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 58	99.43 60	97.48 86	98.88 123	99.30 14	98.47 17	99.85 10	99.43 42	96.71 17	99.96 4	99.86 1	99.80 24	99.89 6

SED-MVS		99.09 1	98.91 4	99.63 4	99.71 21	99.24 5	99.02 81	98.87 82	97.65 38	99.73 21	99.48 32	97.53 7	99.94 13	98.43 66	99.81 15	99.70 64

DVP-MVS++		99.08 3	98.89 5	99.64 3	99.17 107	99.23 7	99.69 1	98.88 75	97.32 62	99.53 36	99.47 34	97.81 3	99.94 13	98.47 62	99.72 64	99.74 47

fmvsm_l_conf0.5_n		99.07 4	99.05 2	99.14 54	99.41 62	97.54 84	98.89 116	99.31 13	98.49 16	99.86 7	99.42 43	96.45 25	99.96 4	99.86 1	99.74 55	99.90 5

DVP-MVS		99.03 5	98.83 9	99.63 4	99.72 14	99.25 2	98.97 92	98.58 173	97.62 40	99.45 38	99.46 39	97.42 9	99.94 13	98.47 62	99.81 15	99.69 67
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 36	98.96 16	99.39 11	98.93 62	97.38 59	99.41 41	99.54 19	96.66 18	99.84 84	98.86 38	99.85 6	99.87 10
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
lecture		98.95 7	98.78 12	99.45 16	99.75 3	98.63 27	99.43 10	99.38 8	97.60 43	99.58 32	99.47 34	95.36 62	99.93 33	98.87 37	99.57 96	99.78 30

reproduce_model		98.94 8	98.81 10	99.34 28	99.52 42	98.26 51	98.94 101	98.84 92	98.06 24	99.35 45	99.61 4	96.39 28	99.94 13	98.77 41	99.82 14	99.83 17

reproduce-ours		98.93 9	98.78 12	99.38 20	99.49 49	98.38 37	98.86 130	98.83 94	98.06 24	99.29 49	99.58 15	96.40 26	99.94 13	98.68 44	99.81 15	99.81 23

our_new_method		98.93 9	98.78 12	99.38 20	99.49 49	98.38 37	98.86 130	98.83 94	98.06 24	99.29 49	99.58 15	96.40 26	99.94 13	98.68 44	99.81 15	99.81 23

test_fmvsmconf_n		98.92 11	98.87 6	99.04 64	98.88 143	97.25 108	98.82 143	99.34 11	98.75 10	99.80 13	99.61 4	95.16 75	99.95 9	99.70 16	99.80 24	99.93 1

DPE-MVS		98.92 11	98.67 18	99.65 2	99.58 34	99.20 9	98.42 251	98.91 69	97.58 44	99.54 35	99.46 39	97.10 12	99.94 13	97.64 115	99.84 11	99.83 17
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
fmvsm_l_conf0.5_n_9		98.90 13	98.79 11	99.24 42	99.34 67	97.83 75	98.70 184	99.26 16	98.85 5	99.92 1	99.51 25	93.91 104	99.95 9	99.86 1	99.79 31	99.92 2

fmvsm_l_conf0.5_n_3		98.90 13	98.74 16	99.37 24	99.36 64	98.25 52	98.89 116	99.24 20	98.77 9	99.89 3	99.59 12	93.39 110	99.96 4	99.78 9	99.76 44	99.89 6

SteuartSystems-ACMMP		98.90 13	98.75 15	99.36 26	99.22 102	98.43 35	99.10 65	98.87 82	97.38 59	99.35 45	99.40 46	97.78 5	99.87 75	97.77 103	99.85 6	99.78 30
Skip Steuart: Steuart Systems R&D Blog.
test_fmvsm_n_1920		98.87 16	99.01 3	98.45 119	99.42 61	96.43 151	98.96 97	99.36 10	98.63 12	99.86 7	99.51 25	95.91 44	99.97 1	99.72 13	99.75 51	98.94 219

MED-MVS		98.83 17	98.60 22	99.52 12	99.58 34	98.86 21	98.69 187	98.93 62	97.00 88	99.17 58	99.35 59	96.62 21	99.90 60	98.30 73	99.80 24	99.79 27

TSAR-MVS + MP.		98.78 18	98.62 20	99.24 42	99.69 26	98.28 50	99.14 56	98.66 150	96.84 94	99.56 33	99.31 67	96.34 29	99.70 138	98.32 72	99.73 59	99.73 52
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 18	98.56 25	99.45 16	99.32 73	98.87 19	98.47 239	98.81 103	97.72 33	98.76 91	99.16 98	97.05 13	99.78 120	98.06 85	99.66 75	99.69 67

MSP-MVS		98.74 20	98.55 26	99.29 35	99.75 3	98.23 53	99.26 29	98.88 75	97.52 47	99.41 41	98.78 174	96.00 40	99.79 117	97.79 102	99.59 92	99.85 14
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
fmvsm_s_conf0.5_n_8		98.73 21	98.62 20	99.05 63	99.35 66	97.27 102	98.80 152	99.23 25	98.93 3	99.79 14	99.59 12	92.34 127	99.95 9	99.82 6	99.71 66	99.92 2

XVS		98.70 22	98.49 33	99.34 28	99.70 24	98.35 46	99.29 24	98.88 75	97.40 56	98.46 114	99.20 88	95.90 46	99.89 64	97.85 98	99.74 55	99.78 30

fmvsm_s_conf0.5_n_10		98.66 23	98.54 28	99.02 65	99.36 64	97.21 111	98.86 130	99.23 25	98.90 4	99.83 11	99.59 12	91.57 156	99.94 13	99.79 8	99.74 55	99.89 6

fmvsm_s_conf0.5_n_6		98.65 24	98.55 26	98.95 74	98.50 183	97.30 98	98.79 160	99.16 37	98.14 22	99.86 7	99.41 45	93.71 107	99.91 52	99.71 14	99.64 83	99.65 80

MCST-MVS		98.65 24	98.37 42	99.48 14	99.60 33	98.87 19	98.41 252	98.68 142	97.04 85	98.52 112	98.80 168	96.78 16	99.83 86	97.93 92	99.61 88	99.74 47

SD-MVS		98.64 26	98.68 17	98.53 108	99.33 70	98.36 45	98.90 112	98.85 91	97.28 66	99.72 24	99.39 47	96.63 20	97.60 411	98.17 80	99.85 6	99.64 83
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
fmvsm_s_conf0.5_n_9		98.63 27	98.66 19	98.54 105	99.40 63	95.83 193	98.79 160	99.17 35	98.94 2	99.92 1	99.61 4	92.49 122	99.93 33	99.86 1	99.76 44	99.86 11

HFP-MVS		98.63 27	98.40 39	99.32 34	99.72 14	98.29 49	99.23 34	98.96 57	96.10 134	98.94 73	99.17 95	96.06 37	99.92 42	97.62 116	99.78 36	99.75 45

ACMMP_NAP		98.61 29	98.30 57	99.55 9	99.62 32	98.95 17	98.82 143	98.81 103	95.80 148	99.16 62	99.47 34	95.37 61	99.92 42	97.89 96	99.75 51	99.79 27

region2R		98.61 29	98.38 41	99.29 35	99.74 9	98.16 59	99.23 34	98.93 62	96.15 130	98.94 73	99.17 95	95.91 44	99.94 13	97.55 124	99.79 31	99.78 30

NCCC		98.61 29	98.35 45	99.38 20	99.28 88	98.61 28	98.45 241	98.76 121	97.82 32	98.45 117	98.93 146	96.65 19	99.83 86	97.38 141	99.41 125	99.71 60

SF-MVS		98.59 32	98.32 56	99.41 19	99.54 38	98.71 23	99.04 75	98.81 103	95.12 193	99.32 48	99.39 47	96.22 31	99.84 84	97.72 106	99.73 59	99.67 76

ACMMPR		98.59 32	98.36 43	99.29 35	99.74 9	98.15 60	99.23 34	98.95 58	96.10 134	98.93 77	99.19 93	95.70 50	99.94 13	97.62 116	99.79 31	99.78 30

test_fmvsmconf0.1_n		98.58 34	98.44 37	98.99 67	97.73 288	97.15 114	98.84 139	98.97 54	98.75 10	99.43 40	99.54 19	93.29 112	99.93 33	99.64 19	99.79 31	99.89 6

SMA-MVS		98.58 34	98.25 60	99.56 8	99.51 43	99.04 15	98.95 98	98.80 110	93.67 287	99.37 44	99.52 22	96.52 23	99.89 64	98.06 85	99.81 15	99.76 44
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 34	98.29 58	99.46 15	99.76 2	98.64 26	98.90 112	98.74 125	97.27 70	98.02 142	99.39 47	94.81 85	99.96 4	97.91 94	99.79 31	99.77 37

HPM-MVS++		98.58 34	98.25 60	99.55 9	99.50 45	99.08 11	98.72 179	98.66 150	97.51 48	98.15 128	98.83 165	95.70 50	99.92 42	97.53 126	99.67 72	99.66 79

SR-MVS		98.57 38	98.35 45	99.24 42	99.53 39	98.18 57	99.09 66	98.82 97	96.58 110	99.10 64	99.32 65	95.39 59	99.82 93	97.70 111	99.63 85	99.72 56

CP-MVS		98.57 38	98.36 43	99.19 47	99.66 28	97.86 71	99.34 17	98.87 82	95.96 140	98.60 108	99.13 103	96.05 38	99.94 13	97.77 103	99.86 2	99.77 37

MSLP-MVS++		98.56 40	98.57 24	98.55 103	99.26 91	96.80 129	98.71 180	99.05 47	97.28 66	98.84 83	99.28 72	96.47 24	99.40 202	98.52 60	99.70 68	99.47 112

DeepC-MVS_fast	96.70 1	98.55 41	98.34 51	99.18 49	99.25 92	98.04 65	98.50 234	98.78 117	97.72 33	98.92 79	99.28 72	95.27 68	99.82 93	97.55 124	99.77 38	99.69 67
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 42	98.35 45	99.13 55	99.49 49	97.86 71	99.11 62	98.80 110	96.49 114	99.17 58	99.35 59	95.34 64	99.82 93	97.72 106	99.65 78	99.71 60

fmvsm_s_conf0.5_n_5		98.53 43	98.35 45	99.08 60	99.07 122	97.46 90	98.68 190	99.20 31	97.50 49	99.87 4	99.50 28	91.96 146	99.96 4	99.76 10	99.65 78	99.82 21

fmvsm_s_conf0.5_n_3		98.53 43	98.45 36	98.79 82	99.23 100	97.32 95	98.80 152	99.26 16	98.82 6	99.87 4	99.60 9	90.95 187	99.93 33	99.76 10	99.73 59	99.12 189

APD-MVS_3200maxsize		98.53 43	98.33 55	99.15 53	99.50 45	97.92 70	99.15 53	98.81 103	96.24 126	99.20 55	99.37 53	95.30 66	99.80 105	97.73 105	99.67 72	99.72 56

MM		98.51 46	98.24 62	99.33 32	99.12 116	98.14 62	98.93 107	97.02 397	98.96 1	99.17 58	99.47 34	91.97 145	99.94 13	99.85 5	99.69 69	99.91 4

mPP-MVS		98.51 46	98.26 59	99.25 41	99.75 3	98.04 65	99.28 26	98.81 103	96.24 126	98.35 124	99.23 82	95.46 56	99.94 13	97.42 136	99.81 15	99.77 37

ZNCC-MVS		98.49 48	98.20 68	99.35 27	99.73 13	98.39 36	99.19 46	98.86 88	95.77 150	98.31 127	99.10 110	95.46 56	99.93 33	97.57 123	99.81 15	99.74 47

SPE-MVS-test		98.49 48	98.50 31	98.46 118	99.20 105	97.05 119	99.64 4	98.50 195	97.45 55	98.88 80	99.14 102	95.25 70	99.15 243	98.83 39	99.56 104	99.20 173

PGM-MVS		98.49 48	98.23 64	99.27 40	99.72 14	98.08 64	98.99 88	99.49 5	95.43 170	99.03 65	99.32 65	95.56 53	99.94 13	96.80 174	99.77 38	99.78 30

EI-MVSNet-Vis-set		98.47 51	98.39 40	98.69 90	99.46 55	96.49 148	98.30 265	98.69 139	97.21 73	98.84 83	99.36 57	95.41 58	99.78 120	98.62 48	99.65 78	99.80 26

MVS_111021_HR		98.47 51	98.34 51	98.88 79	99.22 102	97.32 95	97.91 322	99.58 3	97.20 74	98.33 125	99.00 134	95.99 41	99.64 152	98.05 87	99.76 44	99.69 67

balanced_conf03		98.45 53	98.35 45	98.74 86	98.65 172	97.55 82	99.19 46	98.60 161	96.72 104	99.35 45	98.77 177	95.06 80	99.55 175	98.95 34	99.87 1	99.12 189

test_fmvsmvis_n_1920		98.44 54	98.51 29	98.23 140	98.33 211	96.15 165	98.97 92	99.15 39	98.55 15	98.45 117	99.55 17	94.26 98	99.97 1	99.65 17	99.66 75	98.57 264

CS-MVS		98.44 54	98.49 33	98.31 132	99.08 121	96.73 133	99.67 3	98.47 202	97.17 77	98.94 73	99.10 110	95.73 49	99.13 248	98.71 43	99.49 115	99.09 197

GST-MVS		98.43 56	98.12 72	99.34 28	99.72 14	98.38 37	99.09 66	98.82 97	95.71 154	98.73 94	99.06 125	95.27 68	99.93 33	97.07 151	99.63 85	99.72 56

fmvsm_s_conf0.5_n		98.42 57	98.51 29	98.13 153	99.30 79	95.25 223	98.85 135	99.39 7	97.94 28	99.74 20	99.62 3	92.59 121	99.91 52	99.65 17	99.52 110	99.25 166

EI-MVSNet-UG-set		98.41 58	98.34 51	98.61 97	99.45 58	96.32 158	98.28 268	98.68 142	97.17 77	98.74 92	99.37 53	95.25 70	99.79 117	98.57 51	99.54 107	99.73 52

DELS-MVS		98.40 59	98.20 68	98.99 67	99.00 130	97.66 77	97.75 343	98.89 72	97.71 35	98.33 125	98.97 136	94.97 82	99.88 73	98.42 68	99.76 44	99.42 125
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 60	98.42 38	98.27 134	99.09 120	95.41 213	98.86 130	99.37 9	97.69 37	99.78 16	99.61 4	92.38 125	99.91 52	99.58 22	99.43 123	99.49 108

TSAR-MVS + GP.		98.38 60	98.24 62	98.81 81	99.22 102	97.25 108	98.11 297	98.29 257	97.19 75	98.99 71	99.02 128	96.22 31	99.67 145	98.52 60	98.56 179	99.51 101

HPM-MVS_fast		98.38 60	98.13 71	99.12 57	99.75 3	97.86 71	99.44 9	98.82 97	94.46 241	98.94 73	99.20 88	95.16 75	99.74 130	97.58 119	99.85 6	99.77 37

patch_mono-2		98.36 63	98.87 6	96.82 261	99.53 39	90.68 374	98.64 201	99.29 15	97.88 29	99.19 57	99.52 22	96.80 15	99.97 1	99.11 30	99.86 2	99.82 21

HPM-MVS		98.36 63	98.10 75	99.13 55	99.74 9	97.82 76	99.53 6	98.80 110	94.63 228	98.61 107	98.97 136	95.13 77	99.77 125	97.65 114	99.83 13	99.79 27
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 65	98.50 31	97.90 176	99.16 111	95.08 232	98.75 165	99.24 20	98.39 18	99.81 12	99.52 22	92.35 126	99.90 60	99.74 12	99.51 112	98.71 245

APD-MVS		98.35 65	98.00 81	99.42 18	99.51 43	98.72 22	98.80 152	98.82 97	94.52 236	99.23 54	99.25 81	95.54 55	99.80 105	96.52 183	99.77 38	99.74 47
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_LR		98.34 67	98.23 64	98.67 92	99.27 89	96.90 125	97.95 315	99.58 3	97.14 80	98.44 119	99.01 132	95.03 81	99.62 159	97.91 94	99.75 51	99.50 103

PHI-MVS		98.34 67	98.06 76	99.18 49	99.15 114	98.12 63	99.04 75	99.09 42	93.32 303	98.83 86	99.10 110	96.54 22	99.83 86	97.70 111	99.76 44	99.59 91

MP-MVS		98.33 69	98.01 80	99.28 38	99.75 3	98.18 57	99.22 38	98.79 115	96.13 131	97.92 154	99.23 82	94.54 88	99.94 13	96.74 177	99.78 36	99.73 52
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MVSMamba_PlusPlus		98.31 70	98.19 70	98.67 92	98.96 137	97.36 93	99.24 32	98.57 175	94.81 216	98.99 71	98.90 152	95.22 73	99.59 162	99.15 29	99.84 11	99.07 205

MP-MVS-pluss		98.31 70	97.92 83	99.49 13	99.72 14	98.88 18	98.43 248	98.78 117	94.10 252	97.69 173	99.42 43	95.25 70	99.92 42	98.09 84	99.80 24	99.67 76
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.5_n_2		98.30 72	98.21 66	98.57 100	99.25 92	97.11 116	98.66 197	99.20 31	98.82 6	99.79 14	99.60 9	89.38 227	99.92 42	99.80 7	99.38 130	98.69 247

fmvsm_s_conf0.5_n_7		98.23 73	98.35 45	97.89 178	98.86 147	94.99 238	98.58 213	99.00 50	98.29 19	99.73 21	99.60 9	91.70 151	99.92 42	99.63 20	99.73 59	98.76 239

MGCNet		98.23 73	97.91 84	99.21 46	98.06 251	97.96 69	98.58 213	95.51 436	98.58 13	98.87 81	99.26 76	92.99 116	99.95 9	99.62 21	99.67 72	99.73 52

ACMMP		98.23 73	97.95 82	99.09 59	99.74 9	97.62 80	99.03 78	99.41 6	95.98 139	97.60 185	99.36 57	94.45 93	99.93 33	97.14 148	98.85 163	99.70 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
EC-MVSNet		98.21 76	98.11 73	98.49 115	98.34 208	97.26 107	99.61 5	98.43 215	96.78 97	98.87 81	98.84 161	93.72 106	99.01 272	98.91 36	99.50 113	99.19 177

fmvsm_s_conf0.1_n		98.18 77	98.21 66	98.11 157	98.54 181	95.24 224	98.87 126	99.24 20	97.50 49	99.70 25	99.67 1	91.33 168	99.89 64	99.47 24	99.54 107	99.21 172

fmvsm_s_conf0.1_n_2		98.14 78	98.02 79	98.53 108	98.88 143	97.07 118	98.69 187	98.82 97	98.78 8	99.77 17	99.61 4	88.83 247	99.91 52	99.71 14	99.07 146	98.61 257

fmvsm_s_conf0.1_n_a		98.08 79	98.04 78	98.21 141	97.66 294	95.39 214	98.89 116	99.17 35	97.24 71	99.76 19	99.67 1	91.13 178	99.88 73	99.39 25	99.41 125	99.35 137

dcpmvs_2		98.08 79	98.59 23	96.56 290	99.57 36	90.34 386	99.15 53	98.38 231	96.82 96	99.29 49	99.49 31	95.78 48	99.57 165	98.94 35	99.86 2	99.77 37

NormalMVS		98.07 81	97.90 85	98.59 99	99.75 3	96.60 139	98.94 101	98.60 161	97.86 30	98.71 97	99.08 120	91.22 174	99.80 105	97.40 138	99.57 96	99.37 132

CANet		98.05 82	97.76 88	98.90 78	98.73 157	97.27 102	98.35 255	98.78 117	97.37 61	97.72 170	98.96 141	91.53 161	99.92 42	98.79 40	99.65 78	99.51 101

train_agg		97.97 83	97.52 101	99.33 32	99.31 75	98.50 31	97.92 320	98.73 128	92.98 319	97.74 167	98.68 190	96.20 33	99.80 105	96.59 178	99.57 96	99.68 72

ETV-MVS		97.96 84	97.81 86	98.40 127	98.42 193	97.27 102	98.73 175	98.55 180	96.84 94	98.38 121	97.44 312	95.39 59	99.35 207	97.62 116	98.89 157	98.58 263

UA-Net		97.96 84	97.62 92	98.98 69	98.86 147	97.47 88	98.89 116	99.08 43	96.67 107	98.72 96	99.54 19	93.15 114	99.81 98	94.87 241	98.83 164	99.65 80

CDPH-MVS		97.94 86	97.49 103	99.28 38	99.47 53	98.44 33	97.91 322	98.67 147	92.57 335	98.77 90	98.85 160	95.93 43	99.72 132	95.56 219	99.69 69	99.68 72

DeepPCF-MVS	96.37 2	97.93 87	98.48 35	96.30 316	99.00 130	89.54 402	97.43 365	98.87 82	98.16 21	99.26 53	99.38 52	96.12 36	99.64 152	98.30 73	99.77 38	99.72 56

DeepC-MVS	95.98 3	97.88 88	97.58 94	98.77 84	99.25 92	96.93 123	98.83 141	98.75 123	96.96 90	96.89 217	99.50 28	90.46 197	99.87 75	97.84 100	99.76 44	99.52 98
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 89	97.54 100	98.83 80	95.48 417	96.83 128	98.95 98	98.60 161	98.58 13	98.93 77	99.55 17	88.57 252	99.91 52	99.54 23	99.61 88	99.77 37

DP-MVS Recon		97.86 89	97.46 106	99.06 62	99.53 39	98.35 46	98.33 257	98.89 72	92.62 332	98.05 137	98.94 144	95.34 64	99.65 149	96.04 199	99.42 124	99.19 177

CSCG		97.85 91	97.74 89	98.20 143	99.67 27	95.16 227	99.22 38	99.32 12	93.04 317	97.02 210	98.92 150	95.36 62	99.91 52	97.43 135	99.64 83	99.52 98

SymmetryMVS		97.84 92	97.58 94	98.62 96	99.01 128	96.60 139	98.94 101	98.44 207	97.86 30	98.71 97	99.08 120	91.22 174	99.80 105	97.40 138	97.53 238	99.47 112

BP-MVS1		97.82 93	97.51 102	98.76 85	98.25 221	97.39 92	99.15 53	97.68 329	96.69 105	98.47 113	99.10 110	90.29 201	99.51 182	98.60 49	99.35 133	99.37 132

MG-MVS		97.81 94	97.60 93	98.44 121	99.12 116	95.97 175	97.75 343	98.78 117	96.89 93	98.46 114	99.22 84	93.90 105	99.68 144	94.81 245	99.52 110	99.67 76

VNet		97.79 95	97.40 111	98.96 72	98.88 143	97.55 82	98.63 204	98.93 62	96.74 101	99.02 66	98.84 161	90.33 200	99.83 86	98.53 54	96.66 261	99.50 103

EIA-MVS		97.75 96	97.58 94	98.27 134	98.38 199	96.44 150	99.01 83	98.60 161	95.88 144	97.26 196	97.53 306	94.97 82	99.33 210	97.38 141	99.20 142	99.05 206

PS-MVSNAJ		97.73 97	97.77 87	97.62 208	98.68 167	95.58 203	97.34 374	98.51 190	97.29 64	98.66 104	97.88 270	94.51 89	99.90 60	97.87 97	99.17 144	97.39 307

casdiffmvs_mvg		97.72 98	97.48 105	98.44 121	98.42 193	96.59 143	98.92 109	98.44 207	96.20 128	97.76 164	99.20 88	91.66 154	99.23 230	98.27 78	98.41 196	99.49 108
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 98	97.32 116	98.92 75	99.64 30	97.10 117	99.12 60	98.81 103	92.34 343	98.09 133	99.08 120	93.01 115	99.92 42	96.06 198	99.77 38	99.75 45

PVSNet_Blended_VisFu		97.70 100	97.46 106	98.44 121	99.27 89	95.91 183	98.63 204	99.16 37	94.48 240	97.67 174	98.88 156	92.80 118	99.91 52	97.11 149	99.12 145	99.50 103

mvsany_test1		97.69 101	97.70 90	97.66 204	98.24 222	94.18 281	97.53 359	97.53 350	95.52 165	99.66 27	99.51 25	94.30 96	99.56 168	98.38 69	98.62 174	99.23 168

sasdasda		97.67 102	97.23 123	98.98 69	98.70 162	98.38 37	99.34 17	98.39 227	96.76 99	97.67 174	97.40 316	92.26 131	99.49 186	98.28 75	96.28 279	99.08 201

canonicalmvs		97.67 102	97.23 123	98.98 69	98.70 162	98.38 37	99.34 17	98.39 227	96.76 99	97.67 174	97.40 316	92.26 131	99.49 186	98.28 75	96.28 279	99.08 201

xiu_mvs_v2_base		97.66 104	97.70 90	97.56 212	98.61 176	95.46 211	97.44 363	98.46 203	97.15 79	98.65 105	98.15 245	94.33 95	99.80 105	97.84 100	98.66 173	97.41 305

GDP-MVS		97.64 105	97.28 118	98.71 89	98.30 216	97.33 94	99.05 71	98.52 187	96.34 123	98.80 87	99.05 126	89.74 214	99.51 182	96.86 170	98.86 161	99.28 156

baseline		97.64 105	97.44 108	98.25 138	98.35 203	96.20 162	99.00 85	98.32 244	96.33 125	98.03 140	99.17 95	91.35 167	99.16 239	98.10 83	98.29 205	99.39 129

casdiffmvs		97.63 107	97.41 110	98.28 133	98.33 211	96.14 166	98.82 143	98.32 244	96.38 121	97.95 149	99.21 86	91.23 173	99.23 230	98.12 82	98.37 198	99.48 110
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		97.62 108	97.19 126	98.92 75	98.66 169	98.20 55	99.32 22	98.38 231	96.69 105	97.58 187	97.42 315	92.10 139	99.50 185	98.28 75	96.25 282	99.08 201

xiu_mvs_v1_base_debu		97.60 109	97.56 97	97.72 193	98.35 203	95.98 170	97.86 332	98.51 190	97.13 81	99.01 68	98.40 217	91.56 157	99.80 105	98.53 54	98.68 169	97.37 309

xiu_mvs_v1_base		97.60 109	97.56 97	97.72 193	98.35 203	95.98 170	97.86 332	98.51 190	97.13 81	99.01 68	98.40 217	91.56 157	99.80 105	98.53 54	98.68 169	97.37 309

xiu_mvs_v1_base_debi		97.60 109	97.56 97	97.72 193	98.35 203	95.98 170	97.86 332	98.51 190	97.13 81	99.01 68	98.40 217	91.56 157	99.80 105	98.53 54	98.68 169	97.37 309

diffmvs_AUTHOR		97.59 112	97.44 108	98.01 169	98.26 220	95.47 210	98.12 294	98.36 237	96.38 121	98.84 83	99.10 110	91.13 178	99.26 223	98.24 79	98.56 179	99.30 151

diffmvs		97.58 113	97.40 111	98.13 153	98.32 214	95.81 196	98.06 303	98.37 233	96.20 128	98.74 92	98.89 155	91.31 170	99.25 226	98.16 81	98.52 183	99.34 139
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
guyue		97.57 114	97.37 113	98.20 143	98.50 183	95.86 191	98.89 116	97.03 394	97.29 64	98.73 94	98.90 152	89.41 226	99.32 211	98.68 44	98.86 161	99.42 125

MVSFormer		97.57 114	97.49 103	97.84 180	98.07 248	95.76 198	99.47 7	98.40 222	94.98 205	98.79 88	98.83 165	92.34 127	98.41 346	96.91 158	99.59 92	99.34 139

alignmvs		97.56 116	97.07 133	99.01 66	98.66 169	98.37 44	98.83 141	98.06 309	96.74 101	98.00 146	97.65 293	90.80 189	99.48 191	98.37 70	96.56 265	99.19 177

DPM-MVS		97.55 117	96.99 140	99.23 45	99.04 124	98.55 29	97.17 391	98.35 238	94.85 215	97.93 153	98.58 200	95.07 79	99.71 137	92.60 319	99.34 134	99.43 122

OMC-MVS		97.55 117	97.34 115	98.20 143	99.33 70	95.92 182	98.28 268	98.59 168	95.52 165	97.97 147	99.10 110	93.28 113	99.49 186	95.09 236	98.88 158	99.19 177

viewcassd2359sk11		97.53 119	97.32 116	98.16 147	98.45 190	95.83 193	98.57 220	98.42 219	95.52 165	98.07 134	99.12 106	91.81 149	99.25 226	97.46 134	98.48 188	99.41 128

LuminaMVS		97.49 120	97.18 127	98.42 125	97.50 309	97.15 114	98.45 241	97.68 329	96.56 113	98.68 99	98.78 174	89.84 211	99.32 211	98.60 49	98.57 178	98.79 231

KinetiMVS		97.48 121	97.05 135	98.78 83	98.37 201	97.30 98	98.99 88	98.70 137	97.18 76	99.02 66	99.01 132	87.50 281	99.67 145	95.33 226	99.33 136	99.37 132

viewmanbaseed2359cas		97.47 122	97.25 120	98.14 148	98.41 195	95.84 192	98.57 220	98.43 215	95.55 163	97.97 147	99.12 106	91.26 172	99.15 243	97.42 136	98.53 182	99.43 122

PAPM_NR		97.46 123	97.11 130	98.50 113	99.50 45	96.41 153	98.63 204	98.60 161	95.18 186	97.06 208	98.06 251	94.26 98	99.57 165	93.80 287	98.87 160	99.52 98

EPP-MVSNet		97.46 123	97.28 118	97.99 171	98.64 173	95.38 215	99.33 21	98.31 248	93.61 291	97.19 200	99.07 124	94.05 101	99.23 230	96.89 162	98.43 191	99.37 132

3Dnovator	94.51 5	97.46 123	96.93 144	99.07 61	97.78 282	97.64 78	99.35 16	99.06 45	97.02 86	93.75 334	99.16 98	89.25 231	99.92 42	97.22 147	99.75 51	99.64 83

CNLPA		97.45 126	97.03 137	98.73 87	99.05 123	97.44 91	98.07 302	98.53 184	95.32 179	96.80 222	98.53 205	93.32 111	99.72 132	94.31 268	99.31 137	99.02 210

lupinMVS		97.44 127	97.22 125	98.12 156	98.07 248	95.76 198	97.68 348	97.76 326	94.50 239	98.79 88	98.61 195	92.34 127	99.30 216	97.58 119	99.59 92	99.31 147

3Dnovator+	94.38 6	97.43 128	96.78 155	99.38 20	97.83 279	98.52 30	99.37 13	98.71 133	97.09 84	92.99 364	99.13 103	89.36 228	99.89 64	96.97 154	99.57 96	99.71 60

Vis-MVSNet		97.42 129	97.11 130	98.34 130	98.66 169	96.23 161	99.22 38	99.00 50	96.63 109	98.04 139	99.21 86	88.05 268	99.35 207	96.01 201	99.21 141	99.45 119
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
API-MVS		97.41 130	97.25 120	97.91 175	98.70 162	96.80 129	98.82 143	98.69 139	94.53 234	98.11 131	98.28 232	94.50 92	99.57 165	94.12 276	99.49 115	97.37 309

sss		97.39 131	96.98 142	98.61 97	98.60 177	96.61 138	98.22 274	98.93 62	93.97 262	98.01 145	98.48 210	91.98 143	99.85 80	96.45 185	98.15 209	99.39 129

test_cas_vis1_n_1920		97.38 132	97.36 114	97.45 216	98.95 138	93.25 319	99.00 85	98.53 184	97.70 36	99.77 17	99.35 59	84.71 337	99.85 80	98.57 51	99.66 75	99.26 164

PVSNet_Blended		97.38 132	97.12 129	98.14 148	99.25 92	95.35 218	97.28 379	99.26 16	93.13 313	97.94 151	98.21 240	92.74 119	99.81 98	96.88 164	99.40 128	99.27 157

WTY-MVS		97.37 134	96.92 145	98.72 88	98.86 147	96.89 127	98.31 262	98.71 133	95.26 182	97.67 174	98.56 204	92.21 135	99.78 120	95.89 203	96.85 255	99.48 110

AstraMVS		97.34 135	97.24 122	97.65 205	98.13 242	94.15 282	98.94 101	96.25 426	97.47 53	98.60 108	99.28 72	89.67 216	99.41 201	98.73 42	98.07 213	99.38 131

viewmacassd2359aftdt		97.32 136	97.07 133	98.08 160	98.30 216	95.69 200	98.62 207	98.44 207	95.56 161	97.86 159	99.22 84	89.91 209	99.14 246	97.29 144	98.43 191	99.42 125

jason		97.32 136	97.08 132	98.06 164	97.45 315	95.59 202	97.87 330	97.91 320	94.79 218	98.55 111	98.83 165	91.12 180	99.23 230	97.58 119	99.60 90	99.34 139
jason: jason.
MVS_Test		97.28 138	97.00 138	98.13 153	98.33 211	95.97 175	98.74 169	98.07 304	94.27 247	98.44 119	98.07 250	92.48 123	99.26 223	96.43 186	98.19 208	99.16 183

EPNet		97.28 138	96.87 147	98.51 110	94.98 426	96.14 166	98.90 112	97.02 397	98.28 20	95.99 257	99.11 108	91.36 166	99.89 64	96.98 153	99.19 143	99.50 103
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SSM_0404		97.26 140	97.00 138	98.03 166	98.46 188	95.99 169	98.62 207	98.44 207	94.77 219	97.24 197	98.93 146	91.22 174	99.28 220	96.54 180	98.74 168	98.84 227

mvsmamba		97.25 141	96.99 140	98.02 168	98.34 208	95.54 207	99.18 50	97.47 356	95.04 199	98.15 128	98.57 203	89.46 223	99.31 215	97.68 113	99.01 151	99.22 170

viewdifsd2359ckpt13		97.24 142	96.97 143	98.06 164	98.43 191	95.77 197	98.59 210	98.34 241	94.81 216	97.60 185	98.94 144	90.78 193	99.09 258	96.93 157	98.33 201	99.32 146

test_yl		97.22 143	96.78 155	98.54 105	98.73 157	96.60 139	98.45 241	98.31 248	94.70 222	98.02 142	98.42 215	90.80 189	99.70 138	96.81 171	96.79 257	99.34 139

DCV-MVSNet		97.22 143	96.78 155	98.54 105	98.73 157	96.60 139	98.45 241	98.31 248	94.70 222	98.02 142	98.42 215	90.80 189	99.70 138	96.81 171	96.79 257	99.34 139

IS-MVSNet		97.22 143	96.88 146	98.25 138	98.85 150	96.36 156	99.19 46	97.97 314	95.39 173	97.23 198	98.99 135	91.11 181	98.93 284	94.60 256	98.59 176	99.47 112

viewdifsd2359ckpt07		97.20 146	97.05 135	97.65 205	98.40 197	94.33 274	98.39 253	98.43 215	95.67 156	97.66 178	99.08 120	90.04 206	99.32 211	97.47 133	98.29 205	99.31 147

PLC	95.07 4	97.20 146	96.78 155	98.44 121	99.29 84	96.31 160	98.14 291	98.76 121	92.41 341	96.39 245	98.31 230	94.92 84	99.78 120	94.06 279	98.77 167	99.23 168
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		97.18 148	97.18 127	97.20 229	98.81 153	93.27 316	95.78 436	99.15 39	95.25 183	96.79 223	98.11 248	92.29 130	99.07 261	98.56 53	99.85 6	99.25 166

SSM_0407		97.17 149	96.87 147	98.08 160	98.19 230	95.90 184	98.52 226	98.44 207	94.77 219	96.75 224	98.93 146	91.22 174	99.22 234	96.54 180	98.43 191	99.10 194

LS3D		97.16 150	96.66 164	98.68 91	98.53 182	97.19 112	98.93 107	98.90 70	92.83 326	95.99 257	99.37 53	92.12 138	99.87 75	93.67 291	99.57 96	98.97 215

AdaColmap		97.15 151	96.70 160	98.48 116	99.16 111	96.69 135	98.01 309	98.89 72	94.44 242	96.83 218	98.68 190	90.69 194	99.76 126	94.36 264	99.29 138	98.98 214

viewdifsd2359ckpt09		97.13 152	96.79 153	98.14 148	98.43 191	95.90 184	98.52 226	98.37 233	94.32 245	97.33 192	98.86 159	90.23 204	99.16 239	96.81 171	98.25 207	99.36 136

mamv4		97.13 152	98.11 73	94.17 400	98.97 136	83.70 445	98.66 197	98.71 133	94.63 228	97.83 160	98.90 152	96.25 30	99.55 175	99.27 27	99.76 44	99.27 157

Effi-MVS+		97.12 154	96.69 161	98.39 128	98.19 230	96.72 134	97.37 370	98.43 215	93.71 280	97.65 179	98.02 254	92.20 136	99.25 226	96.87 167	97.79 222	99.19 177

CHOSEN 1792x2688		97.12 154	96.80 151	98.08 160	99.30 79	94.56 263	98.05 304	99.71 1	93.57 293	97.09 204	98.91 151	88.17 262	99.89 64	96.87 167	99.56 104	99.81 23

F-COLMAP		97.09 156	96.80 151	97.97 172	99.45 58	94.95 242	98.55 224	98.62 160	93.02 318	96.17 252	98.58 200	94.01 102	99.81 98	93.95 281	98.90 156	99.14 187

RRT-MVS		97.03 157	96.78 155	97.77 189	97.90 275	94.34 272	99.12 60	98.35 238	95.87 145	98.06 136	98.70 188	86.45 300	99.63 155	98.04 88	98.54 181	99.35 137

TAMVS		97.02 158	96.79 153	97.70 196	98.06 251	95.31 221	98.52 226	98.31 248	93.95 263	97.05 209	98.61 195	93.49 109	98.52 328	95.33 226	97.81 221	99.29 154

viewmambaseed2359dif		97.01 159	96.84 149	97.51 214	98.19 230	94.21 280	98.16 287	98.23 269	93.61 291	97.78 162	99.13 103	90.79 192	99.18 238	97.24 145	98.40 197	99.15 184

CDS-MVSNet		96.99 160	96.69 161	97.90 176	98.05 253	95.98 170	98.20 277	98.33 243	93.67 287	96.95 211	98.49 209	93.54 108	98.42 339	95.24 233	97.74 225	99.31 147
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CANet_DTU		96.96 161	96.55 169	98.21 141	98.17 239	96.07 168	97.98 313	98.21 271	97.24 71	97.13 202	98.93 146	86.88 292	99.91 52	95.00 239	99.37 132	98.66 253

114514_t		96.93 162	96.27 182	98.92 75	99.50 45	97.63 79	98.85 135	98.90 70	84.80 441	97.77 163	99.11 108	92.84 117	99.66 148	94.85 242	99.77 38	99.47 112

MAR-MVS		96.91 163	96.40 176	98.45 119	98.69 165	96.90 125	98.66 197	98.68 142	92.40 342	97.07 207	97.96 261	91.54 160	99.75 128	93.68 289	98.92 155	98.69 247
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		96.90 164	96.49 173	98.14 148	99.33 70	95.56 204	97.38 368	99.65 2	92.34 343	97.61 182	98.20 241	89.29 230	99.10 257	96.97 154	97.60 230	99.77 37

Vis-MVSNet (Re-imp)		96.87 165	96.55 169	97.83 181	98.73 157	95.46 211	99.20 44	98.30 255	94.96 207	96.60 233	98.87 157	90.05 205	98.59 323	93.67 291	98.60 175	99.46 117

SDMVSNet		96.85 166	96.42 174	98.14 148	99.30 79	96.38 154	99.21 41	99.23 25	95.92 141	95.96 259	98.76 182	85.88 312	99.44 198	97.93 92	95.59 294	98.60 258

PAPR		96.84 167	96.24 184	98.65 94	98.72 161	96.92 124	97.36 372	98.57 175	93.33 302	96.67 228	97.57 302	94.30 96	99.56 168	91.05 362	98.59 176	99.47 112

HY-MVS	93.96 8	96.82 168	96.23 185	98.57 100	98.46 188	97.00 120	98.14 291	98.21 271	93.95 263	96.72 227	97.99 258	91.58 155	99.76 126	94.51 260	96.54 266	98.95 218

mamba_0408		96.81 169	96.38 177	98.09 159	98.19 230	95.90 184	95.69 437	98.32 244	94.51 237	96.75 224	98.73 184	90.99 185	99.27 222	95.83 206	98.43 191	99.10 194

UGNet		96.78 170	96.30 181	98.19 146	98.24 222	95.89 189	98.88 123	98.93 62	97.39 58	96.81 221	97.84 274	82.60 366	99.90 60	96.53 182	99.49 115	98.79 231
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
IMVS_0407		96.74 171	96.64 165	97.05 244	97.99 262	92.82 331	98.45 241	98.27 258	95.16 187	97.30 193	98.79 170	91.53 161	99.06 262	94.74 247	97.54 234	99.27 157

IMVS_0403		96.74 171	96.61 166	97.12 238	97.99 262	92.82 331	98.47 239	98.27 258	95.16 187	97.13 202	98.79 170	91.44 164	99.26 223	94.74 247	97.54 234	99.27 157

PVSNet_BlendedMVS		96.73 173	96.60 167	97.12 238	99.25 92	95.35 218	98.26 271	99.26 16	94.28 246	97.94 151	97.46 309	92.74 119	99.81 98	96.88 164	93.32 332	96.20 402

SSM_04072		96.71 174	96.38 177	97.68 199	98.19 230	95.90 184	95.69 437	98.32 244	94.51 237	96.75 224	98.73 184	90.99 185	98.02 385	95.83 206	98.43 191	99.10 194

test_vis1_n_1920		96.71 174	96.84 149	96.31 315	99.11 118	89.74 395	99.05 71	98.58 173	98.08 23	99.87 4	99.37 53	78.48 398	99.93 33	99.29 26	99.69 69	99.27 157

mvs_anonymous		96.70 176	96.53 171	97.18 232	98.19 230	93.78 292	98.31 262	98.19 275	94.01 259	94.47 291	98.27 235	92.08 141	98.46 334	97.39 140	97.91 217	99.31 147

Elysia		96.64 177	96.02 194	98.51 110	98.04 255	97.30 98	98.74 169	98.60 161	95.04 199	97.91 155	98.84 161	83.59 361	99.48 191	94.20 272	99.25 139	98.75 240

StellarMVS		96.64 177	96.02 194	98.51 110	98.04 255	97.30 98	98.74 169	98.60 161	95.04 199	97.91 155	98.84 161	83.59 361	99.48 191	94.20 272	99.25 139	98.75 240

1112_ss		96.63 179	96.00 196	98.50 113	98.56 178	96.37 155	98.18 285	98.10 297	92.92 322	94.84 279	98.43 213	92.14 137	99.58 164	94.35 265	96.51 267	99.56 97

PMMVS		96.60 180	96.33 180	97.41 220	97.90 275	93.93 288	97.35 373	98.41 220	92.84 325	97.76 164	97.45 311	91.10 182	99.20 235	96.26 191	97.91 217	99.11 192

DP-MVS		96.59 181	95.93 199	98.57 100	99.34 67	96.19 164	98.70 184	98.39 227	89.45 412	94.52 289	99.35 59	91.85 147	99.85 80	92.89 315	98.88 158	99.68 72

PatchMatch-RL		96.59 181	96.03 193	98.27 134	99.31 75	96.51 147	97.91 322	99.06 45	93.72 279	96.92 215	98.06 251	88.50 257	99.65 149	91.77 344	99.00 153	98.66 253

GeoE		96.58 183	96.07 190	98.10 158	98.35 203	95.89 189	99.34 17	98.12 291	93.12 314	96.09 253	98.87 157	89.71 215	98.97 274	92.95 311	98.08 212	99.43 122

icg_test_0407_2		96.56 184	96.50 172	96.73 267	97.99 262	92.82 331	97.18 388	98.27 258	95.16 187	97.30 193	98.79 170	91.53 161	98.10 376	94.74 247	97.54 234	99.27 157

XVG-OURS		96.55 185	96.41 175	96.99 247	98.75 156	93.76 293	97.50 362	98.52 187	95.67 156	96.83 218	99.30 70	88.95 245	99.53 178	95.88 204	96.26 281	97.69 298

FIs		96.51 186	96.12 189	97.67 201	97.13 339	97.54 84	99.36 14	99.22 30	95.89 143	94.03 320	98.35 223	91.98 143	98.44 337	96.40 187	92.76 340	97.01 317

XVG-OURS-SEG-HR		96.51 186	96.34 179	97.02 246	98.77 155	93.76 293	97.79 341	98.50 195	95.45 169	96.94 212	99.09 118	87.87 273	99.55 175	96.76 176	95.83 293	97.74 295

PS-MVSNAJss		96.43 188	96.26 183	96.92 256	95.84 406	95.08 232	99.16 52	98.50 195	95.87 145	93.84 329	98.34 227	94.51 89	98.61 319	96.88 164	93.45 327	97.06 315

test_fmvs1		96.42 189	96.67 163	95.66 345	98.82 152	88.53 422	98.80 152	98.20 273	96.39 120	99.64 29	99.20 88	80.35 386	99.67 145	99.04 32	99.57 96	98.78 235

FC-MVSNet-test		96.42 189	96.05 191	97.53 213	96.95 348	97.27 102	99.36 14	99.23 25	95.83 147	93.93 323	98.37 221	92.00 142	98.32 358	96.02 200	92.72 341	97.00 318

ab-mvs		96.42 189	95.71 210	98.55 103	98.63 174	96.75 132	97.88 329	98.74 125	93.84 269	96.54 238	98.18 243	85.34 323	99.75 128	95.93 202	96.35 271	99.15 184

FA-MVS(test-final)		96.41 192	95.94 198	97.82 183	98.21 226	95.20 226	97.80 339	97.58 340	93.21 308	97.36 191	97.70 286	89.47 221	99.56 168	94.12 276	97.99 214	98.71 245

PVSNet	91.96 18	96.35 193	96.15 186	96.96 251	99.17 107	92.05 347	96.08 429	98.68 142	93.69 283	97.75 166	97.80 280	88.86 246	99.69 143	94.26 270	99.01 151	99.15 184

Test_1112_low_res		96.34 194	95.66 215	98.36 129	98.56 178	95.94 178	97.71 346	98.07 304	92.10 352	94.79 283	97.29 324	91.75 150	99.56 168	94.17 274	96.50 268	99.58 95

viewdifsd2359ckpt11		96.30 195	96.13 187	96.81 262	98.10 245	92.10 343	98.49 237	98.40 222	96.02 136	97.61 182	99.31 67	86.37 302	99.29 218	97.52 127	93.36 331	99.04 207

viewmsd2359difaftdt		96.30 195	96.13 187	96.81 262	98.10 245	92.10 343	98.49 237	98.40 222	96.02 136	97.61 182	99.31 67	86.37 302	99.30 216	97.52 127	93.37 330	99.04 207

Effi-MVS+-dtu		96.29 197	96.56 168	95.51 350	97.89 277	90.22 387	98.80 152	98.10 297	96.57 112	96.45 243	96.66 381	90.81 188	98.91 287	95.72 213	97.99 214	97.40 306

QAPM		96.29 197	95.40 221	98.96 72	97.85 278	97.60 81	99.23 34	98.93 62	89.76 406	93.11 361	99.02 128	89.11 236	99.93 33	91.99 338	99.62 87	99.34 139

Fast-Effi-MVS+		96.28 199	95.70 212	98.03 166	98.29 218	95.97 175	98.58 213	98.25 267	91.74 360	95.29 272	97.23 329	91.03 184	99.15 243	92.90 313	97.96 216	98.97 215

nrg030		96.28 199	95.72 207	97.96 174	96.90 353	98.15 60	99.39 11	98.31 248	95.47 168	94.42 297	98.35 223	92.09 140	98.69 311	97.50 131	89.05 391	97.04 316

1314		96.25 201	95.73 206	97.79 185	97.13 339	95.55 206	98.19 280	98.59 168	93.47 297	92.03 390	97.82 278	91.33 168	99.49 186	94.62 255	98.44 189	98.32 278

sd_testset		96.17 202	95.76 205	97.42 219	99.30 79	94.34 272	98.82 143	99.08 43	95.92 141	95.96 259	98.76 182	82.83 365	99.32 211	95.56 219	95.59 294	98.60 258

h-mvs33		96.17 202	95.62 216	97.81 184	99.03 125	94.45 265	98.64 201	98.75 123	97.48 51	98.67 100	98.72 187	89.76 212	99.86 79	97.95 90	81.59 440	99.11 192

HQP_MVS		96.14 204	95.90 200	96.85 259	97.42 317	94.60 261	98.80 152	98.56 178	97.28 66	95.34 268	98.28 232	87.09 287	99.03 267	96.07 195	94.27 302	96.92 325

tttt0517		96.07 205	95.51 219	97.78 186	98.41 195	94.84 246	99.28 26	94.33 449	94.26 248	97.64 180	98.64 194	84.05 352	99.47 195	95.34 225	97.60 230	99.03 209

MVSTER		96.06 206	95.72 207	97.08 242	98.23 224	95.93 181	98.73 175	98.27 258	94.86 213	95.07 274	98.09 249	88.21 261	98.54 326	96.59 178	93.46 325	96.79 344

thisisatest0530		96.01 207	95.36 226	97.97 172	98.38 199	95.52 208	98.88 123	94.19 451	94.04 254	97.64 180	98.31 230	83.82 359	99.46 196	95.29 230	97.70 227	98.93 220

test_djsdf		96.00 208	95.69 213	96.93 253	95.72 408	95.49 209	99.47 7	98.40 222	94.98 205	94.58 287	97.86 271	89.16 234	98.41 346	96.91 158	94.12 310	96.88 334

EI-MVSNet		95.96 209	95.83 202	96.36 311	97.93 273	93.70 299	98.12 294	98.27 258	93.70 282	95.07 274	99.02 128	92.23 134	98.54 326	94.68 251	93.46 325	96.84 340

VortexMVS		95.95 210	95.79 203	96.42 307	98.29 218	93.96 287	98.68 190	98.31 248	96.02 136	94.29 305	97.57 302	89.47 221	98.37 353	97.51 130	91.93 348	96.94 323

ECVR-MVS		95.95 210	95.71 210	96.65 275	99.02 126	90.86 369	99.03 78	91.80 462	96.96 90	98.10 132	99.26 76	81.31 372	99.51 182	96.90 161	99.04 148	99.59 91

BH-untuned		95.95 210	95.72 207	96.65 275	98.55 180	92.26 339	98.23 273	97.79 325	93.73 277	94.62 286	98.01 256	88.97 244	99.00 273	93.04 308	98.51 184	98.68 249

test1111		95.94 213	95.78 204	96.41 308	98.99 133	90.12 388	99.04 75	92.45 461	96.99 89	98.03 140	99.27 75	81.40 371	99.48 191	96.87 167	99.04 148	99.63 85

MSDG		95.93 214	95.30 233	97.83 181	98.90 141	95.36 216	96.83 416	98.37 233	91.32 375	94.43 296	98.73 184	90.27 202	99.60 161	90.05 376	98.82 165	98.52 266

BH-RMVSNet		95.92 215	95.32 231	97.69 197	98.32 214	94.64 255	98.19 280	97.45 361	94.56 232	96.03 255	98.61 195	85.02 328	99.12 251	90.68 367	99.06 147	99.30 151

test_fmvs1_n		95.90 216	95.99 197	95.63 346	98.67 168	88.32 426	99.26 29	98.22 270	96.40 119	99.67 26	99.26 76	73.91 436	99.70 138	99.02 33	99.50 113	98.87 224

Fast-Effi-MVS+-dtu		95.87 217	95.85 201	95.91 332	97.74 287	91.74 353	98.69 187	98.15 287	95.56 161	94.92 277	97.68 291	88.98 243	98.79 305	93.19 303	97.78 223	97.20 313

LFMVS		95.86 218	94.98 248	98.47 117	98.87 146	96.32 158	98.84 139	96.02 427	93.40 300	98.62 106	99.20 88	74.99 429	99.63 155	97.72 106	97.20 243	99.46 117

baseline1		95.84 219	95.12 241	98.01 169	98.49 187	95.98 170	98.73 175	97.03 394	95.37 176	96.22 248	98.19 242	89.96 208	99.16 239	94.60 256	87.48 407	98.90 223

OpenMVS	93.04 13	95.83 220	95.00 246	98.32 131	97.18 336	97.32 95	99.21 41	98.97 54	89.96 402	91.14 399	99.05 126	86.64 295	99.92 42	93.38 297	99.47 118	97.73 296

IMVS_0404		95.82 221	95.52 217	96.73 267	97.99 262	92.82 331	97.23 381	98.27 258	95.16 187	94.31 303	98.79 170	85.63 316	98.10 376	94.74 247	97.54 234	99.27 157

VDD-MVS		95.82 221	95.23 235	97.61 209	98.84 151	93.98 286	98.68 190	97.40 365	95.02 203	97.95 149	99.34 64	74.37 435	99.78 120	98.64 47	96.80 256	99.08 201

UniMVSNet (Re)		95.78 223	95.19 237	97.58 210	96.99 346	97.47 88	98.79 160	99.18 34	95.60 159	93.92 324	97.04 351	91.68 152	98.48 330	95.80 210	87.66 406	96.79 344

VPA-MVSNet		95.75 224	95.11 242	97.69 197	97.24 328	97.27 102	98.94 101	99.23 25	95.13 192	95.51 266	97.32 322	85.73 314	98.91 287	97.33 143	89.55 382	96.89 333

HQP-MVS		95.72 225	95.40 221	96.69 273	97.20 332	94.25 278	98.05 304	98.46 203	96.43 116	94.45 292	97.73 283	86.75 293	98.96 278	95.30 228	94.18 306	96.86 339

hse-mvs2		95.71 226	95.30 233	96.93 253	98.50 183	93.53 304	98.36 254	98.10 297	97.48 51	98.67 100	97.99 258	89.76 212	99.02 270	97.95 90	80.91 446	98.22 281

UniMVSNet_NR-MVSNet		95.71 226	95.15 238	97.40 222	96.84 356	96.97 121	98.74 169	99.24 20	95.16 187	93.88 326	97.72 285	91.68 152	98.31 360	95.81 208	87.25 412	96.92 325

PatchmatchNet		95.71 226	95.52 217	96.29 317	97.58 300	90.72 373	96.84 415	97.52 351	94.06 253	97.08 205	96.96 361	89.24 232	98.90 290	92.03 337	98.37 198	99.26 164
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
OPM-MVS		95.69 229	95.33 230	96.76 266	96.16 392	94.63 256	98.43 248	98.39 227	96.64 108	95.02 276	98.78 174	85.15 327	99.05 263	95.21 235	94.20 305	96.60 367
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMM	93.85 9	95.69 229	95.38 225	96.61 283	97.61 297	93.84 291	98.91 111	98.44 207	95.25 183	94.28 306	98.47 211	86.04 311	99.12 251	95.50 222	93.95 315	96.87 337
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpmrst		95.63 231	95.69 213	95.44 354	97.54 305	88.54 421	96.97 401	97.56 343	93.50 295	97.52 189	96.93 365	89.49 219	99.16 239	95.25 232	96.42 270	98.64 255

FE-MVS		95.62 232	94.90 252	97.78 186	98.37 201	94.92 243	97.17 391	97.38 367	90.95 386	97.73 169	97.70 286	85.32 325	99.63 155	91.18 354	98.33 201	98.79 231

LPG-MVS_test		95.62 232	95.34 227	96.47 301	97.46 312	93.54 302	98.99 88	98.54 182	94.67 226	94.36 300	98.77 177	85.39 320	99.11 253	95.71 214	94.15 308	96.76 347

CLD-MVS		95.62 232	95.34 227	96.46 304	97.52 308	93.75 295	97.27 380	98.46 203	95.53 164	94.42 297	98.00 257	86.21 306	98.97 274	96.25 193	94.37 300	96.66 362
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		95.61 235	94.89 253	97.76 190	98.15 241	95.15 229	96.77 417	94.41 447	92.95 321	97.18 201	97.43 313	84.78 334	99.45 197	94.63 253	97.73 226	98.68 249

MonoMVSNet		95.51 236	95.45 220	95.68 343	95.54 413	90.87 368	98.92 109	97.37 368	95.79 149	95.53 265	97.38 318	89.58 218	97.68 407	96.40 187	92.59 342	98.49 268

thres600view7		95.49 237	94.77 256	97.67 201	98.98 134	95.02 234	98.85 135	96.90 404	95.38 174	96.63 230	96.90 367	84.29 344	99.59 162	88.65 400	96.33 272	98.40 272

test_vis1_n		95.47 238	95.13 239	96.49 298	97.77 283	90.41 383	99.27 28	98.11 294	96.58 110	99.66 27	99.18 94	67.00 450	99.62 159	99.21 28	99.40 128	99.44 120

SCA		95.46 239	95.13 239	96.46 304	97.67 292	91.29 361	97.33 375	97.60 339	94.68 225	96.92 215	97.10 336	83.97 354	98.89 291	92.59 321	98.32 204	99.20 173

IterMVS-LS		95.46 239	95.21 236	96.22 319	98.12 243	93.72 298	98.32 261	98.13 290	93.71 280	94.26 307	97.31 323	92.24 133	98.10 376	94.63 253	90.12 373	96.84 340
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing3-2		95.45 241	95.34 227	95.77 341	98.69 165	88.75 417	98.87 126	97.21 381	96.13 131	97.22 199	97.68 291	77.95 406	99.65 149	97.58 119	96.77 259	98.91 222

jajsoiax		95.45 241	95.03 245	96.73 267	95.42 421	94.63 256	99.14 56	98.52 187	95.74 151	93.22 354	98.36 222	83.87 357	98.65 316	96.95 156	94.04 311	96.91 330

CVMVSNet		95.43 243	96.04 192	93.57 407	97.93 273	83.62 446	98.12 294	98.59 168	95.68 155	96.56 234	99.02 128	87.51 279	97.51 416	93.56 295	97.44 239	99.60 89

anonymousdsp		95.42 244	94.91 251	96.94 252	95.10 425	95.90 184	99.14 56	98.41 220	93.75 274	93.16 357	97.46 309	87.50 281	98.41 346	95.63 218	94.03 312	96.50 386

DU-MVS		95.42 244	94.76 257	97.40 222	96.53 373	96.97 121	98.66 197	98.99 53	95.43 170	93.88 326	97.69 288	88.57 252	98.31 360	95.81 208	87.25 412	96.92 325

mvs_tets		95.41 246	95.00 246	96.65 275	95.58 412	94.42 267	99.00 85	98.55 180	95.73 153	93.21 355	98.38 220	83.45 363	98.63 317	97.09 150	94.00 313	96.91 330

thres100view900		95.38 247	94.70 261	97.41 220	98.98 134	94.92 243	98.87 126	96.90 404	95.38 174	96.61 232	96.88 368	84.29 344	99.56 168	88.11 403	96.29 276	97.76 293

thres400		95.38 247	94.62 265	97.65 205	98.94 139	94.98 239	98.68 190	96.93 402	95.33 177	96.55 236	96.53 387	84.23 348	99.56 168	88.11 403	96.29 276	98.40 272

BH-w/o		95.38 247	95.08 243	96.26 318	98.34 208	91.79 350	97.70 347	97.43 363	92.87 324	94.24 309	97.22 330	88.66 250	98.84 297	91.55 350	97.70 227	98.16 284

VDDNet		95.36 250	94.53 270	97.86 179	98.10 245	95.13 230	98.85 135	97.75 327	90.46 393	98.36 122	99.39 47	73.27 438	99.64 152	97.98 89	96.58 264	98.81 230

TAPA-MVS	93.98 7	95.35 251	94.56 269	97.74 192	99.13 115	94.83 248	98.33 257	98.64 155	86.62 429	96.29 247	98.61 195	94.00 103	99.29 218	80.00 446	99.41 125	99.09 197
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ACMP	93.49 10	95.34 252	94.98 248	96.43 306	97.67 292	93.48 306	98.73 175	98.44 207	94.94 211	92.53 377	98.53 205	84.50 343	99.14 246	95.48 223	94.00 313	96.66 362
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
COLMAP_ROB	93.27 12	95.33 253	94.87 254	96.71 270	99.29 84	93.24 320	98.58 213	98.11 294	89.92 403	93.57 339	99.10 110	86.37 302	99.79 117	90.78 365	98.10 211	97.09 314
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
UBG		95.32 254	94.72 260	97.13 236	98.05 253	93.26 317	97.87 330	97.20 382	94.96 207	96.18 251	95.66 420	80.97 378	99.35 207	94.47 262	97.08 246	98.78 235

tfpn200view9		95.32 254	94.62 265	97.43 218	98.94 139	94.98 239	98.68 190	96.93 402	95.33 177	96.55 236	96.53 387	84.23 348	99.56 168	88.11 403	96.29 276	97.76 293

Anonymous202405211		95.28 256	94.49 272	97.67 201	99.00 130	93.75 295	98.70 184	97.04 393	90.66 389	96.49 240	98.80 168	78.13 402	99.83 86	96.21 194	95.36 298	99.44 120

thres200		95.25 257	94.57 268	97.28 226	98.81 153	94.92 243	98.20 277	97.11 386	95.24 185	96.54 238	96.22 398	84.58 341	99.53 178	87.93 408	96.50 268	97.39 307

AllTest		95.24 258	94.65 264	96.99 247	99.25 92	93.21 321	98.59 210	98.18 278	91.36 371	93.52 341	98.77 177	84.67 338	99.72 132	89.70 383	97.87 219	98.02 288

LCM-MVSNet-Re		95.22 259	95.32 231	94.91 371	98.18 236	87.85 432	98.75 165	95.66 434	95.11 194	88.96 419	96.85 371	90.26 203	97.65 408	95.65 217	98.44 189	99.22 170

EPNet_dtu		95.21 260	94.95 250	95.99 327	96.17 390	90.45 381	98.16 287	97.27 376	96.77 98	93.14 360	98.33 228	90.34 199	98.42 339	85.57 421	98.81 166	99.09 197
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
XXY-MVS		95.20 261	94.45 278	97.46 215	96.75 363	96.56 145	98.86 130	98.65 154	93.30 305	93.27 353	98.27 235	84.85 332	98.87 294	94.82 244	91.26 359	96.96 320

D2MVS		95.18 262	95.08 243	95.48 351	97.10 341	92.07 346	98.30 265	99.13 41	94.02 256	92.90 365	96.73 377	89.48 220	98.73 309	94.48 261	93.60 324	95.65 416

WR-MVS		95.15 263	94.46 275	97.22 228	96.67 368	96.45 149	98.21 275	98.81 103	94.15 250	93.16 357	97.69 288	87.51 279	98.30 362	95.29 230	88.62 397	96.90 332

TranMVSNet+NR-MVSNet		95.14 264	94.48 273	97.11 240	96.45 379	96.36 156	99.03 78	99.03 48	95.04 199	93.58 338	97.93 264	88.27 260	98.03 384	94.13 275	86.90 417	96.95 322

myMVS_eth3d28		95.12 265	94.62 265	96.64 279	98.17 239	92.17 340	98.02 308	97.32 370	95.41 172	96.22 248	96.05 404	78.01 404	99.13 248	95.22 234	97.16 244	98.60 258

baseline2		95.11 266	94.52 271	96.87 258	96.65 369	93.56 301	98.27 270	94.10 453	93.45 298	92.02 391	97.43 313	87.45 284	99.19 236	93.88 284	97.41 241	97.87 291

miper_enhance_ethall		95.10 267	94.75 258	96.12 323	97.53 307	93.73 297	96.61 423	98.08 302	92.20 351	93.89 325	96.65 383	92.44 124	98.30 362	94.21 271	91.16 360	96.34 395

Anonymous20240529		95.10 267	94.22 288	97.75 191	99.01 128	94.26 277	98.87 126	98.83 94	85.79 437	96.64 229	98.97 136	78.73 395	99.85 80	96.27 190	94.89 299	99.12 189

test-LLR		95.10 267	94.87 254	95.80 338	96.77 360	89.70 397	96.91 406	95.21 439	95.11 194	94.83 281	95.72 417	87.71 275	98.97 274	93.06 306	98.50 185	98.72 242

WR-MVS_H		95.05 270	94.46 275	96.81 262	96.86 355	95.82 195	99.24 32	99.24 20	93.87 268	92.53 377	96.84 372	90.37 198	98.24 368	93.24 301	87.93 403	96.38 394

miper_ehance_all_eth		95.01 271	94.69 262	95.97 329	97.70 290	93.31 315	97.02 399	98.07 304	92.23 348	93.51 343	96.96 361	91.85 147	98.15 372	93.68 289	91.16 360	96.44 392

testing11		95.00 272	94.28 285	97.16 234	97.96 270	93.36 314	98.09 300	97.06 392	94.94 211	95.33 271	96.15 400	76.89 419	99.40 202	95.77 212	96.30 275	98.72 242

ADS-MVSNet		95.00 272	94.45 278	96.63 280	98.00 260	91.91 349	96.04 430	97.74 328	90.15 399	96.47 241	96.64 384	87.89 271	98.96 278	90.08 374	97.06 247	99.02 210

VPNet		94.99 274	94.19 290	97.40 222	97.16 337	96.57 144	98.71 180	98.97 54	95.67 156	94.84 279	98.24 239	80.36 385	98.67 315	96.46 184	87.32 411	96.96 320

EPMVS		94.99 274	94.48 273	96.52 296	97.22 330	91.75 352	97.23 381	91.66 463	94.11 251	97.28 195	96.81 374	85.70 315	98.84 297	93.04 308	97.28 242	98.97 215

testing91		94.98 276	94.25 287	97.20 229	97.94 271	93.41 309	98.00 311	97.58 340	94.99 204	95.45 267	96.04 405	77.20 414	99.42 200	94.97 240	96.02 289	98.78 235

NR-MVSNet		94.98 276	94.16 293	97.44 217	96.53 373	97.22 110	98.74 169	98.95 58	94.96 207	89.25 418	97.69 288	89.32 229	98.18 370	94.59 258	87.40 409	96.92 325

FMVSNet3		94.97 278	94.26 286	97.11 240	98.18 236	96.62 136	98.56 223	98.26 266	93.67 287	94.09 316	97.10 336	84.25 346	98.01 386	92.08 333	92.14 345	96.70 356

CostFormer		94.95 279	94.73 259	95.60 348	97.28 326	89.06 410	97.53 359	96.89 406	89.66 408	96.82 220	96.72 378	86.05 309	98.95 283	95.53 221	96.13 287	98.79 231

PAPM		94.95 279	94.00 306	97.78 186	97.04 343	95.65 201	96.03 432	98.25 267	91.23 380	94.19 312	97.80 280	91.27 171	98.86 296	82.61 438	97.61 229	98.84 227

CP-MVSNet		94.94 281	94.30 284	96.83 260	96.72 365	95.56 204	99.11 62	98.95 58	93.89 266	92.42 382	97.90 267	87.19 286	98.12 375	94.32 267	88.21 400	96.82 343

TR-MVS		94.94 281	94.20 289	97.17 233	97.75 284	94.14 283	97.59 356	97.02 397	92.28 347	95.75 263	97.64 296	83.88 356	98.96 278	89.77 380	96.15 286	98.40 272

RPSCF		94.87 283	95.40 221	93.26 413	98.89 142	82.06 452	98.33 257	98.06 309	90.30 398	96.56 234	99.26 76	87.09 287	99.49 186	93.82 286	96.32 273	98.24 279

testing99		94.83 284	94.08 298	97.07 243	97.94 271	93.13 323	98.10 299	97.17 384	94.86 213	95.34 268	96.00 409	76.31 422	99.40 202	95.08 237	95.90 290	98.68 249

GA-MVS		94.81 285	94.03 302	97.14 235	97.15 338	93.86 290	96.76 418	97.58 340	94.00 260	94.76 285	97.04 351	80.91 379	98.48 330	91.79 343	96.25 282	99.09 197

c3_l		94.79 286	94.43 280	95.89 334	97.75 284	93.12 325	97.16 393	98.03 311	92.23 348	93.46 347	97.05 350	91.39 165	98.01 386	93.58 294	89.21 389	96.53 378

V42		94.78 287	94.14 295	96.70 272	96.33 384	95.22 225	98.97 92	98.09 301	92.32 345	94.31 303	97.06 347	88.39 258	98.55 325	92.90 313	88.87 395	96.34 395

reproduce_monomvs		94.77 288	94.67 263	95.08 366	98.40 197	89.48 403	98.80 152	98.64 155	97.57 45	93.21 355	97.65 293	80.57 384	98.83 300	97.72 106	89.47 385	96.93 324

CR-MVSNet		94.76 289	94.15 294	96.59 286	97.00 344	93.43 307	94.96 445	97.56 343	92.46 336	96.93 213	96.24 394	88.15 263	97.88 399	87.38 410	96.65 262	98.46 270

v2v482		94.69 290	94.03 302	96.65 275	96.17 390	94.79 251	98.67 195	98.08 302	92.72 328	94.00 321	97.16 333	87.69 278	98.45 335	92.91 312	88.87 395	96.72 352

pmmvs4		94.69 290	93.99 308	96.81 262	95.74 407	95.94 178	97.40 366	97.67 332	90.42 395	93.37 350	97.59 300	89.08 237	98.20 369	92.97 310	91.67 353	96.30 398

cl22		94.68 292	94.19 290	96.13 322	98.11 244	93.60 300	96.94 403	98.31 248	92.43 340	93.32 352	96.87 370	86.51 296	98.28 366	94.10 278	91.16 360	96.51 384

eth_miper_zixun_eth		94.68 292	94.41 281	95.47 352	97.64 295	91.71 354	96.73 420	98.07 304	92.71 329	93.64 335	97.21 331	90.54 196	98.17 371	93.38 297	89.76 377	96.54 376

PCF-MVS	93.45 11	94.68 292	93.43 344	98.42 125	98.62 175	96.77 131	95.48 442	98.20 273	84.63 442	93.34 351	98.32 229	88.55 255	99.81 98	84.80 430	98.96 154	98.68 249
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS		94.67 295	93.54 339	98.08 160	96.88 354	96.56 145	98.19 280	98.50 195	78.05 454	92.69 372	98.02 254	91.07 183	99.63 155	90.09 373	98.36 200	98.04 287

PS-CasMVS		94.67 295	93.99 308	96.71 270	96.68 367	95.26 222	99.13 59	99.03 48	93.68 285	92.33 383	97.95 262	85.35 322	98.10 376	93.59 293	88.16 402	96.79 344

cascas		94.63 297	93.86 318	96.93 253	96.91 352	94.27 276	96.00 433	98.51 190	85.55 438	94.54 288	96.23 396	84.20 350	98.87 294	95.80 210	96.98 252	97.66 299

tpmvs		94.60 298	94.36 283	95.33 358	97.46 312	88.60 420	96.88 412	97.68 329	91.29 377	93.80 331	96.42 391	88.58 251	99.24 229	91.06 360	96.04 288	98.17 283

LTVRE_ROB	92.95 15	94.60 298	93.90 314	96.68 274	97.41 320	94.42 267	98.52 226	98.59 168	91.69 363	91.21 398	98.35 223	84.87 331	99.04 266	91.06 360	93.44 328	96.60 367
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		94.59 300	93.92 311	96.60 285	96.21 386	94.78 252	98.59 210	98.14 289	91.86 359	94.21 311	97.02 354	87.97 269	98.41 346	91.72 345	89.57 380	96.61 366

ADS-MVSNet2		94.58 301	94.40 282	95.11 364	98.00 260	88.74 418	96.04 430	97.30 372	90.15 399	96.47 241	96.64 384	87.89 271	97.56 414	90.08 374	97.06 247	99.02 210

WBMVS		94.56 302	94.04 300	96.10 324	98.03 257	93.08 327	97.82 338	98.18 278	94.02 256	93.77 333	96.82 373	81.28 373	98.34 355	95.47 224	91.00 363	96.88 334

ACMH	92.88 16	94.55 303	93.95 310	96.34 313	97.63 296	93.26 317	98.81 151	98.49 200	93.43 299	89.74 412	98.53 205	81.91 368	99.08 260	93.69 288	93.30 333	96.70 356
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		94.54 304	93.85 319	96.63 280	97.98 268	93.06 328	98.77 164	97.84 323	93.67 287	93.80 331	98.04 253	76.88 420	98.96 278	94.79 246	92.86 338	97.86 292

XVG-ACMP-BASELINE		94.54 304	94.14 295	95.75 342	96.55 372	91.65 355	98.11 297	98.44 207	94.96 207	94.22 310	97.90 267	79.18 394	99.11 253	94.05 280	93.85 317	96.48 389

AUN-MVS		94.53 306	93.73 329	96.92 256	98.50 183	93.52 305	98.34 256	98.10 297	93.83 271	95.94 261	97.98 260	85.59 318	99.03 267	94.35 265	80.94 445	98.22 281

DIV-MVS_self_test		94.52 307	94.03 302	95.99 327	97.57 304	93.38 312	97.05 397	97.94 317	91.74 360	92.81 367	97.10 336	89.12 235	98.07 382	92.60 319	90.30 370	96.53 378

cl____		94.51 308	94.01 305	96.02 326	97.58 300	93.40 311	97.05 397	97.96 316	91.73 362	92.76 369	97.08 342	89.06 238	98.13 374	92.61 318	90.29 371	96.52 381

ETVMVS		94.50 309	93.44 343	97.68 199	98.18 236	95.35 218	98.19 280	97.11 386	93.73 277	96.40 244	95.39 423	74.53 432	98.84 297	91.10 356	96.31 274	98.84 227

GBi-Net		94.49 310	93.80 322	96.56 290	98.21 226	95.00 235	98.82 143	98.18 278	92.46 336	94.09 316	97.07 343	81.16 374	97.95 391	92.08 333	92.14 345	96.72 352

test1		94.49 310	93.80 322	96.56 290	98.21 226	95.00 235	98.82 143	98.18 278	92.46 336	94.09 316	97.07 343	81.16 374	97.95 391	92.08 333	92.14 345	96.72 352

dmvs_re		94.48 312	94.18 292	95.37 356	97.68 291	90.11 389	98.54 225	97.08 388	94.56 232	94.42 297	97.24 328	84.25 346	97.76 405	91.02 363	92.83 339	98.24 279

v8		94.47 313	93.77 325	96.57 289	96.36 382	94.83 248	99.05 71	98.19 275	91.92 356	93.16 357	96.97 359	88.82 249	98.48 330	91.69 346	87.79 404	96.39 393

FMVSNet2		94.47 313	93.61 335	97.04 245	98.21 226	96.43 151	98.79 160	98.27 258	92.46 336	93.50 344	97.09 340	81.16 374	98.00 388	91.09 357	91.93 348	96.70 356

test2506		94.44 315	93.91 313	96.04 325	99.02 126	88.99 413	99.06 69	79.47 475	96.96 90	98.36 122	99.26 76	77.21 413	99.52 181	96.78 175	99.04 148	99.59 91

Patchmatch-test		94.42 316	93.68 333	96.63 280	97.60 298	91.76 351	94.83 449	97.49 355	89.45 412	94.14 314	97.10 336	88.99 240	98.83 300	85.37 424	98.13 210	99.29 154

PEN-MVS		94.42 316	93.73 329	96.49 298	96.28 385	94.84 246	99.17 51	99.00 50	93.51 294	92.23 385	97.83 277	86.10 308	97.90 395	92.55 324	86.92 416	96.74 349

v144192		94.39 318	93.70 331	96.48 300	96.06 396	94.35 271	98.58 213	98.16 286	91.45 368	94.33 302	97.02 354	87.50 281	98.45 335	91.08 359	89.11 390	96.63 364

Baseline_NR-MVSNet		94.35 319	93.81 321	95.96 330	96.20 387	94.05 285	98.61 209	96.67 416	91.44 369	93.85 328	97.60 299	88.57 252	98.14 373	94.39 263	86.93 415	95.68 415

miper_lstm_enhance		94.33 320	94.07 299	95.11 364	97.75 284	90.97 365	97.22 383	98.03 311	91.67 364	92.76 369	96.97 359	90.03 207	97.78 404	92.51 326	89.64 379	96.56 373

v1192		94.32 321	93.58 336	96.53 295	96.10 394	94.45 265	98.50 234	98.17 284	91.54 366	94.19 312	97.06 347	86.95 291	98.43 338	90.14 372	89.57 380	96.70 356

UWE-MVS		94.30 322	93.89 316	95.53 349	97.83 279	88.95 414	97.52 361	93.25 455	94.44 242	96.63 230	97.07 343	78.70 396	99.28 220	91.99 338	97.56 233	98.36 275

ACMH+	92.99 14	94.30 322	93.77 325	95.88 335	97.81 281	92.04 348	98.71 180	98.37 233	93.99 261	90.60 405	98.47 211	80.86 381	99.05 263	92.75 317	92.40 344	96.55 375

v148		94.29 324	93.76 327	95.91 332	96.10 394	92.93 329	98.58 213	97.97 314	92.59 334	93.47 346	96.95 363	88.53 256	98.32 358	92.56 323	87.06 414	96.49 387

v10		94.29 324	93.55 338	96.51 297	96.39 381	94.80 250	98.99 88	98.19 275	91.35 373	93.02 363	96.99 357	88.09 265	98.41 346	90.50 369	88.41 399	96.33 397

SD_0403		94.28 326	94.46 275	93.73 404	98.02 258	85.32 441	98.31 262	98.40 222	94.75 221	93.59 336	98.16 244	89.01 239	96.54 435	82.32 439	97.58 232	99.34 139

MVP-Stereo		94.28 326	93.92 311	95.35 357	94.95 427	92.60 336	97.97 314	97.65 333	91.61 365	90.68 404	97.09 340	86.32 305	98.42 339	89.70 383	99.34 134	95.02 429
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UniMVSNet_ETH3D		94.24 328	93.33 346	96.97 250	97.19 335	93.38 312	98.74 169	98.57 175	91.21 382	93.81 330	98.58 200	72.85 439	98.77 307	95.05 238	93.93 316	98.77 238

OurMVSNet-221017-0		94.21 329	94.00 306	94.85 376	95.60 411	89.22 408	98.89 116	97.43 363	95.29 180	92.18 387	98.52 208	82.86 364	98.59 323	93.46 296	91.76 351	96.74 349

v1921920		94.20 330	93.47 342	96.40 310	95.98 400	94.08 284	98.52 226	98.15 287	91.33 374	94.25 308	97.20 332	86.41 301	98.42 339	90.04 377	89.39 387	96.69 361

WB-MVSnew		94.19 331	94.04 300	94.66 384	96.82 358	92.14 341	97.86 332	95.96 430	93.50 295	95.64 264	96.77 376	88.06 267	97.99 389	84.87 427	96.86 253	93.85 447

v7n		94.19 331	93.43 344	96.47 301	95.90 403	94.38 270	99.26 29	98.34 241	91.99 354	92.76 369	97.13 335	88.31 259	98.52 328	89.48 388	87.70 405	96.52 381

tpm2		94.19 331	93.76 327	95.46 353	97.23 329	89.04 411	97.31 377	96.85 410	87.08 428	96.21 250	96.79 375	83.75 360	98.74 308	92.43 329	96.23 284	98.59 261

TESTMET0.1,1		94.18 334	93.69 332	95.63 346	96.92 350	89.12 409	96.91 406	94.78 444	93.17 310	94.88 278	96.45 390	78.52 397	98.92 285	93.09 305	98.50 185	98.85 225

dp		94.15 335	93.90 314	94.90 372	97.31 325	86.82 437	96.97 401	97.19 383	91.22 381	96.02 256	96.61 386	85.51 319	99.02 270	90.00 378	94.30 301	98.85 225

ET-MVSNet_ETH3D		94.13 336	92.98 354	97.58 210	98.22 225	96.20 162	97.31 377	95.37 438	94.53 234	79.56 456	97.63 298	86.51 296	97.53 415	96.91 158	90.74 365	99.02 210

tpm		94.13 336	93.80 322	95.12 363	96.50 375	87.91 431	97.44 363	95.89 433	92.62 332	96.37 246	96.30 393	84.13 351	98.30 362	93.24 301	91.66 354	99.14 187

testing222		94.12 338	93.03 353	97.37 225	98.02 258	94.66 253	97.94 318	96.65 418	94.63 228	95.78 262	95.76 412	71.49 440	98.92 285	91.17 355	95.88 291	98.52 266

IterMVS-SCA-FT		94.11 339	93.87 317	94.85 376	97.98 268	90.56 380	97.18 388	98.11 294	93.75 274	92.58 375	97.48 308	83.97 354	97.41 418	92.48 328	91.30 357	96.58 369

Anonymous20231211		94.10 340	93.26 349	96.61 283	99.11 118	94.28 275	99.01 83	98.88 75	86.43 431	92.81 367	97.57 302	81.66 370	98.68 314	94.83 243	89.02 393	96.88 334

IterMVS		94.09 341	93.85 319	94.80 380	97.99 262	90.35 385	97.18 388	98.12 291	93.68 285	92.46 381	97.34 319	84.05 352	97.41 418	92.51 326	91.33 356	96.62 365
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test-mter		94.08 342	93.51 340	95.80 338	96.77 360	89.70 397	96.91 406	95.21 439	92.89 323	94.83 281	95.72 417	77.69 408	98.97 274	93.06 306	98.50 185	98.72 242

test0.0.03 1		94.08 342	93.51 340	95.80 338	95.53 415	92.89 330	97.38 368	95.97 429	95.11 194	92.51 379	96.66 381	87.71 275	96.94 425	87.03 412	93.67 320	97.57 303

v1240		94.06 344	93.29 348	96.34 313	96.03 398	93.90 289	98.44 246	98.17 284	91.18 383	94.13 315	97.01 356	86.05 309	98.42 339	89.13 394	89.50 384	96.70 356

X-MVStestdata		94.06 344	92.30 370	99.34 28	99.70 24	98.35 46	99.29 24	98.88 75	97.40 56	98.46 114	43.50 470	95.90 46	99.89 64	97.85 98	99.74 55	99.78 30

DTE-MVSNet		93.98 346	93.26 349	96.14 321	96.06 396	94.39 269	99.20 44	98.86 88	93.06 316	91.78 392	97.81 279	85.87 313	97.58 413	90.53 368	86.17 421	96.46 391

pm-mvs1		93.94 347	93.06 352	96.59 286	96.49 376	95.16 227	98.95 98	98.03 311	92.32 345	91.08 400	97.84 274	84.54 342	98.41 346	92.16 331	86.13 424	96.19 403

MS-PatchMatch		93.84 348	93.63 334	94.46 394	96.18 389	89.45 404	97.76 342	98.27 258	92.23 348	92.13 388	97.49 307	79.50 391	98.69 311	89.75 381	99.38 130	95.25 421

tfpnnormal		93.66 349	92.70 360	96.55 294	96.94 349	95.94 178	98.97 92	99.19 33	91.04 384	91.38 397	97.34 319	84.94 330	98.61 319	85.45 423	89.02 393	95.11 425

EU-MVSNet		93.66 349	94.14 295	92.25 424	95.96 402	83.38 448	98.52 226	98.12 291	94.69 224	92.61 374	98.13 247	87.36 285	96.39 439	91.82 342	90.00 375	96.98 319

our_test_3		93.65 351	93.30 347	94.69 382	95.45 419	89.68 399	96.91 406	97.65 333	91.97 355	91.66 395	96.88 368	89.67 216	97.93 394	88.02 406	91.49 355	96.48 389

pmmvs5		93.65 351	92.97 355	95.68 343	95.49 416	92.37 337	98.20 277	97.28 375	89.66 408	92.58 375	97.26 325	82.14 367	98.09 380	93.18 304	90.95 364	96.58 369

SSC-MVS3.2		93.59 353	93.13 351	94.97 369	96.81 359	89.71 396	97.95 315	98.49 200	94.59 231	93.50 344	96.91 366	77.74 407	98.37 353	91.69 346	90.47 368	96.83 342

test_fmvs2		93.43 354	93.58 336	92.95 418	96.97 347	83.91 444	99.19 46	97.24 378	95.74 151	95.20 273	98.27 235	69.65 442	98.72 310	96.26 191	93.73 319	96.24 400

tpm cat1		93.36 355	92.80 357	95.07 367	97.58 300	87.97 430	96.76 418	97.86 322	82.17 449	93.53 340	96.04 405	86.13 307	99.13 248	89.24 392	95.87 292	98.10 286

JIA-IIPM		93.35 356	92.49 366	95.92 331	96.48 377	90.65 375	95.01 444	96.96 400	85.93 435	96.08 254	87.33 460	87.70 277	98.78 306	91.35 352	95.58 296	98.34 276

SixPastTwentyTwo		93.34 357	92.86 356	94.75 381	95.67 409	89.41 406	98.75 165	96.67 416	93.89 266	90.15 410	98.25 238	80.87 380	98.27 367	90.90 364	90.64 366	96.57 371

USDC		93.33 358	92.71 359	95.21 360	96.83 357	90.83 371	96.91 406	97.50 353	93.84 269	90.72 403	98.14 246	77.69 408	98.82 302	89.51 387	93.21 335	95.97 409

IB-MVS	91.98 17	93.27 359	91.97 374	97.19 231	97.47 311	93.41 309	97.09 396	95.99 428	93.32 303	92.47 380	95.73 415	78.06 403	99.53 178	94.59 258	82.98 435	98.62 256
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		93.26 360	92.21 371	96.41 308	97.73 288	93.13 323	95.65 439	97.03 394	91.27 379	94.04 319	96.06 403	75.33 427	97.19 421	86.56 414	96.23 284	98.92 221

ppachtmachnet_test		93.22 361	92.63 361	94.97 369	95.45 419	90.84 370	96.88 412	97.88 321	90.60 390	92.08 389	97.26 325	88.08 266	97.86 400	85.12 426	90.33 369	96.22 401

Patchmtry		93.22 361	92.35 369	95.84 337	96.77 360	93.09 326	94.66 452	97.56 343	87.37 427	92.90 365	96.24 394	88.15 263	97.90 395	87.37 411	90.10 374	96.53 378

testing3		93.19 363	92.48 367	95.30 359	98.07 248	92.27 338	98.64 201	97.17 384	93.94 265	93.98 322	97.04 351	67.97 447	96.01 443	88.40 401	97.14 245	97.63 300

FMVSNet1		93.19 363	92.07 372	96.56 290	97.54 305	95.00 235	98.82 143	98.18 278	90.38 396	92.27 384	97.07 343	73.68 437	97.95 391	89.36 390	91.30 357	96.72 352

LF4IMVS		93.14 365	92.79 358	94.20 398	95.88 404	88.67 419	97.66 350	97.07 390	93.81 272	91.71 393	97.65 293	77.96 405	98.81 303	91.47 351	91.92 350	95.12 424

mmtdpeth		93.12 366	92.61 362	94.63 386	97.60 298	89.68 399	99.21 41	97.32 370	94.02 256	97.72 170	94.42 434	77.01 418	99.44 198	99.05 31	77.18 457	94.78 434

testgi		93.06 367	92.45 368	94.88 374	96.43 380	89.90 391	98.75 165	97.54 349	95.60 159	91.63 396	97.91 266	74.46 434	97.02 423	86.10 417	93.67 320	97.72 297

PatchT		93.06 367	91.97 374	96.35 312	96.69 366	92.67 335	94.48 455	97.08 388	86.62 429	97.08 205	92.23 454	87.94 270	97.90 395	78.89 450	96.69 260	98.49 268

RPMNet		92.81 369	91.34 380	97.24 227	97.00 344	93.43 307	94.96 445	98.80 110	82.27 448	96.93 213	92.12 455	86.98 290	99.82 93	76.32 456	96.65 262	98.46 270

UWE-MVS-28		92.79 370	92.51 365	93.62 406	96.46 378	86.28 438	97.93 319	92.71 460	94.17 249	94.78 284	97.16 333	81.05 377	96.43 438	81.45 442	96.86 253	98.14 285

myMVS_eth3d		92.73 371	92.01 373	94.89 373	97.39 321	90.94 366	97.91 322	97.46 357	93.16 311	93.42 348	95.37 424	68.09 446	96.12 441	88.34 402	96.99 249	97.60 301

TransMVSNet (Re)		92.67 372	91.51 379	96.15 320	96.58 371	94.65 254	98.90 112	96.73 412	90.86 387	89.46 417	97.86 271	85.62 317	98.09 380	86.45 415	81.12 443	95.71 414

ttmdpeth		92.61 373	91.96 376	94.55 388	94.10 437	90.60 379	98.52 226	97.29 373	92.67 330	90.18 408	97.92 265	79.75 390	97.79 402	91.09 357	86.15 423	95.26 420

Syy-MVS		92.55 374	92.61 362	92.38 421	97.39 321	83.41 447	97.91 322	97.46 357	93.16 311	93.42 348	95.37 424	84.75 335	96.12 441	77.00 455	96.99 249	97.60 301

K. test v3		92.55 374	91.91 377	94.48 392	95.64 410	89.24 407	99.07 68	94.88 443	94.04 254	86.78 434	97.59 300	77.64 411	97.64 409	92.08 333	89.43 386	96.57 371

DSMNet-mixed		92.52 376	92.58 364	92.33 422	94.15 436	82.65 450	98.30 265	94.26 450	89.08 417	92.65 373	95.73 415	85.01 329	95.76 445	86.24 416	97.76 224	98.59 261

TinyColmap		92.31 377	91.53 378	94.65 385	96.92 350	89.75 394	96.92 404	96.68 415	90.45 394	89.62 414	97.85 273	76.06 425	98.81 303	86.74 413	92.51 343	95.41 418

gg-mvs-nofinetune		92.21 378	90.58 386	97.13 236	96.75 363	95.09 231	95.85 434	89.40 468	85.43 439	94.50 290	81.98 463	80.80 382	98.40 352	92.16 331	98.33 201	97.88 290

FMVSNet5		91.81 379	90.92 382	94.49 391	97.21 331	92.09 345	98.00 311	97.55 348	89.31 415	90.86 402	95.61 421	74.48 433	95.32 449	85.57 421	89.70 378	96.07 407

pmmvs6		91.77 380	90.63 385	95.17 362	94.69 433	91.24 362	98.67 195	97.92 319	86.14 433	89.62 414	97.56 305	75.79 426	98.34 355	90.75 366	84.56 428	95.94 410

Anonymous20231206		91.66 381	91.10 381	93.33 411	94.02 441	87.35 434	98.58 213	97.26 377	90.48 392	90.16 409	96.31 392	83.83 358	96.53 436	79.36 448	89.90 376	96.12 405

Patchmatch-RL test		91.49 382	90.85 383	93.41 409	91.37 452	84.40 442	92.81 459	95.93 432	91.87 358	87.25 430	94.87 430	88.99 240	96.53 436	92.54 325	82.00 437	99.30 151

test_0402		91.32 383	90.27 389	94.48 392	96.60 370	91.12 363	98.50 234	97.22 379	86.10 434	88.30 426	96.98 358	77.65 410	97.99 389	78.13 452	92.94 337	94.34 435

test_vis1_rt		91.29 384	90.65 384	93.19 415	97.45 315	86.25 439	98.57 220	90.90 466	93.30 305	86.94 433	93.59 443	62.07 458	99.11 253	97.48 132	95.58 296	94.22 438

PVSNet_0	88.72 19	91.28 385	90.03 392	95.00 368	97.99 262	87.29 435	94.84 448	98.50 195	92.06 353	89.86 411	95.19 426	79.81 389	99.39 205	92.27 330	69.79 463	98.33 277

mvs5depth		91.23 386	90.17 390	94.41 396	92.09 449	89.79 393	95.26 443	96.50 420	90.73 388	91.69 394	97.06 347	76.12 424	98.62 318	88.02 406	84.11 431	94.82 431

Anonymous20240521		91.18 387	90.44 387	93.42 408	93.70 442	88.47 423	98.94 101	97.56 343	88.46 421	89.56 416	95.08 429	77.15 416	96.97 424	83.92 433	89.55 382	94.82 431

EG-PatchMatch MVS		91.13 388	90.12 391	94.17 400	94.73 432	89.00 412	98.13 293	97.81 324	89.22 416	85.32 444	96.46 389	67.71 448	98.42 339	87.89 409	93.82 318	95.08 426

TDRefinement		91.06 389	89.68 394	95.21 360	85.35 468	91.49 358	98.51 233	97.07 390	91.47 367	88.83 423	97.84 274	77.31 412	99.09 258	92.79 316	77.98 455	95.04 428

sc_t1		91.01 390	89.39 396	95.85 336	95.99 399	90.39 384	98.43 248	97.64 335	78.79 452	92.20 386	97.94 263	66.00 452	98.60 322	91.59 349	85.94 425	98.57 264

UnsupCasMVSNet_eth		90.99 391	89.92 393	94.19 399	94.08 438	89.83 392	97.13 395	98.67 147	93.69 283	85.83 440	96.19 399	75.15 428	96.74 429	89.14 393	79.41 450	96.00 408

test20.03		90.89 392	90.38 388	92.43 420	93.48 443	88.14 429	98.33 257	97.56 343	93.40 300	87.96 427	96.71 379	80.69 383	94.13 455	79.15 449	86.17 421	95.01 430

MDA-MVSNet_test_wron		90.71 393	89.38 398	94.68 383	94.83 429	90.78 372	97.19 387	97.46 357	87.60 425	72.41 463	95.72 417	86.51 296	96.71 432	85.92 419	86.80 418	96.56 373

YYNet1		90.70 394	89.39 396	94.62 387	94.79 431	90.65 375	97.20 385	97.46 357	87.54 426	72.54 462	95.74 413	86.51 296	96.66 433	86.00 418	86.76 419	96.54 376

KD-MVS_self_test		90.38 395	89.38 398	93.40 410	92.85 446	88.94 415	97.95 315	97.94 317	90.35 397	90.25 407	93.96 440	79.82 388	95.94 444	84.62 432	76.69 458	95.33 419

pmmvs-eth3d		90.36 396	89.05 401	94.32 397	91.10 454	92.12 342	97.63 355	96.95 401	88.86 419	84.91 445	93.13 448	78.32 399	96.74 429	88.70 398	81.81 439	94.09 441

tt0320		90.26 397	88.73 404	94.86 375	96.12 393	90.62 377	98.17 286	97.63 336	77.46 455	89.68 413	96.04 405	69.19 444	97.79 402	88.98 395	85.29 427	96.16 404

CL-MVSNet_self_test		90.11 398	89.14 400	93.02 416	91.86 451	88.23 428	96.51 426	98.07 304	90.49 391	90.49 406	94.41 435	84.75 335	95.34 448	80.79 444	74.95 460	95.50 417

new_pmnet		90.06 399	89.00 402	93.22 414	94.18 435	88.32 426	96.42 428	96.89 406	86.19 432	85.67 441	93.62 442	77.18 415	97.10 422	81.61 441	89.29 388	94.23 437

MDA-MVSNet-bldmvs		89.97 400	88.35 406	94.83 379	95.21 423	91.34 359	97.64 352	97.51 352	88.36 423	71.17 464	96.13 401	79.22 393	96.63 434	83.65 434	86.27 420	96.52 381

tt0320-xc		89.79 401	88.11 408	94.84 378	96.19 388	90.61 378	98.16 287	97.22 379	77.35 456	88.75 424	96.70 380	65.94 453	97.63 410	89.31 391	83.39 433	96.28 399

CMPMVS	66.06 21	89.70 402	89.67 395	89.78 429	93.19 444	76.56 455	97.00 400	98.35 238	80.97 450	81.57 451	97.75 282	74.75 431	98.61 319	89.85 379	93.63 322	94.17 439
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet1		89.67 403	88.28 407	93.82 403	92.81 447	91.08 364	98.01 309	97.45 361	87.95 424	87.90 428	95.87 411	67.63 449	94.56 454	78.73 451	88.18 401	95.83 412

KD-MVS_2432*1600		89.61 404	87.96 412	94.54 389	94.06 439	91.59 356	95.59 440	97.63 336	89.87 404	88.95 420	94.38 437	78.28 400	96.82 427	84.83 428	68.05 464	95.21 422

miper_refine_blended		89.61 404	87.96 412	94.54 389	94.06 439	91.59 356	95.59 440	97.63 336	89.87 404	88.95 420	94.38 437	78.28 400	96.82 427	84.83 428	68.05 464	95.21 422

MVStest1		89.53 406	87.99 411	94.14 402	94.39 434	90.42 382	98.25 272	96.84 411	82.81 445	81.18 453	97.33 321	77.09 417	96.94 425	85.27 425	78.79 451	95.06 427

MVS-HIRNet		89.46 407	88.40 405	92.64 419	97.58 300	82.15 451	94.16 458	93.05 459	75.73 459	90.90 401	82.52 462	79.42 392	98.33 357	83.53 435	98.68 169	97.43 304

OpenMVS_ROB	86.42 20	89.00 408	87.43 416	93.69 405	93.08 445	89.42 405	97.91 322	96.89 406	78.58 453	85.86 439	94.69 431	69.48 443	98.29 365	77.13 454	93.29 334	93.36 449

mvsany_test3		88.80 409	88.04 409	91.09 428	89.78 458	81.57 453	97.83 337	95.49 437	93.81 272	87.53 429	93.95 441	56.14 461	97.43 417	94.68 251	83.13 434	94.26 436

FE-MVSNET		88.56 410	87.09 417	92.99 417	89.93 457	89.99 390	98.15 290	95.59 435	88.42 422	84.87 446	92.90 449	74.82 430	94.99 452	77.88 453	81.21 442	93.99 444

new-patchmatchnet		88.50 411	87.45 415	91.67 426	90.31 456	85.89 440	97.16 393	97.33 369	89.47 411	83.63 448	92.77 451	76.38 421	95.06 451	82.70 437	77.29 456	94.06 443

APD_test1		88.22 412	88.01 410	88.86 431	95.98 400	74.66 463	97.21 384	96.44 422	83.96 444	86.66 436	97.90 267	60.95 459	97.84 401	82.73 436	90.23 372	94.09 441

PM-MVS		87.77 413	86.55 419	91.40 427	91.03 455	83.36 449	96.92 404	95.18 441	91.28 378	86.48 438	93.42 444	53.27 462	96.74 429	89.43 389	81.97 438	94.11 440

dmvs_testset		87.64 414	88.93 403	83.79 440	95.25 422	63.36 472	97.20 385	91.17 464	93.07 315	85.64 442	95.98 410	85.30 326	91.52 462	69.42 461	87.33 410	96.49 387

test_fmvs3		87.17 415	87.06 418	87.50 433	91.21 453	75.66 458	99.05 71	96.61 419	92.79 327	88.85 422	92.78 450	43.72 465	93.49 456	93.95 281	84.56 428	93.34 450

UnsupCasMVSNet_bld		87.17 415	85.12 422	93.31 412	91.94 450	88.77 416	94.92 447	98.30 255	84.30 443	82.30 449	90.04 457	63.96 456	97.25 420	85.85 420	74.47 462	93.93 446

N_pmnet		87.12 417	87.77 414	85.17 437	95.46 418	61.92 473	97.37 370	70.66 478	85.83 436	88.73 425	96.04 405	85.33 324	97.76 405	80.02 445	90.48 367	95.84 411

pmmvs3		86.67 418	84.86 423	92.11 425	88.16 462	87.19 436	96.63 422	94.75 445	79.88 451	87.22 431	92.75 452	66.56 451	95.20 450	81.24 443	76.56 459	93.96 445

test_f		86.07 419	85.39 420	88.10 432	89.28 460	75.57 459	97.73 345	96.33 424	89.41 414	85.35 443	91.56 456	43.31 467	95.53 446	91.32 353	84.23 430	93.21 451

WB-MVS		84.86 420	85.33 421	83.46 441	89.48 459	69.56 467	98.19 280	96.42 423	89.55 410	81.79 450	94.67 432	84.80 333	90.12 463	52.44 467	80.64 447	90.69 454

SSC-MVS		84.27 421	84.71 424	82.96 445	89.19 461	68.83 468	98.08 301	96.30 425	89.04 418	81.37 452	94.47 433	84.60 340	89.89 464	49.80 469	79.52 449	90.15 455

dongtai		82.47 422	81.88 425	84.22 439	95.19 424	76.03 456	94.59 454	74.14 477	82.63 446	87.19 432	96.09 402	64.10 455	87.85 467	58.91 465	84.11 431	88.78 459

test_vis3_rt		79.22 423	77.40 430	84.67 438	86.44 466	74.85 462	97.66 350	81.43 473	84.98 440	67.12 466	81.91 464	28.09 475	97.60 411	88.96 396	80.04 448	81.55 464

test_method		79.03 424	78.17 426	81.63 446	86.06 467	54.40 478	82.75 467	96.89 406	39.54 470	80.98 454	95.57 422	58.37 460	94.73 453	84.74 431	78.61 452	95.75 413

testf1		79.02 425	77.70 427	82.99 443	88.10 463	66.90 469	94.67 450	93.11 456	71.08 461	74.02 459	93.41 445	34.15 471	93.25 457	72.25 459	78.50 453	88.82 457

APD_test2		79.02 425	77.70 427	82.99 443	88.10 463	66.90 469	94.67 450	93.11 456	71.08 461	74.02 459	93.41 445	34.15 471	93.25 457	72.25 459	78.50 453	88.82 457

LCM-MVSNet		78.70 427	76.24 433	86.08 435	77.26 474	71.99 465	94.34 456	96.72 413	61.62 465	76.53 457	89.33 458	33.91 473	92.78 460	81.85 440	74.60 461	93.46 448

kuosan		78.45 428	77.69 429	80.72 447	92.73 448	75.32 460	94.63 453	74.51 476	75.96 457	80.87 455	93.19 447	63.23 457	79.99 471	42.56 471	81.56 441	86.85 463

Gipuma		78.40 429	76.75 432	83.38 442	95.54 413	80.43 454	79.42 468	97.40 365	64.67 464	73.46 461	80.82 465	45.65 464	93.14 459	66.32 463	87.43 408	76.56 467
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		77.95 430	75.44 434	85.46 436	82.54 469	74.95 461	94.23 457	93.08 458	72.80 460	74.68 458	87.38 459	36.36 470	91.56 461	73.95 457	63.94 466	89.87 456

FPMVS		77.62 431	77.14 431	79.05 449	79.25 472	60.97 474	95.79 435	95.94 431	65.96 463	67.93 465	94.40 436	37.73 469	88.88 466	68.83 462	88.46 398	87.29 460

EGC-MVSNET		75.22 432	69.54 435	92.28 423	94.81 430	89.58 401	97.64 352	96.50 420	1.82 475	5.57 476	95.74 413	68.21 445	96.26 440	73.80 458	91.71 352	90.99 453

ANet_high		69.08 433	65.37 437	80.22 448	65.99 476	71.96 466	90.91 463	90.09 467	82.62 447	49.93 471	78.39 466	29.36 474	81.75 468	62.49 464	38.52 470	86.95 462

tmp_tt		68.90 434	66.97 436	74.68 451	50.78 478	59.95 475	87.13 464	83.47 472	38.80 471	62.21 467	96.23 396	64.70 454	76.91 473	88.91 397	30.49 471	87.19 461

PMVS	61.03 23	65.95 435	63.57 439	73.09 452	57.90 477	51.22 479	85.05 466	93.93 454	54.45 466	44.32 472	83.57 461	13.22 476	89.15 465	58.68 466	81.00 444	78.91 466
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		64.94 436	64.25 438	67.02 453	82.28 470	59.36 476	91.83 462	85.63 470	52.69 467	60.22 468	77.28 467	41.06 468	80.12 470	46.15 470	41.14 468	61.57 469

EMVS		64.07 437	63.26 440	66.53 454	81.73 471	58.81 477	91.85 461	84.75 471	51.93 469	59.09 469	75.13 468	43.32 466	79.09 472	42.03 472	39.47 469	61.69 468

MVE	62.14 22	63.28 438	59.38 441	74.99 450	74.33 475	65.47 471	85.55 465	80.50 474	52.02 468	51.10 470	75.00 469	10.91 479	80.50 469	51.60 468	53.40 467	78.99 465
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		30.17 439	30.18 443	30.16 455	78.61 473	43.29 480	66.79 469	14.21 479	17.31 472	14.82 475	11.93 475	11.55 478	41.43 474	37.08 473	19.30 472	5.76 472

cdsmvs_eth3d_5k		23.98 440	31.98 442	0.00 458	0.00 481	0.00 483	0.00 470	98.59 168	0.00 476	0.00 477	98.61 195	90.60 195	0.00 477	0.00 476	0.00 475	0.00 473

testmvs		21.48 441	24.95 444	11.09 457	14.89 479	6.47 482	96.56 424	9.87 480	7.55 473	17.93 473	39.02 471	9.43 480	5.90 476	16.56 475	12.72 473	20.91 471

test123		20.95 442	23.72 445	12.64 456	13.54 480	8.19 481	96.55 425	6.13 481	7.48 474	16.74 474	37.98 472	12.97 477	6.05 475	16.69 474	5.43 474	23.68 470

ab-mvs-re		8.20 443	10.94 446	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	98.43 213	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

pcd_1.5k_mvsjas		7.88 444	10.50 447	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	94.51 89	0.00 477	0.00 476	0.00 475	0.00 473

mmdepth		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

monomultidepth		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

test_blank		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

uanet_test		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

DCPMVS		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

sosnet-low-res		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

sosnet		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

uncertanet		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

Regformer		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

uanet		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

TestfortrainingZip							99.32 22

WAC-MVS						90.94 366								88.66 399

FOURS1					99.82 1	98.66 25	99.69 1	98.95 58	97.46 54	99.39 43

MSC_two_6792asdad				99.62 6	99.17 107	99.08 11		98.63 158					99.94 13	98.53 54	99.80 24	99.86 11

PC_three_1452									95.08 198	99.60 31	99.16 98	97.86 2	98.47 333	97.52 127	99.72 64	99.74 47

No_MVS				99.62 6	99.17 107	99.08 11		98.63 158					99.94 13	98.53 54	99.80 24	99.86 11

test_one_0601					99.66 28	99.25 2		98.86 88	97.55 46	99.20 55	99.47 34	97.57 6

eth-test2					0.00 481

eth-test					0.00 481

ZD-MVS					99.46 55	98.70 24		98.79 115	93.21 308	98.67 100	98.97 136	95.70 50	99.83 86	96.07 195	99.58 95

RE-MVS-def			98.34 51		99.49 49	97.86 71	99.11 62	98.80 110	96.49 114	99.17 58	99.35 59	95.29 67		97.72 106	99.65 78	99.71 60

IU-MVS					99.71 21	99.23 7		98.64 155	95.28 181	99.63 30				98.35 71	99.81 15	99.83 17

OPU-MVS				99.37 24	99.24 99	99.05 14	99.02 81				99.16 98	97.81 3	99.37 206	97.24 145	99.73 59	99.70 64

test_241102_TWO								98.87 82	97.65 38	99.53 36	99.48 32	97.34 11	99.94 13	98.43 66	99.80 24	99.83 17

test_241102_ONE					99.71 21	99.24 5		98.87 82	97.62 40	99.73 21	99.39 47	97.53 7	99.74 130

9.14			98.06 76		99.47 53		98.71 180	98.82 97	94.36 244	99.16 62	99.29 71	96.05 38	99.81 98	97.00 152	99.71 66

save fliter					99.46 55	98.38 37	98.21 275	98.71 133	97.95 27

test_0728_THIRD									97.32 62	99.45 38	99.46 39	97.88 1	99.94 13	98.47 62	99.86 2	99.85 14

test_0728_SECOND				99.71 1	99.72 14	99.35 1	98.97 92	98.88 75					99.94 13	98.47 62	99.81 15	99.84 16

test0726					99.72 14	99.25 2	99.06 69	98.88 75	97.62 40	99.56 33	99.50 28	97.42 9

GSMVS																99.20 173

test_part2					99.63 31	99.18 10				99.27 52

sam_mvs1												89.45 224				99.20 173

sam_mvs												88.99 240

ambc				89.49 430	86.66 465	75.78 457	92.66 460	96.72 413		86.55 437	92.50 453	46.01 463	97.90 395	90.32 370	82.09 436	94.80 433

MTGPA								98.74 125

test_post1							96.68 421				30.43 474	87.85 274	98.69 311	92.59 321

test_post											31.83 473	88.83 247	98.91 287

patchmatchnet-post											95.10 428	89.42 225	98.89 291

GG-mvs-BLEND				96.59 286	96.34 383	94.98 239	96.51 426	88.58 469		93.10 362	94.34 439	80.34 387	98.05 383	89.53 386	96.99 249	96.74 349

MTMP							98.89 116	94.14 452

gm-plane-assit					95.88 404	87.47 433			89.74 407		96.94 364		99.19 236	93.32 300

test9_res														96.39 189	99.57 96	99.69 67

TEST9					99.31 75	98.50 31	97.92 320	98.73 128	92.63 331	97.74 167	98.68 190	96.20 33	99.80 105

test_8					99.29 84	98.44 33	97.89 328	98.72 130	92.98 319	97.70 172	98.66 193	96.20 33	99.80 105

agg_prior2														95.87 205	99.57 96	99.68 72

agg_prior					99.30 79	98.38 37		98.72 130		97.57 188			99.81 98

TestCases				96.99 247	99.25 92	93.21 321		98.18 278	91.36 371	93.52 341	98.77 177	84.67 338	99.72 132	89.70 383	97.87 219	98.02 288

test_prior4						98.01 67	97.86 332

test_prior2							97.80 339		96.12 133	97.89 158	98.69 189	95.96 42		96.89 162	99.60 90

test_prior				99.19 47	99.31 75	98.22 54		98.84 92					99.70 138			99.65 80

旧先验2							97.57 358		91.30 376	98.67 100			99.80 105	95.70 216

新几何2							97.64 352

新几何1				99.16 52	99.34 67	98.01 67		98.69 139	90.06 401	98.13 130	98.95 143	94.60 87	99.89 64	91.97 340	99.47 118	99.59 91

旧先验1					99.29 84	97.48 86		98.70 137			99.09 118	95.56 53			99.47 118	99.61 87

无先验							97.58 357	98.72 130	91.38 370				99.87 75	93.36 299		99.60 89

原ACMM2							97.67 349

原ACMM1				98.65 94	99.32 73	96.62 136		98.67 147	93.27 307	97.81 161	98.97 136	95.18 74	99.83 86	93.84 285	99.46 121	99.50 103

test222					99.23 100	97.17 113	97.40 366	98.66 150	88.68 420	98.05 137	98.96 141	94.14 100			99.53 109	99.61 87

testdata2													99.89 64	91.65 348

segment_acmp												96.85 14

testdata				98.26 137	99.20 105	95.36 216		98.68 142	91.89 357	98.60 108	99.10 110	94.44 94	99.82 93	94.27 269	99.44 122	99.58 95

testdata1							97.32 376		96.34 123

test12				99.18 49	99.16 111	98.19 56		98.53 184		98.07 134		95.13 77	99.72 132		99.56 104	99.63 85

plane_prior7					97.42 317	94.63 256

plane_prior6					97.35 324	94.61 259						87.09 287

plane_prior5								98.56 178					99.03 267	96.07 195	94.27 302	96.92 325

plane_prior4											98.28 232

plane_prior3						94.61 259			97.02 86	95.34 268

plane_prior2							98.80 152		97.28 66

plane_prior1					97.37 323

plane_prior						94.60 261	98.44 246		96.74 101						94.22 304

n2								0.00 482

nn								0.00 482

door-mid								94.37 448

lessismore_v0				94.45 395	94.93 428	88.44 424		91.03 465		86.77 435	97.64 296	76.23 423	98.42 339	90.31 371	85.64 426	96.51 384

LGP-MVS_train				96.47 301	97.46 312	93.54 302		98.54 182	94.67 226	94.36 300	98.77 177	85.39 320	99.11 253	95.71 214	94.15 308	96.76 347

test11								98.66 150

door								94.64 446

HQP5-MVS						94.25 278

HQP-NCC					97.20 332		98.05 304		96.43 116	94.45 292

ACMP_Plane					97.20 332		98.05 304		96.43 116	94.45 292

BP-MVS														95.30 228

HQP4-MVS										94.45 292			98.96 278			96.87 337

HQP3-MVS								98.46 203							94.18 306

HQP2-MVS												86.75 293

NP-MVS					97.28 326	94.51 264					97.73 283

MDTV_nov1_ep13_2view						84.26 443	96.89 411		90.97 385	97.90 157		89.89 210		93.91 283		99.18 182

MDTV_nov1_ep13			95.40 221		97.48 310	88.34 425	96.85 414	97.29 373	93.74 276	97.48 190	97.26 325	89.18 233	99.05 263	91.92 341	97.43 240

ACMMP++_ref															92.97 336

ACMMP++															93.61 323

Test By Simon												94.64 86

ITE_SJBPF				95.44 354	97.42 317	91.32 360		97.50 353	95.09 197	93.59 336	98.35 223	81.70 369	98.88 293	89.71 382	93.39 329	96.12 405

DeepMVS_CX				86.78 434	97.09 342	72.30 464		95.17 442	75.92 458	84.34 447	95.19 426	70.58 441	95.35 447	79.98 447	89.04 392	92.68 452

High-resolution multi-view benchmark