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 57	99.43 59	97.48 85	98.88 122	99.30 14	98.47 16	99.85 10	99.43 41	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 80	98.87 80	97.65 37	99.73 20	99.48 31	97.53 7	99.94 13	98.43 65	99.81 15	99.70 62

DVP-MVS++		99.08 3	98.89 5	99.64 3	99.17 105	99.23 7	99.69 1	98.88 73	97.32 61	99.53 35	99.47 33	97.81 3	99.94 13	98.47 61	99.72 62	99.74 45

fmvsm_l_conf0.5_n		99.07 4	99.05 2	99.14 53	99.41 61	97.54 83	98.89 115	99.31 13	98.49 15	99.86 7	99.42 42	96.45 24	99.96 4	99.86 1	99.74 54	99.90 5

DVP-MVS		99.03 5	98.83 9	99.63 4	99.72 14	99.25 2	98.97 91	98.58 171	97.62 39	99.45 37	99.46 38	97.42 9	99.94 13	98.47 61	99.81 15	99.69 65
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 35	98.96 16	99.39 11	98.93 61	97.38 58	99.41 40	99.54 18	96.66 18	99.84 82	98.86 37	99.85 6	99.87 9
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 15	99.75 3	98.63 26	99.43 10	99.38 8	97.60 42	99.58 31	99.47 33	95.36 61	99.93 32	98.87 36	99.57 94	99.78 28

reproduce_model		98.94 8	98.81 10	99.34 27	99.52 41	98.26 50	98.94 100	98.84 90	98.06 23	99.35 44	99.61 4	96.39 27	99.94 13	98.77 40	99.82 14	99.83 16

reproduce-ours		98.93 9	98.78 12	99.38 19	99.49 48	98.38 36	98.86 129	98.83 92	98.06 23	99.29 48	99.58 14	96.40 25	99.94 13	98.68 43	99.81 15	99.81 22

our_new_method		98.93 9	98.78 12	99.38 19	99.49 48	98.38 36	98.86 129	98.83 92	98.06 23	99.29 48	99.58 14	96.40 25	99.94 13	98.68 43	99.81 15	99.81 22

test_fmvsmconf_n		98.92 11	98.87 6	99.04 63	98.88 141	97.25 107	98.82 141	99.34 11	98.75 9	99.80 12	99.61 4	95.16 74	99.95 9	99.70 15	99.80 24	99.93 1

DPE-MVS		98.92 11	98.67 18	99.65 2	99.58 34	99.20 9	98.42 247	98.91 67	97.58 43	99.54 34	99.46 38	97.10 12	99.94 13	97.64 113	99.84 11	99.83 16
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 41	99.34 65	97.83 74	98.70 182	99.26 16	98.85 4	99.92 1	99.51 24	93.91 103	99.95 9	99.86 1	99.79 30	99.92 2

fmvsm_l_conf0.5_n_3		98.90 13	98.74 16	99.37 23	99.36 63	98.25 51	98.89 115	99.24 20	98.77 8	99.89 3	99.59 12	93.39 109	99.96 4	99.78 8	99.76 43	99.89 6

SteuartSystems-ACMMP		98.90 13	98.75 15	99.36 25	99.22 100	98.43 34	99.10 64	98.87 80	97.38 58	99.35 44	99.40 45	97.78 5	99.87 73	97.77 101	99.85 6	99.78 28
Skip Steuart: Steuart Systems R&D Blog.
test_fmvsm_n_1920		98.87 16	99.01 3	98.45 117	99.42 60	96.43 149	98.96 96	99.36 10	98.63 11	99.86 7	99.51 24	95.91 43	99.97 1	99.72 12	99.75 50	98.94 215

TSAR-MVS + MP.		98.78 17	98.62 20	99.24 41	99.69 26	98.28 49	99.14 55	98.66 148	96.84 92	99.56 32	99.31 65	96.34 28	99.70 136	98.32 71	99.73 57	99.73 50
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 17	98.56 24	99.45 15	99.32 71	98.87 19	98.47 235	98.81 101	97.72 32	98.76 89	99.16 96	97.05 13	99.78 118	98.06 83	99.66 73	99.69 65

MSP-MVS		98.74 19	98.55 25	99.29 34	99.75 3	98.23 52	99.26 28	98.88 73	97.52 46	99.41 40	98.78 170	96.00 39	99.79 115	97.79 100	99.59 90	99.85 13
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 20	98.62 20	99.05 62	99.35 64	97.27 101	98.80 150	99.23 25	98.93 3	99.79 13	99.59 12	92.34 126	99.95 9	99.82 6	99.71 64	99.92 2

XVS		98.70 21	98.49 31	99.34 27	99.70 24	98.35 45	99.29 23	98.88 73	97.40 55	98.46 112	99.20 86	95.90 45	99.89 62	97.85 96	99.74 54	99.78 28

fmvsm_s_conf0.5_n_6		98.65 22	98.55 25	98.95 72	98.50 181	97.30 97	98.79 158	99.16 36	98.14 21	99.86 7	99.41 44	93.71 106	99.91 51	99.71 13	99.64 81	99.65 78

MCST-MVS		98.65 22	98.37 40	99.48 13	99.60 33	98.87 19	98.41 248	98.68 140	97.04 84	98.52 110	98.80 164	96.78 16	99.83 84	97.93 90	99.61 86	99.74 45

SD-MVS		98.64 24	98.68 17	98.53 106	99.33 68	98.36 44	98.90 111	98.85 89	97.28 65	99.72 23	99.39 46	96.63 20	97.60 407	98.17 78	99.85 6	99.64 81
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 25	98.66 19	98.54 103	99.40 62	95.83 190	98.79 158	99.17 34	98.94 2	99.92 1	99.61 4	92.49 121	99.93 32	99.86 1	99.76 43	99.86 10

HFP-MVS		98.63 25	98.40 37	99.32 33	99.72 14	98.29 48	99.23 33	98.96 56	96.10 132	98.94 71	99.17 93	96.06 36	99.92 41	97.62 114	99.78 35	99.75 43

ACMMP_NAP		98.61 27	98.30 55	99.55 9	99.62 32	98.95 17	98.82 141	98.81 101	95.80 146	99.16 60	99.47 33	95.37 60	99.92 41	97.89 94	99.75 50	99.79 26

region2R		98.61 27	98.38 39	99.29 34	99.74 9	98.16 58	99.23 33	98.93 61	96.15 128	98.94 71	99.17 93	95.91 43	99.94 13	97.55 122	99.79 30	99.78 28

NCCC		98.61 27	98.35 43	99.38 19	99.28 86	98.61 27	98.45 237	98.76 119	97.82 31	98.45 115	98.93 143	96.65 19	99.83 84	97.38 138	99.41 123	99.71 58

SF-MVS		98.59 30	98.32 54	99.41 18	99.54 37	98.71 22	99.04 74	98.81 101	95.12 190	99.32 47	99.39 46	96.22 30	99.84 82	97.72 104	99.73 57	99.67 74

ACMMPR		98.59 30	98.36 41	99.29 34	99.74 9	98.15 59	99.23 33	98.95 57	96.10 132	98.93 75	99.19 91	95.70 49	99.94 13	97.62 114	99.79 30	99.78 28

test_fmvsmconf0.1_n		98.58 32	98.44 35	98.99 65	97.73 284	97.15 112	98.84 137	98.97 53	98.75 9	99.43 39	99.54 18	93.29 111	99.93 32	99.64 18	99.79 30	99.89 6

SMA-MVS		98.58 32	98.25 58	99.56 8	99.51 42	99.04 15	98.95 97	98.80 108	93.67 283	99.37 43	99.52 21	96.52 22	99.89 62	98.06 83	99.81 15	99.76 42
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 32	98.29 56	99.46 14	99.76 2	98.64 25	98.90 111	98.74 123	97.27 69	98.02 140	99.39 46	94.81 84	99.96 4	97.91 92	99.79 30	99.77 35

HPM-MVS++		98.58 32	98.25 58	99.55 9	99.50 44	99.08 11	98.72 177	98.66 148	97.51 47	98.15 126	98.83 161	95.70 49	99.92 41	97.53 124	99.67 70	99.66 77

SR-MVS		98.57 36	98.35 43	99.24 41	99.53 38	98.18 56	99.09 65	98.82 95	96.58 108	99.10 62	99.32 63	95.39 58	99.82 91	97.70 109	99.63 83	99.72 54

CP-MVS		98.57 36	98.36 41	99.19 46	99.66 28	97.86 70	99.34 17	98.87 80	95.96 138	98.60 106	99.13 101	96.05 37	99.94 13	97.77 101	99.86 2	99.77 35

MSLP-MVS++		98.56 38	98.57 23	98.55 101	99.26 89	96.80 127	98.71 178	99.05 46	97.28 65	98.84 81	99.28 70	96.47 23	99.40 200	98.52 59	99.70 66	99.47 110

DeepC-MVS_fast	96.70 1	98.55 39	98.34 49	99.18 48	99.25 90	98.04 64	98.50 230	98.78 115	97.72 32	98.92 77	99.28 70	95.27 67	99.82 91	97.55 122	99.77 37	99.69 65
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 40	98.35 43	99.13 54	99.49 48	97.86 70	99.11 61	98.80 108	96.49 112	99.17 57	99.35 58	95.34 63	99.82 91	97.72 104	99.65 76	99.71 58

fmvsm_s_conf0.5_n_5		98.53 41	98.35 43	99.08 59	99.07 120	97.46 89	98.68 187	99.20 30	97.50 48	99.87 4	99.50 27	91.96 145	99.96 4	99.76 9	99.65 76	99.82 20

fmvsm_s_conf0.5_n_3		98.53 41	98.45 34	98.79 80	99.23 98	97.32 94	98.80 150	99.26 16	98.82 5	99.87 4	99.60 9	90.95 185	99.93 32	99.76 9	99.73 57	99.12 185

APD-MVS_3200maxsize		98.53 41	98.33 53	99.15 52	99.50 44	97.92 69	99.15 52	98.81 101	96.24 124	99.20 54	99.37 52	95.30 65	99.80 103	97.73 103	99.67 70	99.72 54

MM		98.51 44	98.24 60	99.33 31	99.12 114	98.14 61	98.93 106	97.02 393	98.96 1	99.17 57	99.47 33	91.97 144	99.94 13	99.85 5	99.69 67	99.91 4

mPP-MVS		98.51 44	98.26 57	99.25 40	99.75 3	98.04 64	99.28 25	98.81 101	96.24 124	98.35 122	99.23 80	95.46 55	99.94 13	97.42 133	99.81 15	99.77 35

ZNCC-MVS		98.49 46	98.20 66	99.35 26	99.73 13	98.39 35	99.19 45	98.86 86	95.77 148	98.31 125	99.10 108	95.46 55	99.93 32	97.57 121	99.81 15	99.74 45

SPE-MVS-test		98.49 46	98.50 29	98.46 116	99.20 103	97.05 117	99.64 4	98.50 193	97.45 54	98.88 78	99.14 100	95.25 69	99.15 239	98.83 38	99.56 102	99.20 169

PGM-MVS		98.49 46	98.23 62	99.27 39	99.72 14	98.08 63	98.99 87	99.49 5	95.43 167	99.03 63	99.32 63	95.56 52	99.94 13	96.80 170	99.77 37	99.78 28

EI-MVSNet-Vis-set		98.47 49	98.39 38	98.69 88	99.46 54	96.49 146	98.30 260	98.69 137	97.21 72	98.84 81	99.36 56	95.41 57	99.78 118	98.62 47	99.65 76	99.80 25

MVS_111021_HR		98.47 49	98.34 49	98.88 77	99.22 100	97.32 94	97.91 317	99.58 3	97.20 73	98.33 123	99.00 131	95.99 40	99.64 150	98.05 85	99.76 43	99.69 65

balanced_conf03		98.45 51	98.35 43	98.74 84	98.65 170	97.55 81	99.19 45	98.60 159	96.72 102	99.35 44	98.77 173	95.06 79	99.55 173	98.95 33	99.87 1	99.12 185

test_fmvsmvis_n_1920		98.44 52	98.51 27	98.23 138	98.33 207	96.15 163	98.97 91	99.15 38	98.55 14	98.45 115	99.55 16	94.26 97	99.97 1	99.65 16	99.66 73	98.57 260

CS-MVS		98.44 52	98.49 31	98.31 130	99.08 119	96.73 131	99.67 3	98.47 200	97.17 76	98.94 71	99.10 108	95.73 48	99.13 244	98.71 42	99.49 113	99.09 193

GST-MVS		98.43 54	98.12 70	99.34 27	99.72 14	98.38 36	99.09 65	98.82 95	95.71 152	98.73 92	99.06 122	95.27 67	99.93 32	97.07 148	99.63 83	99.72 54

fmvsm_s_conf0.5_n		98.42 55	98.51 27	98.13 150	99.30 77	95.25 220	98.85 133	99.39 7	97.94 27	99.74 19	99.62 3	92.59 120	99.91 51	99.65 16	99.52 108	99.25 162

EI-MVSNet-UG-set		98.41 56	98.34 49	98.61 95	99.45 57	96.32 156	98.28 263	98.68 140	97.17 76	98.74 90	99.37 52	95.25 69	99.79 115	98.57 50	99.54 105	99.73 50

DELS-MVS		98.40 57	98.20 66	98.99 65	99.00 128	97.66 76	97.75 338	98.89 70	97.71 34	98.33 123	98.97 133	94.97 81	99.88 71	98.42 67	99.76 43	99.42 123
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 58	98.42 36	98.27 132	99.09 118	95.41 210	98.86 129	99.37 9	97.69 36	99.78 15	99.61 4	92.38 124	99.91 51	99.58 21	99.43 121	99.49 106

TSAR-MVS + GP.		98.38 58	98.24 60	98.81 79	99.22 100	97.25 107	98.11 292	98.29 253	97.19 74	98.99 69	99.02 125	96.22 30	99.67 143	98.52 59	98.56 177	99.51 99

HPM-MVS_fast		98.38 58	98.13 69	99.12 56	99.75 3	97.86 70	99.44 9	98.82 95	94.46 238	98.94 71	99.20 86	95.16 74	99.74 128	97.58 117	99.85 6	99.77 35

patch_mono-2		98.36 61	98.87 6	96.82 257	99.53 38	90.68 370	98.64 198	99.29 15	97.88 28	99.19 56	99.52 21	96.80 15	99.97 1	99.11 29	99.86 2	99.82 20

HPM-MVS		98.36 61	98.10 73	99.13 54	99.74 9	97.82 75	99.53 6	98.80 108	94.63 225	98.61 105	98.97 133	95.13 76	99.77 123	97.65 112	99.83 13	99.79 26
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 63	98.50 29	97.90 173	99.16 109	95.08 229	98.75 163	99.24 20	98.39 17	99.81 11	99.52 21	92.35 125	99.90 59	99.74 11	99.51 110	98.71 241

APD-MVS		98.35 63	98.00 79	99.42 17	99.51 42	98.72 21	98.80 150	98.82 95	94.52 233	99.23 53	99.25 79	95.54 54	99.80 103	96.52 179	99.77 37	99.74 45
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_LR		98.34 65	98.23 62	98.67 90	99.27 87	96.90 123	97.95 310	99.58 3	97.14 79	98.44 117	99.01 129	95.03 80	99.62 157	97.91 92	99.75 50	99.50 101

PHI-MVS		98.34 65	98.06 74	99.18 48	99.15 112	98.12 62	99.04 74	99.09 41	93.32 299	98.83 84	99.10 108	96.54 21	99.83 84	97.70 109	99.76 43	99.59 89

MP-MVS		98.33 67	98.01 78	99.28 37	99.75 3	98.18 56	99.22 37	98.79 113	96.13 129	97.92 152	99.23 80	94.54 87	99.94 13	96.74 173	99.78 35	99.73 50
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MVSMamba_PlusPlus		98.31 68	98.19 68	98.67 90	98.96 135	97.36 92	99.24 31	98.57 173	94.81 213	98.99 69	98.90 149	95.22 72	99.59 160	99.15 28	99.84 11	99.07 201

MP-MVS-pluss		98.31 68	97.92 81	99.49 12	99.72 14	98.88 18	98.43 244	98.78 115	94.10 248	97.69 171	99.42 42	95.25 69	99.92 41	98.09 82	99.80 24	99.67 74
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.5_n_2		98.30 70	98.21 64	98.57 98	99.25 90	97.11 114	98.66 194	99.20 30	98.82 5	99.79 13	99.60 9	89.38 223	99.92 41	99.80 7	99.38 128	98.69 243

fmvsm_s_conf0.5_n_7		98.23 71	98.35 43	97.89 175	98.86 145	94.99 235	98.58 210	99.00 49	98.29 18	99.73 20	99.60 9	91.70 150	99.92 41	99.63 19	99.73 57	98.76 235

MVS_0304		98.23 71	97.91 82	99.21 45	98.06 247	97.96 68	98.58 210	95.51 432	98.58 12	98.87 79	99.26 74	92.99 115	99.95 9	99.62 20	99.67 70	99.73 50

ACMMP		98.23 71	97.95 80	99.09 58	99.74 9	97.62 79	99.03 77	99.41 6	95.98 137	97.60 182	99.36 56	94.45 92	99.93 32	97.14 145	98.85 161	99.70 62
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 74	98.11 71	98.49 113	98.34 204	97.26 106	99.61 5	98.43 213	96.78 95	98.87 79	98.84 157	93.72 105	99.01 268	98.91 35	99.50 111	99.19 173

fmvsm_s_conf0.1_n		98.18 75	98.21 64	98.11 154	98.54 179	95.24 221	98.87 125	99.24 20	97.50 48	99.70 24	99.67 1	91.33 166	99.89 62	99.47 23	99.54 105	99.21 168

fmvsm_s_conf0.1_n_2		98.14 76	98.02 77	98.53 106	98.88 141	97.07 116	98.69 185	98.82 95	98.78 7	99.77 16	99.61 4	88.83 243	99.91 51	99.71 13	99.07 144	98.61 253

fmvsm_s_conf0.1_n_a		98.08 77	98.04 76	98.21 139	97.66 290	95.39 211	98.89 115	99.17 34	97.24 70	99.76 18	99.67 1	91.13 176	99.88 71	99.39 24	99.41 123	99.35 134

dcpmvs_2		98.08 77	98.59 22	96.56 286	99.57 35	90.34 382	99.15 52	98.38 228	96.82 94	99.29 48	99.49 30	95.78 47	99.57 163	98.94 34	99.86 2	99.77 35

NormalMVS		98.07 79	97.90 83	98.59 97	99.75 3	96.60 137	98.94 100	98.60 159	97.86 29	98.71 95	99.08 118	91.22 172	99.80 103	97.40 135	99.57 94	99.37 130

CANet		98.05 80	97.76 86	98.90 76	98.73 155	97.27 101	98.35 250	98.78 115	97.37 60	97.72 168	98.96 138	91.53 159	99.92 41	98.79 39	99.65 76	99.51 99

train_agg		97.97 81	97.52 99	99.33 31	99.31 73	98.50 30	97.92 315	98.73 126	92.98 315	97.74 165	98.68 186	96.20 32	99.80 103	96.59 174	99.57 94	99.68 70

ETV-MVS		97.96 82	97.81 84	98.40 125	98.42 190	97.27 101	98.73 173	98.55 178	96.84 92	98.38 119	97.44 308	95.39 58	99.35 205	97.62 114	98.89 155	98.58 259

UA-Net		97.96 82	97.62 90	98.98 67	98.86 145	97.47 87	98.89 115	99.08 42	96.67 105	98.72 94	99.54 18	93.15 113	99.81 96	94.87 237	98.83 162	99.65 78

CDPH-MVS		97.94 84	97.49 101	99.28 37	99.47 52	98.44 32	97.91 317	98.67 145	92.57 331	98.77 88	98.85 156	95.93 42	99.72 130	95.56 215	99.69 67	99.68 70

DeepPCF-MVS	96.37 2	97.93 85	98.48 33	96.30 312	99.00 128	89.54 398	97.43 360	98.87 80	98.16 20	99.26 52	99.38 51	96.12 35	99.64 150	98.30 72	99.77 37	99.72 54

DeepC-MVS	95.98 3	97.88 86	97.58 92	98.77 82	99.25 90	96.93 121	98.83 139	98.75 121	96.96 88	96.89 213	99.50 27	90.46 195	99.87 73	97.84 98	99.76 43	99.52 96
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 87	97.54 98	98.83 78	95.48 413	96.83 126	98.95 97	98.60 159	98.58 12	98.93 75	99.55 16	88.57 248	99.91 51	99.54 22	99.61 86	99.77 35

DP-MVS Recon		97.86 87	97.46 104	99.06 61	99.53 38	98.35 45	98.33 252	98.89 70	92.62 328	98.05 135	98.94 141	95.34 63	99.65 147	96.04 195	99.42 122	99.19 173

CSCG		97.85 89	97.74 87	98.20 141	99.67 27	95.16 224	99.22 37	99.32 12	93.04 313	97.02 206	98.92 147	95.36 61	99.91 51	97.43 132	99.64 81	99.52 96

SymmetryMVS		97.84 90	97.58 92	98.62 94	99.01 126	96.60 137	98.94 100	98.44 205	97.86 29	98.71 95	99.08 118	91.22 172	99.80 103	97.40 135	97.53 234	99.47 110

BP-MVS1		97.82 91	97.51 100	98.76 83	98.25 217	97.39 91	99.15 52	97.68 325	96.69 103	98.47 111	99.10 108	90.29 199	99.51 180	98.60 48	99.35 131	99.37 130

MG-MVS		97.81 92	97.60 91	98.44 119	99.12 114	95.97 173	97.75 338	98.78 115	96.89 91	98.46 112	99.22 82	93.90 104	99.68 142	94.81 241	99.52 108	99.67 74

VNet		97.79 93	97.40 109	98.96 70	98.88 141	97.55 81	98.63 201	98.93 61	96.74 99	99.02 64	98.84 157	90.33 198	99.83 84	98.53 53	96.66 257	99.50 101

EIA-MVS		97.75 94	97.58 92	98.27 132	98.38 195	96.44 148	99.01 82	98.60 159	95.88 142	97.26 192	97.53 302	94.97 81	99.33 208	97.38 138	99.20 140	99.05 202

PS-MVSNAJ		97.73 95	97.77 85	97.62 204	98.68 165	95.58 200	97.34 369	98.51 188	97.29 63	98.66 102	97.88 266	94.51 88	99.90 59	97.87 95	99.17 142	97.39 303

casdiffmvs_mvg		97.72 96	97.48 103	98.44 119	98.42 190	96.59 141	98.92 108	98.44 205	96.20 126	97.76 162	99.20 86	91.66 153	99.23 227	98.27 76	98.41 194	99.49 106
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 96	97.32 114	98.92 73	99.64 30	97.10 115	99.12 59	98.81 101	92.34 339	98.09 131	99.08 118	93.01 114	99.92 41	96.06 194	99.77 37	99.75 43

PVSNet_Blended_VisFu		97.70 98	97.46 104	98.44 119	99.27 87	95.91 181	98.63 201	99.16 36	94.48 237	97.67 172	98.88 153	92.80 117	99.91 51	97.11 146	99.12 143	99.50 101

mvsany_test1		97.69 99	97.70 88	97.66 201	98.24 218	94.18 277	97.53 354	97.53 346	95.52 162	99.66 26	99.51 24	94.30 95	99.56 166	98.38 68	98.62 172	99.23 164

sasdasda		97.67 100	97.23 121	98.98 67	98.70 160	98.38 36	99.34 17	98.39 224	96.76 97	97.67 172	97.40 312	92.26 130	99.49 184	98.28 73	96.28 275	99.08 197

canonicalmvs		97.67 100	97.23 121	98.98 67	98.70 160	98.38 36	99.34 17	98.39 224	96.76 97	97.67 172	97.40 312	92.26 130	99.49 184	98.28 73	96.28 275	99.08 197

xiu_mvs_v2_base		97.66 102	97.70 88	97.56 208	98.61 174	95.46 208	97.44 358	98.46 201	97.15 78	98.65 103	98.15 241	94.33 94	99.80 103	97.84 98	98.66 171	97.41 301

GDP-MVS		97.64 103	97.28 116	98.71 87	98.30 212	97.33 93	99.05 70	98.52 185	96.34 121	98.80 85	99.05 123	89.74 210	99.51 180	96.86 167	98.86 159	99.28 152

baseline		97.64 103	97.44 106	98.25 136	98.35 199	96.20 160	99.00 84	98.32 240	96.33 123	98.03 138	99.17 93	91.35 165	99.16 236	98.10 81	98.29 203	99.39 127

casdiffmvs		97.63 105	97.41 108	98.28 131	98.33 207	96.14 164	98.82 141	98.32 240	96.38 119	97.95 147	99.21 84	91.23 171	99.23 227	98.12 80	98.37 196	99.48 108
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MGCFI-Net		97.62 106	97.19 124	98.92 73	98.66 167	98.20 54	99.32 22	98.38 228	96.69 103	97.58 184	97.42 311	92.10 138	99.50 183	98.28 73	96.25 278	99.08 197

xiu_mvs_v1_base_debu		97.60 107	97.56 95	97.72 190	98.35 199	95.98 168	97.86 327	98.51 188	97.13 80	99.01 66	98.40 213	91.56 155	99.80 103	98.53 53	98.68 167	97.37 305

xiu_mvs_v1_base		97.60 107	97.56 95	97.72 190	98.35 199	95.98 168	97.86 327	98.51 188	97.13 80	99.01 66	98.40 213	91.56 155	99.80 103	98.53 53	98.68 167	97.37 305

xiu_mvs_v1_base_debi		97.60 107	97.56 95	97.72 190	98.35 199	95.98 168	97.86 327	98.51 188	97.13 80	99.01 66	98.40 213	91.56 155	99.80 103	98.53 53	98.68 167	97.37 305

diffmvs_AUTHOR		97.59 110	97.44 106	98.01 166	98.26 216	95.47 207	98.12 289	98.36 233	96.38 119	98.84 81	99.10 108	91.13 176	99.26 220	98.24 77	98.56 177	99.30 147

diffmvs		97.58 111	97.40 109	98.13 150	98.32 210	95.81 193	98.06 298	98.37 230	96.20 126	98.74 90	98.89 152	91.31 168	99.25 223	98.16 79	98.52 181	99.34 136
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		97.57 112	97.37 111	98.20 141	98.50 181	95.86 188	98.89 115	97.03 390	97.29 63	98.73 92	98.90 149	89.41 222	99.32 209	98.68 43	98.86 159	99.42 123

MVSFormer		97.57 112	97.49 101	97.84 177	98.07 244	95.76 195	99.47 7	98.40 219	94.98 202	98.79 86	98.83 161	92.34 126	98.41 342	96.91 155	99.59 90	99.34 136

alignmvs		97.56 114	97.07 131	99.01 64	98.66 167	98.37 43	98.83 139	98.06 305	96.74 99	98.00 144	97.65 289	90.80 187	99.48 189	98.37 69	96.56 261	99.19 173

DPM-MVS		97.55 115	96.99 137	99.23 44	99.04 122	98.55 28	97.17 386	98.35 234	94.85 212	97.93 151	98.58 196	95.07 78	99.71 135	92.60 315	99.34 132	99.43 120

OMC-MVS		97.55 115	97.34 113	98.20 141	99.33 68	95.92 180	98.28 263	98.59 166	95.52 162	97.97 145	99.10 108	93.28 112	99.49 184	95.09 232	98.88 156	99.19 173

viewcassd2359sk11		97.53 117	97.32 114	98.16 145	98.45 188	95.83 190	98.57 217	98.42 216	95.52 162	98.07 132	99.12 104	91.81 148	99.25 223	97.46 131	98.48 186	99.41 126

LuminaMVS		97.49 118	97.18 125	98.42 123	97.50 305	97.15 112	98.45 237	97.68 325	96.56 111	98.68 97	98.78 170	89.84 207	99.32 209	98.60 48	98.57 176	98.79 227

KinetiMVS		97.48 119	97.05 133	98.78 81	98.37 197	97.30 97	98.99 87	98.70 135	97.18 75	99.02 64	99.01 129	87.50 277	99.67 143	95.33 222	99.33 134	99.37 130

viewmanbaseed2359cas		97.47 120	97.25 118	98.14 146	98.41 192	95.84 189	98.57 217	98.43 213	95.55 160	97.97 145	99.12 104	91.26 170	99.15 239	97.42 133	98.53 180	99.43 120

PAPM_NR		97.46 121	97.11 128	98.50 111	99.50 44	96.41 151	98.63 201	98.60 159	95.18 183	97.06 204	98.06 247	94.26 97	99.57 163	93.80 283	98.87 158	99.52 96

EPP-MVSNet		97.46 121	97.28 116	97.99 168	98.64 171	95.38 212	99.33 21	98.31 244	93.61 287	97.19 196	99.07 121	94.05 100	99.23 227	96.89 159	98.43 189	99.37 130

3Dnovator	94.51 5	97.46 121	96.93 141	99.07 60	97.78 278	97.64 77	99.35 16	99.06 44	97.02 85	93.75 330	99.16 96	89.25 227	99.92 41	97.22 144	99.75 50	99.64 81

CNLPA		97.45 124	97.03 134	98.73 85	99.05 121	97.44 90	98.07 297	98.53 182	95.32 176	96.80 218	98.53 201	93.32 110	99.72 130	94.31 264	99.31 135	99.02 206

lupinMVS		97.44 125	97.22 123	98.12 153	98.07 244	95.76 195	97.68 343	97.76 322	94.50 236	98.79 86	98.61 191	92.34 126	99.30 213	97.58 117	99.59 90	99.31 144

3Dnovator+	94.38 6	97.43 126	96.78 151	99.38 19	97.83 275	98.52 29	99.37 13	98.71 131	97.09 83	92.99 360	99.13 101	89.36 224	99.89 62	96.97 151	99.57 94	99.71 58

Vis-MVSNet		97.42 127	97.11 128	98.34 128	98.66 167	96.23 159	99.22 37	99.00 49	96.63 107	98.04 137	99.21 84	88.05 264	99.35 205	96.01 197	99.21 139	99.45 117
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
API-MVS		97.41 128	97.25 118	97.91 172	98.70 160	96.80 127	98.82 141	98.69 137	94.53 231	98.11 129	98.28 228	94.50 91	99.57 163	94.12 272	99.49 113	97.37 305

sss		97.39 129	96.98 139	98.61 95	98.60 175	96.61 136	98.22 269	98.93 61	93.97 258	98.01 143	98.48 206	91.98 142	99.85 78	96.45 181	98.15 205	99.39 127

test_cas_vis1_n_1920		97.38 130	97.36 112	97.45 212	98.95 136	93.25 315	99.00 84	98.53 182	97.70 35	99.77 16	99.35 58	84.71 333	99.85 78	98.57 50	99.66 73	99.26 160

PVSNet_Blended		97.38 130	97.12 127	98.14 146	99.25 90	95.35 215	97.28 374	99.26 16	93.13 309	97.94 149	98.21 236	92.74 118	99.81 96	96.88 161	99.40 126	99.27 153

WTY-MVS		97.37 132	96.92 142	98.72 86	98.86 145	96.89 125	98.31 257	98.71 131	95.26 179	97.67 172	98.56 200	92.21 134	99.78 118	95.89 199	96.85 251	99.48 108

AstraMVS		97.34 133	97.24 120	97.65 202	98.13 238	94.15 278	98.94 100	96.25 422	97.47 52	98.60 106	99.28 70	89.67 212	99.41 199	98.73 41	98.07 209	99.38 129

viewmacassd2359aftdt		97.32 134	97.07 131	98.08 157	98.30 212	95.69 197	98.62 204	98.44 205	95.56 158	97.86 157	99.22 82	89.91 205	99.14 242	97.29 141	98.43 189	99.42 123

jason		97.32 134	97.08 130	98.06 161	97.45 311	95.59 199	97.87 325	97.91 316	94.79 215	98.55 109	98.83 161	91.12 178	99.23 227	97.58 117	99.60 88	99.34 136
jason: jason.
MVS_Test		97.28 136	97.00 135	98.13 150	98.33 207	95.97 173	98.74 167	98.07 300	94.27 243	98.44 117	98.07 246	92.48 122	99.26 220	96.43 182	98.19 204	99.16 179

EPNet		97.28 136	96.87 144	98.51 108	94.98 422	96.14 164	98.90 111	97.02 393	98.28 19	95.99 253	99.11 106	91.36 164	99.89 62	96.98 150	99.19 141	99.50 101
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SSM_0404		97.26 138	97.00 135	98.03 163	98.46 186	95.99 167	98.62 204	98.44 205	94.77 216	97.24 193	98.93 143	91.22 172	99.28 217	96.54 176	98.74 166	98.84 223

mvsmamba		97.25 139	96.99 137	98.02 165	98.34 204	95.54 204	99.18 49	97.47 352	95.04 196	98.15 126	98.57 199	89.46 219	99.31 212	97.68 111	99.01 149	99.22 166

viewdifsd2359ckpt13		97.24 140	96.97 140	98.06 161	98.43 189	95.77 194	98.59 207	98.34 237	94.81 213	97.60 182	98.94 141	90.78 191	99.09 254	96.93 154	98.33 199	99.32 143

test_yl		97.22 141	96.78 151	98.54 103	98.73 155	96.60 137	98.45 237	98.31 244	94.70 219	98.02 140	98.42 211	90.80 187	99.70 136	96.81 168	96.79 253	99.34 136

DCV-MVSNet		97.22 141	96.78 151	98.54 103	98.73 155	96.60 137	98.45 237	98.31 244	94.70 219	98.02 140	98.42 211	90.80 187	99.70 136	96.81 168	96.79 253	99.34 136

IS-MVSNet		97.22 141	96.88 143	98.25 136	98.85 148	96.36 154	99.19 45	97.97 310	95.39 170	97.23 194	98.99 132	91.11 179	98.93 280	94.60 252	98.59 174	99.47 110

PLC	95.07 4	97.20 144	96.78 151	98.44 119	99.29 82	96.31 158	98.14 286	98.76 119	92.41 337	96.39 241	98.31 226	94.92 83	99.78 118	94.06 275	98.77 165	99.23 164
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		97.18 145	97.18 125	97.20 225	98.81 151	93.27 312	95.78 431	99.15 38	95.25 180	96.79 219	98.11 244	92.29 129	99.07 257	98.56 52	99.85 6	99.25 162

SSM_0407		97.17 146	96.87 144	98.08 157	98.19 226	95.90 182	98.52 223	98.44 205	94.77 216	96.75 220	98.93 143	91.22 172	99.22 231	96.54 176	98.43 189	99.10 190

LS3D		97.16 147	96.66 160	98.68 89	98.53 180	97.19 110	98.93 106	98.90 68	92.83 322	95.99 253	99.37 52	92.12 137	99.87 73	93.67 287	99.57 94	98.97 211

AdaColmap		97.15 148	96.70 156	98.48 114	99.16 109	96.69 133	98.01 304	98.89 70	94.44 239	96.83 214	98.68 186	90.69 192	99.76 124	94.36 260	99.29 136	98.98 210

mamv4		97.13 149	98.11 71	94.17 396	98.97 134	83.70 441	98.66 194	98.71 131	94.63 225	97.83 158	98.90 149	96.25 29	99.55 173	99.27 26	99.76 43	99.27 153

Effi-MVS+		97.12 150	96.69 157	98.39 126	98.19 226	96.72 132	97.37 365	98.43 213	93.71 276	97.65 176	98.02 250	92.20 135	99.25 223	96.87 164	97.79 218	99.19 173

CHOSEN 1792x2688		97.12 150	96.80 148	98.08 157	99.30 77	94.56 260	98.05 299	99.71 1	93.57 289	97.09 200	98.91 148	88.17 258	99.89 62	96.87 164	99.56 102	99.81 22

F-COLMAP		97.09 152	96.80 148	97.97 169	99.45 57	94.95 239	98.55 221	98.62 158	93.02 314	96.17 248	98.58 196	94.01 101	99.81 96	93.95 277	98.90 154	99.14 183

RRT-MVS		97.03 153	96.78 151	97.77 186	97.90 271	94.34 269	99.12 59	98.35 234	95.87 143	98.06 134	98.70 184	86.45 296	99.63 153	98.04 86	98.54 179	99.35 134

TAMVS		97.02 154	96.79 150	97.70 193	98.06 247	95.31 218	98.52 223	98.31 244	93.95 259	97.05 205	98.61 191	93.49 108	98.52 324	95.33 222	97.81 217	99.29 150

viewmambaseed2359dif		97.01 155	96.84 146	97.51 210	98.19 226	94.21 276	98.16 282	98.23 265	93.61 287	97.78 160	99.13 101	90.79 190	99.18 235	97.24 142	98.40 195	99.15 180

CDS-MVSNet		96.99 156	96.69 157	97.90 173	98.05 249	95.98 168	98.20 272	98.33 239	93.67 283	96.95 207	98.49 205	93.54 107	98.42 335	95.24 229	97.74 221	99.31 144
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CANet_DTU		96.96 157	96.55 165	98.21 139	98.17 235	96.07 166	97.98 308	98.21 267	97.24 70	97.13 198	98.93 143	86.88 288	99.91 51	95.00 235	99.37 130	98.66 249

114514_t		96.93 158	96.27 178	98.92 73	99.50 44	97.63 78	98.85 133	98.90 68	84.80 437	97.77 161	99.11 106	92.84 116	99.66 146	94.85 238	99.77 37	99.47 110

MAR-MVS		96.91 159	96.40 172	98.45 117	98.69 163	96.90 123	98.66 194	98.68 140	92.40 338	97.07 203	97.96 257	91.54 158	99.75 126	93.68 285	98.92 153	98.69 243
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		96.90 160	96.49 169	98.14 146	99.33 68	95.56 201	97.38 363	99.65 2	92.34 339	97.61 179	98.20 237	89.29 226	99.10 253	96.97 151	97.60 226	99.77 35

Vis-MVSNet (Re-imp)		96.87 161	96.55 165	97.83 178	98.73 155	95.46 208	99.20 43	98.30 251	94.96 204	96.60 229	98.87 154	90.05 202	98.59 319	93.67 287	98.60 173	99.46 115

SDMVSNet		96.85 162	96.42 170	98.14 146	99.30 77	96.38 152	99.21 40	99.23 25	95.92 139	95.96 255	98.76 178	85.88 308	99.44 196	97.93 90	95.59 290	98.60 254

PAPR		96.84 163	96.24 180	98.65 92	98.72 159	96.92 122	97.36 367	98.57 173	93.33 298	96.67 224	97.57 298	94.30 95	99.56 166	91.05 358	98.59 174	99.47 110

HY-MVS	93.96 8	96.82 164	96.23 181	98.57 98	98.46 186	97.00 118	98.14 286	98.21 267	93.95 259	96.72 223	97.99 254	91.58 154	99.76 124	94.51 256	96.54 262	98.95 214

mamba_0408		96.81 165	96.38 173	98.09 156	98.19 226	95.90 182	95.69 432	98.32 240	94.51 234	96.75 220	98.73 180	90.99 183	99.27 219	95.83 202	98.43 189	99.10 190

UGNet		96.78 166	96.30 177	98.19 144	98.24 218	95.89 186	98.88 122	98.93 61	97.39 57	96.81 217	97.84 270	82.60 362	99.90 59	96.53 178	99.49 113	98.79 227
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		96.74 167	96.64 161	97.05 240	97.99 258	92.82 327	98.45 237	98.27 254	95.16 184	97.30 189	98.79 166	91.53 159	99.06 258	94.74 243	97.54 230	99.27 153

IMVS_0403		96.74 167	96.61 162	97.12 234	97.99 258	92.82 327	98.47 235	98.27 254	95.16 184	97.13 198	98.79 166	91.44 162	99.26 220	94.74 243	97.54 230	99.27 153

PVSNet_BlendedMVS		96.73 169	96.60 163	97.12 234	99.25 90	95.35 215	98.26 266	99.26 16	94.28 242	97.94 149	97.46 305	92.74 118	99.81 96	96.88 161	93.32 328	96.20 398

SSM_04072		96.71 170	96.38 173	97.68 196	98.19 226	95.90 182	95.69 432	98.32 240	94.51 234	96.75 220	98.73 180	90.99 183	98.02 381	95.83 202	98.43 189	99.10 190

test_vis1_n_1920		96.71 170	96.84 146	96.31 311	99.11 116	89.74 391	99.05 70	98.58 171	98.08 22	99.87 4	99.37 52	78.48 394	99.93 32	99.29 25	99.69 67	99.27 153

mvs_anonymous		96.70 172	96.53 167	97.18 228	98.19 226	93.78 288	98.31 257	98.19 271	94.01 255	94.47 287	98.27 231	92.08 140	98.46 330	97.39 137	97.91 213	99.31 144

Elysia		96.64 173	96.02 190	98.51 108	98.04 251	97.30 97	98.74 167	98.60 159	95.04 196	97.91 153	98.84 157	83.59 357	99.48 189	94.20 268	99.25 137	98.75 236

StellarMVS		96.64 173	96.02 190	98.51 108	98.04 251	97.30 97	98.74 167	98.60 159	95.04 196	97.91 153	98.84 157	83.59 357	99.48 189	94.20 268	99.25 137	98.75 236

1112_ss		96.63 175	96.00 192	98.50 111	98.56 176	96.37 153	98.18 280	98.10 293	92.92 318	94.84 275	98.43 209	92.14 136	99.58 162	94.35 261	96.51 263	99.56 95

PMMVS		96.60 176	96.33 176	97.41 216	97.90 271	93.93 284	97.35 368	98.41 217	92.84 321	97.76 162	97.45 307	91.10 180	99.20 232	96.26 187	97.91 213	99.11 188

DP-MVS		96.59 177	95.93 195	98.57 98	99.34 65	96.19 162	98.70 182	98.39 224	89.45 408	94.52 285	99.35 58	91.85 146	99.85 78	92.89 311	98.88 156	99.68 70

PatchMatch-RL		96.59 177	96.03 189	98.27 132	99.31 73	96.51 145	97.91 317	99.06 44	93.72 275	96.92 211	98.06 247	88.50 253	99.65 147	91.77 340	99.00 151	98.66 249

GeoE		96.58 179	96.07 186	98.10 155	98.35 199	95.89 186	99.34 17	98.12 287	93.12 310	96.09 249	98.87 154	89.71 211	98.97 270	92.95 307	98.08 208	99.43 120

icg_test_0407_2		96.56 180	96.50 168	96.73 263	97.99 258	92.82 327	97.18 383	98.27 254	95.16 184	97.30 189	98.79 166	91.53 159	98.10 372	94.74 243	97.54 230	99.27 153

XVG-OURS		96.55 181	96.41 171	96.99 243	98.75 154	93.76 289	97.50 357	98.52 185	95.67 154	96.83 214	99.30 68	88.95 241	99.53 176	95.88 200	96.26 277	97.69 294

FIs		96.51 182	96.12 185	97.67 198	97.13 335	97.54 83	99.36 14	99.22 29	95.89 141	94.03 316	98.35 219	91.98 142	98.44 333	96.40 183	92.76 336	97.01 313

XVG-OURS-SEG-HR		96.51 182	96.34 175	97.02 242	98.77 153	93.76 289	97.79 336	98.50 193	95.45 166	96.94 208	99.09 116	87.87 269	99.55 173	96.76 172	95.83 289	97.74 291

PS-MVSNAJss		96.43 184	96.26 179	96.92 252	95.84 402	95.08 229	99.16 51	98.50 193	95.87 143	93.84 325	98.34 223	94.51 88	98.61 315	96.88 161	93.45 323	97.06 311

test_fmvs1		96.42 185	96.67 159	95.66 341	98.82 150	88.53 418	98.80 150	98.20 269	96.39 118	99.64 28	99.20 86	80.35 382	99.67 143	99.04 31	99.57 94	98.78 231

FC-MVSNet-test		96.42 185	96.05 187	97.53 209	96.95 344	97.27 101	99.36 14	99.23 25	95.83 145	93.93 319	98.37 217	92.00 141	98.32 354	96.02 196	92.72 337	97.00 314

ab-mvs		96.42 185	95.71 206	98.55 101	98.63 172	96.75 130	97.88 324	98.74 123	93.84 265	96.54 234	98.18 239	85.34 319	99.75 126	95.93 198	96.35 267	99.15 180

FA-MVS(test-final)		96.41 188	95.94 194	97.82 180	98.21 222	95.20 223	97.80 334	97.58 336	93.21 304	97.36 188	97.70 282	89.47 217	99.56 166	94.12 272	97.99 210	98.71 241

PVSNet	91.96 18	96.35 189	96.15 182	96.96 247	99.17 105	92.05 343	96.08 424	98.68 140	93.69 279	97.75 164	97.80 276	88.86 242	99.69 141	94.26 266	99.01 149	99.15 180

Test_1112_low_res		96.34 190	95.66 211	98.36 127	98.56 176	95.94 176	97.71 341	98.07 300	92.10 348	94.79 279	97.29 320	91.75 149	99.56 166	94.17 270	96.50 264	99.58 93

viewdifsd2359ckpt11		96.30 191	96.13 183	96.81 258	98.10 241	92.10 339	98.49 233	98.40 219	96.02 134	97.61 179	99.31 65	86.37 298	99.29 215	97.52 125	93.36 327	99.04 203

viewmsd2359difaftdt		96.30 191	96.13 183	96.81 258	98.10 241	92.10 339	98.49 233	98.40 219	96.02 134	97.61 179	99.31 65	86.37 298	99.30 213	97.52 125	93.37 326	99.04 203

Effi-MVS+-dtu		96.29 193	96.56 164	95.51 346	97.89 273	90.22 383	98.80 150	98.10 293	96.57 110	96.45 239	96.66 377	90.81 186	98.91 283	95.72 209	97.99 210	97.40 302

QAPM		96.29 193	95.40 217	98.96 70	97.85 274	97.60 80	99.23 33	98.93 61	89.76 402	93.11 357	99.02 125	89.11 232	99.93 32	91.99 334	99.62 85	99.34 136

Fast-Effi-MVS+		96.28 195	95.70 208	98.03 163	98.29 214	95.97 173	98.58 210	98.25 263	91.74 356	95.29 268	97.23 325	91.03 182	99.15 239	92.90 309	97.96 212	98.97 211

nrg030		96.28 195	95.72 203	97.96 171	96.90 349	98.15 59	99.39 11	98.31 244	95.47 165	94.42 293	98.35 219	92.09 139	98.69 307	97.50 129	89.05 387	97.04 312

1314		96.25 197	95.73 202	97.79 182	97.13 335	95.55 203	98.19 275	98.59 166	93.47 293	92.03 386	97.82 274	91.33 166	99.49 184	94.62 251	98.44 187	98.32 274

sd_testset		96.17 198	95.76 201	97.42 215	99.30 77	94.34 269	98.82 141	99.08 42	95.92 139	95.96 255	98.76 178	82.83 361	99.32 209	95.56 215	95.59 290	98.60 254

h-mvs33		96.17 198	95.62 212	97.81 181	99.03 123	94.45 262	98.64 198	98.75 121	97.48 50	98.67 98	98.72 183	89.76 208	99.86 77	97.95 88	81.59 436	99.11 188

HQP_MVS		96.14 200	95.90 196	96.85 255	97.42 313	94.60 258	98.80 150	98.56 176	97.28 65	95.34 264	98.28 228	87.09 283	99.03 263	96.07 191	94.27 298	96.92 321

tttt0517		96.07 201	95.51 215	97.78 183	98.41 192	94.84 243	99.28 25	94.33 445	94.26 244	97.64 177	98.64 190	84.05 348	99.47 193	95.34 221	97.60 226	99.03 205

MVSTER		96.06 202	95.72 203	97.08 238	98.23 220	95.93 179	98.73 173	98.27 254	94.86 210	95.07 270	98.09 245	88.21 257	98.54 322	96.59 174	93.46 321	96.79 340

thisisatest0530		96.01 203	95.36 222	97.97 169	98.38 195	95.52 205	98.88 122	94.19 447	94.04 250	97.64 177	98.31 226	83.82 355	99.46 194	95.29 226	97.70 223	98.93 216

test_djsdf		96.00 204	95.69 209	96.93 249	95.72 404	95.49 206	99.47 7	98.40 219	94.98 202	94.58 283	97.86 267	89.16 230	98.41 342	96.91 155	94.12 306	96.88 330

EI-MVSNet		95.96 205	95.83 198	96.36 307	97.93 269	93.70 295	98.12 289	98.27 254	93.70 278	95.07 270	99.02 125	92.23 133	98.54 322	94.68 247	93.46 321	96.84 336

VortexMVS		95.95 206	95.79 199	96.42 303	98.29 214	93.96 283	98.68 187	98.31 244	96.02 134	94.29 301	97.57 298	89.47 217	98.37 349	97.51 128	91.93 344	96.94 319

ECVR-MVS		95.95 206	95.71 206	96.65 271	99.02 124	90.86 365	99.03 77	91.80 458	96.96 88	98.10 130	99.26 74	81.31 368	99.51 180	96.90 158	99.04 146	99.59 89

BH-untuned		95.95 206	95.72 203	96.65 271	98.55 178	92.26 335	98.23 268	97.79 321	93.73 273	94.62 282	98.01 252	88.97 240	99.00 269	93.04 304	98.51 182	98.68 245

test1111		95.94 209	95.78 200	96.41 304	98.99 131	90.12 384	99.04 74	92.45 457	96.99 87	98.03 138	99.27 73	81.40 367	99.48 189	96.87 164	99.04 146	99.63 83

MSDG		95.93 210	95.30 229	97.83 178	98.90 139	95.36 213	96.83 411	98.37 230	91.32 371	94.43 292	98.73 180	90.27 200	99.60 159	90.05 372	98.82 163	98.52 262

BH-RMVSNet		95.92 211	95.32 227	97.69 194	98.32 210	94.64 252	98.19 275	97.45 357	94.56 229	96.03 251	98.61 191	85.02 324	99.12 247	90.68 363	99.06 145	99.30 147

test_fmvs1_n		95.90 212	95.99 193	95.63 342	98.67 166	88.32 422	99.26 28	98.22 266	96.40 117	99.67 25	99.26 74	73.91 432	99.70 136	99.02 32	99.50 111	98.87 220

Fast-Effi-MVS+-dtu		95.87 213	95.85 197	95.91 328	97.74 283	91.74 349	98.69 185	98.15 283	95.56 158	94.92 273	97.68 287	88.98 239	98.79 301	93.19 299	97.78 219	97.20 309

LFMVS		95.86 214	94.98 244	98.47 115	98.87 144	96.32 156	98.84 137	96.02 423	93.40 296	98.62 104	99.20 86	74.99 425	99.63 153	97.72 104	97.20 239	99.46 115

baseline1		95.84 215	95.12 237	98.01 166	98.49 185	95.98 168	98.73 173	97.03 390	95.37 173	96.22 244	98.19 238	89.96 204	99.16 236	94.60 252	87.48 403	98.90 219

OpenMVS	93.04 13	95.83 216	95.00 242	98.32 129	97.18 332	97.32 94	99.21 40	98.97 53	89.96 398	91.14 395	99.05 123	86.64 291	99.92 41	93.38 293	99.47 116	97.73 292

IMVS_0404		95.82 217	95.52 213	96.73 263	97.99 258	92.82 327	97.23 376	98.27 254	95.16 184	94.31 299	98.79 166	85.63 312	98.10 372	94.74 243	97.54 230	99.27 153

VDD-MVS		95.82 217	95.23 231	97.61 205	98.84 149	93.98 282	98.68 187	97.40 361	95.02 200	97.95 147	99.34 62	74.37 431	99.78 118	98.64 46	96.80 252	99.08 197

UniMVSNet (Re)		95.78 219	95.19 233	97.58 206	96.99 342	97.47 87	98.79 158	99.18 33	95.60 156	93.92 320	97.04 347	91.68 151	98.48 326	95.80 206	87.66 402	96.79 340

VPA-MVSNet		95.75 220	95.11 238	97.69 194	97.24 324	97.27 101	98.94 100	99.23 25	95.13 189	95.51 262	97.32 318	85.73 310	98.91 283	97.33 140	89.55 378	96.89 329

HQP-MVS		95.72 221	95.40 217	96.69 269	97.20 328	94.25 274	98.05 299	98.46 201	96.43 114	94.45 288	97.73 279	86.75 289	98.96 274	95.30 224	94.18 302	96.86 335

hse-mvs2		95.71 222	95.30 229	96.93 249	98.50 181	93.53 300	98.36 249	98.10 293	97.48 50	98.67 98	97.99 254	89.76 208	99.02 266	97.95 88	80.91 442	98.22 277

UniMVSNet_NR-MVSNet		95.71 222	95.15 234	97.40 218	96.84 352	96.97 119	98.74 167	99.24 20	95.16 184	93.88 322	97.72 281	91.68 151	98.31 356	95.81 204	87.25 408	96.92 321

PatchmatchNet		95.71 222	95.52 213	96.29 313	97.58 296	90.72 369	96.84 410	97.52 347	94.06 249	97.08 201	96.96 357	89.24 228	98.90 286	92.03 333	98.37 196	99.26 160
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
OPM-MVS		95.69 225	95.33 226	96.76 262	96.16 388	94.63 253	98.43 244	98.39 224	96.64 106	95.02 272	98.78 170	85.15 323	99.05 259	95.21 231	94.20 301	96.60 363
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMM	93.85 9	95.69 225	95.38 221	96.61 279	97.61 293	93.84 287	98.91 110	98.44 205	95.25 180	94.28 302	98.47 207	86.04 307	99.12 247	95.50 218	93.95 311	96.87 333
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpmrst		95.63 227	95.69 209	95.44 350	97.54 301	88.54 417	96.97 396	97.56 339	93.50 291	97.52 186	96.93 361	89.49 215	99.16 236	95.25 228	96.42 266	98.64 251

FE-MVS		95.62 228	94.90 248	97.78 183	98.37 197	94.92 240	97.17 386	97.38 363	90.95 382	97.73 167	97.70 282	85.32 321	99.63 153	91.18 350	98.33 199	98.79 227

LPG-MVS_test		95.62 228	95.34 223	96.47 297	97.46 308	93.54 298	98.99 87	98.54 180	94.67 223	94.36 296	98.77 173	85.39 316	99.11 249	95.71 210	94.15 304	96.76 343

CLD-MVS		95.62 228	95.34 223	96.46 300	97.52 304	93.75 291	97.27 375	98.46 201	95.53 161	94.42 293	98.00 253	86.21 302	98.97 270	96.25 189	94.37 296	96.66 358
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		95.61 231	94.89 249	97.76 187	98.15 237	95.15 226	96.77 412	94.41 443	92.95 317	97.18 197	97.43 309	84.78 330	99.45 195	94.63 249	97.73 222	98.68 245

MonoMVSNet		95.51 232	95.45 216	95.68 339	95.54 409	90.87 364	98.92 108	97.37 364	95.79 147	95.53 261	97.38 314	89.58 214	97.68 403	96.40 183	92.59 338	98.49 264

thres600view7		95.49 233	94.77 252	97.67 198	98.98 132	95.02 231	98.85 133	96.90 400	95.38 171	96.63 226	96.90 363	84.29 340	99.59 160	88.65 396	96.33 268	98.40 268

test_vis1_n		95.47 234	95.13 235	96.49 294	97.77 279	90.41 379	99.27 27	98.11 290	96.58 108	99.66 26	99.18 92	67.00 446	99.62 157	99.21 27	99.40 126	99.44 118

SCA		95.46 235	95.13 235	96.46 300	97.67 288	91.29 357	97.33 370	97.60 335	94.68 222	96.92 211	97.10 332	83.97 350	98.89 287	92.59 317	98.32 202	99.20 169

IterMVS-LS		95.46 235	95.21 232	96.22 315	98.12 239	93.72 294	98.32 256	98.13 286	93.71 276	94.26 303	97.31 319	92.24 132	98.10 372	94.63 249	90.12 369	96.84 336
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing3-2		95.45 237	95.34 223	95.77 337	98.69 163	88.75 413	98.87 125	97.21 377	96.13 129	97.22 195	97.68 287	77.95 402	99.65 147	97.58 117	96.77 255	98.91 218

jajsoiax		95.45 237	95.03 241	96.73 263	95.42 417	94.63 253	99.14 55	98.52 185	95.74 149	93.22 350	98.36 218	83.87 353	98.65 312	96.95 153	94.04 307	96.91 326

CVMVSNet		95.43 239	96.04 188	93.57 403	97.93 269	83.62 442	98.12 289	98.59 166	95.68 153	96.56 230	99.02 125	87.51 275	97.51 412	93.56 291	97.44 235	99.60 87

anonymousdsp		95.42 240	94.91 247	96.94 248	95.10 421	95.90 182	99.14 55	98.41 217	93.75 270	93.16 353	97.46 305	87.50 277	98.41 342	95.63 214	94.03 308	96.50 382

DU-MVS		95.42 240	94.76 253	97.40 218	96.53 369	96.97 119	98.66 194	98.99 52	95.43 167	93.88 322	97.69 284	88.57 248	98.31 356	95.81 204	87.25 408	96.92 321

mvs_tets		95.41 242	95.00 242	96.65 271	95.58 408	94.42 264	99.00 84	98.55 178	95.73 151	93.21 351	98.38 216	83.45 359	98.63 313	97.09 147	94.00 309	96.91 326

thres100view900		95.38 243	94.70 257	97.41 216	98.98 132	94.92 240	98.87 125	96.90 400	95.38 171	96.61 228	96.88 364	84.29 340	99.56 166	88.11 399	96.29 272	97.76 289

thres400		95.38 243	94.62 261	97.65 202	98.94 137	94.98 236	98.68 187	96.93 398	95.33 174	96.55 232	96.53 383	84.23 344	99.56 166	88.11 399	96.29 272	98.40 268

BH-w/o		95.38 243	95.08 239	96.26 314	98.34 204	91.79 346	97.70 342	97.43 359	92.87 320	94.24 305	97.22 326	88.66 246	98.84 293	91.55 346	97.70 223	98.16 280

VDDNet		95.36 246	94.53 266	97.86 176	98.10 241	95.13 227	98.85 133	97.75 323	90.46 389	98.36 120	99.39 46	73.27 434	99.64 150	97.98 87	96.58 260	98.81 226

TAPA-MVS	93.98 7	95.35 247	94.56 265	97.74 189	99.13 113	94.83 245	98.33 252	98.64 153	86.62 425	96.29 243	98.61 191	94.00 102	99.29 215	80.00 442	99.41 123	99.09 193
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ACMP	93.49 10	95.34 248	94.98 244	96.43 302	97.67 288	93.48 302	98.73 173	98.44 205	94.94 208	92.53 373	98.53 201	84.50 339	99.14 242	95.48 219	94.00 309	96.66 358
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
COLMAP_ROB	93.27 12	95.33 249	94.87 250	96.71 266	99.29 82	93.24 316	98.58 210	98.11 290	89.92 399	93.57 335	99.10 108	86.37 298	99.79 115	90.78 361	98.10 207	97.09 310
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
UBG		95.32 250	94.72 256	97.13 232	98.05 249	93.26 313	97.87 325	97.20 378	94.96 204	96.18 247	95.66 416	80.97 374	99.35 205	94.47 258	97.08 242	98.78 231

tfpn200view9		95.32 250	94.62 261	97.43 214	98.94 137	94.98 236	98.68 187	96.93 398	95.33 174	96.55 232	96.53 383	84.23 344	99.56 166	88.11 399	96.29 272	97.76 289

Anonymous202405211		95.28 252	94.49 268	97.67 198	99.00 128	93.75 291	98.70 182	97.04 389	90.66 385	96.49 236	98.80 164	78.13 398	99.83 84	96.21 190	95.36 294	99.44 118

thres200		95.25 253	94.57 264	97.28 222	98.81 151	94.92 240	98.20 272	97.11 382	95.24 182	96.54 234	96.22 394	84.58 337	99.53 176	87.93 404	96.50 264	97.39 303

AllTest		95.24 254	94.65 260	96.99 243	99.25 90	93.21 317	98.59 207	98.18 274	91.36 367	93.52 337	98.77 173	84.67 334	99.72 130	89.70 379	97.87 215	98.02 284

LCM-MVSNet-Re		95.22 255	95.32 227	94.91 367	98.18 232	87.85 428	98.75 163	95.66 430	95.11 191	88.96 415	96.85 367	90.26 201	97.65 404	95.65 213	98.44 187	99.22 166

EPNet_dtu		95.21 256	94.95 246	95.99 323	96.17 386	90.45 377	98.16 282	97.27 372	96.77 96	93.14 356	98.33 224	90.34 197	98.42 335	85.57 417	98.81 164	99.09 193
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
XXY-MVS		95.20 257	94.45 274	97.46 211	96.75 359	96.56 143	98.86 129	98.65 152	93.30 301	93.27 349	98.27 231	84.85 328	98.87 290	94.82 240	91.26 355	96.96 316

D2MVS		95.18 258	95.08 239	95.48 347	97.10 337	92.07 342	98.30 260	99.13 40	94.02 252	92.90 361	96.73 373	89.48 216	98.73 305	94.48 257	93.60 320	95.65 412

WR-MVS		95.15 259	94.46 271	97.22 224	96.67 364	96.45 147	98.21 270	98.81 101	94.15 246	93.16 353	97.69 284	87.51 275	98.30 358	95.29 226	88.62 393	96.90 328

TranMVSNet+NR-MVSNet		95.14 260	94.48 269	97.11 236	96.45 375	96.36 154	99.03 77	99.03 47	95.04 196	93.58 334	97.93 260	88.27 256	98.03 380	94.13 271	86.90 413	96.95 318

myMVS_eth3d28		95.12 261	94.62 261	96.64 275	98.17 235	92.17 336	98.02 303	97.32 366	95.41 169	96.22 244	96.05 400	78.01 400	99.13 244	95.22 230	97.16 240	98.60 254

baseline2		95.11 262	94.52 267	96.87 254	96.65 365	93.56 297	98.27 265	94.10 449	93.45 294	92.02 387	97.43 309	87.45 280	99.19 233	93.88 280	97.41 237	97.87 287

miper_enhance_ethall		95.10 263	94.75 254	96.12 319	97.53 303	93.73 293	96.61 418	98.08 298	92.20 347	93.89 321	96.65 379	92.44 123	98.30 358	94.21 267	91.16 356	96.34 391

Anonymous20240529		95.10 263	94.22 284	97.75 188	99.01 126	94.26 273	98.87 125	98.83 92	85.79 433	96.64 225	98.97 133	78.73 391	99.85 78	96.27 186	94.89 295	99.12 185

test-LLR		95.10 263	94.87 250	95.80 334	96.77 356	89.70 393	96.91 401	95.21 435	95.11 191	94.83 277	95.72 413	87.71 271	98.97 270	93.06 302	98.50 183	98.72 238

WR-MVS_H		95.05 266	94.46 271	96.81 258	96.86 351	95.82 192	99.24 31	99.24 20	93.87 264	92.53 373	96.84 368	90.37 196	98.24 364	93.24 297	87.93 399	96.38 390

miper_ehance_all_eth		95.01 267	94.69 258	95.97 325	97.70 286	93.31 311	97.02 394	98.07 300	92.23 344	93.51 339	96.96 357	91.85 146	98.15 368	93.68 285	91.16 356	96.44 388

testing11		95.00 268	94.28 281	97.16 230	97.96 266	93.36 310	98.09 295	97.06 388	94.94 208	95.33 267	96.15 396	76.89 415	99.40 200	95.77 208	96.30 271	98.72 238

ADS-MVSNet		95.00 268	94.45 274	96.63 276	98.00 256	91.91 345	96.04 425	97.74 324	90.15 395	96.47 237	96.64 380	87.89 267	98.96 274	90.08 370	97.06 243	99.02 206

VPNet		94.99 270	94.19 286	97.40 218	97.16 333	96.57 142	98.71 178	98.97 53	95.67 154	94.84 275	98.24 235	80.36 381	98.67 311	96.46 180	87.32 407	96.96 316

EPMVS		94.99 270	94.48 269	96.52 292	97.22 326	91.75 348	97.23 376	91.66 459	94.11 247	97.28 191	96.81 370	85.70 311	98.84 293	93.04 304	97.28 238	98.97 211

testing91		94.98 272	94.25 283	97.20 225	97.94 267	93.41 305	98.00 306	97.58 336	94.99 201	95.45 263	96.04 401	77.20 410	99.42 198	94.97 236	96.02 285	98.78 231

NR-MVSNet		94.98 272	94.16 289	97.44 213	96.53 369	97.22 109	98.74 167	98.95 57	94.96 204	89.25 414	97.69 284	89.32 225	98.18 366	94.59 254	87.40 405	96.92 321

FMVSNet3		94.97 274	94.26 282	97.11 236	98.18 232	96.62 134	98.56 220	98.26 262	93.67 283	94.09 312	97.10 332	84.25 342	98.01 382	92.08 329	92.14 341	96.70 352

CostFormer		94.95 275	94.73 255	95.60 344	97.28 322	89.06 406	97.53 354	96.89 402	89.66 404	96.82 216	96.72 374	86.05 305	98.95 279	95.53 217	96.13 283	98.79 227

PAPM		94.95 275	94.00 302	97.78 183	97.04 339	95.65 198	96.03 427	98.25 263	91.23 376	94.19 308	97.80 276	91.27 169	98.86 292	82.61 434	97.61 225	98.84 223

CP-MVSNet		94.94 277	94.30 280	96.83 256	96.72 361	95.56 201	99.11 61	98.95 57	93.89 262	92.42 378	97.90 263	87.19 282	98.12 371	94.32 263	88.21 396	96.82 339

TR-MVS		94.94 277	94.20 285	97.17 229	97.75 280	94.14 279	97.59 351	97.02 393	92.28 343	95.75 259	97.64 292	83.88 352	98.96 274	89.77 376	96.15 282	98.40 268

RPSCF		94.87 279	95.40 217	93.26 409	98.89 140	82.06 448	98.33 252	98.06 305	90.30 394	96.56 230	99.26 74	87.09 283	99.49 184	93.82 282	96.32 269	98.24 275

testing99		94.83 280	94.08 294	97.07 239	97.94 267	93.13 319	98.10 294	97.17 380	94.86 210	95.34 264	96.00 405	76.31 418	99.40 200	95.08 233	95.90 286	98.68 245

GA-MVS		94.81 281	94.03 298	97.14 231	97.15 334	93.86 286	96.76 413	97.58 336	94.00 256	94.76 281	97.04 347	80.91 375	98.48 326	91.79 339	96.25 278	99.09 193

c3_l		94.79 282	94.43 276	95.89 330	97.75 280	93.12 321	97.16 388	98.03 307	92.23 344	93.46 343	97.05 346	91.39 163	98.01 382	93.58 290	89.21 385	96.53 374

V42		94.78 283	94.14 291	96.70 268	96.33 380	95.22 222	98.97 91	98.09 297	92.32 341	94.31 299	97.06 343	88.39 254	98.55 321	92.90 309	88.87 391	96.34 391

reproduce_monomvs		94.77 284	94.67 259	95.08 362	98.40 194	89.48 399	98.80 150	98.64 153	97.57 44	93.21 351	97.65 289	80.57 380	98.83 296	97.72 104	89.47 381	96.93 320

CR-MVSNet		94.76 285	94.15 290	96.59 282	97.00 340	93.43 303	94.96 440	97.56 339	92.46 332	96.93 209	96.24 390	88.15 259	97.88 395	87.38 406	96.65 258	98.46 266

v2v482		94.69 286	94.03 298	96.65 271	96.17 386	94.79 248	98.67 192	98.08 298	92.72 324	94.00 317	97.16 329	87.69 274	98.45 331	92.91 308	88.87 391	96.72 348

pmmvs4		94.69 286	93.99 304	96.81 258	95.74 403	95.94 176	97.40 361	97.67 328	90.42 391	93.37 346	97.59 296	89.08 233	98.20 365	92.97 306	91.67 349	96.30 394

cl22		94.68 288	94.19 286	96.13 318	98.11 240	93.60 296	96.94 398	98.31 244	92.43 336	93.32 348	96.87 366	86.51 292	98.28 362	94.10 274	91.16 356	96.51 380

eth_miper_zixun_eth		94.68 288	94.41 277	95.47 348	97.64 291	91.71 350	96.73 415	98.07 300	92.71 325	93.64 331	97.21 327	90.54 194	98.17 367	93.38 293	89.76 373	96.54 372

PCF-MVS	93.45 11	94.68 288	93.43 340	98.42 123	98.62 173	96.77 129	95.48 437	98.20 269	84.63 438	93.34 347	98.32 225	88.55 251	99.81 96	84.80 426	98.96 152	98.68 245
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS		94.67 291	93.54 335	98.08 157	96.88 350	96.56 143	98.19 275	98.50 193	78.05 450	92.69 368	98.02 250	91.07 181	99.63 153	90.09 369	98.36 198	98.04 283

PS-CasMVS		94.67 291	93.99 304	96.71 266	96.68 363	95.26 219	99.13 58	99.03 47	93.68 281	92.33 379	97.95 258	85.35 318	98.10 372	93.59 289	88.16 398	96.79 340

cascas		94.63 293	93.86 314	96.93 249	96.91 348	94.27 272	96.00 428	98.51 188	85.55 434	94.54 284	96.23 392	84.20 346	98.87 290	95.80 206	96.98 248	97.66 295

tpmvs		94.60 294	94.36 279	95.33 354	97.46 308	88.60 416	96.88 407	97.68 325	91.29 373	93.80 327	96.42 387	88.58 247	99.24 226	91.06 356	96.04 284	98.17 279

LTVRE_ROB	92.95 15	94.60 294	93.90 310	96.68 270	97.41 316	94.42 264	98.52 223	98.59 166	91.69 359	91.21 394	98.35 219	84.87 327	99.04 262	91.06 356	93.44 324	96.60 363
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		94.59 296	93.92 307	96.60 281	96.21 382	94.78 249	98.59 207	98.14 285	91.86 355	94.21 307	97.02 350	87.97 265	98.41 342	91.72 341	89.57 376	96.61 362

ADS-MVSNet2		94.58 297	94.40 278	95.11 360	98.00 256	88.74 414	96.04 425	97.30 368	90.15 395	96.47 237	96.64 380	87.89 267	97.56 410	90.08 370	97.06 243	99.02 206

WBMVS		94.56 298	94.04 296	96.10 320	98.03 253	93.08 323	97.82 333	98.18 274	94.02 252	93.77 329	96.82 369	81.28 369	98.34 351	95.47 220	91.00 359	96.88 330

ACMH	92.88 16	94.55 299	93.95 306	96.34 309	97.63 292	93.26 313	98.81 149	98.49 198	93.43 295	89.74 408	98.53 201	81.91 364	99.08 256	93.69 284	93.30 329	96.70 352
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		94.54 300	93.85 315	96.63 276	97.98 264	93.06 324	98.77 162	97.84 319	93.67 283	93.80 327	98.04 249	76.88 416	98.96 274	94.79 242	92.86 334	97.86 288

XVG-ACMP-BASELINE		94.54 300	94.14 291	95.75 338	96.55 368	91.65 351	98.11 292	98.44 205	94.96 204	94.22 306	97.90 263	79.18 390	99.11 249	94.05 276	93.85 313	96.48 385

AUN-MVS		94.53 302	93.73 325	96.92 252	98.50 181	93.52 301	98.34 251	98.10 293	93.83 267	95.94 257	97.98 256	85.59 314	99.03 263	94.35 261	80.94 441	98.22 277

DIV-MVS_self_test		94.52 303	94.03 298	95.99 323	97.57 300	93.38 308	97.05 392	97.94 313	91.74 356	92.81 363	97.10 332	89.12 231	98.07 378	92.60 315	90.30 366	96.53 374

cl____		94.51 304	94.01 301	96.02 322	97.58 296	93.40 307	97.05 392	97.96 312	91.73 358	92.76 365	97.08 338	89.06 234	98.13 370	92.61 314	90.29 367	96.52 377

ETVMVS		94.50 305	93.44 339	97.68 196	98.18 232	95.35 215	98.19 275	97.11 382	93.73 273	96.40 240	95.39 419	74.53 428	98.84 293	91.10 352	96.31 270	98.84 223

GBi-Net		94.49 306	93.80 318	96.56 286	98.21 222	95.00 232	98.82 141	98.18 274	92.46 332	94.09 312	97.07 339	81.16 370	97.95 387	92.08 329	92.14 341	96.72 348

test1		94.49 306	93.80 318	96.56 286	98.21 222	95.00 232	98.82 141	98.18 274	92.46 332	94.09 312	97.07 339	81.16 370	97.95 387	92.08 329	92.14 341	96.72 348

dmvs_re		94.48 308	94.18 288	95.37 352	97.68 287	90.11 385	98.54 222	97.08 384	94.56 229	94.42 293	97.24 324	84.25 342	97.76 401	91.02 359	92.83 335	98.24 275

v8		94.47 309	93.77 321	96.57 285	96.36 378	94.83 245	99.05 70	98.19 271	91.92 352	93.16 353	96.97 355	88.82 245	98.48 326	91.69 342	87.79 400	96.39 389

FMVSNet2		94.47 309	93.61 331	97.04 241	98.21 222	96.43 149	98.79 158	98.27 254	92.46 332	93.50 340	97.09 336	81.16 370	98.00 384	91.09 353	91.93 344	96.70 352

test2506		94.44 311	93.91 309	96.04 321	99.02 124	88.99 409	99.06 68	79.47 471	96.96 88	98.36 120	99.26 74	77.21 409	99.52 179	96.78 171	99.04 146	99.59 89

Patchmatch-test		94.42 312	93.68 329	96.63 276	97.60 294	91.76 347	94.83 444	97.49 351	89.45 408	94.14 310	97.10 332	88.99 236	98.83 296	85.37 420	98.13 206	99.29 150

PEN-MVS		94.42 312	93.73 325	96.49 294	96.28 381	94.84 243	99.17 50	99.00 49	93.51 290	92.23 381	97.83 273	86.10 304	97.90 391	92.55 320	86.92 412	96.74 345

v144192		94.39 314	93.70 327	96.48 296	96.06 392	94.35 268	98.58 210	98.16 282	91.45 364	94.33 298	97.02 350	87.50 277	98.45 331	91.08 355	89.11 386	96.63 360

Baseline_NR-MVSNet		94.35 315	93.81 317	95.96 326	96.20 383	94.05 281	98.61 206	96.67 412	91.44 365	93.85 324	97.60 295	88.57 248	98.14 369	94.39 259	86.93 411	95.68 411

miper_lstm_enhance		94.33 316	94.07 295	95.11 360	97.75 280	90.97 361	97.22 378	98.03 307	91.67 360	92.76 365	96.97 355	90.03 203	97.78 400	92.51 322	89.64 375	96.56 369

v1192		94.32 317	93.58 332	96.53 291	96.10 390	94.45 262	98.50 230	98.17 280	91.54 362	94.19 308	97.06 343	86.95 287	98.43 334	90.14 368	89.57 376	96.70 352

UWE-MVS		94.30 318	93.89 312	95.53 345	97.83 275	88.95 410	97.52 356	93.25 451	94.44 239	96.63 226	97.07 339	78.70 392	99.28 217	91.99 334	97.56 229	98.36 271

ACMH+	92.99 14	94.30 318	93.77 321	95.88 331	97.81 277	92.04 344	98.71 178	98.37 230	93.99 257	90.60 401	98.47 207	80.86 377	99.05 259	92.75 313	92.40 340	96.55 371

v148		94.29 320	93.76 323	95.91 328	96.10 390	92.93 325	98.58 210	97.97 310	92.59 330	93.47 342	96.95 359	88.53 252	98.32 354	92.56 319	87.06 410	96.49 383

v10		94.29 320	93.55 334	96.51 293	96.39 377	94.80 247	98.99 87	98.19 271	91.35 369	93.02 359	96.99 353	88.09 261	98.41 342	90.50 365	88.41 395	96.33 393

SD_0403		94.28 322	94.46 271	93.73 400	98.02 254	85.32 437	98.31 257	98.40 219	94.75 218	93.59 332	98.16 240	89.01 235	96.54 431	82.32 435	97.58 228	99.34 136

MVP-Stereo		94.28 322	93.92 307	95.35 353	94.95 423	92.60 332	97.97 309	97.65 329	91.61 361	90.68 400	97.09 336	86.32 301	98.42 335	89.70 379	99.34 132	95.02 425
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UniMVSNet_ETH3D		94.24 324	93.33 342	96.97 246	97.19 331	93.38 308	98.74 167	98.57 173	91.21 378	93.81 326	98.58 196	72.85 435	98.77 303	95.05 234	93.93 312	98.77 234

OurMVSNet-221017-0		94.21 325	94.00 302	94.85 372	95.60 407	89.22 404	98.89 115	97.43 359	95.29 177	92.18 383	98.52 204	82.86 360	98.59 319	93.46 292	91.76 347	96.74 345

v1921920		94.20 326	93.47 338	96.40 306	95.98 396	94.08 280	98.52 223	98.15 283	91.33 370	94.25 304	97.20 328	86.41 297	98.42 335	90.04 373	89.39 383	96.69 357

WB-MVSnew		94.19 327	94.04 296	94.66 380	96.82 354	92.14 337	97.86 327	95.96 426	93.50 291	95.64 260	96.77 372	88.06 263	97.99 385	84.87 423	96.86 249	93.85 443

v7n		94.19 327	93.43 340	96.47 297	95.90 399	94.38 267	99.26 28	98.34 237	91.99 350	92.76 365	97.13 331	88.31 255	98.52 324	89.48 384	87.70 401	96.52 377

tpm2		94.19 327	93.76 323	95.46 349	97.23 325	89.04 407	97.31 372	96.85 406	87.08 424	96.21 246	96.79 371	83.75 356	98.74 304	92.43 325	96.23 280	98.59 257

TESTMET0.1,1		94.18 330	93.69 328	95.63 342	96.92 346	89.12 405	96.91 401	94.78 440	93.17 306	94.88 274	96.45 386	78.52 393	98.92 281	93.09 301	98.50 183	98.85 221

dp		94.15 331	93.90 310	94.90 368	97.31 321	86.82 433	96.97 396	97.19 379	91.22 377	96.02 252	96.61 382	85.51 315	99.02 266	90.00 374	94.30 297	98.85 221

ET-MVSNet_ETH3D		94.13 332	92.98 350	97.58 206	98.22 221	96.20 160	97.31 372	95.37 434	94.53 231	79.56 452	97.63 294	86.51 292	97.53 411	96.91 155	90.74 361	99.02 206

tpm		94.13 332	93.80 318	95.12 359	96.50 371	87.91 427	97.44 358	95.89 429	92.62 328	96.37 242	96.30 389	84.13 347	98.30 358	93.24 297	91.66 350	99.14 183

testing222		94.12 334	93.03 349	97.37 221	98.02 254	94.66 250	97.94 313	96.65 414	94.63 225	95.78 258	95.76 408	71.49 436	98.92 281	91.17 351	95.88 287	98.52 262

IterMVS-SCA-FT		94.11 335	93.87 313	94.85 372	97.98 264	90.56 376	97.18 383	98.11 290	93.75 270	92.58 371	97.48 304	83.97 350	97.41 414	92.48 324	91.30 353	96.58 365

Anonymous20231211		94.10 336	93.26 345	96.61 279	99.11 116	94.28 271	99.01 82	98.88 73	86.43 427	92.81 363	97.57 298	81.66 366	98.68 310	94.83 239	89.02 389	96.88 330

IterMVS		94.09 337	93.85 315	94.80 376	97.99 258	90.35 381	97.18 383	98.12 287	93.68 281	92.46 377	97.34 315	84.05 348	97.41 414	92.51 322	91.33 352	96.62 361
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test-mter		94.08 338	93.51 336	95.80 334	96.77 356	89.70 393	96.91 401	95.21 435	92.89 319	94.83 277	95.72 413	77.69 404	98.97 270	93.06 302	98.50 183	98.72 238

test0.0.03 1		94.08 338	93.51 336	95.80 334	95.53 411	92.89 326	97.38 363	95.97 425	95.11 191	92.51 375	96.66 377	87.71 271	96.94 421	87.03 408	93.67 316	97.57 299

v1240		94.06 340	93.29 344	96.34 309	96.03 394	93.90 285	98.44 242	98.17 280	91.18 379	94.13 311	97.01 352	86.05 305	98.42 335	89.13 390	89.50 380	96.70 352

X-MVStestdata		94.06 340	92.30 366	99.34 27	99.70 24	98.35 45	99.29 23	98.88 73	97.40 55	98.46 112	43.50 466	95.90 45	99.89 62	97.85 96	99.74 54	99.78 28

DTE-MVSNet		93.98 342	93.26 345	96.14 317	96.06 392	94.39 266	99.20 43	98.86 86	93.06 312	91.78 388	97.81 275	85.87 309	97.58 409	90.53 364	86.17 417	96.46 387

pm-mvs1		93.94 343	93.06 348	96.59 282	96.49 372	95.16 224	98.95 97	98.03 307	92.32 341	91.08 396	97.84 270	84.54 338	98.41 342	92.16 327	86.13 420	96.19 399

MS-PatchMatch		93.84 344	93.63 330	94.46 390	96.18 385	89.45 400	97.76 337	98.27 254	92.23 344	92.13 384	97.49 303	79.50 387	98.69 307	89.75 377	99.38 128	95.25 417

tfpnnormal		93.66 345	92.70 356	96.55 290	96.94 345	95.94 176	98.97 91	99.19 32	91.04 380	91.38 393	97.34 315	84.94 326	98.61 315	85.45 419	89.02 389	95.11 421

EU-MVSNet		93.66 345	94.14 291	92.25 420	95.96 398	83.38 444	98.52 223	98.12 287	94.69 221	92.61 370	98.13 243	87.36 281	96.39 435	91.82 338	90.00 371	96.98 315

our_test_3		93.65 347	93.30 343	94.69 378	95.45 415	89.68 395	96.91 401	97.65 329	91.97 351	91.66 391	96.88 364	89.67 212	97.93 390	88.02 402	91.49 351	96.48 385

pmmvs5		93.65 347	92.97 351	95.68 339	95.49 412	92.37 333	98.20 272	97.28 371	89.66 404	92.58 371	97.26 321	82.14 363	98.09 376	93.18 300	90.95 360	96.58 365

SSC-MVS3.2		93.59 349	93.13 347	94.97 365	96.81 355	89.71 392	97.95 310	98.49 198	94.59 228	93.50 340	96.91 362	77.74 403	98.37 349	91.69 342	90.47 364	96.83 338

test_fmvs2		93.43 350	93.58 332	92.95 414	96.97 343	83.91 440	99.19 45	97.24 374	95.74 149	95.20 269	98.27 231	69.65 438	98.72 306	96.26 187	93.73 315	96.24 396

tpm cat1		93.36 351	92.80 353	95.07 363	97.58 296	87.97 426	96.76 413	97.86 318	82.17 445	93.53 336	96.04 401	86.13 303	99.13 244	89.24 388	95.87 288	98.10 282

JIA-IIPM		93.35 352	92.49 362	95.92 327	96.48 373	90.65 371	95.01 439	96.96 396	85.93 431	96.08 250	87.33 456	87.70 273	98.78 302	91.35 348	95.58 292	98.34 272

SixPastTwentyTwo		93.34 353	92.86 352	94.75 377	95.67 405	89.41 402	98.75 163	96.67 412	93.89 262	90.15 406	98.25 234	80.87 376	98.27 363	90.90 360	90.64 362	96.57 367

USDC		93.33 354	92.71 355	95.21 356	96.83 353	90.83 367	96.91 401	97.50 349	93.84 265	90.72 399	98.14 242	77.69 404	98.82 298	89.51 383	93.21 331	95.97 405

IB-MVS	91.98 17	93.27 355	91.97 370	97.19 227	97.47 307	93.41 305	97.09 391	95.99 424	93.32 299	92.47 376	95.73 411	78.06 399	99.53 176	94.59 254	82.98 431	98.62 252
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		93.26 356	92.21 367	96.41 304	97.73 284	93.13 319	95.65 434	97.03 390	91.27 375	94.04 315	96.06 399	75.33 423	97.19 417	86.56 410	96.23 280	98.92 217

ppachtmachnet_test		93.22 357	92.63 357	94.97 365	95.45 415	90.84 366	96.88 407	97.88 317	90.60 386	92.08 385	97.26 321	88.08 262	97.86 396	85.12 422	90.33 365	96.22 397

Patchmtry		93.22 357	92.35 365	95.84 333	96.77 356	93.09 322	94.66 447	97.56 339	87.37 423	92.90 361	96.24 390	88.15 259	97.90 391	87.37 407	90.10 370	96.53 374

testing3		93.19 359	92.48 363	95.30 355	98.07 244	92.27 334	98.64 198	97.17 380	93.94 261	93.98 318	97.04 347	67.97 443	96.01 439	88.40 397	97.14 241	97.63 296

FMVSNet1		93.19 359	92.07 368	96.56 286	97.54 301	95.00 232	98.82 141	98.18 274	90.38 392	92.27 380	97.07 339	73.68 433	97.95 387	89.36 386	91.30 353	96.72 348

LF4IMVS		93.14 361	92.79 354	94.20 394	95.88 400	88.67 415	97.66 345	97.07 386	93.81 268	91.71 389	97.65 289	77.96 401	98.81 299	91.47 347	91.92 346	95.12 420

mmtdpeth		93.12 362	92.61 358	94.63 382	97.60 294	89.68 395	99.21 40	97.32 366	94.02 252	97.72 168	94.42 430	77.01 414	99.44 196	99.05 30	77.18 453	94.78 430

testgi		93.06 363	92.45 364	94.88 370	96.43 376	89.90 387	98.75 163	97.54 345	95.60 156	91.63 392	97.91 262	74.46 430	97.02 419	86.10 413	93.67 316	97.72 293

PatchT		93.06 363	91.97 370	96.35 308	96.69 362	92.67 331	94.48 450	97.08 384	86.62 425	97.08 201	92.23 450	87.94 266	97.90 391	78.89 446	96.69 256	98.49 264

RPMNet		92.81 365	91.34 376	97.24 223	97.00 340	93.43 303	94.96 440	98.80 108	82.27 444	96.93 209	92.12 451	86.98 286	99.82 91	76.32 452	96.65 258	98.46 266

UWE-MVS-28		92.79 366	92.51 361	93.62 402	96.46 374	86.28 434	97.93 314	92.71 456	94.17 245	94.78 280	97.16 329	81.05 373	96.43 434	81.45 438	96.86 249	98.14 281

myMVS_eth3d		92.73 367	92.01 369	94.89 369	97.39 317	90.94 362	97.91 317	97.46 353	93.16 307	93.42 344	95.37 420	68.09 442	96.12 437	88.34 398	96.99 245	97.60 297

TransMVSNet (Re)		92.67 368	91.51 375	96.15 316	96.58 367	94.65 251	98.90 111	96.73 408	90.86 383	89.46 413	97.86 267	85.62 313	98.09 376	86.45 411	81.12 439	95.71 410

ttmdpeth		92.61 369	91.96 372	94.55 384	94.10 433	90.60 375	98.52 223	97.29 369	92.67 326	90.18 404	97.92 261	79.75 386	97.79 398	91.09 353	86.15 419	95.26 416

Syy-MVS		92.55 370	92.61 358	92.38 417	97.39 317	83.41 443	97.91 317	97.46 353	93.16 307	93.42 344	95.37 420	84.75 331	96.12 437	77.00 451	96.99 245	97.60 297

K. test v3		92.55 370	91.91 373	94.48 388	95.64 406	89.24 403	99.07 67	94.88 439	94.04 250	86.78 430	97.59 296	77.64 407	97.64 405	92.08 329	89.43 382	96.57 367

DSMNet-mixed		92.52 372	92.58 360	92.33 418	94.15 432	82.65 446	98.30 260	94.26 446	89.08 413	92.65 369	95.73 411	85.01 325	95.76 441	86.24 412	97.76 220	98.59 257

TinyColmap		92.31 373	91.53 374	94.65 381	96.92 346	89.75 390	96.92 399	96.68 411	90.45 390	89.62 410	97.85 269	76.06 421	98.81 299	86.74 409	92.51 339	95.41 414

gg-mvs-nofinetune		92.21 374	90.58 382	97.13 232	96.75 359	95.09 228	95.85 429	89.40 464	85.43 435	94.50 286	81.98 459	80.80 378	98.40 348	92.16 327	98.33 199	97.88 286

FMVSNet5		91.81 375	90.92 378	94.49 387	97.21 327	92.09 341	98.00 306	97.55 344	89.31 411	90.86 398	95.61 417	74.48 429	95.32 445	85.57 417	89.70 374	96.07 403

pmmvs6		91.77 376	90.63 381	95.17 358	94.69 429	91.24 358	98.67 192	97.92 315	86.14 429	89.62 410	97.56 301	75.79 422	98.34 351	90.75 362	84.56 424	95.94 406

Anonymous20231206		91.66 377	91.10 377	93.33 407	94.02 437	87.35 430	98.58 210	97.26 373	90.48 388	90.16 405	96.31 388	83.83 354	96.53 432	79.36 444	89.90 372	96.12 401

Patchmatch-RL test		91.49 378	90.85 379	93.41 405	91.37 448	84.40 438	92.81 454	95.93 428	91.87 354	87.25 426	94.87 426	88.99 236	96.53 432	92.54 321	82.00 433	99.30 147

test_0402		91.32 379	90.27 385	94.48 388	96.60 366	91.12 359	98.50 230	97.22 375	86.10 430	88.30 422	96.98 354	77.65 406	97.99 385	78.13 448	92.94 333	94.34 431

test_vis1_rt		91.29 380	90.65 380	93.19 411	97.45 311	86.25 435	98.57 217	90.90 462	93.30 301	86.94 429	93.59 439	62.07 454	99.11 249	97.48 130	95.58 292	94.22 434

PVSNet_0	88.72 19	91.28 381	90.03 388	95.00 364	97.99 258	87.29 431	94.84 443	98.50 193	92.06 349	89.86 407	95.19 422	79.81 385	99.39 203	92.27 326	69.79 459	98.33 273

mvs5depth		91.23 382	90.17 386	94.41 392	92.09 445	89.79 389	95.26 438	96.50 416	90.73 384	91.69 390	97.06 343	76.12 420	98.62 314	88.02 402	84.11 427	94.82 427

Anonymous20240521		91.18 383	90.44 383	93.42 404	93.70 438	88.47 419	98.94 100	97.56 339	88.46 417	89.56 412	95.08 425	77.15 412	96.97 420	83.92 429	89.55 378	94.82 427

EG-PatchMatch MVS		91.13 384	90.12 387	94.17 396	94.73 428	89.00 408	98.13 288	97.81 320	89.22 412	85.32 440	96.46 385	67.71 444	98.42 335	87.89 405	93.82 314	95.08 422

TDRefinement		91.06 385	89.68 390	95.21 356	85.35 464	91.49 354	98.51 229	97.07 386	91.47 363	88.83 419	97.84 270	77.31 408	99.09 254	92.79 312	77.98 451	95.04 424

sc_t1		91.01 386	89.39 392	95.85 332	95.99 395	90.39 380	98.43 244	97.64 331	78.79 448	92.20 382	97.94 259	66.00 448	98.60 318	91.59 345	85.94 421	98.57 260

UnsupCasMVSNet_eth		90.99 387	89.92 389	94.19 395	94.08 434	89.83 388	97.13 390	98.67 145	93.69 279	85.83 436	96.19 395	75.15 424	96.74 425	89.14 389	79.41 446	96.00 404

test20.03		90.89 388	90.38 384	92.43 416	93.48 439	88.14 425	98.33 252	97.56 339	93.40 296	87.96 423	96.71 375	80.69 379	94.13 451	79.15 445	86.17 417	95.01 426

MDA-MVSNet_test_wron		90.71 389	89.38 394	94.68 379	94.83 425	90.78 368	97.19 382	97.46 353	87.60 421	72.41 459	95.72 413	86.51 292	96.71 428	85.92 415	86.80 414	96.56 369

YYNet1		90.70 390	89.39 392	94.62 383	94.79 427	90.65 371	97.20 380	97.46 353	87.54 422	72.54 458	95.74 409	86.51 292	96.66 429	86.00 414	86.76 415	96.54 372

KD-MVS_self_test		90.38 391	89.38 394	93.40 406	92.85 442	88.94 411	97.95 310	97.94 313	90.35 393	90.25 403	93.96 436	79.82 384	95.94 440	84.62 428	76.69 454	95.33 415

pmmvs-eth3d		90.36 392	89.05 397	94.32 393	91.10 450	92.12 338	97.63 350	96.95 397	88.86 415	84.91 441	93.13 444	78.32 395	96.74 425	88.70 394	81.81 435	94.09 437

tt0320		90.26 393	88.73 400	94.86 371	96.12 389	90.62 373	98.17 281	97.63 332	77.46 451	89.68 409	96.04 401	69.19 440	97.79 398	88.98 391	85.29 423	96.16 400

CL-MVSNet_self_test		90.11 394	89.14 396	93.02 412	91.86 447	88.23 424	96.51 421	98.07 300	90.49 387	90.49 402	94.41 431	84.75 331	95.34 444	80.79 440	74.95 456	95.50 413

new_pmnet		90.06 395	89.00 398	93.22 410	94.18 431	88.32 422	96.42 423	96.89 402	86.19 428	85.67 437	93.62 438	77.18 411	97.10 418	81.61 437	89.29 384	94.23 433

MDA-MVSNet-bldmvs		89.97 396	88.35 402	94.83 375	95.21 419	91.34 355	97.64 347	97.51 348	88.36 419	71.17 460	96.13 397	79.22 389	96.63 430	83.65 430	86.27 416	96.52 377

tt0320-xc		89.79 397	88.11 404	94.84 374	96.19 384	90.61 374	98.16 282	97.22 375	77.35 452	88.75 420	96.70 376	65.94 449	97.63 406	89.31 387	83.39 429	96.28 395

CMPMVS	66.06 21	89.70 398	89.67 391	89.78 425	93.19 440	76.56 451	97.00 395	98.35 234	80.97 446	81.57 447	97.75 278	74.75 427	98.61 315	89.85 375	93.63 318	94.17 435
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet1		89.67 399	88.28 403	93.82 399	92.81 443	91.08 360	98.01 304	97.45 357	87.95 420	87.90 424	95.87 407	67.63 445	94.56 450	78.73 447	88.18 397	95.83 408

KD-MVS_2432*1600		89.61 400	87.96 408	94.54 385	94.06 435	91.59 352	95.59 435	97.63 332	89.87 400	88.95 416	94.38 433	78.28 396	96.82 423	84.83 424	68.05 460	95.21 418

miper_refine_blended		89.61 400	87.96 408	94.54 385	94.06 435	91.59 352	95.59 435	97.63 332	89.87 400	88.95 416	94.38 433	78.28 396	96.82 423	84.83 424	68.05 460	95.21 418

MVStest1		89.53 402	87.99 407	94.14 398	94.39 430	90.42 378	98.25 267	96.84 407	82.81 441	81.18 449	97.33 317	77.09 413	96.94 421	85.27 421	78.79 447	95.06 423

MVS-HIRNet		89.46 403	88.40 401	92.64 415	97.58 296	82.15 447	94.16 453	93.05 455	75.73 455	90.90 397	82.52 458	79.42 388	98.33 353	83.53 431	98.68 167	97.43 300

OpenMVS_ROB	86.42 20	89.00 404	87.43 412	93.69 401	93.08 441	89.42 401	97.91 317	96.89 402	78.58 449	85.86 435	94.69 427	69.48 439	98.29 361	77.13 450	93.29 330	93.36 445

mvsany_test3		88.80 405	88.04 405	91.09 424	89.78 454	81.57 449	97.83 332	95.49 433	93.81 268	87.53 425	93.95 437	56.14 457	97.43 413	94.68 247	83.13 430	94.26 432

FE-MVSNET		88.56 406	87.09 413	92.99 413	89.93 453	89.99 386	98.15 285	95.59 431	88.42 418	84.87 442	92.90 445	74.82 426	94.99 448	77.88 449	81.21 438	93.99 440

new-patchmatchnet		88.50 407	87.45 411	91.67 422	90.31 452	85.89 436	97.16 388	97.33 365	89.47 407	83.63 444	92.77 447	76.38 417	95.06 447	82.70 433	77.29 452	94.06 439

APD_test1		88.22 408	88.01 406	88.86 427	95.98 396	74.66 459	97.21 379	96.44 418	83.96 440	86.66 432	97.90 263	60.95 455	97.84 397	82.73 432	90.23 368	94.09 437

PM-MVS		87.77 409	86.55 415	91.40 423	91.03 451	83.36 445	96.92 399	95.18 437	91.28 374	86.48 434	93.42 440	53.27 458	96.74 425	89.43 385	81.97 434	94.11 436

dmvs_testset		87.64 410	88.93 399	83.79 436	95.25 418	63.36 468	97.20 380	91.17 460	93.07 311	85.64 438	95.98 406	85.30 322	91.52 458	69.42 457	87.33 406	96.49 383

test_fmvs3		87.17 411	87.06 414	87.50 429	91.21 449	75.66 454	99.05 70	96.61 415	92.79 323	88.85 418	92.78 446	43.72 461	93.49 452	93.95 277	84.56 424	93.34 446

UnsupCasMVSNet_bld		87.17 411	85.12 418	93.31 408	91.94 446	88.77 412	94.92 442	98.30 251	84.30 439	82.30 445	90.04 453	63.96 452	97.25 416	85.85 416	74.47 458	93.93 442

N_pmnet		87.12 413	87.77 410	85.17 433	95.46 414	61.92 469	97.37 365	70.66 474	85.83 432	88.73 421	96.04 401	85.33 320	97.76 401	80.02 441	90.48 363	95.84 407

pmmvs3		86.67 414	84.86 419	92.11 421	88.16 458	87.19 432	96.63 417	94.75 441	79.88 447	87.22 427	92.75 448	66.56 447	95.20 446	81.24 439	76.56 455	93.96 441

test_f		86.07 415	85.39 416	88.10 428	89.28 456	75.57 455	97.73 340	96.33 420	89.41 410	85.35 439	91.56 452	43.31 463	95.53 442	91.32 349	84.23 426	93.21 447

WB-MVS		84.86 416	85.33 417	83.46 437	89.48 455	69.56 463	98.19 275	96.42 419	89.55 406	81.79 446	94.67 428	84.80 329	90.12 459	52.44 463	80.64 443	90.69 450

SSC-MVS		84.27 417	84.71 420	82.96 441	89.19 457	68.83 464	98.08 296	96.30 421	89.04 414	81.37 448	94.47 429	84.60 336	89.89 460	49.80 465	79.52 445	90.15 451

dongtai		82.47 418	81.88 421	84.22 435	95.19 420	76.03 452	94.59 449	74.14 473	82.63 442	87.19 428	96.09 398	64.10 451	87.85 463	58.91 461	84.11 427	88.78 455

test_vis3_rt		79.22 419	77.40 426	84.67 434	86.44 462	74.85 458	97.66 345	81.43 469	84.98 436	67.12 462	81.91 460	28.09 471	97.60 407	88.96 392	80.04 444	81.55 460

test_method		79.03 420	78.17 422	81.63 442	86.06 463	54.40 474	82.75 462	96.89 402	39.54 466	80.98 450	95.57 418	58.37 456	94.73 449	84.74 427	78.61 448	95.75 409

testf1		79.02 421	77.70 423	82.99 439	88.10 459	66.90 465	94.67 445	93.11 452	71.08 457	74.02 455	93.41 441	34.15 467	93.25 453	72.25 455	78.50 449	88.82 453

APD_test2		79.02 421	77.70 423	82.99 439	88.10 459	66.90 465	94.67 445	93.11 452	71.08 457	74.02 455	93.41 441	34.15 467	93.25 453	72.25 455	78.50 449	88.82 453

LCM-MVSNet		78.70 423	76.24 429	86.08 431	77.26 470	71.99 461	94.34 451	96.72 409	61.62 461	76.53 453	89.33 454	33.91 469	92.78 456	81.85 436	74.60 457	93.46 444

kuosan		78.45 424	77.69 425	80.72 443	92.73 444	75.32 456	94.63 448	74.51 472	75.96 453	80.87 451	93.19 443	63.23 453	79.99 467	42.56 467	81.56 437	86.85 459

Gipuma		78.40 425	76.75 428	83.38 438	95.54 409	80.43 450	79.42 463	97.40 361	64.67 460	73.46 457	80.82 461	45.65 460	93.14 455	66.32 459	87.43 404	76.56 463
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		77.95 426	75.44 430	85.46 432	82.54 465	74.95 457	94.23 452	93.08 454	72.80 456	74.68 454	87.38 455	36.36 466	91.56 457	73.95 453	63.94 462	89.87 452

FPMVS		77.62 427	77.14 427	79.05 445	79.25 468	60.97 470	95.79 430	95.94 427	65.96 459	67.93 461	94.40 432	37.73 465	88.88 462	68.83 458	88.46 394	87.29 456

EGC-MVSNET		75.22 428	69.54 431	92.28 419	94.81 426	89.58 397	97.64 347	96.50 416	1.82 471	5.57 472	95.74 409	68.21 441	96.26 436	73.80 454	91.71 348	90.99 449

ANet_high		69.08 429	65.37 433	80.22 444	65.99 472	71.96 462	90.91 458	90.09 463	82.62 443	49.93 467	78.39 462	29.36 470	81.75 464	62.49 460	38.52 466	86.95 458

tmp_tt		68.90 430	66.97 432	74.68 447	50.78 474	59.95 471	87.13 459	83.47 468	38.80 467	62.21 463	96.23 392	64.70 450	76.91 469	88.91 393	30.49 467	87.19 457

PMVS	61.03 23	65.95 431	63.57 435	73.09 448	57.90 473	51.22 475	85.05 461	93.93 450	54.45 462	44.32 468	83.57 457	13.22 472	89.15 461	58.68 462	81.00 440	78.91 462
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		64.94 432	64.25 434	67.02 449	82.28 466	59.36 472	91.83 457	85.63 466	52.69 463	60.22 464	77.28 463	41.06 464	80.12 466	46.15 466	41.14 464	61.57 465

EMVS		64.07 433	63.26 436	66.53 450	81.73 467	58.81 473	91.85 456	84.75 467	51.93 465	59.09 465	75.13 464	43.32 462	79.09 468	42.03 468	39.47 465	61.69 464

MVE	62.14 22	63.28 434	59.38 437	74.99 446	74.33 471	65.47 467	85.55 460	80.50 470	52.02 464	51.10 466	75.00 465	10.91 475	80.50 465	51.60 464	53.40 463	78.99 461
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		30.17 435	30.18 439	30.16 451	78.61 469	43.29 476	66.79 464	14.21 475	17.31 468	14.82 471	11.93 471	11.55 474	41.43 470	37.08 469	19.30 468	5.76 468

cdsmvs_eth3d_5k		23.98 436	31.98 438	0.00 454	0.00 477	0.00 479	0.00 465	98.59 166	0.00 472	0.00 473	98.61 191	90.60 193	0.00 473	0.00 472	0.00 471	0.00 469

testmvs		21.48 437	24.95 440	11.09 453	14.89 475	6.47 478	96.56 419	9.87 476	7.55 469	17.93 469	39.02 467	9.43 476	5.90 472	16.56 471	12.72 469	20.91 467

test123		20.95 438	23.72 441	12.64 452	13.54 476	8.19 477	96.55 420	6.13 477	7.48 470	16.74 470	37.98 468	12.97 473	6.05 471	16.69 470	5.43 470	23.68 466

ab-mvs-re		8.20 439	10.94 442	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	98.43 209	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

pcd_1.5k_mvsjas		7.88 440	10.50 443	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	94.51 88	0.00 473	0.00 472	0.00 471	0.00 469

mmdepth		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

monomultidepth		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

test_blank		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

uanet_test		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

DCPMVS		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

sosnet-low-res		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

sosnet		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

uncertanet		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

Regformer		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

uanet		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

WAC-MVS						90.94 362								88.66 395

FOURS1					99.82 1	98.66 24	99.69 1	98.95 57	97.46 53	99.39 42

MSC_two_6792asdad				99.62 6	99.17 105	99.08 11		98.63 156					99.94 13	98.53 53	99.80 24	99.86 10

PC_three_1452									95.08 195	99.60 30	99.16 96	97.86 2	98.47 329	97.52 125	99.72 62	99.74 45

No_MVS				99.62 6	99.17 105	99.08 11		98.63 156					99.94 13	98.53 53	99.80 24	99.86 10

test_one_0601					99.66 28	99.25 2		98.86 86	97.55 45	99.20 54	99.47 33	97.57 6

eth-test2					0.00 477

eth-test					0.00 477

ZD-MVS					99.46 54	98.70 23		98.79 113	93.21 304	98.67 98	98.97 133	95.70 49	99.83 84	96.07 191	99.58 93

RE-MVS-def			98.34 49		99.49 48	97.86 70	99.11 61	98.80 108	96.49 112	99.17 57	99.35 58	95.29 66		97.72 104	99.65 76	99.71 58

IU-MVS					99.71 21	99.23 7		98.64 153	95.28 178	99.63 29				98.35 70	99.81 15	99.83 16

OPU-MVS				99.37 23	99.24 97	99.05 14	99.02 80				99.16 96	97.81 3	99.37 204	97.24 142	99.73 57	99.70 62

test_241102_TWO								98.87 80	97.65 37	99.53 35	99.48 31	97.34 11	99.94 13	98.43 65	99.80 24	99.83 16

test_241102_ONE					99.71 21	99.24 5		98.87 80	97.62 39	99.73 20	99.39 46	97.53 7	99.74 128

9.14			98.06 74		99.47 52		98.71 178	98.82 95	94.36 241	99.16 60	99.29 69	96.05 37	99.81 96	97.00 149	99.71 64

save fliter					99.46 54	98.38 36	98.21 270	98.71 131	97.95 26

test_0728_THIRD									97.32 61	99.45 37	99.46 38	97.88 1	99.94 13	98.47 61	99.86 2	99.85 13

test_0728_SECOND				99.71 1	99.72 14	99.35 1	98.97 91	98.88 73					99.94 13	98.47 61	99.81 15	99.84 15

test0726					99.72 14	99.25 2	99.06 68	98.88 73	97.62 39	99.56 32	99.50 27	97.42 9

GSMVS																99.20 169

test_part2					99.63 31	99.18 10				99.27 51

sam_mvs1												89.45 220				99.20 169

sam_mvs												88.99 236

ambc				89.49 426	86.66 461	75.78 453	92.66 455	96.72 409		86.55 433	92.50 449	46.01 459	97.90 391	90.32 366	82.09 432	94.80 429

MTGPA								98.74 123

test_post1							96.68 416				30.43 470	87.85 270	98.69 307	92.59 317

test_post											31.83 469	88.83 243	98.91 283

patchmatchnet-post											95.10 424	89.42 221	98.89 287

GG-mvs-BLEND				96.59 282	96.34 379	94.98 236	96.51 421	88.58 465		93.10 358	94.34 435	80.34 383	98.05 379	89.53 382	96.99 245	96.74 345

MTMP							98.89 115	94.14 448

gm-plane-assit					95.88 400	87.47 429			89.74 403		96.94 360		99.19 233	93.32 296

test9_res														96.39 185	99.57 94	99.69 65

TEST9					99.31 73	98.50 30	97.92 315	98.73 126	92.63 327	97.74 165	98.68 186	96.20 32	99.80 103

test_8					99.29 82	98.44 32	97.89 323	98.72 128	92.98 315	97.70 170	98.66 189	96.20 32	99.80 103

agg_prior2														95.87 201	99.57 94	99.68 70

agg_prior					99.30 77	98.38 36		98.72 128		97.57 185			99.81 96

TestCases				96.99 243	99.25 90	93.21 317		98.18 274	91.36 367	93.52 337	98.77 173	84.67 334	99.72 130	89.70 379	97.87 215	98.02 284

test_prior4						98.01 66	97.86 327

test_prior2							97.80 334		96.12 131	97.89 156	98.69 185	95.96 41		96.89 159	99.60 88

test_prior				99.19 46	99.31 73	98.22 53		98.84 90					99.70 136			99.65 78

旧先验2							97.57 353		91.30 372	98.67 98			99.80 103	95.70 212

新几何2							97.64 347

新几何1				99.16 51	99.34 65	98.01 66		98.69 137	90.06 397	98.13 128	98.95 140	94.60 86	99.89 62	91.97 336	99.47 116	99.59 89

旧先验1					99.29 82	97.48 85		98.70 135			99.09 116	95.56 52			99.47 116	99.61 85

无先验							97.58 352	98.72 128	91.38 366				99.87 73	93.36 295		99.60 87

原ACMM2							97.67 344

原ACMM1				98.65 92	99.32 71	96.62 134		98.67 145	93.27 303	97.81 159	98.97 133	95.18 73	99.83 84	93.84 281	99.46 119	99.50 101

test222					99.23 98	97.17 111	97.40 361	98.66 148	88.68 416	98.05 135	98.96 138	94.14 99			99.53 107	99.61 85

testdata2													99.89 62	91.65 344

segment_acmp												96.85 14

testdata				98.26 135	99.20 103	95.36 213		98.68 140	91.89 353	98.60 106	99.10 108	94.44 93	99.82 91	94.27 265	99.44 120	99.58 93

testdata1							97.32 371		96.34 121

test12				99.18 48	99.16 109	98.19 55		98.53 182		98.07 132		95.13 76	99.72 130		99.56 102	99.63 83

plane_prior7					97.42 313	94.63 253

plane_prior6					97.35 320	94.61 256						87.09 283

plane_prior5								98.56 176					99.03 263	96.07 191	94.27 298	96.92 321

plane_prior4											98.28 228

plane_prior3						94.61 256			97.02 85	95.34 264

plane_prior2							98.80 150		97.28 65

plane_prior1					97.37 319

plane_prior						94.60 258	98.44 242		96.74 99						94.22 300

n2								0.00 478

nn								0.00 478

door-mid								94.37 444

lessismore_v0				94.45 391	94.93 424	88.44 420		91.03 461		86.77 431	97.64 292	76.23 419	98.42 335	90.31 367	85.64 422	96.51 380

LGP-MVS_train				96.47 297	97.46 308	93.54 298		98.54 180	94.67 223	94.36 296	98.77 173	85.39 316	99.11 249	95.71 210	94.15 304	96.76 343

test11								98.66 148

door								94.64 442

HQP5-MVS						94.25 274

HQP-NCC					97.20 328		98.05 299		96.43 114	94.45 288

ACMP_Plane					97.20 328		98.05 299		96.43 114	94.45 288

BP-MVS														95.30 224

HQP4-MVS										94.45 288			98.96 274			96.87 333

HQP3-MVS								98.46 201							94.18 302

HQP2-MVS												86.75 289

NP-MVS					97.28 322	94.51 261					97.73 279

MDTV_nov1_ep13_2view						84.26 439	96.89 406		90.97 381	97.90 155		89.89 206		93.91 279		99.18 178

MDTV_nov1_ep13			95.40 217		97.48 306	88.34 421	96.85 409	97.29 369	93.74 272	97.48 187	97.26 321	89.18 229	99.05 259	91.92 337	97.43 236

ACMMP++_ref															92.97 332

ACMMP++															93.61 319

Test By Simon												94.64 85

ITE_SJBPF				95.44 350	97.42 313	91.32 356		97.50 349	95.09 194	93.59 332	98.35 219	81.70 365	98.88 289	89.71 378	93.39 325	96.12 401

DeepMVS_CX				86.78 430	97.09 338	72.30 460		95.17 438	75.92 454	84.34 443	95.19 422	70.58 437	95.35 443	79.98 443	89.04 388	92.68 448

High-resolution multi-view benchmark