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.

DVP-MVS++		98.06 1	97.99 1	98.28 9	98.67 61	95.39 11	99.29 1	98.28 41	94.78 49	98.93 14	98.87 24	96.04 2	99.86 9	97.45 38	99.58 23	99.59 25

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 35	98.27 44	95.13 31	99.19 7	98.89 21	95.54 5	99.85 18	97.52 34	99.66 10	99.56 32

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 42	97.85 125	94.92 40	98.73 24	98.87 24	95.08 8	99.84 23	97.52 34	99.67 6	99.48 48
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
DPE-MVS		97.86 4	97.65 8	98.47 5	99.17 32	95.78 7	97.21 173	98.35 32	95.16 30	98.71 26	98.80 31	95.05 10	99.89 3	96.70 55	99.73 1	99.73 10
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		97.82 5	97.73 7	98.08 18	99.15 33	94.82 28	98.81 7	98.30 37	94.76 51	98.30 32	98.90 19	93.77 17	99.68 63	97.93 22	99.69 3	99.75 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CNVR-MVS		97.68 6	97.44 17	98.37 7	98.90 53	95.86 6	97.27 165	98.08 82	95.81 13	97.87 46	98.31 69	94.26 13	99.68 63	97.02 46	99.49 38	99.57 29

fmvsm_l_conf0.5_n		97.65 7	97.75 6	97.34 56	98.21 95	92.75 84	97.83 89	98.73 9	95.04 36	99.30 3	98.84 29	93.34 22	99.78 40	99.32 3	99.13 85	99.50 44

fmvsm_l_conf0.5_n_3		97.64 8	97.60 9	97.79 30	98.14 102	93.94 52	97.93 75	98.65 18	96.70 3	99.38 1	99.07 7	89.92 86	99.81 30	99.16 9	99.43 48	99.61 23

fmvsm_l_conf0.5_n_a		97.63 9	97.76 5	97.26 63	98.25 89	92.59 90	97.81 93	98.68 13	94.93 38	99.24 6	98.87 24	93.52 20	99.79 37	99.32 3	99.21 75	99.40 58

SteuartSystems-ACMMP		97.62 10	97.53 12	97.87 24	98.39 80	94.25 40	98.43 22	98.27 44	95.34 25	98.11 35	98.56 39	94.53 12	99.71 55	96.57 59	99.62 17	99.65 17
Skip Steuart: Steuart Systems R&D Blog.
MSP-MVS		97.59 11	97.54 11	97.73 38	99.40 11	93.77 57	98.53 14	98.29 39	95.55 20	98.56 28	97.81 110	93.90 15	99.65 67	96.62 56	99.21 75	99.77 2
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
test_fmvsm_n_1920		97.55 12	97.89 3	96.53 90	98.41 77	91.73 118	98.01 60	99.02 1	96.37 8	99.30 3	98.92 17	92.39 41	99.79 37	99.16 9	99.46 41	98.08 183

reproduce-ours		97.53 13	97.51 14	97.60 47	98.97 47	93.31 69	97.71 106	98.20 58	95.80 14	97.88 43	98.98 13	92.91 27	99.81 30	97.68 26	99.43 48	99.67 13

our_new_method		97.53 13	97.51 14	97.60 47	98.97 47	93.31 69	97.71 106	98.20 58	95.80 14	97.88 43	98.98 13	92.91 27	99.81 30	97.68 26	99.43 48	99.67 13

reproduce_model		97.51 15	97.51 14	97.50 50	98.99 46	93.01 78	97.79 95	98.21 56	95.73 17	97.99 39	99.03 10	92.63 36	99.82 28	97.80 24	99.42 51	99.67 13

test_fmvsmconf_n		97.49 16	97.56 10	97.29 59	97.44 153	92.37 97	97.91 77	98.88 4	95.83 12	98.92 17	99.05 9	91.45 57	99.80 34	99.12 11	99.46 41	99.69 12

TSAR-MVS + MP.		97.42 17	97.33 20	97.69 42	99.25 27	94.24 41	98.07 55	97.85 125	93.72 88	98.57 27	98.35 60	93.69 18	99.40 119	97.06 45	99.46 41	99.44 53
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SD-MVS		97.41 18	97.53 12	97.06 75	98.57 72	94.46 34	97.92 76	98.14 72	94.82 46	99.01 11	98.55 41	94.18 14	97.41 346	96.94 47	99.64 14	99.32 66
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
SF-MVS		97.39 19	97.13 21	98.17 15	99.02 42	95.28 19	98.23 39	98.27 44	92.37 142	98.27 33	98.65 37	93.33 23	99.72 54	96.49 61	99.52 30	99.51 41

SMA-MVS		97.35 20	97.03 30	98.30 8	99.06 38	95.42 10	97.94 73	98.18 65	90.57 210	98.85 21	98.94 16	93.33 23	99.83 26	96.72 54	99.68 4	99.63 19
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
HPM-MVS++		97.34 21	96.97 33	98.47 5	99.08 36	96.16 4	97.55 132	97.97 109	95.59 18	96.61 85	97.89 99	92.57 38	99.84 23	95.95 83	99.51 33	99.40 58

NCCC		97.30 22	97.03 30	98.11 17	98.77 56	95.06 25	97.34 158	98.04 97	95.96 10	97.09 67	97.88 101	93.18 25	99.71 55	95.84 88	99.17 80	99.56 32

MM		97.29 23	96.98 32	98.23 11	98.01 112	95.03 26	98.07 55	95.76 301	97.78 1	97.52 50	98.80 31	88.09 110	99.86 9	99.44 1	99.37 62	99.80 1

ACMMP_NAP		97.20 24	96.86 39	98.23 11	99.09 34	95.16 22	97.60 124	98.19 63	92.82 133	97.93 42	98.74 34	91.60 55	99.86 9	96.26 64	99.52 30	99.67 13

XVS		97.18 25	96.96 35	97.81 28	99.38 14	94.03 50	98.59 12	98.20 58	94.85 42	96.59 87	98.29 72	91.70 52	99.80 34	95.66 92	99.40 56	99.62 20

MCST-MVS		97.18 25	96.84 41	98.20 14	99.30 24	95.35 15	97.12 180	98.07 87	93.54 97	96.08 109	97.69 117	93.86 16	99.71 55	96.50 60	99.39 58	99.55 35

fmvsm_s_conf0.5_n_3		97.15 27	97.36 19	96.52 91	97.98 115	91.19 146	97.84 86	98.65 18	97.08 2	99.25 5	99.10 3	87.88 116	99.79 37	99.32 3	99.18 79	98.59 137

HFP-MVS		97.14 28	96.92 37	97.83 26	99.42 7	94.12 46	98.52 15	98.32 35	93.21 110	97.18 61	98.29 72	92.08 46	99.83 26	95.63 97	99.59 19	99.54 37

test_fmvsmconf0.1_n		97.09 29	97.06 25	97.19 68	95.67 261	92.21 104	97.95 72	98.27 44	95.78 16	98.40 31	99.00 11	89.99 84	99.78 40	99.06 12	99.41 54	99.59 25

MTAPA		97.08 30	96.78 48	97.97 23	99.37 16	94.42 36	97.24 167	98.08 82	95.07 35	96.11 107	98.59 38	90.88 74	99.90 2	96.18 76	99.50 35	99.58 28

region2R		97.07 31	96.84 41	97.77 34	99.46 2	93.79 55	98.52 15	98.24 52	93.19 113	97.14 64	98.34 63	91.59 56	99.87 7	95.46 103	99.59 19	99.64 18

ACMMPR		97.07 31	96.84 41	97.79 30	99.44 6	93.88 53	98.52 15	98.31 36	93.21 110	97.15 63	98.33 66	91.35 61	99.86 9	95.63 97	99.59 19	99.62 20

CP-MVS		97.02 33	96.81 46	97.64 45	99.33 21	93.54 60	98.80 8	98.28 41	92.99 122	96.45 95	98.30 71	91.90 49	99.85 18	95.61 99	99.68 4	99.54 37

SR-MVS		97.01 34	96.86 39	97.47 52	99.09 34	93.27 71	97.98 63	98.07 87	93.75 87	97.45 52	98.48 49	91.43 59	99.59 83	96.22 67	99.27 68	99.54 37

fmvsm_s_conf0.5_n_5		97.00 35	96.97 33	97.09 72	97.58 149	92.56 91	97.68 110	98.47 26	94.02 78	98.90 19	98.89 21	88.94 96	99.78 40	99.18 7	99.03 94	98.93 105

ZNCC-MVS		96.96 36	96.67 53	97.85 25	99.37 16	94.12 46	98.49 19	98.18 65	92.64 138	96.39 97	98.18 79	91.61 54	99.88 4	95.59 102	99.55 26	99.57 29

APD-MVS		96.95 37	96.60 55	98.01 20	99.03 41	94.93 27	97.72 104	98.10 80	91.50 168	98.01 38	98.32 68	92.33 42	99.58 86	94.85 115	99.51 33	99.53 40
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MSLP-MVS++		96.94 38	97.06 25	96.59 87	98.72 58	91.86 116	97.67 111	98.49 23	94.66 56	97.24 60	98.41 55	92.31 44	98.94 178	96.61 57	99.46 41	98.96 99

DeepC-MVS_fast	93.89 2	96.93 39	96.64 54	97.78 32	98.64 67	94.30 37	97.41 148	98.04 97	94.81 47	96.59 87	98.37 58	91.24 64	99.64 75	95.16 108	99.52 30	99.42 57
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SPE-MVS-test		96.89 40	97.04 29	96.45 102	98.29 85	91.66 124	99.03 4	97.85 125	95.84 11	96.90 71	97.97 95	91.24 64	98.75 199	96.92 48	99.33 64	98.94 102

SR-MVS-dyc-post		96.88 41	96.80 47	97.11 71	99.02 42	92.34 98	97.98 63	98.03 99	93.52 100	97.43 55	98.51 44	91.40 60	99.56 94	96.05 78	99.26 70	99.43 55

CS-MVS		96.86 42	97.06 25	96.26 118	98.16 101	91.16 151	99.09 3	97.87 120	95.30 26	97.06 68	98.03 89	91.72 50	98.71 206	97.10 44	99.17 80	98.90 110

mPP-MVS		96.86 42	96.60 55	97.64 45	99.40 11	93.44 62	98.50 18	98.09 81	93.27 109	95.95 115	98.33 66	91.04 69	99.88 4	95.20 106	99.57 25	99.60 24

fmvsm_s_conf0.5_n		96.85 44	97.13 21	96.04 131	98.07 109	90.28 180	97.97 69	98.76 8	94.93 38	98.84 22	99.06 8	88.80 99	99.65 67	99.06 12	98.63 110	98.18 171

GST-MVS		96.85 44	96.52 59	97.82 27	99.36 18	94.14 45	98.29 29	98.13 73	92.72 135	96.70 79	98.06 86	91.35 61	99.86 9	94.83 117	99.28 67	99.47 50

balanced_conf03		96.84 46	96.89 38	96.68 81	97.63 141	92.22 103	98.17 48	97.82 131	94.44 66	98.23 34	97.36 142	90.97 71	99.22 136	97.74 25	99.66 10	98.61 134

patch_mono-2		96.83 47	97.44 17	95.01 187	99.05 39	85.39 314	96.98 192	98.77 7	94.70 53	97.99 39	98.66 35	93.61 19	99.91 1	97.67 30	99.50 35	99.72 11

APD-MVS_3200maxsize		96.81 48	96.71 52	97.12 70	99.01 45	92.31 100	97.98 63	98.06 90	93.11 119	97.44 53	98.55 41	90.93 72	99.55 96	96.06 77	99.25 72	99.51 41

PGM-MVS		96.81 48	96.53 58	97.65 43	99.35 20	93.53 61	97.65 115	98.98 2	92.22 145	97.14 64	98.44 52	91.17 67	99.85 18	94.35 130	99.46 41	99.57 29

MP-MVS		96.77 50	96.45 66	97.72 39	99.39 13	93.80 54	98.41 23	98.06 90	93.37 105	95.54 130	98.34 63	90.59 78	99.88 4	94.83 117	99.54 28	99.49 46
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PHI-MVS		96.77 50	96.46 65	97.71 41	98.40 78	94.07 48	98.21 42	98.45 27	89.86 227	97.11 66	98.01 92	92.52 39	99.69 61	96.03 81	99.53 29	99.36 64

fmvsm_s_conf0.5_n_4		96.75 52	97.07 24	95.79 146	97.76 130	89.57 201	97.66 114	98.66 16	95.36 23	99.03 10	98.90 19	88.39 106	99.73 50	99.17 8	98.66 108	98.08 183

fmvsm_s_conf0.5_n_a		96.75 52	96.93 36	96.20 123	97.64 139	90.72 166	98.00 61	98.73 9	94.55 60	98.91 18	99.08 4	88.22 109	99.63 76	98.91 15	98.37 123	98.25 166

MVS_0304		96.74 54	96.31 70	98.02 19	96.87 182	94.65 30	97.58 125	94.39 363	96.47 7	97.16 62	98.39 56	87.53 125	99.87 7	98.97 14	99.41 54	99.55 35

test_fmvsmvis_n_1920		96.70 55	96.84 41	96.31 112	96.62 202	91.73 118	97.98 63	98.30 37	96.19 9	96.10 108	98.95 15	89.42 89	99.76 44	98.90 16	99.08 89	97.43 221

MP-MVS-pluss		96.70 55	96.27 72	97.98 22	99.23 30	94.71 29	96.96 194	98.06 90	90.67 201	95.55 128	98.78 33	91.07 68	99.86 9	96.58 58	99.55 26	99.38 62
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
TSAR-MVS + GP.		96.69 57	96.49 60	97.27 62	98.31 84	93.39 63	96.79 207	96.72 252	94.17 74	97.44 53	97.66 121	92.76 31	99.33 124	96.86 50	97.76 146	99.08 88

HPM-MVS		96.69 57	96.45 66	97.40 54	99.36 18	93.11 76	98.87 6	98.06 90	91.17 184	96.40 96	97.99 93	90.99 70	99.58 86	95.61 99	99.61 18	99.49 46
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MVS_111021_HR		96.68 59	96.58 57	96.99 77	98.46 73	92.31 100	96.20 261	98.90 3	94.30 73	95.86 117	97.74 115	92.33 42	99.38 122	96.04 80	99.42 51	99.28 69

fmvsm_s_conf0.5_n_2		96.62 60	96.82 45	96.02 133	97.98 115	90.43 176	97.50 136	98.59 20	96.59 5	99.31 2	99.08 4	84.47 168	99.75 47	99.37 2	98.45 120	97.88 194

DELS-MVS		96.61 61	96.38 69	97.30 58	97.79 128	93.19 74	95.96 272	98.18 65	95.23 27	95.87 116	97.65 122	91.45 57	99.70 60	95.87 84	99.44 47	99.00 97
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
DeepPCF-MVS	93.97 1	96.61 61	97.09 23	95.15 179	98.09 105	86.63 290	96.00 270	98.15 70	95.43 21	97.95 41	98.56 39	93.40 21	99.36 123	96.77 51	99.48 39	99.45 51

fmvsm_s_conf0.1_n		96.58 63	96.77 49	96.01 136	96.67 200	90.25 181	97.91 77	98.38 28	94.48 64	98.84 22	99.14 1	88.06 111	99.62 77	98.82 17	98.60 112	98.15 175

MVSMamba_PlusPlus		96.51 64	96.48 61	96.59 87	98.07 109	91.97 113	98.14 49	97.79 133	90.43 214	97.34 58	97.52 135	91.29 63	99.19 139	98.12 21	99.64 14	98.60 135

EI-MVSNet-Vis-set		96.51 64	96.47 62	96.63 84	98.24 90	91.20 145	96.89 198	97.73 139	94.74 52	96.49 91	98.49 46	90.88 74	99.58 86	96.44 62	98.32 125	99.13 81

HPM-MVS_fast		96.51 64	96.27 72	97.22 65	99.32 22	92.74 85	98.74 9	98.06 90	90.57 210	96.77 76	98.35 60	90.21 81	99.53 100	94.80 120	99.63 16	99.38 62

EC-MVSNet		96.42 67	96.47 62	96.26 118	97.01 176	91.52 130	98.89 5	97.75 136	94.42 67	96.64 84	97.68 118	89.32 90	98.60 216	97.45 38	99.11 88	98.67 132

fmvsm_s_conf0.1_n_a		96.40 68	96.47 62	96.16 125	95.48 269	90.69 167	97.91 77	98.33 34	94.07 76	98.93 14	99.14 1	87.44 129	99.61 78	98.63 19	98.32 125	98.18 171

CANet		96.39 69	96.02 76	97.50 50	97.62 142	93.38 64	97.02 186	97.96 110	95.42 22	94.86 141	97.81 110	87.38 131	99.82 28	96.88 49	99.20 77	99.29 67

dcpmvs_2		96.37 70	97.05 28	94.31 229	98.96 49	84.11 335	97.56 128	97.51 168	93.92 82	97.43 55	98.52 43	92.75 32	99.32 126	97.32 43	99.50 35	99.51 41

EI-MVSNet-UG-set		96.34 71	96.30 71	96.47 99	98.20 96	90.93 158	96.86 200	97.72 141	94.67 55	96.16 106	98.46 50	90.43 79	99.58 86	96.23 66	97.96 139	98.90 110

fmvsm_s_conf0.1_n_2		96.33 72	96.44 68	96.00 137	97.30 156	90.37 179	97.53 133	97.92 115	96.52 6	99.14 9	99.08 4	83.21 190	99.74 48	99.22 6	98.06 136	97.88 194

train_agg		96.30 73	95.83 81	97.72 39	98.70 59	94.19 42	96.41 240	98.02 102	88.58 272	96.03 110	97.56 132	92.73 34	99.59 83	95.04 110	99.37 62	99.39 60

ACMMP		96.27 74	95.93 77	97.28 61	99.24 28	92.62 88	98.25 35	98.81 5	92.99 122	94.56 148	98.39 56	88.96 95	99.85 18	94.57 128	97.63 147	99.36 64
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
MVS_111021_LR		96.24 75	96.19 74	96.39 107	98.23 94	91.35 138	96.24 259	98.79 6	93.99 80	95.80 119	97.65 122	89.92 86	99.24 134	95.87 84	99.20 77	98.58 138

test_fmvsmconf0.01_n		96.15 76	95.85 80	97.03 76	92.66 379	91.83 117	97.97 69	97.84 129	95.57 19	97.53 49	99.00 11	84.20 174	99.76 44	98.82 17	99.08 89	99.48 48

DeepC-MVS	93.07 3	96.06 77	95.66 82	97.29 59	97.96 117	93.17 75	97.30 163	98.06 90	93.92 82	93.38 177	98.66 35	86.83 137	99.73 50	95.60 101	99.22 74	98.96 99
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CSCG		96.05 78	95.91 78	96.46 101	99.24 28	90.47 173	98.30 28	98.57 22	89.01 255	93.97 164	97.57 130	92.62 37	99.76 44	94.66 123	99.27 68	99.15 79

sasdasda		96.02 79	95.45 88	97.75 36	97.59 145	95.15 23	98.28 30	97.60 155	94.52 62	96.27 101	96.12 212	87.65 120	99.18 142	96.20 72	94.82 212	98.91 107

ETV-MVS		96.02 79	95.89 79	96.40 105	97.16 162	92.44 95	97.47 143	97.77 135	94.55 60	96.48 92	94.51 293	91.23 66	98.92 180	95.65 95	98.19 130	97.82 202

canonicalmvs		96.02 79	95.45 88	97.75 36	97.59 145	95.15 23	98.28 30	97.60 155	94.52 62	96.27 101	96.12 212	87.65 120	99.18 142	96.20 72	94.82 212	98.91 107

CDPH-MVS		95.97 82	95.38 93	97.77 34	98.93 50	94.44 35	96.35 248	97.88 118	86.98 318	96.65 83	97.89 99	91.99 48	99.47 111	92.26 166	99.46 41	99.39 60

UA-Net		95.95 83	95.53 84	97.20 67	97.67 135	92.98 80	97.65 115	98.13 73	94.81 47	96.61 85	98.35 60	88.87 97	99.51 105	90.36 208	97.35 157	99.11 85

MGCFI-Net		95.94 84	95.40 92	97.56 49	97.59 145	94.62 31	98.21 42	97.57 160	94.41 68	96.17 105	96.16 210	87.54 124	99.17 144	96.19 74	94.73 217	98.91 107

BP-MVS1		95.89 85	95.49 85	97.08 74	96.67 200	93.20 73	98.08 53	96.32 276	94.56 59	96.32 98	97.84 107	84.07 177	99.15 148	96.75 52	98.78 103	98.90 110

VNet		95.89 85	95.45 88	97.21 66	98.07 109	92.94 81	97.50 136	98.15 70	93.87 84	97.52 50	97.61 128	85.29 157	99.53 100	95.81 89	95.27 203	99.16 77

alignmvs		95.87 87	95.23 97	97.78 32	97.56 151	95.19 21	97.86 82	97.17 210	94.39 70	96.47 93	96.40 198	85.89 150	99.20 138	96.21 71	95.11 208	98.95 101

casdiffmvs_mvg		95.81 88	95.57 83	96.51 95	96.87 182	91.49 131	97.50 136	97.56 164	93.99 80	95.13 137	97.92 98	87.89 115	98.78 194	95.97 82	97.33 158	99.26 71
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DPM-MVS		95.69 89	94.92 104	98.01 20	98.08 108	95.71 9	95.27 311	97.62 154	90.43 214	95.55 128	97.07 158	91.72 50	99.50 108	89.62 224	98.94 98	98.82 122

DP-MVS Recon		95.68 90	95.12 102	97.37 55	99.19 31	94.19 42	97.03 184	98.08 82	88.35 281	95.09 138	97.65 122	89.97 85	99.48 110	92.08 175	98.59 113	98.44 155

casdiffmvs		95.64 91	95.49 85	96.08 127	96.76 198	90.45 174	97.29 164	97.44 186	94.00 79	95.46 132	97.98 94	87.52 127	98.73 202	95.64 96	97.33 158	99.08 88
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GDP-MVS		95.62 92	95.13 100	97.09 72	96.79 192	93.26 72	97.89 80	97.83 130	93.58 92	96.80 73	97.82 109	83.06 197	99.16 146	94.40 129	97.95 140	98.87 116

MG-MVS		95.61 93	95.38 93	96.31 112	98.42 76	90.53 171	96.04 267	97.48 172	93.47 102	95.67 125	98.10 82	89.17 92	99.25 133	91.27 193	98.77 104	99.13 81

baseline		95.58 94	95.42 91	96.08 127	96.78 193	90.41 177	97.16 177	97.45 182	93.69 91	95.65 126	97.85 105	87.29 132	98.68 208	95.66 92	97.25 163	99.13 81

CPTT-MVS		95.57 95	95.19 98	96.70 80	99.27 26	91.48 132	98.33 26	98.11 78	87.79 299	95.17 136	98.03 89	87.09 135	99.61 78	93.51 145	99.42 51	99.02 91

EIA-MVS		95.53 96	95.47 87	95.71 154	97.06 170	89.63 197	97.82 91	97.87 120	93.57 93	93.92 165	95.04 266	90.61 77	98.95 176	94.62 125	98.68 107	98.54 140

3Dnovator+	91.43 4	95.40 97	94.48 120	98.16 16	96.90 181	95.34 16	98.48 20	97.87 120	94.65 57	88.53 306	98.02 91	83.69 181	99.71 55	93.18 153	98.96 97	99.44 53

PS-MVSNAJ		95.37 98	95.33 95	95.49 167	97.35 155	90.66 169	95.31 308	97.48 172	93.85 85	96.51 90	95.70 237	88.65 102	99.65 67	94.80 120	98.27 127	96.17 259

MVSFormer		95.37 98	95.16 99	95.99 138	96.34 230	91.21 143	98.22 40	97.57 160	91.42 172	96.22 103	97.32 143	86.20 147	97.92 297	94.07 133	99.05 91	98.85 118

xiu_mvs_v2_base		95.32 100	95.29 96	95.40 172	97.22 158	90.50 172	95.44 301	97.44 186	93.70 90	96.46 94	96.18 207	88.59 105	99.53 100	94.79 122	97.81 143	96.17 259

PVSNet_Blended_VisFu		95.27 101	94.91 105	96.38 108	98.20 96	90.86 160	97.27 165	98.25 50	90.21 218	94.18 158	97.27 147	87.48 128	99.73 50	93.53 144	97.77 145	98.55 139

diffmvs		95.25 102	95.13 100	95.63 157	96.43 225	89.34 214	95.99 271	97.35 199	92.83 132	96.31 99	97.37 141	86.44 142	98.67 209	96.26 64	97.19 165	98.87 116
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Vis-MVSNet		95.23 103	94.81 106	96.51 95	97.18 161	91.58 128	98.26 34	98.12 75	94.38 71	94.90 140	98.15 81	82.28 216	98.92 180	91.45 190	98.58 114	99.01 94
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
EPP-MVSNet		95.22 104	95.04 103	95.76 147	97.49 152	89.56 202	98.67 10	97.00 230	90.69 199	94.24 156	97.62 127	89.79 88	98.81 191	93.39 150	96.49 180	98.92 106

EPNet		95.20 105	94.56 114	97.14 69	92.80 376	92.68 87	97.85 85	94.87 350	96.64 4	92.46 194	97.80 112	86.23 144	99.65 67	93.72 143	98.62 111	99.10 86
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
3Dnovator	91.36 5	95.19 106	94.44 122	97.44 53	96.56 209	93.36 66	98.65 11	98.36 29	94.12 75	89.25 289	98.06 86	82.20 218	99.77 43	93.41 149	99.32 65	99.18 76

OMC-MVS		95.09 107	94.70 110	96.25 121	98.46 73	91.28 139	96.43 238	97.57 160	92.04 154	94.77 144	97.96 96	87.01 136	99.09 159	91.31 192	96.77 172	98.36 162

xiu_mvs_v1_base_debu		95.01 108	94.76 107	95.75 149	96.58 206	91.71 120	96.25 256	97.35 199	92.99 122	96.70 79	96.63 185	82.67 206	99.44 115	96.22 67	97.46 150	96.11 265

xiu_mvs_v1_base		95.01 108	94.76 107	95.75 149	96.58 206	91.71 120	96.25 256	97.35 199	92.99 122	96.70 79	96.63 185	82.67 206	99.44 115	96.22 67	97.46 150	96.11 265

xiu_mvs_v1_base_debi		95.01 108	94.76 107	95.75 149	96.58 206	91.71 120	96.25 256	97.35 199	92.99 122	96.70 79	96.63 185	82.67 206	99.44 115	96.22 67	97.46 150	96.11 265

PAPM_NR		95.01 108	94.59 112	96.26 118	98.89 54	90.68 168	97.24 167	97.73 139	91.80 159	92.93 191	96.62 188	89.13 93	99.14 151	89.21 237	97.78 144	98.97 98

lupinMVS		94.99 112	94.56 114	96.29 116	96.34 230	91.21 143	95.83 279	96.27 280	88.93 260	96.22 103	96.88 168	86.20 147	98.85 187	95.27 105	99.05 91	98.82 122

Effi-MVS+		94.93 113	94.45 121	96.36 110	96.61 203	91.47 133	96.41 240	97.41 191	91.02 190	94.50 150	95.92 221	87.53 125	98.78 194	93.89 139	96.81 171	98.84 121

IS-MVSNet		94.90 114	94.52 118	96.05 130	97.67 135	90.56 170	98.44 21	96.22 283	93.21 110	93.99 162	97.74 115	85.55 155	98.45 228	89.98 213	97.86 141	99.14 80

MVS_Test		94.89 115	94.62 111	95.68 155	96.83 187	89.55 203	96.70 216	97.17 210	91.17 184	95.60 127	96.11 216	87.87 117	98.76 198	93.01 161	97.17 166	98.72 127

PVSNet_Blended		94.87 116	94.56 114	95.81 145	98.27 86	89.46 209	95.47 300	98.36 29	88.84 263	94.36 153	96.09 217	88.02 112	99.58 86	93.44 147	98.18 131	98.40 158

jason		94.84 117	94.39 123	96.18 124	95.52 267	90.93 158	96.09 265	96.52 267	89.28 246	96.01 113	97.32 143	84.70 164	98.77 197	95.15 109	98.91 100	98.85 118
jason: jason.
API-MVS		94.84 117	94.49 119	95.90 140	97.90 123	92.00 112	97.80 94	97.48 172	89.19 249	94.81 142	96.71 174	88.84 98	99.17 144	88.91 244	98.76 105	96.53 248

test_yl		94.78 119	94.23 125	96.43 103	97.74 131	91.22 141	96.85 201	97.10 215	91.23 181	95.71 122	96.93 163	84.30 171	99.31 128	93.10 154	95.12 206	98.75 124

DCV-MVSNet		94.78 119	94.23 125	96.43 103	97.74 131	91.22 141	96.85 201	97.10 215	91.23 181	95.71 122	96.93 163	84.30 171	99.31 128	93.10 154	95.12 206	98.75 124

WTY-MVS		94.71 121	94.02 128	96.79 79	97.71 133	92.05 110	96.59 231	97.35 199	90.61 207	94.64 146	96.93 163	86.41 143	99.39 120	91.20 195	94.71 218	98.94 102

mamv4		94.66 122	96.10 75	90.37 361	98.01 112	73.41 410	96.82 205	97.78 134	89.95 225	94.52 149	97.43 139	92.91 27	99.09 159	98.28 20	99.16 82	98.60 135

mvsmamba		94.57 123	94.14 127	95.87 141	97.03 174	89.93 192	97.84 86	95.85 297	91.34 175	94.79 143	96.80 170	80.67 242	98.81 191	94.85 115	98.12 134	98.85 118

RRT-MVS		94.51 124	94.35 124	94.98 190	96.40 226	86.55 293	97.56 128	97.41 191	93.19 113	94.93 139	97.04 160	79.12 271	99.30 130	96.19 74	97.32 160	99.09 87

sss		94.51 124	93.80 132	96.64 82	97.07 167	91.97 113	96.32 251	98.06 90	88.94 259	94.50 150	96.78 171	84.60 165	99.27 132	91.90 176	96.02 185	98.68 131

test_cas_vis1_n_1920		94.48 126	94.55 117	94.28 231	96.78 193	86.45 295	97.63 121	97.64 151	93.32 108	97.68 48	98.36 59	73.75 331	99.08 162	96.73 53	99.05 91	97.31 228

CANet_DTU		94.37 127	93.65 136	96.55 89	96.46 223	92.13 108	96.21 260	96.67 259	94.38 71	93.53 173	97.03 161	79.34 267	99.71 55	90.76 201	98.45 120	97.82 202

AdaColmap		94.34 128	93.68 135	96.31 112	98.59 69	91.68 123	96.59 231	97.81 132	89.87 226	92.15 205	97.06 159	83.62 184	99.54 98	89.34 231	98.07 135	97.70 207

CNLPA		94.28 129	93.53 141	96.52 91	98.38 81	92.55 92	96.59 231	96.88 243	90.13 222	91.91 213	97.24 149	85.21 158	99.09 159	87.64 270	97.83 142	97.92 191

MAR-MVS		94.22 130	93.46 146	96.51 95	98.00 114	92.19 107	97.67 111	97.47 175	88.13 289	93.00 186	95.84 225	84.86 163	99.51 105	87.99 257	98.17 132	97.83 201
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
PAPR		94.18 131	93.42 150	96.48 98	97.64 139	91.42 136	95.55 295	97.71 145	88.99 256	92.34 201	95.82 227	89.19 91	99.11 154	86.14 296	97.38 155	98.90 110

SDMVSNet		94.17 132	93.61 137	95.86 143	98.09 105	91.37 137	97.35 157	98.20 58	93.18 115	91.79 217	97.28 145	79.13 270	98.93 179	94.61 126	92.84 249	97.28 229

test_vis1_n_1920		94.17 132	94.58 113	92.91 294	97.42 154	82.02 361	97.83 89	97.85 125	94.68 54	98.10 36	98.49 46	70.15 355	99.32 126	97.91 23	98.82 101	97.40 223

h-mvs33		94.15 134	93.52 143	96.04 131	97.81 127	90.22 182	97.62 123	97.58 159	95.19 28	96.74 77	97.45 136	83.67 182	99.61 78	95.85 86	79.73 386	98.29 165

CHOSEN 1792x2688		94.15 134	93.51 144	96.06 129	98.27 86	89.38 212	95.18 317	98.48 25	85.60 341	93.76 168	97.11 156	83.15 193	99.61 78	91.33 191	98.72 106	99.19 75

Vis-MVSNet (Re-imp)		94.15 134	93.88 131	94.95 194	97.61 143	87.92 258	98.10 51	95.80 300	92.22 145	93.02 185	97.45 136	84.53 167	97.91 300	88.24 253	97.97 138	99.02 91

CDS-MVSNet		94.14 137	93.54 140	95.93 139	96.18 237	91.46 134	96.33 250	97.04 225	88.97 258	93.56 170	96.51 192	87.55 123	97.89 301	89.80 218	95.95 187	98.44 155
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PLC	91.00 6	94.11 138	93.43 148	96.13 126	98.58 71	91.15 152	96.69 218	97.39 193	87.29 313	91.37 227	96.71 174	88.39 106	99.52 104	87.33 277	97.13 167	97.73 205
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
FIs		94.09 139	93.70 134	95.27 175	95.70 259	92.03 111	98.10 51	98.68 13	93.36 107	90.39 248	96.70 176	87.63 122	97.94 294	92.25 168	90.50 290	95.84 273

PVSNet_BlendedMVS		94.06 140	93.92 130	94.47 218	98.27 86	89.46 209	96.73 212	98.36 29	90.17 219	94.36 153	95.24 260	88.02 112	99.58 86	93.44 147	90.72 286	94.36 357

nrg030		94.05 141	93.31 152	96.27 117	95.22 291	94.59 32	98.34 25	97.46 177	92.93 129	91.21 237	96.64 181	87.23 134	98.22 248	94.99 113	85.80 334	95.98 269

UGNet		94.04 142	93.28 153	96.31 112	96.85 184	91.19 146	97.88 81	97.68 146	94.40 69	93.00 186	96.18 207	73.39 333	99.61 78	91.72 182	98.46 119	98.13 176
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
TAMVS		94.01 143	93.46 146	95.64 156	96.16 239	90.45 174	96.71 215	96.89 242	89.27 247	93.46 175	96.92 166	87.29 132	97.94 294	88.70 249	95.74 192	98.53 141

114514_t		93.95 144	93.06 157	96.63 84	99.07 37	91.61 125	97.46 145	97.96 110	77.99 404	93.00 186	97.57 130	86.14 149	99.33 124	89.22 236	99.15 83	98.94 102

FC-MVSNet-test		93.94 145	93.57 138	95.04 185	95.48 269	91.45 135	98.12 50	98.71 11	93.37 105	90.23 251	96.70 176	87.66 119	97.85 303	91.49 188	90.39 291	95.83 274

mvsany_test1		93.93 146	93.98 129	93.78 259	94.94 308	86.80 283	94.62 329	92.55 394	88.77 269	96.85 72	98.49 46	88.98 94	98.08 266	95.03 111	95.62 197	96.46 253

GeoE		93.89 147	93.28 153	95.72 153	96.96 179	89.75 196	98.24 38	96.92 239	89.47 240	92.12 207	97.21 151	84.42 169	98.39 236	87.71 264	96.50 179	99.01 94

HY-MVS	89.66 9	93.87 148	92.95 160	96.63 84	97.10 166	92.49 94	95.64 292	96.64 260	89.05 254	93.00 186	95.79 231	85.77 153	99.45 114	89.16 240	94.35 220	97.96 189

XVG-OURS-SEG-HR		93.86 149	93.55 139	94.81 200	97.06 170	88.53 240	95.28 309	97.45 182	91.68 164	94.08 161	97.68 118	82.41 214	98.90 183	93.84 141	92.47 255	96.98 236

VDD-MVS		93.82 150	93.08 156	96.02 133	97.88 124	89.96 191	97.72 104	95.85 297	92.43 140	95.86 117	98.44 52	68.42 372	99.39 120	96.31 63	94.85 210	98.71 129

mvs_anonymous		93.82 150	93.74 133	94.06 239	96.44 224	85.41 312	95.81 280	97.05 223	89.85 229	90.09 261	96.36 200	87.44 129	97.75 316	93.97 135	96.69 176	99.02 91

HQP_MVS		93.78 152	93.43 148	94.82 198	96.21 234	89.99 187	97.74 99	97.51 168	94.85 42	91.34 228	96.64 181	81.32 232	98.60 216	93.02 159	92.23 258	95.86 270

PS-MVSNAJss		93.74 153	93.51 144	94.44 220	93.91 346	89.28 219	97.75 98	97.56 164	92.50 139	89.94 264	96.54 191	88.65 102	98.18 253	93.83 142	90.90 284	95.86 270

XVG-OURS		93.72 154	93.35 151	94.80 203	97.07 167	88.61 235	94.79 326	97.46 177	91.97 157	93.99 162	97.86 104	81.74 227	98.88 184	92.64 165	92.67 254	96.92 240

HyFIR lowres test		93.66 155	92.92 161	95.87 141	98.24 90	89.88 193	94.58 331	98.49 23	85.06 351	93.78 167	95.78 232	82.86 202	98.67 209	91.77 181	95.71 194	99.07 90

LFMVS		93.60 156	92.63 174	96.52 91	98.13 104	91.27 140	97.94 73	93.39 383	90.57 210	96.29 100	98.31 69	69.00 365	99.16 146	94.18 132	95.87 189	99.12 84

F-COLMAP		93.58 157	92.98 159	95.37 173	98.40 78	88.98 228	97.18 175	97.29 204	87.75 302	90.49 246	97.10 157	85.21 158	99.50 108	86.70 287	96.72 175	97.63 209

ab-mvs		93.57 158	92.55 178	96.64 82	97.28 157	91.96 115	95.40 302	97.45 182	89.81 231	93.22 183	96.28 203	79.62 264	99.46 112	90.74 202	93.11 246	98.50 145

LS3D		93.57 158	92.61 176	96.47 99	97.59 145	91.61 125	97.67 111	97.72 141	85.17 349	90.29 250	98.34 63	84.60 165	99.73 50	83.85 331	98.27 127	98.06 185

FA-MVS(test-final)		93.52 160	92.92 161	95.31 174	96.77 195	88.54 239	94.82 325	96.21 285	89.61 235	94.20 157	95.25 259	83.24 189	99.14 151	90.01 212	96.16 184	98.25 166

Fast-Effi-MVS+		93.46 161	92.75 169	95.59 160	96.77 195	90.03 184	96.81 206	97.13 212	88.19 284	91.30 231	94.27 310	86.21 146	98.63 213	87.66 269	96.46 182	98.12 178

hse-mvs2		93.45 162	92.99 158	94.81 200	97.02 175	88.59 236	96.69 218	96.47 270	95.19 28	96.74 77	96.16 210	83.67 182	98.48 227	95.85 86	79.13 390	97.35 226

QAPM		93.45 162	92.27 188	96.98 78	96.77 195	92.62 88	98.39 24	98.12 75	84.50 359	88.27 314	97.77 113	82.39 215	99.81 30	85.40 309	98.81 102	98.51 144

UniMVSNet_NR-MVSNet		93.37 164	92.67 173	95.47 170	95.34 280	92.83 82	97.17 176	98.58 21	92.98 127	90.13 256	95.80 228	88.37 108	97.85 303	91.71 183	83.93 363	95.73 284

1112_ss		93.37 164	92.42 185	96.21 122	97.05 172	90.99 154	96.31 252	96.72 252	86.87 321	89.83 268	96.69 178	86.51 141	99.14 151	88.12 254	93.67 240	98.50 145

UniMVSNet (Re)		93.31 166	92.55 178	95.61 159	95.39 274	93.34 67	97.39 153	98.71 11	93.14 118	90.10 260	94.83 276	87.71 118	98.03 277	91.67 186	83.99 362	95.46 293

OPM-MVS		93.28 167	92.76 167	94.82 198	94.63 324	90.77 164	96.65 222	97.18 208	93.72 88	91.68 221	97.26 148	79.33 268	98.63 213	92.13 172	92.28 257	95.07 320
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
VPA-MVSNet		93.24 168	92.48 183	95.51 165	95.70 259	92.39 96	97.86 82	98.66 16	92.30 143	92.09 209	95.37 252	80.49 246	98.40 231	93.95 136	85.86 333	95.75 282

test_fmvs1		93.21 169	93.53 141	92.25 316	96.55 211	81.20 368	97.40 152	96.96 232	90.68 200	96.80 73	98.04 88	69.25 363	98.40 231	97.58 33	98.50 115	97.16 233

MVSTER		93.20 170	92.81 166	94.37 223	96.56 209	89.59 200	97.06 183	97.12 213	91.24 180	91.30 231	95.96 219	82.02 221	98.05 273	93.48 146	90.55 288	95.47 292

test1111		93.19 171	92.82 165	94.30 230	97.58 149	84.56 329	98.21 42	89.02 413	93.53 98	94.58 147	98.21 76	72.69 334	99.05 169	93.06 157	98.48 118	99.28 69

ECVR-MVS		93.19 171	92.73 171	94.57 215	97.66 137	85.41 312	98.21 42	88.23 415	93.43 103	94.70 145	98.21 76	72.57 335	99.07 166	93.05 158	98.49 116	99.25 72

HQP-MVS		93.19 171	92.74 170	94.54 216	95.86 251	89.33 215	96.65 222	97.39 193	93.55 94	90.14 252	95.87 223	80.95 236	98.50 224	92.13 172	92.10 263	95.78 278

CHOSEN 280x420		93.12 174	92.72 172	94.34 226	96.71 199	87.27 271	90.29 404	97.72 141	86.61 325	91.34 228	95.29 254	84.29 173	98.41 230	93.25 151	98.94 98	97.35 226

sd_testset		93.10 175	92.45 184	95.05 184	98.09 105	89.21 221	96.89 198	97.64 151	93.18 115	91.79 217	97.28 145	75.35 317	98.65 211	88.99 242	92.84 249	97.28 229

Effi-MVS+-dtu		93.08 176	93.21 155	92.68 305	96.02 248	83.25 345	97.14 179	96.72 252	93.85 85	91.20 238	93.44 348	83.08 195	98.30 243	91.69 185	95.73 193	96.50 250

test_djsdf		93.07 177	92.76 167	94.00 243	93.49 360	88.70 234	98.22 40	97.57 160	91.42 172	90.08 262	95.55 245	82.85 203	97.92 297	94.07 133	91.58 270	95.40 299

VDDNet		93.05 178	92.07 192	96.02 133	96.84 185	90.39 178	98.08 53	95.85 297	86.22 333	95.79 120	98.46 50	67.59 375	99.19 139	94.92 114	94.85 210	98.47 150

thisisatest0530		93.03 179	92.21 190	95.49 167	97.07 167	89.11 226	97.49 142	92.19 396	90.16 220	94.09 160	96.41 197	76.43 308	99.05 169	90.38 207	95.68 195	98.31 164

EI-MVSNet		93.03 179	92.88 163	93.48 273	95.77 257	86.98 280	96.44 236	97.12 213	90.66 203	91.30 231	97.64 125	86.56 139	98.05 273	89.91 215	90.55 288	95.41 296

CLD-MVS		92.98 181	92.53 180	94.32 227	96.12 244	89.20 222	95.28 309	97.47 175	92.66 136	89.90 265	95.62 241	80.58 244	98.40 231	92.73 164	92.40 256	95.38 301
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
tttt0517		92.96 182	92.33 187	94.87 197	97.11 165	87.16 277	97.97 69	92.09 397	90.63 205	93.88 166	97.01 162	76.50 305	99.06 168	90.29 210	95.45 200	98.38 160

ACMM	89.79 8	92.96 182	92.50 182	94.35 224	96.30 232	88.71 233	97.58 125	97.36 198	91.40 174	90.53 245	96.65 180	79.77 260	98.75 199	91.24 194	91.64 268	95.59 288
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LPG-MVS_test		92.94 184	92.56 177	94.10 237	96.16 239	88.26 247	97.65 115	97.46 177	91.29 176	90.12 258	97.16 153	79.05 273	98.73 202	92.25 168	91.89 266	95.31 306

BH-untuned		92.94 184	92.62 175	93.92 253	97.22 158	86.16 303	96.40 244	96.25 282	90.06 223	89.79 269	96.17 209	83.19 191	98.35 239	87.19 280	97.27 162	97.24 231

DU-MVS		92.90 186	92.04 194	95.49 167	94.95 306	92.83 82	97.16 177	98.24 52	93.02 121	90.13 256	95.71 235	83.47 185	97.85 303	91.71 183	83.93 363	95.78 278

PatchMatch-RL		92.90 186	92.02 196	95.56 161	98.19 98	90.80 162	95.27 311	97.18 208	87.96 291	91.86 216	95.68 238	80.44 247	98.99 174	84.01 326	97.54 149	96.89 241

PMMVS		92.86 188	92.34 186	94.42 222	94.92 309	86.73 286	94.53 333	96.38 274	84.78 356	94.27 155	95.12 265	83.13 194	98.40 231	91.47 189	96.49 180	98.12 178

OpenMVS	89.19 12	92.86 188	91.68 208	96.40 105	95.34 280	92.73 86	98.27 32	98.12 75	84.86 354	85.78 355	97.75 114	78.89 280	99.74 48	87.50 274	98.65 109	96.73 245

Test_1112_low_res		92.84 190	91.84 202	95.85 144	97.04 173	89.97 190	95.53 297	96.64 260	85.38 344	89.65 274	95.18 261	85.86 151	99.10 156	87.70 265	93.58 245	98.49 147

baseline1		92.82 191	91.90 200	95.55 163	97.20 160	90.77 164	97.19 174	94.58 356	92.20 147	92.36 198	96.34 201	84.16 175	98.21 249	89.20 238	83.90 366	97.68 208

1314		92.81 192	92.03 195	95.14 180	95.33 283	89.52 206	96.04 267	97.44 186	87.72 303	86.25 352	95.33 253	83.84 179	98.79 193	89.26 234	97.05 168	97.11 234

DP-MVS		92.76 193	91.51 216	96.52 91	98.77 56	90.99 154	97.38 155	96.08 289	82.38 380	89.29 286	97.87 102	83.77 180	99.69 61	81.37 353	96.69 176	98.89 114

test_fmvs1_n		92.73 194	92.88 163	92.29 313	96.08 247	81.05 369	97.98 63	97.08 218	90.72 198	96.79 75	98.18 79	63.07 397	98.45 228	97.62 32	98.42 122	97.36 224

BH-RMVSNet		92.72 195	91.97 198	94.97 192	97.16 162	87.99 256	96.15 263	95.60 311	90.62 206	91.87 215	97.15 155	78.41 286	98.57 220	83.16 333	97.60 148	98.36 162

ACMP	89.59 10	92.62 196	92.14 191	94.05 240	96.40 226	88.20 250	97.36 156	97.25 207	91.52 167	88.30 312	96.64 181	78.46 285	98.72 205	91.86 179	91.48 272	95.23 313
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LCM-MVSNet-Re		92.50 197	92.52 181	92.44 307	96.82 189	81.89 362	96.92 196	93.71 380	92.41 141	84.30 368	94.60 288	85.08 160	97.03 359	91.51 187	97.36 156	98.40 158

TranMVSNet+NR-MVSNet		92.50 197	91.63 209	95.14 180	94.76 317	92.07 109	97.53 133	98.11 78	92.90 131	89.56 277	96.12 212	83.16 192	97.60 329	89.30 232	83.20 372	95.75 282

thres600view7		92.49 199	91.60 210	95.18 178	97.91 122	89.47 207	97.65 115	94.66 353	92.18 151	93.33 178	94.91 271	78.06 293	99.10 156	81.61 347	94.06 235	96.98 236

thres100view900		92.43 200	91.58 211	94.98 190	97.92 121	89.37 213	97.71 106	94.66 353	92.20 147	93.31 179	94.90 272	78.06 293	99.08 162	81.40 350	94.08 231	96.48 251

jajsoiax		92.42 201	91.89 201	94.03 242	93.33 366	88.50 241	97.73 101	97.53 166	92.00 156	88.85 298	96.50 193	75.62 315	98.11 260	93.88 140	91.56 271	95.48 290

thres400		92.42 201	91.52 214	95.12 182	97.85 125	89.29 217	97.41 148	94.88 347	92.19 149	93.27 181	94.46 298	78.17 289	99.08 162	81.40 350	94.08 231	96.98 236

tfpn200view9		92.38 203	91.52 214	94.95 194	97.85 125	89.29 217	97.41 148	94.88 347	92.19 149	93.27 181	94.46 298	78.17 289	99.08 162	81.40 350	94.08 231	96.48 251

test_vis1_n		92.37 204	92.26 189	92.72 302	94.75 318	82.64 351	98.02 59	96.80 249	91.18 183	97.77 47	97.93 97	58.02 406	98.29 244	97.63 31	98.21 129	97.23 232

WR-MVS		92.34 205	91.53 213	94.77 205	95.13 299	90.83 161	96.40 244	97.98 108	91.88 158	89.29 286	95.54 246	82.50 211	97.80 310	89.79 219	85.27 342	95.69 285

NR-MVSNet		92.34 205	91.27 224	95.53 164	94.95 306	93.05 77	97.39 153	98.07 87	92.65 137	84.46 366	95.71 235	85.00 161	97.77 314	89.71 220	83.52 369	95.78 278

mvs_tets		92.31 207	91.76 204	93.94 250	93.41 363	88.29 245	97.63 121	97.53 166	92.04 154	88.76 301	96.45 195	74.62 323	98.09 265	93.91 138	91.48 272	95.45 294

TAPA-MVS	90.10 7	92.30 208	91.22 227	95.56 161	98.33 83	89.60 199	96.79 207	97.65 149	81.83 384	91.52 223	97.23 150	87.94 114	98.91 182	71.31 405	98.37 123	98.17 174
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
thisisatest0515		92.29 209	91.30 222	95.25 176	96.60 204	88.90 230	94.36 342	92.32 395	87.92 292	93.43 176	94.57 289	77.28 300	99.00 173	89.42 229	95.86 190	97.86 198

Fast-Effi-MVS+-dtu		92.29 209	91.99 197	93.21 284	95.27 287	85.52 310	97.03 184	96.63 263	92.09 152	89.11 292	95.14 263	80.33 250	98.08 266	87.54 273	94.74 216	96.03 268

IterMVS-LS		92.29 209	91.94 199	93.34 278	96.25 233	86.97 281	96.57 234	97.05 223	90.67 201	89.50 280	94.80 278	86.59 138	97.64 324	89.91 215	86.11 332	95.40 299
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PVSNet	86.66 18	92.24 212	91.74 207	93.73 260	97.77 129	83.69 342	92.88 384	96.72 252	87.91 293	93.00 186	94.86 274	78.51 284	99.05 169	86.53 288	97.45 154	98.47 150

VPNet		92.23 213	91.31 221	94.99 188	95.56 265	90.96 156	97.22 172	97.86 124	92.96 128	90.96 239	96.62 188	75.06 318	98.20 250	91.90 176	83.65 368	95.80 276

thres200		92.23 213	91.39 217	94.75 207	97.61 143	89.03 227	96.60 230	95.09 336	92.08 153	93.28 180	94.00 325	78.39 287	99.04 172	81.26 356	94.18 227	96.19 258

anonymousdsp		92.16 215	91.55 212	93.97 246	92.58 381	89.55 203	97.51 135	97.42 190	89.42 243	88.40 308	94.84 275	80.66 243	97.88 302	91.87 178	91.28 276	94.48 352

XXY-MVS		92.16 215	91.23 226	94.95 194	94.75 318	90.94 157	97.47 143	97.43 189	89.14 250	88.90 294	96.43 196	79.71 261	98.24 246	89.56 225	87.68 315	95.67 286

BH-w/o		92.14 217	91.75 205	93.31 279	96.99 178	85.73 307	95.67 287	95.69 306	88.73 270	89.26 288	94.82 277	82.97 200	98.07 270	85.26 312	96.32 183	96.13 264

testing3-2		92.10 218	92.05 193	92.27 314	97.71 133	79.56 388	97.42 147	94.41 362	93.53 98	93.22 183	95.49 248	69.16 364	99.11 154	93.25 151	94.22 225	98.13 176

Anonymous202405211		92.07 219	90.83 243	95.76 147	98.19 98	88.75 232	97.58 125	95.00 339	86.00 336	93.64 169	97.45 136	66.24 387	99.53 100	90.68 204	92.71 252	99.01 94

FE-MVS		92.05 220	91.05 232	95.08 183	96.83 187	87.93 257	93.91 360	95.70 304	86.30 330	94.15 159	94.97 267	76.59 304	99.21 137	84.10 324	96.86 169	98.09 182

WR-MVS_H		92.00 221	91.35 218	93.95 248	95.09 301	89.47 207	98.04 58	98.68 13	91.46 170	88.34 310	94.68 283	85.86 151	97.56 331	85.77 304	84.24 360	94.82 337

Anonymous20240529		91.98 222	90.73 249	95.73 152	98.14 102	89.40 211	97.99 62	97.72 141	79.63 398	93.54 172	97.41 140	69.94 357	99.56 94	91.04 198	91.11 279	98.22 168

MonoMVSNet		91.92 223	91.77 203	92.37 309	92.94 372	83.11 347	97.09 182	95.55 314	92.91 130	90.85 241	94.55 290	81.27 234	96.52 371	93.01 161	87.76 314	97.47 220

PatchmatchNet		91.91 224	91.35 218	93.59 268	95.38 275	84.11 335	93.15 379	95.39 319	89.54 237	92.10 208	93.68 338	82.82 204	98.13 256	84.81 316	95.32 202	98.52 142
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
testing91		91.90 225	91.02 233	94.53 217	96.54 212	86.55 293	95.86 277	95.64 310	91.77 161	91.89 214	93.47 347	69.94 357	98.86 185	90.23 211	93.86 238	98.18 171

CP-MVSNet		91.89 226	91.24 225	93.82 256	95.05 302	88.57 237	97.82 91	98.19 63	91.70 163	88.21 316	95.76 233	81.96 222	97.52 337	87.86 259	84.65 351	95.37 302

SCA		91.84 227	91.18 229	93.83 255	95.59 263	84.95 325	94.72 327	95.58 313	90.82 193	92.25 203	93.69 336	75.80 312	98.10 261	86.20 294	95.98 186	98.45 152

FMVSNet3		91.78 228	90.69 252	95.03 186	96.53 214	92.27 102	97.02 186	96.93 235	89.79 232	89.35 283	94.65 286	77.01 301	97.47 340	86.12 297	88.82 303	95.35 303

AUN-MVS		91.76 229	90.75 247	94.81 200	97.00 177	88.57 237	96.65 222	96.49 269	89.63 234	92.15 205	96.12 212	78.66 282	98.50 224	90.83 199	79.18 389	97.36 224

X-MVStestdata		91.71 230	89.67 295	97.81 28	99.38 14	94.03 50	98.59 12	98.20 58	94.85 42	96.59 87	32.69 430	91.70 52	99.80 34	95.66 92	99.40 56	99.62 20

MVS		91.71 230	90.44 259	95.51 165	95.20 293	91.59 127	96.04 267	97.45 182	73.44 414	87.36 333	95.60 242	85.42 156	99.10 156	85.97 301	97.46 150	95.83 274

EPNet_dtu		91.71 230	91.28 223	92.99 291	93.76 351	83.71 341	96.69 218	95.28 326	93.15 117	87.02 342	95.95 220	83.37 188	97.38 348	79.46 368	96.84 170	97.88 194
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing11		91.68 233	90.75 247	94.47 218	96.53 214	86.56 292	95.76 284	94.51 359	91.10 188	91.24 236	93.59 342	68.59 369	98.86 185	91.10 196	94.29 223	98.00 188

baseline2		91.63 234	90.86 239	93.94 250	94.33 335	86.32 297	95.92 274	91.64 401	89.37 244	86.94 345	94.69 282	81.62 229	98.69 207	88.64 250	94.57 219	96.81 243

testing99		91.62 235	90.72 250	94.32 227	96.48 220	86.11 304	95.81 280	94.76 351	91.55 166	91.75 219	93.44 348	68.55 370	98.82 189	90.43 205	93.69 239	98.04 186

test2506		91.60 236	90.78 244	94.04 241	97.66 137	83.81 338	98.27 32	75.53 431	93.43 103	95.23 134	98.21 76	67.21 378	99.07 166	93.01 161	98.49 116	99.25 72

miper_ehance_all_eth		91.59 237	91.13 230	92.97 292	95.55 266	86.57 291	94.47 336	96.88 243	87.77 300	88.88 296	94.01 324	86.22 145	97.54 333	89.49 226	86.93 323	94.79 342

v2v482		91.59 237	90.85 241	93.80 257	93.87 348	88.17 252	96.94 195	96.88 243	89.54 237	89.53 278	94.90 272	81.70 228	98.02 278	89.25 235	85.04 348	95.20 314

V42		91.58 239	90.87 238	93.73 260	94.05 343	88.50 241	97.32 161	96.97 231	88.80 268	89.71 270	94.33 305	82.54 210	98.05 273	89.01 241	85.07 346	94.64 350

PCF-MVS	89.48 11	91.56 240	89.95 283	96.36 110	96.60 204	92.52 93	92.51 389	97.26 205	79.41 399	88.90 294	96.56 190	84.04 178	99.55 96	77.01 382	97.30 161	97.01 235
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UBG		91.55 241	90.76 245	93.94 250	96.52 216	85.06 321	95.22 314	94.54 357	90.47 213	91.98 211	92.71 359	72.02 338	98.74 201	88.10 255	95.26 204	98.01 187

PS-CasMVS		91.55 241	90.84 242	93.69 264	94.96 305	88.28 246	97.84 86	98.24 52	91.46 170	88.04 320	95.80 228	79.67 262	97.48 339	87.02 284	84.54 357	95.31 306

miper_enhance_ethall		91.54 243	91.01 234	93.15 286	95.35 279	87.07 279	93.97 355	96.90 240	86.79 322	89.17 290	93.43 351	86.55 140	97.64 324	89.97 214	86.93 323	94.74 346

myMVS_eth3d28		91.52 244	90.97 235	93.17 285	96.91 180	83.24 346	95.61 293	94.96 343	92.24 144	91.98 211	93.28 352	69.31 362	98.40 231	88.71 248	95.68 195	97.88 194

PAPM		91.52 244	90.30 265	95.20 177	95.30 286	89.83 194	93.38 375	96.85 246	86.26 332	88.59 304	95.80 228	84.88 162	98.15 255	75.67 387	95.93 188	97.63 209

ET-MVSNet_ETH3D		91.49 246	90.11 275	95.63 157	96.40 226	91.57 129	95.34 305	93.48 382	90.60 209	75.58 406	95.49 248	80.08 254	96.79 368	94.25 131	89.76 296	98.52 142

TR-MVS		91.48 247	90.59 255	94.16 235	96.40 226	87.33 268	95.67 287	95.34 325	87.68 304	91.46 225	95.52 247	76.77 303	98.35 239	82.85 338	93.61 243	96.79 244

tpmrst		91.44 248	91.32 220	91.79 330	95.15 297	79.20 394	93.42 374	95.37 321	88.55 275	93.49 174	93.67 339	82.49 212	98.27 245	90.41 206	89.34 300	97.90 192

test-LLR		91.42 249	91.19 228	92.12 318	94.59 325	80.66 372	94.29 347	92.98 387	91.11 186	90.76 243	92.37 367	79.02 275	98.07 270	88.81 245	96.74 173	97.63 209

MSDG		91.42 249	90.24 269	94.96 193	97.15 164	88.91 229	93.69 367	96.32 276	85.72 340	86.93 346	96.47 194	80.24 251	98.98 175	80.57 359	95.05 209	96.98 236

c3_l		91.38 251	90.89 237	92.88 296	95.58 264	86.30 298	94.68 328	96.84 247	88.17 285	88.83 300	94.23 313	85.65 154	97.47 340	89.36 230	84.63 352	94.89 332

GA-MVS		91.38 251	90.31 264	94.59 210	94.65 323	87.62 266	94.34 343	96.19 286	90.73 197	90.35 249	93.83 329	71.84 340	97.96 289	87.22 279	93.61 243	98.21 169

v1144		91.37 253	90.60 254	93.68 265	93.89 347	88.23 249	96.84 203	97.03 227	88.37 280	89.69 272	94.39 300	82.04 220	97.98 282	87.80 261	85.37 339	94.84 334

GBi-Net		91.35 254	90.27 267	94.59 210	96.51 217	91.18 148	97.50 136	96.93 235	88.82 265	89.35 283	94.51 293	73.87 327	97.29 352	86.12 297	88.82 303	95.31 306

test1		91.35 254	90.27 267	94.59 210	96.51 217	91.18 148	97.50 136	96.93 235	88.82 265	89.35 283	94.51 293	73.87 327	97.29 352	86.12 297	88.82 303	95.31 306

UniMVSNet_ETH3D		91.34 256	90.22 272	94.68 208	94.86 313	87.86 261	97.23 171	97.46 177	87.99 290	89.90 265	96.92 166	66.35 385	98.23 247	90.30 209	90.99 282	97.96 189

FMVSNet2		91.31 257	90.08 276	94.99 188	96.51 217	92.21 104	97.41 148	96.95 233	88.82 265	88.62 303	94.75 280	73.87 327	97.42 345	85.20 313	88.55 308	95.35 303

reproduce_monomvs		91.30 258	91.10 231	91.92 322	96.82 189	82.48 355	97.01 189	97.49 171	94.64 58	88.35 309	95.27 257	70.53 350	98.10 261	95.20 106	84.60 354	95.19 317

D2MVS		91.30 258	90.95 236	92.35 310	94.71 321	85.52 310	96.18 262	98.21 56	88.89 261	86.60 349	93.82 331	79.92 258	97.95 293	89.29 233	90.95 283	93.56 370

v8		91.29 260	90.53 258	93.57 270	94.15 339	88.12 254	97.34 158	97.06 222	88.99 256	88.32 311	94.26 312	83.08 195	98.01 279	87.62 271	83.92 365	94.57 351

CVMVSNet		91.23 261	91.75 205	89.67 369	95.77 257	74.69 405	96.44 236	94.88 347	85.81 338	92.18 204	97.64 125	79.07 272	95.58 388	88.06 256	95.86 190	98.74 126

cl22		91.21 262	90.56 257	93.14 287	96.09 246	86.80 283	94.41 340	96.58 266	87.80 298	88.58 305	93.99 326	80.85 241	97.62 327	89.87 217	86.93 323	94.99 323

PEN-MVS		91.20 263	90.44 259	93.48 273	94.49 329	87.91 260	97.76 97	98.18 65	91.29 176	87.78 324	95.74 234	80.35 249	97.33 350	85.46 308	82.96 373	95.19 317

Baseline_NR-MVSNet		91.20 263	90.62 253	92.95 293	93.83 349	88.03 255	97.01 189	95.12 335	88.42 279	89.70 271	95.13 264	83.47 185	97.44 343	89.66 223	83.24 371	93.37 374

cascas		91.20 263	90.08 276	94.58 214	94.97 304	89.16 225	93.65 369	97.59 158	79.90 397	89.40 281	92.92 357	75.36 316	98.36 238	92.14 171	94.75 215	96.23 255

CostFormer		91.18 266	90.70 251	92.62 306	94.84 314	81.76 363	94.09 353	94.43 360	84.15 362	92.72 193	93.77 333	79.43 266	98.20 250	90.70 203	92.18 261	97.90 192

tt0805		91.09 267	90.07 279	94.16 235	95.61 262	88.31 244	97.56 128	96.51 268	89.56 236	89.17 290	95.64 240	67.08 382	98.38 237	91.07 197	88.44 309	95.80 276

v1192		91.07 268	90.23 270	93.58 269	93.70 352	87.82 263	96.73 212	97.07 220	87.77 300	89.58 275	94.32 307	80.90 240	97.97 285	86.52 289	85.48 337	94.95 324

v144192		91.06 269	90.28 266	93.39 276	93.66 355	87.23 274	96.83 204	97.07 220	87.43 309	89.69 272	94.28 309	81.48 230	98.00 280	87.18 281	84.92 350	94.93 328

v10		91.04 270	90.23 270	93.49 272	94.12 340	88.16 253	97.32 161	97.08 218	88.26 283	88.29 313	94.22 315	82.17 219	97.97 285	86.45 291	84.12 361	94.33 358

eth_miper_zixun_eth		91.02 271	90.59 255	92.34 312	95.33 283	84.35 331	94.10 352	96.90 240	88.56 274	88.84 299	94.33 305	84.08 176	97.60 329	88.77 247	84.37 359	95.06 321

v148		90.99 272	90.38 261	92.81 299	93.83 349	85.80 306	96.78 209	96.68 257	89.45 242	88.75 302	93.93 328	82.96 201	97.82 307	87.83 260	83.25 370	94.80 340

LTVRE_ROB	88.41 13	90.99 272	89.92 285	94.19 233	96.18 237	89.55 203	96.31 252	97.09 217	87.88 294	85.67 356	95.91 222	78.79 281	98.57 220	81.50 348	89.98 293	94.44 355
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
DIV-MVS_self_test		90.97 274	90.33 262	92.88 296	95.36 278	86.19 302	94.46 338	96.63 263	87.82 296	88.18 317	94.23 313	82.99 198	97.53 335	87.72 262	85.57 336	94.93 328

cl____		90.96 275	90.32 263	92.89 295	95.37 277	86.21 301	94.46 338	96.64 260	87.82 296	88.15 318	94.18 316	82.98 199	97.54 333	87.70 265	85.59 335	94.92 330

pmmvs4		90.93 276	89.85 287	94.17 234	93.34 365	90.79 163	94.60 330	96.02 290	84.62 357	87.45 329	95.15 262	81.88 225	97.45 342	87.70 265	87.87 313	94.27 362

XVG-ACMP-BASELINE		90.93 276	90.21 273	93.09 288	94.31 337	85.89 305	95.33 306	97.26 205	91.06 189	89.38 282	95.44 251	68.61 368	98.60 216	89.46 227	91.05 280	94.79 342

v1921920		90.85 278	90.03 281	93.29 280	93.55 356	86.96 282	96.74 211	97.04 225	87.36 311	89.52 279	94.34 304	80.23 252	97.97 285	86.27 292	85.21 343	94.94 326

CR-MVSNet		90.82 279	89.77 291	93.95 248	94.45 331	87.19 275	90.23 405	95.68 308	86.89 320	92.40 195	92.36 370	80.91 238	97.05 358	81.09 357	93.95 236	97.60 214

v7n		90.76 280	89.86 286	93.45 275	93.54 357	87.60 267	97.70 109	97.37 196	88.85 262	87.65 326	94.08 322	81.08 235	98.10 261	84.68 318	83.79 367	94.66 349

RPSCF		90.75 281	90.86 239	90.42 360	96.84 185	76.29 403	95.61 293	96.34 275	83.89 365	91.38 226	97.87 102	76.45 306	98.78 194	87.16 282	92.23 258	96.20 257

MVP-Stereo		90.74 282	90.08 276	92.71 303	93.19 368	88.20 250	95.86 277	96.27 280	86.07 335	84.86 364	94.76 279	77.84 296	97.75 316	83.88 330	98.01 137	92.17 395
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
pm-mvs1		90.72 283	89.65 297	93.96 247	94.29 338	89.63 197	97.79 95	96.82 248	89.07 252	86.12 354	95.48 250	78.61 283	97.78 312	86.97 285	81.67 378	94.46 353

v1240		90.70 284	89.85 287	93.23 282	93.51 359	86.80 283	96.61 228	97.02 229	87.16 316	89.58 275	94.31 308	79.55 265	97.98 282	85.52 307	85.44 338	94.90 331

EPMVS		90.70 284	89.81 289	93.37 277	94.73 320	84.21 333	93.67 368	88.02 416	89.50 239	92.38 197	93.49 345	77.82 297	97.78 312	86.03 300	92.68 253	98.11 181

WBMVS		90.69 286	89.99 282	92.81 299	96.48 220	85.00 322	95.21 316	96.30 278	89.46 241	89.04 293	94.05 323	72.45 337	97.82 307	89.46 227	87.41 320	95.61 287

Anonymous20231211		90.63 287	89.42 302	94.27 232	98.24 90	89.19 224	98.05 57	97.89 116	79.95 396	88.25 315	94.96 268	72.56 336	98.13 256	89.70 221	85.14 344	95.49 289

DTE-MVSNet		90.56 288	89.75 293	93.01 290	93.95 344	87.25 272	97.64 119	97.65 149	90.74 196	87.12 337	95.68 238	79.97 257	97.00 362	83.33 332	81.66 379	94.78 344

ACMH	87.59 16	90.53 289	89.42 302	93.87 254	96.21 234	87.92 258	97.24 167	96.94 234	88.45 278	83.91 376	96.27 204	71.92 339	98.62 215	84.43 321	89.43 299	95.05 322
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETVMVS		90.52 290	89.14 310	94.67 209	96.81 191	87.85 262	95.91 275	93.97 374	89.71 233	92.34 201	92.48 365	65.41 392	97.96 289	81.37 353	94.27 224	98.21 169

OurMVSNet-221017-0		90.51 291	90.19 274	91.44 339	93.41 363	81.25 366	96.98 192	96.28 279	91.68 164	86.55 350	96.30 202	74.20 326	97.98 282	88.96 243	87.40 321	95.09 319

miper_lstm_enhance		90.50 292	90.06 280	91.83 327	95.33 283	83.74 339	93.86 361	96.70 256	87.56 307	87.79 323	93.81 332	83.45 187	96.92 364	87.39 275	84.62 353	94.82 337

COLMAP_ROB	87.81 15	90.40 293	89.28 305	93.79 258	97.95 118	87.13 278	96.92 196	95.89 296	82.83 377	86.88 348	97.18 152	73.77 330	99.29 131	78.44 373	93.62 242	94.95 324
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
testing222		90.31 294	88.96 312	94.35 224	96.54 212	87.29 269	95.50 298	93.84 378	90.97 191	91.75 219	92.96 356	62.18 402	98.00 280	82.86 336	94.08 231	97.76 204

IterMVS-SCA-FT		90.31 294	89.81 289	91.82 328	95.52 267	84.20 334	94.30 346	96.15 287	90.61 207	87.39 332	94.27 310	75.80 312	96.44 372	87.34 276	86.88 327	94.82 337

MS-PatchMatch		90.27 296	89.77 291	91.78 331	94.33 335	84.72 328	95.55 295	96.73 251	86.17 334	86.36 351	95.28 256	71.28 344	97.80 310	84.09 325	98.14 133	92.81 380

tpm		90.25 297	89.74 294	91.76 333	93.92 345	79.73 387	93.98 354	93.54 381	88.28 282	91.99 210	93.25 353	77.51 299	97.44 343	87.30 278	87.94 312	98.12 178

AllTest		90.23 298	88.98 311	93.98 244	97.94 119	86.64 287	96.51 235	95.54 315	85.38 344	85.49 358	96.77 172	70.28 352	99.15 148	80.02 363	92.87 247	96.15 262

dmvs_re		90.21 299	89.50 300	92.35 310	95.47 272	85.15 318	95.70 286	94.37 365	90.94 192	88.42 307	93.57 343	74.63 322	95.67 385	82.80 339	89.57 298	96.22 256

ACMH+	87.92 14	90.20 300	89.18 308	93.25 281	96.48 220	86.45 295	96.99 191	96.68 257	88.83 264	84.79 365	96.22 206	70.16 354	98.53 222	84.42 322	88.04 311	94.77 345

test-mter		90.19 301	89.54 299	92.12 318	94.59 325	80.66 372	94.29 347	92.98 387	87.68 304	90.76 243	92.37 367	67.67 374	98.07 270	88.81 245	96.74 173	97.63 209

IterMVS		90.15 302	89.67 295	91.61 335	95.48 269	83.72 340	94.33 344	96.12 288	89.99 224	87.31 335	94.15 318	75.78 314	96.27 375	86.97 285	86.89 326	94.83 335
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TESTMET0.1,1		90.06 303	89.42 302	91.97 321	94.41 333	80.62 374	94.29 347	91.97 399	87.28 314	90.44 247	92.47 366	68.79 366	97.67 321	88.50 252	96.60 178	97.61 213

tpm2		89.96 304	89.21 307	92.23 317	94.91 311	81.25 366	93.78 363	94.42 361	80.62 394	91.56 222	93.44 348	76.44 307	97.94 294	85.60 306	92.08 265	97.49 218

UWE-MVS		89.91 305	89.48 301	91.21 343	95.88 250	78.23 399	94.91 324	90.26 409	89.11 251	92.35 200	94.52 292	68.76 367	97.96 289	83.95 328	95.59 198	97.42 222

IB-MVS	87.33 17	89.91 305	88.28 322	94.79 204	95.26 290	87.70 265	95.12 319	93.95 375	89.35 245	87.03 341	92.49 364	70.74 349	99.19 139	89.18 239	81.37 380	97.49 218
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
ADS-MVSNet		89.89 307	88.68 317	93.53 271	95.86 251	84.89 326	90.93 400	95.07 337	83.23 375	91.28 234	91.81 379	79.01 277	97.85 303	79.52 365	91.39 274	97.84 199

WB-MVSnew		89.88 308	89.56 298	90.82 352	94.57 328	83.06 348	95.65 291	92.85 389	87.86 295	90.83 242	94.10 319	79.66 263	96.88 365	76.34 383	94.19 226	92.54 386

FMVSNet1		89.88 308	88.31 321	94.59 210	95.41 273	91.18 148	97.50 136	96.93 235	86.62 324	87.41 331	94.51 293	65.94 390	97.29 352	83.04 335	87.43 318	95.31 306

pmmvs5		89.86 310	88.87 315	92.82 298	92.86 374	86.23 300	96.26 255	95.39 319	84.24 361	87.12 337	94.51 293	74.27 325	97.36 349	87.61 272	87.57 316	94.86 333

tpmvs		89.83 311	89.15 309	91.89 325	94.92 309	80.30 379	93.11 380	95.46 318	86.28 331	88.08 319	92.65 360	80.44 247	98.52 223	81.47 349	89.92 294	96.84 242

test_fmvs2		89.77 312	89.93 284	89.31 375	93.68 354	76.37 402	97.64 119	95.90 294	89.84 230	91.49 224	96.26 205	58.77 405	97.10 356	94.65 124	91.13 278	94.46 353

SSC-MVS3.2		89.74 313	89.26 306	91.19 346	95.16 294	80.29 380	94.53 333	97.03 227	91.79 160	88.86 297	94.10 319	69.94 357	97.82 307	85.29 310	86.66 328	95.45 294

mmtdpeth		89.70 314	88.96 312	91.90 324	95.84 256	84.42 330	97.46 145	95.53 317	90.27 217	94.46 152	90.50 387	69.74 361	98.95 176	97.39 42	69.48 412	92.34 389

tfpnnormal		89.70 314	88.40 320	93.60 267	95.15 297	90.10 183	97.56 128	98.16 69	87.28 314	86.16 353	94.63 287	77.57 298	98.05 273	74.48 391	84.59 355	92.65 383

ADS-MVSNet2		89.45 316	88.59 318	92.03 320	95.86 251	82.26 359	90.93 400	94.32 368	83.23 375	91.28 234	91.81 379	79.01 277	95.99 377	79.52 365	91.39 274	97.84 199

Patchmatch-test		89.42 317	87.99 324	93.70 263	95.27 287	85.11 319	88.98 412	94.37 365	81.11 388	87.10 340	93.69 336	82.28 216	97.50 338	74.37 393	94.76 214	98.48 149

test0.0.03 1		89.37 318	88.70 316	91.41 340	92.47 383	85.63 308	95.22 314	92.70 392	91.11 186	86.91 347	93.65 340	79.02 275	93.19 411	78.00 375	89.18 301	95.41 296

SixPastTwentyTwo		89.15 319	88.54 319	90.98 348	93.49 360	80.28 381	96.70 216	94.70 352	90.78 194	84.15 371	95.57 243	71.78 341	97.71 319	84.63 319	85.07 346	94.94 326

RPMNet		88.98 320	87.05 334	94.77 205	94.45 331	87.19 275	90.23 405	98.03 99	77.87 406	92.40 195	87.55 410	80.17 253	99.51 105	68.84 410	93.95 236	97.60 214

TransMVSNet (Re)		88.94 321	87.56 327	93.08 289	94.35 334	88.45 243	97.73 101	95.23 330	87.47 308	84.26 369	95.29 254	79.86 259	97.33 350	79.44 369	74.44 403	93.45 373

USDC		88.94 321	87.83 326	92.27 314	94.66 322	84.96 324	93.86 361	95.90 294	87.34 312	83.40 378	95.56 244	67.43 376	98.19 252	82.64 343	89.67 297	93.66 369

dp		88.90 323	88.26 323	90.81 353	94.58 327	76.62 401	92.85 385	94.93 344	85.12 350	90.07 263	93.07 354	75.81 311	98.12 259	80.53 360	87.42 319	97.71 206

PatchT		88.87 324	87.42 328	93.22 283	94.08 342	85.10 320	89.51 410	94.64 355	81.92 383	92.36 198	88.15 406	80.05 255	97.01 361	72.43 401	93.65 241	97.54 217

our_test_3		88.78 325	87.98 325	91.20 345	92.45 384	82.53 353	93.61 371	95.69 306	85.77 339	84.88 363	93.71 334	79.99 256	96.78 369	79.47 367	86.24 329	94.28 361

EU-MVSNet		88.72 326	88.90 314	88.20 379	93.15 369	74.21 407	96.63 227	94.22 370	85.18 348	87.32 334	95.97 218	76.16 309	94.98 394	85.27 311	86.17 330	95.41 296

Patchmtry		88.64 327	87.25 330	92.78 301	94.09 341	86.64 287	89.82 409	95.68 308	80.81 392	87.63 327	92.36 370	80.91 238	97.03 359	78.86 371	85.12 345	94.67 348

MIMVSNet		88.50 328	86.76 338	93.72 262	94.84 314	87.77 264	91.39 395	94.05 371	86.41 328	87.99 321	92.59 363	63.27 396	95.82 382	77.44 376	92.84 249	97.57 216

tpm cat1		88.36 329	87.21 332	91.81 329	95.13 299	80.55 375	92.58 388	95.70 304	74.97 410	87.45 329	91.96 377	78.01 295	98.17 254	80.39 361	88.74 306	96.72 246

ppachtmachnet_test		88.35 330	87.29 329	91.53 336	92.45 384	83.57 343	93.75 364	95.97 291	84.28 360	85.32 361	94.18 316	79.00 279	96.93 363	75.71 386	84.99 349	94.10 363

JIA-IIPM		88.26 331	87.04 335	91.91 323	93.52 358	81.42 365	89.38 411	94.38 364	80.84 391	90.93 240	80.74 418	79.22 269	97.92 297	82.76 340	91.62 269	96.38 254

testgi		87.97 332	87.21 332	90.24 363	92.86 374	80.76 370	96.67 221	94.97 341	91.74 162	85.52 357	95.83 226	62.66 400	94.47 398	76.25 384	88.36 310	95.48 290

LF4IMVS		87.94 333	87.25 330	89.98 366	92.38 386	80.05 385	94.38 341	95.25 329	87.59 306	84.34 367	94.74 281	64.31 394	97.66 323	84.83 315	87.45 317	92.23 392

gg-mvs-nofinetune		87.82 334	85.61 347	94.44 220	94.46 330	89.27 220	91.21 399	84.61 425	80.88 390	89.89 267	74.98 421	71.50 342	97.53 335	85.75 305	97.21 164	96.51 249

pmmvs6		87.81 335	86.19 343	92.69 304	91.32 391	86.30 298	97.34 158	96.41 273	80.59 395	84.05 375	94.37 302	67.37 377	97.67 321	84.75 317	79.51 388	94.09 365

testing3		87.67 336	86.88 337	90.05 365	96.14 242	80.71 371	97.10 181	92.85 389	90.15 221	87.54 328	94.55 290	55.70 411	94.10 401	73.77 397	94.10 230	95.35 303

K. test v3		87.64 337	86.75 339	90.32 362	93.02 371	79.48 392	96.61 228	92.08 398	90.66 203	80.25 395	94.09 321	67.21 378	96.65 370	85.96 302	80.83 382	94.83 335

Patchmatch-RL test		87.38 338	86.24 342	90.81 353	88.74 409	78.40 398	88.12 417	93.17 385	87.11 317	82.17 386	89.29 398	81.95 223	95.60 387	88.64 250	77.02 394	98.41 157

FMVSNet5		87.29 339	85.79 346	91.78 331	94.80 316	87.28 270	95.49 299	95.28 326	84.09 363	83.85 377	91.82 378	62.95 398	94.17 400	78.48 372	85.34 341	93.91 367

myMVS_eth3d		87.18 340	86.38 341	89.58 370	95.16 294	79.53 389	95.00 321	93.93 376	88.55 275	86.96 343	91.99 375	56.23 410	94.00 402	75.47 389	94.11 228	95.20 314

Syy-MVS		87.13 341	87.02 336	87.47 383	95.16 294	73.21 411	95.00 321	93.93 376	88.55 275	86.96 343	91.99 375	75.90 310	94.00 402	61.59 417	94.11 228	95.20 314

Anonymous20231206		87.09 342	86.14 344	89.93 367	91.22 392	80.35 377	96.11 264	95.35 322	83.57 372	84.16 370	93.02 355	73.54 332	95.61 386	72.16 402	86.14 331	93.84 368

EG-PatchMatch MVS		87.02 343	85.44 348	91.76 333	92.67 378	85.00 322	96.08 266	96.45 271	83.41 374	79.52 397	93.49 345	57.10 408	97.72 318	79.34 370	90.87 285	92.56 385

TinyColmap		86.82 344	85.35 351	91.21 343	94.91 311	82.99 349	93.94 357	94.02 373	83.58 371	81.56 387	94.68 283	62.34 401	98.13 256	75.78 385	87.35 322	92.52 387

UWE-MVS-28		86.81 345	86.41 340	88.02 381	92.87 373	74.60 406	95.38 304	86.70 421	88.17 285	87.28 336	94.67 285	70.83 348	93.30 409	67.45 411	94.31 222	96.17 259

mvs5depth		86.53 346	85.08 353	90.87 350	88.74 409	82.52 354	91.91 393	94.23 369	86.35 329	87.11 339	93.70 335	66.52 383	97.76 315	81.37 353	75.80 399	92.31 391

TDRefinement		86.53 346	84.76 358	91.85 326	82.23 424	84.25 332	96.38 246	95.35 322	84.97 353	84.09 373	94.94 269	65.76 391	98.34 242	84.60 320	74.52 402	92.97 377

test_0402		86.46 348	84.79 357	91.45 338	95.02 303	85.55 309	96.29 254	94.89 346	80.90 389	82.21 385	93.97 327	68.21 373	97.29 352	62.98 415	88.68 307	91.51 400

Anonymous20240521		86.42 349	85.44 348	89.34 374	90.33 396	79.79 386	96.73 212	95.92 292	83.71 370	83.25 380	91.36 383	63.92 395	96.01 376	78.39 374	85.36 340	92.22 393

DSMNet-mixed		86.34 350	86.12 345	87.00 387	89.88 400	70.43 413	94.93 323	90.08 410	77.97 405	85.42 360	92.78 358	74.44 324	93.96 404	74.43 392	95.14 205	96.62 247

CL-MVSNet_self_test		86.31 351	85.15 352	89.80 368	88.83 407	81.74 364	93.93 358	96.22 283	86.67 323	85.03 362	90.80 386	78.09 292	94.50 396	74.92 390	71.86 408	93.15 376

pmmvs-eth3d		86.22 352	84.45 360	91.53 336	88.34 411	87.25 272	94.47 336	95.01 338	83.47 373	79.51 398	89.61 396	69.75 360	95.71 383	83.13 334	76.73 397	91.64 397

test_vis1_rt		86.16 353	85.06 354	89.46 371	93.47 362	80.46 376	96.41 240	86.61 422	85.22 347	79.15 399	88.64 401	52.41 414	97.06 357	93.08 156	90.57 287	90.87 405

test20.03		86.14 354	85.40 350	88.35 377	90.12 397	80.06 384	95.90 276	95.20 331	88.59 271	81.29 388	93.62 341	71.43 343	92.65 412	71.26 406	81.17 381	92.34 389

UnsupCasMVSNet_eth		85.99 355	84.45 360	90.62 357	89.97 399	82.40 358	93.62 370	97.37 196	89.86 227	78.59 401	92.37 367	65.25 393	95.35 392	82.27 345	70.75 409	94.10 363

KD-MVS_self_test		85.95 356	84.95 355	88.96 376	89.55 403	79.11 395	95.13 318	96.42 272	85.91 337	84.07 374	90.48 388	70.03 356	94.82 395	80.04 362	72.94 406	92.94 378

ttmdpeth		85.91 357	84.76 358	89.36 373	89.14 404	80.25 382	95.66 290	93.16 386	83.77 368	83.39 379	95.26 258	66.24 387	95.26 393	80.65 358	75.57 400	92.57 384

YYNet1		85.87 358	84.23 362	90.78 356	92.38 386	82.46 357	93.17 377	95.14 334	82.12 382	67.69 414	92.36 370	78.16 291	95.50 390	77.31 378	79.73 386	94.39 356

MDA-MVSNet_test_wron		85.87 358	84.23 362	90.80 355	92.38 386	82.57 352	93.17 377	95.15 333	82.15 381	67.65 416	92.33 373	78.20 288	95.51 389	77.33 377	79.74 385	94.31 360

CMPMVS	62.92 21	85.62 360	84.92 356	87.74 382	89.14 404	73.12 412	94.17 350	96.80 249	73.98 411	73.65 410	94.93 270	66.36 384	97.61 328	83.95 328	91.28 276	92.48 388
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
PVSNet_0	82.17 19	85.46 361	83.64 364	90.92 349	95.27 287	79.49 391	90.55 403	95.60 311	83.76 369	83.00 383	89.95 393	71.09 345	97.97 285	82.75 341	60.79 423	95.31 306

MDA-MVSNet-bldmvs		85.00 362	82.95 367	91.17 347	93.13 370	83.33 344	94.56 332	95.00 339	84.57 358	65.13 420	92.65 360	70.45 351	95.85 380	73.57 398	77.49 393	94.33 358

MIMVSNet1		84.93 363	83.05 365	90.56 358	89.56 402	84.84 327	95.40 302	95.35 322	83.91 364	80.38 393	92.21 374	57.23 407	93.34 408	70.69 408	82.75 376	93.50 371

KD-MVS_2432*1600		84.81 364	82.64 368	91.31 341	91.07 393	85.34 316	91.22 397	95.75 302	85.56 342	83.09 381	90.21 391	67.21 378	95.89 378	77.18 380	62.48 421	92.69 381

miper_refine_blended		84.81 364	82.64 368	91.31 341	91.07 393	85.34 316	91.22 397	95.75 302	85.56 342	83.09 381	90.21 391	67.21 378	95.89 378	77.18 380	62.48 421	92.69 381

OpenMVS_ROB	81.14 20	84.42 366	82.28 372	90.83 351	90.06 398	84.05 337	95.73 285	94.04 372	73.89 413	80.17 396	91.53 382	59.15 404	97.64 324	66.92 413	89.05 302	90.80 406

mvsany_test3		83.59 367	82.44 371	87.03 386	83.80 419	73.82 408	93.70 365	90.92 407	86.42 327	82.51 384	90.26 390	46.76 419	95.71 383	90.82 200	76.76 396	91.57 399

PM-MVS		83.48 368	81.86 374	88.31 378	87.83 413	77.59 400	93.43 373	91.75 400	86.91 319	80.63 391	89.91 394	44.42 420	95.84 381	85.17 314	76.73 397	91.50 401

test_fmvs3		83.21 369	83.02 366	83.78 392	86.77 416	68.34 418	96.76 210	94.91 345	86.49 326	84.14 372	89.48 397	36.04 424	91.73 414	91.86 179	80.77 383	91.26 404

new-patchmatchnet		83.18 370	81.87 373	87.11 385	86.88 415	75.99 404	93.70 365	95.18 332	85.02 352	77.30 404	88.40 403	65.99 389	93.88 405	74.19 395	70.18 410	91.47 402

new_pmnet		82.89 371	81.12 376	88.18 380	89.63 401	80.18 383	91.77 394	92.57 393	76.79 408	75.56 407	88.23 405	61.22 403	94.48 397	71.43 404	82.92 374	89.87 409

MVS-HIRNet		82.47 372	81.21 375	86.26 389	95.38 275	69.21 416	88.96 413	89.49 411	66.28 418	80.79 390	74.08 423	68.48 371	97.39 347	71.93 403	95.47 199	92.18 394

MVStest1		82.38 373	80.04 377	89.37 372	87.63 414	82.83 350	95.03 320	93.37 384	73.90 412	73.50 411	94.35 303	62.89 399	93.25 410	73.80 396	65.92 418	92.04 396

UnsupCasMVSNet_bld		82.13 374	79.46 379	90.14 364	88.00 412	82.47 356	90.89 402	96.62 265	78.94 401	75.61 405	84.40 416	56.63 409	96.31 374	77.30 379	66.77 417	91.63 398

dmvs_testset		81.38 375	82.60 370	77.73 398	91.74 390	51.49 433	93.03 382	84.21 426	89.07 252	78.28 402	91.25 384	76.97 302	88.53 421	56.57 421	82.24 377	93.16 375

test_f		80.57 376	79.62 378	83.41 393	83.38 422	67.80 420	93.57 372	93.72 379	80.80 393	77.91 403	87.63 409	33.40 425	92.08 413	87.14 283	79.04 391	90.34 408

pmmvs3		79.97 377	77.50 382	87.39 384	82.80 423	79.38 393	92.70 387	90.75 408	70.69 415	78.66 400	87.47 411	51.34 415	93.40 407	73.39 399	69.65 411	89.38 410

APD_test1		79.31 378	77.70 381	84.14 391	89.11 406	69.07 417	92.36 392	91.50 402	69.07 416	73.87 409	92.63 362	39.93 422	94.32 399	70.54 409	80.25 384	89.02 411

N_pmnet		78.73 379	78.71 380	78.79 397	92.80 376	46.50 436	94.14 351	43.71 438	78.61 402	80.83 389	91.66 381	74.94 320	96.36 373	67.24 412	84.45 358	93.50 371

WB-MVS		76.77 380	76.63 383	77.18 399	85.32 417	56.82 431	94.53 333	89.39 412	82.66 379	71.35 412	89.18 399	75.03 319	88.88 419	35.42 428	66.79 416	85.84 413

SSC-MVS		76.05 381	75.83 384	76.72 403	84.77 418	56.22 432	94.32 345	88.96 414	81.82 385	70.52 413	88.91 400	74.79 321	88.71 420	33.69 429	64.71 419	85.23 414

test_vis3_rt		72.73 382	70.55 385	79.27 396	80.02 425	68.13 419	93.92 359	74.30 433	76.90 407	58.99 424	73.58 424	20.29 433	95.37 391	84.16 323	72.80 407	74.31 421

LCM-MVSNet		72.55 383	69.39 387	82.03 394	70.81 434	65.42 423	90.12 407	94.36 367	55.02 424	65.88 418	81.72 417	24.16 432	89.96 415	74.32 394	68.10 415	90.71 407

FPMVS		71.27 384	69.85 386	75.50 404	74.64 429	59.03 429	91.30 396	91.50 402	58.80 421	57.92 425	88.28 404	29.98 428	85.53 424	53.43 422	82.84 375	81.95 417

PMMVS2		70.19 385	66.92 389	80.01 395	76.35 428	65.67 422	86.22 418	87.58 418	64.83 420	62.38 421	80.29 420	26.78 430	88.49 422	63.79 414	54.07 425	85.88 412

dongtai		69.99 386	69.33 388	71.98 407	88.78 408	61.64 427	89.86 408	59.93 437	75.67 409	74.96 408	85.45 413	50.19 416	81.66 426	43.86 425	55.27 424	72.63 422

testf1		69.31 387	66.76 390	76.94 401	78.61 426	61.93 425	88.27 415	86.11 423	55.62 422	59.69 422	85.31 414	20.19 434	89.32 416	57.62 418	69.44 413	79.58 418

APD_test2		69.31 387	66.76 390	76.94 401	78.61 426	61.93 425	88.27 415	86.11 423	55.62 422	59.69 422	85.31 414	20.19 434	89.32 416	57.62 418	69.44 413	79.58 418

EGC-MVSNET		68.77 389	63.01 395	86.07 390	92.49 382	82.24 360	93.96 356	90.96 406	0.71 435	2.62 436	90.89 385	53.66 412	93.46 406	57.25 420	84.55 356	82.51 416

Gipuma		67.86 390	65.41 392	75.18 405	92.66 379	73.45 409	66.50 426	94.52 358	53.33 425	57.80 426	66.07 426	30.81 426	89.20 418	48.15 424	78.88 392	62.90 426
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_method		66.11 391	64.89 393	69.79 408	72.62 432	35.23 440	65.19 427	92.83 391	20.35 430	65.20 419	88.08 407	43.14 421	82.70 425	73.12 400	63.46 420	91.45 403

kuosan		65.27 392	64.66 394	67.11 410	83.80 419	61.32 428	88.53 414	60.77 436	68.22 417	67.67 415	80.52 419	49.12 417	70.76 432	29.67 431	53.64 426	69.26 424

ANet_high		63.94 393	59.58 396	77.02 400	61.24 436	66.06 421	85.66 420	87.93 417	78.53 403	42.94 428	71.04 425	25.42 431	80.71 427	52.60 423	30.83 429	84.28 415

PMVS	53.92 22	58.58 394	55.40 397	68.12 409	51.00 437	48.64 434	78.86 423	87.10 420	46.77 426	35.84 432	74.28 422	8.76 436	86.34 423	42.07 426	73.91 404	69.38 423
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		53.28 395	52.56 399	55.43 412	74.43 430	47.13 435	83.63 422	76.30 430	42.23 427	42.59 429	62.22 428	28.57 429	74.40 429	31.53 430	31.51 428	44.78 427

MVE	50.73 23	53.25 396	48.81 401	66.58 411	65.34 435	57.50 430	72.49 425	70.94 434	40.15 429	39.28 431	63.51 427	6.89 438	73.48 431	38.29 427	42.38 427	68.76 425
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		52.08 397	51.31 400	54.39 413	72.62 432	45.39 437	83.84 421	75.51 432	41.13 428	40.77 430	59.65 429	30.08 427	73.60 430	28.31 432	29.90 430	44.18 428

tmp_tt		51.94 398	53.82 398	46.29 414	33.73 438	45.30 438	78.32 424	67.24 435	18.02 431	50.93 427	87.05 412	52.99 413	53.11 433	70.76 407	25.29 431	40.46 429

wuyk23d		25.11 399	24.57 403	26.74 415	73.98 431	39.89 439	57.88 428	9.80 439	12.27 432	10.39 433	6.97 435	7.03 437	36.44 434	25.43 433	17.39 432	3.89 432

cdsmvs_eth3d_5k		23.24 400	30.99 402	0.00 418	0.00 441	0.00 443	0.00 429	97.63 153	0.00 436	0.00 437	96.88 168	84.38 170	0.00 437	0.00 436	0.00 435	0.00 433

testmvs		13.36 401	16.33 404	4.48 417	5.04 439	2.26 442	93.18 376	3.28 440	2.70 433	8.24 434	21.66 431	2.29 440	2.19 435	7.58 434	2.96 433	9.00 431

test123		13.04 402	15.66 405	5.18 416	4.51 440	3.45 441	92.50 390	1.81 441	2.50 434	7.58 435	20.15 432	3.67 439	2.18 436	7.13 435	1.07 434	9.90 430

ab-mvs-re		8.06 403	10.74 406	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	96.69 178	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

pcd_1.5k_mvsjas		7.39 404	9.85 407	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	88.65 102	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						79.53 389								75.56 388

FOURS1					99.55 1	93.34 67	99.29 1	98.35 32	94.98 37	98.49 29

MSC_two_6792asdad				98.86 1	98.67 61	96.94 1		97.93 113					99.86 9	97.68 26	99.67 6	99.77 2

PC_three_1452									90.77 195	98.89 20	98.28 74	96.24 1	98.35 239	95.76 90	99.58 23	99.59 25

No_MVS				98.86 1	98.67 61	96.94 1		97.93 113					99.86 9	97.68 26	99.67 6	99.77 2

test_one_0601					99.32 22	95.20 20		98.25 50	95.13 31	98.48 30	98.87 24	95.16 7

eth-test2					0.00 441

eth-test					0.00 441

ZD-MVS					99.05 39	94.59 32		98.08 82	89.22 248	97.03 69	98.10 82	92.52 39	99.65 67	94.58 127	99.31 66

RE-MVS-def			96.72 51		99.02 42	92.34 98	97.98 63	98.03 99	93.52 100	97.43 55	98.51 44	90.71 76		96.05 78	99.26 70	99.43 55

IU-MVS					99.42 7	95.39 11		97.94 112	90.40 216	98.94 13				97.41 41	99.66 10	99.74 8

OPU-MVS				98.55 3	98.82 55	96.86 3	98.25 35				98.26 75	96.04 2	99.24 134	95.36 104	99.59 19	99.56 32

test_241102_TWO								98.27 44	95.13 31	98.93 14	98.89 21	94.99 11	99.85 18	97.52 34	99.65 13	99.74 8

test_241102_ONE					99.42 7	95.30 17		98.27 44	95.09 34	99.19 7	98.81 30	95.54 5	99.65 67

9.14			96.75 50		98.93 50		97.73 101	98.23 55	91.28 179	97.88 43	98.44 52	93.00 26	99.65 67	95.76 90	99.47 40

save fliter					98.91 52	94.28 38	97.02 186	98.02 102	95.35 24

test_0728_THIRD									94.78 49	98.73 24	98.87 24	95.87 4	99.84 23	97.45 38	99.72 2	99.77 2

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 42	98.28 41					99.86 9	97.52 34	99.67 6	99.75 6

test0726					99.45 3	95.36 13	98.31 27	98.29 39	94.92 40	98.99 12	98.92 17	95.08 8

GSMVS																98.45 152

test_part2					99.28 25	95.74 8				98.10 36

sam_mvs1												82.76 205				98.45 152

sam_mvs												81.94 224

ambc				86.56 388	83.60 421	70.00 415	85.69 419	94.97 341		80.60 392	88.45 402	37.42 423	96.84 367	82.69 342	75.44 401	92.86 379

MTGPA								98.08 82

test_post1							92.81 386				16.58 434	80.53 245	97.68 320	86.20 294

test_post											17.58 433	81.76 226	98.08 266

patchmatchnet-post											90.45 389	82.65 209	98.10 261

GG-mvs-BLEND				93.62 266	93.69 353	89.20 222	92.39 391	83.33 427		87.98 322	89.84 395	71.00 346	96.87 366	82.08 346	95.40 201	94.80 340

MTMP							97.86 82	82.03 428

gm-plane-assit					93.22 367	78.89 397			84.82 355		93.52 344		98.64 212	87.72 262

test9_res														94.81 119	99.38 59	99.45 51

TEST9					98.70 59	94.19 42	96.41 240	98.02 102	88.17 285	96.03 110	97.56 132	92.74 33	99.59 83

test_8					98.67 61	94.06 49	96.37 247	98.01 105	88.58 272	95.98 114	97.55 134	92.73 34	99.58 86

agg_prior2														93.94 137	99.38 59	99.50 44

agg_prior					98.67 61	93.79 55		98.00 106		95.68 124			99.57 93

TestCases				93.98 244	97.94 119	86.64 287		95.54 315	85.38 344	85.49 358	96.77 172	70.28 352	99.15 148	80.02 363	92.87 247	96.15 262

test_prior4						93.66 58	96.42 239

test_prior2							96.35 248		92.80 134	96.03 110	97.59 129	92.01 47		95.01 112	99.38 59

test_prior				97.23 64	98.67 61	92.99 79		98.00 106					99.41 118			99.29 67

旧先验2							95.94 273		81.66 386	97.34 58			98.82 189	92.26 166

新几何2							95.79 282

新几何1				97.32 57	98.60 68	93.59 59		97.75 136	81.58 387	95.75 121	97.85 105	90.04 83	99.67 65	86.50 290	99.13 85	98.69 130

旧先验1					98.38 81	93.38 64		97.75 136			98.09 84	92.30 45			99.01 95	99.16 77

无先验							95.79 282	97.87 120	83.87 367				99.65 67	87.68 268		98.89 114

原ACMM2							95.67 287

原ACMM1				96.38 108	98.59 69	91.09 153		97.89 116	87.41 310	95.22 135	97.68 118	90.25 80	99.54 98	87.95 258	99.12 87	98.49 147

test222					98.24 90	92.21 104	95.33 306	97.60 155	79.22 400	95.25 133	97.84 107	88.80 99			99.15 83	98.72 127

testdata2													99.67 65	85.96 302

segment_acmp												92.89 30

testdata				95.46 171	98.18 100	88.90 230		97.66 147	82.73 378	97.03 69	98.07 85	90.06 82	98.85 187	89.67 222	98.98 96	98.64 133

testdata1							95.26 313		93.10 120

test12				97.65 43	98.46 73	94.26 39		97.66 147		95.52 131		90.89 73	99.46 112		99.25 72	99.22 74

plane_prior7					96.21 234	89.98 189

plane_prior6					96.10 245	90.00 185						81.32 232

plane_prior5								97.51 168					98.60 216	93.02 159	92.23 258	95.86 270

plane_prior4											96.64 181

plane_prior3						90.00 185			94.46 65	91.34 228

plane_prior2							97.74 99		94.85 42

plane_prior1					96.14 242

plane_prior						89.99 187	97.24 167		94.06 77						92.16 262

n2								0.00 442

nn								0.00 442

door-mid								91.06 405

lessismore_v0				90.45 359	91.96 389	79.09 396		87.19 419		80.32 394	94.39 300	66.31 386	97.55 332	84.00 327	76.84 395	94.70 347

LGP-MVS_train				94.10 237	96.16 239	88.26 247		97.46 177	91.29 176	90.12 258	97.16 153	79.05 273	98.73 202	92.25 168	91.89 266	95.31 306

test11								97.88 118

door								91.13 404

HQP5-MVS						89.33 215

HQP-NCC					95.86 251		96.65 222		93.55 94	90.14 252

ACMP_Plane					95.86 251		96.65 222		93.55 94	90.14 252

BP-MVS														92.13 172

HQP4-MVS										90.14 252			98.50 224			95.78 278

HQP3-MVS								97.39 193							92.10 263

HQP2-MVS												80.95 236

NP-MVS					95.99 249	89.81 195					95.87 223

MDTV_nov1_ep13_2view						70.35 414	93.10 381		83.88 366	93.55 171		82.47 213		86.25 293		98.38 160

MDTV_nov1_ep13			90.76 245		95.22 291	80.33 378	93.03 382	95.28 326	88.14 288	92.84 192	93.83 329	81.34 231	98.08 266	82.86 336	94.34 221

ACMMP++_ref															90.30 292

ACMMP++															91.02 281

Test By Simon												88.73 101

ITE_SJBPF				92.43 308	95.34 280	85.37 315		95.92 292	91.47 169	87.75 325	96.39 199	71.00 346	97.96 289	82.36 344	89.86 295	93.97 366

DeepMVS_CX				74.68 406	90.84 395	64.34 424		81.61 429	65.34 419	67.47 417	88.01 408	48.60 418	80.13 428	62.33 416	73.68 405	79.58 418

High-resolution multi-view benchmark