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	98.88 130	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 85	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	98.89 123	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 97	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	98.94 107	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	98.86 141	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	98.86 141	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	98.82 154	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	98.42 266	98.91 72	97.58 47	99.54 37	99.46 42	97.10 13	99.94 14	97.64 120	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	98.70 195	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	98.89 123	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	97.77 108	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	98.96 103	99.36 10	98.63 13	99.86 8	99.51 28	95.91 46	99.97 1	99.72 14	99.75 53	98.94 233

ME-MVS		98.83 19	98.60 24	99.52 14	99.58 37	98.86 23	98.69 198	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	98.47 253	98.81 107	97.72 36	98.76 96	99.16 108	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	98.78 189	96.00 42	99.79 121	97.79 107	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	98.80 163	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 93	95.90 48	99.89 68	97.85 103	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	98.86 141	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	98.79 171	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	98.41 267	98.68 145	97.04 88	98.52 117	98.80 183	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	98.90 119	98.85 95	97.28 69	99.72 26	99.39 50	96.63 22	97.60 441	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	98.79 171	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	96.10 140	98.94 78	99.17 105	96.06 39	99.92 43	97.62 121	99.78 39	99.75 48

ACMMP_NAP		98.61 31	98.30 60	99.55 11	99.62 35	98.95 19	98.82 154	98.81 107	95.80 155	99.16 67	99.47 37	95.37 63	99.92 43	97.89 100	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	96.15 135	98.94 78	99.17 105	95.91 46	99.94 14	97.55 133	99.79 34	99.78 33

NCCC		98.61 31	98.35 48	99.38 24	99.28 92	98.61 32	98.45 255	98.76 125	97.82 35	98.45 122	98.93 162	96.65 21	99.83 90	97.38 155	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 79	98.81 107	95.12 209	99.32 51	99.39 50	96.22 33	99.84 88	97.72 111	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	96.10 140	98.93 82	99.19 100	95.70 52	99.94 14	97.62 121	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 97	98.86 91	98.91 4	99.87 4	99.66 3	91.82 152	99.95 9	99.82 6	99.82 14	98.75 255

test_fmvsmconf0.1_n		98.58 36	98.44 40	98.99 71	97.73 304	97.15 119	98.84 150	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	98.95 104	98.80 114	93.67 303	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	98.90 119	98.74 129	97.27 73	98.02 150	99.39 50	94.81 87	99.96 4	97.91 98	99.79 34	99.77 40

HPM-MVS++		98.58 36	98.25 63	99.55 11	99.50 48	99.08 12	98.72 190	98.66 153	97.51 51	98.15 135	98.83 180	95.70 52	99.92 43	97.53 136	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	97.70 116	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	95.96 146	98.60 113	99.13 115	96.05 40	99.94 14	97.77 108	99.86 2	99.77 40

MSLP-MVS++		98.56 43	98.57 26	98.55 108	99.26 95	96.80 134	98.71 191	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	98.50 248	98.78 121	97.72 36	98.92 84	99.28 76	95.27 70	99.82 97	97.55 133	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	97.72 111	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	98.68 201	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	98.80 163	99.26 16	98.82 7	99.87 4	99.60 10	90.95 193	99.93 34	99.76 11	99.73 61	99.12 203

APD-MVS_3200maxsize		98.53 46	98.33 58	99.15 57	99.50 48	97.92 74	99.15 57	98.81 107	96.24 131	99.20 60	99.37 56	95.30 68	99.80 109	97.73 110	99.67 74	99.72 59

MM		98.51 49	98.24 65	99.33 36	99.12 121	98.14 66	98.93 113	97.02 423	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	96.24 131	98.35 130	99.23 86	95.46 58	99.94 14	97.42 150	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	95.77 157	98.31 134	99.10 123	95.46 58	99.93 34	97.57 132	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	99.14 112	95.25 72	99.15 258	98.83 40	99.56 106	99.20 187

PGM-MVS		98.49 51	98.23 67	99.27 44	99.72 17	98.08 68	98.99 93	99.49 5	95.43 184	99.03 70	99.32 69	95.56 55	99.94 14	96.80 188	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	98.30 280	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	97.91 339	99.58 3	97.20 77	98.33 132	99.00 150	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	98.77 192	95.06 82	99.55 181	98.95 34	99.87 1	99.12 203

test_fmvsmvis_n_1920		98.44 57	98.51 32	98.23 146	98.33 220	96.15 171	98.97 97	99.15 41	98.55 16	98.45 122	99.55 18	94.26 100	99.97 1	99.65 18	99.66 77	98.57 280

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	99.10 123	95.73 51	99.13 263	98.71 44	99.49 117	99.09 211

GST-MVS		98.43 59	98.12 75	99.34 32	99.72 17	98.38 41	99.09 70	98.82 101	95.71 161	98.73 99	99.06 139	95.27 70	99.93 34	97.07 165	99.63 87	99.72 59

fmvsm_s_conf0.5_n		98.42 60	98.51 32	98.13 163	99.30 83	95.25 241	98.85 146	99.39 7	97.94 29	99.74 21	99.62 4	92.59 123	99.91 56	99.65 18	99.52 112	99.25 180

EI-MVSNet-UG-set		98.41 61	98.34 54	98.61 102	99.45 61	96.32 163	98.28 283	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	97.75 361	98.89 75	97.71 38	98.33 132	98.97 152	94.97 84	99.88 77	98.42 69	99.76 47	99.42 132
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	95.41 227	98.86 141	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	98.11 314	98.29 275	97.19 78	98.99 76	99.02 144	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	94.46 257	98.94 78	99.20 93	95.16 77	99.74 134	97.58 128	99.85 6	99.77 40

patch_mono-2		98.36 66	98.87 7	96.82 280	99.53 42	90.68 404	98.64 211	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	94.63 245	98.61 112	98.97 152	95.13 79	99.77 129	97.65 119	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	97.90 192	99.16 115	95.08 251	98.75 176	99.24 20	98.39 19	99.81 13	99.52 25	92.35 128	99.90 64	99.74 13	99.51 114	98.71 261

APD-MVS		98.35 68	98.00 83	99.42 22	99.51 46	98.72 26	98.80 163	98.82 101	94.52 252	99.23 59	99.25 85	95.54 57	99.80 109	96.52 197	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	97.95 332	99.58 3	97.14 83	98.44 124	99.01 148	95.03 83	99.62 164	97.91 98	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 79	99.09 44	93.32 321	98.83 91	99.10 123	96.54 24	99.83 90	97.70 116	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	96.13 136	97.92 164	99.23 86	94.54 90	99.94 14	96.74 191	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	94.81 233	98.99 76	98.90 168	95.22 75	99.59 167	99.15 29	99.84 11	99.07 219

MP-MVS-pluss		98.31 73	97.92 85	99.49 16	99.72 17	98.88 20	98.43 263	98.78 121	94.10 268	97.69 187	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	98.66 208	99.20 33	98.82 7	99.79 15	99.60 10	89.38 240	99.92 43	99.80 8	99.38 133	98.69 263

fmvsm_s_conf0.5_n_7		98.23 76	98.35 48	97.89 194	98.86 151	94.99 257	98.58 224	99.00 53	98.29 20	99.73 23	99.60 10	91.70 155	99.92 43	99.63 21	99.73 61	98.76 254

MGCNet		98.23 76	97.91 86	99.21 50	98.06 267	97.96 73	98.58 224	95.51 463	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 82	99.41 6	95.98 145	97.60 200	99.36 60	94.45 95	99.93 34	97.14 162	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	98.34 216	97.26 111	99.61 5	98.43 226	96.78 101	98.87 86	98.84 176	93.72 108	99.01 291	98.91 37	99.50 115	99.19 191

fmvsm_s_conf0.1_n		98.18 80	98.21 69	98.11 168	98.54 185	95.24 242	98.87 133	99.24 20	97.50 52	99.70 27	99.67 1	91.33 172	99.89 68	99.47 25	99.54 109	99.21 186

fmvsm_s_conf0.1_n_2		98.14 81	98.02 81	98.53 113	98.88 147	97.07 123	98.69 198	98.82 101	98.78 9	99.77 18	99.61 5	88.83 262	99.91 56	99.71 15	99.07 150	98.61 273

fmvsm_s_conf0.1_n_a		98.08 82	98.04 80	98.21 147	97.66 310	95.39 232	98.89 123	99.17 37	97.24 74	99.76 20	99.67 1	91.13 184	99.88 77	99.39 26	99.41 128	99.35 147

dcpmvs_2		98.08 82	98.59 25	96.56 310	99.57 39	90.34 416	99.15 57	98.38 247	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	98.94 107	98.60 164	97.86 33	98.71 102	99.08 134	91.22 179	99.80 109	97.40 152	99.57 98	99.37 142

CANet		98.05 85	97.76 90	98.90 82	98.73 161	97.27 106	98.35 270	98.78 121	97.37 64	97.72 184	98.96 157	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	97.92 337	98.73 132	92.98 337	97.74 181	98.68 205	96.20 35	99.80 109	96.59 192	99.57 98	99.68 75

ETV-MVS		97.96 87	97.81 88	98.40 132	98.42 199	97.27 106	98.73 186	98.55 184	96.84 98	98.38 127	97.44 328	95.39 61	99.35 212	97.62 121	98.89 161	98.58 279

UA-Net		97.96 87	97.62 94	98.98 73	98.86 151	97.47 92	98.89 123	99.08 45	96.67 111	98.72 101	99.54 20	93.15 116	99.81 102	94.87 256	98.83 168	99.65 83

CDPH-MVS		97.94 89	97.49 105	99.28 42	99.47 56	98.44 37	97.91 339	98.67 150	92.57 353	98.77 95	98.85 175	95.93 45	99.72 137	95.56 234	99.69 71	99.68 75

DeepPCF-MVS	96.37 2	97.93 90	98.48 38	96.30 338	99.00 135	89.54 432	97.43 386	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	98.83 152	98.75 127	96.96 93	96.89 232	99.50 31	90.46 206	99.87 79	97.84 105	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	95.48 435	96.83 133	98.95 104	98.60 164	98.58 14	98.93 82	99.55 18	88.57 267	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	98.33 272	98.89 75	92.62 350	98.05 145	98.94 160	95.34 66	99.65 154	96.04 213	99.42 127	99.19 191

CSCG		97.85 94	97.74 91	98.20 149	99.67 30	95.16 246	99.22 42	99.32 12	93.04 335	97.02 225	98.92 166	95.36 64	99.91 56	97.43 148	99.64 85	99.52 101

SymmetryMVS		97.84 95	97.58 96	98.62 100	99.01 133	96.60 144	98.94 107	98.44 215	97.86 33	98.71 102	99.08 134	91.22 179	99.80 109	97.40 152	97.53 254	99.47 116

BP-MVS1		97.82 96	97.51 104	98.76 89	98.25 236	97.39 96	99.15 57	97.68 354	96.69 109	98.47 118	99.10 123	90.29 214	99.51 187	98.60 50	99.35 136	99.37 142

MG-MVS		97.81 97	97.60 95	98.44 126	99.12 121	95.97 184	97.75 361	98.78 121	96.89 96	98.46 119	99.22 89	93.90 107	99.68 149	94.81 260	99.52 112	99.67 79

VNet		97.79 98	97.40 113	98.96 76	98.88 147	97.55 86	98.63 214	98.93 65	96.74 105	99.02 71	98.84 176	90.33 213	99.83 90	98.53 55	96.66 277	99.50 107

EIA-MVS		97.75 99	97.58 96	98.27 139	98.38 206	96.44 155	99.01 88	98.60 164	95.88 150	97.26 211	97.53 322	94.97 84	99.33 215	97.38 155	99.20 146	99.05 220

PS-MVSNAJ		97.73 100	97.77 89	97.62 225	98.68 171	95.58 216	97.34 395	98.51 194	97.29 67	98.66 109	97.88 286	94.51 91	99.90 64	97.87 102	99.17 148	97.39 326

casdiffmvs_mvg		97.72 101	97.48 107	98.44 126	98.42 199	96.59 148	98.92 116	98.44 215	96.20 133	97.76 178	99.20 93	91.66 158	99.23 243	98.27 82	98.41 205	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	97.32 120	98.92 79	99.64 33	97.10 122	99.12 64	98.81 107	92.34 361	98.09 140	99.08 134	93.01 117	99.92 43	96.06 212	99.77 41	99.75 48

PVSNet_Blended_VisFu		97.70 103	97.46 108	98.44 126	99.27 93	95.91 192	98.63 214	99.16 39	94.48 256	97.67 189	98.88 171	92.80 120	99.91 56	97.11 163	99.12 149	99.50 107

mvsany_test1		97.69 104	97.70 92	97.66 221	98.24 238	94.18 300	97.53 377	97.53 375	95.52 179	99.66 29	99.51 28	94.30 98	99.56 174	98.38 70	98.62 178	99.23 182

sasdasda		97.67 105	97.23 130	98.98 73	98.70 166	98.38 41	99.34 17	98.39 240	96.76 103	97.67 189	97.40 332	92.26 133	99.49 191	98.28 79	96.28 295	99.08 215

canonicalmvs		97.67 105	97.23 130	98.98 73	98.70 166	98.38 41	99.34 17	98.39 240	96.76 103	97.67 189	97.40 332	92.26 133	99.49 191	98.28 79	96.28 295	99.08 215

xiu_mvs_v2_base		97.66 107	97.70 92	97.56 229	98.61 180	95.46 225	97.44 383	98.46 207	97.15 82	98.65 110	98.15 261	94.33 97	99.80 109	97.84 105	98.66 177	97.41 324

GDP-MVS		97.64 108	97.28 123	98.71 93	98.30 225	97.33 98	99.05 75	98.52 191	96.34 128	98.80 92	99.05 141	89.74 227	99.51 187	96.86 184	98.86 165	99.28 170

baseline		97.64 108	97.44 110	98.25 143	98.35 211	96.20 168	99.00 90	98.32 262	96.33 130	98.03 148	99.17 105	91.35 171	99.16 254	98.10 87	98.29 215	99.39 137

casdiffmvs		97.63 110	97.41 112	98.28 138	98.33 220	96.14 172	98.82 154	98.32 262	96.38 126	97.95 159	99.21 91	91.23 178	99.23 243	98.12 86	98.37 208	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
MGCFI-Net		97.62 111	97.19 133	98.92 79	98.66 173	98.20 59	99.32 22	98.38 247	96.69 109	97.58 202	97.42 331	92.10 142	99.50 190	98.28 79	96.25 298	99.08 215

xiu_mvs_v1_base_debu		97.60 112	97.56 99	97.72 210	98.35 211	95.98 179	97.86 349	98.51 194	97.13 84	99.01 73	98.40 233	91.56 161	99.80 109	98.53 55	98.68 173	97.37 328

xiu_mvs_v1_base		97.60 112	97.56 99	97.72 210	98.35 211	95.98 179	97.86 349	98.51 194	97.13 84	99.01 73	98.40 233	91.56 161	99.80 109	98.53 55	98.68 173	97.37 328

xiu_mvs_v1_base_debi		97.60 112	97.56 99	97.72 210	98.35 211	95.98 179	97.86 349	98.51 194	97.13 84	99.01 73	98.40 233	91.56 161	99.80 109	98.53 55	98.68 173	97.37 328

diffmvs_AUTHOR		97.59 115	97.44 110	98.01 181	98.26 234	95.47 224	98.12 310	98.36 253	96.38 126	98.84 88	99.10 123	91.13 184	99.26 228	98.24 83	98.56 184	99.30 161

diffmvs		97.58 116	97.40 113	98.13 163	98.32 223	95.81 206	98.06 320	98.37 249	96.20 133	98.74 97	98.89 170	91.31 174	99.25 232	98.16 85	98.52 188	99.34 149
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		97.57 117	97.37 116	98.20 149	98.50 187	95.86 200	98.89 123	97.03 420	97.29 67	98.73 99	98.90 168	89.41 239	99.32 216	98.68 45	98.86 165	99.42 132

MVSFormer		97.57 117	97.49 105	97.84 197	98.07 264	95.76 210	99.47 7	98.40 234	94.98 222	98.79 93	98.83 180	92.34 129	98.41 365	96.91 172	99.59 94	99.34 149

alignmvs		97.56 119	97.07 146	99.01 70	98.66 173	98.37 48	98.83 152	98.06 327	96.74 105	98.00 154	97.65 309	90.80 195	99.48 196	98.37 71	96.56 281	99.19 191

E3new		97.55 120	97.35 118	98.16 154	98.48 192	95.85 201	98.55 237	98.41 231	95.42 186	98.06 143	99.12 118	92.23 136	99.24 239	97.43 148	98.45 194	99.39 137

DPM-MVS		97.55 120	96.99 153	99.23 49	99.04 129	98.55 33	97.17 413	98.35 254	94.85 232	97.93 163	98.58 216	95.07 81	99.71 142	92.60 346	99.34 137	99.43 129

OMC-MVS		97.55 120	97.34 119	98.20 149	99.33 74	95.92 191	98.28 283	98.59 171	95.52 179	97.97 157	99.10 123	93.28 115	99.49 191	95.09 251	98.88 162	99.19 191

balanced_ft_v1		97.54 123	97.38 115	98.02 179	98.34 216	95.58 216	99.32 22	98.40 234	95.88 150	98.43 126	98.65 209	88.95 259	99.59 167	98.94 35	99.48 120	98.90 237

viewcassd2359sk11		97.53 124	97.32 120	98.16 154	98.45 195	95.83 203	98.57 233	98.42 230	95.52 179	98.07 141	99.12 118	91.81 153	99.25 232	97.46 146	98.48 193	99.41 135

hybridcas		97.52 125	97.29 122	98.20 149	98.44 196	96.00 177	99.02 85	98.39 240	96.12 138	97.69 187	99.23 86	90.77 200	99.17 253	97.55 133	98.42 204	99.44 126

LuminaMVS		97.49 126	97.18 134	98.42 130	97.50 325	97.15 119	98.45 255	97.68 354	96.56 117	98.68 104	98.78 189	89.84 224	99.32 216	98.60 50	98.57 183	98.79 246

E2		97.48 127	97.25 125	98.16 154	98.40 203	95.79 207	98.58 224	98.44 215	95.58 168	98.00 154	99.14 112	91.21 183	99.24 239	97.50 141	98.43 198	99.45 123

E3		97.48 127	97.25 125	98.16 154	98.38 206	95.79 207	98.58 224	98.44 215	95.58 168	98.00 154	99.14 112	91.25 177	99.24 239	97.50 141	98.44 195	99.45 123

KinetiMVS		97.48 127	97.05 148	98.78 87	98.37 209	97.30 102	98.99 93	98.70 140	97.18 79	99.02 71	99.01 148	87.50 298	99.67 150	95.33 241	99.33 139	99.37 142

viewmanbaseed2359cas		97.47 130	97.25 125	98.14 158	98.41 201	95.84 202	98.57 233	98.43 226	95.55 175	97.97 157	99.12 118	91.26 176	99.15 258	97.42 150	98.53 187	99.43 129

PAPM_NR		97.46 131	97.11 143	98.50 118	99.50 48	96.41 158	98.63 214	98.60 164	95.18 202	97.06 223	98.06 267	94.26 100	99.57 171	93.80 305	98.87 164	99.52 101

EPP-MVSNet		97.46 131	97.28 123	97.99 183	98.64 177	95.38 233	99.33 21	98.31 266	93.61 309	97.19 215	99.07 138	94.05 103	99.23 243	96.89 176	98.43 198	99.37 142

3Dnovator	94.51 5	97.46 131	96.93 157	99.07 65	97.78 298	97.64 82	99.35 16	99.06 47	97.02 89	93.75 352	99.16 108	89.25 244	99.92 43	97.22 161	99.75 53	99.64 86

CNLPA		97.45 134	97.03 150	98.73 91	99.05 128	97.44 95	98.07 319	98.53 188	95.32 195	96.80 238	98.53 221	93.32 113	99.72 137	94.31 286	99.31 141	99.02 224

lupinMVS		97.44 135	97.22 132	98.12 166	98.07 264	95.76 210	97.68 366	97.76 351	94.50 255	98.79 93	98.61 211	92.34 129	99.30 221	97.58 128	99.59 94	99.31 157

3Dnovator+	94.38 6	97.43 136	96.78 168	99.38 24	97.83 295	98.52 34	99.37 13	98.71 137	97.09 87	92.99 382	99.13 115	89.36 241	99.89 68	96.97 168	99.57 98	99.71 63

Vis-MVSNet		97.42 137	97.11 143	98.34 135	98.66 173	96.23 167	99.22 42	99.00 53	96.63 113	98.04 147	99.21 91	88.05 285	99.35 212	96.01 215	99.21 145	99.45 123
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
API-MVS		97.41 138	97.25 125	97.91 191	98.70 166	96.80 134	98.82 154	98.69 142	94.53 250	98.11 138	98.28 248	94.50 94	99.57 171	94.12 294	99.49 117	97.37 328

sss		97.39 139	96.98 155	98.61 102	98.60 181	96.61 143	98.22 289	98.93 65	93.97 278	98.01 153	98.48 226	91.98 146	99.85 84	96.45 199	98.15 224	99.39 137

test_cas_vis1_n_1920		97.38 140	97.36 117	97.45 233	98.95 142	93.25 343	99.00 90	98.53 188	97.70 39	99.77 18	99.35 62	84.71 354	99.85 84	98.57 52	99.66 77	99.26 178

PVSNet_Blended		97.38 140	97.12 142	98.14 158	99.25 96	95.35 236	97.28 400	99.26 16	93.13 331	97.94 161	98.21 256	92.74 121	99.81 102	96.88 178	99.40 131	99.27 171

E5new		97.37 142	97.16 136	97.98 184	98.30 225	95.41 227	98.87 133	98.45 211	95.56 170	97.84 170	99.19 100	90.39 209	99.25 232	97.61 124	98.22 219	99.29 164

E6new		97.37 142	97.16 136	97.98 184	98.28 231	95.40 230	98.87 133	98.45 211	95.55 175	97.84 170	99.20 93	90.44 207	99.25 232	97.61 124	98.22 219	99.29 164

E6		97.37 142	97.16 136	97.98 184	98.28 231	95.40 230	98.87 133	98.45 211	95.55 175	97.84 170	99.20 93	90.44 207	99.25 232	97.61 124	98.22 219	99.29 164

E5		97.37 142	97.16 136	97.98 184	98.30 225	95.41 227	98.87 133	98.45 211	95.56 170	97.84 170	99.19 100	90.39 209	99.25 232	97.61 124	98.22 219	99.29 164

E4		97.37 142	97.13 141	98.12 166	98.27 233	95.70 212	98.59 220	98.44 215	95.56 170	97.80 175	99.18 103	90.57 204	99.26 228	97.45 147	98.28 217	99.40 136

WTY-MVS		97.37 142	96.92 158	98.72 92	98.86 151	96.89 132	98.31 277	98.71 137	95.26 198	97.67 189	98.56 220	92.21 138	99.78 124	95.89 217	96.85 271	99.48 114

hybrid		97.34 148	97.16 136	97.88 195	98.25 236	95.18 245	98.18 300	98.33 259	95.36 192	98.35 130	99.06 139	90.61 202	99.18 251	97.88 101	98.40 206	99.27 171

AstraMVS		97.34 148	97.24 129	97.65 222	98.13 258	94.15 301	98.94 107	96.25 453	97.47 56	98.60 113	99.28 76	89.67 229	99.41 206	98.73 43	98.07 228	99.38 141

viewmacassd2359aftdt		97.32 150	97.07 146	98.08 171	98.30 225	95.69 213	98.62 217	98.44 215	95.56 170	97.86 169	99.22 89	89.91 222	99.14 261	97.29 158	98.43 198	99.42 132

jason		97.32 150	97.08 145	98.06 175	97.45 331	95.59 215	97.87 347	97.91 338	94.79 235	98.55 116	98.83 180	91.12 186	99.23 243	97.58 128	99.60 92	99.34 149
jason: jason.
MVS_Test		97.28 152	97.00 151	98.13 163	98.33 220	95.97 184	98.74 180	98.07 322	94.27 263	98.44 124	98.07 266	92.48 125	99.26 228	96.43 200	98.19 223	99.16 197

EPNet		97.28 152	96.87 160	98.51 115	94.98 444	96.14 172	98.90 119	97.02 423	98.28 21	95.99 273	99.11 121	91.36 170	99.89 68	96.98 167	99.19 147	99.50 107
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SSM_0404		97.26 154	97.00 151	98.03 177	98.46 193	95.99 178	98.62 217	98.44 215	94.77 236	97.24 212	98.93 162	91.22 179	99.28 225	96.54 194	98.74 172	98.84 242

mvsmamba		97.25 155	96.99 153	98.02 179	98.34 216	95.54 221	99.18 54	97.47 381	95.04 215	98.15 135	98.57 219	89.46 236	99.31 220	97.68 118	99.01 155	99.22 184

viewdifsd2359ckpt13		97.24 156	96.97 156	98.06 175	98.43 197	95.77 209	98.59 220	98.34 257	94.81 233	97.60 200	98.94 160	90.78 199	99.09 273	96.93 171	98.33 211	99.32 156

test_yl		97.22 157	96.78 168	98.54 110	98.73 161	96.60 144	98.45 255	98.31 266	94.70 239	98.02 150	98.42 231	90.80 195	99.70 143	96.81 185	96.79 273	99.34 149

DCV-MVSNet		97.22 157	96.78 168	98.54 110	98.73 161	96.60 144	98.45 255	98.31 266	94.70 239	98.02 150	98.42 231	90.80 195	99.70 143	96.81 185	96.79 273	99.34 149

IS-MVSNet		97.22 157	96.88 159	98.25 143	98.85 154	96.36 161	99.19 50	97.97 332	95.39 188	97.23 213	98.99 151	91.11 187	98.93 303	94.60 274	98.59 180	99.47 116

viewdifsd2359ckpt07		97.20 160	97.05 148	97.65 222	98.40 203	94.33 293	98.39 268	98.43 226	95.67 163	97.66 193	99.08 134	90.04 219	99.32 216	97.47 145	98.29 215	99.31 157

PLC	95.07 4	97.20 160	96.78 168	98.44 126	99.29 88	96.31 165	98.14 307	98.76 125	92.41 359	96.39 261	98.31 246	94.92 86	99.78 124	94.06 297	98.77 171	99.23 182
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		97.18 162	97.18 134	97.20 246	98.81 157	93.27 340	95.78 462	99.15 41	95.25 199	96.79 239	98.11 264	92.29 132	99.07 276	98.56 54	99.85 6	99.25 180

SSM_0407		97.17 163	96.87 160	98.08 171	98.19 246	95.90 193	98.52 240	98.44 215	94.77 236	96.75 240	98.93 162	91.22 179	99.22 247	96.54 194	98.43 198	99.10 208

LS3D		97.16 164	96.66 177	98.68 95	98.53 186	97.19 116	98.93 113	98.90 73	92.83 344	95.99 273	99.37 56	92.12 141	99.87 79	93.67 309	99.57 98	98.97 229

AdaColmap		97.15 165	96.70 173	98.48 121	99.16 115	96.69 140	98.01 326	98.89 75	94.44 258	96.83 234	98.68 205	90.69 201	99.76 130	94.36 282	99.29 142	98.98 228

viewdifsd2359ckpt09		97.13 166	96.79 166	98.14 158	98.43 197	95.90 193	98.52 240	98.37 249	94.32 261	97.33 207	98.86 174	90.23 217	99.16 254	96.81 185	98.25 218	99.36 146

Effi-MVS+		97.12 167	96.69 174	98.39 133	98.19 246	96.72 139	97.37 391	98.43 226	93.71 296	97.65 194	98.02 270	92.20 139	99.25 232	96.87 181	97.79 237	99.19 191

CHOSEN 1792x2688		97.12 167	96.80 164	98.08 171	99.30 83	94.56 282	98.05 321	99.71 1	93.57 311	97.09 219	98.91 167	88.17 279	99.89 68	96.87 181	99.56 106	99.81 25

F-COLMAP		97.09 169	96.80 164	97.97 188	99.45 61	94.95 261	98.55 237	98.62 163	93.02 336	96.17 268	98.58 216	94.01 104	99.81 102	93.95 299	98.90 160	99.14 201

RRT-MVS		97.03 170	96.78 168	97.77 206	97.90 291	94.34 291	99.12 64	98.35 254	95.87 152	98.06 143	98.70 203	86.45 317	99.63 160	98.04 92	98.54 186	99.35 147

TAMVS		97.02 171	96.79 166	97.70 213	98.06 267	95.31 239	98.52 240	98.31 266	93.95 279	97.05 224	98.61 211	93.49 111	98.52 347	95.33 241	97.81 236	99.29 164

viewmambaseed2359dif		97.01 172	96.84 162	97.51 231	98.19 246	94.21 299	98.16 303	98.23 287	93.61 309	97.78 176	99.13 115	90.79 198	99.18 251	97.24 159	98.40 206	99.15 198

CDS-MVSNet		96.99 173	96.69 174	97.90 192	98.05 269	95.98 179	98.20 292	98.33 259	93.67 303	96.95 226	98.49 225	93.54 110	98.42 358	95.24 248	97.74 241	99.31 157
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
casdiffseed414692147		96.97 174	96.55 182	98.25 143	98.26 234	96.28 166	98.93 113	98.33 259	94.99 220	96.87 233	99.09 131	88.97 257	99.07 276	95.70 230	97.77 239	99.39 137

CANet_DTU		96.96 175	96.55 182	98.21 147	98.17 255	96.07 176	97.98 330	98.21 289	97.24 74	97.13 217	98.93 162	86.88 309	99.91 56	95.00 254	99.37 135	98.66 269

114514_t		96.93 176	96.27 196	98.92 79	99.50 48	97.63 83	98.85 146	98.90 73	84.80 469	97.77 177	99.11 121	92.84 119	99.66 153	94.85 257	99.77 41	99.47 116

MAR-MVS		96.91 177	96.40 190	98.45 124	98.69 169	96.90 130	98.66 208	98.68 145	92.40 360	97.07 222	97.96 277	91.54 164	99.75 132	93.68 307	98.92 159	98.69 263
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		96.90 178	96.49 187	98.14 158	99.33 74	95.56 218	97.38 389	99.65 2	92.34 361	97.61 197	98.20 257	89.29 243	99.10 272	96.97 168	97.60 246	99.77 40

Vis-MVSNet (Re-imp)		96.87 179	96.55 182	97.83 198	98.73 161	95.46 225	99.20 48	98.30 273	94.96 224	96.60 249	98.87 172	90.05 218	98.59 342	93.67 309	98.60 179	99.46 121

SDMVSNet		96.85 180	96.42 188	98.14 158	99.30 83	96.38 159	99.21 45	99.23 27	95.92 147	95.96 275	98.76 197	85.88 329	99.44 203	97.93 96	95.59 310	98.60 274

PAPR		96.84 181	96.24 198	98.65 98	98.72 165	96.92 129	97.36 393	98.57 178	93.33 320	96.67 244	97.57 318	94.30 98	99.56 174	91.05 389	98.59 180	99.47 116

HY-MVS	93.96 8	96.82 182	96.23 199	98.57 105	98.46 193	97.00 125	98.14 307	98.21 289	93.95 279	96.72 243	97.99 274	91.58 159	99.76 130	94.51 278	96.54 282	98.95 232

mamba_0408		96.81 183	96.38 191	98.09 170	98.19 246	95.90 193	95.69 463	98.32 262	94.51 253	96.75 240	98.73 199	90.99 191	99.27 227	95.83 220	98.43 198	99.10 208

UGNet		96.78 184	96.30 195	98.19 153	98.24 238	95.89 198	98.88 130	98.93 65	97.39 61	96.81 237	97.84 290	82.60 383	99.90 64	96.53 196	99.49 117	98.79 246
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		96.74 185	96.64 178	97.05 261	97.99 278	92.82 357	98.45 255	98.27 276	95.16 203	97.30 208	98.79 185	91.53 165	99.06 278	94.74 262	97.54 250	99.27 171

IMVS_0403		96.74 185	96.61 179	97.12 255	97.99 278	92.82 357	98.47 253	98.27 276	95.16 203	97.13 217	98.79 185	91.44 168	99.26 228	94.74 262	97.54 250	99.27 171

PVSNet_BlendedMVS		96.73 187	96.60 180	97.12 255	99.25 96	95.35 236	98.26 286	99.26 16	94.28 262	97.94 161	97.46 325	92.74 121	99.81 102	96.88 178	93.32 348	96.20 430

SSM_04072		96.71 188	96.38 191	97.68 216	98.19 246	95.90 193	95.69 463	98.32 262	94.51 253	96.75 240	98.73 199	90.99 191	98.02 414	95.83 220	98.43 198	99.10 208

test_vis1_n_1920		96.71 188	96.84 162	96.31 337	99.11 123	89.74 425	99.05 75	98.58 176	98.08 24	99.87 4	99.37 56	78.48 421	99.93 34	99.29 27	99.69 71	99.27 171

mvs_anonymous		96.70 190	96.53 185	97.18 249	98.19 246	93.78 311	98.31 277	98.19 293	94.01 275	94.47 307	98.27 251	92.08 144	98.46 353	97.39 154	97.91 232	99.31 157

Elysia		96.64 191	96.02 208	98.51 115	98.04 271	97.30 102	98.74 180	98.60 164	95.04 215	97.91 165	98.84 176	83.59 378	99.48 196	94.20 290	99.25 143	98.75 255

StellarMVS		96.64 191	96.02 208	98.51 115	98.04 271	97.30 102	98.74 180	98.60 164	95.04 215	97.91 165	98.84 176	83.59 378	99.48 196	94.20 290	99.25 143	98.75 255

1112_ss		96.63 193	96.00 210	98.50 118	98.56 182	96.37 160	98.18 300	98.10 315	92.92 340	94.84 295	98.43 229	92.14 140	99.58 170	94.35 283	96.51 283	99.56 100

PMMVS		96.60 194	96.33 194	97.41 237	97.90 291	93.93 307	97.35 394	98.41 231	92.84 343	97.76 178	97.45 327	91.10 188	99.20 248	96.26 205	97.91 232	99.11 206

DP-MVS		96.59 195	95.93 213	98.57 105	99.34 71	96.19 170	98.70 195	98.39 240	89.45 431	94.52 305	99.35 62	91.85 150	99.85 84	92.89 334	98.88 162	99.68 75

PatchMatch-RL		96.59 195	96.03 207	98.27 139	99.31 79	96.51 152	97.91 339	99.06 47	93.72 295	96.92 230	98.06 267	88.50 272	99.65 154	91.77 371	99.00 157	98.66 269

GeoE		96.58 197	96.07 204	98.10 169	98.35 211	95.89 198	99.34 17	98.12 309	93.12 332	96.09 269	98.87 172	89.71 228	98.97 293	92.95 330	98.08 227	99.43 129

icg_test_0407_2		96.56 198	96.50 186	96.73 286	97.99 278	92.82 357	97.18 410	98.27 276	95.16 203	97.30 208	98.79 185	91.53 165	98.10 399	94.74 262	97.54 250	99.27 171

XVG-OURS		96.55 199	96.41 189	96.99 264	98.75 160	93.76 312	97.50 380	98.52 191	95.67 163	96.83 234	99.30 74	88.95 259	99.53 183	95.88 218	96.26 297	97.69 317

FIs		96.51 200	96.12 203	97.67 218	97.13 355	97.54 88	99.36 14	99.22 32	95.89 149	94.03 336	98.35 239	91.98 146	98.44 356	96.40 201	92.76 356	97.01 336

XVG-OURS-SEG-HR		96.51 200	96.34 193	97.02 263	98.77 159	93.76 312	97.79 358	98.50 199	95.45 183	96.94 227	99.09 131	87.87 290	99.55 181	96.76 190	95.83 309	97.74 314

PS-MVSNAJss		96.43 202	96.26 197	96.92 275	95.84 424	95.08 251	99.16 56	98.50 199	95.87 152	93.84 347	98.34 243	94.51 91	98.61 338	96.88 178	93.45 343	97.06 334

test_fmvs1		96.42 203	96.67 176	95.66 374	98.82 156	88.53 452	98.80 163	98.20 291	96.39 125	99.64 31	99.20 93	80.35 408	99.67 150	99.04 32	99.57 98	98.78 250

FC-MVSNet-test		96.42 203	96.05 205	97.53 230	96.95 364	97.27 106	99.36 14	99.23 27	95.83 154	93.93 339	98.37 237	92.00 145	98.32 377	96.02 214	92.72 357	97.00 337

ab-mvs		96.42 203	95.71 224	98.55 108	98.63 178	96.75 137	97.88 346	98.74 129	93.84 285	96.54 254	98.18 259	85.34 340	99.75 132	95.93 216	96.35 287	99.15 198

FA-MVS(test-final)		96.41 206	95.94 212	97.82 200	98.21 242	95.20 244	97.80 356	97.58 365	93.21 326	97.36 206	97.70 302	89.47 234	99.56 174	94.12 294	97.99 229	98.71 261

PVSNet	91.96 18	96.35 207	96.15 200	96.96 270	99.17 111	92.05 377	96.08 455	98.68 145	93.69 299	97.75 180	97.80 296	88.86 261	99.69 148	94.26 288	99.01 155	99.15 198

Test_1112_low_res		96.34 208	95.66 229	98.36 134	98.56 182	95.94 187	97.71 364	98.07 322	92.10 370	94.79 299	97.29 340	91.75 154	99.56 174	94.17 292	96.50 284	99.58 98

viewdifsd2359ckpt11		96.30 209	96.13 201	96.81 281	98.10 261	92.10 373	98.49 251	98.40 234	96.02 142	97.61 197	99.31 71	86.37 319	99.29 223	97.52 137	93.36 347	99.04 221

viewmsd2359difaftdt		96.30 209	96.13 201	96.81 281	98.10 261	92.10 373	98.49 251	98.40 234	96.02 142	97.61 197	99.31 71	86.37 319	99.30 221	97.52 137	93.37 346	99.04 221

Effi-MVS+-dtu		96.29 211	96.56 181	95.51 379	97.89 293	90.22 417	98.80 163	98.10 315	96.57 116	96.45 259	96.66 397	90.81 194	98.91 306	95.72 227	97.99 229	97.40 325

QAPM		96.29 211	95.40 235	98.96 76	97.85 294	97.60 85	99.23 38	98.93 65	89.76 425	93.11 379	99.02 144	89.11 249	99.93 34	91.99 365	99.62 89	99.34 149

Fast-Effi-MVS+		96.28 213	95.70 226	98.03 177	98.29 229	95.97 184	98.58 224	98.25 285	91.74 378	95.29 288	97.23 345	91.03 190	99.15 258	92.90 332	97.96 231	98.97 229

nrg030		96.28 213	95.72 221	97.96 190	96.90 369	98.15 64	99.39 11	98.31 266	95.47 182	94.42 313	98.35 239	92.09 143	98.69 330	97.50 141	89.05 409	97.04 335

1314		96.25 215	95.73 220	97.79 202	97.13 355	95.55 220	98.19 295	98.59 171	93.47 315	92.03 415	97.82 294	91.33 172	99.49 191	94.62 272	98.44 195	98.32 294

sd_testset		96.17 216	95.76 219	97.42 236	99.30 83	94.34 291	98.82 154	99.08 45	95.92 147	95.96 275	98.76 197	82.83 382	99.32 216	95.56 234	95.59 310	98.60 274

h-mvs33		96.17 216	95.62 230	97.81 201	99.03 130	94.45 284	98.64 211	98.75 127	97.48 54	98.67 105	98.72 202	89.76 225	99.86 83	97.95 94	81.59 459	99.11 206

HQP_MVS		96.14 218	95.90 214	96.85 278	97.42 333	94.60 280	98.80 163	98.56 182	97.28 69	95.34 284	98.28 248	87.09 304	99.03 285	96.07 209	94.27 318	96.92 344

tttt0517		96.07 219	95.51 233	97.78 203	98.41 201	94.84 265	99.28 30	94.33 479	94.26 264	97.64 195	98.64 210	84.05 369	99.47 200	95.34 240	97.60 246	99.03 223

MVSTER		96.06 220	95.72 221	97.08 259	98.23 240	95.93 190	98.73 186	98.27 276	94.86 230	95.07 290	98.09 265	88.21 278	98.54 345	96.59 192	93.46 341	96.79 363

thisisatest0530		96.01 221	95.36 240	97.97 188	98.38 206	95.52 222	98.88 130	94.19 482	94.04 270	97.64 195	98.31 246	83.82 376	99.46 201	95.29 245	97.70 243	98.93 234

test_djsdf		96.00 222	95.69 227	96.93 272	95.72 426	95.49 223	99.47 7	98.40 234	94.98 222	94.58 303	97.86 287	89.16 247	98.41 365	96.91 172	94.12 326	96.88 353

EI-MVSNet		95.96 223	95.83 216	96.36 333	97.93 289	93.70 318	98.12 310	98.27 276	93.70 298	95.07 290	99.02 144	92.23 136	98.54 345	94.68 267	93.46 341	96.84 359

VortexMVS		95.95 224	95.79 217	96.42 328	98.29 229	93.96 306	98.68 201	98.31 266	96.02 142	94.29 321	97.57 318	89.47 234	98.37 372	97.51 140	91.93 366	96.94 342

ECVR-MVS		95.95 224	95.71 224	96.65 295	99.02 131	90.86 399	99.03 82	91.80 495	96.96 93	98.10 139	99.26 80	81.31 394	99.51 187	96.90 175	99.04 152	99.59 94

BH-untuned		95.95 224	95.72 221	96.65 295	98.55 184	92.26 368	98.23 288	97.79 350	93.73 293	94.62 302	98.01 272	88.97 257	99.00 292	93.04 327	98.51 189	98.68 265

test1111		95.94 227	95.78 218	96.41 329	98.99 138	90.12 418	99.04 79	92.45 494	96.99 92	98.03 148	99.27 79	81.40 393	99.48 196	96.87 181	99.04 152	99.63 88

MSDG		95.93 228	95.30 247	97.83 198	98.90 145	95.36 234	96.83 442	98.37 249	91.32 394	94.43 312	98.73 199	90.27 215	99.60 166	90.05 403	98.82 169	98.52 282

BH-RMVSNet		95.92 229	95.32 245	97.69 214	98.32 223	94.64 274	98.19 295	97.45 386	94.56 248	96.03 271	98.61 211	85.02 345	99.12 266	90.68 394	99.06 151	99.30 161

test_fmvs1_n		95.90 230	95.99 211	95.63 375	98.67 172	88.32 456	99.26 33	98.22 288	96.40 124	99.67 28	99.26 80	73.91 463	99.70 143	99.02 33	99.50 115	98.87 239

Fast-Effi-MVS+-dtu		95.87 231	95.85 215	95.91 359	97.74 303	91.74 383	98.69 198	98.15 305	95.56 170	94.92 293	97.68 307	88.98 256	98.79 324	93.19 321	97.78 238	97.20 332

LFMVS		95.86 232	94.98 262	98.47 122	98.87 150	96.32 163	98.84 150	96.02 454	93.40 318	98.62 111	99.20 93	74.99 455	99.63 160	97.72 111	97.20 259	99.46 121

baseline1		95.84 233	95.12 255	98.01 181	98.49 191	95.98 179	98.73 186	97.03 420	95.37 191	96.22 264	98.19 258	89.96 221	99.16 254	94.60 274	87.48 425	98.90 237

OpenMVS	93.04 13	95.83 234	95.00 260	98.32 136	97.18 352	97.32 99	99.21 45	98.97 57	89.96 421	91.14 424	99.05 141	86.64 312	99.92 43	93.38 315	99.47 121	97.73 315

IMVS_0404		95.82 235	95.52 231	96.73 286	97.99 278	92.82 357	97.23 402	98.27 276	95.16 203	94.31 319	98.79 185	85.63 333	98.10 399	94.74 262	97.54 250	99.27 171

VDD-MVS		95.82 235	95.23 249	97.61 226	98.84 155	93.98 305	98.68 201	97.40 390	95.02 219	97.95 159	99.34 68	74.37 461	99.78 124	98.64 48	96.80 272	99.08 215

UniMVSNet (Re)		95.78 237	95.19 251	97.58 227	96.99 362	97.47 92	98.79 171	99.18 36	95.60 166	93.92 340	97.04 367	91.68 156	98.48 349	95.80 224	87.66 424	96.79 363

VPA-MVSNet		95.75 238	95.11 256	97.69 214	97.24 344	97.27 106	98.94 107	99.23 27	95.13 208	95.51 282	97.32 338	85.73 331	98.91 306	97.33 157	89.55 400	96.89 352

HQP-MVS		95.72 239	95.40 235	96.69 292	97.20 348	94.25 297	98.05 321	98.46 207	96.43 120	94.45 308	97.73 299	86.75 310	98.96 297	95.30 243	94.18 322	96.86 358

hse-mvs2		95.71 240	95.30 247	96.93 272	98.50 187	93.53 323	98.36 269	98.10 315	97.48 54	98.67 105	97.99 274	89.76 225	99.02 289	97.95 94	80.91 465	98.22 297

UniMVSNet_NR-MVSNet		95.71 240	95.15 252	97.40 239	96.84 372	96.97 126	98.74 180	99.24 20	95.16 203	93.88 342	97.72 301	91.68 156	98.31 379	95.81 222	87.25 430	96.92 344

PatchmatchNet		95.71 240	95.52 231	96.29 339	97.58 316	90.72 403	96.84 441	97.52 376	94.06 269	97.08 220	96.96 377	89.24 245	98.90 309	92.03 364	98.37 208	99.26 178
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
OPM-MVS		95.69 243	95.33 244	96.76 285	96.16 408	94.63 275	98.43 263	98.39 240	96.64 112	95.02 292	98.78 189	85.15 344	99.05 279	95.21 250	94.20 321	96.60 389
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMM	93.85 9	95.69 243	95.38 239	96.61 303	97.61 313	93.84 310	98.91 118	98.44 215	95.25 199	94.28 322	98.47 227	86.04 328	99.12 266	95.50 237	93.95 331	96.87 356
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpmrst		95.63 245	95.69 227	95.44 383	97.54 321	88.54 451	96.97 425	97.56 368	93.50 313	97.52 204	96.93 381	89.49 232	99.16 254	95.25 247	96.42 286	98.64 271

FE-MVS		95.62 246	94.90 266	97.78 203	98.37 209	94.92 262	97.17 413	97.38 392	90.95 405	97.73 183	97.70 302	85.32 342	99.63 160	91.18 381	98.33 211	98.79 246

LPG-MVS_test		95.62 246	95.34 241	96.47 322	97.46 328	93.54 321	98.99 93	98.54 186	94.67 243	94.36 316	98.77 192	85.39 337	99.11 268	95.71 228	94.15 324	96.76 366

CLD-MVS		95.62 246	95.34 241	96.46 325	97.52 324	93.75 314	97.27 401	98.46 207	95.53 178	94.42 313	98.00 273	86.21 323	98.97 293	96.25 207	94.37 316	96.66 381
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		95.61 249	94.89 267	97.76 207	98.15 257	95.15 248	96.77 443	94.41 477	92.95 339	97.18 216	97.43 329	84.78 351	99.45 202	94.63 270	97.73 242	98.68 265

MonoMVSNet		95.51 250	95.45 234	95.68 372	95.54 431	90.87 398	98.92 116	97.37 393	95.79 156	95.53 281	97.38 334	89.58 231	97.68 437	96.40 201	92.59 358	98.49 284

thres600view7		95.49 251	94.77 270	97.67 218	98.98 139	95.02 253	98.85 146	96.90 430	95.38 189	96.63 246	96.90 383	84.29 361	99.59 167	88.65 427	96.33 288	98.40 288

test_vis1_n		95.47 252	95.13 253	96.49 319	97.77 299	90.41 413	99.27 32	98.11 312	96.58 114	99.66 29	99.18 103	67.00 478	99.62 164	99.21 28	99.40 131	99.44 126

SCA		95.46 253	95.13 253	96.46 325	97.67 308	91.29 391	97.33 396	97.60 364	94.68 242	96.92 230	97.10 352	83.97 371	98.89 310	92.59 348	98.32 214	99.20 187

IterMVS-LS		95.46 253	95.21 250	96.22 341	98.12 259	93.72 317	98.32 276	98.13 308	93.71 296	94.26 323	97.31 339	92.24 135	98.10 399	94.63 270	90.12 391	96.84 359
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing3-2		95.45 255	95.34 241	95.77 370	98.69 169	88.75 447	98.87 133	97.21 407	96.13 136	97.22 214	97.68 307	77.95 429	99.65 154	97.58 128	96.77 275	98.91 236

jajsoiax		95.45 255	95.03 259	96.73 286	95.42 439	94.63 275	99.14 60	98.52 191	95.74 158	93.22 372	98.36 238	83.87 374	98.65 335	96.95 170	94.04 327	96.91 349

CVMVSNet		95.43 257	96.04 206	93.57 436	97.93 289	83.62 476	98.12 310	98.59 171	95.68 162	96.56 250	99.02 144	87.51 296	97.51 446	93.56 313	97.44 255	99.60 92

anonymousdsp		95.42 258	94.91 265	96.94 271	95.10 443	95.90 193	99.14 60	98.41 231	93.75 290	93.16 375	97.46 325	87.50 298	98.41 365	95.63 233	94.03 328	96.50 414

DU-MVS		95.42 258	94.76 271	97.40 239	96.53 389	96.97 126	98.66 208	98.99 56	95.43 184	93.88 342	97.69 304	88.57 267	98.31 379	95.81 222	87.25 430	96.92 344

mvs_tets		95.41 260	95.00 260	96.65 295	95.58 430	94.42 286	99.00 90	98.55 184	95.73 160	93.21 373	98.38 236	83.45 380	98.63 336	97.09 164	94.00 329	96.91 349

thres100view900		95.38 261	94.70 275	97.41 237	98.98 139	94.92 262	98.87 133	96.90 430	95.38 189	96.61 248	96.88 384	84.29 361	99.56 174	88.11 430	96.29 292	97.76 312

thres400		95.38 261	94.62 279	97.65 222	98.94 143	94.98 258	98.68 201	96.93 428	95.33 193	96.55 252	96.53 403	84.23 365	99.56 174	88.11 430	96.29 292	98.40 288

BH-w/o		95.38 261	95.08 257	96.26 340	98.34 216	91.79 380	97.70 365	97.43 388	92.87 342	94.24 325	97.22 346	88.66 265	98.84 316	91.55 377	97.70 243	98.16 301

VDDNet		95.36 264	94.53 284	97.86 196	98.10 261	95.13 249	98.85 146	97.75 352	90.46 412	98.36 128	99.39 50	73.27 465	99.64 157	97.98 93	96.58 280	98.81 245

TAPA-MVS	93.98 7	95.35 265	94.56 283	97.74 209	99.13 119	94.83 267	98.33 272	98.64 158	86.62 457	96.29 263	98.61 211	94.00 105	99.29 223	80.00 474	99.41 128	99.09 211
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ACMP	93.49 10	95.34 266	94.98 262	96.43 327	97.67 308	93.48 325	98.73 186	98.44 215	94.94 228	92.53 396	98.53 221	84.50 360	99.14 261	95.48 238	94.00 329	96.66 381
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
COLMAP_ROB	93.27 12	95.33 267	94.87 268	96.71 289	99.29 88	93.24 344	98.58 224	98.11 312	89.92 422	93.57 357	99.10 123	86.37 319	99.79 121	90.78 392	98.10 226	97.09 333
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
UBG		95.32 268	94.72 274	97.13 253	98.05 269	93.26 341	97.87 347	97.20 408	94.96 224	96.18 267	95.66 439	80.97 400	99.35 212	94.47 280	97.08 262	98.78 250

tfpn200view9		95.32 268	94.62 279	97.43 235	98.94 143	94.98 258	98.68 201	96.93 428	95.33 193	96.55 252	96.53 403	84.23 365	99.56 174	88.11 430	96.29 292	97.76 312

Anonymous202405211		95.28 270	94.49 286	97.67 218	99.00 135	93.75 314	98.70 195	97.04 419	90.66 408	96.49 256	98.80 183	78.13 425	99.83 90	96.21 208	95.36 314	99.44 126

thres200		95.25 271	94.57 282	97.28 243	98.81 157	94.92 262	98.20 292	97.11 412	95.24 201	96.54 254	96.22 416	84.58 358	99.53 183	87.93 435	96.50 284	97.39 326

AllTest		95.24 272	94.65 278	96.99 264	99.25 96	93.21 345	98.59 220	98.18 296	91.36 390	93.52 359	98.77 192	84.67 355	99.72 137	89.70 410	97.87 234	98.02 306

LCM-MVSNet-Re		95.22 273	95.32 245	94.91 400	98.18 252	87.85 462	98.75 176	95.66 461	95.11 210	88.96 447	96.85 387	90.26 216	97.65 438	95.65 232	98.44 195	99.22 184

EPNet_dtu		95.21 274	94.95 264	95.99 352	96.17 406	90.45 411	98.16 303	97.27 402	96.77 102	93.14 378	98.33 244	90.34 212	98.42 358	85.57 449	98.81 170	99.09 211
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
XXY-MVS		95.20 275	94.45 292	97.46 232	96.75 379	96.56 150	98.86 141	98.65 157	93.30 323	93.27 371	98.27 251	84.85 349	98.87 313	94.82 259	91.26 377	96.96 339

D2MVS		95.18 276	95.08 257	95.48 380	97.10 357	92.07 376	98.30 280	99.13 43	94.02 272	92.90 383	96.73 393	89.48 233	98.73 328	94.48 279	93.60 340	95.65 445

WR-MVS		95.15 277	94.46 289	97.22 245	96.67 384	96.45 154	98.21 290	98.81 107	94.15 266	93.16 375	97.69 304	87.51 296	98.30 381	95.29 245	88.62 415	96.90 351

TranMVSNet+NR-MVSNet		95.14 278	94.48 287	97.11 257	96.45 395	96.36 161	99.03 82	99.03 50	95.04 215	93.58 356	97.93 280	88.27 277	98.03 413	94.13 293	86.90 435	96.95 341

myMVS_eth3d28		95.12 279	94.62 279	96.64 299	98.17 255	92.17 369	98.02 325	97.32 396	95.41 187	96.22 264	96.05 422	78.01 427	99.13 263	95.22 249	97.16 260	98.60 274

baseline2		95.11 280	94.52 285	96.87 277	96.65 385	93.56 320	98.27 285	94.10 484	93.45 316	92.02 416	97.43 329	87.45 301	99.19 249	93.88 302	97.41 257	97.87 310

miper_enhance_ethall		95.10 281	94.75 272	96.12 345	97.53 323	93.73 316	96.61 449	98.08 320	92.20 369	93.89 341	96.65 399	92.44 126	98.30 381	94.21 289	91.16 378	96.34 423

Anonymous20240529		95.10 281	94.22 304	97.75 208	99.01 133	94.26 296	98.87 133	98.83 98	85.79 465	96.64 245	98.97 152	78.73 418	99.85 84	96.27 204	94.89 315	99.12 203

test-LLR		95.10 281	94.87 268	95.80 367	96.77 376	89.70 427	96.91 430	95.21 466	95.11 210	94.83 297	95.72 435	87.71 292	98.97 293	93.06 325	98.50 190	98.72 258

WR-MVS_H		95.05 284	94.46 289	96.81 281	96.86 371	95.82 205	99.24 36	99.24 20	93.87 284	92.53 396	96.84 388	90.37 211	98.24 387	93.24 319	87.93 421	96.38 422

miper_ehance_all_eth		95.01 285	94.69 276	95.97 356	97.70 306	93.31 337	97.02 423	98.07 322	92.23 366	93.51 361	96.96 377	91.85 150	98.15 394	93.68 307	91.16 378	96.44 420

testing11		95.00 286	94.28 299	97.16 251	97.96 286	93.36 334	98.09 317	97.06 418	94.94 228	95.33 287	96.15 418	76.89 442	99.40 207	95.77 226	96.30 291	98.72 258

ADS-MVSNet		95.00 286	94.45 292	96.63 300	98.00 276	91.91 379	96.04 456	97.74 353	90.15 418	96.47 257	96.64 400	87.89 288	98.96 297	90.08 401	97.06 263	99.02 224

VPNet		94.99 288	94.19 306	97.40 239	97.16 353	96.57 149	98.71 191	98.97 57	95.67 163	94.84 295	98.24 255	80.36 407	98.67 334	96.46 198	87.32 429	96.96 339

EPMVS		94.99 288	94.48 287	96.52 316	97.22 346	91.75 382	97.23 402	91.66 496	94.11 267	97.28 210	96.81 390	85.70 332	98.84 316	93.04 327	97.28 258	98.97 229

testing91		94.98 290	94.25 303	97.20 246	97.94 287	93.41 328	98.00 328	97.58 365	94.99 220	95.45 283	96.04 423	77.20 437	99.42 205	94.97 255	96.02 305	98.78 250

NR-MVSNet		94.98 290	94.16 309	97.44 234	96.53 389	97.22 114	98.74 180	98.95 61	94.96 224	89.25 445	97.69 304	89.32 242	98.18 391	94.59 276	87.40 427	96.92 344

FMVSNet3		94.97 292	94.26 302	97.11 257	98.18 252	96.62 141	98.56 236	98.26 284	93.67 303	94.09 332	97.10 352	84.25 363	98.01 415	92.08 360	92.14 363	96.70 375

usedtu_dtu_shiyan1		94.96 293	94.28 299	96.98 267	95.93 419	96.11 174	97.08 419	98.39 240	93.62 307	93.86 344	96.40 408	88.28 275	98.21 388	92.61 343	92.36 361	96.63 383

FE-MVSNET3		94.96 293	94.28 299	96.98 267	95.93 419	96.11 174	97.08 419	98.39 240	93.62 307	93.86 344	96.40 408	88.28 275	98.21 388	92.61 343	92.36 361	96.63 383

CostFormer		94.95 295	94.73 273	95.60 377	97.28 342	89.06 440	97.53 377	96.89 432	89.66 427	96.82 236	96.72 394	86.05 326	98.95 302	95.53 236	96.13 303	98.79 246

PAPM		94.95 295	94.00 322	97.78 203	97.04 359	95.65 214	96.03 458	98.25 285	91.23 399	94.19 328	97.80 296	91.27 175	98.86 315	82.61 466	97.61 245	98.84 242

CP-MVSNet		94.94 297	94.30 298	96.83 279	96.72 381	95.56 218	99.11 66	98.95 61	93.89 282	92.42 402	97.90 283	87.19 303	98.12 398	94.32 285	88.21 418	96.82 362

TR-MVS		94.94 297	94.20 305	97.17 250	97.75 300	94.14 302	97.59 374	97.02 423	92.28 365	95.75 279	97.64 312	83.88 373	98.96 297	89.77 407	96.15 302	98.40 288

RPSCF		94.87 299	95.40 235	93.26 442	98.89 146	82.06 482	98.33 272	98.06 327	90.30 417	96.56 250	99.26 80	87.09 304	99.49 191	93.82 304	96.32 289	98.24 295

testing99		94.83 300	94.08 314	97.07 260	97.94 287	93.13 347	98.10 316	97.17 410	94.86 230	95.34 284	96.00 427	76.31 445	99.40 207	95.08 252	95.90 306	98.68 265

GA-MVS		94.81 301	94.03 318	97.14 252	97.15 354	93.86 309	96.76 444	97.58 365	94.00 276	94.76 301	97.04 367	80.91 401	98.48 349	91.79 370	96.25 298	99.09 211

c3_l		94.79 302	94.43 294	95.89 361	97.75 300	93.12 349	97.16 415	98.03 329	92.23 366	93.46 365	97.05 366	91.39 169	98.01 415	93.58 312	89.21 407	96.53 405

V42		94.78 303	94.14 311	96.70 291	96.33 400	95.22 243	98.97 97	98.09 319	92.32 363	94.31 319	97.06 363	88.39 273	98.55 344	92.90 332	88.87 413	96.34 423

reproduce_monomvs		94.77 304	94.67 277	95.08 395	98.40 203	89.48 433	98.80 163	98.64 158	97.57 48	93.21 373	97.65 309	80.57 406	98.83 319	97.72 111	89.47 403	96.93 343

CR-MVSNet		94.76 305	94.15 310	96.59 306	97.00 360	93.43 326	94.96 475	97.56 368	92.46 354	96.93 228	96.24 412	88.15 280	97.88 429	87.38 438	96.65 278	98.46 286

v2v482		94.69 306	94.03 318	96.65 295	96.17 406	94.79 270	98.67 206	98.08 320	92.72 346	94.00 337	97.16 349	87.69 295	98.45 354	92.91 331	88.87 413	96.72 371

pmmvs4		94.69 306	93.99 324	96.81 281	95.74 425	95.94 187	97.40 387	97.67 357	90.42 414	93.37 368	97.59 316	89.08 250	98.20 390	92.97 329	91.67 371	96.30 426

cl22		94.68 308	94.19 306	96.13 344	98.11 260	93.60 319	96.94 427	98.31 266	92.43 358	93.32 370	96.87 386	86.51 313	98.28 385	94.10 296	91.16 378	96.51 412

eth_miper_zixun_eth		94.68 308	94.41 295	95.47 381	97.64 311	91.71 384	96.73 446	98.07 322	92.71 347	93.64 353	97.21 347	90.54 205	98.17 392	93.38 315	89.76 395	96.54 403

PCF-MVS	93.45 11	94.68 308	93.43 360	98.42 130	98.62 179	96.77 136	95.48 469	98.20 291	84.63 470	93.34 369	98.32 245	88.55 270	99.81 102	84.80 458	98.96 158	98.68 265
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS		94.67 311	93.54 355	98.08 171	96.88 370	96.56 150	98.19 295	98.50 199	78.05 487	92.69 390	98.02 270	91.07 189	99.63 160	90.09 400	98.36 210	98.04 305

PS-CasMVS		94.67 311	93.99 324	96.71 289	96.68 383	95.26 240	99.13 63	99.03 50	93.68 301	92.33 406	97.95 278	85.35 339	98.10 399	93.59 311	88.16 420	96.79 363

cascas		94.63 313	93.86 334	96.93 272	96.91 368	94.27 295	96.00 459	98.51 194	85.55 466	94.54 304	96.23 414	84.20 367	98.87 313	95.80 224	96.98 268	97.66 318

tpmvs		94.60 314	94.36 297	95.33 387	97.46 328	88.60 450	96.88 438	97.68 354	91.29 396	93.80 349	96.42 407	88.58 266	99.24 239	91.06 387	96.04 304	98.17 300

LTVRE_ROB	92.95 15	94.60 314	93.90 330	96.68 293	97.41 336	94.42 286	98.52 240	98.59 171	91.69 381	91.21 423	98.35 239	84.87 348	99.04 282	91.06 387	93.44 344	96.60 389
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		94.59 316	93.92 327	96.60 305	96.21 402	94.78 271	98.59 220	98.14 307	91.86 377	94.21 327	97.02 370	87.97 286	98.41 365	91.72 372	89.57 398	96.61 387

ADS-MVSNet2		94.58 317	94.40 296	95.11 393	98.00 276	88.74 448	96.04 456	97.30 398	90.15 418	96.47 257	96.64 400	87.89 288	97.56 444	90.08 401	97.06 263	99.02 224

WBMVS		94.56 318	94.04 316	96.10 346	98.03 273	93.08 351	97.82 355	98.18 296	94.02 272	93.77 351	96.82 389	81.28 395	98.34 374	95.47 239	91.00 381	96.88 353

ACMH	92.88 16	94.55 319	93.95 326	96.34 335	97.63 312	93.26 341	98.81 162	98.49 204	93.43 317	89.74 439	98.53 221	81.91 387	99.08 275	93.69 306	93.30 349	96.70 375
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		94.54 320	93.85 335	96.63 300	97.98 284	93.06 352	98.77 175	97.84 341	93.67 303	93.80 349	98.04 269	76.88 443	98.96 297	94.79 261	92.86 354	97.86 311

XVG-ACMP-BASELINE		94.54 320	94.14 311	95.75 371	96.55 388	91.65 385	98.11 314	98.44 215	94.96 224	94.22 326	97.90 283	79.18 416	99.11 268	94.05 298	93.85 333	96.48 417

AUN-MVS		94.53 322	93.73 345	96.92 275	98.50 187	93.52 324	98.34 271	98.10 315	93.83 287	95.94 277	97.98 276	85.59 335	99.03 285	94.35 283	80.94 464	98.22 297

DIV-MVS_self_test		94.52 323	94.03 318	95.99 352	97.57 320	93.38 332	97.05 421	97.94 335	91.74 378	92.81 385	97.10 352	89.12 248	98.07 407	92.60 346	90.30 388	96.53 405

cl____		94.51 324	94.01 321	96.02 348	97.58 316	93.40 331	97.05 421	97.96 334	91.73 380	92.76 387	97.08 358	89.06 251	98.13 396	92.61 343	90.29 389	96.52 408

ETVMVS		94.50 325	93.44 359	97.68 216	98.18 252	95.35 236	98.19 295	97.11 412	93.73 293	96.40 260	95.39 442	74.53 458	98.84 316	91.10 383	96.31 290	98.84 242

GBi-Net		94.49 326	93.80 338	96.56 310	98.21 242	95.00 254	98.82 154	98.18 296	92.46 354	94.09 332	97.07 359	81.16 396	97.95 420	92.08 360	92.14 363	96.72 371

test1		94.49 326	93.80 338	96.56 310	98.21 242	95.00 254	98.82 154	98.18 296	92.46 354	94.09 332	97.07 359	81.16 396	97.95 420	92.08 360	92.14 363	96.72 371

dmvs_re		94.48 328	94.18 308	95.37 385	97.68 307	90.11 419	98.54 239	97.08 414	94.56 248	94.42 313	97.24 344	84.25 363	97.76 435	91.02 390	92.83 355	98.24 295

v8		94.47 329	93.77 341	96.57 309	96.36 398	94.83 267	99.05 75	98.19 293	91.92 374	93.16 375	96.97 375	88.82 264	98.48 349	91.69 373	87.79 422	96.39 421

FMVSNet2		94.47 329	93.61 351	97.04 262	98.21 242	96.43 156	98.79 171	98.27 276	92.46 354	93.50 362	97.09 356	81.16 396	98.00 417	91.09 384	91.93 366	96.70 375

test2506		94.44 331	93.91 329	96.04 347	99.02 131	88.99 443	99.06 73	79.47 510	96.96 93	98.36 128	99.26 80	77.21 436	99.52 186	96.78 189	99.04 152	99.59 94

Patchmatch-test		94.42 332	93.68 349	96.63 300	97.60 314	91.76 381	94.83 479	97.49 380	89.45 431	94.14 330	97.10 352	88.99 253	98.83 319	85.37 452	98.13 225	99.29 164

PEN-MVS		94.42 332	93.73 345	96.49 319	96.28 401	94.84 265	99.17 55	99.00 53	93.51 312	92.23 408	97.83 293	86.10 325	97.90 424	92.55 351	86.92 434	96.74 368

v144192		94.39 334	93.70 347	96.48 321	96.06 412	94.35 290	98.58 224	98.16 304	91.45 387	94.33 318	97.02 370	87.50 298	98.45 354	91.08 386	89.11 408	96.63 383

Baseline_NR-MVSNet		94.35 335	93.81 337	95.96 357	96.20 403	94.05 304	98.61 219	96.67 442	91.44 388	93.85 346	97.60 315	88.57 267	98.14 395	94.39 281	86.93 433	95.68 444

miper_lstm_enhance		94.33 336	94.07 315	95.11 393	97.75 300	90.97 395	97.22 404	98.03 329	91.67 382	92.76 387	96.97 375	90.03 220	97.78 434	92.51 353	89.64 397	96.56 400

v1192		94.32 337	93.58 352	96.53 315	96.10 410	94.45 284	98.50 248	98.17 302	91.54 385	94.19 328	97.06 363	86.95 308	98.43 357	90.14 399	89.57 398	96.70 375

UWE-MVS		94.30 338	93.89 332	95.53 378	97.83 295	88.95 444	97.52 379	93.25 487	94.44 258	96.63 246	97.07 359	78.70 419	99.28 225	91.99 365	97.56 249	98.36 291

ACMH+	92.99 14	94.30 338	93.77 341	95.88 362	97.81 297	92.04 378	98.71 191	98.37 249	93.99 277	90.60 430	98.47 227	80.86 403	99.05 279	92.75 339	92.40 360	96.55 402

v148		94.29 340	93.76 343	95.91 359	96.10 410	92.93 355	98.58 224	97.97 332	92.59 352	93.47 364	96.95 379	88.53 271	98.32 377	92.56 350	87.06 432	96.49 415

v10		94.29 340	93.55 354	96.51 317	96.39 397	94.80 269	98.99 93	98.19 293	91.35 392	93.02 381	96.99 373	88.09 282	98.41 365	90.50 396	88.41 417	96.33 425

SD_0403		94.28 342	94.46 289	93.73 433	98.02 274	85.32 472	98.31 277	98.40 234	94.75 238	93.59 354	98.16 260	89.01 252	96.54 465	82.32 467	97.58 248	99.34 149

MVP-Stereo		94.28 342	93.92 327	95.35 386	94.95 445	92.60 363	97.97 331	97.65 358	91.61 383	90.68 429	97.09 356	86.32 322	98.42 358	89.70 410	99.34 137	95.02 458
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UniMVSNet_ETH3D		94.24 344	93.33 362	96.97 269	97.19 351	93.38 332	98.74 180	98.57 178	91.21 401	93.81 348	98.58 216	72.85 467	98.77 326	95.05 253	93.93 332	98.77 253

OurMVSNet-221017-0		94.21 345	94.00 322	94.85 405	95.60 429	89.22 438	98.89 123	97.43 388	95.29 196	92.18 411	98.52 224	82.86 381	98.59 342	93.46 314	91.76 369	96.74 368

v1921920		94.20 346	93.47 358	96.40 331	95.98 416	94.08 303	98.52 240	98.15 305	91.33 393	94.25 324	97.20 348	86.41 318	98.42 358	90.04 404	89.39 405	96.69 380

WB-MVSnew		94.19 347	94.04 316	94.66 413	96.82 374	92.14 370	97.86 349	95.96 457	93.50 313	95.64 280	96.77 392	88.06 284	97.99 418	84.87 455	96.86 269	93.85 479

v7n		94.19 347	93.43 360	96.47 322	95.90 421	94.38 289	99.26 33	98.34 257	91.99 372	92.76 387	97.13 351	88.31 274	98.52 347	89.48 415	87.70 423	96.52 408

tpm2		94.19 347	93.76 343	95.46 382	97.23 345	89.04 441	97.31 398	96.85 436	87.08 450	96.21 266	96.79 391	83.75 377	98.74 327	92.43 356	96.23 300	98.59 277

TESTMET0.1,1		94.18 350	93.69 348	95.63 375	96.92 366	89.12 439	96.91 430	94.78 474	93.17 328	94.88 294	96.45 406	78.52 420	98.92 304	93.09 324	98.50 190	98.85 240

dp		94.15 351	93.90 330	94.90 401	97.31 341	86.82 467	96.97 425	97.19 409	91.22 400	96.02 272	96.61 402	85.51 336	99.02 289	90.00 405	94.30 317	98.85 240

ET-MVSNet_ETH3D		94.13 352	92.98 370	97.58 227	98.22 241	96.20 168	97.31 398	95.37 465	94.53 250	79.56 487	97.63 314	86.51 313	97.53 445	96.91 172	90.74 383	99.02 224

tpm		94.13 352	93.80 338	95.12 392	96.50 391	87.91 461	97.44 383	95.89 460	92.62 350	96.37 262	96.30 411	84.13 368	98.30 381	93.24 319	91.66 372	99.14 201

testing222		94.12 354	93.03 369	97.37 242	98.02 274	94.66 272	97.94 335	96.65 444	94.63 245	95.78 278	95.76 430	71.49 468	98.92 304	91.17 382	95.88 307	98.52 282

IterMVS-SCA-FT		94.11 355	93.87 333	94.85 405	97.98 284	90.56 410	97.18 410	98.11 312	93.75 290	92.58 393	97.48 324	83.97 371	97.41 448	92.48 355	91.30 375	96.58 396

Anonymous20231211		94.10 356	93.26 365	96.61 303	99.11 123	94.28 294	99.01 88	98.88 78	86.43 459	92.81 385	97.57 318	81.66 392	98.68 333	94.83 258	89.02 411	96.88 353

IterMVS		94.09 357	93.85 335	94.80 409	97.99 278	90.35 415	97.18 410	98.12 309	93.68 301	92.46 400	97.34 335	84.05 369	97.41 448	92.51 353	91.33 374	96.62 386
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test-mter		94.08 358	93.51 356	95.80 367	96.77 376	89.70 427	96.91 430	95.21 466	92.89 341	94.83 297	95.72 435	77.69 431	98.97 293	93.06 325	98.50 190	98.72 258

test0.0.03 1		94.08 358	93.51 356	95.80 367	95.53 433	92.89 356	97.38 389	95.97 456	95.11 210	92.51 398	96.66 397	87.71 292	96.94 455	87.03 440	93.67 336	97.57 322

v1240		94.06 360	93.29 364	96.34 335	96.03 414	93.90 308	98.44 261	98.17 302	91.18 402	94.13 331	97.01 372	86.05 326	98.42 358	89.13 421	89.50 402	96.70 375

X-MVStestdata		94.06 360	92.30 386	99.34 32	99.70 27	98.35 50	99.29 28	98.88 78	97.40 59	98.46 119	43.50 531	95.90 48	99.89 68	97.85 103	99.74 57	99.78 33

DTE-MVSNet		93.98 362	93.26 365	96.14 343	96.06 412	94.39 288	99.20 48	98.86 91	93.06 334	91.78 417	97.81 295	85.87 330	97.58 443	90.53 395	86.17 439	96.46 419

pm-mvs1		93.94 363	93.06 368	96.59 306	96.49 392	95.16 246	98.95 104	98.03 329	92.32 363	91.08 425	97.84 290	84.54 359	98.41 365	92.16 358	86.13 442	96.19 431

MS-PatchMatch		93.84 364	93.63 350	94.46 423	96.18 405	89.45 434	97.76 360	98.27 276	92.23 366	92.13 413	97.49 323	79.50 413	98.69 330	89.75 408	99.38 133	95.25 450

tfpnnormal		93.66 365	92.70 376	96.55 314	96.94 365	95.94 187	98.97 97	99.19 35	91.04 403	91.38 422	97.34 335	84.94 347	98.61 338	85.45 451	89.02 411	95.11 454

EU-MVSNet		93.66 365	94.14 311	92.25 454	95.96 418	83.38 478	98.52 240	98.12 309	94.69 241	92.61 392	98.13 263	87.36 302	96.39 470	91.82 369	90.00 393	96.98 338

our_test_3		93.65 367	93.30 363	94.69 411	95.45 437	89.68 429	96.91 430	97.65 358	91.97 373	91.66 420	96.88 384	89.67 229	97.93 423	88.02 433	91.49 373	96.48 417

pmmvs5		93.65 367	92.97 371	95.68 372	95.49 434	92.37 365	98.20 292	97.28 401	89.66 427	92.58 393	97.26 341	82.14 386	98.09 403	93.18 322	90.95 382	96.58 396

SSC-MVS3.2		93.59 369	93.13 367	94.97 398	96.81 375	89.71 426	97.95 332	98.49 204	94.59 247	93.50 362	96.91 382	77.74 430	98.37 372	91.69 373	90.47 386	96.83 361

test_fmvs2		93.43 370	93.58 352	92.95 447	96.97 363	83.91 475	99.19 50	97.24 404	95.74 158	95.20 289	98.27 251	69.65 470	98.72 329	96.26 205	93.73 335	96.24 428

tpm cat1		93.36 371	92.80 373	95.07 396	97.58 316	87.97 460	96.76 444	97.86 340	82.17 477	93.53 358	96.04 423	86.13 324	99.13 263	89.24 419	95.87 308	98.10 303

JIA-IIPM		93.35 372	92.49 382	95.92 358	96.48 393	90.65 405	95.01 474	96.96 426	85.93 463	96.08 270	87.33 496	87.70 294	98.78 325	91.35 379	95.58 312	98.34 292

SixPastTwentyTwo		93.34 373	92.86 372	94.75 410	95.67 427	89.41 436	98.75 176	96.67 442	93.89 282	90.15 436	98.25 254	80.87 402	98.27 386	90.90 391	90.64 384	96.57 398

USDC		93.33 374	92.71 375	95.21 389	96.83 373	90.83 401	96.91 430	97.50 378	93.84 285	90.72 428	98.14 262	77.69 431	98.82 321	89.51 414	93.21 351	95.97 437

IB-MVS	91.98 17	93.27 375	91.97 390	97.19 248	97.47 327	93.41 328	97.09 418	95.99 455	93.32 321	92.47 399	95.73 433	78.06 426	99.53 183	94.59 276	82.98 453	98.62 272
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		93.26 376	92.21 387	96.41 329	97.73 304	93.13 347	95.65 465	97.03 420	91.27 398	94.04 335	96.06 421	75.33 451	97.19 451	86.56 442	96.23 300	98.92 235

ppachtmachnet_test		93.22 377	92.63 377	94.97 398	95.45 437	90.84 400	96.88 438	97.88 339	90.60 409	92.08 414	97.26 341	88.08 283	97.86 430	85.12 454	90.33 387	96.22 429

Patchmtry		93.22 377	92.35 385	95.84 366	96.77 376	93.09 350	94.66 482	97.56 368	87.37 449	92.90 383	96.24 412	88.15 280	97.90 424	87.37 439	90.10 392	96.53 405

testing3		93.19 379	92.48 383	95.30 388	98.07 264	92.27 366	98.64 211	97.17 410	93.94 281	93.98 338	97.04 367	67.97 475	96.01 474	88.40 428	97.14 261	97.63 319

FMVSNet1		93.19 379	92.07 388	96.56 310	97.54 321	95.00 254	98.82 154	98.18 296	90.38 415	92.27 407	97.07 359	73.68 464	97.95 420	89.36 417	91.30 375	96.72 371

LF4IMVS		93.14 381	92.79 374	94.20 428	95.88 422	88.67 449	97.66 368	97.07 416	93.81 288	91.71 418	97.65 309	77.96 428	98.81 322	91.47 378	91.92 368	95.12 453

mmtdpeth		93.12 382	92.61 378	94.63 415	97.60 314	89.68 429	99.21 45	97.32 396	94.02 272	97.72 184	94.42 453	77.01 441	99.44 203	99.05 31	77.18 477	94.78 463

testgi		93.06 383	92.45 384	94.88 403	96.43 396	89.90 421	98.75 176	97.54 374	95.60 166	91.63 421	97.91 282	74.46 460	97.02 453	86.10 445	93.67 336	97.72 316

PatchT		93.06 383	91.97 390	96.35 334	96.69 382	92.67 362	94.48 486	97.08 414	86.62 457	97.08 220	92.23 479	87.94 287	97.90 424	78.89 480	96.69 276	98.49 284

RPMNet		92.81 385	91.34 396	97.24 244	97.00 360	93.43 326	94.96 475	98.80 114	82.27 476	96.93 228	92.12 480	86.98 307	99.82 97	76.32 487	96.65 278	98.46 286

UWE-MVS-28		92.79 386	92.51 381	93.62 435	96.46 394	86.28 468	97.93 336	92.71 492	94.17 265	94.78 300	97.16 349	81.05 399	96.43 468	81.45 470	96.86 269	98.14 302

myMVS_eth3d		92.73 387	92.01 389	94.89 402	97.39 337	90.94 396	97.91 339	97.46 382	93.16 329	93.42 366	95.37 443	68.09 474	96.12 472	88.34 429	96.99 265	97.60 320

TransMVSNet (Re)		92.67 388	91.51 395	96.15 342	96.58 387	94.65 273	98.90 119	96.73 438	90.86 406	89.46 444	97.86 287	85.62 334	98.09 403	86.45 443	81.12 462	95.71 443

ttmdpeth		92.61 389	91.96 392	94.55 417	94.10 456	90.60 409	98.52 240	97.29 399	92.67 348	90.18 434	97.92 281	79.75 412	97.79 432	91.09 384	86.15 441	95.26 449

Syy-MVS		92.55 390	92.61 378	92.38 450	97.39 337	83.41 477	97.91 339	97.46 382	93.16 329	93.42 366	95.37 443	84.75 352	96.12 472	77.00 486	96.99 265	97.60 320

K. test v3		92.55 390	91.91 393	94.48 421	95.64 428	89.24 437	99.07 72	94.88 473	94.04 270	86.78 462	97.59 316	77.64 434	97.64 439	92.08 360	89.43 404	96.57 398

DSMNet-mixed		92.52 392	92.58 380	92.33 451	94.15 454	82.65 480	98.30 280	94.26 481	89.08 437	92.65 391	95.73 433	85.01 346	95.76 476	86.24 444	97.76 240	98.59 277

TinyColmap		92.31 393	91.53 394	94.65 414	96.92 366	89.75 424	96.92 428	96.68 441	90.45 413	89.62 441	97.85 289	76.06 448	98.81 322	86.74 441	92.51 359	95.41 447

gg-mvs-nofinetune		92.21 394	90.58 402	97.13 253	96.75 379	95.09 250	95.85 460	89.40 502	85.43 467	94.50 306	81.98 502	80.80 404	98.40 371	92.16 358	98.33 211	97.88 309

FMVSNet5		91.81 395	90.92 398	94.49 420	97.21 347	92.09 375	98.00 328	97.55 373	89.31 434	90.86 427	95.61 440	74.48 459	95.32 480	85.57 449	89.70 396	96.07 435

pmmvs6		91.77 396	90.63 401	95.17 391	94.69 451	91.24 392	98.67 206	97.92 337	86.14 461	89.62 441	97.56 321	75.79 449	98.34 374	90.75 393	84.56 446	95.94 438

Anonymous20231206		91.66 397	91.10 397	93.33 440	94.02 460	87.35 464	98.58 224	97.26 403	90.48 411	90.16 435	96.31 410	83.83 375	96.53 466	79.36 477	89.90 394	96.12 433

Patchmatch-RL test		91.49 398	90.85 399	93.41 438	91.37 484	84.40 473	92.81 492	95.93 459	91.87 376	87.25 458	94.87 449	88.99 253	96.53 466	92.54 352	82.00 456	99.30 161

blended_shiyan8		91.42 399	89.89 410	96.01 349	91.50 481	93.30 338	97.48 381	97.83 342	86.93 452	92.57 395	92.37 477	82.46 384	98.13 396	92.86 337	74.99 484	96.61 387

blended_shiyan6		91.37 400	89.84 411	95.98 355	91.49 482	93.28 339	97.48 381	97.83 342	86.93 452	92.43 401	92.36 478	82.44 385	98.06 408	92.74 342	74.82 487	96.59 392

test_0402		91.32 401	90.27 405	94.48 421	96.60 386	91.12 393	98.50 248	97.22 405	86.10 462	88.30 454	96.98 374	77.65 433	97.99 418	78.13 482	92.94 353	94.34 465

test_vis1_rt		91.29 402	90.65 400	93.19 444	97.45 331	86.25 469	98.57 233	90.90 500	93.30 323	86.94 461	93.59 463	62.07 486	99.11 268	97.48 144	95.58 312	94.22 469

PVSNet_0	88.72 19	91.28 403	90.03 408	95.00 397	97.99 278	87.29 465	94.84 478	98.50 199	92.06 371	89.86 438	95.19 445	79.81 411	99.39 210	92.27 357	69.79 502	98.33 293

mvs5depth		91.23 404	90.17 406	94.41 425	92.09 476	89.79 423	95.26 472	96.50 447	90.73 407	91.69 419	97.06 363	76.12 447	98.62 337	88.02 433	84.11 449	94.82 460

Anonymous20240521		91.18 405	90.44 403	93.42 437	93.70 461	88.47 453	98.94 107	97.56 368	88.46 443	89.56 443	95.08 448	77.15 439	96.97 454	83.92 461	89.55 400	94.82 460

wanda-best-256-512		91.17 406	89.60 414	95.88 362	91.33 485	92.99 353	96.89 435	97.82 345	86.89 455	92.36 403	91.75 483	81.83 388	98.06 408	92.75 339	74.82 487	96.59 392

FE-blended-shiyan7		91.17 406	89.60 414	95.88 362	91.33 485	92.99 353	96.89 435	97.82 345	86.89 455	92.36 403	91.75 483	81.83 388	98.06 408	92.75 339	74.82 487	96.59 392

EG-PatchMatch MVS		91.13 408	90.12 407	94.17 430	94.73 450	89.00 442	98.13 309	97.81 349	89.22 435	85.32 472	96.46 405	67.71 476	98.42 358	87.89 437	93.82 334	95.08 455

TDRefinement		91.06 409	89.68 412	95.21 389	85.35 510	91.49 388	98.51 247	97.07 416	91.47 386	88.83 451	97.84 290	77.31 435	99.09 273	92.79 338	77.98 475	95.04 457

gbinet_0.2-2-1-0.02		91.03 410	89.37 420	96.01 349	91.39 483	93.41 328	97.19 408	97.82 345	87.00 451	92.18 411	91.87 482	78.97 417	98.04 412	93.13 323	74.75 491	96.60 389

sc_t1		91.01 411	89.39 416	95.85 365	95.99 415	90.39 414	98.43 263	97.64 360	78.79 484	92.20 410	97.94 279	66.00 480	98.60 341	91.59 376	85.94 443	98.57 280

UnsupCasMVSNet_eth		90.99 412	89.92 409	94.19 429	94.08 457	89.83 422	97.13 417	98.67 150	93.69 299	85.83 468	96.19 417	75.15 454	96.74 459	89.14 420	79.41 469	96.00 436

0.4-1-1-0.1		90.89 413	88.97 426	96.67 294	94.15 454	92.76 361	95.28 471	95.03 471	89.11 436	90.43 432	89.57 491	75.41 450	99.04 282	94.70 266	77.06 478	98.20 299

test20.03		90.89 413	90.38 404	92.43 449	93.48 464	88.14 459	98.33 272	97.56 368	93.40 318	87.96 455	96.71 395	80.69 405	94.13 487	79.15 478	86.17 439	95.01 459

usedtu_blend_shiyan5		90.87 415	89.15 421	96.01 349	91.33 485	93.35 335	98.12 310	97.36 394	81.93 478	92.36 403	91.75 483	81.83 388	98.09 403	92.88 335	74.82 487	96.59 392

blend_shiyan4		90.76 416	89.01 424	95.99 352	91.69 480	93.35 335	97.44 383	97.83 342	86.93 452	92.23 408	91.98 481	75.19 453	98.09 403	92.88 335	74.96 485	96.52 408

MDA-MVSNet_test_wron		90.71 417	89.38 418	94.68 412	94.83 447	90.78 402	97.19 408	97.46 382	87.60 447	72.41 495	95.72 435	86.51 313	96.71 462	85.92 447	86.80 436	96.56 400

YYNet1		90.70 418	89.39 416	94.62 416	94.79 449	90.65 405	97.20 406	97.46 382	87.54 448	72.54 494	95.74 431	86.51 313	96.66 463	86.00 446	86.76 437	96.54 403

0.4-1-1-0.2		90.43 419	88.45 430	96.38 332	93.34 466	92.12 371	93.88 491	95.04 470	88.62 442	90.00 437	88.31 494	75.31 452	99.03 285	94.61 273	76.91 480	98.01 308

KD-MVS_self_test		90.38 420	89.38 418	93.40 439	92.85 471	88.94 445	97.95 332	97.94 335	90.35 416	90.25 433	93.96 460	79.82 410	95.94 475	84.62 460	76.69 482	95.33 448

pmmvs-eth3d		90.36 421	89.05 423	94.32 427	91.10 489	92.12 371	97.63 373	96.95 427	88.86 439	84.91 473	93.13 469	78.32 422	96.74 459	88.70 425	81.81 458	94.09 472

0.3-1-1-0.015		90.29 422	88.21 434	96.51 317	93.56 463	92.44 364	94.41 487	95.03 471	88.71 440	89.20 446	88.50 493	73.12 466	99.04 282	94.67 269	76.70 481	98.05 304

FE-MVSNET2		90.29 422	88.94 427	94.36 426	90.48 494	92.27 366	98.45 255	97.82 345	91.59 384	84.90 474	93.10 470	73.92 462	96.42 469	87.92 436	82.26 454	94.39 464

tt0320		90.26 424	88.73 429	94.86 404	96.12 409	90.62 407	98.17 302	97.63 361	77.46 488	89.68 440	96.04 423	69.19 472	97.79 432	88.98 422	85.29 445	96.16 432

CL-MVSNet_self_test		90.11 425	89.14 422	93.02 445	91.86 478	88.23 458	96.51 452	98.07 322	90.49 410	90.49 431	94.41 454	84.75 352	95.34 479	80.79 472	74.95 486	95.50 446

new_pmnet		90.06 426	89.00 425	93.22 443	94.18 453	88.32 456	96.42 454	96.89 432	86.19 460	85.67 469	93.62 462	77.18 438	97.10 452	81.61 469	89.29 406	94.23 468

MDA-MVSNet-bldmvs		89.97 427	88.35 432	94.83 408	95.21 441	91.34 389	97.64 370	97.51 377	88.36 445	71.17 496	96.13 419	79.22 415	96.63 464	83.65 462	86.27 438	96.52 408

tt0320-xc		89.79 428	88.11 435	94.84 407	96.19 404	90.61 408	98.16 303	97.22 405	77.35 489	88.75 452	96.70 396	65.94 481	97.63 440	89.31 418	83.39 451	96.28 427

CMPMVS	66.06 21	89.70 429	89.67 413	89.78 460	93.19 469	76.56 489	97.00 424	98.35 254	80.97 479	81.57 481	97.75 298	74.75 457	98.61 338	89.85 406	93.63 338	94.17 470
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet1		89.67 430	88.28 433	93.82 432	92.81 472	91.08 394	98.01 326	97.45 386	87.95 446	87.90 456	95.87 429	67.63 477	94.56 486	78.73 481	88.18 419	95.83 441

KD-MVS_2432*1600		89.61 431	87.96 439	94.54 418	94.06 458	91.59 386	95.59 466	97.63 361	89.87 423	88.95 448	94.38 456	78.28 423	96.82 457	84.83 456	68.05 503	95.21 451

miper_refine_blended		89.61 431	87.96 439	94.54 418	94.06 458	91.59 386	95.59 466	97.63 361	89.87 423	88.95 448	94.38 456	78.28 423	96.82 457	84.83 456	68.05 503	95.21 451

MVStest1		89.53 433	87.99 438	94.14 431	94.39 452	90.42 412	98.25 287	96.84 437	82.81 473	81.18 483	97.33 337	77.09 440	96.94 455	85.27 453	78.79 470	95.06 456

MVS-HIRNet		89.46 434	88.40 431	92.64 448	97.58 316	82.15 481	94.16 490	93.05 491	75.73 492	90.90 426	82.52 500	79.42 414	98.33 376	83.53 463	98.68 173	97.43 323

OpenMVS_ROB	86.42 20	89.00 435	87.43 443	93.69 434	93.08 470	89.42 435	97.91 339	96.89 432	78.58 485	85.86 467	94.69 450	69.48 471	98.29 384	77.13 485	93.29 350	93.36 481

mvsany_test3		88.80 436	88.04 436	91.09 458	89.78 498	81.57 483	97.83 354	95.49 464	93.81 288	87.53 457	93.95 461	56.14 489	97.43 447	94.68 267	83.13 452	94.26 466

FE-MVSNET		88.56 437	87.09 444	92.99 446	89.93 497	89.99 420	98.15 306	95.59 462	88.42 444	84.87 475	92.90 472	74.82 456	94.99 484	77.88 483	81.21 461	93.99 475

new-patchmatchnet		88.50 438	87.45 442	91.67 456	90.31 496	85.89 470	97.16 415	97.33 395	89.47 430	83.63 478	92.77 474	76.38 444	95.06 483	82.70 465	77.29 476	94.06 474

APD_test1		88.22 439	88.01 437	88.86 464	95.98 416	74.66 497	97.21 405	96.44 449	83.96 472	86.66 464	97.90 283	60.95 487	97.84 431	82.73 464	90.23 390	94.09 472

PM-MVS		87.77 440	86.55 446	91.40 457	91.03 491	83.36 479	96.92 428	95.18 468	91.28 397	86.48 466	93.42 465	53.27 491	96.74 459	89.43 416	81.97 457	94.11 471

dmvs_testset		87.64 441	88.93 428	83.79 475	95.25 440	63.36 508	97.20 406	91.17 497	93.07 333	85.64 470	95.98 428	85.30 343	91.52 497	69.42 495	87.33 428	96.49 415

test_fmvs3		87.17 442	87.06 445	87.50 467	91.21 488	75.66 492	99.05 75	96.61 445	92.79 345	88.85 450	92.78 473	43.72 496	93.49 489	93.95 299	84.56 446	93.34 482

UnsupCasMVSNet_bld		87.17 442	85.12 449	93.31 441	91.94 477	88.77 446	94.92 477	98.30 273	84.30 471	82.30 479	90.04 489	63.96 484	97.25 450	85.85 448	74.47 494	93.93 477

N_pmnet		87.12 444	87.77 441	85.17 471	95.46 436	61.92 511	97.37 391	70.66 522	85.83 464	88.73 453	96.04 423	85.33 341	97.76 435	80.02 473	90.48 385	95.84 440

pmmvs3		86.67 445	84.86 450	92.11 455	88.16 502	87.19 466	96.63 448	94.75 475	79.88 481	87.22 459	92.75 475	66.56 479	95.20 482	81.24 471	76.56 483	93.96 476

test_f		86.07 446	85.39 447	88.10 465	89.28 500	75.57 493	97.73 363	96.33 451	89.41 433	85.35 471	91.56 486	43.31 498	95.53 477	91.32 380	84.23 448	93.21 483

WB-MVS		84.86 447	85.33 448	83.46 476	89.48 499	69.56 502	98.19 295	96.42 450	89.55 429	81.79 480	94.67 451	84.80 350	90.12 498	52.44 503	80.64 466	90.69 489

usedtu_dtu_shiyan2		84.80 448	82.31 452	92.27 453	86.38 507	85.55 471	97.77 359	96.56 446	78.34 486	83.90 477	93.50 464	54.16 490	95.32 480	77.55 484	72.62 495	95.92 439

SSC-MVS		84.27 449	84.71 451	82.96 480	89.19 501	68.83 503	98.08 318	96.30 452	89.04 438	81.37 482	94.47 452	84.60 357	89.89 499	49.80 506	79.52 468	90.15 490

RoMa-SfM		83.81 450	82.08 453	89.00 463	93.33 467	79.94 486	95.51 468	92.48 493	79.75 482	79.89 486	95.69 438	46.23 493	93.20 492	78.90 479	76.93 479	93.87 478

LoFTR		83.16 451	80.62 455	90.80 459	92.28 475	80.01 485	95.35 470	94.33 479	80.44 480	70.79 497	92.93 471	46.38 492	98.17 392	75.01 489	78.03 474	94.24 467

dongtai		82.47 452	81.88 454	84.22 474	95.19 442	76.03 490	94.59 485	74.14 514	82.63 474	87.19 460	96.09 420	64.10 483	87.85 502	58.91 501	84.11 449	88.78 496

DKM		81.60 453	79.57 456	87.68 466	92.65 474	78.36 487	94.65 483	91.17 497	79.69 483	76.11 489	93.98 459	37.88 507	91.54 496	79.64 476	70.38 499	93.15 484

MatchFormer		80.21 454	77.20 462	89.24 462	91.79 479	77.21 488	95.16 473	93.59 486	72.46 496	67.08 500	89.93 490	43.14 499	97.90 424	67.07 497	74.55 493	92.61 486

test_vis3_rt		79.22 455	77.40 461	84.67 472	86.44 506	74.85 496	97.66 368	81.43 508	84.98 468	67.12 499	81.91 503	28.09 519	97.60 441	88.96 423	80.04 467	81.55 506

test_method		79.03 456	78.17 457	81.63 481	86.06 508	54.40 522	82.75 510	96.89 432	39.54 515	80.98 484	95.57 441	58.37 488	94.73 485	84.74 459	78.61 471	95.75 442

testf1		79.02 457	77.70 458	82.99 478	88.10 503	66.90 505	94.67 480	93.11 488	71.08 497	74.02 491	93.41 466	34.15 512	93.25 490	72.25 492	78.50 472	88.82 494

APD_test2		79.02 457	77.70 458	82.99 478	88.10 503	66.90 505	94.67 480	93.11 488	71.08 497	74.02 491	93.41 466	34.15 512	93.25 490	72.25 492	78.50 472	88.82 494

LCM-MVSNet		78.70 459	76.24 465	86.08 469	77.26 524	71.99 499	94.34 488	96.72 439	61.62 501	76.53 488	89.33 492	33.91 515	92.78 494	81.85 468	74.60 492	93.46 480

kuosan		78.45 460	77.69 460	80.72 482	92.73 473	75.32 494	94.63 484	74.51 513	75.96 490	80.87 485	93.19 468	63.23 485	79.99 511	42.56 513	81.56 460	86.85 503

Gipuma		78.40 461	76.75 464	83.38 477	95.54 431	80.43 484	79.42 511	97.40 390	64.67 500	73.46 493	80.82 504	45.65 495	93.14 493	66.32 498	87.43 426	76.56 509
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		77.95 462	75.44 466	85.46 470	82.54 513	74.95 495	94.23 489	93.08 490	72.80 494	74.68 490	87.38 495	36.36 510	91.56 495	73.95 490	63.94 505	89.87 491

FPMVS		77.62 463	77.14 463	79.05 485	79.25 519	60.97 513	95.79 461	95.94 458	65.96 499	67.93 498	94.40 455	37.73 508	88.88 501	68.83 496	88.46 416	87.29 500

ELoFTR		75.37 464	72.33 467	84.51 473	84.48 511	68.41 504	91.57 496	88.78 503	73.84 493	62.84 503	90.14 488	27.38 520	94.11 488	71.45 494	60.46 508	91.00 487

EGC-MVSNET		75.22 465	69.54 468	92.28 452	94.81 448	89.58 431	97.64 370	96.50 447	1.82 536	5.57 537	95.74 431	68.21 473	96.26 471	73.80 491	91.71 370	90.99 488

PDCNetPlus		71.79 466	69.26 469	79.39 484	85.67 509	69.92 501	90.34 501	62.32 524	72.62 495	65.36 502	90.26 487	39.20 504	86.38 503	75.32 488	42.24 517	81.88 505

SP-DiffGlue		70.13 467	69.16 470	73.04 494	77.73 522	57.48 517	88.44 505	74.91 512	50.96 507	66.64 501	85.99 497	41.44 500	73.46 517	64.21 499	72.15 496	88.19 499

ANet_high		69.08 468	65.37 475	80.22 483	65.99 537	71.96 500	90.91 500	90.09 501	82.62 475	49.93 517	78.39 511	29.36 518	81.75 508	62.49 500	38.52 521	86.95 502

tmp_tt		68.90 469	66.97 471	74.68 487	50.78 539	59.95 514	87.13 507	83.47 507	38.80 516	62.21 504	96.23 414	64.70 482	76.91 513	88.91 424	30.49 525	87.19 501

SP-LightGlue		68.17 470	66.54 473	73.06 493	91.08 490	55.79 518	91.09 498	72.78 516	48.55 511	60.77 506	79.95 508	38.55 505	74.10 515	45.47 508	70.64 498	89.28 492

SP-SuperGlue		68.14 471	66.58 472	72.81 495	90.65 493	55.53 519	91.37 497	73.04 515	49.07 510	61.03 505	80.24 507	38.13 506	74.06 516	45.46 509	70.26 500	88.84 493

ALIKED-LG		67.40 472	65.16 476	74.11 489	93.21 468	62.30 509	88.98 503	71.99 517	55.04 502	59.47 509	82.33 501	39.27 503	85.49 505	32.61 519	63.58 507	74.55 510

SP-NN		67.39 473	65.69 474	72.49 497	90.68 492	55.34 520	90.33 502	71.01 520	46.77 513	59.09 510	79.83 509	37.26 509	73.38 518	44.68 510	71.51 497	88.74 497

ALIKED-NN		66.93 474	64.81 477	73.32 491	93.41 465	62.03 510	87.55 506	71.25 518	50.21 508	59.98 508	82.57 499	39.72 502	84.03 507	34.94 517	63.64 506	73.90 511

SP-MNN		66.66 475	64.70 478	72.53 496	90.32 495	55.08 521	91.01 499	71.05 519	44.81 514	56.48 513	79.62 510	35.87 511	74.11 514	43.13 512	69.98 501	88.39 498

PMVS	61.03 23	65.95 476	63.57 480	73.09 492	57.90 538	51.22 524	85.05 509	93.93 485	54.45 503	44.32 519	83.57 498	13.22 533	89.15 500	58.68 502	81.00 463	78.91 508
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ALIKED-MNN		65.35 477	62.68 482	73.35 490	93.70 461	61.07 512	88.63 504	70.76 521	47.76 512	57.06 512	80.59 505	34.03 514	85.39 506	32.73 518	58.87 509	73.59 512

E-PMN		64.94 478	64.25 479	67.02 498	82.28 514	59.36 515	91.83 495	85.63 505	52.69 504	60.22 507	77.28 512	41.06 501	80.12 510	46.15 507	41.14 518	61.57 515

EMVS		64.07 479	63.26 481	66.53 499	81.73 515	58.81 516	91.85 494	84.75 506	51.93 506	59.09 510	75.13 515	43.32 497	79.09 512	42.03 514	39.47 519	61.69 514

MVE	62.14 22	63.28 480	59.38 483	74.99 486	74.33 529	65.47 507	85.55 508	80.50 509	52.02 505	51.10 515	75.00 516	10.91 538	80.50 509	51.60 505	53.40 511	78.99 507
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
GLUNet-SfM		61.12 481	56.63 484	74.58 488	69.78 534	53.99 523	78.71 512	76.81 511	49.09 509	49.42 518	80.47 506	24.43 521	85.82 504	51.80 504	29.17 526	83.92 504

XFeat-NN		56.16 482	56.10 485	56.36 501	72.10 531	42.54 534	76.45 514	61.18 525	38.16 517	53.08 514	76.48 513	32.95 516	65.67 520	44.15 511	50.31 514	60.87 516

XFeat-MNN		55.84 483	55.19 486	57.82 500	69.33 535	43.25 529	78.25 513	62.64 523	37.53 518	50.90 516	76.32 514	32.43 517	68.13 519	42.00 515	47.26 516	62.07 513

SIFT-NN		49.27 484	49.25 487	49.32 502	83.88 512	45.20 525	74.57 515	53.44 526	32.44 519	42.88 520	64.93 517	20.60 522	61.35 521	16.59 521	53.96 510	41.40 517

SIFT-MNN		47.78 485	47.47 488	48.69 503	81.04 516	44.17 526	73.46 516	53.36 527	31.82 520	38.54 521	63.76 518	18.11 526	61.27 522	15.96 523	51.17 512	40.64 520

SIFT-NN-NCMNet		47.55 486	47.18 489	48.67 504	79.60 518	44.09 527	73.43 517	52.90 528	31.82 520	38.38 522	63.56 521	18.47 523	61.19 523	15.91 524	50.50 513	40.74 519

SIFT-NN-CMatch		45.31 487	44.49 490	47.75 505	76.46 525	42.98 532	70.17 521	49.20 531	31.63 523	37.94 523	63.68 520	18.19 525	59.32 526	15.91 524	37.27 522	40.95 518

SIFT-NCM-Cal		44.98 488	44.20 491	47.33 506	79.81 517	43.05 530	72.12 518	49.31 530	30.81 525	25.90 529	61.87 526	15.80 528	60.28 524	14.09 532	48.07 515	38.66 523

SIFT-NN-UMatch		44.69 489	43.84 492	47.24 507	74.56 528	42.59 533	71.89 519	49.78 529	31.80 522	29.27 526	63.70 519	18.26 524	59.43 525	15.86 526	39.43 520	39.71 521

SIFT-ConvMatch		43.26 490	42.18 494	46.50 508	78.34 521	43.05 530	68.67 523	47.17 532	31.06 524	30.28 525	62.56 523	15.43 529	58.95 528	14.92 528	31.22 524	37.51 525

SIFT-NN-PointCN		43.09 491	42.61 493	44.51 511	72.48 530	37.95 538	70.10 522	46.55 533	30.16 529	34.48 524	61.93 525	18.02 527	55.90 531	15.40 527	34.41 523	39.69 522

SIFT-UMatch		42.35 492	41.04 495	46.29 509	76.09 526	41.80 535	70.21 520	45.21 534	30.75 526	27.33 528	62.62 522	15.13 530	59.11 527	14.72 529	27.30 527	37.95 524

SIFT-CM-Cal		41.25 493	40.03 496	44.88 510	77.37 523	41.08 536	65.71 527	41.18 536	30.42 528	28.83 527	61.42 527	14.88 531	56.40 529	14.13 531	26.37 529	37.16 526

SIFT-UM-Cal		39.93 494	38.61 497	43.88 512	76.08 527	39.30 537	68.10 524	37.89 537	30.49 527	22.74 531	62.27 524	13.89 532	56.16 530	14.17 530	21.90 530	36.17 527

SIFT-PointCN		37.89 495	37.50 498	39.07 513	71.45 532	31.31 539	66.27 526	41.69 535	27.82 530	22.63 532	56.73 529	12.00 536	50.56 533	12.18 534	26.71 528	35.34 528

SIFT-PCN-Cal		36.85 496	36.40 499	38.19 514	71.43 533	30.42 540	64.34 528	37.72 538	27.48 531	22.98 530	57.03 528	12.99 534	51.22 532	12.51 533	21.13 531	32.92 529

SIFT-NCMNet		32.45 497	31.84 501	34.30 515	68.74 536	28.10 541	57.85 529	24.54 539	27.25 532	19.31 533	52.59 530	9.75 539	45.69 534	10.92 535	15.56 533	29.13 530

wuyk23d		30.17 498	30.18 502	30.16 516	78.61 520	43.29 528	66.79 525	14.21 540	17.31 533	14.82 536	11.93 536	11.55 537	41.43 535	37.08 516	19.30 532	5.76 533

cdsmvs_eth3d_5k		23.98 499	31.98 500	0.00 519	0.00 542	0.00 544	0.00 530	98.59 171	0.00 537	0.00 538	98.61 211	90.60 203	0.00 538	0.00 536	0.00 536	0.00 534

testmvs		21.48 500	24.95 503	11.09 518	14.89 540	6.47 543	96.56 450	9.87 541	7.55 534	17.93 534	39.02 532	9.43 540	5.90 537	16.56 522	12.72 534	20.91 532

test123		20.95 501	23.72 504	12.64 517	13.54 541	8.19 542	96.55 451	6.13 542	7.48 535	16.74 535	37.98 533	12.97 535	6.05 536	16.69 520	5.43 535	23.68 531

ab-mvs-re		8.20 502	10.94 505	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	98.43 229	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

pcd_1.5k_mvsjas		7.88 503	10.50 506	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	94.51 91	0.00 538	0.00 536	0.00 536	0.00 534

mmdepth		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

monomultidepth		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

test_blank		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

uanet_test		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

DCPMVS		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

sosnet-low-res		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

sosnet		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

uncertanet		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

Regformer		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

uanet		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

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	99.05 141	96.54 24	99.73 136		98.59 180	99.51 104

WAC-MVS						90.94 396								88.66 426

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									95.08 214	99.60 33	99.16 108	97.86 2	98.47 352	97.52 137	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					0.00 542

eth-test					0.00 542

ZD-MVS					99.46 58	98.70 28		98.79 119	93.21 326	98.67 105	98.97 152	95.70 52	99.83 90	96.07 209	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		97.72 111	99.65 80	99.71 63

IU-MVS					99.71 24	99.23 7		98.64 158	95.28 197	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 85				99.16 108	97.81 3	99.37 211	97.24 159	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		98.71 191	98.82 101	94.36 260	99.16 67	99.29 75	96.05 40	99.81 102	97.00 166	99.71 68

save fliter					99.46 58	98.38 41	98.21 290	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 97	98.88 78					99.94 14	98.47 63	99.81 16	99.84 18

test0726					99.72 17	99.25 2	99.06 73	98.88 78	97.62 43	99.56 35	99.50 31	97.42 10

GSMVS																99.20 187

test_part2					99.63 34	99.18 10				99.27 57

sam_mvs1												89.45 237				99.20 187

sam_mvs												88.99 253

ambc				89.49 461	86.66 505	75.78 491	92.66 493	96.72 439		86.55 465	92.50 476	46.01 494	97.90 424	90.32 397	82.09 455	94.80 462

MTGPA								98.74 129

test_post1							96.68 447				30.43 535	87.85 291	98.69 330	92.59 348

test_post											31.83 534	88.83 262	98.91 306

patchmatchnet-post											95.10 447	89.42 238	98.89 310

GG-mvs-BLEND				96.59 306	96.34 399	94.98 258	96.51 452	88.58 504		93.10 380	94.34 458	80.34 409	98.05 411	89.53 413	96.99 265	96.74 368

MTMP							98.89 123	94.14 483

gm-plane-assit					95.88 422	87.47 463			89.74 426		96.94 380		99.19 249	93.32 318

test9_res														96.39 203	99.57 98	99.69 70

TEST9					99.31 79	98.50 35	97.92 337	98.73 132	92.63 349	97.74 181	98.68 205	96.20 35	99.80 109

test_8					99.29 88	98.44 37	97.89 345	98.72 134	92.98 337	97.70 186	98.66 208	96.20 35	99.80 109

agg_prior2														95.87 219	99.57 98	99.68 75

agg_prior					99.30 83	98.38 41		98.72 134		97.57 203			99.81 102

TestCases				96.99 264	99.25 96	93.21 345		98.18 296	91.36 390	93.52 359	98.77 192	84.67 355	99.72 137	89.70 410	97.87 234	98.02 306

test_prior4						98.01 71	97.86 349

test_prior2							97.80 356		96.12 138	97.89 168	98.69 204	95.96 44		96.89 176	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							97.57 376		91.30 395	98.67 105			99.80 109	95.70 230

新几何2							97.64 370

新几何1				99.16 56	99.34 71	98.01 71		98.69 142	90.06 420	98.13 137	98.95 159	94.60 89	99.89 68	91.97 367	99.47 121	99.59 94

旧先验1					99.29 88	97.48 90		98.70 140			99.09 131	95.56 55			99.47 121	99.61 90

无先验							97.58 375	98.72 134	91.38 389				99.87 79	93.36 317		99.60 92

原ACMM2							97.67 367

原ACMM1				98.65 98	99.32 77	96.62 141		98.67 150	93.27 325	97.81 174	98.97 152	95.18 76	99.83 90	93.84 303	99.46 124	99.50 107

test222					99.23 104	97.17 117	97.40 387	98.66 153	88.68 441	98.05 145	98.96 157	94.14 102			99.53 111	99.61 90

testdata2													99.89 68	91.65 375

segment_acmp												96.85 15

testdata				98.26 142	99.20 109	95.36 234		98.68 145	91.89 375	98.60 113	99.10 123	94.44 96	99.82 97	94.27 287	99.44 125	99.58 98

testdata1							97.32 397		96.34 128

test12				99.18 53	99.16 115	98.19 60		98.53 188		98.07 141		95.13 79	99.72 137		99.56 106	99.63 88

plane_prior7					97.42 333	94.63 275

plane_prior6					97.35 340	94.61 278						87.09 304

plane_prior5								98.56 182					99.03 285	96.07 209	94.27 318	96.92 344

plane_prior4											98.28 248

plane_prior3						94.61 278			97.02 89	95.34 284

plane_prior2							98.80 163		97.28 69

plane_prior1					97.37 339

plane_prior						94.60 280	98.44 261		96.74 105						94.22 320

n2								0.00 543

nn								0.00 543

door-mid								94.37 478

lessismore_v0				94.45 424	94.93 446	88.44 454		91.03 499		86.77 463	97.64 312	76.23 446	98.42 358	90.31 398	85.64 444	96.51 412

LGP-MVS_train				96.47 322	97.46 328	93.54 321		98.54 186	94.67 243	94.36 316	98.77 192	85.39 337	99.11 268	95.71 228	94.15 324	96.76 366

test11								98.66 153

door								94.64 476

HQP5-MVS						94.25 297

HQP-NCC					97.20 348		98.05 321		96.43 120	94.45 308

ACMP_Plane					97.20 348		98.05 321		96.43 120	94.45 308

BP-MVS														95.30 243

HQP4-MVS										94.45 308			98.96 297			96.87 356

HQP3-MVS								98.46 207							94.18 322

HQP2-MVS												86.75 310

NP-MVS					97.28 342	94.51 283					97.73 299

MDTV_nov1_ep13_2view						84.26 474	96.89 435		90.97 404	97.90 167		89.89 223		93.91 301		99.18 196

MDTV_nov1_ep13			95.40 235		97.48 326	88.34 455	96.85 440	97.29 399	93.74 292	97.48 205	97.26 341	89.18 246	99.05 279	91.92 368	97.43 256

ACMMP++_ref															92.97 352

ACMMP++															93.61 339

Test By Simon												94.64 88

ITE_SJBPF				95.44 383	97.42 333	91.32 390		97.50 378	95.09 213	93.59 354	98.35 239	81.70 391	98.88 312	89.71 409	93.39 345	96.12 433

DeepMVS_CX				86.78 468	97.09 358	72.30 498		95.17 469	75.92 491	84.34 476	95.19 445	70.58 469	95.35 478	79.98 475	89.04 410	92.68 485

High-resolution multi-view benchmark