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.

MED-MVS		99.12 1	98.97 4	99.56 9	99.77 2	98.86 23	99.32 22	99.24 20	97.87 31	99.30 52	99.54 20	97.61 6	99.92 43	98.30 75	99.80 25	99.90 5

fmvsm_l_conf0.5_n_a		99.09 2	99.08 1	99.11 62	99.43 63	97.48 90	98.88 131	99.30 14	98.47 18	99.85 11	99.43 45	96.71 18	99.96 4	99.86 1	99.80 25	99.89 8

SED-MVS		99.09 2	98.91 5	99.63 5	99.71 24	99.24 5	99.02 86	98.87 85	97.65 41	99.73 23	99.48 35	97.53 8	99.94 14	98.43 67	99.81 16	99.70 67

DVP-MVS++		99.08 4	98.89 6	99.64 4	99.17 111	99.23 7	99.69 1	98.88 78	97.32 65	99.53 38	99.47 37	97.81 3	99.94 14	98.47 63	99.72 66	99.74 50

fmvsm_l_conf0.5_n		99.07 5	99.05 2	99.14 58	99.41 66	97.54 88	98.89 124	99.31 13	98.49 17	99.86 8	99.42 46	96.45 28	99.96 4	99.86 1	99.74 57	99.90 5

TestfortrainingZip a		99.05 6	98.85 9	99.65 2	99.77 2	99.13 11	99.32 22	99.01 52	97.87 31	99.74 21	99.54 20	96.71 18	99.92 43	98.35 72	99.33 139	99.90 5

DVP-MVS		99.03 7	98.83 11	99.63 5	99.72 17	99.25 2	98.97 98	98.58 176	97.62 43	99.45 40	99.46 42	97.42 10	99.94 14	98.47 63	99.81 16	99.69 70
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
APDe-MVS		99.02 8	98.84 10	99.55 11	99.57 39	98.96 18	99.39 11	98.93 65	97.38 62	99.41 44	99.54 20	96.66 20	99.84 88	98.86 39	99.85 6	99.87 12
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
lecture		98.95 9	98.78 14	99.45 19	99.75 6	98.63 31	99.43 10	99.38 8	97.60 46	99.58 34	99.47 37	95.36 64	99.93 34	98.87 38	99.57 98	99.78 33

reproduce_model		98.94 10	98.81 12	99.34 32	99.52 45	98.26 55	98.94 108	98.84 96	98.06 25	99.35 48	99.61 5	96.39 31	99.94 14	98.77 42	99.82 14	99.83 19

reproduce-ours		98.93 11	98.78 14	99.38 24	99.49 52	98.38 41	98.86 142	98.83 98	98.06 25	99.29 54	99.58 16	96.40 29	99.94 14	98.68 45	99.81 16	99.81 25

our_new_method		98.93 11	98.78 14	99.38 24	99.49 52	98.38 41	98.86 142	98.83 98	98.06 25	99.29 54	99.58 16	96.40 29	99.94 14	98.68 45	99.81 16	99.81 25

test_fmvsmconf_n		98.92 13	98.87 7	99.04 68	98.88 147	97.25 112	98.82 155	99.34 11	98.75 11	99.80 14	99.61 5	95.16 77	99.95 9	99.70 17	99.80 25	99.93 1

DPE-MVS		98.92 13	98.67 20	99.65 2	99.58 37	99.20 9	98.42 267	98.91 72	97.58 47	99.54 37	99.46 42	97.10 13	99.94 14	97.64 122	99.84 11	99.83 19
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
fmvsm_l_conf0.5_n_9		98.90 15	98.79 13	99.24 46	99.34 71	97.83 79	98.70 196	99.26 16	98.85 6	99.92 1	99.51 28	93.91 106	99.95 9	99.86 1	99.79 34	99.92 2

fmvsm_l_conf0.5_n_3		98.90 15	98.74 18	99.37 28	99.36 68	98.25 56	98.89 124	99.24 20	98.77 10	99.89 3	99.59 13	93.39 112	99.96 4	99.78 10	99.76 47	99.89 8

SteuartSystems-ACMMP		98.90 15	98.75 17	99.36 30	99.22 106	98.43 39	99.10 69	98.87 85	97.38 62	99.35 48	99.40 49	97.78 5	99.87 79	97.77 110	99.85 6	99.78 33
Skip Steuart: Steuart Systems R&D Blog.
test_fmvsm_n_1920		98.87 18	99.01 3	98.45 124	99.42 64	96.43 156	98.96 104	99.36 10	98.63 13	99.86 8	99.51 28	95.91 46	99.97 1	99.72 14	99.75 53	98.94 236

ME-MVS		98.83 19	98.60 24	99.52 14	99.58 37	98.86 23	98.69 199	98.93 65	97.00 91	99.17 63	99.35 62	96.62 23	99.90 64	98.30 75	99.80 25	99.79 29

TSAR-MVS + MP.		98.78 20	98.62 22	99.24 46	99.69 29	98.28 54	99.14 60	98.66 153	96.84 98	99.56 35	99.31 71	96.34 32	99.70 143	98.32 74	99.73 61	99.73 55
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CNVR-MVS		98.78 20	98.56 28	99.45 19	99.32 77	98.87 21	98.47 254	98.81 107	97.72 36	98.76 96	99.16 110	97.05 14	99.78 124	98.06 89	99.66 77	99.69 70

MSP-MVS		98.74 22	98.55 29	99.29 39	99.75 6	98.23 57	99.26 33	98.88 78	97.52 50	99.41 44	98.78 192	96.00 42	99.79 121	97.79 109	99.59 94	99.85 16
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
fmvsm_s_conf0.5_n_8		98.73 23	98.62 22	99.05 67	99.35 70	97.27 106	98.80 164	99.23 27	98.93 3	99.79 15	99.59 13	92.34 129	99.95 9	99.82 6	99.71 68	99.92 2

XVS		98.70 24	98.49 36	99.34 32	99.70 27	98.35 50	99.29 28	98.88 78	97.40 59	98.46 119	99.20 95	95.90 48	99.89 68	97.85 104	99.74 57	99.78 33

fmvsm_s_conf0.5_n_10		98.66 25	98.54 31	99.02 69	99.36 68	97.21 115	98.86 142	99.23 27	98.90 5	99.83 12	99.59 13	91.57 160	99.94 14	99.79 9	99.74 57	99.89 8

fmvsm_s_conf0.5_n_6		98.65 26	98.55 29	98.95 78	98.50 187	97.30 102	98.79 172	99.16 39	98.14 23	99.86 8	99.41 48	93.71 109	99.91 56	99.71 15	99.64 85	99.65 83

MCST-MVS		98.65 26	98.37 45	99.48 17	99.60 36	98.87 21	98.41 268	98.68 145	97.04 88	98.52 117	98.80 186	96.78 17	99.83 90	97.93 96	99.61 90	99.74 50

SD-MVS		98.64 28	98.68 19	98.53 113	99.33 74	98.36 49	98.90 120	98.85 95	97.28 69	99.72 26	99.39 50	96.63 22	97.60 446	98.17 84	99.85 6	99.64 86
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
fmvsm_s_conf0.5_n_9		98.63 29	98.66 21	98.54 110	99.40 67	95.83 203	98.79 172	99.17 37	98.94 2	99.92 1	99.61 5	92.49 124	99.93 34	99.86 1	99.76 47	99.86 13

HFP-MVS		98.63 29	98.40 42	99.32 38	99.72 17	98.29 53	99.23 38	98.96 60	96.10 141	98.94 78	99.17 107	96.06 39	99.92 43	97.62 123	99.78 39	99.75 48

ACMMP_NAP		98.61 31	98.30 60	99.55 11	99.62 35	98.95 19	98.82 155	98.81 107	95.80 157	99.16 67	99.47 37	95.37 63	99.92 43	97.89 101	99.75 53	99.79 29

region2R		98.61 31	98.38 44	99.29 39	99.74 12	98.16 63	99.23 38	98.93 65	96.15 136	98.94 78	99.17 107	95.91 46	99.94 14	97.55 135	99.79 34	99.78 33

NCCC		98.61 31	98.35 48	99.38 24	99.28 92	98.61 32	98.45 256	98.76 125	97.82 35	98.45 122	98.93 164	96.65 21	99.83 90	97.38 157	99.41 128	99.71 63

SF-MVS		98.59 34	98.32 59	99.41 23	99.54 41	98.71 27	99.04 80	98.81 107	95.12 211	99.32 51	99.39 50	96.22 33	99.84 88	97.72 113	99.73 61	99.67 79

ACMMPR		98.59 34	98.36 46	99.29 39	99.74 12	98.15 64	99.23 38	98.95 61	96.10 141	98.93 82	99.19 102	95.70 52	99.94 14	97.62 123	99.79 34	99.78 33

fmvsm_s_conf0.5_n_11		98.58 36	98.57 26	98.62 100	99.42 64	97.16 118	98.97 98	98.86 91	98.91 4	99.87 4	99.66 3	91.82 152	99.95 9	99.82 6	99.82 14	98.75 259

test_fmvsmconf0.1_n		98.58 36	98.44 40	98.99 71	97.73 307	97.15 119	98.84 151	98.97 57	98.75 11	99.43 42	99.54 20	93.29 114	99.93 34	99.64 20	99.79 34	99.89 8

SMA-MVS		98.58 36	98.25 63	99.56 9	99.51 46	99.04 17	98.95 105	98.80 114	93.67 306	99.37 47	99.52 25	96.52 26	99.89 68	98.06 89	99.81 16	99.76 47
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
MTAPA		98.58 36	98.29 61	99.46 18	99.76 5	98.64 30	98.90 120	98.74 129	97.27 73	98.02 152	99.39 50	94.81 87	99.96 4	97.91 99	99.79 34	99.77 40

HPM-MVS++		98.58 36	98.25 63	99.55 11	99.50 48	99.08 12	98.72 191	98.66 153	97.51 51	98.15 136	98.83 183	95.70 52	99.92 43	97.53 138	99.67 74	99.66 82

SR-MVS		98.57 41	98.35 48	99.24 46	99.53 42	98.18 61	99.09 70	98.82 101	96.58 114	99.10 69	99.32 69	95.39 61	99.82 97	97.70 118	99.63 87	99.72 59

CP-MVS		98.57 41	98.36 46	99.19 51	99.66 31	97.86 75	99.34 17	98.87 85	95.96 148	98.60 113	99.13 117	96.05 40	99.94 14	97.77 110	99.86 2	99.77 40

MSLP-MVS++		98.56 43	98.57 26	98.55 108	99.26 95	96.80 134	98.71 192	99.05 49	97.28 69	98.84 88	99.28 76	96.47 27	99.40 207	98.52 61	99.70 70	99.47 116

DeepC-MVS_fast	96.70 1	98.55 44	98.34 54	99.18 53	99.25 96	98.04 69	98.50 249	98.78 121	97.72 36	98.92 84	99.28 76	95.27 70	99.82 97	97.55 135	99.77 41	99.69 70
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SR-MVS-dyc-post		98.54 45	98.35 48	99.13 59	99.49 52	97.86 75	99.11 66	98.80 114	96.49 118	99.17 63	99.35 62	95.34 66	99.82 97	97.72 113	99.65 80	99.71 63

fmvsm_s_conf0.5_n_5		98.53 46	98.35 48	99.08 64	99.07 127	97.46 94	98.68 202	99.20 33	97.50 52	99.87 4	99.50 31	91.96 149	99.96 4	99.76 11	99.65 80	99.82 23

fmvsm_s_conf0.5_n_3		98.53 46	98.45 39	98.79 86	99.23 104	97.32 99	98.80 164	99.26 16	98.82 7	99.87 4	99.60 10	90.95 194	99.93 34	99.76 11	99.73 61	99.12 206

APD-MVS_3200maxsize		98.53 46	98.33 58	99.15 57	99.50 48	97.92 74	99.15 57	98.81 107	96.24 132	99.20 60	99.37 56	95.30 68	99.80 109	97.73 112	99.67 74	99.72 59

MM		98.51 49	98.24 65	99.33 36	99.12 121	98.14 66	98.93 114	97.02 428	98.96 1	99.17 63	99.47 37	91.97 148	99.94 14	99.85 5	99.69 71	99.91 4

mPP-MVS		98.51 49	98.26 62	99.25 45	99.75 6	98.04 69	99.28 30	98.81 107	96.24 132	98.35 131	99.23 87	95.46 58	99.94 14	97.42 152	99.81 16	99.77 40

ZNCC-MVS		98.49 51	98.20 71	99.35 31	99.73 16	98.39 40	99.19 50	98.86 91	95.77 159	98.31 135	99.10 125	95.46 58	99.93 34	97.57 134	99.81 16	99.74 50

SPE-MVS-test		98.49 51	98.50 34	98.46 123	99.20 109	97.05 124	99.64 4	98.50 199	97.45 58	98.88 85	99.14 114	95.25 72	99.15 261	98.83 40	99.56 106	99.20 189

PGM-MVS		98.49 51	98.23 67	99.27 44	99.72 17	98.08 68	98.99 94	99.49 5	95.43 186	99.03 70	99.32 69	95.56 55	99.94 14	96.80 191	99.77 41	99.78 33

EI-MVSNet-Vis-set		98.47 54	98.39 43	98.69 94	99.46 58	96.49 153	98.30 281	98.69 142	97.21 76	98.84 88	99.36 60	95.41 60	99.78 124	98.62 49	99.65 80	99.80 28

MVS_111021_HR		98.47 54	98.34 54	98.88 83	99.22 106	97.32 99	97.91 342	99.58 3	97.20 77	98.33 133	99.00 152	95.99 43	99.64 157	98.05 91	99.76 47	99.69 70

BridgeMVS		98.45 56	98.35 48	98.74 90	98.65 176	97.55 86	99.19 50	98.60 164	96.72 108	99.35 48	98.77 195	95.06 82	99.55 181	98.95 34	99.87 1	99.12 206

test_fmvsmvis_n_1920		98.44 57	98.51 32	98.23 146	98.33 221	96.15 171	98.97 98	99.15 41	98.55 16	98.45 122	99.55 18	94.26 100	99.97 1	99.65 18	99.66 77	98.57 284

CS-MVS		98.44 57	98.49 36	98.31 137	99.08 126	96.73 138	99.67 3	98.47 206	97.17 80	98.94 78	99.10 125	95.73 51	99.13 266	98.71 44	99.49 117	99.09 214

GST-MVS		98.43 59	98.12 75	99.34 32	99.72 17	98.38 41	99.09 70	98.82 101	95.71 163	98.73 99	99.06 141	95.27 70	99.93 34	97.07 167	99.63 87	99.72 59

fmvsm_s_conf0.5_n		98.42 60	98.51 32	98.13 164	99.30 83	95.25 243	98.85 147	99.39 7	97.94 29	99.74 21	99.62 4	92.59 123	99.91 56	99.65 18	99.52 112	99.25 182

EI-MVSNet-UG-set		98.41 61	98.34 54	98.61 102	99.45 61	96.32 163	98.28 284	98.68 145	97.17 80	98.74 97	99.37 56	95.25 72	99.79 121	98.57 52	99.54 109	99.73 55

DELS-MVS		98.40 62	98.20 71	98.99 71	99.00 135	97.66 81	97.75 364	98.89 75	97.71 38	98.33 133	98.97 154	94.97 84	99.88 77	98.42 69	99.76 47	99.42 133
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
fmvsm_s_conf0.5_n_a		98.38 63	98.42 41	98.27 139	99.09 125	95.41 229	98.86 142	99.37 9	97.69 40	99.78 17	99.61 5	92.38 127	99.91 56	99.58 23	99.43 126	99.49 112

TSAR-MVS + GP.		98.38 63	98.24 65	98.81 85	99.22 106	97.25 112	98.11 317	98.29 277	97.19 78	98.99 76	99.02 146	96.22 33	99.67 150	98.52 61	98.56 184	99.51 104

HPM-MVS_fast		98.38 63	98.13 74	99.12 61	99.75 6	97.86 75	99.44 9	98.82 101	94.46 259	98.94 78	99.20 95	95.16 77	99.74 134	97.58 130	99.85 6	99.77 40

patch_mono-2		98.36 66	98.87 7	96.82 283	99.53 42	90.68 407	98.64 212	99.29 15	97.88 30	99.19 62	99.52 25	96.80 16	99.97 1	99.11 30	99.86 2	99.82 23

HPM-MVS		98.36 66	98.10 77	99.13 59	99.74 12	97.82 80	99.53 6	98.80 114	94.63 247	98.61 112	98.97 154	95.13 79	99.77 129	97.65 121	99.83 13	99.79 29
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
fmvsm_s_conf0.5_n_4		98.35 68	98.50 34	97.90 194	99.16 115	95.08 253	98.75 177	99.24 20	98.39 19	99.81 13	99.52 25	92.35 128	99.90 64	99.74 13	99.51 114	98.71 265

APD-MVS		98.35 68	98.00 83	99.42 22	99.51 46	98.72 26	98.80 164	98.82 101	94.52 254	99.23 59	99.25 86	95.54 57	99.80 109	96.52 200	99.77 41	99.74 50
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_LR		98.34 70	98.23 67	98.67 96	99.27 93	96.90 130	97.95 335	99.58 3	97.14 83	98.44 124	99.01 150	95.03 83	99.62 164	97.91 99	99.75 53	99.50 107

PHI-MVS		98.34 70	98.06 78	99.18 53	99.15 118	98.12 67	99.04 80	99.09 44	93.32 325	98.83 91	99.10 125	96.54 24	99.83 90	97.70 118	99.76 47	99.59 94

MP-MVS		98.33 72	98.01 82	99.28 42	99.75 6	98.18 61	99.22 42	98.79 119	96.13 137	97.92 166	99.23 87	94.54 90	99.94 14	96.74 194	99.78 39	99.73 55
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MVSMamba_PlusPlus		98.31 73	98.19 73	98.67 96	98.96 141	97.36 97	99.24 36	98.57 178	94.81 235	98.99 76	98.90 171	95.22 75	99.59 167	99.15 29	99.84 11	99.07 222

MP-MVS-pluss		98.31 73	97.92 85	99.49 16	99.72 17	98.88 20	98.43 264	98.78 121	94.10 271	97.69 189	99.42 46	95.25 72	99.92 43	98.09 88	99.80 25	99.67 79
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.5_n_2		98.30 75	98.21 69	98.57 105	99.25 96	97.11 121	98.66 209	99.20 33	98.82 7	99.79 15	99.60 10	89.38 243	99.92 43	99.80 8	99.38 133	98.69 267

fmvsm_s_conf0.5_n_7		98.23 76	98.35 48	97.89 196	98.86 151	94.99 259	98.58 225	99.00 53	98.29 20	99.73 23	99.60 10	91.70 155	99.92 43	99.63 21	99.73 61	98.76 258

MGCNet		98.23 76	97.91 86	99.21 50	98.06 270	97.96 73	98.58 225	95.51 469	98.58 14	98.87 86	99.26 80	92.99 118	99.95 9	99.62 22	99.67 74	99.73 55

ACMMP		98.23 76	97.95 84	99.09 63	99.74 12	97.62 84	99.03 83	99.41 6	95.98 146	97.60 203	99.36 60	94.45 95	99.93 34	97.14 164	98.85 167	99.70 67
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
EC-MVSNet		98.21 79	98.11 76	98.49 120	98.34 217	97.26 111	99.61 5	98.43 226	96.78 101	98.87 86	98.84 179	93.72 108	99.01 294	98.91 37	99.50 115	99.19 193

fmvsm_s_conf0.1_n		98.18 80	98.21 69	98.11 169	98.54 185	95.24 244	98.87 134	99.24 20	97.50 52	99.70 27	99.67 1	91.33 172	99.89 68	99.47 25	99.54 109	99.21 188

fmvsm_s_conf0.1_n_2		98.14 81	98.02 81	98.53 113	98.88 147	97.07 123	98.69 199	98.82 101	98.78 9	99.77 18	99.61 5	88.83 265	99.91 56	99.71 15	99.07 150	98.61 277

fmvsm_s_conf0.1_n_a		98.08 82	98.04 80	98.21 147	97.66 313	95.39 234	98.89 124	99.17 37	97.24 74	99.76 20	99.67 1	91.13 184	99.88 77	99.39 26	99.41 128	99.35 148

dcpmvs_2		98.08 82	98.59 25	96.56 313	99.57 39	90.34 419	99.15 57	98.38 248	96.82 100	99.29 54	99.49 34	95.78 50	99.57 171	98.94 35	99.86 2	99.77 40

NormalMVS		98.07 84	97.90 87	98.59 104	99.75 6	96.60 144	98.94 108	98.60 164	97.86 33	98.71 102	99.08 136	91.22 179	99.80 109	97.40 154	99.57 98	99.37 143

CANet		98.05 85	97.76 90	98.90 82	98.73 161	97.27 106	98.35 271	98.78 121	97.37 64	97.72 186	98.96 159	91.53 165	99.92 43	98.79 41	99.65 80	99.51 104

train_agg		97.97 86	97.52 103	99.33 36	99.31 79	98.50 35	97.92 340	98.73 132	92.98 341	97.74 183	98.68 208	96.20 35	99.80 109	96.59 195	99.57 98	99.68 75

ETV-MVS		97.96 87	97.81 88	98.40 132	98.42 200	97.27 106	98.73 187	98.55 184	96.84 98	98.38 127	97.44 332	95.39 61	99.35 212	97.62 123	98.89 161	98.58 283

UA-Net		97.96 87	97.62 94	98.98 73	98.86 151	97.47 92	98.89 124	99.08 45	96.67 111	98.72 101	99.54 20	93.15 116	99.81 102	94.87 259	98.83 168	99.65 83

CDPH-MVS		97.94 89	97.49 105	99.28 42	99.47 56	98.44 37	97.91 342	98.67 150	92.57 358	98.77 95	98.85 178	95.93 45	99.72 137	95.56 237	99.69 71	99.68 75

DeepPCF-MVS	96.37 2	97.93 90	98.48 38	96.30 341	99.00 135	89.54 435	97.43 389	98.87 85	98.16 22	99.26 58	99.38 55	96.12 38	99.64 157	98.30 75	99.77 41	99.72 59

DeepC-MVS	95.98 3	97.88 91	97.58 96	98.77 88	99.25 96	96.93 128	98.83 153	98.75 127	96.96 93	96.89 235	99.50 31	90.46 208	99.87 79	97.84 106	99.76 47	99.52 101
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		97.86 92	97.54 102	98.83 84	95.48 441	96.83 133	98.95 105	98.60 164	98.58 14	98.93 82	99.55 18	88.57 270	99.91 56	99.54 24	99.61 90	99.77 40

DP-MVS Recon		97.86 92	97.46 108	99.06 66	99.53 42	98.35 50	98.33 273	98.89 75	92.62 355	98.05 147	98.94 162	95.34 66	99.65 154	96.04 216	99.42 127	99.19 193

CSCG		97.85 94	97.74 91	98.20 149	99.67 30	95.16 248	99.22 42	99.32 12	93.04 339	97.02 228	98.92 169	95.36 64	99.91 56	97.43 150	99.64 85	99.52 101

SymmetryMVS		97.84 95	97.58 96	98.62 100	99.01 133	96.60 144	98.94 108	98.44 215	97.86 33	98.71 102	99.08 136	91.22 179	99.80 109	97.40 154	97.53 258	99.47 116

BP-MVS1		97.82 96	97.51 104	98.76 89	98.25 237	97.39 96	99.15 57	97.68 357	96.69 109	98.47 118	99.10 125	90.29 216	99.51 187	98.60 50	99.35 136	99.37 143

MG-MVS		97.81 97	97.60 95	98.44 126	99.12 121	95.97 184	97.75 364	98.78 121	96.89 96	98.46 119	99.22 90	93.90 107	99.68 149	94.81 263	99.52 112	99.67 79

VNet		97.79 98	97.40 114	98.96 76	98.88 147	97.55 86	98.63 215	98.93 65	96.74 105	99.02 71	98.84 179	90.33 215	99.83 90	98.53 55	96.66 281	99.50 107

EIA-MVS		97.75 99	97.58 96	98.27 139	98.38 207	96.44 155	99.01 89	98.60 164	95.88 152	97.26 214	97.53 326	94.97 84	99.33 215	97.38 157	99.20 146	99.05 223

PS-MVSNAJ		97.73 100	97.77 89	97.62 227	98.68 171	95.58 217	97.34 398	98.51 194	97.29 67	98.66 109	97.88 290	94.51 91	99.90 64	97.87 103	99.17 148	97.39 330

casdiffmvs_mvg		97.72 101	97.48 107	98.44 126	98.42 200	96.59 148	98.92 117	98.44 215	96.20 134	97.76 180	99.20 95	91.66 158	99.23 244	98.27 82	98.41 207	99.49 112
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CPTT-MVS		97.72 101	97.32 121	98.92 79	99.64 33	97.10 122	99.12 64	98.81 107	92.34 366	98.09 141	99.08 136	93.01 117	99.92 43	96.06 215	99.77 41	99.75 48

PVSNet_Blended_VisFu		97.70 103	97.46 108	98.44 126	99.27 93	95.91 192	98.63 215	99.16 39	94.48 258	97.67 191	98.88 174	92.80 120	99.91 56	97.11 165	99.12 149	99.50 107

mvsany_test1		97.69 104	97.70 92	97.66 223	98.24 239	94.18 303	97.53 380	97.53 378	95.52 181	99.66 29	99.51 28	94.30 98	99.56 174	98.38 70	98.62 178	99.23 184

sasdasda		97.67 105	97.23 131	98.98 73	98.70 166	98.38 41	99.34 17	98.39 241	96.76 103	97.67 191	97.40 336	92.26 133	99.49 191	98.28 79	96.28 299	99.08 218

canonicalmvs		97.67 105	97.23 131	98.98 73	98.70 166	98.38 41	99.34 17	98.39 241	96.76 103	97.67 191	97.40 336	92.26 133	99.49 191	98.28 79	96.28 299	99.08 218

xiu_mvs_v2_base		97.66 107	97.70 92	97.56 231	98.61 180	95.46 226	97.44 386	98.46 207	97.15 82	98.65 110	98.15 265	94.33 97	99.80 109	97.84 106	98.66 177	97.41 328

GDP-MVS		97.64 108	97.28 124	98.71 93	98.30 226	97.33 98	99.05 76	98.52 191	96.34 128	98.80 92	99.05 143	89.74 230	99.51 187	96.86 187	98.86 165	99.28 172

baseline		97.64 108	97.44 110	98.25 143	98.35 212	96.20 168	99.00 91	98.32 263	96.33 130	98.03 150	99.17 107	91.35 171	99.16 257	98.10 87	98.29 218	99.39 138

casdiffmvs		97.63 110	97.41 113	98.28 138	98.33 221	96.14 172	98.82 155	98.32 263	96.38 126	97.95 161	99.21 93	91.23 178	99.23 244	98.12 86	98.37 210	99.48 114
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
cashybrid2		97.62 111	97.43 112	98.19 153	98.48 192	95.83 203	99.07 72	98.42 230	96.27 131	98.09 141	99.26 80	91.00 191	99.30 221	97.81 108	98.48 193	99.44 126

MGCFI-Net		97.62 111	97.19 135	98.92 79	98.66 173	98.20 59	99.32 22	98.38 248	96.69 109	97.58 205	97.42 335	92.10 142	99.50 190	98.28 79	96.25 302	99.08 218

xiu_mvs_v1_base_debu		97.60 113	97.56 99	97.72 212	98.35 212	95.98 179	97.86 352	98.51 194	97.13 84	99.01 73	98.40 237	91.56 161	99.80 109	98.53 55	98.68 173	97.37 332

xiu_mvs_v1_base		97.60 113	97.56 99	97.72 212	98.35 212	95.98 179	97.86 352	98.51 194	97.13 84	99.01 73	98.40 237	91.56 161	99.80 109	98.53 55	98.68 173	97.37 332

xiu_mvs_v1_base_debi		97.60 113	97.56 99	97.72 212	98.35 212	95.98 179	97.86 352	98.51 194	97.13 84	99.01 73	98.40 237	91.56 161	99.80 109	98.53 55	98.68 173	97.37 332

diffmvs_AUTHOR		97.59 116	97.44 110	98.01 182	98.26 235	95.47 225	98.12 313	98.36 254	96.38 126	98.84 88	99.10 125	91.13 184	99.26 229	98.24 83	98.56 184	99.30 163

diffmvs		97.58 117	97.40 114	98.13 164	98.32 224	95.81 207	98.06 323	98.37 250	96.20 134	98.74 97	98.89 173	91.31 174	99.25 233	98.16 85	98.52 188	99.34 150
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
guyue		97.57 118	97.37 117	98.20 149	98.50 187	95.86 200	98.89 124	97.03 425	97.29 67	98.73 99	98.90 171	89.41 242	99.32 216	98.68 45	98.86 165	99.42 133

MVSFormer		97.57 118	97.49 105	97.84 199	98.07 267	95.76 211	99.47 7	98.40 235	94.98 224	98.79 93	98.83 183	92.34 129	98.41 369	96.91 175	99.59 94	99.34 150

alignmvs		97.56 120	97.07 148	99.01 70	98.66 173	98.37 48	98.83 153	98.06 330	96.74 105	98.00 156	97.65 313	90.80 196	99.48 196	98.37 71	96.56 285	99.19 193

E3new		97.55 121	97.35 119	98.16 155	98.48 192	95.85 201	98.55 238	98.41 232	95.42 188	98.06 145	99.12 120	92.23 136	99.24 240	97.43 150	98.45 196	99.39 138

DPM-MVS		97.55 121	96.99 155	99.23 49	99.04 129	98.55 33	97.17 417	98.35 255	94.85 234	97.93 165	98.58 219	95.07 81	99.71 142	92.60 349	99.34 137	99.43 130

OMC-MVS		97.55 121	97.34 120	98.20 149	99.33 74	95.92 191	98.28 284	98.59 171	95.52 181	97.97 159	99.10 125	93.28 115	99.49 191	95.09 254	98.88 162	99.19 193

balanced_ft_v1		97.54 124	97.38 116	98.02 180	98.34 217	95.58 217	99.32 22	98.40 235	95.88 152	98.43 126	98.65 212	88.95 262	99.59 167	98.94 35	99.48 120	98.90 240

viewcassd2359sk11		97.53 125	97.32 121	98.16 155	98.45 196	95.83 203	98.57 234	98.42 230	95.52 181	98.07 143	99.12 120	91.81 153	99.25 233	97.46 148	98.48 193	99.41 136

hybridcas		97.52 126	97.29 123	98.20 149	98.44 197	96.00 177	99.02 86	98.39 241	96.12 139	97.69 189	99.23 87	90.77 201	99.17 255	97.55 135	98.42 206	99.44 126

LuminaMVS		97.49 127	97.18 136	98.42 130	97.50 328	97.15 119	98.45 256	97.68 357	96.56 117	98.68 104	98.78 192	89.84 227	99.32 216	98.60 50	98.57 183	98.79 250

E2		97.48 128	97.25 126	98.16 155	98.40 204	95.79 208	98.58 225	98.44 215	95.58 170	98.00 156	99.14 114	91.21 183	99.24 240	97.50 143	98.43 200	99.45 123

E3		97.48 128	97.25 126	98.16 155	98.38 207	95.79 208	98.58 225	98.44 215	95.58 170	98.00 156	99.14 114	91.25 177	99.24 240	97.50 143	98.44 197	99.45 123

KinetiMVS		97.48 128	97.05 150	98.78 87	98.37 210	97.30 102	98.99 94	98.70 140	97.18 79	99.02 71	99.01 150	87.50 302	99.67 150	95.33 244	99.33 139	99.37 143

viewmanbaseed2359cas		97.47 131	97.25 126	98.14 159	98.41 202	95.84 202	98.57 234	98.43 226	95.55 177	97.97 159	99.12 120	91.26 176	99.15 261	97.42 152	98.53 187	99.43 130

PAPM_NR		97.46 132	97.11 145	98.50 118	99.50 48	96.41 158	98.63 215	98.60 164	95.18 204	97.06 226	98.06 271	94.26 100	99.57 171	93.80 308	98.87 164	99.52 101

EPP-MVSNet		97.46 132	97.28 124	97.99 184	98.64 177	95.38 235	99.33 21	98.31 268	93.61 312	97.19 218	99.07 140	94.05 103	99.23 244	96.89 179	98.43 200	99.37 143

3Dnovator	94.51 5	97.46 132	96.93 159	99.07 65	97.78 301	97.64 82	99.35 16	99.06 47	97.02 89	93.75 356	99.16 110	89.25 247	99.92 43	97.22 163	99.75 53	99.64 86

CNLPA		97.45 135	97.03 152	98.73 91	99.05 128	97.44 95	98.07 322	98.53 188	95.32 197	96.80 241	98.53 224	93.32 113	99.72 137	94.31 289	99.31 141	99.02 227

lupinMVS		97.44 136	97.22 133	98.12 167	98.07 267	95.76 211	97.68 369	97.76 354	94.50 257	98.79 93	98.61 214	92.34 129	99.30 221	97.58 130	99.59 94	99.31 159

3Dnovator+	94.38 6	97.43 137	96.78 171	99.38 24	97.83 298	98.52 34	99.37 13	98.71 137	97.09 87	92.99 386	99.13 117	89.36 244	99.89 68	96.97 171	99.57 98	99.71 63

Vis-MVSNet		97.42 138	97.11 145	98.34 135	98.66 173	96.23 167	99.22 42	99.00 53	96.63 113	98.04 149	99.21 93	88.05 288	99.35 212	96.01 218	99.21 145	99.45 123
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
hybridnocas07		97.41 139	97.21 134	97.99 184	98.24 239	95.42 228	98.21 291	98.32 263	95.97 147	98.38 127	98.93 164	90.48 207	99.21 249	97.92 98	98.46 195	99.34 150

API-MVS		97.41 139	97.25 126	97.91 193	98.70 166	96.80 134	98.82 155	98.69 142	94.53 252	98.11 139	98.28 252	94.50 94	99.57 171	94.12 297	99.49 117	97.37 332

sss		97.39 141	96.98 157	98.61 102	98.60 181	96.61 143	98.22 290	98.93 65	93.97 281	98.01 155	98.48 230	91.98 146	99.85 84	96.45 202	98.15 227	99.39 138

test_cas_vis1_n_1920		97.38 142	97.36 118	97.45 236	98.95 142	93.25 346	99.00 91	98.53 188	97.70 39	99.77 18	99.35 62	84.71 358	99.85 84	98.57 52	99.66 77	99.26 180

PVSNet_Blended		97.38 142	97.12 144	98.14 159	99.25 96	95.35 238	97.28 403	99.26 16	93.13 335	97.94 163	98.21 260	92.74 121	99.81 102	96.88 181	99.40 131	99.27 173

E5new		97.37 144	97.16 138	97.98 186	98.30 226	95.41 229	98.87 134	98.45 211	95.56 172	97.84 172	99.19 102	90.39 211	99.25 233	97.61 126	98.22 222	99.29 166

E6new		97.37 144	97.16 138	97.98 186	98.28 232	95.40 232	98.87 134	98.45 211	95.55 177	97.84 172	99.20 95	90.44 209	99.25 233	97.61 126	98.22 222	99.29 166

E6		97.37 144	97.16 138	97.98 186	98.28 232	95.40 232	98.87 134	98.45 211	95.55 177	97.84 172	99.20 95	90.44 209	99.25 233	97.61 126	98.22 222	99.29 166

E5		97.37 144	97.16 138	97.98 186	98.30 226	95.41 229	98.87 134	98.45 211	95.56 172	97.84 172	99.19 102	90.39 211	99.25 233	97.61 126	98.22 222	99.29 166

E4		97.37 144	97.13 143	98.12 167	98.27 234	95.70 213	98.59 221	98.44 215	95.56 172	97.80 177	99.18 105	90.57 205	99.26 229	97.45 149	98.28 220	99.40 137

WTY-MVS		97.37 144	96.92 160	98.72 92	98.86 151	96.89 132	98.31 278	98.71 137	95.26 200	97.67 191	98.56 223	92.21 138	99.78 124	95.89 220	96.85 275	99.48 114

hybrid		97.34 150	97.16 138	97.88 197	98.25 237	95.18 247	98.18 303	98.33 260	95.36 194	98.35 131	99.06 141	90.61 203	99.18 253	97.88 102	98.40 208	99.27 173

AstraMVS		97.34 150	97.24 130	97.65 224	98.13 261	94.15 304	98.94 108	96.25 459	97.47 56	98.60 113	99.28 76	89.67 232	99.41 206	98.73 43	98.07 231	99.38 142

viewmacassd2359aftdt		97.32 152	97.07 148	98.08 172	98.30 226	95.69 214	98.62 218	98.44 215	95.56 172	97.86 171	99.22 90	89.91 225	99.14 264	97.29 160	98.43 200	99.42 133

jason		97.32 152	97.08 147	98.06 176	97.45 334	95.59 216	97.87 350	97.91 341	94.79 237	98.55 116	98.83 183	91.12 186	99.23 244	97.58 130	99.60 92	99.34 150
jason: jason.
MVS_Test		97.28 154	97.00 153	98.13 164	98.33 221	95.97 184	98.74 181	98.07 325	94.27 266	98.44 124	98.07 270	92.48 125	99.26 229	96.43 203	98.19 226	99.16 199

EPNet		97.28 154	96.87 162	98.51 115	94.98 450	96.14 172	98.90 120	97.02 428	98.28 21	95.99 277	99.11 123	91.36 170	99.89 68	96.98 170	99.19 147	99.50 107
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SSM_0404		97.26 156	97.00 153	98.03 178	98.46 194	95.99 178	98.62 218	98.44 215	94.77 238	97.24 215	98.93 164	91.22 179	99.28 226	96.54 197	98.74 172	98.84 245

mvsmamba		97.25 157	96.99 155	98.02 180	98.34 217	95.54 222	99.18 54	97.47 384	95.04 217	98.15 136	98.57 222	89.46 239	99.31 220	97.68 120	99.01 155	99.22 186

viewdifsd2359ckpt13		97.24 158	96.97 158	98.06 176	98.43 198	95.77 210	98.59 221	98.34 258	94.81 235	97.60 203	98.94 162	90.78 200	99.09 276	96.93 174	98.33 214	99.32 158

test_yl		97.22 159	96.78 171	98.54 110	98.73 161	96.60 144	98.45 256	98.31 268	94.70 241	98.02 152	98.42 235	90.80 196	99.70 143	96.81 188	96.79 277	99.34 150

DCV-MVSNet		97.22 159	96.78 171	98.54 110	98.73 161	96.60 144	98.45 256	98.31 268	94.70 241	98.02 152	98.42 235	90.80 196	99.70 143	96.81 188	96.79 277	99.34 150

IS-MVSNet		97.22 159	96.88 161	98.25 143	98.85 154	96.36 161	99.19 50	97.97 335	95.39 190	97.23 216	98.99 153	91.11 187	98.93 307	94.60 277	98.59 180	99.47 116

viewdifsd2359ckpt07		97.20 162	97.05 150	97.65 224	98.40 204	94.33 295	98.39 269	98.43 226	95.67 165	97.66 195	99.08 136	90.04 222	99.32 216	97.47 147	98.29 218	99.31 159

PLC	95.07 4	97.20 162	96.78 171	98.44 126	99.29 88	96.31 165	98.14 310	98.76 125	92.41 364	96.39 264	98.31 250	94.92 86	99.78 124	94.06 300	98.77 171	99.23 184
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		97.18 164	97.18 136	97.20 249	98.81 157	93.27 343	95.78 468	99.15 41	95.25 201	96.79 242	98.11 268	92.29 132	99.07 279	98.56 54	99.85 6	99.25 182

SSM_0407		97.17 165	96.87 162	98.08 172	98.19 248	95.90 193	98.52 241	98.44 215	94.77 238	96.75 243	98.93 164	91.22 179	99.22 248	96.54 197	98.43 200	99.10 211

LS3D		97.16 166	96.66 180	98.68 95	98.53 186	97.19 116	98.93 114	98.90 73	92.83 349	95.99 277	99.37 56	92.12 141	99.87 79	93.67 312	99.57 98	98.97 232

AdaColmap		97.15 167	96.70 176	98.48 121	99.16 115	96.69 140	98.01 329	98.89 75	94.44 260	96.83 237	98.68 208	90.69 202	99.76 130	94.36 285	99.29 142	98.98 231

viewdifsd2359ckpt09		97.13 168	96.79 169	98.14 159	98.43 198	95.90 193	98.52 241	98.37 250	94.32 264	97.33 210	98.86 177	90.23 219	99.16 257	96.81 188	98.25 221	99.36 147

Effi-MVS+		97.12 169	96.69 177	98.39 133	98.19 248	96.72 139	97.37 394	98.43 226	93.71 299	97.65 197	98.02 274	92.20 139	99.25 233	96.87 184	97.79 241	99.19 193

CHOSEN 1792x2688		97.12 169	96.80 167	98.08 172	99.30 83	94.56 284	98.05 324	99.71 1	93.57 314	97.09 222	98.91 170	88.17 282	99.89 68	96.87 184	99.56 106	99.81 25

F-COLMAP		97.09 171	96.80 167	97.97 190	99.45 61	94.95 263	98.55 238	98.62 163	93.02 340	96.17 272	98.58 219	94.01 104	99.81 102	93.95 302	98.90 160	99.14 203

RRT-MVS		97.03 172	96.78 171	97.77 208	97.90 294	94.34 293	99.12 64	98.35 255	95.87 154	98.06 145	98.70 206	86.45 321	99.63 160	98.04 92	98.54 186	99.35 148

TAMVS		97.02 173	96.79 169	97.70 215	98.06 270	95.31 241	98.52 241	98.31 268	93.95 282	97.05 227	98.61 214	93.49 111	98.52 351	95.33 244	97.81 240	99.29 166

viewmambaseed2359dif		97.01 174	96.84 164	97.51 233	98.19 248	94.21 301	98.16 306	98.23 289	93.61 312	97.78 178	99.13 117	90.79 199	99.18 253	97.24 161	98.40 208	99.15 200

dtuplus		97.00 175	96.83 166	97.51 233	98.18 254	94.21 301	98.21 291	98.20 293	94.42 262	97.66 195	99.22 90	90.18 220	99.17 255	97.01 168	98.36 212	99.13 205

CDS-MVSNet		96.99 176	96.69 177	97.90 194	98.05 272	95.98 179	98.20 295	98.33 260	93.67 306	96.95 229	98.49 229	93.54 110	98.42 362	95.24 251	97.74 245	99.31 159
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
casdiffseed414692147		96.97 177	96.55 185	98.25 143	98.26 235	96.28 166	98.93 114	98.33 260	94.99 222	96.87 236	99.09 133	88.97 260	99.07 279	95.70 233	97.77 243	99.39 138

CANet_DTU		96.96 178	96.55 185	98.21 147	98.17 258	96.07 176	97.98 333	98.21 291	97.24 74	97.13 220	98.93 164	86.88 313	99.91 56	95.00 257	99.37 135	98.66 273

114514_t		96.93 179	96.27 199	98.92 79	99.50 48	97.63 83	98.85 147	98.90 73	84.80 476	97.77 179	99.11 123	92.84 119	99.66 153	94.85 260	99.77 41	99.47 116

MAR-MVS		96.91 180	96.40 193	98.45 124	98.69 169	96.90 130	98.66 209	98.68 145	92.40 365	97.07 225	97.96 281	91.54 164	99.75 132	93.68 310	98.92 159	98.69 267
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
HyFIR lowres test		96.90 181	96.49 190	98.14 159	99.33 74	95.56 219	97.38 392	99.65 2	92.34 366	97.61 200	98.20 261	89.29 246	99.10 275	96.97 171	97.60 250	99.77 40

Vis-MVSNet (Re-imp)		96.87 182	96.55 185	97.83 200	98.73 161	95.46 226	99.20 48	98.30 275	94.96 226	96.60 252	98.87 175	90.05 221	98.59 346	93.67 312	98.60 179	99.46 121

SDMVSNet		96.85 183	96.42 191	98.14 159	99.30 83	96.38 159	99.21 45	99.23 27	95.92 149	95.96 279	98.76 200	85.88 333	99.44 203	97.93 96	95.59 314	98.60 278

PAPR		96.84 184	96.24 201	98.65 98	98.72 165	96.92 129	97.36 396	98.57 178	93.33 324	96.67 247	97.57 322	94.30 98	99.56 174	91.05 393	98.59 180	99.47 116

HY-MVS	93.96 8	96.82 185	96.23 202	98.57 105	98.46 194	97.00 125	98.14 310	98.21 291	93.95 282	96.72 246	97.99 278	91.58 159	99.76 130	94.51 281	96.54 286	98.95 235

mamba_0408		96.81 186	96.38 194	98.09 171	98.19 248	95.90 193	95.69 469	98.32 263	94.51 255	96.75 243	98.73 202	90.99 192	99.27 228	95.83 223	98.43 200	99.10 211

UGNet		96.78 187	96.30 198	98.19 153	98.24 239	95.89 198	98.88 131	98.93 65	97.39 61	96.81 240	97.84 294	82.60 387	99.90 64	96.53 199	99.49 117	98.79 250
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
IMVS_0407		96.74 188	96.64 181	97.05 264	97.99 281	92.82 360	98.45 256	98.27 278	95.16 205	97.30 211	98.79 188	91.53 165	99.06 281	94.74 265	97.54 254	99.27 173

IMVS_0403		96.74 188	96.61 182	97.12 258	97.99 281	92.82 360	98.47 254	98.27 278	95.16 205	97.13 220	98.79 188	91.44 168	99.26 229	94.74 265	97.54 254	99.27 173

PVSNet_BlendedMVS		96.73 190	96.60 183	97.12 258	99.25 96	95.35 238	98.26 287	99.26 16	94.28 265	97.94 163	97.46 329	92.74 121	99.81 102	96.88 181	93.32 352	96.20 434

SSM_04072		96.71 191	96.38 194	97.68 218	98.19 248	95.90 193	95.69 469	98.32 263	94.51 255	96.75 243	98.73 202	90.99 192	98.02 418	95.83 223	98.43 200	99.10 211

test_vis1_n_1920		96.71 191	96.84 164	96.31 340	99.11 123	89.74 428	99.05 76	98.58 176	98.08 24	99.87 4	99.37 56	78.48 426	99.93 34	99.29 27	99.69 71	99.27 173

mvs_anonymous		96.70 193	96.53 188	97.18 252	98.19 248	93.78 314	98.31 278	98.19 296	94.01 278	94.47 311	98.27 255	92.08 144	98.46 357	97.39 156	97.91 236	99.31 159

Elysia		96.64 194	96.02 211	98.51 115	98.04 274	97.30 102	98.74 181	98.60 164	95.04 217	97.91 167	98.84 179	83.59 382	99.48 196	94.20 293	99.25 143	98.75 259

StellarMVS		96.64 194	96.02 211	98.51 115	98.04 274	97.30 102	98.74 181	98.60 164	95.04 217	97.91 167	98.84 179	83.59 382	99.48 196	94.20 293	99.25 143	98.75 259

1112_ss		96.63 196	96.00 213	98.50 118	98.56 182	96.37 160	98.18 303	98.10 318	92.92 344	94.84 299	98.43 233	92.14 140	99.58 170	94.35 286	96.51 287	99.56 100

PMMVS		96.60 197	96.33 197	97.41 240	97.90 294	93.93 310	97.35 397	98.41 232	92.84 348	97.76 180	97.45 331	91.10 188	99.20 250	96.26 208	97.91 236	99.11 209

DP-MVS		96.59 198	95.93 216	98.57 105	99.34 71	96.19 170	98.70 196	98.39 241	89.45 437	94.52 309	99.35 62	91.85 150	99.85 84	92.89 337	98.88 162	99.68 75

PatchMatch-RL		96.59 198	96.03 210	98.27 139	99.31 79	96.51 152	97.91 342	99.06 47	93.72 298	96.92 233	98.06 271	88.50 275	99.65 154	91.77 375	99.00 157	98.66 273

GeoE		96.58 200	96.07 207	98.10 170	98.35 212	95.89 198	99.34 17	98.12 312	93.12 336	96.09 273	98.87 175	89.71 231	98.97 297	92.95 333	98.08 230	99.43 130

icg_test_0407_2		96.56 201	96.50 189	96.73 289	97.99 281	92.82 360	97.18 414	98.27 278	95.16 205	97.30 211	98.79 188	91.53 165	98.10 403	94.74 265	97.54 254	99.27 173

XVG-OURS		96.55 202	96.41 192	96.99 267	98.75 160	93.76 315	97.50 383	98.52 191	95.67 165	96.83 237	99.30 74	88.95 262	99.53 183	95.88 221	96.26 301	97.69 321

FIs		96.51 203	96.12 206	97.67 220	97.13 358	97.54 88	99.36 14	99.22 32	95.89 151	94.03 340	98.35 243	91.98 146	98.44 360	96.40 204	92.76 360	97.01 340

XVG-OURS-SEG-HR		96.51 203	96.34 196	97.02 266	98.77 159	93.76 315	97.79 361	98.50 199	95.45 185	96.94 230	99.09 133	87.87 293	99.55 181	96.76 193	95.83 313	97.74 318

PS-MVSNAJss		96.43 205	96.26 200	96.92 278	95.84 429	95.08 253	99.16 56	98.50 199	95.87 154	93.84 351	98.34 247	94.51 91	98.61 342	96.88 181	93.45 347	97.06 338

test_fmvs1		96.42 206	96.67 179	95.66 377	98.82 156	88.53 455	98.80 164	98.20 293	96.39 125	99.64 31	99.20 95	80.35 412	99.67 150	99.04 32	99.57 98	98.78 254

FC-MVSNet-test		96.42 206	96.05 208	97.53 232	96.95 367	97.27 106	99.36 14	99.23 27	95.83 156	93.93 343	98.37 241	92.00 145	98.32 381	96.02 217	92.72 361	97.00 341

ab-mvs		96.42 206	95.71 227	98.55 108	98.63 178	96.75 137	97.88 349	98.74 129	93.84 288	96.54 257	98.18 263	85.34 344	99.75 132	95.93 219	96.35 291	99.15 200

FA-MVS(test-final)		96.41 209	95.94 215	97.82 202	98.21 244	95.20 246	97.80 359	97.58 368	93.21 330	97.36 209	97.70 306	89.47 237	99.56 174	94.12 297	97.99 233	98.71 265

PVSNet	91.96 18	96.35 210	96.15 203	96.96 273	99.17 111	92.05 380	96.08 461	98.68 145	93.69 302	97.75 182	97.80 300	88.86 264	99.69 148	94.26 291	99.01 155	99.15 200

Test_1112_low_res		96.34 211	95.66 232	98.36 134	98.56 182	95.94 187	97.71 367	98.07 325	92.10 376	94.79 303	97.29 344	91.75 154	99.56 174	94.17 295	96.50 288	99.58 98

viewdifsd2359ckpt11		96.30 212	96.13 204	96.81 284	98.10 264	92.10 376	98.49 252	98.40 235	96.02 143	97.61 200	99.31 71	86.37 323	99.29 224	97.52 139	93.36 351	99.04 224

viewmsd2359difaftdt		96.30 212	96.13 204	96.81 284	98.10 264	92.10 376	98.49 252	98.40 235	96.02 143	97.61 200	99.31 71	86.37 323	99.30 221	97.52 139	93.37 350	99.04 224

Effi-MVS+-dtu		96.29 214	96.56 184	95.51 382	97.89 296	90.22 420	98.80 164	98.10 318	96.57 116	96.45 262	96.66 402	90.81 195	98.91 310	95.72 230	97.99 233	97.40 329

QAPM		96.29 214	95.40 238	98.96 76	97.85 297	97.60 85	99.23 38	98.93 65	89.76 431	93.11 383	99.02 146	89.11 252	99.93 34	91.99 368	99.62 89	99.34 150

Fast-Effi-MVS+		96.28 216	95.70 229	98.03 178	98.29 230	95.97 184	98.58 225	98.25 287	91.74 384	95.29 292	97.23 349	91.03 190	99.15 261	92.90 335	97.96 235	98.97 232

nrg030		96.28 216	95.72 224	97.96 192	96.90 372	98.15 64	99.39 11	98.31 268	95.47 184	94.42 317	98.35 243	92.09 143	98.69 334	97.50 143	89.05 413	97.04 339

1314		96.25 218	95.73 223	97.79 204	97.13 358	95.55 221	98.19 298	98.59 171	93.47 318	92.03 419	97.82 298	91.33 172	99.49 191	94.62 275	98.44 197	98.32 298

sd_testset		96.17 219	95.76 222	97.42 239	99.30 83	94.34 293	98.82 155	99.08 45	95.92 149	95.96 279	98.76 200	82.83 386	99.32 216	95.56 237	95.59 314	98.60 278

h-mvs33		96.17 219	95.62 233	97.81 203	99.03 130	94.45 286	98.64 212	98.75 127	97.48 54	98.67 105	98.72 205	89.76 228	99.86 83	97.95 94	81.59 466	99.11 209

HQP_MVS		96.14 221	95.90 217	96.85 281	97.42 336	94.60 282	98.80 164	98.56 182	97.28 69	95.34 288	98.28 252	87.09 308	99.03 288	96.07 212	94.27 322	96.92 348

tttt0517		96.07 222	95.51 236	97.78 205	98.41 202	94.84 267	99.28 30	94.33 486	94.26 267	97.64 198	98.64 213	84.05 373	99.47 200	95.34 243	97.60 250	99.03 226

MVSTER		96.06 223	95.72 224	97.08 262	98.23 242	95.93 190	98.73 187	98.27 278	94.86 232	95.07 294	98.09 269	88.21 281	98.54 349	96.59 195	93.46 345	96.79 367

thisisatest0530		96.01 224	95.36 243	97.97 190	98.38 207	95.52 223	98.88 131	94.19 490	94.04 273	97.64 198	98.31 250	83.82 380	99.46 201	95.29 248	97.70 247	98.93 237

test_djsdf		96.00 225	95.69 230	96.93 275	95.72 431	95.49 224	99.47 7	98.40 235	94.98 224	94.58 307	97.86 291	89.16 250	98.41 369	96.91 175	94.12 330	96.88 357

EI-MVSNet		95.96 226	95.83 219	96.36 336	97.93 292	93.70 321	98.12 313	98.27 278	93.70 301	95.07 294	99.02 146	92.23 136	98.54 349	94.68 270	93.46 345	96.84 363

VortexMVS		95.95 227	95.79 220	96.42 331	98.29 230	93.96 309	98.68 202	98.31 268	96.02 143	94.29 325	97.57 322	89.47 237	98.37 376	97.51 142	91.93 370	96.94 346

ECVR-MVS		95.95 227	95.71 227	96.65 298	99.02 131	90.86 402	99.03 83	91.80 503	96.96 93	98.10 140	99.26 80	81.31 398	99.51 187	96.90 178	99.04 152	99.59 94

BH-untuned		95.95 227	95.72 224	96.65 298	98.55 184	92.26 371	98.23 289	97.79 353	93.73 296	94.62 306	98.01 276	88.97 260	99.00 295	93.04 330	98.51 189	98.68 269

test1111		95.94 230	95.78 221	96.41 332	98.99 138	90.12 421	99.04 80	92.45 502	96.99 92	98.03 150	99.27 79	81.40 397	99.48 196	96.87 184	99.04 152	99.63 88

MSDG		95.93 231	95.30 250	97.83 200	98.90 145	95.36 236	96.83 447	98.37 250	91.32 400	94.43 316	98.73 202	90.27 217	99.60 166	90.05 407	98.82 169	98.52 286

BH-RMVSNet		95.92 232	95.32 248	97.69 216	98.32 224	94.64 276	98.19 298	97.45 389	94.56 250	96.03 275	98.61 214	85.02 349	99.12 269	90.68 398	99.06 151	99.30 163

test_fmvs1_n		95.90 233	95.99 214	95.63 378	98.67 172	88.32 459	99.26 33	98.22 290	96.40 124	99.67 28	99.26 80	73.91 468	99.70 143	99.02 33	99.50 115	98.87 242

Fast-Effi-MVS+-dtu		95.87 234	95.85 218	95.91 362	97.74 306	91.74 386	98.69 199	98.15 308	95.56 172	94.92 297	97.68 311	88.98 259	98.79 328	93.19 324	97.78 242	97.20 336

LFMVS		95.86 235	94.98 266	98.47 122	98.87 150	96.32 163	98.84 151	96.02 460	93.40 322	98.62 111	99.20 95	74.99 460	99.63 160	97.72 113	97.20 263	99.46 121

baseline1		95.84 236	95.12 258	98.01 182	98.49 191	95.98 179	98.73 187	97.03 425	95.37 193	96.22 268	98.19 262	89.96 224	99.16 257	94.60 277	87.48 430	98.90 240

OpenMVS	93.04 13	95.83 237	95.00 264	98.32 136	97.18 355	97.32 99	99.21 45	98.97 57	89.96 427	91.14 429	99.05 143	86.64 316	99.92 43	93.38 318	99.47 121	97.73 319

IMVS_0404		95.82 238	95.52 234	96.73 289	97.99 281	92.82 360	97.23 405	98.27 278	95.16 205	94.31 323	98.79 188	85.63 337	98.10 403	94.74 265	97.54 254	99.27 173

VDD-MVS		95.82 238	95.23 252	97.61 228	98.84 155	93.98 308	98.68 202	97.40 393	95.02 221	97.95 161	99.34 68	74.37 466	99.78 124	98.64 48	96.80 276	99.08 218

UniMVSNet (Re)		95.78 240	95.19 254	97.58 229	96.99 365	97.47 92	98.79 172	99.18 36	95.60 168	93.92 344	97.04 371	91.68 156	98.48 353	95.80 227	87.66 429	96.79 367

VPA-MVSNet		95.75 241	95.11 259	97.69 216	97.24 347	97.27 106	98.94 108	99.23 27	95.13 210	95.51 286	97.32 342	85.73 335	98.91 310	97.33 159	89.55 404	96.89 356

HQP-MVS		95.72 242	95.40 238	96.69 295	97.20 351	94.25 299	98.05 324	98.46 207	96.43 120	94.45 312	97.73 303	86.75 314	98.96 301	95.30 246	94.18 326	96.86 362

hse-mvs2		95.71 243	95.30 250	96.93 275	98.50 187	93.53 326	98.36 270	98.10 318	97.48 54	98.67 105	97.99 278	89.76 228	99.02 292	97.95 94	80.91 472	98.22 301

UniMVSNet_NR-MVSNet		95.71 243	95.15 255	97.40 242	96.84 375	96.97 126	98.74 181	99.24 20	95.16 205	93.88 346	97.72 305	91.68 156	98.31 383	95.81 225	87.25 435	96.92 348

PatchmatchNet		95.71 243	95.52 234	96.29 342	97.58 319	90.72 406	96.84 446	97.52 379	94.06 272	97.08 223	96.96 381	89.24 248	98.90 313	92.03 367	98.37 210	99.26 180
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
OPM-MVS		95.69 246	95.33 247	96.76 288	96.16 412	94.63 277	98.43 264	98.39 241	96.64 112	95.02 296	98.78 192	85.15 348	99.05 282	95.21 253	94.20 325	96.60 393
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMM	93.85 9	95.69 246	95.38 242	96.61 306	97.61 316	93.84 313	98.91 119	98.44 215	95.25 201	94.28 326	98.47 231	86.04 332	99.12 269	95.50 240	93.95 335	96.87 360
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpmrst		95.63 248	95.69 230	95.44 386	97.54 324	88.54 454	96.97 429	97.56 371	93.50 316	97.52 207	96.93 386	89.49 235	99.16 257	95.25 250	96.42 290	98.64 275

FE-MVS		95.62 249	94.90 270	97.78 205	98.37 210	94.92 264	97.17 417	97.38 395	90.95 411	97.73 185	97.70 306	85.32 346	99.63 160	91.18 385	98.33 214	98.79 250

LPG-MVS_test		95.62 249	95.34 244	96.47 325	97.46 331	93.54 324	98.99 94	98.54 186	94.67 245	94.36 320	98.77 195	85.39 341	99.11 271	95.71 231	94.15 328	96.76 370

CLD-MVS		95.62 249	95.34 244	96.46 328	97.52 327	93.75 317	97.27 404	98.46 207	95.53 180	94.42 317	98.00 277	86.21 327	98.97 297	96.25 210	94.37 320	96.66 385
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		95.61 252	94.89 271	97.76 209	98.15 260	95.15 250	96.77 448	94.41 484	92.95 343	97.18 219	97.43 333	84.78 355	99.45 202	94.63 273	97.73 246	98.68 269

MonoMVSNet		95.51 253	95.45 237	95.68 375	95.54 437	90.87 401	98.92 117	97.37 396	95.79 158	95.53 285	97.38 338	89.58 234	97.68 442	96.40 204	92.59 362	98.49 288

thres600view7		95.49 254	94.77 274	97.67 220	98.98 139	95.02 255	98.85 147	96.90 435	95.38 191	96.63 249	96.90 388	84.29 365	99.59 167	88.65 431	96.33 292	98.40 292

test_vis1_n		95.47 255	95.13 256	96.49 322	97.77 302	90.41 416	99.27 32	98.11 315	96.58 114	99.66 29	99.18 105	67.00 483	99.62 164	99.21 28	99.40 131	99.44 126

SCA		95.46 256	95.13 256	96.46 328	97.67 311	91.29 394	97.33 399	97.60 367	94.68 244	96.92 233	97.10 356	83.97 375	98.89 314	92.59 351	98.32 217	99.20 189

IterMVS-LS		95.46 256	95.21 253	96.22 344	98.12 262	93.72 320	98.32 277	98.13 311	93.71 299	94.26 327	97.31 343	92.24 135	98.10 403	94.63 273	90.12 395	96.84 363
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing3-2		95.45 258	95.34 244	95.77 373	98.69 169	88.75 450	98.87 134	97.21 410	96.13 137	97.22 217	97.68 311	77.95 434	99.65 154	97.58 130	96.77 279	98.91 239

jajsoiax		95.45 258	95.03 263	96.73 289	95.42 445	94.63 277	99.14 60	98.52 191	95.74 160	93.22 376	98.36 242	83.87 378	98.65 339	96.95 173	94.04 331	96.91 353

CVMVSNet		95.43 260	96.04 209	93.57 440	97.93 292	83.62 482	98.12 313	98.59 171	95.68 164	96.56 253	99.02 146	87.51 300	97.51 451	93.56 316	97.44 259	99.60 92

anonymousdsp		95.42 261	94.91 269	96.94 274	95.10 449	95.90 193	99.14 60	98.41 232	93.75 293	93.16 379	97.46 329	87.50 302	98.41 369	95.63 236	94.03 332	96.50 418

DU-MVS		95.42 261	94.76 275	97.40 242	96.53 392	96.97 126	98.66 209	98.99 56	95.43 186	93.88 346	97.69 308	88.57 270	98.31 383	95.81 225	87.25 435	96.92 348

mvs_tets		95.41 263	95.00 264	96.65 298	95.58 436	94.42 288	99.00 91	98.55 184	95.73 162	93.21 377	98.38 240	83.45 384	98.63 340	97.09 166	94.00 333	96.91 353

thres100view900		95.38 264	94.70 279	97.41 240	98.98 139	94.92 264	98.87 134	96.90 435	95.38 191	96.61 251	96.88 389	84.29 365	99.56 174	88.11 434	96.29 296	97.76 316

thres400		95.38 264	94.62 283	97.65 224	98.94 143	94.98 260	98.68 202	96.93 433	95.33 195	96.55 255	96.53 408	84.23 369	99.56 174	88.11 434	96.29 296	98.40 292

BH-w/o		95.38 264	95.08 261	96.26 343	98.34 217	91.79 383	97.70 368	97.43 391	92.87 347	94.24 329	97.22 350	88.66 268	98.84 320	91.55 381	97.70 247	98.16 305

VDDNet		95.36 267	94.53 288	97.86 198	98.10 264	95.13 251	98.85 147	97.75 355	90.46 418	98.36 129	99.39 50	73.27 470	99.64 157	97.98 93	96.58 284	98.81 248

TAPA-MVS	93.98 7	95.35 268	94.56 287	97.74 211	99.13 119	94.83 269	98.33 273	98.64 158	86.62 463	96.29 266	98.61 214	94.00 105	99.29 224	80.00 482	99.41 128	99.09 214
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ACMP	93.49 10	95.34 269	94.98 266	96.43 330	97.67 311	93.48 328	98.73 187	98.44 215	94.94 230	92.53 400	98.53 224	84.50 364	99.14 264	95.48 241	94.00 333	96.66 385
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
COLMAP_ROB	93.27 12	95.33 270	94.87 272	96.71 292	99.29 88	93.24 347	98.58 225	98.11 315	89.92 428	93.57 361	99.10 125	86.37 323	99.79 121	90.78 396	98.10 229	97.09 337
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
UBG		95.32 271	94.72 278	97.13 256	98.05 272	93.26 344	97.87 350	97.20 413	94.96 226	96.18 271	95.66 446	80.97 404	99.35 212	94.47 283	97.08 266	98.78 254

tfpn200view9		95.32 271	94.62 283	97.43 238	98.94 143	94.98 260	98.68 202	96.93 433	95.33 195	96.55 255	96.53 408	84.23 369	99.56 174	88.11 434	96.29 296	97.76 316

Anonymous202405211		95.28 273	94.49 290	97.67 220	99.00 135	93.75 317	98.70 196	97.04 424	90.66 414	96.49 259	98.80 186	78.13 430	99.83 90	96.21 211	95.36 318	99.44 126

thres200		95.25 274	94.57 286	97.28 246	98.81 157	94.92 264	98.20 295	97.11 417	95.24 203	96.54 257	96.22 423	84.58 362	99.53 183	87.93 440	96.50 288	97.39 330

AllTest		95.24 275	94.65 282	96.99 267	99.25 96	93.21 348	98.59 221	98.18 299	91.36 396	93.52 363	98.77 195	84.67 359	99.72 137	89.70 414	97.87 238	98.02 310

LCM-MVSNet-Re		95.22 276	95.32 248	94.91 404	98.18 254	87.85 465	98.75 177	95.66 467	95.11 212	88.96 452	96.85 392	90.26 218	97.65 443	95.65 235	98.44 197	99.22 186

EPNet_dtu		95.21 277	94.95 268	95.99 355	96.17 410	90.45 414	98.16 306	97.27 405	96.77 102	93.14 382	98.33 248	90.34 214	98.42 362	85.57 456	98.81 170	99.09 214
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
XXY-MVS		95.20 278	94.45 296	97.46 235	96.75 382	96.56 150	98.86 142	98.65 157	93.30 327	93.27 375	98.27 255	84.85 353	98.87 317	94.82 262	91.26 381	96.96 343

D2MVS		95.18 279	95.08 261	95.48 383	97.10 360	92.07 379	98.30 281	99.13 43	94.02 275	92.90 387	96.73 398	89.48 236	98.73 332	94.48 282	93.60 344	95.65 449

WR-MVS		95.15 280	94.46 293	97.22 248	96.67 387	96.45 154	98.21 291	98.81 107	94.15 269	93.16 379	97.69 308	87.51 300	98.30 385	95.29 248	88.62 419	96.90 355

TranMVSNet+NR-MVSNet		95.14 281	94.48 291	97.11 260	96.45 399	96.36 161	99.03 83	99.03 50	95.04 217	93.58 360	97.93 284	88.27 280	98.03 417	94.13 296	86.90 440	96.95 345

myMVS_eth3d28		95.12 282	94.62 283	96.64 302	98.17 258	92.17 372	98.02 328	97.32 399	95.41 189	96.22 268	96.05 429	78.01 432	99.13 266	95.22 252	97.16 264	98.60 278

baseline2		95.11 283	94.52 289	96.87 280	96.65 388	93.56 323	98.27 286	94.10 492	93.45 319	92.02 420	97.43 333	87.45 305	99.19 251	93.88 305	97.41 261	97.87 314

miper_enhance_ethall		95.10 284	94.75 276	96.12 348	97.53 326	93.73 319	96.61 454	98.08 323	92.20 374	93.89 345	96.65 404	92.44 126	98.30 385	94.21 292	91.16 382	96.34 427

Anonymous20240529		95.10 284	94.22 308	97.75 210	99.01 133	94.26 298	98.87 134	98.83 98	85.79 471	96.64 248	98.97 154	78.73 423	99.85 84	96.27 207	94.89 319	99.12 206

test-LLR		95.10 284	94.87 272	95.80 370	96.77 379	89.70 430	96.91 435	95.21 473	95.11 212	94.83 301	95.72 442	87.71 295	98.97 297	93.06 328	98.50 190	98.72 262

dtuonly		95.08 287	95.10 260	95.02 400	96.53 392	87.27 469	96.33 460	97.21 410	93.41 321	96.28 267	98.51 228	87.71 295	98.99 296	91.88 372	98.01 232	98.80 249

WR-MVS_H		95.05 288	94.46 293	96.81 284	96.86 374	95.82 206	99.24 36	99.24 20	93.87 287	92.53 400	96.84 393	90.37 213	98.24 391	93.24 322	87.93 425	96.38 426

miper_ehance_all_eth		95.01 289	94.69 280	95.97 359	97.70 309	93.31 340	97.02 427	98.07 325	92.23 371	93.51 365	96.96 381	91.85 150	98.15 398	93.68 310	91.16 382	96.44 424

testing11		95.00 290	94.28 303	97.16 254	97.96 289	93.36 337	98.09 320	97.06 423	94.94 230	95.33 291	96.15 425	76.89 447	99.40 207	95.77 229	96.30 295	98.72 262

ADS-MVSNet		95.00 290	94.45 296	96.63 303	98.00 279	91.91 382	96.04 462	97.74 356	90.15 424	96.47 260	96.64 405	87.89 291	98.96 301	90.08 405	97.06 267	99.02 227

VPNet		94.99 292	94.19 310	97.40 242	97.16 356	96.57 149	98.71 192	98.97 57	95.67 165	94.84 299	98.24 259	80.36 411	98.67 338	96.46 201	87.32 434	96.96 343

EPMVS		94.99 292	94.48 291	96.52 319	97.22 349	91.75 385	97.23 405	91.66 504	94.11 270	97.28 213	96.81 395	85.70 336	98.84 320	93.04 330	97.28 262	98.97 232

testing91		94.98 294	94.25 307	97.20 249	97.94 290	93.41 331	98.00 331	97.58 368	94.99 222	95.45 287	96.04 430	77.20 442	99.42 205	94.97 258	96.02 309	98.78 254

NR-MVSNet		94.98 294	94.16 313	97.44 237	96.53 392	97.22 114	98.74 181	98.95 61	94.96 226	89.25 450	97.69 308	89.32 245	98.18 395	94.59 279	87.40 432	96.92 348

FMVSNet3		94.97 296	94.26 306	97.11 260	98.18 254	96.62 141	98.56 237	98.26 286	93.67 306	94.09 336	97.10 356	84.25 367	98.01 419	92.08 363	92.14 367	96.70 379

usedtu_dtu_shiyan1		94.96 297	94.28 303	96.98 270	95.93 423	96.11 174	97.08 423	98.39 241	93.62 310	93.86 348	96.40 414	88.28 278	98.21 392	92.61 346	92.36 365	96.63 387

FE-MVSNET3		94.96 297	94.28 303	96.98 270	95.93 423	96.11 174	97.08 423	98.39 241	93.62 310	93.86 348	96.40 414	88.28 278	98.21 392	92.61 346	92.36 365	96.63 387

CostFormer		94.95 299	94.73 277	95.60 380	97.28 345	89.06 443	97.53 380	96.89 437	89.66 433	96.82 239	96.72 399	86.05 330	98.95 306	95.53 239	96.13 307	98.79 250

PAPM		94.95 299	94.00 326	97.78 205	97.04 362	95.65 215	96.03 464	98.25 287	91.23 405	94.19 332	97.80 300	91.27 175	98.86 319	82.61 473	97.61 249	98.84 245

CP-MVSNet		94.94 301	94.30 302	96.83 282	96.72 384	95.56 219	99.11 66	98.95 61	93.89 285	92.42 406	97.90 287	87.19 307	98.12 402	94.32 288	88.21 422	96.82 366

TR-MVS		94.94 301	94.20 309	97.17 253	97.75 303	94.14 305	97.59 377	97.02 428	92.28 370	95.75 283	97.64 316	83.88 377	98.96 301	89.77 411	96.15 306	98.40 292

RPSCF		94.87 303	95.40 238	93.26 446	98.89 146	82.06 489	98.33 273	98.06 330	90.30 423	96.56 253	99.26 80	87.09 308	99.49 191	93.82 307	96.32 293	98.24 299

testing99		94.83 304	94.08 318	97.07 263	97.94 290	93.13 350	98.10 319	97.17 415	94.86 232	95.34 288	96.00 434	76.31 450	99.40 207	95.08 255	95.90 310	98.68 269

GA-MVS		94.81 305	94.03 322	97.14 255	97.15 357	93.86 312	96.76 449	97.58 368	94.00 279	94.76 305	97.04 371	80.91 405	98.48 353	91.79 374	96.25 302	99.09 214

c3_l		94.79 306	94.43 298	95.89 364	97.75 303	93.12 352	97.16 419	98.03 332	92.23 371	93.46 369	97.05 370	91.39 169	98.01 419	93.58 315	89.21 411	96.53 409

V42		94.78 307	94.14 315	96.70 294	96.33 404	95.22 245	98.97 98	98.09 322	92.32 368	94.31 323	97.06 367	88.39 276	98.55 348	92.90 335	88.87 417	96.34 427

reproduce_monomvs		94.77 308	94.67 281	95.08 398	98.40 204	89.48 436	98.80 164	98.64 158	97.57 48	93.21 377	97.65 313	80.57 410	98.83 323	97.72 113	89.47 407	96.93 347

CR-MVSNet		94.76 309	94.15 314	96.59 309	97.00 363	93.43 329	94.96 482	97.56 371	92.46 359	96.93 231	96.24 419	88.15 283	97.88 433	87.38 443	96.65 282	98.46 290

v2v482		94.69 310	94.03 322	96.65 298	96.17 410	94.79 272	98.67 207	98.08 323	92.72 351	94.00 341	97.16 353	87.69 299	98.45 358	92.91 334	88.87 417	96.72 375

pmmvs4		94.69 310	93.99 328	96.81 284	95.74 430	95.94 187	97.40 390	97.67 360	90.42 420	93.37 372	97.59 320	89.08 253	98.20 394	92.97 332	91.67 375	96.30 430

cl22		94.68 312	94.19 310	96.13 347	98.11 263	93.60 322	96.94 431	98.31 268	92.43 363	93.32 374	96.87 391	86.51 317	98.28 389	94.10 299	91.16 382	96.51 416

eth_miper_zixun_eth		94.68 312	94.41 299	95.47 384	97.64 314	91.71 387	96.73 451	98.07 325	92.71 352	93.64 357	97.21 351	90.54 206	98.17 396	93.38 318	89.76 399	96.54 407

PCF-MVS	93.45 11	94.68 312	93.43 364	98.42 130	98.62 179	96.77 136	95.48 475	98.20 293	84.63 477	93.34 373	98.32 249	88.55 273	99.81 102	84.80 465	98.96 158	98.68 269
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS		94.67 315	93.54 359	98.08 172	96.88 373	96.56 150	98.19 298	98.50 199	78.05 495	92.69 394	98.02 274	91.07 189	99.63 160	90.09 404	98.36 212	98.04 309

PS-CasMVS		94.67 315	93.99 328	96.71 292	96.68 386	95.26 242	99.13 63	99.03 50	93.68 304	92.33 410	97.95 282	85.35 343	98.10 403	93.59 314	88.16 424	96.79 367

cascas		94.63 317	93.86 338	96.93 275	96.91 371	94.27 297	96.00 465	98.51 194	85.55 473	94.54 308	96.23 421	84.20 371	98.87 317	95.80 227	96.98 272	97.66 322

tpmvs		94.60 318	94.36 301	95.33 390	97.46 331	88.60 453	96.88 443	97.68 357	91.29 402	93.80 353	96.42 413	88.58 269	99.24 240	91.06 391	96.04 308	98.17 304

LTVRE_ROB	92.95 15	94.60 318	93.90 334	96.68 296	97.41 339	94.42 288	98.52 241	98.59 171	91.69 387	91.21 428	98.35 243	84.87 352	99.04 285	91.06 391	93.44 348	96.60 393
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
v1144		94.59 320	93.92 331	96.60 308	96.21 406	94.78 273	98.59 221	98.14 310	91.86 383	94.21 331	97.02 374	87.97 289	98.41 369	91.72 376	89.57 402	96.61 391

ADS-MVSNet2		94.58 321	94.40 300	95.11 396	98.00 279	88.74 451	96.04 462	97.30 401	90.15 424	96.47 260	96.64 405	87.89 291	97.56 449	90.08 405	97.06 267	99.02 227

WBMVS		94.56 322	94.04 320	96.10 349	98.03 276	93.08 354	97.82 358	98.18 299	94.02 275	93.77 355	96.82 394	81.28 399	98.34 378	95.47 242	91.00 385	96.88 357

ACMH	92.88 16	94.55 323	93.95 330	96.34 338	97.63 315	93.26 344	98.81 163	98.49 204	93.43 320	89.74 444	98.53 224	81.91 391	99.08 278	93.69 309	93.30 353	96.70 379
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		94.54 324	93.85 339	96.63 303	97.98 287	93.06 355	98.77 176	97.84 344	93.67 306	93.80 353	98.04 273	76.88 448	98.96 301	94.79 264	92.86 358	97.86 315

XVG-ACMP-BASELINE		94.54 324	94.14 315	95.75 374	96.55 391	91.65 388	98.11 317	98.44 215	94.96 226	94.22 330	97.90 287	79.18 421	99.11 271	94.05 301	93.85 337	96.48 421

AUN-MVS		94.53 326	93.73 349	96.92 278	98.50 187	93.52 327	98.34 272	98.10 318	93.83 290	95.94 281	97.98 280	85.59 339	99.03 288	94.35 286	80.94 471	98.22 301

DIV-MVS_self_test		94.52 327	94.03 322	95.99 355	97.57 323	93.38 335	97.05 425	97.94 338	91.74 384	92.81 389	97.10 356	89.12 251	98.07 411	92.60 349	90.30 392	96.53 409

cl____		94.51 328	94.01 325	96.02 351	97.58 319	93.40 334	97.05 425	97.96 337	91.73 386	92.76 391	97.08 362	89.06 254	98.13 400	92.61 346	90.29 393	96.52 412

ETVMVS		94.50 329	93.44 363	97.68 218	98.18 254	95.35 238	98.19 298	97.11 417	93.73 296	96.40 263	95.39 449	74.53 463	98.84 320	91.10 387	96.31 294	98.84 245

GBi-Net		94.49 330	93.80 342	96.56 313	98.21 244	95.00 256	98.82 155	98.18 299	92.46 359	94.09 336	97.07 363	81.16 400	97.95 424	92.08 363	92.14 367	96.72 375

test1		94.49 330	93.80 342	96.56 313	98.21 244	95.00 256	98.82 155	98.18 299	92.46 359	94.09 336	97.07 363	81.16 400	97.95 424	92.08 363	92.14 367	96.72 375

dmvs_re		94.48 332	94.18 312	95.37 388	97.68 310	90.11 422	98.54 240	97.08 419	94.56 250	94.42 317	97.24 348	84.25 367	97.76 439	91.02 394	92.83 359	98.24 299

v8		94.47 333	93.77 345	96.57 312	96.36 402	94.83 269	99.05 76	98.19 296	91.92 380	93.16 379	96.97 379	88.82 267	98.48 353	91.69 377	87.79 426	96.39 425

FMVSNet2		94.47 333	93.61 355	97.04 265	98.21 244	96.43 156	98.79 172	98.27 278	92.46 359	93.50 366	97.09 360	81.16 400	98.00 421	91.09 388	91.93 370	96.70 379

test2506		94.44 335	93.91 333	96.04 350	99.02 131	88.99 446	99.06 74	79.47 518	96.96 93	98.36 129	99.26 80	77.21 441	99.52 186	96.78 192	99.04 152	99.59 94

Patchmatch-test		94.42 336	93.68 353	96.63 303	97.60 317	91.76 384	94.83 486	97.49 383	89.45 437	94.14 334	97.10 356	88.99 256	98.83 323	85.37 459	98.13 228	99.29 166

PEN-MVS		94.42 336	93.73 349	96.49 322	96.28 405	94.84 267	99.17 55	99.00 53	93.51 315	92.23 412	97.83 297	86.10 329	97.90 428	92.55 354	86.92 439	96.74 372

v144192		94.39 338	93.70 351	96.48 324	96.06 416	94.35 292	98.58 225	98.16 307	91.45 393	94.33 322	97.02 374	87.50 302	98.45 358	91.08 390	89.11 412	96.63 387

Baseline_NR-MVSNet		94.35 339	93.81 341	95.96 360	96.20 407	94.05 307	98.61 220	96.67 448	91.44 394	93.85 350	97.60 319	88.57 270	98.14 399	94.39 284	86.93 438	95.68 448

miper_lstm_enhance		94.33 340	94.07 319	95.11 396	97.75 303	90.97 398	97.22 407	98.03 332	91.67 388	92.76 391	96.97 379	90.03 223	97.78 438	92.51 356	89.64 401	96.56 404

v1192		94.32 341	93.58 356	96.53 318	96.10 414	94.45 286	98.50 249	98.17 305	91.54 391	94.19 332	97.06 367	86.95 312	98.43 361	90.14 403	89.57 402	96.70 379

UWE-MVS		94.30 342	93.89 336	95.53 381	97.83 298	88.95 447	97.52 382	93.25 495	94.44 260	96.63 249	97.07 363	78.70 424	99.28 226	91.99 368	97.56 253	98.36 295

ACMH+	92.99 14	94.30 342	93.77 345	95.88 365	97.81 300	92.04 381	98.71 192	98.37 250	93.99 280	90.60 435	98.47 231	80.86 407	99.05 282	92.75 342	92.40 364	96.55 406

v148		94.29 344	93.76 347	95.91 362	96.10 414	92.93 358	98.58 225	97.97 335	92.59 357	93.47 368	96.95 383	88.53 274	98.32 381	92.56 353	87.06 437	96.49 419

v10		94.29 344	93.55 358	96.51 320	96.39 401	94.80 271	98.99 94	98.19 296	91.35 398	93.02 385	96.99 377	88.09 285	98.41 369	90.50 400	88.41 421	96.33 429

SD_0403		94.28 346	94.46 293	93.73 437	98.02 277	85.32 477	98.31 278	98.40 235	94.75 240	93.59 358	98.16 264	89.01 255	96.54 470	82.32 474	97.58 252	99.34 150

MVP-Stereo		94.28 346	93.92 331	95.35 389	94.95 451	92.60 366	97.97 334	97.65 361	91.61 389	90.68 434	97.09 360	86.32 326	98.42 362	89.70 414	99.34 137	95.02 463
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UniMVSNet_ETH3D		94.24 348	93.33 366	96.97 272	97.19 354	93.38 335	98.74 181	98.57 178	91.21 407	93.81 352	98.58 219	72.85 472	98.77 330	95.05 256	93.93 336	98.77 257

OurMVSNet-221017-0		94.21 349	94.00 326	94.85 409	95.60 435	89.22 441	98.89 124	97.43 391	95.29 198	92.18 415	98.52 227	82.86 385	98.59 346	93.46 317	91.76 373	96.74 372

v1921920		94.20 350	93.47 362	96.40 334	95.98 420	94.08 306	98.52 241	98.15 308	91.33 399	94.25 328	97.20 352	86.41 322	98.42 362	90.04 408	89.39 409	96.69 384

WB-MVSnew		94.19 351	94.04 320	94.66 417	96.82 377	92.14 373	97.86 352	95.96 463	93.50 316	95.64 284	96.77 397	88.06 287	97.99 422	84.87 462	96.86 273	93.85 485

v7n		94.19 351	93.43 364	96.47 325	95.90 426	94.38 291	99.26 33	98.34 258	91.99 378	92.76 391	97.13 355	88.31 277	98.52 351	89.48 419	87.70 427	96.52 412

tpm2		94.19 351	93.76 347	95.46 385	97.23 348	89.04 444	97.31 401	96.85 441	87.08 456	96.21 270	96.79 396	83.75 381	98.74 331	92.43 359	96.23 304	98.59 281

TESTMET0.1,1		94.18 354	93.69 352	95.63 378	96.92 369	89.12 442	96.91 435	94.78 481	93.17 332	94.88 298	96.45 412	78.52 425	98.92 308	93.09 327	98.50 190	98.85 243

dp		94.15 355	93.90 334	94.90 405	97.31 344	86.82 471	96.97 429	97.19 414	91.22 406	96.02 276	96.61 407	85.51 340	99.02 292	90.00 409	94.30 321	98.85 243

ET-MVSNet_ETH3D		94.13 356	92.98 374	97.58 229	98.22 243	96.20 168	97.31 401	95.37 471	94.53 252	79.56 495	97.63 318	86.51 317	97.53 450	96.91 175	90.74 387	99.02 227

tpm		94.13 356	93.80 342	95.12 395	96.50 395	87.91 464	97.44 386	95.89 466	92.62 355	96.37 265	96.30 418	84.13 372	98.30 385	93.24 322	91.66 376	99.14 203

testing222		94.12 358	93.03 373	97.37 245	98.02 277	94.66 274	97.94 338	96.65 450	94.63 247	95.78 282	95.76 437	71.49 473	98.92 308	91.17 386	95.88 311	98.52 286

IterMVS-SCA-FT		94.11 359	93.87 337	94.85 409	97.98 287	90.56 413	97.18 414	98.11 315	93.75 293	92.58 397	97.48 328	83.97 375	97.41 453	92.48 358	91.30 379	96.58 400

Anonymous20231211		94.10 360	93.26 369	96.61 306	99.11 123	94.28 296	99.01 89	98.88 78	86.43 465	92.81 389	97.57 322	81.66 396	98.68 337	94.83 261	89.02 415	96.88 357

IterMVS		94.09 361	93.85 339	94.80 413	97.99 281	90.35 418	97.18 414	98.12 312	93.68 304	92.46 404	97.34 339	84.05 373	97.41 453	92.51 356	91.33 378	96.62 390
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test-mter		94.08 362	93.51 360	95.80 370	96.77 379	89.70 430	96.91 435	95.21 473	92.89 346	94.83 301	95.72 442	77.69 436	98.97 297	93.06 328	98.50 190	98.72 262

test0.0.03 1		94.08 362	93.51 360	95.80 370	95.53 439	92.89 359	97.38 392	95.97 462	95.11 212	92.51 402	96.66 402	87.71 295	96.94 460	87.03 446	93.67 340	97.57 326

v1240		94.06 364	93.29 368	96.34 338	96.03 418	93.90 311	98.44 262	98.17 305	91.18 408	94.13 335	97.01 376	86.05 330	98.42 362	89.13 425	89.50 406	96.70 379

X-MVStestdata		94.06 364	92.30 390	99.34 32	99.70 27	98.35 50	99.29 28	98.88 78	97.40 59	98.46 119	43.50 540	95.90 48	99.89 68	97.85 104	99.74 57	99.78 33

DTE-MVSNet		93.98 366	93.26 369	96.14 346	96.06 416	94.39 290	99.20 48	98.86 91	93.06 338	91.78 421	97.81 299	85.87 334	97.58 448	90.53 399	86.17 444	96.46 423

pm-mvs1		93.94 367	93.06 372	96.59 309	96.49 396	95.16 248	98.95 105	98.03 332	92.32 368	91.08 430	97.84 294	84.54 363	98.41 369	92.16 361	86.13 447	96.19 435

MS-PatchMatch		93.84 368	93.63 354	94.46 427	96.18 409	89.45 437	97.76 363	98.27 278	92.23 371	92.13 417	97.49 327	79.50 418	98.69 334	89.75 412	99.38 133	95.25 455

tfpnnormal		93.66 369	92.70 380	96.55 317	96.94 368	95.94 187	98.97 98	99.19 35	91.04 409	91.38 427	97.34 339	84.94 351	98.61 342	85.45 458	89.02 415	95.11 459

EU-MVSNet		93.66 369	94.14 315	92.25 459	95.96 422	83.38 484	98.52 241	98.12 312	94.69 243	92.61 396	98.13 267	87.36 306	96.39 475	91.82 373	90.00 397	96.98 342

our_test_3		93.65 371	93.30 367	94.69 415	95.45 443	89.68 432	96.91 435	97.65 361	91.97 379	91.66 424	96.88 389	89.67 232	97.93 427	88.02 438	91.49 377	96.48 421

pmmvs5		93.65 371	92.97 375	95.68 375	95.49 440	92.37 368	98.20 295	97.28 404	89.66 433	92.58 397	97.26 345	82.14 390	98.09 407	93.18 325	90.95 386	96.58 400

SSC-MVS3.2		93.59 373	93.13 371	94.97 402	96.81 378	89.71 429	97.95 335	98.49 204	94.59 249	93.50 366	96.91 387	77.74 435	98.37 376	91.69 377	90.47 390	96.83 365

test_fmvs2		93.43 374	93.58 356	92.95 452	96.97 366	83.91 481	99.19 50	97.24 407	95.74 160	95.20 293	98.27 255	69.65 475	98.72 333	96.26 208	93.73 339	96.24 432

tpm cat1		93.36 375	92.80 377	95.07 399	97.58 319	87.97 463	96.76 449	97.86 343	82.17 484	93.53 362	96.04 430	86.13 328	99.13 266	89.24 423	95.87 312	98.10 307

JIA-IIPM		93.35 376	92.49 386	95.92 361	96.48 397	90.65 408	95.01 480	96.96 431	85.93 469	96.08 274	87.33 505	87.70 298	98.78 329	91.35 383	95.58 316	98.34 296

SixPastTwentyTwo		93.34 377	92.86 376	94.75 414	95.67 432	89.41 439	98.75 177	96.67 448	93.89 285	90.15 441	98.25 258	80.87 406	98.27 390	90.90 395	90.64 388	96.57 402

USDC		93.33 378	92.71 379	95.21 392	96.83 376	90.83 404	96.91 435	97.50 381	93.84 288	90.72 433	98.14 266	77.69 436	98.82 325	89.51 418	93.21 355	95.97 441

IB-MVS	91.98 17	93.27 379	91.97 394	97.19 251	97.47 330	93.41 331	97.09 422	95.99 461	93.32 325	92.47 403	95.73 440	78.06 431	99.53 183	94.59 279	82.98 459	98.62 276
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
MIMVSNet		93.26 380	92.21 391	96.41 332	97.73 307	93.13 350	95.65 471	97.03 425	91.27 404	94.04 339	96.06 428	75.33 456	97.19 456	86.56 449	96.23 304	98.92 238

ppachtmachnet_test		93.22 381	92.63 381	94.97 402	95.45 443	90.84 403	96.88 443	97.88 342	90.60 415	92.08 418	97.26 345	88.08 286	97.86 434	85.12 461	90.33 391	96.22 433

Patchmtry		93.22 381	92.35 389	95.84 369	96.77 379	93.09 353	94.66 489	97.56 371	87.37 455	92.90 387	96.24 419	88.15 283	97.90 428	87.37 444	90.10 396	96.53 409

testing3		93.19 383	92.48 387	95.30 391	98.07 267	92.27 369	98.64 212	97.17 415	93.94 284	93.98 342	97.04 371	67.97 480	96.01 479	88.40 432	97.14 265	97.63 323

FMVSNet1		93.19 383	92.07 392	96.56 313	97.54 324	95.00 256	98.82 155	98.18 299	90.38 421	92.27 411	97.07 363	73.68 469	97.95 424	89.36 421	91.30 379	96.72 375

LF4IMVS		93.14 385	92.79 378	94.20 432	95.88 427	88.67 452	97.66 371	97.07 421	93.81 291	91.71 422	97.65 313	77.96 433	98.81 326	91.47 382	91.92 372	95.12 458

mmtdpeth		93.12 386	92.61 382	94.63 419	97.60 317	89.68 432	99.21 45	97.32 399	94.02 275	97.72 186	94.42 460	77.01 446	99.44 203	99.05 31	77.18 484	94.78 468

testgi		93.06 387	92.45 388	94.88 407	96.43 400	89.90 424	98.75 177	97.54 377	95.60 168	91.63 425	97.91 286	74.46 465	97.02 458	86.10 452	93.67 340	97.72 320

PatchT		93.06 387	91.97 394	96.35 337	96.69 385	92.67 365	94.48 493	97.08 419	86.62 463	97.08 223	92.23 487	87.94 290	97.90 428	78.89 488	96.69 280	98.49 288

RPMNet		92.81 389	91.34 400	97.24 247	97.00 363	93.43 329	94.96 482	98.80 114	82.27 483	96.93 231	92.12 488	86.98 311	99.82 97	76.32 495	96.65 282	98.46 290

UWE-MVS-28		92.79 390	92.51 385	93.62 439	96.46 398	86.28 472	97.93 339	92.71 500	94.17 268	94.78 304	97.16 353	81.05 403	96.43 473	81.45 477	96.86 273	98.14 306

myMVS_eth3d		92.73 391	92.01 393	94.89 406	97.39 340	90.94 399	97.91 342	97.46 385	93.16 333	93.42 370	95.37 450	68.09 479	96.12 477	88.34 433	96.99 269	97.60 324

TransMVSNet (Re)		92.67 392	91.51 399	96.15 345	96.58 390	94.65 275	98.90 120	96.73 444	90.86 412	89.46 449	97.86 291	85.62 338	98.09 407	86.45 450	81.12 469	95.71 447

ttmdpeth		92.61 393	91.96 396	94.55 421	94.10 463	90.60 412	98.52 241	97.29 402	92.67 353	90.18 439	97.92 285	79.75 416	97.79 436	91.09 388	86.15 446	95.26 454

Syy-MVS		92.55 394	92.61 382	92.38 455	97.39 340	83.41 483	97.91 342	97.46 385	93.16 333	93.42 370	95.37 450	84.75 356	96.12 477	77.00 494	96.99 269	97.60 324

K. test v3		92.55 394	91.91 397	94.48 425	95.64 433	89.24 440	99.07 72	94.88 480	94.04 273	86.78 469	97.59 320	77.64 439	97.64 444	92.08 363	89.43 408	96.57 402

DSMNet-mixed		92.52 396	92.58 384	92.33 456	94.15 461	82.65 487	98.30 281	94.26 488	89.08 443	92.65 395	95.73 440	85.01 350	95.76 481	86.24 451	97.76 244	98.59 281

TinyColmap		92.31 397	91.53 398	94.65 418	96.92 369	89.75 427	96.92 433	96.68 447	90.45 419	89.62 446	97.85 293	76.06 453	98.81 326	86.74 447	92.51 363	95.41 452

gg-mvs-nofinetune		92.21 398	90.58 407	97.13 256	96.75 382	95.09 252	95.85 466	89.40 510	85.43 474	94.50 310	81.98 511	80.80 408	98.40 375	92.16 361	98.33 214	97.88 313

FMVSNet5		91.81 399	90.92 403	94.49 424	97.21 350	92.09 378	98.00 331	97.55 376	89.31 440	90.86 432	95.61 447	74.48 464	95.32 485	85.57 456	89.70 400	96.07 439

pmmvs6		91.77 400	90.63 406	95.17 394	94.69 457	91.24 395	98.67 207	97.92 340	86.14 467	89.62 446	97.56 325	75.79 454	98.34 378	90.75 397	84.56 452	95.94 442

Anonymous20231206		91.66 401	91.10 402	93.33 444	94.02 467	87.35 467	98.58 225	97.26 406	90.48 417	90.16 440	96.31 417	83.83 379	96.53 471	79.36 485	89.90 398	96.12 437

Patchmatch-RL test		91.49 402	90.85 404	93.41 442	91.37 491	84.40 478	92.81 500	95.93 465	91.87 382	87.25 465	94.87 456	88.99 256	96.53 471	92.54 355	82.00 463	99.30 163

blended_shiyan8		91.42 403	89.89 415	96.01 352	91.50 488	93.30 341	97.48 384	97.83 345	86.93 458	92.57 399	92.37 485	82.46 388	98.13 400	92.86 340	74.99 492	96.61 391

blended_shiyan6		91.37 404	89.84 416	95.98 358	91.49 489	93.28 342	97.48 384	97.83 345	86.93 458	92.43 405	92.36 486	82.44 389	98.06 412	92.74 345	74.82 495	96.59 396

test_0402		91.32 405	90.27 410	94.48 425	96.60 389	91.12 396	98.50 249	97.22 408	86.10 468	88.30 461	96.98 378	77.65 438	97.99 422	78.13 490	92.94 357	94.34 471

dtuonlycased		91.29 406	91.26 401	91.36 463	95.63 434	84.25 480	96.93 432	97.21 410	92.16 375	88.34 460	96.47 410	79.56 417	95.18 488	87.37 444	87.70 427	94.64 469

test_vis1_rt		91.29 406	90.65 405	93.19 448	97.45 334	86.25 473	98.57 234	90.90 508	93.30 327	86.94 468	93.59 471	62.07 492	99.11 271	97.48 146	95.58 316	94.22 475

PVSNet_0	88.72 19	91.28 408	90.03 413	95.00 401	97.99 281	87.29 468	94.84 485	98.50 199	92.06 377	89.86 443	95.19 452	79.81 415	99.39 210	92.27 360	69.79 510	98.33 297

mvs5depth		91.23 409	90.17 411	94.41 429	92.09 483	89.79 426	95.26 478	96.50 453	90.73 413	91.69 423	97.06 367	76.12 452	98.62 341	88.02 438	84.11 455	94.82 465

Anonymous20240521		91.18 410	90.44 408	93.42 441	93.70 468	88.47 456	98.94 108	97.56 371	88.46 449	89.56 448	95.08 455	77.15 444	96.97 459	83.92 468	89.55 404	94.82 465

wanda-best-256-512		91.17 411	89.60 420	95.88 365	91.33 492	92.99 356	96.89 440	97.82 348	86.89 461	92.36 407	91.75 492	81.83 392	98.06 412	92.75 342	74.82 495	96.59 396

FE-blended-shiyan7		91.17 411	89.60 420	95.88 365	91.33 492	92.99 356	96.89 440	97.82 348	86.89 461	92.36 407	91.75 492	81.83 392	98.06 412	92.75 342	74.82 495	96.59 396

EG-PatchMatch MVS		91.13 413	90.12 412	94.17 434	94.73 456	89.00 445	98.13 312	97.81 352	89.22 441	85.32 479	96.46 411	67.71 481	98.42 362	87.89 442	93.82 338	95.08 460

TDRefinement		91.06 414	89.68 418	95.21 392	85.35 518	91.49 391	98.51 248	97.07 421	91.47 392	88.83 456	97.84 294	77.31 440	99.09 276	92.79 341	77.98 482	95.04 462

gbinet_0.2-2-1-0.02		91.03 415	89.37 426	96.01 352	91.39 490	93.41 331	97.19 412	97.82 348	87.00 457	92.18 415	91.87 491	78.97 422	98.04 416	93.13 326	74.75 499	96.60 393

sc_t1		91.01 416	89.39 422	95.85 368	95.99 419	90.39 417	98.43 264	97.64 363	78.79 492	92.20 414	97.94 283	66.00 485	98.60 345	91.59 380	85.94 448	98.57 284

UnsupCasMVSNet_eth		90.99 417	89.92 414	94.19 433	94.08 464	89.83 425	97.13 421	98.67 150	93.69 302	85.83 475	96.19 424	75.15 459	96.74 464	89.14 424	79.41 476	96.00 440

0.4-1-1-0.1		90.89 418	88.97 432	96.67 297	94.15 461	92.76 364	95.28 477	95.03 478	89.11 442	90.43 437	89.57 500	75.41 455	99.04 285	94.70 269	77.06 485	98.20 303

test20.03		90.89 418	90.38 409	92.43 454	93.48 471	88.14 462	98.33 273	97.56 371	93.40 322	87.96 462	96.71 400	80.69 409	94.13 495	79.15 486	86.17 444	95.01 464

usedtu_blend_shiyan5		90.87 420	89.15 427	96.01 352	91.33 492	93.35 338	98.12 313	97.36 397	81.93 486	92.36 407	91.75 492	81.83 392	98.09 407	92.88 338	74.82 495	96.59 396

blend_shiyan4		90.76 421	89.01 430	95.99 355	91.69 487	93.35 338	97.44 386	97.83 345	86.93 458	92.23 412	91.98 489	75.19 458	98.09 407	92.88 338	74.96 493	96.52 412

MDA-MVSNet_test_wron		90.71 422	89.38 424	94.68 416	94.83 453	90.78 405	97.19 412	97.46 385	87.60 453	72.41 503	95.72 442	86.51 317	96.71 467	85.92 454	86.80 441	96.56 404

YYNet1		90.70 423	89.39 422	94.62 420	94.79 455	90.65 408	97.20 409	97.46 385	87.54 454	72.54 502	95.74 438	86.51 317	96.66 468	86.00 453	86.76 442	96.54 407

ArgMatch-SfM		90.55 424	89.69 417	93.14 449	95.91 425	86.12 474	97.20 409	96.81 443	92.91 345	91.39 426	96.95 383	65.65 487	97.72 441	88.03 437	82.36 460	95.57 450

0.4-1-1-0.2		90.43 425	88.45 436	96.38 335	93.34 473	92.12 374	93.88 498	95.04 477	88.62 448	90.00 442	88.31 503	75.31 457	99.03 288	94.61 276	76.91 487	98.01 312

KD-MVS_self_test		90.38 426	89.38 424	93.40 443	92.85 478	88.94 448	97.95 335	97.94 338	90.35 422	90.25 438	93.96 468	79.82 414	95.94 480	84.62 467	76.69 489	95.33 453

pmmvs-eth3d		90.36 427	89.05 429	94.32 431	91.10 496	92.12 374	97.63 376	96.95 432	88.86 445	84.91 480	93.13 477	78.32 427	96.74 464	88.70 429	81.81 465	94.09 478

0.3-1-1-0.015		90.29 428	88.21 440	96.51 320	93.56 470	92.44 367	94.41 494	95.03 478	88.71 446	89.20 451	88.50 502	73.12 471	99.04 285	94.67 272	76.70 488	98.05 308

FE-MVSNET2		90.29 428	88.94 433	94.36 430	90.48 501	92.27 369	98.45 256	97.82 348	91.59 390	84.90 481	93.10 478	73.92 467	96.42 474	87.92 441	82.26 461	94.39 470

tt0320		90.26 430	88.73 435	94.86 408	96.12 413	90.62 410	98.17 305	97.63 364	77.46 496	89.68 445	96.04 430	69.19 477	97.79 436	88.98 426	85.29 450	96.16 436

CL-MVSNet_self_test		90.11 431	89.14 428	93.02 450	91.86 485	88.23 461	96.51 457	98.07 325	90.49 416	90.49 436	94.41 461	84.75 356	95.34 484	80.79 479	74.95 494	95.50 451

new_pmnet		90.06 432	89.00 431	93.22 447	94.18 459	88.32 459	96.42 459	96.89 437	86.19 466	85.67 476	93.62 470	77.18 443	97.10 457	81.61 476	89.29 410	94.23 474

MDA-MVSNet-bldmvs		89.97 433	88.35 438	94.83 412	95.21 447	91.34 392	97.64 373	97.51 380	88.36 451	71.17 504	96.13 426	79.22 420	96.63 469	83.65 469	86.27 443	96.52 412

tt0320-xc		89.79 434	88.11 441	94.84 411	96.19 408	90.61 411	98.16 306	97.22 408	77.35 497	88.75 458	96.70 401	65.94 486	97.63 445	89.31 422	83.39 457	96.28 431

CMPMVS	66.06 21	89.70 435	89.67 419	89.78 467	93.19 476	76.56 496	97.00 428	98.35 255	80.97 487	81.57 488	97.75 302	74.75 462	98.61 342	89.85 410	93.63 342	94.17 476
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet1		89.67 436	88.28 439	93.82 436	92.81 479	91.08 397	98.01 329	97.45 389	87.95 452	87.90 463	95.87 436	67.63 482	94.56 493	78.73 489	88.18 423	95.83 445

KD-MVS_2432*1600		89.61 437	87.96 445	94.54 422	94.06 465	91.59 389	95.59 472	97.63 364	89.87 429	88.95 453	94.38 463	78.28 428	96.82 462	84.83 463	68.05 511	95.21 456

miper_refine_blended		89.61 437	87.96 445	94.54 422	94.06 465	91.59 389	95.59 472	97.63 364	89.87 429	88.95 453	94.38 463	78.28 428	96.82 462	84.83 463	68.05 511	95.21 456

MVStest1		89.53 439	87.99 444	94.14 435	94.39 458	90.42 415	98.25 288	96.84 442	82.81 480	81.18 490	97.33 341	77.09 445	96.94 460	85.27 460	78.79 477	95.06 461

MVS-HIRNet		89.46 440	88.40 437	92.64 453	97.58 319	82.15 488	94.16 497	93.05 499	75.73 500	90.90 431	82.52 509	79.42 419	98.33 380	83.53 470	98.68 173	97.43 327

OpenMVS_ROB	86.42 20	89.00 441	87.43 449	93.69 438	93.08 477	89.42 438	97.91 342	96.89 437	78.58 493	85.86 474	94.69 457	69.48 476	98.29 388	77.13 493	93.29 354	93.36 488

mvsany_test3		88.80 442	88.04 442	91.09 464	89.78 506	81.57 490	97.83 357	95.49 470	93.81 291	87.53 464	93.95 469	56.14 495	97.43 452	94.68 270	83.13 458	94.26 472

FE-MVSNET		88.56 443	87.09 450	92.99 451	89.93 505	89.99 423	98.15 309	95.59 468	88.42 450	84.87 482	92.90 480	74.82 461	94.99 490	77.88 491	81.21 468	93.99 481

new-patchmatchnet		88.50 444	87.45 448	91.67 461	90.31 503	85.89 475	97.16 419	97.33 398	89.47 436	83.63 485	92.77 482	76.38 449	95.06 489	82.70 472	77.29 483	94.06 480

APD_test1		88.22 445	88.01 443	88.86 471	95.98 420	74.66 504	97.21 408	96.44 455	83.96 479	86.66 471	97.90 287	60.95 493	97.84 435	82.73 471	90.23 394	94.09 478

PM-MVS		87.77 446	86.55 452	91.40 462	91.03 498	83.36 485	96.92 433	95.18 475	91.28 403	86.48 473	93.42 473	53.27 497	96.74 464	89.43 420	81.97 464	94.11 477

dmvs_testset		87.64 447	88.93 434	83.79 483	95.25 446	63.36 517	97.20 409	91.17 505	93.07 337	85.64 477	95.98 435	85.30 347	91.52 505	69.42 504	87.33 433	96.49 419

test_fmvs3		87.17 448	87.06 451	87.50 474	91.21 495	75.66 499	99.05 76	96.61 451	92.79 350	88.85 455	92.78 481	43.72 504	93.49 497	93.95 302	84.56 452	93.34 489

UnsupCasMVSNet_bld		87.17 448	85.12 456	93.31 445	91.94 484	88.77 449	94.92 484	98.30 275	84.30 478	82.30 486	90.04 498	63.96 490	97.25 455	85.85 455	74.47 502	93.93 483

N_pmnet		87.12 450	87.77 447	85.17 478	95.46 442	61.92 520	97.37 394	70.66 531	85.83 470	88.73 459	96.04 430	85.33 345	97.76 439	80.02 480	90.48 389	95.84 444

pmmvs3		86.67 451	84.86 457	92.11 460	88.16 510	87.19 470	96.63 453	94.75 482	79.88 489	87.22 466	92.75 483	66.56 484	95.20 487	81.24 478	76.56 490	93.96 482

test_f		86.07 452	85.39 454	88.10 472	89.28 508	75.57 500	97.73 366	96.33 457	89.41 439	85.35 478	91.56 495	43.31 506	95.53 482	91.32 384	84.23 454	93.21 490

MASt3R-SfM		85.54 453	85.89 453	84.50 481	90.13 504	66.13 515	92.89 499	95.33 472	85.73 472	88.77 457	96.36 416	52.50 498	94.89 491	86.66 448	84.65 451	92.50 494

WB-MVS		84.86 454	85.33 455	83.46 484	89.48 507	69.56 509	98.19 298	96.42 456	89.55 435	81.79 487	94.67 458	84.80 354	90.12 506	52.44 512	80.64 473	90.69 498

usedtu_dtu_shiyan2		84.80 455	82.31 460	92.27 458	86.38 515	85.55 476	97.77 362	96.56 452	78.34 494	83.90 484	93.50 472	54.16 496	95.32 485	77.55 492	72.62 503	95.92 443

DenseAffine		84.37 456	82.38 459	90.31 466	94.17 460	82.89 486	94.98 481	94.23 489	82.16 485	79.68 494	94.33 466	46.28 500	94.25 494	80.01 481	75.62 491	93.78 486

SSC-MVS		84.27 457	84.71 458	82.96 489	89.19 509	68.83 510	98.08 321	96.30 458	89.04 444	81.37 489	94.47 459	84.60 361	89.89 507	49.80 515	79.52 475	90.15 499

RoMa-SfM		83.81 458	82.08 461	89.00 470	93.33 474	79.94 493	95.51 474	92.48 501	79.75 490	79.89 493	95.69 445	46.23 501	93.20 500	78.90 487	76.93 486	93.87 484

LoFTR		83.16 459	80.62 463	90.80 465	92.28 482	80.01 492	95.35 476	94.33 486	80.44 488	70.79 505	92.93 479	46.38 499	98.17 396	75.01 497	78.03 481	94.24 473

dongtai		82.47 460	81.88 462	84.22 482	95.19 448	76.03 497	94.59 492	74.14 523	82.63 481	87.19 467	96.09 427	64.10 489	87.85 511	58.91 510	84.11 455	88.78 505

DKM		81.60 461	79.57 464	87.68 473	92.65 481	78.36 494	94.65 490	91.17 505	79.69 491	76.11 497	93.98 467	37.88 515	91.54 504	79.64 484	70.38 507	93.15 491

MatchFormer		80.21 462	77.20 470	89.24 469	91.79 486	77.21 495	95.16 479	93.59 494	72.46 504	67.08 508	89.93 499	43.14 507	97.90 428	67.07 506	74.55 501	92.61 493

test_vis3_rt		79.22 463	77.40 469	84.67 479	86.44 514	74.85 503	97.66 371	81.43 516	84.98 475	67.12 507	81.91 512	28.09 527	97.60 446	88.96 427	80.04 474	81.55 515

test_method		79.03 464	78.17 465	81.63 490	86.06 516	54.40 531	82.75 519	96.89 437	39.54 524	80.98 491	95.57 448	58.37 494	94.73 492	84.74 466	78.61 478	95.75 446

testf1		79.02 465	77.70 466	82.99 487	88.10 511	66.90 513	94.67 487	93.11 496	71.08 506	74.02 499	93.41 474	34.15 520	93.25 498	72.25 501	78.50 479	88.82 503

APD_test2		79.02 465	77.70 466	82.99 487	88.10 511	66.90 513	94.67 487	93.11 496	71.08 506	74.02 499	93.41 474	34.15 520	93.25 498	72.25 501	78.50 479	88.82 503

LCM-MVSNet		78.70 467	76.24 473	86.08 476	77.26 533	71.99 506	94.34 495	96.72 445	61.62 510	76.53 496	89.33 501	33.91 523	92.78 502	81.85 475	74.60 500	93.46 487

kuosan		78.45 468	77.69 468	80.72 491	92.73 480	75.32 501	94.63 491	74.51 522	75.96 498	80.87 492	93.19 476	63.23 491	79.99 520	42.56 522	81.56 467	86.85 512

Gipuma		78.40 469	76.75 472	83.38 485	95.54 437	80.43 491	79.42 520	97.40 393	64.67 509	73.46 501	80.82 513	45.65 503	93.14 501	66.32 507	87.43 431	76.56 518
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		77.95 470	75.44 474	85.46 477	82.54 522	74.95 502	94.23 496	93.08 498	72.80 502	74.68 498	87.38 504	36.36 518	91.56 503	73.95 499	63.94 513	89.87 500

FPMVS		77.62 471	77.14 471	79.05 494	79.25 528	60.97 522	95.79 467	95.94 464	65.96 508	67.93 506	94.40 462	37.73 516	88.88 510	68.83 505	88.46 420	87.29 509

ELoFTR		75.37 472	72.33 475	84.51 480	84.48 520	68.41 512	91.57 504	88.78 511	73.84 501	62.84 512	90.14 497	27.38 528	94.11 496	71.45 503	60.46 516	91.00 496

EGC-MVSNET		75.22 473	69.54 477	92.28 457	94.81 454	89.58 434	97.64 373	96.50 453	1.82 545	5.57 546	95.74 438	68.21 478	96.26 476	73.80 500	91.71 374	90.99 497

PMatch-SfM		73.49 474	70.32 476	83.00 486	85.01 519	68.63 511	90.17 511	79.05 519	71.64 505	63.27 511	91.93 490	17.27 536	89.10 509	74.59 498	59.95 517	91.26 495

PDCNetPlus		71.79 475	69.26 478	79.39 493	85.67 517	69.92 508	90.34 509	62.32 533	72.62 503	65.36 510	90.26 496	39.20 512	86.38 512	75.32 496	42.24 526	81.88 514

SP-DiffGlue		70.13 476	69.16 479	73.04 503	77.73 531	57.48 526	88.44 514	74.91 521	50.96 516	66.64 509	85.99 506	41.44 508	73.46 526	64.21 508	72.15 504	88.19 508

ANet_high		69.08 477	65.37 484	80.22 492	65.99 546	71.96 507	90.91 508	90.09 509	82.62 482	49.93 526	78.39 520	29.36 526	81.75 517	62.49 509	38.52 530	86.95 511

tmp_tt		68.90 478	66.97 480	74.68 496	50.78 548	59.95 523	87.13 516	83.47 515	38.80 525	62.21 513	96.23 421	64.70 488	76.91 522	88.91 428	30.49 534	87.19 510

SP-LightGlue		68.17 479	66.54 482	73.06 502	91.08 497	55.79 527	91.09 506	72.78 525	48.55 520	60.77 515	79.95 517	38.55 513	74.10 524	45.47 517	70.64 506	89.28 501

SP-SuperGlue		68.14 480	66.58 481	72.81 504	90.65 500	55.53 528	91.37 505	73.04 524	49.07 519	61.03 514	80.24 516	38.13 514	74.06 525	45.46 518	70.26 508	88.84 502

ALIKED-LG		67.40 481	65.16 485	74.11 498	93.21 475	62.30 518	88.98 512	71.99 526	55.04 511	59.47 518	82.33 510	39.27 511	85.49 514	32.61 528	63.58 515	74.55 519

SP-NN		67.39 482	65.69 483	72.49 506	90.68 499	55.34 529	90.33 510	71.01 529	46.77 522	59.09 519	79.83 518	37.26 517	73.38 527	44.68 519	71.51 505	88.74 506

ALIKED-NN		66.93 483	64.81 486	73.32 500	93.41 472	62.03 519	87.55 515	71.25 527	50.21 517	59.98 517	82.57 508	39.72 510	84.03 516	34.94 526	63.64 514	73.90 520

SP-MNN		66.66 484	64.70 487	72.53 505	90.32 502	55.08 530	91.01 507	71.05 528	44.81 523	56.48 522	79.62 519	35.87 519	74.11 523	43.13 521	69.98 509	88.39 507

PMVS	61.03 23	65.95 485	63.57 489	73.09 501	57.90 547	51.22 533	85.05 518	93.93 493	54.45 512	44.32 528	83.57 507	13.22 542	89.15 508	58.68 511	81.00 470	78.91 517
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ALIKED-MNN		65.35 486	62.68 491	73.35 499	93.70 468	61.07 521	88.63 513	70.76 530	47.76 521	57.06 521	80.59 514	34.03 522	85.39 515	32.73 527	58.87 518	73.59 521

E-PMN		64.94 487	64.25 488	67.02 507	82.28 523	59.36 524	91.83 503	85.63 513	52.69 513	60.22 516	77.28 521	41.06 509	80.12 519	46.15 516	41.14 527	61.57 524

EMVS		64.07 488	63.26 490	66.53 508	81.73 524	58.81 525	91.85 502	84.75 514	51.93 515	59.09 519	75.13 524	43.32 505	79.09 521	42.03 523	39.47 528	61.69 523

MVE	62.14 22	63.28 489	59.38 492	74.99 495	74.33 538	65.47 516	85.55 517	80.50 517	52.02 514	51.10 524	75.00 525	10.91 547	80.50 518	51.60 514	53.40 520	78.99 516
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
GLUNet-SfM		61.12 490	56.63 493	74.58 497	69.78 543	53.99 532	78.71 521	76.81 520	49.09 518	49.42 527	80.47 515	24.43 529	85.82 513	51.80 513	29.17 535	83.92 513

XFeat-NN		56.16 491	56.10 494	56.36 510	72.10 540	42.54 543	76.45 523	61.18 534	38.16 526	53.08 523	76.48 522	32.95 524	65.67 529	44.15 520	50.31 523	60.87 525

XFeat-MNN		55.84 492	55.19 495	57.82 509	69.33 544	43.25 538	78.25 522	62.64 532	37.53 527	50.90 525	76.32 523	32.43 525	68.13 528	42.00 524	47.26 525	62.07 522

SIFT-NN		49.27 493	49.25 496	49.32 511	83.88 521	45.20 534	74.57 524	53.44 535	32.44 528	42.88 529	64.93 526	20.60 530	61.35 530	16.59 530	53.96 519	41.40 526

SIFT-MNN		47.78 494	47.47 497	48.69 512	81.04 525	44.17 535	73.46 525	53.36 536	31.82 529	38.54 530	63.76 527	18.11 534	61.27 531	15.96 532	51.17 521	40.64 529

SIFT-NN-NCMNet		47.55 495	47.18 498	48.67 513	79.60 527	44.09 536	73.43 526	52.90 537	31.82 529	38.38 531	63.56 530	18.47 531	61.19 532	15.91 533	50.50 522	40.74 528

SIFT-NN-CMatch		45.31 496	44.49 499	47.75 514	76.46 534	42.98 541	70.17 530	49.20 540	31.63 532	37.94 532	63.68 529	18.19 533	59.32 535	15.91 533	37.27 531	40.95 527

SIFT-NCM-Cal		44.98 497	44.20 500	47.33 515	79.81 526	43.05 539	72.12 527	49.31 539	30.81 534	25.90 538	61.87 535	15.80 537	60.28 533	14.09 541	48.07 524	38.66 532

SIFT-NN-UMatch		44.69 498	43.84 501	47.24 516	74.56 537	42.59 542	71.89 528	49.78 538	31.80 531	29.27 535	63.70 528	18.26 532	59.43 534	15.86 535	39.43 529	39.71 530

SIFT-ConvMatch		43.26 499	42.18 503	46.50 517	78.34 530	43.05 539	68.67 532	47.17 541	31.06 533	30.28 534	62.56 532	15.43 538	58.95 537	14.92 537	31.22 533	37.51 534

SIFT-NN-PointCN		43.09 500	42.61 502	44.51 520	72.48 539	37.95 547	70.10 531	46.55 542	30.16 538	34.48 533	61.93 534	18.02 535	55.90 540	15.40 536	34.41 532	39.69 531

SIFT-UMatch		42.35 501	41.04 504	46.29 518	76.09 535	41.80 544	70.21 529	45.21 543	30.75 535	27.33 537	62.62 531	15.13 539	59.11 536	14.72 538	27.30 536	37.95 533

SIFT-CM-Cal		41.25 502	40.03 505	44.88 519	77.37 532	41.08 545	65.71 536	41.18 545	30.42 537	28.83 536	61.42 536	14.88 540	56.40 538	14.13 540	26.37 538	37.16 535

SIFT-UM-Cal		39.93 503	38.61 506	43.88 521	76.08 536	39.30 546	68.10 533	37.89 546	30.49 536	22.74 540	62.27 533	13.89 541	56.16 539	14.17 539	21.90 539	36.17 536

SIFT-PointCN		37.89 504	37.50 507	39.07 522	71.45 541	31.31 548	66.27 535	41.69 544	27.82 539	22.63 541	56.73 538	12.00 545	50.56 542	12.18 543	26.71 537	35.34 537

SIFT-PCN-Cal		36.85 505	36.40 508	38.19 523	71.43 542	30.42 549	64.34 537	37.72 547	27.48 540	22.98 539	57.03 537	12.99 543	51.22 541	12.51 542	21.13 540	32.92 538

SIFT-NCMNet		32.45 506	31.84 510	34.30 524	68.74 545	28.10 550	57.85 538	24.54 548	27.25 541	19.31 542	52.59 539	9.75 548	45.69 543	10.92 544	15.56 542	29.13 539

wuyk23d		30.17 507	30.18 511	30.16 525	78.61 529	43.29 537	66.79 534	14.21 549	17.31 542	14.82 545	11.93 545	11.55 546	41.43 544	37.08 525	19.30 541	5.76 542

cdsmvs_eth3d_5k		23.98 508	31.98 509	0.00 528	0.00 551	0.00 553	0.00 539	98.59 171	0.00 546	0.00 547	98.61 214	90.60 204	0.00 547	0.00 545	0.00 545	0.00 543

testmvs		21.48 509	24.95 512	11.09 527	14.89 549	6.47 552	96.56 455	9.87 550	7.55 543	17.93 543	39.02 541	9.43 549	5.90 546	16.56 531	12.72 543	20.91 541

test123		20.95 510	23.72 513	12.64 526	13.54 550	8.19 551	96.55 456	6.13 551	7.48 544	16.74 544	37.98 542	12.97 544	6.05 545	16.69 529	5.43 544	23.68 540

ab-mvs-re		8.20 511	10.94 514	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	98.43 233	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

pcd_1.5k_mvsjas		7.88 512	10.50 515	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	94.51 91	0.00 547	0.00 545	0.00 545	0.00 543

mmdepth		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

monomultidepth		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

test_blank		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

uanet_test		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

DCPMVS		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

sosnet-low-res		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

sosnet		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

uncertanet		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

Regformer		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

uanet		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

MED-MVS test				99.52 14	99.77 2	98.86 23	99.32 22	99.24 20	96.41 123	99.30 52	99.35 62		99.92 43	98.30 75	99.80 25	99.79 29

TestfortrainingZip				99.43 21	99.13 119	99.06 15	99.32 22	98.57 178	96.88 97	99.42 43	99.05 143	96.54 24	99.73 136		98.59 180	99.51 104

WAC-MVS						90.94 399								88.66 430

FOURS1					99.82 1	98.66 29	99.69 1	98.95 61	97.46 57	99.39 46

MSC_two_6792asdad				99.62 7	99.17 111	99.08 12		98.63 161					99.94 14	98.53 55	99.80 25	99.86 13

PC_three_1452									95.08 216	99.60 33	99.16 110	97.86 2	98.47 356	97.52 139	99.72 66	99.74 50

No_MVS				99.62 7	99.17 111	99.08 12		98.63 161					99.94 14	98.53 55	99.80 25	99.86 13

test_one_0601					99.66 31	99.25 2		98.86 91	97.55 49	99.20 60	99.47 37	97.57 7

eth-test2					0.00 551

eth-test					0.00 551

ZD-MVS					99.46 58	98.70 28		98.79 119	93.21 330	98.67 105	98.97 154	95.70 52	99.83 90	96.07 212	99.58 97

RE-MVS-def			98.34 54		99.49 52	97.86 75	99.11 66	98.80 114	96.49 118	99.17 63	99.35 62	95.29 69		97.72 113	99.65 80	99.71 63

IU-MVS					99.71 24	99.23 7		98.64 158	95.28 199	99.63 32				98.35 72	99.81 16	99.83 19

OPU-MVS				99.37 28	99.24 103	99.05 16	99.02 86				99.16 110	97.81 3	99.37 211	97.24 161	99.73 61	99.70 67

test_241102_TWO								98.87 85	97.65 41	99.53 38	99.48 35	97.34 12	99.94 14	98.43 67	99.80 25	99.83 19

test_241102_ONE					99.71 24	99.24 5		98.87 85	97.62 43	99.73 23	99.39 50	97.53 8	99.74 134

9.14			98.06 78		99.47 56		98.71 192	98.82 101	94.36 263	99.16 67	99.29 75	96.05 40	99.81 102	97.00 169	99.71 68

save fliter					99.46 58	98.38 41	98.21 291	98.71 137	97.95 28

test_0728_THIRD									97.32 65	99.45 40	99.46 42	97.88 1	99.94 14	98.47 63	99.86 2	99.85 16

test_0728_SECOND				99.71 1	99.72 17	99.35 1	98.97 98	98.88 78					99.94 14	98.47 63	99.81 16	99.84 18

test0726					99.72 17	99.25 2	99.06 74	98.88 78	97.62 43	99.56 35	99.50 31	97.42 10

GSMVS																99.20 189

test_part2					99.63 34	99.18 10				99.27 57

sam_mvs1												89.45 240				99.20 189

sam_mvs												88.99 256

ambc				89.49 468	86.66 513	75.78 498	92.66 501	96.72 445		86.55 472	92.50 484	46.01 502	97.90 428	90.32 401	82.09 462	94.80 467

MTGPA								98.74 129

test_post1							96.68 452				30.43 544	87.85 294	98.69 334	92.59 351

test_post											31.83 543	88.83 265	98.91 310

patchmatchnet-post											95.10 454	89.42 241	98.89 314

GG-mvs-BLEND				96.59 309	96.34 403	94.98 260	96.51 457	88.58 512		93.10 384	94.34 465	80.34 413	98.05 415	89.53 417	96.99 269	96.74 372

MTMP							98.89 124	94.14 491

gm-plane-assit					95.88 427	87.47 466			89.74 432		96.94 385		99.19 251	93.32 321

test9_res														96.39 206	99.57 98	99.69 70

TEST9					99.31 79	98.50 35	97.92 340	98.73 132	92.63 354	97.74 183	98.68 208	96.20 35	99.80 109

test_8					99.29 88	98.44 37	97.89 348	98.72 134	92.98 341	97.70 188	98.66 211	96.20 35	99.80 109

agg_prior2														95.87 222	99.57 98	99.68 75

agg_prior					99.30 83	98.38 41		98.72 134		97.57 206			99.81 102

TestCases				96.99 267	99.25 96	93.21 348		98.18 299	91.36 396	93.52 363	98.77 195	84.67 359	99.72 137	89.70 414	97.87 238	98.02 310

test_prior4						98.01 71	97.86 352

test_prior2							97.80 359		96.12 139	97.89 170	98.69 207	95.96 44		96.89 179	99.60 92

test_prior				99.19 51	99.31 79	98.22 58		98.84 96					99.70 143			99.65 83

旧先验2							97.57 379		91.30 401	98.67 105			99.80 109	95.70 233

新几何2							97.64 373

新几何1				99.16 56	99.34 71	98.01 71		98.69 142	90.06 426	98.13 138	98.95 161	94.60 89	99.89 68	91.97 370	99.47 121	99.59 94

旧先验1					99.29 88	97.48 90		98.70 140			99.09 133	95.56 55			99.47 121	99.61 90

无先验							97.58 378	98.72 134	91.38 395				99.87 79	93.36 320		99.60 92

原ACMM2							97.67 370

原ACMM1				98.65 98	99.32 77	96.62 141		98.67 150	93.27 329	97.81 176	98.97 154	95.18 76	99.83 90	93.84 306	99.46 124	99.50 107

test222					99.23 104	97.17 117	97.40 390	98.66 153	88.68 447	98.05 147	98.96 159	94.14 102			99.53 111	99.61 90

testdata2													99.89 68	91.65 379

segment_acmp												96.85 15

testdata				98.26 142	99.20 109	95.36 236		98.68 145	91.89 381	98.60 113	99.10 125	94.44 96	99.82 97	94.27 290	99.44 125	99.58 98

testdata1							97.32 400		96.34 128

test12				99.18 53	99.16 115	98.19 60		98.53 188		98.07 143		95.13 79	99.72 137		99.56 106	99.63 88

plane_prior7					97.42 336	94.63 277

plane_prior6					97.35 343	94.61 280						87.09 308

plane_prior5								98.56 182					99.03 288	96.07 212	94.27 322	96.92 348

plane_prior4											98.28 252

plane_prior3						94.61 280			97.02 89	95.34 288

plane_prior2							98.80 164		97.28 69

plane_prior1					97.37 342

plane_prior						94.60 282	98.44 262		96.74 105						94.22 324

n2								0.00 552

nn								0.00 552

door-mid								94.37 485

lessismore_v0				94.45 428	94.93 452	88.44 457		91.03 507		86.77 470	97.64 316	76.23 451	98.42 362	90.31 402	85.64 449	96.51 416

LGP-MVS_train				96.47 325	97.46 331	93.54 324		98.54 186	94.67 245	94.36 320	98.77 195	85.39 341	99.11 271	95.71 231	94.15 328	96.76 370

test11								98.66 153

door								94.64 483

HQP5-MVS						94.25 299

HQP-NCC					97.20 351		98.05 324		96.43 120	94.45 312

ACMP_Plane					97.20 351		98.05 324		96.43 120	94.45 312

BP-MVS														95.30 246

HQP4-MVS										94.45 312			98.96 301			96.87 360

HQP3-MVS								98.46 207							94.18 326

HQP2-MVS												86.75 314

NP-MVS					97.28 345	94.51 285					97.73 303

MDTV_nov1_ep13_2view						84.26 479	96.89 440		90.97 410	97.90 169		89.89 226		93.91 304		99.18 198

MDTV_nov1_ep13			95.40 238		97.48 329	88.34 458	96.85 445	97.29 402	93.74 295	97.48 208	97.26 345	89.18 249	99.05 282	91.92 371	97.43 260

ACMMP++_ref															92.97 356

ACMMP++															93.61 343

Test By Simon												94.64 88

ITE_SJBPF				95.44 386	97.42 336	91.32 393		97.50 381	95.09 215	93.59 358	98.35 243	81.70 395	98.88 316	89.71 413	93.39 349	96.12 437

DeepMVS_CX				86.78 475	97.09 361	72.30 505		95.17 476	75.92 499	84.34 483	95.19 452	70.58 474	95.35 483	79.98 483	89.04 414	92.68 492

High-resolution multi-view benchmark