03 326	96.79 355	97.31 383	94.14 367	99.63 83	99.08 310	96.17 326	97.04 362	99.06 330	93.94 255	97.76 386	86.96 395	95.06 336	98.47 338

test_0402		96.64 318	96.24 321	97.85 318	98.85 328	96.43 321	99.44 195	99.26 285	93.52 371	96.98 363	99.52 236	88.52 356	99.20 319	92.58 375	97.50 270	97.93 374

MIMVSNet1		95.51 336	95.04 341	96.92 352	97.38 380	95.60 338	99.52 149	99.50 135	93.65 370	96.97 364	99.17 318	85.28 377	96.56 395	88.36 390	95.55 326	98.60 327

TDRefinement		95.42 338	94.57 345	97.97 312	89.83 406	96.11 331	99.48 179	98.75 353	96.74 282	96.68 365	99.88 36	88.65 354	99.71 221	98.37 178	82.74 395	98.09 362

baseline2		97.87 239	97.55 250	98.82 228	99.18 266	98.02 241	99.41 208	96.58 399	96.97 268	96.51 366	99.17 318	93.43 267	99.57 256	97.71 238	99.03 181	98.86 252

pmmvs3		94.09 351	93.25 357	96.60 357	94.76 400	94.49 362	98.92 342	98.18 380	89.66 387	96.48 367	98.06 381	86.28 369	97.33 389	89.68 385	87.20 389	97.97 372

DeepMVS_CX				93.34 369	99.29 240	82.27 397		99.22 292	85.15 394	96.33 368	99.05 331	90.97 327	99.73 211	93.57 362	97.77 252	98.01 367

LCM-MVSNet-Re		97.83 247	98.15 182	96.87 353	99.30 236	92.25 383	99.59 102	98.26 374	97.43 225	96.20 369	99.13 323	96.27 161	98.73 366	98.17 194	98.99 184	99.64 136

test20.03		96.12 329	95.96 328	96.63 356	97.44 379	95.45 345	99.51 157	99.38 231	96.55 299	96.16 370	99.25 310	93.76 263	96.17 396	87.35 394	94.22 351	98.27 354

K. test v3		97.10 310	96.79 310	98.01 308	98.72 344	96.33 324	99.87 9	97.05 392	97.59 203	96.16 370	99.80 102	88.71 351	99.04 338	96.69 307	96.55 301	98.65 303

UnsupCasMVSNet_eth		96.44 322	96.12 323	97.40 338	98.65 351	95.65 337	99.36 231	99.51 115	97.13 251	96.04 372	98.99 338	88.40 357	98.17 376	96.71 305	90.27 382	98.40 347

test_method		91.10 359	91.36 361	90.31 378	95.85 391	73.72 411	94.89 399	99.25 287	68.39 402	95.82 373	99.02 335	80.50 392	98.95 356	93.64 361	94.89 342	98.25 356

lessismore_v0				97.79 325	98.69 348	95.44 346		94.75 404		95.71 374	99.87 44	88.69 352	99.32 295	95.89 324	94.93 340	98.62 315

test_vis1_rt		95.81 334	95.65 334	96.32 360	99.67 111	91.35 387	99.49 175	96.74 396	98.25 121	95.24 375	98.10 379	74.96 394	99.90 116	99.53 32	98.85 194	97.70 379

dmvs_testset		95.02 341	96.12 323	91.72 374	99.10 287	80.43 402	99.58 110	97.87 384	97.47 218	95.22 376	98.82 352	93.99 253	95.18 399	88.09 391	94.91 341	99.56 158

Patchmatch-RL test		95.84 333	95.81 332	95.95 362	95.61 393	90.57 388	98.24 388	98.39 372	95.10 351	95.20 377	98.67 360	94.78 215	97.77 385	96.28 318	90.02 383	99.51 173

test_fmvs3		92.10 357	91.77 360	93.08 370	96.19 389	86.25 392	99.82 17	98.62 367	96.65 289	95.19 378	96.90 390	55.05 405	95.93 398	96.63 311	90.92 380	97.06 386

ambc				93.06 371	92.68 402	82.36 396	98.47 378	98.73 361		95.09 379	97.41 385	55.55 403	99.10 333	96.42 315	91.32 375	97.71 377

PM-MVS		92.96 355	92.23 359	95.14 364	95.61 393	89.98 390	99.37 227	98.21 378	94.80 358	95.04 380	97.69 383	65.06 398	97.90 383	94.30 352	89.98 384	97.54 383

OpenMVS_ROB	92.34 20	94.38 349	93.70 355	96.41 359	97.38 380	93.17 378	99.06 309	98.75 353	86.58 393	94.84 381	98.26 373	81.53 391	99.32 295	89.01 387	97.87 248	96.76 387

mvsany_test3		93.77 352	93.45 356	94.74 365	95.78 392	88.01 391	99.64 79	98.25 375	98.28 117	94.31 382	97.97 382	68.89 397	98.51 371	97.50 257	90.37 381	97.71 377

EG-PatchMatch MVS		95.97 331	95.69 333	96.81 354	97.78 374	92.79 380	99.16 287	98.93 328	96.16 327	94.08 383	99.22 313	82.72 387	99.47 263	95.67 332	97.50 270	98.17 359

test_f		91.90 358	91.26 362	93.84 367	95.52 396	85.92 393	99.69 56	98.53 371	95.31 346	93.87 384	96.37 393	55.33 404	98.27 374	95.70 329	90.98 379	97.32 385

pmmvs-eth3d		95.34 340	94.73 343	97.15 342	95.53 395	95.94 333	99.35 236	99.10 307	95.13 347	93.55 385	97.54 384	88.15 361	97.91 382	94.58 349	89.69 385	97.61 380

new-patchmatchnet		94.48 348	94.08 349	95.67 363	95.08 398	92.41 382	99.18 285	99.28 281	94.55 363	93.49 386	97.37 387	87.86 364	97.01 392	91.57 378	88.36 386	97.61 380

UnsupCasMVSNet_bld		93.53 353	92.51 358	96.58 358	97.38 380	93.82 369	98.24 388	99.48 155	91.10 385	93.10 387	96.66 391	74.89 395	98.37 372	94.03 358	87.71 388	97.56 382

WB-MVS		93.10 354	94.10 348	90.12 379	95.51 397	81.88 399	99.73 48	99.27 284	95.05 352	93.09 388	98.91 349	94.70 224	91.89 403	76.62 402	94.02 356	96.58 389

SSC-MVS		92.73 356	93.73 352	89.72 380	95.02 399	81.38 400	99.76 38	99.23 290	94.87 356	92.80 389	98.93 345	94.71 223	91.37 404	74.49 404	93.80 358	96.42 390

Gipuma		90.99 360	90.15 365	93.51 368	98.73 342	90.12 389	93.98 400	99.45 195	79.32 398	92.28 390	94.91 395	69.61 396	97.98 381	87.42 393	95.67 323	92.45 398
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
CMPMVS	69.68 23	94.13 350	94.90 342	91.84 373	97.24 384	80.01 403	98.52 376	99.48 155	89.01 390	91.99 391	99.67 178	85.67 372	99.13 326	95.44 336	97.03 293	96.39 391
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testf1		90.42 361	90.68 363	89.65 381	97.78 374	73.97 409	99.13 293	98.81 349	89.62 388	91.80 392	98.93 345	62.23 401	98.80 363	86.61 397	91.17 376	96.19 392

APD_test2		90.42 361	90.68 363	89.65 381	97.78 374	73.97 409	99.13 293	98.81 349	89.62 388	91.80 392	98.93 345	62.23 401	98.80 363	86.61 397	91.17 376	96.19 392

PMMVS2		86.87 364	85.37 368	91.35 376	90.21 405	83.80 395	98.89 345	97.45 391	83.13 397	91.67 394	95.03 394	48.49 407	94.70 400	85.86 399	77.62 399	95.54 395

LCM-MVSNet		86.80 365	85.22 369	91.53 375	87.81 407	80.96 401	98.23 390	98.99 321	71.05 400	90.13 395	96.51 392	48.45 408	96.88 393	90.51 381	85.30 391	96.76 387

ET-MVSNet_ETH3D		96.49 321	95.64 335	99.05 184	99.53 163	98.82 183	98.84 350	97.51 390	97.63 201	84.77 396	99.21 316	92.09 303	98.91 358	98.98 92	92.21 373	99.41 197

E-PMN		80.61 369	79.88 371	82.81 386	90.75 404	76.38 407	97.69 395	95.76 401	66.44 404	83.52 397	92.25 399	62.54 400	87.16 406	68.53 406	61.40 403	84.89 404

FPMVS		84.93 366	85.65 367	82.75 387	86.77 408	63.39 413	98.35 382	98.92 331	74.11 399	83.39 398	98.98 340	50.85 406	92.40 402	84.54 400	94.97 338	92.46 397

EMVS		80.02 370	79.22 372	82.43 388	91.19 403	76.40 406	97.55 397	92.49 411	66.36 405	83.01 399	91.27 401	64.63 399	85.79 407	65.82 407	60.65 404	85.08 403

test_vis3_rt		87.04 363	85.81 366	90.73 377	93.99 401	81.96 398	99.76 38	90.23 412	92.81 378	81.35 400	91.56 400	40.06 409	99.07 335	94.27 354	88.23 387	91.15 400

YYNet1		95.36 339	94.51 346	97.92 314	97.89 372	97.10 282	99.10 304	99.23 290	93.26 375	80.77 401	99.04 332	92.81 280	98.02 379	94.30 352	94.18 352	98.64 305

MDA-MVSNet_test_wron		95.45 337	94.60 344	98.01 308	98.16 369	97.21 278	99.11 302	99.24 289	93.49 372	80.73 402	98.98 340	93.02 274	98.18 375	94.22 356	94.45 347	98.64 305

MDA-MVSNet-bldmvs		94.96 343	93.98 350	97.92 314	98.24 368	97.27 273	99.15 290	99.33 257	93.80 368	80.09 403	99.03 333	88.31 358	97.86 384	93.49 363	94.36 349	98.62 315

tmp_tt		82.80 367	81.52 370	86.66 383	66.61 413	68.44 412	92.79 402	97.92 382	68.96 401	80.04 404	99.85 53	85.77 371	96.15 397	97.86 219	43.89 406	95.39 396

MVE	76.82 21	76.91 372	74.31 376	84.70 384	85.38 410	76.05 408	96.88 398	93.17 408	67.39 403	71.28 405	89.01 404	21.66 415	87.69 405	71.74 405	72.29 402	90.35 401
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		77.30 371	74.86 375	84.62 385	75.88 411	77.61 405	97.63 396	93.15 409	88.81 391	64.27 406	89.29 403	36.51 410	83.93 408	75.89 403	52.31 405	92.33 399

PMVS	70.75 22	75.98 373	74.97 374	79.01 389	70.98 412	55.18 414	93.37 401	98.21 378	65.08 406	61.78 407	93.83 397	21.74 414	92.53 401	78.59 401	91.12 378	89.34 402
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test123		39.01 376	42.50 378	28.53 391	39.17 414	20.91 416	98.75 359	19.17 416	19.83 409	38.57 408	66.67 406	33.16 411	15.42 410	37.50 410	29.66 408	49.26 405

testmvs		39.17 375	43.78 377	25.37 392	36.04 415	16.84 417	98.36 381	26.56 414	20.06 408	38.51 409	67.32 405	29.64 412	15.30 411	37.59 409	39.90 407	43.98 406

wuyk23d		40.18 374	41.29 379	36.84 390	86.18 409	49.12 415	79.73 403	22.81 415	27.64 407	25.46 410	28.45 410	21.98 413	48.89 409	55.80 408	23.56 409	12.51 407

EGC-MVSNET		82.80 367	77.86 373	97.62 331	97.91 371	96.12 330	99.33 241	99.28 281	8.40 410	25.05 411	99.27 307	84.11 382	99.33 292	89.20 386	98.22 229	97.42 384

test_blank		0.13 380	0.17 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	1.57 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet_test		0.02 381	0.03 384	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.27 412	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

DCPMVS		0.02 381	0.03 384	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.27 412	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

cdsmvs_eth3d_5k		24.64 377	32.85 380	0.00 393	0.00 416	0.00 418	0.00 404	99.51 115	0.00 411	0.00 412	99.56 221	96.58 149	0.00 412	0.00 411	0.00 410	0.00 408

pcd_1.5k_mvsjas		8.27 379	11.03 382	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.27 412	99.01 18	0.00 412	0.00 411	0.00 410	0.00 408

sosnet-low-res		0.02 381	0.03 384	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.27 412	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

sosnet		0.02 381	0.03 384	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.27 412	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uncertanet		0.02 381	0.03 384	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.27 412	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

Regformer		0.02 381	0.03 384	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.27 412	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

ab-mvs-re		8.30 378	11.06 381	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	99.58 214	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet		0.02 381	0.03 384	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.27 412	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

WAC-MVS						97.16 279								95.47 335

MSC_two_6792asdad				99.87 11	99.51 170	99.76 37		99.33 257					99.96 30	98.87 107	99.84 78	99.89 20

No_MVS				99.87 11	99.51 170	99.76 37		99.33 257					99.96 30	98.87 107	99.84 78	99.89 20

eth-test2					0.00 416

eth-test					0.00 416

OPU-MVS				99.64 78	99.56 156	99.72 42	99.60 96				99.70 156	99.27 5	99.42 275	98.24 188	99.80 98	99.79 74

save fliter					99.76 65	99.59 70	99.14 292	99.40 220	99.00 43

test_0728_SECOND				99.91 2	99.84 32	99.89 4	99.57 117	99.51 115					99.96 30	98.93 98	99.86 63	99.88 26

GSMVS																99.52 167

sam_mvs1												94.86 210				99.52 167

sam_mvs												94.72 222

MTGPA								99.47 175

test_post1							99.23 276				65.14 408	94.18 248	99.71 221	97.58 247

test_post											65.99 407	94.65 228	99.73 211

patchmatchnet-post											98.70 359	94.79 214	99.74 205

MTMP							99.54 140	98.88 340

gm-plane-assit					98.54 361	92.96 379			94.65 361		99.15 321		99.64 246	97.56 252

test9_res														97.49 258	99.72 119	99.75 88

agg_prior2														97.21 276	99.73 118	99.75 88

test_prior4						99.56 75	98.99 327

test_prior				99.68 68	99.67 111	99.48 89		99.56 69					99.83 168			99.74 92

新几何2							99.01 324

旧先验1					99.74 80	99.59 70		99.54 85			99.69 166	98.47 80			99.68 127	99.73 97

无先验							98.99 327	99.51 115	96.89 275				99.93 84	97.53 255		99.72 103

原ACMM2							98.95 338

testdata2													99.95 59	96.67 308

segment_acmp												98.96 24

testdata1							98.85 349		98.32 115

plane_prior7					99.29 240	97.03 292

plane_prior6					99.27 245	96.98 296						92.71 286

plane_prior5								99.47 175					99.69 232	97.78 227	97.63 257	98.67 293

plane_prior4											99.61 205

plane_prior2							99.39 220		98.97 51

plane_prior1					99.26 247

plane_prior						96.97 297	99.21 282		98.45 100						97.60 260

n2								0.00 417

nn								0.00 417

door-mid								98.05 381

test11								99.35 246

door								97.92 382

HQP5-MVS						96.83 304

BP-MVS														97.19 280

HQP3-MVS								99.39 223							97.58 262

HQP2-MVS												92.47 295

NP-MVS					99.23 253	96.92 300					99.40 272

ACMMP++_ref															97.19 290

ACMMP++															97.43 280

Test By Simon												98.75 55

High-resolution multi-view benchmark