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.

fmvsm_l_conf0.5_n_a		99.09 1	99.08 1	99.11 55	99.43 57	97.48 83	98.88 116	99.30 13	98.47 13	99.85 7	99.43 36	96.71 17	99.96 4	99.86 1	99.80 24	99.89 4

SED-MVS		99.09 1	98.91 4	99.63 4	99.71 19	99.24 5	99.02 79	98.87 74	97.65 30	99.73 16	99.48 27	97.53 7	99.94 11	98.43 56	99.81 15	99.70 58

DVP-MVS++		99.08 3	98.89 5	99.64 3	99.17 100	99.23 7	99.69 1	98.88 67	97.32 52	99.53 29	99.47 29	97.81 3	99.94 11	98.47 52	99.72 59	99.74 41

fmvsm_l_conf0.5_n		99.07 4	99.05 2	99.14 51	99.41 59	97.54 81	98.89 110	99.31 12	98.49 12	99.86 5	99.42 37	96.45 24	99.96 4	99.86 1	99.74 52	99.90 3

DVP-MVS		99.03 5	98.83 9	99.63 4	99.72 12	99.25 2	98.97 89	98.58 161	97.62 32	99.45 31	99.46 33	97.42 9	99.94 11	98.47 52	99.81 15	99.69 61
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
APDe-MVS		99.02 6	98.84 8	99.55 9	99.57 33	98.96 16	99.39 10	98.93 55	97.38 49	99.41 34	99.54 15	96.66 18	99.84 76	98.86 31	99.85 6	99.87 7
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
reproduce_model		98.94 7	98.81 10	99.34 26	99.52 39	98.26 49	98.94 98	98.84 84	98.06 18	99.35 38	99.61 4	96.39 27	99.94 11	98.77 34	99.82 14	99.83 13

reproduce-ours		98.93 8	98.78 11	99.38 18	99.49 46	98.38 35	98.86 123	98.83 86	98.06 18	99.29 42	99.58 11	96.40 25	99.94 11	98.68 36	99.81 15	99.81 19

our_new_method		98.93 8	98.78 11	99.38 18	99.49 46	98.38 35	98.86 123	98.83 86	98.06 18	99.29 42	99.58 11	96.40 25	99.94 11	98.68 36	99.81 15	99.81 19

test_fmvsmconf_n		98.92 10	98.87 6	99.04 60	98.88 135	97.25 100	98.82 135	99.34 10	98.75 6	99.80 9	99.61 4	95.16 73	99.95 9	99.70 11	99.80 24	99.93 1

DPE-MVS		98.92 10	98.67 16	99.65 2	99.58 32	99.20 9	98.42 221	98.91 61	97.58 35	99.54 28	99.46 33	97.10 12	99.94 11	97.64 103	99.84 11	99.83 13
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_3		98.90 12	98.74 14	99.37 22	99.36 60	98.25 50	98.89 110	99.24 18	98.77 5	99.89 1	99.59 10	93.39 106	99.96 4	99.78 5	99.76 42	99.89 4

SteuartSystems-ACMMP		98.90 12	98.75 13	99.36 24	99.22 95	98.43 33	99.10 63	98.87 74	97.38 49	99.35 38	99.40 39	97.78 5	99.87 67	97.77 91	99.85 6	99.78 25
Skip Steuart: Steuart Systems R&D Blog.
test_fmvsm_n_1920		98.87 14	99.01 3	98.45 107	99.42 58	96.43 139	98.96 94	99.36 9	98.63 8	99.86 5	99.51 21	95.91 43	99.97 1	99.72 9	99.75 48	98.94 189

TSAR-MVS + MP.		98.78 15	98.62 17	99.24 40	99.69 24	98.28 48	99.14 54	98.66 141	96.84 81	99.56 26	99.31 59	96.34 28	99.70 128	98.32 62	99.73 55	99.73 46
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 15	98.56 20	99.45 15	99.32 66	98.87 19	98.47 213	98.81 95	97.72 25	98.76 81	99.16 86	97.05 13	99.78 110	98.06 73	99.66 69	99.69 61

MSP-MVS		98.74 17	98.55 21	99.29 33	99.75 3	98.23 51	99.26 27	98.88 67	97.52 38	99.41 34	98.78 143	96.00 39	99.79 107	97.79 90	99.59 85	99.85 10
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
XVS		98.70 18	98.49 26	99.34 26	99.70 22	98.35 44	99.29 22	98.88 67	97.40 46	98.46 99	99.20 76	95.90 45	99.89 56	97.85 86	99.74 52	99.78 25

MCST-MVS		98.65 19	98.37 35	99.48 13	99.60 31	98.87 19	98.41 222	98.68 133	97.04 73	98.52 97	98.80 141	96.78 16	99.83 78	97.93 80	99.61 81	99.74 41

SD-MVS		98.64 20	98.68 15	98.53 98	99.33 63	98.36 43	98.90 106	98.85 83	97.28 55	99.72 18	99.39 40	96.63 20	97.60 373	98.17 68	99.85 6	99.64 76
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
HFP-MVS		98.63 21	98.40 32	99.32 32	99.72 12	98.29 47	99.23 32	98.96 50	96.10 119	98.94 64	99.17 83	96.06 36	99.92 37	97.62 104	99.78 34	99.75 39

ACMMP_NAP		98.61 22	98.30 49	99.55 9	99.62 30	98.95 17	98.82 135	98.81 95	95.80 130	99.16 54	99.47 29	95.37 60	99.92 37	97.89 84	99.75 48	99.79 23

region2R		98.61 22	98.38 34	99.29 33	99.74 7	98.16 57	99.23 32	98.93 55	96.15 115	98.94 64	99.17 83	95.91 43	99.94 11	97.55 112	99.79 30	99.78 25

NCCC		98.61 22	98.35 38	99.38 18	99.28 81	98.61 26	98.45 214	98.76 113	97.82 24	98.45 102	98.93 125	96.65 19	99.83 78	97.38 121	99.41 116	99.71 54

SF-MVS		98.59 25	98.32 48	99.41 17	99.54 35	98.71 22	99.04 73	98.81 95	95.12 167	99.32 41	99.39 40	96.22 30	99.84 76	97.72 94	99.73 55	99.67 70

ACMMPR		98.59 25	98.36 36	99.29 33	99.74 7	98.15 58	99.23 32	98.95 51	96.10 119	98.93 68	99.19 81	95.70 49	99.94 11	97.62 104	99.79 30	99.78 25

test_fmvsmconf0.1_n		98.58 27	98.44 30	98.99 62	97.73 253	97.15 105	98.84 131	98.97 47	98.75 6	99.43 33	99.54 15	93.29 108	99.93 30	99.64 14	99.79 30	99.89 4

SMA-MVS		98.58 27	98.25 52	99.56 8	99.51 40	99.04 15	98.95 95	98.80 102	93.67 252	99.37 37	99.52 18	96.52 22	99.89 56	98.06 73	99.81 15	99.76 38
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 27	98.29 50	99.46 14	99.76 2	98.64 25	98.90 106	98.74 117	97.27 59	98.02 126	99.39 40	94.81 83	99.96 4	97.91 82	99.79 30	99.77 31

HPM-MVS++		98.58 27	98.25 52	99.55 9	99.50 42	99.08 11	98.72 166	98.66 141	97.51 39	98.15 113	98.83 138	95.70 49	99.92 37	97.53 114	99.67 66	99.66 73

SR-MVS		98.57 31	98.35 38	99.24 40	99.53 36	98.18 55	99.09 64	98.82 89	96.58 97	99.10 56	99.32 57	95.39 58	99.82 85	97.70 99	99.63 78	99.72 50

CP-MVS		98.57 31	98.36 36	99.19 44	99.66 26	97.86 69	99.34 16	98.87 74	95.96 122	98.60 94	99.13 91	96.05 37	99.94 11	97.77 91	99.86 2	99.77 31

MSLP-MVS++		98.56 33	98.57 19	98.55 94	99.26 84	96.80 119	98.71 167	99.05 41	97.28 55	98.84 74	99.28 62	96.47 23	99.40 188	98.52 50	99.70 62	99.47 105

DeepC-MVS_fast	96.70 1	98.55 34	98.34 43	99.18 46	99.25 85	98.04 63	98.50 210	98.78 109	97.72 25	98.92 70	99.28 62	95.27 66	99.82 85	97.55 112	99.77 36	99.69 61
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 35	98.35 38	99.13 52	99.49 46	97.86 69	99.11 60	98.80 102	96.49 100	99.17 51	99.35 52	95.34 62	99.82 85	97.72 94	99.65 72	99.71 54

fmvsm_s_conf0.5_n_5		98.53 36	98.35 38	99.08 57	99.07 115	97.46 87	98.68 175	99.20 27	97.50 40	99.87 2	99.50 23	91.96 140	99.96 4	99.76 6	99.65 72	99.82 17

fmvsm_s_conf0.5_n_3		98.53 36	98.45 29	98.79 76	99.23 93	97.32 92	98.80 144	99.26 15	98.82 2	99.87 2	99.60 8	90.95 167	99.93 30	99.76 6	99.73 55	99.12 164

APD-MVS_3200maxsize		98.53 36	98.33 47	99.15 50	99.50 42	97.92 68	99.15 51	98.81 95	96.24 111	99.20 48	99.37 46	95.30 64	99.80 97	97.73 93	99.67 66	99.72 50

MM		98.51 39	98.24 54	99.33 30	99.12 109	98.14 60	98.93 101	97.02 359	98.96 1	99.17 51	99.47 29	91.97 139	99.94 11	99.85 3	99.69 63	99.91 2

mPP-MVS		98.51 39	98.26 51	99.25 39	99.75 3	98.04 63	99.28 24	98.81 95	96.24 111	98.35 109	99.23 71	95.46 55	99.94 11	97.42 119	99.81 15	99.77 31

ZNCC-MVS		98.49 41	98.20 60	99.35 25	99.73 11	98.39 34	99.19 44	98.86 80	95.77 132	98.31 112	99.10 95	95.46 55	99.93 30	97.57 111	99.81 15	99.74 41

SPE-MVS-test		98.49 41	98.50 24	98.46 106	99.20 98	97.05 109	99.64 4	98.50 183	97.45 45	98.88 71	99.14 90	95.25 68	99.15 216	98.83 32	99.56 95	99.20 149

PGM-MVS		98.49 41	98.23 56	99.27 38	99.72 12	98.08 62	98.99 86	99.49 5	95.43 148	99.03 57	99.32 57	95.56 52	99.94 11	96.80 150	99.77 36	99.78 25

EI-MVSNet-Vis-set		98.47 44	98.39 33	98.69 83	99.46 52	96.49 136	98.30 233	98.69 130	97.21 62	98.84 74	99.36 50	95.41 57	99.78 110	98.62 39	99.65 72	99.80 22

MVS_111021_HR		98.47 44	98.34 43	98.88 73	99.22 95	97.32 92	97.91 285	99.58 3	97.20 63	98.33 110	99.00 114	95.99 40	99.64 141	98.05 75	99.76 42	99.69 61

balanced_conf03		98.45 46	98.35 38	98.74 79	98.65 163	97.55 79	99.19 44	98.60 152	96.72 91	99.35 38	98.77 145	95.06 78	99.55 164	98.95 28	99.87 1	99.12 164

test_fmvsmvis_n_1920		98.44 47	98.51 22	98.23 127	98.33 193	96.15 153	98.97 89	99.15 33	98.55 11	98.45 102	99.55 13	94.26 96	99.97 1	99.65 12	99.66 69	98.57 229

CS-MVS		98.44 47	98.49 26	98.31 119	99.08 114	96.73 123	99.67 3	98.47 190	97.17 65	98.94 64	99.10 95	95.73 48	99.13 219	98.71 35	99.49 106	99.09 169

GST-MVS		98.43 49	98.12 64	99.34 26	99.72 12	98.38 35	99.09 64	98.82 89	95.71 136	98.73 84	99.06 106	95.27 66	99.93 30	97.07 129	99.63 78	99.72 50

fmvsm_s_conf0.5_n		98.42 50	98.51 22	98.13 136	99.30 72	95.25 199	98.85 127	99.39 7	97.94 22	99.74 15	99.62 3	92.59 117	99.91 46	99.65 12	99.52 101	99.25 142

EI-MVSNet-UG-set		98.41 51	98.34 43	98.61 89	99.45 55	96.32 146	98.28 236	98.68 133	97.17 65	98.74 82	99.37 46	95.25 68	99.79 107	98.57 41	99.54 98	99.73 46

DELS-MVS		98.40 52	98.20 60	98.99 62	99.00 122	97.66 74	97.75 306	98.89 64	97.71 27	98.33 110	98.97 116	94.97 80	99.88 65	98.42 58	99.76 42	99.42 116
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 53	98.42 31	98.27 121	99.09 113	95.41 189	98.86 123	99.37 8	97.69 29	99.78 11	99.61 4	92.38 120	99.91 46	99.58 16	99.43 114	99.49 101

TSAR-MVS + GP.		98.38 53	98.24 54	98.81 75	99.22 95	97.25 100	98.11 260	98.29 229	97.19 64	98.99 62	99.02 109	96.22 30	99.67 135	98.52 50	98.56 164	99.51 94

HPM-MVS_fast		98.38 53	98.13 63	99.12 54	99.75 3	97.86 69	99.44 9	98.82 89	94.46 207	98.94 64	99.20 76	95.16 73	99.74 120	97.58 107	99.85 6	99.77 31

patch_mono-2		98.36 56	98.87 6	96.82 231	99.53 36	90.68 339	98.64 185	99.29 14	97.88 23	99.19 50	99.52 18	96.80 15	99.97 1	99.11 24	99.86 2	99.82 17

HPM-MVS		98.36 56	98.10 67	99.13 52	99.74 7	97.82 73	99.53 6	98.80 102	94.63 196	98.61 93	98.97 116	95.13 75	99.77 115	97.65 102	99.83 13	99.79 23
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 58	98.50 24	97.90 153	99.16 104	95.08 208	98.75 154	99.24 18	98.39 14	99.81 8	99.52 18	92.35 121	99.90 53	99.74 8	99.51 103	98.71 210

APD-MVS		98.35 58	98.00 73	99.42 16	99.51 40	98.72 21	98.80 144	98.82 89	94.52 204	99.23 47	99.25 70	95.54 54	99.80 97	96.52 157	99.77 36	99.74 41
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_LR		98.34 60	98.23 56	98.67 85	99.27 82	96.90 115	97.95 278	99.58 3	97.14 68	98.44 104	99.01 113	95.03 79	99.62 148	97.91 82	99.75 48	99.50 96

PHI-MVS		98.34 60	98.06 68	99.18 46	99.15 107	98.12 61	99.04 73	99.09 36	93.32 267	98.83 76	99.10 95	96.54 21	99.83 78	97.70 99	99.76 42	99.59 84

MP-MVS		98.33 62	98.01 72	99.28 36	99.75 3	98.18 55	99.22 36	98.79 107	96.13 116	97.92 137	99.23 71	94.54 86	99.94 11	96.74 153	99.78 34	99.73 46
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MVSMamba_PlusPlus		98.31 63	98.19 62	98.67 85	98.96 129	97.36 90	99.24 30	98.57 163	94.81 188	98.99 62	98.90 129	95.22 71	99.59 151	99.15 23	99.84 11	99.07 177

MP-MVS-pluss		98.31 63	97.92 75	99.49 12	99.72 12	98.88 18	98.43 219	98.78 109	94.10 217	97.69 152	99.42 37	95.25 68	99.92 37	98.09 72	99.80 24	99.67 70
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.5_n_2		98.30 65	98.21 58	98.57 91	99.25 85	97.11 106	98.66 181	99.20 27	98.82 2	99.79 10	99.60 8	89.38 198	99.92 37	99.80 4	99.38 121	98.69 212

MVS_0304		98.23 66	97.91 76	99.21 43	98.06 223	97.96 67	98.58 194	95.51 396	98.58 9	98.87 72	99.26 65	92.99 112	99.95 9	99.62 15	99.67 66	99.73 46

ACMMP		98.23 66	97.95 74	99.09 56	99.74 7	97.62 77	99.03 76	99.41 6	95.98 121	97.60 161	99.36 50	94.45 91	99.93 30	97.14 126	98.85 150	99.70 58
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 68	98.11 65	98.49 103	98.34 190	97.26 99	99.61 5	98.43 199	96.78 84	98.87 72	98.84 136	93.72 103	99.01 241	98.91 30	99.50 104	99.19 153

fmvsm_s_conf0.1_n		98.18 69	98.21 58	98.11 140	98.54 172	95.24 200	98.87 119	99.24 18	97.50 40	99.70 19	99.67 1	91.33 156	99.89 56	99.47 18	99.54 98	99.21 148

fmvsm_s_conf0.1_n_2		98.14 70	98.02 71	98.53 98	98.88 135	97.07 108	98.69 173	98.82 89	98.78 4	99.77 12	99.61 4	88.83 217	99.91 46	99.71 10	99.07 134	98.61 222

fmvsm_s_conf0.1_n_a		98.08 71	98.04 70	98.21 128	97.66 259	95.39 190	98.89 110	99.17 31	97.24 60	99.76 14	99.67 1	91.13 161	99.88 65	99.39 19	99.41 116	99.35 121

dcpmvs_2		98.08 71	98.59 18	96.56 256	99.57 33	90.34 348	99.15 51	98.38 209	96.82 83	99.29 42	99.49 26	95.78 47	99.57 154	98.94 29	99.86 2	99.77 31

CANet		98.05 73	97.76 79	98.90 72	98.73 148	97.27 95	98.35 224	98.78 109	97.37 51	97.72 149	98.96 121	91.53 152	99.92 37	98.79 33	99.65 72	99.51 94

train_agg		97.97 74	97.52 91	99.33 30	99.31 68	98.50 29	97.92 283	98.73 120	92.98 283	97.74 146	98.68 156	96.20 32	99.80 97	96.59 154	99.57 89	99.68 66

ETV-MVS		97.96 75	97.81 77	98.40 114	98.42 178	97.27 95	98.73 162	98.55 168	96.84 81	98.38 106	97.44 275	95.39 58	99.35 193	97.62 104	98.89 145	98.58 228

UA-Net		97.96 75	97.62 83	98.98 64	98.86 139	97.47 85	98.89 110	99.08 37	96.67 94	98.72 85	99.54 15	93.15 110	99.81 90	94.87 212	98.83 151	99.65 74

CDPH-MVS		97.94 77	97.49 93	99.28 36	99.47 50	98.44 31	97.91 285	98.67 138	92.57 299	98.77 80	98.85 135	95.93 42	99.72 122	95.56 191	99.69 63	99.68 66

DeepPCF-MVS	96.37 2	97.93 78	98.48 28	96.30 281	99.00 122	89.54 363	97.43 328	98.87 74	98.16 16	99.26 46	99.38 45	96.12 35	99.64 141	98.30 63	99.77 36	99.72 50

DeepC-MVS	95.98 3	97.88 79	97.58 85	98.77 77	99.25 85	96.93 113	98.83 133	98.75 115	96.96 77	96.89 187	99.50 23	90.46 175	99.87 67	97.84 88	99.76 42	99.52 91
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 80	97.54 90	98.83 74	95.48 378	96.83 118	98.95 95	98.60 152	98.58 9	98.93 68	99.55 13	88.57 222	99.91 46	99.54 17	99.61 81	99.77 31

DP-MVS Recon		97.86 80	97.46 96	99.06 59	99.53 36	98.35 44	98.33 226	98.89 64	92.62 296	98.05 121	98.94 124	95.34 62	99.65 138	96.04 173	99.42 115	99.19 153

CSCG		97.85 82	97.74 80	98.20 130	99.67 25	95.16 203	99.22 36	99.32 11	93.04 281	97.02 180	98.92 127	95.36 61	99.91 46	97.43 118	99.64 77	99.52 91

BP-MVS1		97.82 83	97.51 92	98.76 78	98.25 200	97.39 89	99.15 51	97.68 296	96.69 92	98.47 98	99.10 95	90.29 179	99.51 171	98.60 40	99.35 124	99.37 119

MG-MVS		97.81 84	97.60 84	98.44 109	99.12 109	95.97 162	97.75 306	98.78 109	96.89 80	98.46 99	99.22 73	93.90 102	99.68 134	94.81 216	99.52 101	99.67 70

VNet		97.79 85	97.40 100	98.96 67	98.88 135	97.55 79	98.63 188	98.93 55	96.74 88	99.02 58	98.84 136	90.33 178	99.83 78	98.53 44	96.66 228	99.50 96

EIA-MVS		97.75 86	97.58 85	98.27 121	98.38 182	96.44 138	99.01 81	98.60 152	95.88 126	97.26 168	97.53 269	94.97 80	99.33 196	97.38 121	99.20 130	99.05 178

PS-MVSNAJ		97.73 87	97.77 78	97.62 181	98.68 158	95.58 180	97.34 337	98.51 178	97.29 54	98.66 90	97.88 234	94.51 87	99.90 53	97.87 85	99.17 132	97.39 271

casdiffmvs_mvg		97.72 88	97.48 95	98.44 109	98.42 178	96.59 131	98.92 103	98.44 195	96.20 113	97.76 143	99.20 76	91.66 146	99.23 206	98.27 67	98.41 174	99.49 101
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 88	97.32 104	98.92 69	99.64 28	97.10 107	99.12 58	98.81 95	92.34 307	98.09 118	99.08 104	93.01 111	99.92 37	96.06 172	99.77 36	99.75 39

PVSNet_Blended_VisFu		97.70 90	97.46 96	98.44 109	99.27 82	95.91 170	98.63 188	99.16 32	94.48 206	97.67 153	98.88 132	92.80 114	99.91 46	97.11 127	99.12 133	99.50 96

mvsany_test1		97.69 91	97.70 81	97.66 179	98.24 201	94.18 254	97.53 322	97.53 314	95.52 144	99.66 21	99.51 21	94.30 94	99.56 157	98.38 59	98.62 160	99.23 144

sasdasda		97.67 92	97.23 108	98.98 64	98.70 153	98.38 35	99.34 16	98.39 205	96.76 86	97.67 153	97.40 279	92.26 125	99.49 175	98.28 64	96.28 246	99.08 173

canonicalmvs		97.67 92	97.23 108	98.98 64	98.70 153	98.38 35	99.34 16	98.39 205	96.76 86	97.67 153	97.40 279	92.26 125	99.49 175	98.28 64	96.28 246	99.08 173

xiu_mvs_v2_base		97.66 94	97.70 81	97.56 185	98.61 167	95.46 187	97.44 326	98.46 191	97.15 67	98.65 91	98.15 210	94.33 93	99.80 97	97.84 88	98.66 159	97.41 269

GDP-MVS		97.64 95	97.28 105	98.71 82	98.30 198	97.33 91	99.05 69	98.52 175	96.34 108	98.80 77	99.05 107	89.74 188	99.51 171	96.86 147	98.86 149	99.28 136

baseline		97.64 95	97.44 98	98.25 125	98.35 185	96.20 150	99.00 83	98.32 219	96.33 110	98.03 124	99.17 83	91.35 155	99.16 213	98.10 71	98.29 181	99.39 117

casdiffmvs		97.63 97	97.41 99	98.28 120	98.33 193	96.14 154	98.82 135	98.32 219	96.38 107	97.95 132	99.21 74	91.23 160	99.23 206	98.12 70	98.37 175	99.48 103
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 98	97.19 111	98.92 69	98.66 160	98.20 53	99.32 21	98.38 209	96.69 92	97.58 162	97.42 278	92.10 133	99.50 174	98.28 64	96.25 249	99.08 173

xiu_mvs_v1_base_debu		97.60 99	97.56 87	97.72 169	98.35 185	95.98 157	97.86 295	98.51 178	97.13 69	99.01 59	98.40 183	91.56 148	99.80 97	98.53 44	98.68 155	97.37 273

xiu_mvs_v1_base		97.60 99	97.56 87	97.72 169	98.35 185	95.98 157	97.86 295	98.51 178	97.13 69	99.01 59	98.40 183	91.56 148	99.80 97	98.53 44	98.68 155	97.37 273

xiu_mvs_v1_base_debi		97.60 99	97.56 87	97.72 169	98.35 185	95.98 157	97.86 295	98.51 178	97.13 69	99.01 59	98.40 183	91.56 148	99.80 97	98.53 44	98.68 155	97.37 273

diffmvs		97.58 102	97.40 100	98.13 136	98.32 196	95.81 175	98.06 266	98.37 211	96.20 113	98.74 82	98.89 131	91.31 158	99.25 203	98.16 69	98.52 166	99.34 123
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVSFormer		97.57 103	97.49 93	97.84 156	98.07 220	95.76 176	99.47 7	98.40 203	94.98 177	98.79 78	98.83 138	92.34 122	98.41 314	96.91 135	99.59 85	99.34 123

alignmvs		97.56 104	97.07 117	99.01 61	98.66 160	98.37 42	98.83 133	98.06 276	96.74 88	98.00 130	97.65 257	90.80 169	99.48 180	98.37 60	96.56 232	99.19 153

DPM-MVS		97.55 105	96.99 120	99.23 42	99.04 117	98.55 27	97.17 352	98.35 214	94.85 187	97.93 136	98.58 166	95.07 77	99.71 127	92.60 284	99.34 125	99.43 114

OMC-MVS		97.55 105	97.34 103	98.20 130	99.33 63	95.92 169	98.28 236	98.59 156	95.52 144	97.97 131	99.10 95	93.28 109	99.49 175	95.09 207	98.88 146	99.19 153

PAPM_NR		97.46 107	97.11 114	98.50 101	99.50 42	96.41 141	98.63 188	98.60 152	95.18 164	97.06 178	98.06 216	94.26 96	99.57 154	93.80 252	98.87 148	99.52 91

EPP-MVSNet		97.46 107	97.28 105	97.99 148	98.64 164	95.38 191	99.33 20	98.31 221	93.61 256	97.19 171	99.07 105	94.05 99	99.23 206	96.89 139	98.43 173	99.37 119

3Dnovator	94.51 5	97.46 107	96.93 123	99.07 58	97.78 247	97.64 75	99.35 15	99.06 39	97.02 74	93.75 299	99.16 86	89.25 202	99.92 37	97.22 125	99.75 48	99.64 76

CNLPA		97.45 110	97.03 118	98.73 80	99.05 116	97.44 88	98.07 265	98.53 172	95.32 157	96.80 192	98.53 171	93.32 107	99.72 122	94.31 235	99.31 127	99.02 180

lupinMVS		97.44 111	97.22 110	98.12 139	98.07 220	95.76 176	97.68 311	97.76 293	94.50 205	98.79 78	98.61 161	92.34 122	99.30 199	97.58 107	99.59 85	99.31 129

3Dnovator+	94.38 6	97.43 112	96.78 131	99.38 18	97.83 244	98.52 28	99.37 12	98.71 125	97.09 72	92.99 328	99.13 91	89.36 199	99.89 56	96.97 132	99.57 89	99.71 54

Vis-MVSNet		97.42 113	97.11 114	98.34 117	98.66 160	96.23 149	99.22 36	99.00 44	96.63 96	98.04 123	99.21 74	88.05 238	99.35 193	96.01 175	99.21 129	99.45 111
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
API-MVS		97.41 114	97.25 107	97.91 152	98.70 153	96.80 119	98.82 135	98.69 130	94.53 202	98.11 116	98.28 198	94.50 90	99.57 154	94.12 241	99.49 106	97.37 273

sss		97.39 115	96.98 122	98.61 89	98.60 168	96.61 128	98.22 242	98.93 55	93.97 227	98.01 129	98.48 176	91.98 137	99.85 72	96.45 159	98.15 183	99.39 117

test_cas_vis1_n_1920		97.38 116	97.36 102	97.45 188	98.95 130	93.25 290	99.00 83	98.53 172	97.70 28	99.77 12	99.35 52	84.71 303	99.85 72	98.57 41	99.66 69	99.26 140

PVSNet_Blended		97.38 116	97.12 113	98.14 133	99.25 85	95.35 194	97.28 342	99.26 15	93.13 277	97.94 134	98.21 206	92.74 115	99.81 90	96.88 141	99.40 119	99.27 137

WTY-MVS		97.37 118	96.92 124	98.72 81	98.86 139	96.89 117	98.31 231	98.71 125	95.26 160	97.67 153	98.56 170	92.21 129	99.78 110	95.89 177	96.85 222	99.48 103

jason		97.32 119	97.08 116	98.06 144	97.45 279	95.59 179	97.87 293	97.91 287	94.79 189	98.55 96	98.83 138	91.12 162	99.23 206	97.58 107	99.60 83	99.34 123
jason: jason.
MVS_Test		97.28 120	97.00 119	98.13 136	98.33 193	95.97 162	98.74 158	98.07 271	94.27 212	98.44 104	98.07 215	92.48 118	99.26 202	96.43 160	98.19 182	99.16 159

EPNet		97.28 120	96.87 126	98.51 100	94.98 387	96.14 154	98.90 106	97.02 359	98.28 15	95.99 224	99.11 93	91.36 154	99.89 56	96.98 131	99.19 131	99.50 96
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvsmamba		97.25 122	96.99 120	98.02 146	98.34 190	95.54 184	99.18 48	97.47 320	95.04 173	98.15 113	98.57 169	89.46 195	99.31 198	97.68 101	99.01 139	99.22 146

test_yl		97.22 123	96.78 131	98.54 96	98.73 148	96.60 129	98.45 214	98.31 221	94.70 190	98.02 126	98.42 181	90.80 169	99.70 128	96.81 148	96.79 224	99.34 123

DCV-MVSNet		97.22 123	96.78 131	98.54 96	98.73 148	96.60 129	98.45 214	98.31 221	94.70 190	98.02 126	98.42 181	90.80 169	99.70 128	96.81 148	96.79 224	99.34 123

IS-MVSNet		97.22 123	96.88 125	98.25 125	98.85 141	96.36 144	99.19 44	97.97 281	95.39 151	97.23 169	98.99 115	91.11 163	98.93 253	94.60 223	98.59 162	99.47 105

PLC	95.07 4	97.20 126	96.78 131	98.44 109	99.29 77	96.31 148	98.14 255	98.76 113	92.41 305	96.39 212	98.31 196	94.92 82	99.78 110	94.06 244	98.77 154	99.23 144
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		97.18 127	97.18 112	97.20 201	98.81 144	93.27 287	95.78 397	99.15 33	95.25 161	96.79 193	98.11 213	92.29 124	99.07 231	98.56 43	99.85 6	99.25 142

LS3D		97.16 128	96.66 140	98.68 84	98.53 173	97.19 103	98.93 101	98.90 62	92.83 290	95.99 224	99.37 46	92.12 132	99.87 67	93.67 256	99.57 89	98.97 185

AdaColmap		97.15 129	96.70 136	98.48 104	99.16 104	96.69 125	98.01 272	98.89 64	94.44 208	96.83 188	98.68 156	90.69 172	99.76 116	94.36 231	99.29 128	98.98 184

mamv4		97.13 130	98.11 65	94.17 362	98.97 128	83.70 405	98.66 181	98.71 125	94.63 196	97.83 140	98.90 129	96.25 29	99.55 164	99.27 21	99.76 42	99.27 137

Effi-MVS+		97.12 131	96.69 137	98.39 115	98.19 209	96.72 124	97.37 333	98.43 199	93.71 245	97.65 157	98.02 219	92.20 130	99.25 203	96.87 144	97.79 195	99.19 153

CHOSEN 1792x2688		97.12 131	96.80 128	98.08 142	99.30 72	94.56 238	98.05 267	99.71 1	93.57 257	97.09 174	98.91 128	88.17 232	99.89 56	96.87 144	99.56 95	99.81 19

F-COLMAP		97.09 133	96.80 128	97.97 149	99.45 55	94.95 217	98.55 202	98.62 151	93.02 282	96.17 219	98.58 166	94.01 100	99.81 90	93.95 246	98.90 144	99.14 162

RRT-MVS		97.03 134	96.78 131	97.77 165	97.90 240	94.34 247	99.12 58	98.35 214	95.87 127	98.06 120	98.70 154	86.45 269	99.63 144	98.04 76	98.54 165	99.35 121

TAMVS		97.02 135	96.79 130	97.70 172	98.06 223	95.31 197	98.52 204	98.31 221	93.95 228	97.05 179	98.61 161	93.49 105	98.52 296	95.33 198	97.81 194	99.29 134

CDS-MVSNet		96.99 136	96.69 137	97.90 153	98.05 225	95.98 157	98.20 245	98.33 218	93.67 252	96.95 181	98.49 175	93.54 104	98.42 307	95.24 204	97.74 198	99.31 129
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CANet_DTU		96.96 137	96.55 143	98.21 128	98.17 214	96.07 156	97.98 276	98.21 238	97.24 60	97.13 173	98.93 125	86.88 261	99.91 46	95.00 210	99.37 123	98.66 218

114514_t		96.93 138	96.27 153	98.92 69	99.50 42	97.63 76	98.85 127	98.90 62	84.80 404	97.77 142	99.11 93	92.84 113	99.66 137	94.85 213	99.77 36	99.47 105

MAR-MVS		96.91 139	96.40 149	98.45 107	98.69 156	96.90 115	98.66 181	98.68 133	92.40 306	97.07 177	97.96 226	91.54 151	99.75 118	93.68 254	98.92 143	98.69 212
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		96.90 140	96.49 146	98.14 133	99.33 63	95.56 181	97.38 331	99.65 2	92.34 307	97.61 160	98.20 207	89.29 201	99.10 228	96.97 132	97.60 203	99.77 31

Vis-MVSNet (Re-imp)		96.87 141	96.55 143	97.83 157	98.73 148	95.46 187	99.20 42	98.30 227	94.96 179	96.60 200	98.87 133	90.05 182	98.59 291	93.67 256	98.60 161	99.46 109

SDMVSNet		96.85 142	96.42 147	98.14 133	99.30 72	96.38 142	99.21 39	99.23 23	95.92 123	95.96 226	98.76 150	85.88 279	99.44 185	97.93 80	95.59 261	98.60 223

PAPR		96.84 143	96.24 155	98.65 87	98.72 152	96.92 114	97.36 335	98.57 163	93.33 266	96.67 195	97.57 266	94.30 94	99.56 157	91.05 326	98.59 162	99.47 105

HY-MVS	93.96 8	96.82 144	96.23 156	98.57 91	98.46 177	97.00 110	98.14 255	98.21 238	93.95 228	96.72 194	97.99 223	91.58 147	99.76 116	94.51 227	96.54 233	98.95 188

UGNet		96.78 145	96.30 152	98.19 132	98.24 201	95.89 172	98.88 116	98.93 55	97.39 48	96.81 191	97.84 238	82.60 330	99.90 53	96.53 156	99.49 106	98.79 200
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
PVSNet_BlendedMVS		96.73 146	96.60 141	97.12 210	99.25 85	95.35 194	98.26 239	99.26 15	94.28 211	97.94 134	97.46 272	92.74 115	99.81 90	96.88 141	93.32 297	96.20 364

test_vis1_n_1920		96.71 147	96.84 127	96.31 280	99.11 111	89.74 356	99.05 69	98.58 161	98.08 17	99.87 2	99.37 46	78.48 362	99.93 30	99.29 20	99.69 63	99.27 137

mvs_anonymous		96.70 148	96.53 145	97.18 204	98.19 209	93.78 263	98.31 231	98.19 242	94.01 224	94.47 258	98.27 201	92.08 135	98.46 302	97.39 120	97.91 190	99.31 129

1112_ss		96.63 149	96.00 163	98.50 101	98.56 169	96.37 143	98.18 253	98.10 264	92.92 286	94.84 246	98.43 179	92.14 131	99.58 153	94.35 232	96.51 234	99.56 90

PMMVS		96.60 150	96.33 151	97.41 192	97.90 240	93.93 259	97.35 336	98.41 201	92.84 289	97.76 143	97.45 274	91.10 164	99.20 210	96.26 165	97.91 190	99.11 167

DP-MVS		96.59 151	95.93 166	98.57 91	99.34 61	96.19 152	98.70 171	98.39 205	89.45 376	94.52 256	99.35 52	91.85 141	99.85 72	92.89 280	98.88 146	99.68 66

PatchMatch-RL		96.59 151	96.03 162	98.27 121	99.31 68	96.51 135	97.91 285	99.06 39	93.72 244	96.92 185	98.06 216	88.50 227	99.65 138	91.77 309	99.00 141	98.66 218

GeoE		96.58 153	96.07 159	98.10 141	98.35 185	95.89 172	99.34 16	98.12 258	93.12 278	96.09 220	98.87 133	89.71 189	98.97 243	92.95 276	98.08 186	99.43 114

XVG-OURS		96.55 154	96.41 148	96.99 217	98.75 147	93.76 264	97.50 325	98.52 175	95.67 138	96.83 188	99.30 60	88.95 215	99.53 167	95.88 178	96.26 248	97.69 262

FIs		96.51 155	96.12 158	97.67 176	97.13 303	97.54 81	99.36 13	99.22 26	95.89 125	94.03 285	98.35 189	91.98 137	98.44 305	96.40 161	92.76 305	97.01 281

XVG-OURS-SEG-HR		96.51 155	96.34 150	97.02 216	98.77 146	93.76 264	97.79 304	98.50 183	95.45 147	96.94 182	99.09 102	87.87 243	99.55 164	96.76 152	95.83 260	97.74 259

PS-MVSNAJss		96.43 157	96.26 154	96.92 226	95.84 367	95.08 208	99.16 50	98.50 183	95.87 127	93.84 294	98.34 193	94.51 87	98.61 288	96.88 141	93.45 294	97.06 279

test_fmvs1		96.42 158	96.67 139	95.66 309	98.82 143	88.53 383	98.80 144	98.20 240	96.39 106	99.64 23	99.20 76	80.35 350	99.67 135	99.04 26	99.57 89	98.78 203

FC-MVSNet-test		96.42 158	96.05 160	97.53 186	96.95 312	97.27 95	99.36 13	99.23 23	95.83 129	93.93 288	98.37 187	92.00 136	98.32 325	96.02 174	92.72 306	97.00 282

ab-mvs		96.42 158	95.71 176	98.55 94	98.63 165	96.75 122	97.88 292	98.74 117	93.84 234	96.54 205	98.18 209	85.34 289	99.75 118	95.93 176	96.35 238	99.15 160

FA-MVS(test-final)		96.41 161	95.94 165	97.82 159	98.21 205	95.20 202	97.80 302	97.58 304	93.21 272	97.36 166	97.70 250	89.47 194	99.56 157	94.12 241	97.99 187	98.71 210

PVSNet	91.96 18	96.35 162	96.15 157	96.96 221	99.17 100	92.05 312	96.08 390	98.68 133	93.69 248	97.75 145	97.80 244	88.86 216	99.69 133	94.26 237	99.01 139	99.15 160

Test_1112_low_res		96.34 163	95.66 181	98.36 116	98.56 169	95.94 165	97.71 309	98.07 271	92.10 316	94.79 250	97.29 287	91.75 143	99.56 157	94.17 239	96.50 235	99.58 88

Effi-MVS+-dtu		96.29 164	96.56 142	95.51 314	97.89 242	90.22 349	98.80 144	98.10 264	96.57 99	96.45 210	96.66 343	90.81 168	98.91 256	95.72 185	97.99 187	97.40 270

QAPM		96.29 164	95.40 186	98.96 67	97.85 243	97.60 78	99.23 32	98.93 55	89.76 370	93.11 325	99.02 109	89.11 207	99.93 30	91.99 303	99.62 80	99.34 123

Fast-Effi-MVS+		96.28 166	95.70 178	98.03 145	98.29 199	95.97 162	98.58 194	98.25 235	91.74 324	95.29 239	97.23 292	91.03 166	99.15 216	92.90 278	97.96 189	98.97 185

nrg030		96.28 166	95.72 173	97.96 151	96.90 317	98.15 58	99.39 10	98.31 221	95.47 146	94.42 264	98.35 189	92.09 134	98.69 280	97.50 116	89.05 355	97.04 280

1314		96.25 168	95.73 172	97.79 161	97.13 303	95.55 183	98.19 248	98.59 156	93.47 261	92.03 353	97.82 242	91.33 156	99.49 175	94.62 222	98.44 171	98.32 242

sd_testset		96.17 169	95.76 171	97.42 191	99.30 72	94.34 247	98.82 135	99.08 37	95.92 123	95.96 226	98.76 150	82.83 329	99.32 197	95.56 191	95.59 261	98.60 223

h-mvs33		96.17 169	95.62 182	97.81 160	99.03 118	94.45 240	98.64 185	98.75 115	97.48 42	98.67 86	98.72 153	89.76 186	99.86 71	97.95 78	81.59 401	99.11 167

HQP_MVS		96.14 171	95.90 167	96.85 229	97.42 281	94.60 236	98.80 144	98.56 166	97.28 55	95.34 235	98.28 198	87.09 256	99.03 236	96.07 169	94.27 269	96.92 288

tttt0517		96.07 172	95.51 184	97.78 162	98.41 180	94.84 221	99.28 24	94.33 409	94.26 213	97.64 158	98.64 160	84.05 318	99.47 182	95.34 197	97.60 203	99.03 179

MVSTER		96.06 173	95.72 173	97.08 213	98.23 203	95.93 168	98.73 162	98.27 230	94.86 185	95.07 241	98.09 214	88.21 231	98.54 294	96.59 154	93.46 292	96.79 307

thisisatest0530		96.01 174	95.36 191	97.97 149	98.38 182	95.52 185	98.88 116	94.19 411	94.04 219	97.64 158	98.31 196	83.82 325	99.46 183	95.29 201	97.70 200	98.93 190

test_djsdf		96.00 175	95.69 179	96.93 223	95.72 369	95.49 186	99.47 7	98.40 203	94.98 177	94.58 254	97.86 235	89.16 205	98.41 314	96.91 135	94.12 277	96.88 297

EI-MVSNet		95.96 176	95.83 169	96.36 276	97.93 238	93.70 270	98.12 258	98.27 230	93.70 247	95.07 241	99.02 109	92.23 128	98.54 294	94.68 218	93.46 292	96.84 303

ECVR-MVS		95.95 177	95.71 176	96.65 241	99.02 119	90.86 334	99.03 76	91.80 422	96.96 77	98.10 117	99.26 65	81.31 336	99.51 171	96.90 138	99.04 136	99.59 84

BH-untuned		95.95 177	95.72 173	96.65 241	98.55 171	92.26 306	98.23 241	97.79 292	93.73 242	94.62 253	98.01 221	88.97 214	99.00 242	93.04 273	98.51 167	98.68 214

test1111		95.94 179	95.78 170	96.41 273	98.99 125	90.12 350	99.04 73	92.45 421	96.99 76	98.03 124	99.27 64	81.40 335	99.48 180	96.87 144	99.04 136	99.63 78

MSDG		95.93 180	95.30 198	97.83 157	98.90 133	95.36 192	96.83 377	98.37 211	91.32 339	94.43 263	98.73 152	90.27 180	99.60 150	90.05 340	98.82 152	98.52 230

BH-RMVSNet		95.92 181	95.32 196	97.69 173	98.32 196	94.64 230	98.19 248	97.45 325	94.56 200	96.03 222	98.61 161	85.02 294	99.12 222	90.68 331	99.06 135	99.30 132

test_fmvs1_n		95.90 182	95.99 164	95.63 310	98.67 159	88.32 387	99.26 27	98.22 237	96.40 105	99.67 20	99.26 65	73.91 399	99.70 128	99.02 27	99.50 104	98.87 194

Fast-Effi-MVS+-dtu		95.87 183	95.85 168	95.91 297	97.74 252	91.74 318	98.69 173	98.15 254	95.56 142	94.92 244	97.68 255	88.98 213	98.79 274	93.19 268	97.78 196	97.20 277

LFMVS		95.86 184	94.98 213	98.47 105	98.87 138	96.32 146	98.84 131	96.02 388	93.40 264	98.62 92	99.20 76	74.99 393	99.63 144	97.72 94	97.20 210	99.46 109

baseline1		95.84 185	95.12 206	98.01 147	98.49 176	95.98 157	98.73 162	97.03 357	95.37 154	96.22 215	98.19 208	89.96 184	99.16 213	94.60 223	87.48 371	98.90 193

OpenMVS	93.04 13	95.83 186	95.00 211	98.32 118	97.18 300	97.32 92	99.21 39	98.97 47	89.96 366	91.14 362	99.05 107	86.64 264	99.92 37	93.38 262	99.47 109	97.73 260

VDD-MVS		95.82 187	95.23 200	97.61 182	98.84 142	93.98 258	98.68 175	97.40 329	95.02 175	97.95 132	99.34 56	74.37 398	99.78 110	98.64 38	96.80 223	99.08 173

UniMVSNet (Re)		95.78 188	95.19 202	97.58 183	96.99 310	97.47 85	98.79 151	99.18 30	95.60 140	93.92 289	97.04 314	91.68 144	98.48 298	95.80 182	87.66 370	96.79 307

VPA-MVSNet		95.75 189	95.11 207	97.69 173	97.24 292	97.27 95	98.94 98	99.23 23	95.13 166	95.51 233	97.32 285	85.73 281	98.91 256	97.33 123	89.55 346	96.89 296

HQP-MVS		95.72 190	95.40 186	96.69 239	97.20 296	94.25 252	98.05 267	98.46 191	96.43 102	94.45 259	97.73 247	86.75 262	98.96 247	95.30 199	94.18 273	96.86 302

hse-mvs2		95.71 191	95.30 198	96.93 223	98.50 174	93.53 275	98.36 223	98.10 264	97.48 42	98.67 86	97.99 223	89.76 186	99.02 239	97.95 78	80.91 406	98.22 245

UniMVSNet_NR-MVSNet		95.71 191	95.15 203	97.40 194	96.84 320	96.97 111	98.74 158	99.24 18	95.16 165	93.88 291	97.72 249	91.68 144	98.31 327	95.81 180	87.25 376	96.92 288

PatchmatchNet		95.71 191	95.52 183	96.29 282	97.58 265	90.72 338	96.84 376	97.52 315	94.06 218	97.08 175	96.96 324	89.24 203	98.90 259	92.03 302	98.37 175	99.26 140
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
OPM-MVS		95.69 194	95.33 195	96.76 234	96.16 355	94.63 231	98.43 219	98.39 205	96.64 95	95.02 243	98.78 143	85.15 293	99.05 232	95.21 206	94.20 272	96.60 330
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMM	93.85 9	95.69 194	95.38 190	96.61 249	97.61 262	93.84 262	98.91 105	98.44 195	95.25 161	94.28 271	98.47 177	86.04 278	99.12 222	95.50 194	93.95 282	96.87 300
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpmrst		95.63 196	95.69 179	95.44 318	97.54 270	88.54 382	96.97 362	97.56 307	93.50 259	97.52 164	96.93 328	89.49 192	99.16 213	95.25 203	96.42 237	98.64 220

FE-MVS		95.62 197	94.90 217	97.78 162	98.37 184	94.92 218	97.17 352	97.38 331	90.95 350	97.73 148	97.70 250	85.32 291	99.63 144	91.18 318	98.33 178	98.79 200

LPG-MVS_test		95.62 197	95.34 192	96.47 267	97.46 276	93.54 273	98.99 86	98.54 170	94.67 194	94.36 267	98.77 145	85.39 286	99.11 224	95.71 186	94.15 275	96.76 310

CLD-MVS		95.62 197	95.34 192	96.46 270	97.52 273	93.75 266	97.27 343	98.46 191	95.53 143	94.42 264	98.00 222	86.21 273	98.97 243	96.25 167	94.37 267	96.66 325
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		95.61 200	94.89 218	97.76 166	98.15 216	95.15 205	96.77 378	94.41 407	92.95 285	97.18 172	97.43 276	84.78 300	99.45 184	94.63 220	97.73 199	98.68 214

MonoMVSNet		95.51 201	95.45 185	95.68 307	95.54 374	90.87 333	98.92 103	97.37 332	95.79 131	95.53 232	97.38 281	89.58 191	97.68 370	96.40 161	92.59 307	98.49 232

thres600view7		95.49 202	94.77 221	97.67 176	98.98 126	95.02 210	98.85 127	96.90 366	95.38 152	96.63 197	96.90 330	84.29 310	99.59 151	88.65 362	96.33 239	98.40 236

test_vis1_n		95.47 203	95.13 204	96.49 264	97.77 248	90.41 346	99.27 26	98.11 261	96.58 97	99.66 21	99.18 82	67.00 412	99.62 148	99.21 22	99.40 119	99.44 112

SCA		95.46 204	95.13 204	96.46 270	97.67 257	91.29 326	97.33 338	97.60 303	94.68 193	96.92 185	97.10 299	83.97 320	98.89 260	92.59 286	98.32 180	99.20 149

IterMVS-LS		95.46 204	95.21 201	96.22 284	98.12 217	93.72 269	98.32 230	98.13 257	93.71 245	94.26 272	97.31 286	92.24 127	98.10 343	94.63 220	90.12 337	96.84 303
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing3-2		95.45 206	95.34 192	95.77 305	98.69 156	88.75 378	98.87 119	97.21 344	96.13 116	97.22 170	97.68 255	77.95 370	99.65 138	97.58 107	96.77 226	98.91 192

jajsoiax		95.45 206	95.03 210	96.73 235	95.42 382	94.63 231	99.14 54	98.52 175	95.74 133	93.22 318	98.36 188	83.87 323	98.65 285	96.95 134	94.04 278	96.91 293

CVMVSNet		95.43 208	96.04 161	93.57 368	97.93 238	83.62 406	98.12 258	98.59 156	95.68 137	96.56 201	99.02 109	87.51 249	97.51 378	93.56 260	97.44 206	99.60 82

anonymousdsp		95.42 209	94.91 216	96.94 222	95.10 386	95.90 171	99.14 54	98.41 201	93.75 239	93.16 321	97.46 272	87.50 251	98.41 314	95.63 190	94.03 279	96.50 349

DU-MVS		95.42 209	94.76 222	97.40 194	96.53 337	96.97 111	98.66 181	98.99 46	95.43 148	93.88 291	97.69 252	88.57 222	98.31 327	95.81 180	87.25 376	96.92 288

mvs_tets		95.41 211	95.00 211	96.65 241	95.58 373	94.42 242	99.00 83	98.55 168	95.73 135	93.21 319	98.38 186	83.45 327	98.63 286	97.09 128	94.00 280	96.91 293

thres100view900		95.38 212	94.70 226	97.41 192	98.98 126	94.92 218	98.87 119	96.90 366	95.38 152	96.61 199	96.88 331	84.29 310	99.56 157	88.11 365	96.29 243	97.76 257

thres400		95.38 212	94.62 230	97.65 180	98.94 131	94.98 214	98.68 175	96.93 364	95.33 155	96.55 203	96.53 349	84.23 314	99.56 157	88.11 365	96.29 243	98.40 236

BH-w/o		95.38 212	95.08 208	96.26 283	98.34 190	91.79 315	97.70 310	97.43 327	92.87 288	94.24 274	97.22 293	88.66 220	98.84 266	91.55 314	97.70 200	98.16 248

VDDNet		95.36 215	94.53 235	97.86 155	98.10 219	95.13 206	98.85 127	97.75 294	90.46 357	98.36 107	99.39 40	73.27 401	99.64 141	97.98 77	96.58 231	98.81 199

TAPA-MVS	93.98 7	95.35 216	94.56 234	97.74 168	99.13 108	94.83 223	98.33 226	98.64 146	86.62 392	96.29 214	98.61 161	94.00 101	99.29 200	80.00 407	99.41 116	99.09 169
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ACMP	93.49 10	95.34 217	94.98 213	96.43 272	97.67 257	93.48 277	98.73 162	98.44 195	94.94 183	92.53 341	98.53 171	84.50 309	99.14 218	95.48 195	94.00 280	96.66 325
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
COLMAP_ROB	93.27 12	95.33 218	94.87 219	96.71 236	99.29 77	93.24 291	98.58 194	98.11 261	89.92 367	93.57 303	99.10 95	86.37 271	99.79 107	90.78 329	98.10 185	97.09 278
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
UBG		95.32 219	94.72 225	97.13 208	98.05 225	93.26 288	97.87 293	97.20 345	94.96 179	96.18 218	95.66 381	80.97 342	99.35 193	94.47 229	97.08 213	98.78 203

tfpn200view9		95.32 219	94.62 230	97.43 190	98.94 131	94.98 214	98.68 175	96.93 364	95.33 155	96.55 203	96.53 349	84.23 314	99.56 157	88.11 365	96.29 243	97.76 257

Anonymous202405211		95.28 221	94.49 237	97.67 176	99.00 122	93.75 266	98.70 171	97.04 356	90.66 353	96.49 207	98.80 141	78.13 366	99.83 78	96.21 168	95.36 265	99.44 112

thres200		95.25 222	94.57 233	97.28 198	98.81 144	94.92 218	98.20 245	97.11 349	95.24 163	96.54 205	96.22 360	84.58 307	99.53 167	87.93 370	96.50 235	97.39 271

AllTest		95.24 223	94.65 229	96.99 217	99.25 85	93.21 292	98.59 192	98.18 245	91.36 335	93.52 305	98.77 145	84.67 304	99.72 122	89.70 347	97.87 192	98.02 252

LCM-MVSNet-Re		95.22 224	95.32 196	94.91 335	98.18 211	87.85 393	98.75 154	95.66 395	95.11 168	88.96 381	96.85 334	90.26 181	97.65 371	95.65 189	98.44 171	99.22 146

EPNet_dtu		95.21 225	94.95 215	95.99 292	96.17 353	90.45 344	98.16 254	97.27 340	96.77 85	93.14 324	98.33 194	90.34 177	98.42 307	85.57 383	98.81 153	99.09 169
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
XXY-MVS		95.20 226	94.45 242	97.46 187	96.75 327	96.56 133	98.86 123	98.65 145	93.30 269	93.27 317	98.27 201	84.85 298	98.87 263	94.82 215	91.26 323	96.96 284

D2MVS		95.18 227	95.08 208	95.48 315	97.10 305	92.07 311	98.30 233	99.13 35	94.02 221	92.90 329	96.73 340	89.48 193	98.73 278	94.48 228	93.60 291	95.65 377

WR-MVS		95.15 228	94.46 240	97.22 200	96.67 332	96.45 137	98.21 243	98.81 95	94.15 215	93.16 321	97.69 252	87.51 249	98.30 329	95.29 201	88.62 361	96.90 295

TranMVSNet+NR-MVSNet		95.14 229	94.48 238	97.11 211	96.45 343	96.36 144	99.03 76	99.03 42	95.04 173	93.58 302	97.93 228	88.27 230	98.03 349	94.13 240	86.90 381	96.95 286

myMVS_eth3d28		95.12 230	94.62 230	96.64 245	98.17 214	92.17 307	98.02 271	97.32 334	95.41 150	96.22 215	96.05 366	78.01 368	99.13 219	95.22 205	97.16 211	98.60 223

baseline2		95.11 231	94.52 236	96.87 228	96.65 333	93.56 272	98.27 238	94.10 413	93.45 262	92.02 354	97.43 276	87.45 253	99.19 211	93.88 249	97.41 208	97.87 255

miper_enhance_ethall		95.10 232	94.75 223	96.12 288	97.53 272	93.73 268	96.61 384	98.08 269	92.20 315	93.89 290	96.65 345	92.44 119	98.30 329	94.21 238	91.16 324	96.34 358

Anonymous20240529		95.10 232	94.22 252	97.75 167	99.01 121	94.26 251	98.87 119	98.83 86	85.79 400	96.64 196	98.97 116	78.73 359	99.85 72	96.27 164	94.89 266	99.12 164

test-LLR		95.10 232	94.87 219	95.80 302	96.77 324	89.70 358	96.91 367	95.21 399	95.11 168	94.83 248	95.72 378	87.71 245	98.97 243	93.06 271	98.50 168	98.72 207

WR-MVS_H		95.05 235	94.46 240	96.81 232	96.86 319	95.82 174	99.24 30	99.24 18	93.87 233	92.53 341	96.84 335	90.37 176	98.24 335	93.24 266	87.93 367	96.38 357

miper_ehance_all_eth		95.01 236	94.69 227	95.97 294	97.70 255	93.31 286	97.02 360	98.07 271	92.23 312	93.51 307	96.96 324	91.85 141	98.15 339	93.68 254	91.16 324	96.44 355

testing11		95.00 237	94.28 249	97.16 206	97.96 235	93.36 285	98.09 263	97.06 355	94.94 183	95.33 238	96.15 362	76.89 383	99.40 188	95.77 184	96.30 242	98.72 207

ADS-MVSNet		95.00 237	94.45 242	96.63 246	98.00 229	91.91 314	96.04 391	97.74 295	90.15 363	96.47 208	96.64 346	87.89 241	98.96 247	90.08 338	97.06 214	99.02 180

VPNet		94.99 239	94.19 254	97.40 194	97.16 301	96.57 132	98.71 167	98.97 47	95.67 138	94.84 246	98.24 205	80.36 349	98.67 284	96.46 158	87.32 375	96.96 284

EPMVS		94.99 239	94.48 238	96.52 262	97.22 294	91.75 317	97.23 344	91.66 423	94.11 216	97.28 167	96.81 337	85.70 282	98.84 266	93.04 273	97.28 209	98.97 185

testing91		94.98 241	94.25 251	97.20 201	97.94 236	93.41 280	98.00 274	97.58 304	94.99 176	95.45 234	96.04 367	77.20 378	99.42 187	94.97 211	96.02 256	98.78 203

NR-MVSNet		94.98 241	94.16 257	97.44 189	96.53 337	97.22 102	98.74 158	98.95 51	94.96 179	89.25 380	97.69 252	89.32 200	98.18 337	94.59 225	87.40 373	96.92 288

FMVSNet3		94.97 243	94.26 250	97.11 211	98.18 211	96.62 126	98.56 201	98.26 234	93.67 252	94.09 281	97.10 299	84.25 312	98.01 350	92.08 298	92.14 310	96.70 319

CostFormer		94.95 244	94.73 224	95.60 312	97.28 290	89.06 371	97.53 322	96.89 368	89.66 372	96.82 190	96.72 341	86.05 276	98.95 252	95.53 193	96.13 254	98.79 200

PAPM		94.95 244	94.00 270	97.78 162	97.04 307	95.65 178	96.03 393	98.25 235	91.23 344	94.19 277	97.80 244	91.27 159	98.86 265	82.61 400	97.61 202	98.84 197

CP-MVSNet		94.94 246	94.30 248	96.83 230	96.72 329	95.56 181	99.11 60	98.95 51	93.89 231	92.42 346	97.90 231	87.19 255	98.12 342	94.32 234	88.21 364	96.82 306

TR-MVS		94.94 246	94.20 253	97.17 205	97.75 249	94.14 255	97.59 319	97.02 359	92.28 311	95.75 230	97.64 260	83.88 322	98.96 247	89.77 344	96.15 253	98.40 236

RPSCF		94.87 248	95.40 186	93.26 374	98.89 134	82.06 412	98.33 226	98.06 276	90.30 362	96.56 201	99.26 65	87.09 256	99.49 175	93.82 251	96.32 240	98.24 243

testing99		94.83 249	94.08 262	97.07 214	97.94 236	93.13 294	98.10 262	97.17 347	94.86 185	95.34 235	96.00 370	76.31 386	99.40 188	95.08 208	95.90 257	98.68 214

GA-MVS		94.81 250	94.03 266	97.14 207	97.15 302	93.86 261	96.76 379	97.58 304	94.00 225	94.76 252	97.04 314	80.91 343	98.48 298	91.79 308	96.25 249	99.09 169

c3_l		94.79 251	94.43 244	95.89 299	97.75 249	93.12 296	97.16 354	98.03 278	92.23 312	93.46 311	97.05 313	91.39 153	98.01 350	93.58 259	89.21 353	96.53 341

V42		94.78 252	94.14 259	96.70 238	96.33 348	95.22 201	98.97 89	98.09 268	92.32 309	94.31 270	97.06 310	88.39 228	98.55 293	92.90 278	88.87 359	96.34 358

reproduce_monomvs		94.77 253	94.67 228	95.08 330	98.40 181	89.48 364	98.80 144	98.64 146	97.57 36	93.21 319	97.65 257	80.57 348	98.83 269	97.72 94	89.47 349	96.93 287

CR-MVSNet		94.76 254	94.15 258	96.59 252	97.00 308	93.43 278	94.96 404	97.56 307	92.46 300	96.93 183	96.24 356	88.15 233	97.88 363	87.38 372	96.65 229	98.46 234

v2v482		94.69 255	94.03 266	96.65 241	96.17 353	94.79 226	98.67 179	98.08 269	92.72 292	94.00 286	97.16 296	87.69 248	98.45 303	92.91 277	88.87 359	96.72 315

pmmvs4		94.69 255	93.99 272	96.81 232	95.74 368	95.94 165	97.40 329	97.67 298	90.42 359	93.37 314	97.59 264	89.08 208	98.20 336	92.97 275	91.67 317	96.30 361

cl22		94.68 257	94.19 254	96.13 287	98.11 218	93.60 271	96.94 364	98.31 221	92.43 304	93.32 316	96.87 333	86.51 265	98.28 333	94.10 243	91.16 324	96.51 347

eth_miper_zixun_eth		94.68 257	94.41 245	95.47 316	97.64 260	91.71 319	96.73 381	98.07 271	92.71 293	93.64 300	97.21 294	90.54 174	98.17 338	93.38 262	89.76 341	96.54 339

PCF-MVS	93.45 11	94.68 257	93.43 308	98.42 113	98.62 166	96.77 121	95.48 401	98.20 240	84.63 405	93.34 315	98.32 195	88.55 225	99.81 90	84.80 392	98.96 142	98.68 214
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS		94.67 260	93.54 303	98.08 142	96.88 318	96.56 133	98.19 248	98.50 183	78.05 416	92.69 336	98.02 219	91.07 165	99.63 144	90.09 337	98.36 177	98.04 251

PS-CasMVS		94.67 260	93.99 272	96.71 236	96.68 331	95.26 198	99.13 57	99.03 42	93.68 250	92.33 347	97.95 227	85.35 288	98.10 343	93.59 258	88.16 366	96.79 307

cascas		94.63 262	93.86 282	96.93 223	96.91 316	94.27 250	96.00 394	98.51 178	85.55 401	94.54 255	96.23 358	84.20 316	98.87 263	95.80 182	96.98 219	97.66 263

tpmvs		94.60 263	94.36 247	95.33 322	97.46 276	88.60 381	96.88 373	97.68 296	91.29 341	93.80 296	96.42 353	88.58 221	99.24 205	91.06 324	96.04 255	98.17 247

LTVRE_ROB	92.95 15	94.60 263	93.90 278	96.68 240	97.41 284	94.42 242	98.52 204	98.59 156	91.69 327	91.21 361	98.35 189	84.87 297	99.04 235	91.06 324	93.44 295	96.60 330
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		94.59 265	93.92 275	96.60 251	96.21 350	94.78 227	98.59 192	98.14 256	91.86 323	94.21 276	97.02 317	87.97 239	98.41 314	91.72 310	89.57 344	96.61 329

ADS-MVSNet2		94.58 266	94.40 246	95.11 328	98.00 229	88.74 379	96.04 391	97.30 336	90.15 363	96.47 208	96.64 346	87.89 241	97.56 376	90.08 338	97.06 214	99.02 180

WBMVS		94.56 267	94.04 264	96.10 289	98.03 227	93.08 298	97.82 301	98.18 245	94.02 221	93.77 298	96.82 336	81.28 337	98.34 322	95.47 196	91.00 327	96.88 297

ACMH	92.88 16	94.55 268	93.95 274	96.34 278	97.63 261	93.26 288	98.81 143	98.49 188	93.43 263	89.74 375	98.53 171	81.91 332	99.08 230	93.69 253	93.30 298	96.70 319
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		94.54 269	93.85 283	96.63 246	97.98 233	93.06 299	98.77 153	97.84 290	93.67 252	93.80 296	98.04 218	76.88 384	98.96 247	94.79 217	92.86 303	97.86 256

XVG-ACMP-BASELINE		94.54 269	94.14 259	95.75 306	96.55 336	91.65 320	98.11 260	98.44 195	94.96 179	94.22 275	97.90 231	79.18 358	99.11 224	94.05 245	93.85 284	96.48 352

AUN-MVS		94.53 271	93.73 293	96.92 226	98.50 174	93.52 276	98.34 225	98.10 264	93.83 236	95.94 228	97.98 225	85.59 284	99.03 236	94.35 232	80.94 405	98.22 245

DIV-MVS_self_test		94.52 272	94.03 266	95.99 292	97.57 269	93.38 283	97.05 358	97.94 284	91.74 324	92.81 331	97.10 299	89.12 206	98.07 347	92.60 284	90.30 334	96.53 341

cl____		94.51 273	94.01 269	96.02 291	97.58 265	93.40 282	97.05 358	97.96 283	91.73 326	92.76 333	97.08 305	89.06 209	98.13 341	92.61 283	90.29 335	96.52 344

ETVMVS		94.50 274	93.44 307	97.68 175	98.18 211	95.35 194	98.19 248	97.11 349	93.73 242	96.40 211	95.39 384	74.53 395	98.84 266	91.10 320	96.31 241	98.84 197

GBi-Net		94.49 275	93.80 286	96.56 256	98.21 205	95.00 211	98.82 135	98.18 245	92.46 300	94.09 281	97.07 306	81.16 338	97.95 355	92.08 298	92.14 310	96.72 315

test1		94.49 275	93.80 286	96.56 256	98.21 205	95.00 211	98.82 135	98.18 245	92.46 300	94.09 281	97.07 306	81.16 338	97.95 355	92.08 298	92.14 310	96.72 315

dmvs_re		94.48 277	94.18 256	95.37 320	97.68 256	90.11 351	98.54 203	97.08 351	94.56 200	94.42 264	97.24 291	84.25 312	97.76 368	91.02 327	92.83 304	98.24 243

v8		94.47 278	93.77 289	96.57 255	96.36 346	94.83 223	99.05 69	98.19 242	91.92 320	93.16 321	96.97 322	88.82 219	98.48 298	91.69 311	87.79 368	96.39 356

FMVSNet2		94.47 278	93.61 299	97.04 215	98.21 205	96.43 139	98.79 151	98.27 230	92.46 300	93.50 308	97.09 303	81.16 338	98.00 352	91.09 321	91.93 313	96.70 319

test2506		94.44 280	93.91 277	96.04 290	99.02 119	88.99 374	99.06 67	79.47 435	96.96 77	98.36 107	99.26 65	77.21 377	99.52 170	96.78 151	99.04 136	99.59 84

Patchmatch-test		94.42 281	93.68 297	96.63 246	97.60 263	91.76 316	94.83 408	97.49 319	89.45 376	94.14 279	97.10 299	88.99 210	98.83 269	85.37 386	98.13 184	99.29 134

PEN-MVS		94.42 281	93.73 293	96.49 264	96.28 349	94.84 221	99.17 49	99.00 44	93.51 258	92.23 349	97.83 241	86.10 275	97.90 359	92.55 289	86.92 380	96.74 312

v144192		94.39 283	93.70 295	96.48 266	96.06 358	94.35 246	98.58 194	98.16 253	91.45 332	94.33 269	97.02 317	87.50 251	98.45 303	91.08 323	89.11 354	96.63 327

Baseline_NR-MVSNet		94.35 284	93.81 285	95.96 295	96.20 351	94.05 257	98.61 191	96.67 378	91.44 333	93.85 293	97.60 263	88.57 222	98.14 340	94.39 230	86.93 379	95.68 376

miper_lstm_enhance		94.33 285	94.07 263	95.11 328	97.75 249	90.97 330	97.22 345	98.03 278	91.67 328	92.76 333	96.97 322	90.03 183	97.78 367	92.51 291	89.64 343	96.56 336

v1192		94.32 286	93.58 300	96.53 261	96.10 356	94.45 240	98.50 210	98.17 251	91.54 330	94.19 277	97.06 310	86.95 260	98.43 306	90.14 336	89.57 344	96.70 319

UWE-MVS		94.30 287	93.89 280	95.53 313	97.83 244	88.95 375	97.52 324	93.25 415	94.44 208	96.63 197	97.07 306	78.70 360	99.28 201	91.99 303	97.56 205	98.36 239

ACMH+	92.99 14	94.30 287	93.77 289	95.88 300	97.81 246	92.04 313	98.71 167	98.37 211	93.99 226	90.60 368	98.47 177	80.86 345	99.05 232	92.75 282	92.40 309	96.55 338

v148		94.29 289	93.76 291	95.91 297	96.10 356	92.93 300	98.58 194	97.97 281	92.59 298	93.47 310	96.95 326	88.53 226	98.32 325	92.56 288	87.06 378	96.49 350

v10		94.29 289	93.55 302	96.51 263	96.39 345	94.80 225	98.99 86	98.19 242	91.35 337	93.02 327	96.99 320	88.09 235	98.41 314	90.50 333	88.41 363	96.33 360

MVP-Stereo		94.28 291	93.92 275	95.35 321	94.95 388	92.60 303	97.97 277	97.65 299	91.61 329	90.68 367	97.09 303	86.32 272	98.42 307	89.70 347	99.34 125	95.02 390
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UniMVSNet_ETH3D		94.24 292	93.33 310	96.97 220	97.19 299	93.38 283	98.74 158	98.57 163	91.21 346	93.81 295	98.58 166	72.85 402	98.77 276	95.05 209	93.93 283	98.77 206

OurMVSNet-221017-0		94.21 293	94.00 270	94.85 339	95.60 372	89.22 369	98.89 110	97.43 327	95.29 158	92.18 350	98.52 174	82.86 328	98.59 291	93.46 261	91.76 315	96.74 312

v1921920		94.20 294	93.47 306	96.40 275	95.98 361	94.08 256	98.52 204	98.15 254	91.33 338	94.25 273	97.20 295	86.41 270	98.42 307	90.04 341	89.39 351	96.69 324

WB-MVSnew		94.19 295	94.04 264	94.66 346	96.82 322	92.14 308	97.86 295	95.96 391	93.50 259	95.64 231	96.77 339	88.06 237	97.99 353	84.87 389	96.86 220	93.85 407

v7n		94.19 295	93.43 308	96.47 267	95.90 364	94.38 245	99.26 27	98.34 217	91.99 318	92.76 333	97.13 298	88.31 229	98.52 296	89.48 352	87.70 369	96.52 344

tpm2		94.19 295	93.76 291	95.46 317	97.23 293	89.04 372	97.31 340	96.85 372	87.08 391	96.21 217	96.79 338	83.75 326	98.74 277	92.43 294	96.23 251	98.59 226

TESTMET0.1,1		94.18 298	93.69 296	95.63 310	96.92 314	89.12 370	96.91 367	94.78 404	93.17 274	94.88 245	96.45 352	78.52 361	98.92 254	93.09 270	98.50 168	98.85 195

dp		94.15 299	93.90 278	94.90 336	97.31 289	86.82 398	96.97 362	97.19 346	91.22 345	96.02 223	96.61 348	85.51 285	99.02 239	90.00 342	94.30 268	98.85 195

ET-MVSNet_ETH3D		94.13 300	92.98 318	97.58 183	98.22 204	96.20 150	97.31 340	95.37 398	94.53 202	79.56 416	97.63 262	86.51 265	97.53 377	96.91 135	90.74 329	99.02 180

tpm		94.13 300	93.80 286	95.12 327	96.50 339	87.91 392	97.44 326	95.89 394	92.62 296	96.37 213	96.30 355	84.13 317	98.30 329	93.24 266	91.66 318	99.14 162

testing222		94.12 302	93.03 317	97.37 197	98.02 228	94.66 228	97.94 281	96.65 380	94.63 196	95.78 229	95.76 373	71.49 403	98.92 254	91.17 319	95.88 258	98.52 230

IterMVS-SCA-FT		94.11 303	93.87 281	94.85 339	97.98 233	90.56 343	97.18 350	98.11 261	93.75 239	92.58 339	97.48 271	83.97 320	97.41 380	92.48 293	91.30 321	96.58 332

Anonymous20231211		94.10 304	93.26 313	96.61 249	99.11 111	94.28 249	99.01 81	98.88 67	86.43 394	92.81 331	97.57 266	81.66 334	98.68 283	94.83 214	89.02 357	96.88 297

IterMVS		94.09 305	93.85 283	94.80 342	97.99 231	90.35 347	97.18 350	98.12 258	93.68 250	92.46 345	97.34 282	84.05 318	97.41 380	92.51 291	91.33 320	96.62 328
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test-mter		94.08 306	93.51 304	95.80 302	96.77 324	89.70 358	96.91 367	95.21 399	92.89 287	94.83 248	95.72 378	77.69 372	98.97 243	93.06 271	98.50 168	98.72 207

test0.0.03 1		94.08 306	93.51 304	95.80 302	95.53 376	92.89 301	97.38 331	95.97 390	95.11 168	92.51 343	96.66 343	87.71 245	96.94 387	87.03 374	93.67 287	97.57 267

v1240		94.06 308	93.29 312	96.34 278	96.03 360	93.90 260	98.44 217	98.17 251	91.18 347	94.13 280	97.01 319	86.05 276	98.42 307	89.13 357	89.50 348	96.70 319

X-MVStestdata		94.06 308	92.30 334	99.34 26	99.70 22	98.35 44	99.29 22	98.88 67	97.40 46	98.46 99	43.50 430	95.90 45	99.89 56	97.85 86	99.74 52	99.78 25

DTE-MVSNet		93.98 310	93.26 313	96.14 286	96.06 358	94.39 244	99.20 42	98.86 80	93.06 280	91.78 355	97.81 243	85.87 280	97.58 375	90.53 332	86.17 385	96.46 354

pm-mvs1		93.94 311	93.06 316	96.59 252	96.49 340	95.16 203	98.95 95	98.03 278	92.32 309	91.08 363	97.84 238	84.54 308	98.41 314	92.16 296	86.13 388	96.19 365

MS-PatchMatch		93.84 312	93.63 298	94.46 356	96.18 352	89.45 365	97.76 305	98.27 230	92.23 312	92.13 351	97.49 270	79.50 355	98.69 280	89.75 345	99.38 121	95.25 382

tfpnnormal		93.66 313	92.70 324	96.55 260	96.94 313	95.94 165	98.97 89	99.19 29	91.04 348	91.38 360	97.34 282	84.94 296	98.61 288	85.45 385	89.02 357	95.11 386

EU-MVSNet		93.66 313	94.14 259	92.25 384	95.96 363	83.38 408	98.52 204	98.12 258	94.69 192	92.61 338	98.13 212	87.36 254	96.39 400	91.82 307	90.00 339	96.98 283

our_test_3		93.65 315	93.30 311	94.69 344	95.45 380	89.68 360	96.91 367	97.65 299	91.97 319	91.66 358	96.88 331	89.67 190	97.93 358	88.02 368	91.49 319	96.48 352

pmmvs5		93.65 315	92.97 319	95.68 307	95.49 377	92.37 304	98.20 245	97.28 339	89.66 372	92.58 339	97.26 288	82.14 331	98.09 345	93.18 269	90.95 328	96.58 332

SSC-MVS3.2		93.59 317	93.13 315	94.97 333	96.81 323	89.71 357	97.95 278	98.49 188	94.59 199	93.50 308	96.91 329	77.74 371	98.37 321	91.69 311	90.47 332	96.83 305

test_fmvs2		93.43 318	93.58 300	92.95 378	96.97 311	83.91 404	99.19 44	97.24 342	95.74 133	95.20 240	98.27 201	69.65 405	98.72 279	96.26 165	93.73 286	96.24 362

tpm cat1		93.36 319	92.80 321	95.07 331	97.58 265	87.97 391	96.76 379	97.86 289	82.17 412	93.53 304	96.04 367	86.13 274	99.13 219	89.24 355	95.87 259	98.10 250

JIA-IIPM		93.35 320	92.49 330	95.92 296	96.48 341	90.65 340	95.01 403	96.96 362	85.93 398	96.08 221	87.33 420	87.70 247	98.78 275	91.35 316	95.58 263	98.34 240

SixPastTwentyTwo		93.34 321	92.86 320	94.75 343	95.67 370	89.41 367	98.75 154	96.67 378	93.89 231	90.15 373	98.25 204	80.87 344	98.27 334	90.90 328	90.64 330	96.57 334

USDC		93.33 322	92.71 323	95.21 324	96.83 321	90.83 336	96.91 367	97.50 317	93.84 234	90.72 366	98.14 211	77.69 372	98.82 271	89.51 351	93.21 300	95.97 370

IB-MVS	91.98 17	93.27 323	91.97 338	97.19 203	97.47 275	93.41 280	97.09 357	95.99 389	93.32 267	92.47 344	95.73 376	78.06 367	99.53 167	94.59 225	82.98 396	98.62 221
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		93.26 324	92.21 335	96.41 273	97.73 253	93.13 294	95.65 398	97.03 357	91.27 343	94.04 284	96.06 365	75.33 391	97.19 383	86.56 376	96.23 251	98.92 191

ppachtmachnet_test		93.22 325	92.63 325	94.97 333	95.45 380	90.84 335	96.88 373	97.88 288	90.60 354	92.08 352	97.26 288	88.08 236	97.86 364	85.12 388	90.33 333	96.22 363

Patchmtry		93.22 325	92.35 333	95.84 301	96.77 324	93.09 297	94.66 411	97.56 307	87.37 390	92.90 329	96.24 356	88.15 233	97.90 359	87.37 373	90.10 338	96.53 341

testing3		93.19 327	92.48 331	95.30 323	98.07 220	92.27 305	98.64 185	97.17 347	93.94 230	93.98 287	97.04 314	67.97 409	96.01 404	88.40 363	97.14 212	97.63 264

FMVSNet1		93.19 327	92.07 336	96.56 256	97.54 270	95.00 211	98.82 135	98.18 245	90.38 360	92.27 348	97.07 306	73.68 400	97.95 355	89.36 354	91.30 321	96.72 315

LF4IMVS		93.14 329	92.79 322	94.20 360	95.88 365	88.67 380	97.66 313	97.07 353	93.81 237	91.71 356	97.65 257	77.96 369	98.81 272	91.47 315	91.92 314	95.12 385

mmtdpeth		93.12 330	92.61 326	94.63 348	97.60 263	89.68 360	99.21 39	97.32 334	94.02 221	97.72 149	94.42 395	77.01 382	99.44 185	99.05 25	77.18 417	94.78 395

testgi		93.06 331	92.45 332	94.88 338	96.43 344	89.90 352	98.75 154	97.54 313	95.60 140	91.63 359	97.91 230	74.46 397	97.02 385	86.10 379	93.67 287	97.72 261

PatchT		93.06 331	91.97 338	96.35 277	96.69 330	92.67 302	94.48 414	97.08 351	86.62 392	97.08 175	92.23 414	87.94 240	97.90 359	78.89 411	96.69 227	98.49 232

RPMNet		92.81 333	91.34 344	97.24 199	97.00 308	93.43 278	94.96 404	98.80 102	82.27 411	96.93 183	92.12 415	86.98 259	99.82 85	76.32 416	96.65 229	98.46 234

UWE-MVS-28		92.79 334	92.51 329	93.62 367	96.46 342	86.28 399	97.93 282	92.71 420	94.17 214	94.78 251	97.16 296	81.05 341	96.43 399	81.45 403	96.86 220	98.14 249

myMVS_eth3d		92.73 335	92.01 337	94.89 337	97.39 285	90.94 331	97.91 285	97.46 321	93.16 275	93.42 312	95.37 385	68.09 408	96.12 402	88.34 364	96.99 216	97.60 265

TransMVSNet (Re)		92.67 336	91.51 343	96.15 285	96.58 335	94.65 229	98.90 106	96.73 374	90.86 351	89.46 379	97.86 235	85.62 283	98.09 345	86.45 377	81.12 403	95.71 375

ttmdpeth		92.61 337	91.96 340	94.55 350	94.10 398	90.60 342	98.52 204	97.29 337	92.67 294	90.18 371	97.92 229	79.75 354	97.79 366	91.09 321	86.15 387	95.26 381

Syy-MVS		92.55 338	92.61 326	92.38 381	97.39 285	83.41 407	97.91 285	97.46 321	93.16 275	93.42 312	95.37 385	84.75 301	96.12 402	77.00 415	96.99 216	97.60 265

K. test v3		92.55 338	91.91 341	94.48 354	95.64 371	89.24 368	99.07 66	94.88 403	94.04 219	86.78 395	97.59 264	77.64 375	97.64 372	92.08 298	89.43 350	96.57 334

DSMNet-mixed		92.52 340	92.58 328	92.33 382	94.15 397	82.65 410	98.30 233	94.26 410	89.08 381	92.65 337	95.73 376	85.01 295	95.76 406	86.24 378	97.76 197	98.59 226

TinyColmap		92.31 341	91.53 342	94.65 347	96.92 314	89.75 355	96.92 365	96.68 377	90.45 358	89.62 376	97.85 237	76.06 389	98.81 272	86.74 375	92.51 308	95.41 379

gg-mvs-nofinetune		92.21 342	90.58 350	97.13 208	96.75 327	95.09 207	95.85 395	89.40 428	85.43 402	94.50 257	81.98 423	80.80 346	98.40 320	92.16 296	98.33 178	97.88 254

FMVSNet5		91.81 343	90.92 346	94.49 353	97.21 295	92.09 310	98.00 274	97.55 312	89.31 379	90.86 365	95.61 382	74.48 396	95.32 410	85.57 383	89.70 342	96.07 368

pmmvs6		91.77 344	90.63 349	95.17 326	94.69 394	91.24 327	98.67 179	97.92 286	86.14 396	89.62 376	97.56 268	75.79 390	98.34 322	90.75 330	84.56 390	95.94 371

Anonymous20231206		91.66 345	91.10 345	93.33 372	94.02 402	87.35 395	98.58 194	97.26 341	90.48 356	90.16 372	96.31 354	83.83 324	96.53 397	79.36 409	89.90 340	96.12 366

Patchmatch-RL test		91.49 346	90.85 347	93.41 370	91.37 413	84.40 402	92.81 418	95.93 393	91.87 322	87.25 391	94.87 391	88.99 210	96.53 397	92.54 290	82.00 398	99.30 132

test_0402		91.32 347	90.27 353	94.48 354	96.60 334	91.12 328	98.50 210	97.22 343	86.10 397	88.30 387	96.98 321	77.65 374	97.99 353	78.13 413	92.94 302	94.34 396

test_vis1_rt		91.29 348	90.65 348	93.19 376	97.45 279	86.25 400	98.57 200	90.90 426	93.30 269	86.94 394	93.59 404	62.07 418	99.11 224	97.48 117	95.58 263	94.22 399

PVSNet_0	88.72 19	91.28 349	90.03 356	95.00 332	97.99 231	87.29 396	94.84 407	98.50 183	92.06 317	89.86 374	95.19 387	79.81 353	99.39 191	92.27 295	69.79 423	98.33 241

mvs5depth		91.23 350	90.17 354	94.41 358	92.09 410	89.79 354	95.26 402	96.50 382	90.73 352	91.69 357	97.06 310	76.12 388	98.62 287	88.02 368	84.11 393	94.82 392

Anonymous20240521		91.18 351	90.44 351	93.42 369	93.70 403	88.47 384	98.94 98	97.56 307	88.46 385	89.56 378	95.08 390	77.15 380	96.97 386	83.92 395	89.55 346	94.82 392

EG-PatchMatch MVS		91.13 352	90.12 355	94.17 362	94.73 393	89.00 373	98.13 257	97.81 291	89.22 380	85.32 405	96.46 351	67.71 410	98.42 307	87.89 371	93.82 285	95.08 387

TDRefinement		91.06 353	89.68 358	95.21 324	85.35 428	91.49 323	98.51 209	97.07 353	91.47 331	88.83 385	97.84 238	77.31 376	99.09 229	92.79 281	77.98 415	95.04 389

UnsupCasMVSNet_eth		90.99 354	89.92 357	94.19 361	94.08 399	89.83 353	97.13 356	98.67 138	93.69 248	85.83 401	96.19 361	75.15 392	96.74 391	89.14 356	79.41 410	96.00 369

test20.03		90.89 355	90.38 352	92.43 380	93.48 404	88.14 390	98.33 226	97.56 307	93.40 264	87.96 388	96.71 342	80.69 347	94.13 415	79.15 410	86.17 385	95.01 391

MDA-MVSNet_test_wron		90.71 356	89.38 361	94.68 345	94.83 390	90.78 337	97.19 349	97.46 321	87.60 388	72.41 423	95.72 378	86.51 265	96.71 394	85.92 381	86.80 382	96.56 336

YYNet1		90.70 357	89.39 360	94.62 349	94.79 392	90.65 340	97.20 347	97.46 321	87.54 389	72.54 422	95.74 374	86.51 265	96.66 395	86.00 380	86.76 383	96.54 339

KD-MVS_self_test		90.38 358	89.38 361	93.40 371	92.85 407	88.94 376	97.95 278	97.94 284	90.35 361	90.25 370	93.96 401	79.82 352	95.94 405	84.62 394	76.69 418	95.33 380

pmmvs-eth3d		90.36 359	89.05 364	94.32 359	91.10 415	92.12 309	97.63 318	96.95 363	88.86 383	84.91 406	93.13 409	78.32 363	96.74 391	88.70 360	81.81 400	94.09 402

CL-MVSNet_self_test		90.11 360	89.14 363	93.02 377	91.86 412	88.23 389	96.51 387	98.07 271	90.49 355	90.49 369	94.41 396	84.75 301	95.34 409	80.79 405	74.95 420	95.50 378

new_pmnet		90.06 361	89.00 365	93.22 375	94.18 396	88.32 387	96.42 389	96.89 368	86.19 395	85.67 402	93.62 403	77.18 379	97.10 384	81.61 402	89.29 352	94.23 398

MDA-MVSNet-bldmvs		89.97 362	88.35 368	94.83 341	95.21 384	91.34 324	97.64 315	97.51 316	88.36 386	71.17 424	96.13 363	79.22 357	96.63 396	83.65 396	86.27 384	96.52 344

CMPMVS	66.06 21	89.70 363	89.67 359	89.78 389	93.19 405	76.56 415	97.00 361	98.35 214	80.97 413	81.57 411	97.75 246	74.75 394	98.61 288	89.85 343	93.63 289	94.17 400
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet1		89.67 364	88.28 369	93.82 365	92.81 408	91.08 329	98.01 272	97.45 325	87.95 387	87.90 389	95.87 372	67.63 411	94.56 414	78.73 412	88.18 365	95.83 373

KD-MVS_2432*1600		89.61 365	87.96 373	94.54 351	94.06 400	91.59 321	95.59 399	97.63 301	89.87 368	88.95 382	94.38 398	78.28 364	96.82 389	84.83 390	68.05 424	95.21 383

miper_refine_blended		89.61 365	87.96 373	94.54 351	94.06 400	91.59 321	95.59 399	97.63 301	89.87 368	88.95 382	94.38 398	78.28 364	96.82 389	84.83 390	68.05 424	95.21 383

MVStest1		89.53 367	87.99 372	94.14 364	94.39 395	90.42 345	98.25 240	96.84 373	82.81 408	81.18 413	97.33 284	77.09 381	96.94 387	85.27 387	78.79 411	95.06 388

MVS-HIRNet		89.46 368	88.40 367	92.64 379	97.58 265	82.15 411	94.16 417	93.05 419	75.73 419	90.90 364	82.52 422	79.42 356	98.33 324	83.53 397	98.68 155	97.43 268

OpenMVS_ROB	86.42 20	89.00 369	87.43 377	93.69 366	93.08 406	89.42 366	97.91 285	96.89 368	78.58 415	85.86 400	94.69 392	69.48 406	98.29 332	77.13 414	93.29 299	93.36 409

mvsany_test3		88.80 370	88.04 370	91.09 388	89.78 418	81.57 413	97.83 300	95.49 397	93.81 237	87.53 390	93.95 402	56.14 421	97.43 379	94.68 218	83.13 395	94.26 397

new-patchmatchnet		88.50 371	87.45 376	91.67 386	90.31 417	85.89 401	97.16 354	97.33 333	89.47 375	83.63 408	92.77 411	76.38 385	95.06 412	82.70 399	77.29 416	94.06 404

APD_test1		88.22 372	88.01 371	88.86 391	95.98 361	74.66 423	97.21 346	96.44 384	83.96 407	86.66 397	97.90 231	60.95 419	97.84 365	82.73 398	90.23 336	94.09 402

PM-MVS		87.77 373	86.55 379	91.40 387	91.03 416	83.36 409	96.92 365	95.18 401	91.28 342	86.48 399	93.42 405	53.27 422	96.74 391	89.43 353	81.97 399	94.11 401

dmvs_testset		87.64 374	88.93 366	83.79 400	95.25 383	63.36 432	97.20 347	91.17 424	93.07 279	85.64 403	95.98 371	85.30 292	91.52 422	69.42 421	87.33 374	96.49 350

test_fmvs3		87.17 375	87.06 378	87.50 393	91.21 414	75.66 418	99.05 69	96.61 381	92.79 291	88.85 384	92.78 410	43.72 425	93.49 416	93.95 246	84.56 390	93.34 410

UnsupCasMVSNet_bld		87.17 375	85.12 382	93.31 373	91.94 411	88.77 377	94.92 406	98.30 227	84.30 406	82.30 409	90.04 417	63.96 416	97.25 382	85.85 382	74.47 422	93.93 406

N_pmnet		87.12 377	87.77 375	85.17 397	95.46 379	61.92 433	97.37 333	70.66 438	85.83 399	88.73 386	96.04 367	85.33 290	97.76 368	80.02 406	90.48 331	95.84 372

pmmvs3		86.67 378	84.86 383	92.11 385	88.16 422	87.19 397	96.63 383	94.75 405	79.88 414	87.22 392	92.75 412	66.56 413	95.20 411	81.24 404	76.56 419	93.96 405

test_f		86.07 379	85.39 380	88.10 392	89.28 420	75.57 419	97.73 308	96.33 386	89.41 378	85.35 404	91.56 416	43.31 427	95.53 407	91.32 317	84.23 392	93.21 411

WB-MVS		84.86 380	85.33 381	83.46 401	89.48 419	69.56 427	98.19 248	96.42 385	89.55 374	81.79 410	94.67 393	84.80 299	90.12 423	52.44 427	80.64 407	90.69 414

SSC-MVS		84.27 381	84.71 384	82.96 405	89.19 421	68.83 428	98.08 264	96.30 387	89.04 382	81.37 412	94.47 394	84.60 306	89.89 424	49.80 429	79.52 409	90.15 415

dongtai		82.47 382	81.88 385	84.22 399	95.19 385	76.03 416	94.59 413	74.14 437	82.63 409	87.19 393	96.09 364	64.10 415	87.85 427	58.91 425	84.11 393	88.78 419

test_vis3_rt		79.22 383	77.40 390	84.67 398	86.44 426	74.85 422	97.66 313	81.43 433	84.98 403	67.12 426	81.91 424	28.09 435	97.60 373	88.96 358	80.04 408	81.55 424

test_method		79.03 384	78.17 386	81.63 406	86.06 427	54.40 438	82.75 426	96.89 368	39.54 430	80.98 414	95.57 383	58.37 420	94.73 413	84.74 393	78.61 412	95.75 374

testf1		79.02 385	77.70 387	82.99 403	88.10 423	66.90 429	94.67 409	93.11 416	71.08 421	74.02 419	93.41 406	34.15 431	93.25 417	72.25 419	78.50 413	88.82 417

APD_test2		79.02 385	77.70 387	82.99 403	88.10 423	66.90 429	94.67 409	93.11 416	71.08 421	74.02 419	93.41 406	34.15 431	93.25 417	72.25 419	78.50 413	88.82 417

LCM-MVSNet		78.70 387	76.24 393	86.08 395	77.26 434	71.99 425	94.34 415	96.72 375	61.62 425	76.53 417	89.33 418	33.91 433	92.78 420	81.85 401	74.60 421	93.46 408

kuosan		78.45 388	77.69 389	80.72 407	92.73 409	75.32 420	94.63 412	74.51 436	75.96 417	80.87 415	93.19 408	63.23 417	79.99 431	42.56 431	81.56 402	86.85 423

Gipuma		78.40 389	76.75 392	83.38 402	95.54 374	80.43 414	79.42 427	97.40 329	64.67 424	73.46 421	80.82 425	45.65 424	93.14 419	66.32 423	87.43 372	76.56 427
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		77.95 390	75.44 394	85.46 396	82.54 429	74.95 421	94.23 416	93.08 418	72.80 420	74.68 418	87.38 419	36.36 430	91.56 421	73.95 417	63.94 426	89.87 416

FPMVS		77.62 391	77.14 391	79.05 409	79.25 432	60.97 434	95.79 396	95.94 392	65.96 423	67.93 425	94.40 397	37.73 429	88.88 426	68.83 422	88.46 362	87.29 420

EGC-MVSNET		75.22 392	69.54 395	92.28 383	94.81 391	89.58 362	97.64 315	96.50 382	1.82 435	5.57 436	95.74 374	68.21 407	96.26 401	73.80 418	91.71 316	90.99 413

ANet_high		69.08 393	65.37 397	80.22 408	65.99 436	71.96 426	90.91 422	90.09 427	82.62 410	49.93 431	78.39 426	29.36 434	81.75 428	62.49 424	38.52 430	86.95 422

tmp_tt		68.90 394	66.97 396	74.68 411	50.78 438	59.95 435	87.13 423	83.47 432	38.80 431	62.21 427	96.23 358	64.70 414	76.91 433	88.91 359	30.49 431	87.19 421

PMVS	61.03 23	65.95 395	63.57 399	73.09 412	57.90 437	51.22 439	85.05 425	93.93 414	54.45 426	44.32 432	83.57 421	13.22 436	89.15 425	58.68 426	81.00 404	78.91 426
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		64.94 396	64.25 398	67.02 413	82.28 430	59.36 436	91.83 421	85.63 430	52.69 427	60.22 428	77.28 427	41.06 428	80.12 430	46.15 430	41.14 428	61.57 429

EMVS		64.07 397	63.26 400	66.53 414	81.73 431	58.81 437	91.85 420	84.75 431	51.93 429	59.09 429	75.13 428	43.32 426	79.09 432	42.03 432	39.47 429	61.69 428

MVE	62.14 22	63.28 398	59.38 401	74.99 410	74.33 435	65.47 431	85.55 424	80.50 434	52.02 428	51.10 430	75.00 429	10.91 439	80.50 429	51.60 428	53.40 427	78.99 425
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		30.17 399	30.18 403	30.16 415	78.61 433	43.29 440	66.79 428	14.21 439	17.31 432	14.82 435	11.93 435	11.55 438	41.43 434	37.08 433	19.30 432	5.76 432

cdsmvs_eth3d_5k		23.98 400	31.98 402	0.00 418	0.00 441	0.00 443	0.00 429	98.59 156	0.00 436	0.00 437	98.61 161	90.60 173	0.00 437	0.00 436	0.00 435	0.00 433

testmvs		21.48 401	24.95 404	11.09 417	14.89 439	6.47 442	96.56 385	9.87 440	7.55 433	17.93 433	39.02 431	9.43 440	5.90 436	16.56 435	12.72 433	20.91 431

test123		20.95 402	23.72 405	12.64 416	13.54 440	8.19 441	96.55 386	6.13 441	7.48 434	16.74 434	37.98 432	12.97 437	6.05 435	16.69 434	5.43 434	23.68 430

ab-mvs-re		8.20 403	10.94 406	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	98.43 179	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

pcd_1.5k_mvsjas		7.88 404	10.50 407	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	94.51 87	0.00 437	0.00 436	0.00 435	0.00 433

mmdepth		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

monomultidepth		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

test_blank		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uanet_test		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

DCPMVS		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

sosnet-low-res		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

sosnet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uncertanet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

Regformer		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uanet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

WAC-MVS						90.94 331								88.66 361

FOURS1					99.82 1	98.66 24	99.69 1	98.95 51	97.46 44	99.39 36

MSC_two_6792asdad				99.62 6	99.17 100	99.08 11		98.63 149					99.94 11	98.53 44	99.80 24	99.86 8

PC_three_1452									95.08 172	99.60 25	99.16 86	97.86 2	98.47 301	97.52 115	99.72 59	99.74 41

No_MVS				99.62 6	99.17 100	99.08 11		98.63 149					99.94 11	98.53 44	99.80 24	99.86 8

test_one_0601					99.66 26	99.25 2		98.86 80	97.55 37	99.20 48	99.47 29	97.57 6

eth-test2					0.00 441

eth-test					0.00 441

ZD-MVS					99.46 52	98.70 23		98.79 107	93.21 272	98.67 86	98.97 116	95.70 49	99.83 78	96.07 169	99.58 88

RE-MVS-def			98.34 43		99.49 46	97.86 69	99.11 60	98.80 102	96.49 100	99.17 51	99.35 52	95.29 65		97.72 94	99.65 72	99.71 54

IU-MVS					99.71 19	99.23 7		98.64 146	95.28 159	99.63 24				98.35 61	99.81 15	99.83 13

OPU-MVS				99.37 22	99.24 92	99.05 14	99.02 79				99.16 86	97.81 3	99.37 192	97.24 124	99.73 55	99.70 58

test_241102_TWO								98.87 74	97.65 30	99.53 29	99.48 27	97.34 11	99.94 11	98.43 56	99.80 24	99.83 13

test_241102_ONE					99.71 19	99.24 5		98.87 74	97.62 32	99.73 16	99.39 40	97.53 7	99.74 120

9.14			98.06 68		99.47 50		98.71 167	98.82 89	94.36 210	99.16 54	99.29 61	96.05 37	99.81 90	97.00 130	99.71 61

save fliter					99.46 52	98.38 35	98.21 243	98.71 125	97.95 21

test_0728_THIRD									97.32 52	99.45 31	99.46 33	97.88 1	99.94 11	98.47 52	99.86 2	99.85 10

test_0728_SECOND				99.71 1	99.72 12	99.35 1	98.97 89	98.88 67					99.94 11	98.47 52	99.81 15	99.84 12

test0726					99.72 12	99.25 2	99.06 67	98.88 67	97.62 32	99.56 26	99.50 23	97.42 9

GSMVS																99.20 149

test_part2					99.63 29	99.18 10				99.27 45

sam_mvs1												89.45 196				99.20 149

sam_mvs												88.99 210

ambc				89.49 390	86.66 425	75.78 417	92.66 419	96.72 375		86.55 398	92.50 413	46.01 423	97.90 359	90.32 334	82.09 397	94.80 394

MTGPA								98.74 117

test_post1							96.68 382				30.43 434	87.85 244	98.69 280	92.59 286

test_post											31.83 433	88.83 217	98.91 256

patchmatchnet-post											95.10 389	89.42 197	98.89 260

GG-mvs-BLEND				96.59 252	96.34 347	94.98 214	96.51 387	88.58 429		93.10 326	94.34 400	80.34 351	98.05 348	89.53 350	96.99 216	96.74 312

MTMP							98.89 110	94.14 412

gm-plane-assit					95.88 365	87.47 394			89.74 371		96.94 327		99.19 211	93.32 265

test9_res														96.39 163	99.57 89	99.69 61

TEST9					99.31 68	98.50 29	97.92 283	98.73 120	92.63 295	97.74 146	98.68 156	96.20 32	99.80 97

test_8					99.29 77	98.44 31	97.89 291	98.72 122	92.98 283	97.70 151	98.66 159	96.20 32	99.80 97

agg_prior2														95.87 179	99.57 89	99.68 66

agg_prior					99.30 72	98.38 35		98.72 122		97.57 163			99.81 90

TestCases				96.99 217	99.25 85	93.21 292		98.18 245	91.36 335	93.52 305	98.77 145	84.67 304	99.72 122	89.70 347	97.87 192	98.02 252

test_prior4						98.01 65	97.86 295

test_prior2							97.80 302		96.12 118	97.89 139	98.69 155	95.96 41		96.89 139	99.60 83

test_prior				99.19 44	99.31 68	98.22 52		98.84 84					99.70 128			99.65 74

旧先验2							97.57 321		91.30 340	98.67 86			99.80 97	95.70 188

新几何2							97.64 315

新几何1				99.16 49	99.34 61	98.01 65		98.69 130	90.06 365	98.13 115	98.95 123	94.60 85	99.89 56	91.97 305	99.47 109	99.59 84

旧先验1					99.29 77	97.48 83		98.70 129			99.09 102	95.56 52			99.47 109	99.61 80

无先验							97.58 320	98.72 122	91.38 334				99.87 67	93.36 264		99.60 82

原ACMM2							97.67 312

原ACMM1				98.65 87	99.32 66	96.62 126		98.67 138	93.27 271	97.81 141	98.97 116	95.18 72	99.83 78	93.84 250	99.46 112	99.50 96

test222					99.23 93	97.17 104	97.40 329	98.66 141	88.68 384	98.05 121	98.96 121	94.14 98			99.53 100	99.61 80

testdata2													99.89 56	91.65 313

segment_acmp												96.85 14

testdata				98.26 124	99.20 98	95.36 192		98.68 133	91.89 321	98.60 94	99.10 95	94.44 92	99.82 85	94.27 236	99.44 113	99.58 88

testdata1							97.32 339		96.34 108

test12				99.18 46	99.16 104	98.19 54		98.53 172		98.07 119		95.13 75	99.72 122		99.56 95	99.63 78

plane_prior7					97.42 281	94.63 231

plane_prior6					97.35 288	94.61 234						87.09 256

plane_prior5								98.56 166					99.03 236	96.07 169	94.27 269	96.92 288

plane_prior4											98.28 198

plane_prior3						94.61 234			97.02 74	95.34 235

plane_prior2							98.80 144		97.28 55

plane_prior1					97.37 287

plane_prior						94.60 236	98.44 217		96.74 88						94.22 271

n2								0.00 442

nn								0.00 442

door-mid								94.37 408

lessismore_v0				94.45 357	94.93 389	88.44 385		91.03 425		86.77 396	97.64 260	76.23 387	98.42 307	90.31 335	85.64 389	96.51 347

LGP-MVS_train				96.47 267	97.46 276	93.54 273		98.54 170	94.67 194	94.36 267	98.77 145	85.39 286	99.11 224	95.71 186	94.15 275	96.76 310

test11								98.66 141

door								94.64 406

HQP5-MVS						94.25 252

HQP-NCC					97.20 296		98.05 267		96.43 102	94.45 259

ACMP_Plane					97.20 296		98.05 267		96.43 102	94.45 259

BP-MVS														95.30 199

HQP4-MVS										94.45 259			98.96 247			96.87 300

HQP3-MVS								98.46 191							94.18 273

HQP2-MVS												86.75 262

NP-MVS					97.28 290	94.51 239					97.73 247

MDTV_nov1_ep13_2view						84.26 403	96.89 372		90.97 349	97.90 138		89.89 185		93.91 248		99.18 158

MDTV_nov1_ep13			95.40 186		97.48 274	88.34 386	96.85 375	97.29 337	93.74 241	97.48 165	97.26 288	89.18 204	99.05 232	91.92 306	97.43 207

ACMMP++_ref															92.97 301

ACMMP++															93.61 290

Test By Simon												94.64 84

ITE_SJBPF				95.44 318	97.42 281	91.32 325		97.50 317	95.09 171	93.59 301	98.35 189	81.70 333	98.88 262	89.71 346	93.39 296	96.12 366

DeepMVS_CX				86.78 394	97.09 306	72.30 424		95.17 402	75.92 418	84.34 407	95.19 387	70.58 404	95.35 408	79.98 408	89.04 356	92.68 412

High-resolution multi-view benchmark