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 60	99.43 62	97.48 88	98.88 125	99.30 14	98.47 17	99.85 10	99.43 42	96.71 18	99.96 4	99.86 1	99.80 24	99.89 6

SED-MVS		99.09 1	98.91 4	99.63 5	99.71 23	99.24 6	99.02 83	98.87 84	97.65 38	99.73 21	99.48 32	97.53 8	99.94 13	98.43 66	99.81 15	99.70 66

DVP-MVS++		99.08 3	98.89 5	99.64 4	99.17 109	99.23 8	99.69 1	98.88 77	97.32 62	99.53 36	99.47 34	97.81 3	99.94 13	98.47 62	99.72 66	99.74 49

fmvsm_l_conf0.5_n		99.07 4	99.05 2	99.14 56	99.41 64	97.54 86	98.89 118	99.31 13	98.49 16	99.86 7	99.42 43	96.45 26	99.96 4	99.86 1	99.74 57	99.90 5

DVP-MVS		99.03 5	98.83 9	99.63 5	99.72 16	99.25 3	98.97 94	98.58 175	97.62 40	99.45 38	99.46 39	97.42 10	99.94 13	98.47 62	99.81 15	99.69 69
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
TestfortrainingZip a		99.02 6	98.79 11	99.70 2	99.77 2	99.30 2	99.32 22	99.24 20	96.41 119	99.30 49	99.35 59	97.61 6	99.92 42	98.35 71	99.80 24	99.88 10

APDe-MVS		99.02 6	98.84 8	99.55 10	99.57 38	98.96 17	99.39 11	98.93 64	97.38 59	99.41 41	99.54 19	96.66 19	99.84 86	98.86 38	99.85 6	99.87 11
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
lecture		98.95 8	98.78 13	99.45 18	99.75 5	98.63 29	99.43 10	99.38 8	97.60 43	99.58 32	99.47 34	95.36 63	99.93 33	98.87 37	99.57 98	99.78 32

reproduce_model		98.94 9	98.81 10	99.34 30	99.52 44	98.26 53	98.94 103	98.84 94	98.06 24	99.35 45	99.61 4	96.39 29	99.94 13	98.77 41	99.82 14	99.83 18

reproduce-ours		98.93 10	98.78 13	99.38 22	99.49 51	98.38 39	98.86 132	98.83 96	98.06 24	99.29 51	99.58 15	96.40 27	99.94 13	98.68 44	99.81 15	99.81 24

our_new_method		98.93 10	98.78 13	99.38 22	99.49 51	98.38 39	98.86 132	98.83 96	98.06 24	99.29 51	99.58 15	96.40 27	99.94 13	98.68 44	99.81 15	99.81 24

test_fmvsmconf_n		98.92 12	98.87 6	99.04 66	98.88 145	97.25 110	98.82 145	99.34 11	98.75 10	99.80 13	99.61 4	95.16 76	99.95 9	99.70 16	99.80 24	99.93 1

DPE-MVS		98.92 12	98.67 19	99.65 3	99.58 36	99.20 10	98.42 254	98.91 71	97.58 44	99.54 35	99.46 39	97.10 13	99.94 13	97.64 117	99.84 11	99.83 18
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 14	98.79 11	99.24 44	99.34 69	97.83 77	98.70 186	99.26 16	98.85 5	99.92 1	99.51 25	93.91 105	99.95 9	99.86 1	99.79 33	99.92 2

fmvsm_l_conf0.5_n_3		98.90 14	98.74 17	99.37 26	99.36 66	98.25 54	98.89 118	99.24 20	98.77 9	99.89 3	99.59 12	93.39 111	99.96 4	99.78 9	99.76 46	99.89 6

SteuartSystems-ACMMP		98.90 14	98.75 16	99.36 28	99.22 104	98.43 37	99.10 67	98.87 84	97.38 59	99.35 45	99.40 46	97.78 5	99.87 77	97.77 105	99.85 6	99.78 32
Skip Steuart: Steuart Systems R&D Blog.
test_fmvsm_n_1920		98.87 17	99.01 3	98.45 121	99.42 63	96.43 153	98.96 99	99.36 10	98.63 12	99.86 7	99.51 25	95.91 45	99.97 1	99.72 13	99.75 53	98.94 222

ME-MVS		98.83 18	98.60 23	99.52 13	99.58 36	98.86 22	98.69 189	98.93 64	97.00 88	99.17 60	99.35 59	96.62 22	99.90 62	98.30 74	99.80 24	99.79 28

TSAR-MVS + MP.		98.78 19	98.62 21	99.24 44	99.69 28	98.28 52	99.14 58	98.66 152	96.84 94	99.56 33	99.31 69	96.34 30	99.70 140	98.32 73	99.73 61	99.73 54
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 19	98.56 26	99.45 18	99.32 75	98.87 20	98.47 242	98.81 105	97.72 33	98.76 93	99.16 100	97.05 14	99.78 122	98.06 87	99.66 77	99.69 69

MSP-MVS		98.74 21	98.55 27	99.29 37	99.75 5	98.23 55	99.26 31	98.88 77	97.52 47	99.41 41	98.78 177	96.00 41	99.79 119	97.79 104	99.59 94	99.85 15
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 22	98.62 21	99.05 65	99.35 68	97.27 104	98.80 154	99.23 27	98.93 3	99.79 14	99.59 12	92.34 128	99.95 9	99.82 6	99.71 68	99.92 2

XVS		98.70 23	98.49 34	99.34 30	99.70 26	98.35 48	99.29 26	98.88 77	97.40 56	98.46 116	99.20 90	95.90 47	99.89 66	97.85 100	99.74 57	99.78 32

fmvsm_s_conf0.5_n_10		98.66 24	98.54 29	99.02 67	99.36 66	97.21 113	98.86 132	99.23 27	98.90 4	99.83 11	99.59 12	91.57 157	99.94 13	99.79 8	99.74 57	99.89 6

fmvsm_s_conf0.5_n_6		98.65 25	98.55 27	98.95 76	98.50 185	97.30 100	98.79 162	99.16 39	98.14 22	99.86 7	99.41 45	93.71 108	99.91 54	99.71 14	99.64 85	99.65 82

MCST-MVS		98.65 25	98.37 43	99.48 16	99.60 35	98.87 20	98.41 255	98.68 144	97.04 85	98.52 114	98.80 171	96.78 17	99.83 88	97.93 94	99.61 90	99.74 49

SD-MVS		98.64 27	98.68 18	98.53 110	99.33 72	98.36 47	98.90 114	98.85 93	97.28 66	99.72 24	99.39 47	96.63 21	97.60 414	98.17 82	99.85 6	99.64 85
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 28	98.66 20	98.54 107	99.40 65	95.83 195	98.79 162	99.17 37	98.94 2	99.92 1	99.61 4	92.49 123	99.93 33	99.86 1	99.76 46	99.86 12

HFP-MVS		98.63 28	98.40 40	99.32 36	99.72 16	98.29 51	99.23 36	98.96 59	96.10 136	98.94 75	99.17 97	96.06 38	99.92 42	97.62 118	99.78 38	99.75 47

ACMMP_NAP		98.61 30	98.30 58	99.55 10	99.62 34	98.95 18	98.82 145	98.81 105	95.80 150	99.16 64	99.47 34	95.37 62	99.92 42	97.89 98	99.75 53	99.79 28

region2R		98.61 30	98.38 42	99.29 37	99.74 11	98.16 61	99.23 36	98.93 64	96.15 132	98.94 75	99.17 97	95.91 45	99.94 13	97.55 126	99.79 33	99.78 32

NCCC		98.61 30	98.35 46	99.38 22	99.28 90	98.61 30	98.45 244	98.76 123	97.82 32	98.45 119	98.93 149	96.65 20	99.83 88	97.38 144	99.41 127	99.71 62

SF-MVS		98.59 33	98.32 57	99.41 21	99.54 40	98.71 25	99.04 77	98.81 105	95.12 196	99.32 48	99.39 47	96.22 32	99.84 86	97.72 108	99.73 61	99.67 78

ACMMPR		98.59 33	98.36 44	99.29 37	99.74 11	98.15 62	99.23 36	98.95 60	96.10 136	98.93 79	99.19 95	95.70 51	99.94 13	97.62 118	99.79 33	99.78 32

test_fmvsmconf0.1_n		98.58 35	98.44 38	98.99 69	97.73 291	97.15 116	98.84 141	98.97 56	98.75 10	99.43 40	99.54 19	93.29 113	99.93 33	99.64 19	99.79 33	99.89 6

SMA-MVS		98.58 35	98.25 61	99.56 9	99.51 45	99.04 16	98.95 100	98.80 112	93.67 290	99.37 44	99.52 22	96.52 24	99.89 66	98.06 87	99.81 15	99.76 46
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 35	98.29 59	99.46 17	99.76 4	98.64 28	98.90 114	98.74 127	97.27 70	98.02 144	99.39 47	94.81 86	99.96 4	97.91 96	99.79 33	99.77 39

HPM-MVS++		98.58 35	98.25 61	99.55 10	99.50 47	99.08 12	98.72 181	98.66 152	97.51 48	98.15 130	98.83 168	95.70 51	99.92 42	97.53 128	99.67 74	99.66 81

SR-MVS		98.57 39	98.35 46	99.24 44	99.53 41	98.18 59	99.09 68	98.82 99	96.58 110	99.10 66	99.32 67	95.39 60	99.82 95	97.70 113	99.63 87	99.72 58

CP-MVS		98.57 39	98.36 44	99.19 49	99.66 30	97.86 73	99.34 17	98.87 84	95.96 142	98.60 110	99.13 106	96.05 39	99.94 13	97.77 105	99.86 2	99.77 39

MSLP-MVS++		98.56 41	98.57 25	98.55 105	99.26 93	96.80 131	98.71 182	99.05 49	97.28 66	98.84 85	99.28 74	96.47 25	99.40 204	98.52 60	99.70 70	99.47 114

DeepC-MVS_fast	96.70 1	98.55 42	98.34 52	99.18 51	99.25 94	98.04 67	98.50 237	98.78 119	97.72 33	98.92 81	99.28 74	95.27 69	99.82 95	97.55 126	99.77 40	99.69 69
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 43	98.35 46	99.13 57	99.49 51	97.86 73	99.11 64	98.80 112	96.49 114	99.17 60	99.35 59	95.34 65	99.82 95	97.72 108	99.65 80	99.71 62

fmvsm_s_conf0.5_n_5		98.53 44	98.35 46	99.08 62	99.07 124	97.46 92	98.68 192	99.20 33	97.50 49	99.87 4	99.50 28	91.96 147	99.96 4	99.76 10	99.65 80	99.82 22

fmvsm_s_conf0.5_n_3		98.53 44	98.45 37	98.79 84	99.23 102	97.32 97	98.80 154	99.26 16	98.82 6	99.87 4	99.60 9	90.95 189	99.93 33	99.76 10	99.73 61	99.12 192

APD-MVS_3200maxsize		98.53 44	98.33 56	99.15 55	99.50 47	97.92 72	99.15 55	98.81 105	96.24 128	99.20 57	99.37 53	95.30 67	99.80 107	97.73 107	99.67 74	99.72 58

MM		98.51 47	98.24 63	99.33 34	99.12 118	98.14 64	98.93 109	97.02 400	98.96 1	99.17 60	99.47 34	91.97 146	99.94 13	99.85 5	99.69 71	99.91 4

mPP-MVS		98.51 47	98.26 60	99.25 43	99.75 5	98.04 67	99.28 28	98.81 105	96.24 128	98.35 126	99.23 84	95.46 57	99.94 13	97.42 139	99.81 15	99.77 39

ZNCC-MVS		98.49 49	98.20 69	99.35 29	99.73 15	98.39 38	99.19 48	98.86 90	95.77 152	98.31 129	99.10 113	95.46 57	99.93 33	97.57 125	99.81 15	99.74 49

SPE-MVS-test		98.49 49	98.50 32	98.46 120	99.20 107	97.05 121	99.64 4	98.50 197	97.45 55	98.88 82	99.14 104	95.25 71	99.15 246	98.83 39	99.56 106	99.20 176

PGM-MVS		98.49 49	98.23 65	99.27 42	99.72 16	98.08 66	98.99 90	99.49 5	95.43 173	99.03 67	99.32 67	95.56 54	99.94 13	96.80 177	99.77 40	99.78 32

EI-MVSNet-Vis-set		98.47 52	98.39 41	98.69 92	99.46 57	96.49 150	98.30 268	98.69 141	97.21 73	98.84 85	99.36 57	95.41 59	99.78 122	98.62 48	99.65 80	99.80 27

MVS_111021_HR		98.47 52	98.34 52	98.88 81	99.22 104	97.32 97	97.91 325	99.58 3	97.20 74	98.33 127	99.00 137	95.99 42	99.64 154	98.05 89	99.76 46	99.69 69

balanced_conf03		98.45 54	98.35 46	98.74 88	98.65 174	97.55 84	99.19 48	98.60 163	96.72 104	99.35 45	98.77 180	95.06 81	99.55 177	98.95 34	99.87 1	99.12 192

test_fmvsmvis_n_1920		98.44 55	98.51 30	98.23 142	98.33 214	96.15 167	98.97 94	99.15 41	98.55 15	98.45 119	99.55 17	94.26 99	99.97 1	99.65 17	99.66 77	98.57 267

CS-MVS		98.44 55	98.49 34	98.31 134	99.08 123	96.73 135	99.67 3	98.47 204	97.17 77	98.94 75	99.10 113	95.73 50	99.13 251	98.71 43	99.49 117	99.09 200

GST-MVS		98.43 57	98.12 73	99.34 30	99.72 16	98.38 39	99.09 68	98.82 99	95.71 156	98.73 96	99.06 128	95.27 69	99.93 33	97.07 154	99.63 87	99.72 58

fmvsm_s_conf0.5_n		98.42 58	98.51 30	98.13 156	99.30 81	95.25 226	98.85 137	99.39 7	97.94 28	99.74 20	99.62 3	92.59 122	99.91 54	99.65 17	99.52 112	99.25 169

EI-MVSNet-UG-set		98.41 59	98.34 52	98.61 99	99.45 60	96.32 160	98.28 271	98.68 144	97.17 77	98.74 94	99.37 53	95.25 71	99.79 119	98.57 51	99.54 109	99.73 54

DELS-MVS		98.40 60	98.20 69	98.99 69	99.00 132	97.66 79	97.75 346	98.89 74	97.71 35	98.33 127	98.97 139	94.97 83	99.88 75	98.42 68	99.76 46	99.42 128
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 61	98.42 39	98.27 136	99.09 122	95.41 216	98.86 132	99.37 9	97.69 37	99.78 16	99.61 4	92.38 126	99.91 54	99.58 22	99.43 125	99.49 110

TSAR-MVS + GP.		98.38 61	98.24 63	98.81 83	99.22 104	97.25 110	98.11 300	98.29 260	97.19 75	98.99 73	99.02 131	96.22 32	99.67 147	98.52 60	98.56 181	99.51 103

HPM-MVS_fast		98.38 61	98.13 72	99.12 59	99.75 5	97.86 73	99.44 9	98.82 99	94.46 244	98.94 75	99.20 90	95.16 76	99.74 132	97.58 121	99.85 6	99.77 39

patch_mono-2		98.36 64	98.87 6	96.82 264	99.53 41	90.68 377	98.64 203	99.29 15	97.88 29	99.19 59	99.52 22	96.80 16	99.97 1	99.11 30	99.86 2	99.82 22

HPM-MVS		98.36 64	98.10 76	99.13 57	99.74 11	97.82 78	99.53 6	98.80 112	94.63 231	98.61 109	98.97 139	95.13 78	99.77 127	97.65 116	99.83 13	99.79 28
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 66	98.50 32	97.90 179	99.16 113	95.08 235	98.75 167	99.24 20	98.39 18	99.81 12	99.52 22	92.35 127	99.90 62	99.74 12	99.51 114	98.71 248

APD-MVS		98.35 66	98.00 82	99.42 20	99.51 45	98.72 24	98.80 154	98.82 99	94.52 239	99.23 56	99.25 83	95.54 56	99.80 107	96.52 186	99.77 40	99.74 49
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_LR		98.34 68	98.23 65	98.67 94	99.27 91	96.90 127	97.95 318	99.58 3	97.14 80	98.44 121	99.01 135	95.03 82	99.62 161	97.91 96	99.75 53	99.50 105

PHI-MVS		98.34 68	98.06 77	99.18 51	99.15 116	98.12 65	99.04 77	99.09 44	93.32 306	98.83 88	99.10 113	96.54 23	99.83 88	97.70 113	99.76 46	99.59 93

MP-MVS		98.33 70	98.01 81	99.28 40	99.75 5	98.18 59	99.22 40	98.79 117	96.13 133	97.92 157	99.23 84	94.54 89	99.94 13	96.74 180	99.78 38	99.73 54
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MVSMamba_PlusPlus		98.31 71	98.19 71	98.67 94	98.96 139	97.36 95	99.24 34	98.57 177	94.81 219	98.99 73	98.90 155	95.22 74	99.59 164	99.15 29	99.84 11	99.07 208

MP-MVS-pluss		98.31 71	97.92 84	99.49 15	99.72 16	98.88 19	98.43 251	98.78 119	94.10 255	97.69 176	99.42 43	95.25 71	99.92 42	98.09 86	99.80 24	99.67 78
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.5_n_2		98.30 73	98.21 67	98.57 102	99.25 94	97.11 118	98.66 199	99.20 33	98.82 6	99.79 14	99.60 9	89.38 229	99.92 42	99.80 7	99.38 132	98.69 250

fmvsm_s_conf0.5_n_7		98.23 74	98.35 46	97.89 181	98.86 149	94.99 241	98.58 215	99.00 52	98.29 19	99.73 21	99.60 9	91.70 152	99.92 42	99.63 20	99.73 61	98.76 242

MGCNet		98.23 74	97.91 85	99.21 48	98.06 254	97.96 71	98.58 215	95.51 439	98.58 13	98.87 83	99.26 78	92.99 117	99.95 9	99.62 21	99.67 74	99.73 54

ACMMP		98.23 74	97.95 83	99.09 61	99.74 11	97.62 82	99.03 80	99.41 6	95.98 141	97.60 188	99.36 57	94.45 94	99.93 33	97.14 151	98.85 165	99.70 66
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 77	98.11 74	98.49 117	98.34 211	97.26 109	99.61 5	98.43 218	96.78 97	98.87 83	98.84 164	93.72 107	99.01 275	98.91 36	99.50 115	99.19 180

fmvsm_s_conf0.1_n		98.18 78	98.21 67	98.11 160	98.54 183	95.24 227	98.87 128	99.24 20	97.50 49	99.70 25	99.67 1	91.33 169	99.89 66	99.47 24	99.54 109	99.21 175

fmvsm_s_conf0.1_n_2		98.14 79	98.02 80	98.53 110	98.88 145	97.07 120	98.69 189	98.82 99	98.78 8	99.77 17	99.61 4	88.83 249	99.91 54	99.71 14	99.07 148	98.61 260

fmvsm_s_conf0.1_n_a		98.08 80	98.04 79	98.21 143	97.66 297	95.39 217	98.89 118	99.17 37	97.24 71	99.76 19	99.67 1	91.13 180	99.88 75	99.39 25	99.41 127	99.35 140

dcpmvs_2		98.08 80	98.59 24	96.56 293	99.57 38	90.34 389	99.15 55	98.38 234	96.82 96	99.29 51	99.49 31	95.78 49	99.57 167	98.94 35	99.86 2	99.77 39

NormalMVS		98.07 82	97.90 86	98.59 101	99.75 5	96.60 141	98.94 103	98.60 163	97.86 30	98.71 99	99.08 123	91.22 176	99.80 107	97.40 141	99.57 98	99.37 135

CANet		98.05 83	97.76 89	98.90 80	98.73 159	97.27 104	98.35 258	98.78 119	97.37 61	97.72 173	98.96 144	91.53 162	99.92 42	98.79 40	99.65 80	99.51 103

train_agg		97.97 84	97.52 102	99.33 34	99.31 77	98.50 33	97.92 323	98.73 130	92.98 322	97.74 170	98.68 193	96.20 34	99.80 107	96.59 181	99.57 98	99.68 74

ETV-MVS		97.96 85	97.81 87	98.40 129	98.42 195	97.27 104	98.73 177	98.55 182	96.84 94	98.38 123	97.44 315	95.39 60	99.35 209	97.62 118	98.89 159	98.58 266

UA-Net		97.96 85	97.62 93	98.98 71	98.86 149	97.47 90	98.89 118	99.08 45	96.67 107	98.72 98	99.54 19	93.15 115	99.81 100	94.87 244	98.83 166	99.65 82

CDPH-MVS		97.94 87	97.49 104	99.28 40	99.47 55	98.44 35	97.91 325	98.67 149	92.57 338	98.77 92	98.85 163	95.93 44	99.72 134	95.56 222	99.69 71	99.68 74

DeepPCF-MVS	96.37 2	97.93 88	98.48 36	96.30 319	99.00 132	89.54 405	97.43 368	98.87 84	98.16 21	99.26 55	99.38 52	96.12 37	99.64 154	98.30 74	99.77 40	99.72 58

DeepC-MVS	95.98 3	97.88 89	97.58 95	98.77 86	99.25 94	96.93 125	98.83 143	98.75 125	96.96 90	96.89 220	99.50 28	90.46 199	99.87 77	97.84 102	99.76 46	99.52 100
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 90	97.54 101	98.83 82	95.48 420	96.83 130	98.95 100	98.60 163	98.58 13	98.93 79	99.55 17	88.57 254	99.91 54	99.54 23	99.61 90	99.77 39

DP-MVS Recon		97.86 90	97.46 107	99.06 64	99.53 41	98.35 48	98.33 260	98.89 74	92.62 335	98.05 139	98.94 147	95.34 65	99.65 151	96.04 202	99.42 126	99.19 180

CSCG		97.85 92	97.74 90	98.20 145	99.67 29	95.16 230	99.22 40	99.32 12	93.04 320	97.02 213	98.92 153	95.36 63	99.91 54	97.43 138	99.64 85	99.52 100

SymmetryMVS		97.84 93	97.58 95	98.62 98	99.01 130	96.60 141	98.94 103	98.44 209	97.86 30	98.71 99	99.08 123	91.22 176	99.80 107	97.40 141	97.53 241	99.47 114

BP-MVS1		97.82 94	97.51 103	98.76 87	98.25 224	97.39 94	99.15 55	97.68 332	96.69 105	98.47 115	99.10 113	90.29 203	99.51 184	98.60 49	99.35 135	99.37 135

MG-MVS		97.81 95	97.60 94	98.44 123	99.12 118	95.97 177	97.75 346	98.78 119	96.89 93	98.46 116	99.22 86	93.90 106	99.68 146	94.81 248	99.52 112	99.67 78

VNet		97.79 96	97.40 112	98.96 74	98.88 145	97.55 84	98.63 206	98.93 64	96.74 101	99.02 68	98.84 164	90.33 202	99.83 88	98.53 54	96.66 264	99.50 105

EIA-MVS		97.75 97	97.58 95	98.27 136	98.38 201	96.44 152	99.01 85	98.60 163	95.88 146	97.26 199	97.53 309	94.97 83	99.33 212	97.38 144	99.20 144	99.05 209

PS-MVSNAJ		97.73 98	97.77 88	97.62 211	98.68 169	95.58 206	97.34 377	98.51 192	97.29 64	98.66 106	97.88 273	94.51 90	99.90 62	97.87 99	99.17 146	97.39 310

casdiffmvs_mvg		97.72 99	97.48 106	98.44 123	98.42 195	96.59 145	98.92 111	98.44 209	96.20 130	97.76 167	99.20 90	91.66 155	99.23 233	98.27 80	98.41 199	99.49 110
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CPTT-MVS		97.72 99	97.32 117	98.92 77	99.64 32	97.10 119	99.12 62	98.81 105	92.34 346	98.09 135	99.08 123	93.01 116	99.92 42	96.06 201	99.77 40	99.75 47

PVSNet_Blended_VisFu		97.70 101	97.46 107	98.44 123	99.27 91	95.91 185	98.63 206	99.16 39	94.48 243	97.67 177	98.88 159	92.80 119	99.91 54	97.11 152	99.12 147	99.50 105

mvsany_test1		97.69 102	97.70 91	97.66 207	98.24 225	94.18 284	97.53 362	97.53 353	95.52 168	99.66 27	99.51 25	94.30 97	99.56 170	98.38 69	98.62 176	99.23 171

sasdasda		97.67 103	97.23 125	98.98 71	98.70 164	98.38 39	99.34 17	98.39 230	96.76 99	97.67 177	97.40 319	92.26 132	99.49 188	98.28 77	96.28 282	99.08 204

canonicalmvs		97.67 103	97.23 125	98.98 71	98.70 164	98.38 39	99.34 17	98.39 230	96.76 99	97.67 177	97.40 319	92.26 132	99.49 188	98.28 77	96.28 282	99.08 204

xiu_mvs_v2_base		97.66 105	97.70 91	97.56 215	98.61 178	95.46 214	97.44 366	98.46 205	97.15 79	98.65 107	98.15 248	94.33 96	99.80 107	97.84 102	98.66 175	97.41 308

GDP-MVS		97.64 106	97.28 119	98.71 91	98.30 219	97.33 96	99.05 73	98.52 189	96.34 125	98.80 89	99.05 129	89.74 216	99.51 184	96.86 173	98.86 163	99.28 159

baseline		97.64 106	97.44 109	98.25 140	98.35 206	96.20 164	99.00 87	98.32 247	96.33 127	98.03 142	99.17 97	91.35 168	99.16 242	98.10 85	98.29 208	99.39 132

casdiffmvs		97.63 108	97.41 111	98.28 135	98.33 214	96.14 168	98.82 145	98.32 247	96.38 123	97.95 152	99.21 88	91.23 175	99.23 233	98.12 84	98.37 201	99.48 112
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MGCFI-Net		97.62 109	97.19 128	98.92 77	98.66 171	98.20 57	99.32 22	98.38 234	96.69 105	97.58 190	97.42 318	92.10 140	99.50 187	98.28 77	96.25 285	99.08 204

xiu_mvs_v1_base_debu		97.60 110	97.56 98	97.72 196	98.35 206	95.98 172	97.86 335	98.51 192	97.13 81	99.01 70	98.40 220	91.56 158	99.80 107	98.53 54	98.68 171	97.37 312

xiu_mvs_v1_base		97.60 110	97.56 98	97.72 196	98.35 206	95.98 172	97.86 335	98.51 192	97.13 81	99.01 70	98.40 220	91.56 158	99.80 107	98.53 54	98.68 171	97.37 312

xiu_mvs_v1_base_debi		97.60 110	97.56 98	97.72 196	98.35 206	95.98 172	97.86 335	98.51 192	97.13 81	99.01 70	98.40 220	91.56 158	99.80 107	98.53 54	98.68 171	97.37 312

diffmvs_AUTHOR		97.59 113	97.44 109	98.01 172	98.26 223	95.47 213	98.12 297	98.36 240	96.38 123	98.84 85	99.10 113	91.13 180	99.26 225	98.24 81	98.56 181	99.30 154

diffmvs		97.58 114	97.40 112	98.13 156	98.32 217	95.81 198	98.06 306	98.37 236	96.20 130	98.74 94	98.89 158	91.31 171	99.25 228	98.16 83	98.52 185	99.34 142
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		97.57 115	97.37 114	98.20 145	98.50 185	95.86 193	98.89 118	97.03 397	97.29 64	98.73 96	98.90 155	89.41 228	99.32 213	98.68 44	98.86 163	99.42 128

MVSFormer		97.57 115	97.49 104	97.84 183	98.07 251	95.76 201	99.47 7	98.40 225	94.98 208	98.79 90	98.83 168	92.34 128	98.41 349	96.91 161	99.59 94	99.34 142

alignmvs		97.56 117	97.07 135	99.01 68	98.66 171	98.37 46	98.83 143	98.06 312	96.74 101	98.00 148	97.65 296	90.80 191	99.48 193	98.37 70	96.56 268	99.19 180

DPM-MVS		97.55 118	96.99 142	99.23 47	99.04 126	98.55 31	97.17 394	98.35 241	94.85 218	97.93 156	98.58 203	95.07 80	99.71 139	92.60 322	99.34 136	99.43 125

OMC-MVS		97.55 118	97.34 116	98.20 145	99.33 72	95.92 184	98.28 271	98.59 170	95.52 168	97.97 150	99.10 113	93.28 114	99.49 188	95.09 239	98.88 160	99.19 180

viewcassd2359sk11		97.53 120	97.32 117	98.16 149	98.45 192	95.83 195	98.57 223	98.42 222	95.52 168	98.07 136	99.12 109	91.81 150	99.25 228	97.46 137	98.48 190	99.41 131

LuminaMVS		97.49 121	97.18 129	98.42 127	97.50 312	97.15 116	98.45 244	97.68 332	96.56 113	98.68 101	98.78 177	89.84 213	99.32 213	98.60 49	98.57 180	98.79 234

E3		97.48 122	97.25 121	98.16 149	98.38 201	95.79 199	98.58 215	98.44 209	95.58 163	98.00 148	99.14 104	91.25 174	99.24 231	97.50 133	98.44 191	99.45 121

KinetiMVS		97.48 122	97.05 137	98.78 85	98.37 204	97.30 100	98.99 90	98.70 139	97.18 76	99.02 68	99.01 135	87.50 283	99.67 147	95.33 229	99.33 138	99.37 135

viewmanbaseed2359cas		97.47 124	97.25 121	98.14 151	98.41 197	95.84 194	98.57 223	98.43 218	95.55 166	97.97 150	99.12 109	91.26 173	99.15 246	97.42 139	98.53 184	99.43 125

PAPM_NR		97.46 125	97.11 132	98.50 115	99.50 47	96.41 155	98.63 206	98.60 163	95.18 189	97.06 211	98.06 254	94.26 99	99.57 167	93.80 290	98.87 162	99.52 100

EPP-MVSNet		97.46 125	97.28 119	97.99 174	98.64 175	95.38 218	99.33 21	98.31 251	93.61 294	97.19 203	99.07 127	94.05 102	99.23 233	96.89 165	98.43 194	99.37 135

3Dnovator	94.51 5	97.46 125	96.93 146	99.07 63	97.78 285	97.64 80	99.35 16	99.06 47	97.02 86	93.75 337	99.16 100	89.25 233	99.92 42	97.22 150	99.75 53	99.64 85

CNLPA		97.45 128	97.03 139	98.73 89	99.05 125	97.44 93	98.07 305	98.53 186	95.32 182	96.80 225	98.53 208	93.32 112	99.72 134	94.31 271	99.31 139	99.02 213

lupinMVS		97.44 129	97.22 127	98.12 159	98.07 251	95.76 201	97.68 351	97.76 329	94.50 242	98.79 90	98.61 198	92.34 128	99.30 218	97.58 121	99.59 94	99.31 150

3Dnovator+	94.38 6	97.43 130	96.78 157	99.38 22	97.83 282	98.52 32	99.37 13	98.71 135	97.09 84	92.99 367	99.13 106	89.36 230	99.89 66	96.97 157	99.57 98	99.71 62

Vis-MVSNet		97.42 131	97.11 132	98.34 132	98.66 171	96.23 163	99.22 40	99.00 52	96.63 109	98.04 141	99.21 88	88.05 270	99.35 209	96.01 204	99.21 143	99.45 121
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
API-MVS		97.41 132	97.25 121	97.91 178	98.70 164	96.80 131	98.82 145	98.69 141	94.53 237	98.11 133	98.28 235	94.50 93	99.57 167	94.12 279	99.49 117	97.37 312

sss		97.39 133	96.98 144	98.61 99	98.60 179	96.61 140	98.22 277	98.93 64	93.97 265	98.01 147	98.48 213	91.98 144	99.85 82	96.45 188	98.15 212	99.39 132

test_cas_vis1_n_1920		97.38 134	97.36 115	97.45 219	98.95 140	93.25 322	99.00 87	98.53 186	97.70 36	99.77 17	99.35 59	84.71 339	99.85 82	98.57 51	99.66 77	99.26 167

PVSNet_Blended		97.38 134	97.12 131	98.14 151	99.25 94	95.35 221	97.28 382	99.26 16	93.13 316	97.94 154	98.21 243	92.74 120	99.81 100	96.88 167	99.40 130	99.27 160

WTY-MVS		97.37 136	96.92 147	98.72 90	98.86 149	96.89 129	98.31 265	98.71 135	95.26 185	97.67 177	98.56 207	92.21 136	99.78 122	95.89 206	96.85 258	99.48 112

AstraMVS		97.34 137	97.24 124	97.65 208	98.13 245	94.15 285	98.94 103	96.25 429	97.47 53	98.60 110	99.28 74	89.67 218	99.41 203	98.73 42	98.07 216	99.38 134

viewmacassd2359aftdt		97.32 138	97.07 135	98.08 163	98.30 219	95.69 203	98.62 209	98.44 209	95.56 164	97.86 162	99.22 86	89.91 211	99.14 249	97.29 147	98.43 194	99.42 128

jason		97.32 138	97.08 134	98.06 167	97.45 318	95.59 205	97.87 333	97.91 323	94.79 221	98.55 113	98.83 168	91.12 182	99.23 233	97.58 121	99.60 92	99.34 142
jason: jason.
MVS_Test		97.28 140	97.00 140	98.13 156	98.33 214	95.97 177	98.74 171	98.07 307	94.27 250	98.44 121	98.07 253	92.48 124	99.26 225	96.43 189	98.19 211	99.16 186

EPNet		97.28 140	96.87 149	98.51 112	94.98 429	96.14 168	98.90 114	97.02 400	98.28 20	95.99 260	99.11 111	91.36 167	99.89 66	96.98 156	99.19 145	99.50 105
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SSM_0404		97.26 142	97.00 140	98.03 169	98.46 190	95.99 171	98.62 209	98.44 209	94.77 222	97.24 200	98.93 149	91.22 176	99.28 222	96.54 183	98.74 170	98.84 230

mvsmamba		97.25 143	96.99 142	98.02 171	98.34 211	95.54 210	99.18 52	97.47 359	95.04 202	98.15 130	98.57 206	89.46 225	99.31 217	97.68 115	99.01 153	99.22 173

viewdifsd2359ckpt13		97.24 144	96.97 145	98.06 167	98.43 193	95.77 200	98.59 212	98.34 244	94.81 219	97.60 188	98.94 147	90.78 195	99.09 261	96.93 160	98.33 204	99.32 149

test_yl		97.22 145	96.78 157	98.54 107	98.73 159	96.60 141	98.45 244	98.31 251	94.70 225	98.02 144	98.42 218	90.80 191	99.70 140	96.81 174	96.79 260	99.34 142

DCV-MVSNet		97.22 145	96.78 157	98.54 107	98.73 159	96.60 141	98.45 244	98.31 251	94.70 225	98.02 144	98.42 218	90.80 191	99.70 140	96.81 174	96.79 260	99.34 142

IS-MVSNet		97.22 145	96.88 148	98.25 140	98.85 152	96.36 158	99.19 48	97.97 317	95.39 176	97.23 201	98.99 138	91.11 183	98.93 287	94.60 259	98.59 178	99.47 114

viewdifsd2359ckpt07		97.20 148	97.05 137	97.65 208	98.40 199	94.33 277	98.39 256	98.43 218	95.67 158	97.66 181	99.08 123	90.04 208	99.32 213	97.47 136	98.29 208	99.31 150

PLC	95.07 4	97.20 148	96.78 157	98.44 123	99.29 86	96.31 162	98.14 294	98.76 123	92.41 344	96.39 248	98.31 233	94.92 85	99.78 122	94.06 282	98.77 169	99.23 171
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		97.18 150	97.18 129	97.20 232	98.81 155	93.27 319	95.78 439	99.15 41	95.25 186	96.79 226	98.11 251	92.29 131	99.07 264	98.56 53	99.85 6	99.25 169

SSM_0407		97.17 151	96.87 149	98.08 163	98.19 233	95.90 186	98.52 229	98.44 209	94.77 222	96.75 227	98.93 149	91.22 176	99.22 237	96.54 183	98.43 194	99.10 197

LS3D		97.16 152	96.66 166	98.68 93	98.53 184	97.19 114	98.93 109	98.90 72	92.83 329	95.99 260	99.37 53	92.12 139	99.87 77	93.67 294	99.57 98	98.97 218

AdaColmap		97.15 153	96.70 162	98.48 118	99.16 113	96.69 137	98.01 312	98.89 74	94.44 245	96.83 221	98.68 193	90.69 196	99.76 128	94.36 267	99.29 140	98.98 217

viewdifsd2359ckpt09		97.13 154	96.79 155	98.14 151	98.43 193	95.90 186	98.52 229	98.37 236	94.32 248	97.33 195	98.86 162	90.23 206	99.16 242	96.81 174	98.25 210	99.36 139

mamv4		97.13 154	98.11 74	94.17 403	98.97 138	83.70 448	98.66 199	98.71 135	94.63 231	97.83 163	98.90 155	96.25 31	99.55 177	99.27 27	99.76 46	99.27 160

Effi-MVS+		97.12 156	96.69 163	98.39 130	98.19 233	96.72 136	97.37 373	98.43 218	93.71 283	97.65 182	98.02 257	92.20 137	99.25 228	96.87 170	97.79 225	99.19 180

CHOSEN 1792x2688		97.12 156	96.80 153	98.08 163	99.30 81	94.56 266	98.05 307	99.71 1	93.57 296	97.09 207	98.91 154	88.17 264	99.89 66	96.87 170	99.56 106	99.81 24

F-COLMAP		97.09 158	96.80 153	97.97 175	99.45 60	94.95 245	98.55 227	98.62 162	93.02 321	96.17 255	98.58 203	94.01 103	99.81 100	93.95 284	98.90 158	99.14 190

RRT-MVS		97.03 159	96.78 157	97.77 192	97.90 278	94.34 275	99.12 62	98.35 241	95.87 147	98.06 138	98.70 191	86.45 302	99.63 157	98.04 90	98.54 183	99.35 140

TAMVS		97.02 160	96.79 155	97.70 199	98.06 254	95.31 224	98.52 229	98.31 251	93.95 266	97.05 212	98.61 198	93.49 110	98.52 331	95.33 229	97.81 224	99.29 157

viewmambaseed2359dif		97.01 161	96.84 151	97.51 217	98.19 233	94.21 283	98.16 290	98.23 272	93.61 294	97.78 165	99.13 106	90.79 194	99.18 241	97.24 148	98.40 200	99.15 187

CDS-MVSNet		96.99 162	96.69 163	97.90 179	98.05 256	95.98 172	98.20 280	98.33 246	93.67 290	96.95 214	98.49 212	93.54 109	98.42 342	95.24 236	97.74 228	99.31 150
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CANet_DTU		96.96 163	96.55 171	98.21 143	98.17 242	96.07 170	97.98 316	98.21 274	97.24 71	97.13 205	98.93 149	86.88 294	99.91 54	95.00 242	99.37 134	98.66 256

114514_t		96.93 164	96.27 184	98.92 77	99.50 47	97.63 81	98.85 137	98.90 72	84.80 444	97.77 166	99.11 111	92.84 118	99.66 150	94.85 245	99.77 40	99.47 114

MAR-MVS		96.91 165	96.40 178	98.45 121	98.69 167	96.90 127	98.66 199	98.68 144	92.40 345	97.07 210	97.96 264	91.54 161	99.75 130	93.68 292	98.92 157	98.69 250
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		96.90 166	96.49 175	98.14 151	99.33 72	95.56 207	97.38 371	99.65 2	92.34 346	97.61 185	98.20 244	89.29 232	99.10 260	96.97 157	97.60 233	99.77 39

Vis-MVSNet (Re-imp)		96.87 167	96.55 171	97.83 184	98.73 159	95.46 214	99.20 46	98.30 258	94.96 210	96.60 236	98.87 160	90.05 207	98.59 326	93.67 294	98.60 177	99.46 119

SDMVSNet		96.85 168	96.42 176	98.14 151	99.30 81	96.38 156	99.21 43	99.23 27	95.92 143	95.96 262	98.76 185	85.88 314	99.44 200	97.93 94	95.59 297	98.60 261

PAPR		96.84 169	96.24 186	98.65 96	98.72 163	96.92 126	97.36 375	98.57 177	93.33 305	96.67 231	97.57 305	94.30 97	99.56 170	91.05 365	98.59 178	99.47 114

HY-MVS	93.96 8	96.82 170	96.23 187	98.57 102	98.46 190	97.00 122	98.14 294	98.21 274	93.95 266	96.72 230	97.99 261	91.58 156	99.76 128	94.51 263	96.54 269	98.95 221

mamba_0408		96.81 171	96.38 179	98.09 162	98.19 233	95.90 186	95.69 440	98.32 247	94.51 240	96.75 227	98.73 187	90.99 187	99.27 224	95.83 209	98.43 194	99.10 197

UGNet		96.78 172	96.30 183	98.19 148	98.24 225	95.89 191	98.88 125	98.93 64	97.39 58	96.81 224	97.84 277	82.60 368	99.90 62	96.53 185	99.49 117	98.79 234
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		96.74 173	96.64 167	97.05 247	97.99 265	92.82 334	98.45 244	98.27 261	95.16 190	97.30 196	98.79 173	91.53 162	99.06 265	94.74 250	97.54 237	99.27 160

IMVS_0403		96.74 173	96.61 168	97.12 241	97.99 265	92.82 334	98.47 242	98.27 261	95.16 190	97.13 205	98.79 173	91.44 165	99.26 225	94.74 250	97.54 237	99.27 160

PVSNet_BlendedMVS		96.73 175	96.60 169	97.12 241	99.25 94	95.35 221	98.26 274	99.26 16	94.28 249	97.94 154	97.46 312	92.74 120	99.81 100	96.88 167	93.32 335	96.20 405

SSM_04072		96.71 176	96.38 179	97.68 202	98.19 233	95.90 186	95.69 440	98.32 247	94.51 240	96.75 227	98.73 187	90.99 187	98.02 388	95.83 209	98.43 194	99.10 197

test_vis1_n_1920		96.71 176	96.84 151	96.31 318	99.11 120	89.74 398	99.05 73	98.58 175	98.08 23	99.87 4	99.37 53	78.48 400	99.93 33	99.29 26	99.69 71	99.27 160

mvs_anonymous		96.70 178	96.53 173	97.18 235	98.19 233	93.78 295	98.31 265	98.19 278	94.01 262	94.47 294	98.27 238	92.08 142	98.46 337	97.39 143	97.91 220	99.31 150

Elysia		96.64 179	96.02 196	98.51 112	98.04 258	97.30 100	98.74 171	98.60 163	95.04 202	97.91 158	98.84 164	83.59 363	99.48 193	94.20 275	99.25 141	98.75 243

StellarMVS		96.64 179	96.02 196	98.51 112	98.04 258	97.30 100	98.74 171	98.60 163	95.04 202	97.91 158	98.84 164	83.59 363	99.48 193	94.20 275	99.25 141	98.75 243

1112_ss		96.63 181	96.00 198	98.50 115	98.56 180	96.37 157	98.18 288	98.10 300	92.92 325	94.84 282	98.43 216	92.14 138	99.58 166	94.35 268	96.51 270	99.56 99

PMMVS		96.60 182	96.33 182	97.41 223	97.90 278	93.93 291	97.35 376	98.41 223	92.84 328	97.76 167	97.45 314	91.10 184	99.20 238	96.26 194	97.91 220	99.11 195

DP-MVS		96.59 183	95.93 201	98.57 102	99.34 69	96.19 166	98.70 186	98.39 230	89.45 415	94.52 292	99.35 59	91.85 148	99.85 82	92.89 318	98.88 160	99.68 74

PatchMatch-RL		96.59 183	96.03 195	98.27 136	99.31 77	96.51 149	97.91 325	99.06 47	93.72 282	96.92 218	98.06 254	88.50 259	99.65 151	91.77 347	99.00 155	98.66 256

GeoE		96.58 185	96.07 192	98.10 161	98.35 206	95.89 191	99.34 17	98.12 294	93.12 317	96.09 256	98.87 160	89.71 217	98.97 277	92.95 314	98.08 215	99.43 125

icg_test_0407_2		96.56 186	96.50 174	96.73 270	97.99 265	92.82 334	97.18 391	98.27 261	95.16 190	97.30 196	98.79 173	91.53 162	98.10 379	94.74 250	97.54 237	99.27 160

XVG-OURS		96.55 187	96.41 177	96.99 250	98.75 158	93.76 296	97.50 365	98.52 189	95.67 158	96.83 221	99.30 72	88.95 247	99.53 180	95.88 207	96.26 284	97.69 301

FIs		96.51 188	96.12 191	97.67 204	97.13 342	97.54 86	99.36 14	99.22 32	95.89 145	94.03 323	98.35 226	91.98 144	98.44 340	96.40 190	92.76 343	97.01 320

XVG-OURS-SEG-HR		96.51 188	96.34 181	97.02 249	98.77 157	93.76 296	97.79 344	98.50 197	95.45 172	96.94 215	99.09 121	87.87 275	99.55 177	96.76 179	95.83 296	97.74 298

PS-MVSNAJss		96.43 190	96.26 185	96.92 259	95.84 409	95.08 235	99.16 54	98.50 197	95.87 147	93.84 332	98.34 230	94.51 90	98.61 322	96.88 167	93.45 330	97.06 318

test_fmvs1		96.42 191	96.67 165	95.66 348	98.82 154	88.53 425	98.80 154	98.20 276	96.39 122	99.64 29	99.20 90	80.35 388	99.67 147	99.04 32	99.57 98	98.78 238

FC-MVSNet-test		96.42 191	96.05 193	97.53 216	96.95 351	97.27 104	99.36 14	99.23 27	95.83 149	93.93 326	98.37 224	92.00 143	98.32 361	96.02 203	92.72 344	97.00 321

ab-mvs		96.42 191	95.71 212	98.55 105	98.63 176	96.75 134	97.88 332	98.74 127	93.84 272	96.54 241	98.18 246	85.34 325	99.75 130	95.93 205	96.35 274	99.15 187

FA-MVS(test-final)		96.41 194	95.94 200	97.82 186	98.21 229	95.20 229	97.80 342	97.58 343	93.21 311	97.36 194	97.70 289	89.47 223	99.56 170	94.12 279	97.99 217	98.71 248

PVSNet	91.96 18	96.35 195	96.15 188	96.96 254	99.17 109	92.05 350	96.08 432	98.68 144	93.69 286	97.75 169	97.80 283	88.86 248	99.69 145	94.26 273	99.01 153	99.15 187

Test_1112_low_res		96.34 196	95.66 217	98.36 131	98.56 180	95.94 180	97.71 349	98.07 307	92.10 355	94.79 286	97.29 327	91.75 151	99.56 170	94.17 277	96.50 271	99.58 97

viewdifsd2359ckpt11		96.30 197	96.13 189	96.81 265	98.10 248	92.10 346	98.49 240	98.40 225	96.02 138	97.61 185	99.31 69	86.37 304	99.29 220	97.52 129	93.36 334	99.04 210

viewmsd2359difaftdt		96.30 197	96.13 189	96.81 265	98.10 248	92.10 346	98.49 240	98.40 225	96.02 138	97.61 185	99.31 69	86.37 304	99.30 218	97.52 129	93.37 333	99.04 210

Effi-MVS+-dtu		96.29 199	96.56 170	95.51 353	97.89 280	90.22 390	98.80 154	98.10 300	96.57 112	96.45 246	96.66 384	90.81 190	98.91 290	95.72 216	97.99 217	97.40 309

QAPM		96.29 199	95.40 223	98.96 74	97.85 281	97.60 83	99.23 36	98.93 64	89.76 409	93.11 364	99.02 131	89.11 238	99.93 33	91.99 341	99.62 89	99.34 142

Fast-Effi-MVS+		96.28 201	95.70 214	98.03 169	98.29 221	95.97 177	98.58 215	98.25 270	91.74 363	95.29 275	97.23 332	91.03 186	99.15 246	92.90 316	97.96 219	98.97 218

nrg030		96.28 201	95.72 209	97.96 177	96.90 356	98.15 62	99.39 11	98.31 251	95.47 171	94.42 300	98.35 226	92.09 141	98.69 314	97.50 133	89.05 394	97.04 319

1314		96.25 203	95.73 208	97.79 188	97.13 342	95.55 209	98.19 283	98.59 170	93.47 300	92.03 393	97.82 281	91.33 169	99.49 188	94.62 258	98.44 191	98.32 281

sd_testset		96.17 204	95.76 207	97.42 222	99.30 81	94.34 275	98.82 145	99.08 45	95.92 143	95.96 262	98.76 185	82.83 367	99.32 213	95.56 222	95.59 297	98.60 261

h-mvs33		96.17 204	95.62 218	97.81 187	99.03 127	94.45 268	98.64 203	98.75 125	97.48 51	98.67 102	98.72 190	89.76 214	99.86 81	97.95 92	81.59 443	99.11 195

HQP_MVS		96.14 206	95.90 202	96.85 262	97.42 320	94.60 264	98.80 154	98.56 180	97.28 66	95.34 271	98.28 235	87.09 289	99.03 270	96.07 198	94.27 305	96.92 328

tttt0517		96.07 207	95.51 221	97.78 189	98.41 197	94.84 249	99.28 28	94.33 452	94.26 251	97.64 183	98.64 197	84.05 354	99.47 197	95.34 228	97.60 233	99.03 212

MVSTER		96.06 208	95.72 209	97.08 245	98.23 227	95.93 183	98.73 177	98.27 261	94.86 216	95.07 277	98.09 252	88.21 263	98.54 329	96.59 181	93.46 328	96.79 347

thisisatest0530		96.01 209	95.36 228	97.97 175	98.38 201	95.52 211	98.88 125	94.19 454	94.04 257	97.64 183	98.31 233	83.82 361	99.46 198	95.29 233	97.70 230	98.93 223

test_djsdf		96.00 210	95.69 215	96.93 256	95.72 411	95.49 212	99.47 7	98.40 225	94.98 208	94.58 290	97.86 274	89.16 236	98.41 349	96.91 161	94.12 313	96.88 337

EI-MVSNet		95.96 211	95.83 204	96.36 314	97.93 276	93.70 302	98.12 297	98.27 261	93.70 285	95.07 277	99.02 131	92.23 135	98.54 329	94.68 254	93.46 328	96.84 343

VortexMVS		95.95 212	95.79 205	96.42 310	98.29 221	93.96 290	98.68 192	98.31 251	96.02 138	94.29 308	97.57 305	89.47 223	98.37 356	97.51 132	91.93 351	96.94 326

ECVR-MVS		95.95 212	95.71 212	96.65 278	99.02 128	90.86 372	99.03 80	91.80 465	96.96 90	98.10 134	99.26 78	81.31 374	99.51 184	96.90 164	99.04 150	99.59 93

BH-untuned		95.95 212	95.72 209	96.65 278	98.55 182	92.26 342	98.23 276	97.79 328	93.73 280	94.62 289	98.01 259	88.97 246	99.00 276	93.04 311	98.51 186	98.68 252

test1111		95.94 215	95.78 206	96.41 311	98.99 135	90.12 391	99.04 77	92.45 464	96.99 89	98.03 142	99.27 77	81.40 373	99.48 193	96.87 170	99.04 150	99.63 87

MSDG		95.93 216	95.30 235	97.83 184	98.90 143	95.36 219	96.83 419	98.37 236	91.32 378	94.43 299	98.73 187	90.27 204	99.60 163	90.05 379	98.82 167	98.52 269

BH-RMVSNet		95.92 217	95.32 233	97.69 200	98.32 217	94.64 258	98.19 283	97.45 364	94.56 235	96.03 258	98.61 198	85.02 330	99.12 254	90.68 370	99.06 149	99.30 154

test_fmvs1_n		95.90 218	95.99 199	95.63 349	98.67 170	88.32 429	99.26 31	98.22 273	96.40 121	99.67 26	99.26 78	73.91 438	99.70 140	99.02 33	99.50 115	98.87 227

Fast-Effi-MVS+-dtu		95.87 219	95.85 203	95.91 335	97.74 290	91.74 356	98.69 189	98.15 290	95.56 164	94.92 280	97.68 294	88.98 245	98.79 308	93.19 306	97.78 226	97.20 316

LFMVS		95.86 220	94.98 250	98.47 119	98.87 148	96.32 160	98.84 141	96.02 430	93.40 303	98.62 108	99.20 90	74.99 431	99.63 157	97.72 108	97.20 246	99.46 119

baseline1		95.84 221	95.12 243	98.01 172	98.49 189	95.98 172	98.73 177	97.03 397	95.37 179	96.22 251	98.19 245	89.96 210	99.16 242	94.60 259	87.48 410	98.90 226

OpenMVS	93.04 13	95.83 222	95.00 248	98.32 133	97.18 339	97.32 97	99.21 43	98.97 56	89.96 405	91.14 402	99.05 129	86.64 297	99.92 42	93.38 300	99.47 120	97.73 299

IMVS_0404		95.82 223	95.52 219	96.73 270	97.99 265	92.82 334	97.23 384	98.27 261	95.16 190	94.31 306	98.79 173	85.63 318	98.10 379	94.74 250	97.54 237	99.27 160

VDD-MVS		95.82 223	95.23 237	97.61 212	98.84 153	93.98 289	98.68 192	97.40 368	95.02 206	97.95 152	99.34 66	74.37 437	99.78 122	98.64 47	96.80 259	99.08 204

UniMVSNet (Re)		95.78 225	95.19 239	97.58 213	96.99 349	97.47 90	98.79 162	99.18 36	95.60 161	93.92 327	97.04 354	91.68 153	98.48 333	95.80 213	87.66 409	96.79 347

VPA-MVSNet		95.75 226	95.11 244	97.69 200	97.24 331	97.27 104	98.94 103	99.23 27	95.13 195	95.51 269	97.32 325	85.73 316	98.91 290	97.33 146	89.55 385	96.89 336

HQP-MVS		95.72 227	95.40 223	96.69 276	97.20 335	94.25 281	98.05 307	98.46 205	96.43 116	94.45 295	97.73 286	86.75 295	98.96 281	95.30 231	94.18 309	96.86 342

hse-mvs2		95.71 228	95.30 235	96.93 256	98.50 185	93.53 307	98.36 257	98.10 300	97.48 51	98.67 102	97.99 261	89.76 214	99.02 273	97.95 92	80.91 449	98.22 284

UniMVSNet_NR-MVSNet		95.71 228	95.15 240	97.40 225	96.84 359	96.97 123	98.74 171	99.24 20	95.16 190	93.88 329	97.72 288	91.68 153	98.31 363	95.81 211	87.25 415	96.92 328

PatchmatchNet		95.71 228	95.52 219	96.29 320	97.58 303	90.72 376	96.84 418	97.52 354	94.06 256	97.08 208	96.96 364	89.24 234	98.90 293	92.03 340	98.37 201	99.26 167
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
OPM-MVS		95.69 231	95.33 232	96.76 269	96.16 395	94.63 259	98.43 251	98.39 230	96.64 108	95.02 279	98.78 177	85.15 329	99.05 266	95.21 238	94.20 308	96.60 370
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMM	93.85 9	95.69 231	95.38 227	96.61 286	97.61 300	93.84 294	98.91 113	98.44 209	95.25 186	94.28 309	98.47 214	86.04 313	99.12 254	95.50 225	93.95 318	96.87 340
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpmrst		95.63 233	95.69 215	95.44 357	97.54 308	88.54 424	96.97 404	97.56 346	93.50 298	97.52 192	96.93 368	89.49 221	99.16 242	95.25 235	96.42 273	98.64 258

FE-MVS		95.62 234	94.90 254	97.78 189	98.37 204	94.92 246	97.17 394	97.38 370	90.95 389	97.73 172	97.70 289	85.32 327	99.63 157	91.18 357	98.33 204	98.79 234

LPG-MVS_test		95.62 234	95.34 229	96.47 304	97.46 315	93.54 305	98.99 90	98.54 184	94.67 229	94.36 303	98.77 180	85.39 322	99.11 256	95.71 217	94.15 311	96.76 350

CLD-MVS		95.62 234	95.34 229	96.46 307	97.52 311	93.75 298	97.27 383	98.46 205	95.53 167	94.42 300	98.00 260	86.21 308	98.97 277	96.25 196	94.37 303	96.66 365
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		95.61 237	94.89 255	97.76 193	98.15 244	95.15 232	96.77 420	94.41 450	92.95 324	97.18 204	97.43 316	84.78 336	99.45 199	94.63 256	97.73 229	98.68 252

MonoMVSNet		95.51 238	95.45 222	95.68 346	95.54 416	90.87 371	98.92 111	97.37 371	95.79 151	95.53 268	97.38 321	89.58 220	97.68 410	96.40 190	92.59 345	98.49 271

thres600view7		95.49 239	94.77 258	97.67 204	98.98 136	95.02 237	98.85 137	96.90 407	95.38 177	96.63 233	96.90 370	84.29 346	99.59 164	88.65 403	96.33 275	98.40 275

test_vis1_n		95.47 240	95.13 241	96.49 301	97.77 286	90.41 386	99.27 30	98.11 297	96.58 110	99.66 27	99.18 96	67.00 452	99.62 161	99.21 28	99.40 130	99.44 123

SCA		95.46 241	95.13 241	96.46 307	97.67 295	91.29 364	97.33 378	97.60 342	94.68 228	96.92 218	97.10 339	83.97 356	98.89 294	92.59 324	98.32 207	99.20 176

IterMVS-LS		95.46 241	95.21 238	96.22 322	98.12 246	93.72 301	98.32 264	98.13 293	93.71 283	94.26 310	97.31 326	92.24 134	98.10 379	94.63 256	90.12 376	96.84 343
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing3-2		95.45 243	95.34 229	95.77 344	98.69 167	88.75 420	98.87 128	97.21 384	96.13 133	97.22 202	97.68 294	77.95 408	99.65 151	97.58 121	96.77 262	98.91 225

jajsoiax		95.45 243	95.03 247	96.73 270	95.42 424	94.63 259	99.14 58	98.52 189	95.74 153	93.22 357	98.36 225	83.87 359	98.65 319	96.95 159	94.04 314	96.91 333

CVMVSNet		95.43 245	96.04 194	93.57 410	97.93 276	83.62 449	98.12 297	98.59 170	95.68 157	96.56 237	99.02 131	87.51 281	97.51 419	93.56 298	97.44 242	99.60 91

anonymousdsp		95.42 246	94.91 253	96.94 255	95.10 428	95.90 186	99.14 58	98.41 223	93.75 277	93.16 360	97.46 312	87.50 283	98.41 349	95.63 221	94.03 315	96.50 389

DU-MVS		95.42 246	94.76 259	97.40 225	96.53 376	96.97 123	98.66 199	98.99 55	95.43 173	93.88 329	97.69 291	88.57 254	98.31 363	95.81 211	87.25 415	96.92 328

mvs_tets		95.41 248	95.00 248	96.65 278	95.58 415	94.42 270	99.00 87	98.55 182	95.73 155	93.21 358	98.38 223	83.45 365	98.63 320	97.09 153	94.00 316	96.91 333

thres100view900		95.38 249	94.70 263	97.41 223	98.98 136	94.92 246	98.87 128	96.90 407	95.38 177	96.61 235	96.88 371	84.29 346	99.56 170	88.11 406	96.29 279	97.76 296

thres400		95.38 249	94.62 267	97.65 208	98.94 141	94.98 242	98.68 192	96.93 405	95.33 180	96.55 239	96.53 390	84.23 350	99.56 170	88.11 406	96.29 279	98.40 275

BH-w/o		95.38 249	95.08 245	96.26 321	98.34 211	91.79 353	97.70 350	97.43 366	92.87 327	94.24 312	97.22 333	88.66 252	98.84 300	91.55 353	97.70 230	98.16 287

VDDNet		95.36 252	94.53 272	97.86 182	98.10 248	95.13 233	98.85 137	97.75 330	90.46 396	98.36 124	99.39 47	73.27 440	99.64 154	97.98 91	96.58 267	98.81 233

TAPA-MVS	93.98 7	95.35 253	94.56 271	97.74 195	99.13 117	94.83 251	98.33 260	98.64 157	86.62 432	96.29 250	98.61 198	94.00 104	99.29 220	80.00 449	99.41 127	99.09 200
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ACMP	93.49 10	95.34 254	94.98 250	96.43 309	97.67 295	93.48 309	98.73 177	98.44 209	94.94 214	92.53 380	98.53 208	84.50 345	99.14 249	95.48 226	94.00 316	96.66 365
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
COLMAP_ROB	93.27 12	95.33 255	94.87 256	96.71 273	99.29 86	93.24 323	98.58 215	98.11 297	89.92 406	93.57 342	99.10 113	86.37 304	99.79 119	90.78 368	98.10 214	97.09 317
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
UBG		95.32 256	94.72 262	97.13 239	98.05 256	93.26 320	97.87 333	97.20 385	94.96 210	96.18 254	95.66 423	80.97 380	99.35 209	94.47 265	97.08 249	98.78 238

tfpn200view9		95.32 256	94.62 267	97.43 221	98.94 141	94.98 242	98.68 192	96.93 405	95.33 180	96.55 239	96.53 390	84.23 350	99.56 170	88.11 406	96.29 279	97.76 296

Anonymous202405211		95.28 258	94.49 274	97.67 204	99.00 132	93.75 298	98.70 186	97.04 396	90.66 392	96.49 243	98.80 171	78.13 404	99.83 88	96.21 197	95.36 301	99.44 123

thres200		95.25 259	94.57 270	97.28 229	98.81 155	94.92 246	98.20 280	97.11 389	95.24 188	96.54 241	96.22 401	84.58 343	99.53 180	87.93 411	96.50 271	97.39 310

AllTest		95.24 260	94.65 266	96.99 250	99.25 94	93.21 324	98.59 212	98.18 281	91.36 374	93.52 344	98.77 180	84.67 340	99.72 134	89.70 386	97.87 222	98.02 291

LCM-MVSNet-Re		95.22 261	95.32 233	94.91 374	98.18 239	87.85 435	98.75 167	95.66 437	95.11 197	88.96 422	96.85 374	90.26 205	97.65 411	95.65 220	98.44 191	99.22 173

EPNet_dtu		95.21 262	94.95 252	95.99 330	96.17 393	90.45 384	98.16 290	97.27 379	96.77 98	93.14 363	98.33 231	90.34 201	98.42 342	85.57 424	98.81 168	99.09 200
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
XXY-MVS		95.20 263	94.45 280	97.46 218	96.75 366	96.56 147	98.86 132	98.65 156	93.30 308	93.27 356	98.27 238	84.85 334	98.87 297	94.82 247	91.26 362	96.96 323

D2MVS		95.18 264	95.08 245	95.48 354	97.10 344	92.07 349	98.30 268	99.13 43	94.02 259	92.90 368	96.73 380	89.48 222	98.73 312	94.48 264	93.60 327	95.65 419

WR-MVS		95.15 265	94.46 277	97.22 231	96.67 371	96.45 151	98.21 278	98.81 105	94.15 253	93.16 360	97.69 291	87.51 281	98.30 365	95.29 233	88.62 400	96.90 335

TranMVSNet+NR-MVSNet		95.14 266	94.48 275	97.11 243	96.45 382	96.36 158	99.03 80	99.03 50	95.04 202	93.58 341	97.93 267	88.27 262	98.03 387	94.13 278	86.90 420	96.95 325

myMVS_eth3d28		95.12 267	94.62 267	96.64 282	98.17 242	92.17 343	98.02 311	97.32 373	95.41 175	96.22 251	96.05 407	78.01 406	99.13 251	95.22 237	97.16 247	98.60 261

baseline2		95.11 268	94.52 273	96.87 261	96.65 372	93.56 304	98.27 273	94.10 456	93.45 301	92.02 394	97.43 316	87.45 286	99.19 239	93.88 287	97.41 244	97.87 294

miper_enhance_ethall		95.10 269	94.75 260	96.12 326	97.53 310	93.73 300	96.61 426	98.08 305	92.20 354	93.89 328	96.65 386	92.44 125	98.30 365	94.21 274	91.16 363	96.34 398

Anonymous20240529		95.10 269	94.22 290	97.75 194	99.01 130	94.26 280	98.87 128	98.83 96	85.79 440	96.64 232	98.97 139	78.73 397	99.85 82	96.27 193	94.89 302	99.12 192

test-LLR		95.10 269	94.87 256	95.80 341	96.77 363	89.70 400	96.91 409	95.21 442	95.11 197	94.83 284	95.72 420	87.71 277	98.97 277	93.06 309	98.50 187	98.72 245

WR-MVS_H		95.05 272	94.46 277	96.81 265	96.86 358	95.82 197	99.24 34	99.24 20	93.87 271	92.53 380	96.84 375	90.37 200	98.24 371	93.24 304	87.93 406	96.38 397

miper_ehance_all_eth		95.01 273	94.69 264	95.97 332	97.70 293	93.31 318	97.02 402	98.07 307	92.23 351	93.51 346	96.96 364	91.85 148	98.15 375	93.68 292	91.16 363	96.44 395

testing11		95.00 274	94.28 287	97.16 237	97.96 273	93.36 317	98.09 303	97.06 395	94.94 214	95.33 274	96.15 403	76.89 421	99.40 204	95.77 215	96.30 278	98.72 245

ADS-MVSNet		95.00 274	94.45 280	96.63 283	98.00 263	91.91 352	96.04 433	97.74 331	90.15 402	96.47 244	96.64 387	87.89 273	98.96 281	90.08 377	97.06 250	99.02 213

VPNet		94.99 276	94.19 292	97.40 225	97.16 340	96.57 146	98.71 182	98.97 56	95.67 158	94.84 282	98.24 242	80.36 387	98.67 318	96.46 187	87.32 414	96.96 323

EPMVS		94.99 276	94.48 275	96.52 299	97.22 333	91.75 355	97.23 384	91.66 466	94.11 254	97.28 198	96.81 377	85.70 317	98.84 300	93.04 311	97.28 245	98.97 218

testing91		94.98 278	94.25 289	97.20 232	97.94 274	93.41 312	98.00 314	97.58 343	94.99 207	95.45 270	96.04 408	77.20 416	99.42 202	94.97 243	96.02 292	98.78 238

NR-MVSNet		94.98 278	94.16 295	97.44 220	96.53 376	97.22 112	98.74 171	98.95 60	94.96 210	89.25 421	97.69 291	89.32 231	98.18 373	94.59 261	87.40 412	96.92 328

FMVSNet3		94.97 280	94.26 288	97.11 243	98.18 239	96.62 138	98.56 226	98.26 269	93.67 290	94.09 319	97.10 339	84.25 348	98.01 389	92.08 336	92.14 348	96.70 359

CostFormer		94.95 281	94.73 261	95.60 351	97.28 329	89.06 413	97.53 362	96.89 409	89.66 411	96.82 223	96.72 381	86.05 311	98.95 286	95.53 224	96.13 290	98.79 234

PAPM		94.95 281	94.00 308	97.78 189	97.04 346	95.65 204	96.03 435	98.25 270	91.23 383	94.19 315	97.80 283	91.27 172	98.86 299	82.61 441	97.61 232	98.84 230

CP-MVSNet		94.94 283	94.30 286	96.83 263	96.72 368	95.56 207	99.11 64	98.95 60	93.89 269	92.42 385	97.90 270	87.19 288	98.12 378	94.32 270	88.21 403	96.82 346

TR-MVS		94.94 283	94.20 291	97.17 236	97.75 287	94.14 286	97.59 359	97.02 400	92.28 350	95.75 266	97.64 299	83.88 358	98.96 281	89.77 383	96.15 289	98.40 275

RPSCF		94.87 285	95.40 223	93.26 416	98.89 144	82.06 455	98.33 260	98.06 312	90.30 401	96.56 237	99.26 78	87.09 289	99.49 188	93.82 289	96.32 276	98.24 282

testing99		94.83 286	94.08 300	97.07 246	97.94 274	93.13 326	98.10 302	97.17 387	94.86 216	95.34 271	96.00 412	76.31 424	99.40 204	95.08 240	95.90 293	98.68 252

GA-MVS		94.81 287	94.03 304	97.14 238	97.15 341	93.86 293	96.76 421	97.58 343	94.00 263	94.76 288	97.04 354	80.91 381	98.48 333	91.79 346	96.25 285	99.09 200

c3_l		94.79 288	94.43 282	95.89 337	97.75 287	93.12 328	97.16 396	98.03 314	92.23 351	93.46 350	97.05 353	91.39 166	98.01 389	93.58 297	89.21 392	96.53 381

V42		94.78 289	94.14 297	96.70 275	96.33 387	95.22 228	98.97 94	98.09 304	92.32 348	94.31 306	97.06 350	88.39 260	98.55 328	92.90 316	88.87 398	96.34 398

reproduce_monomvs		94.77 290	94.67 265	95.08 369	98.40 199	89.48 406	98.80 154	98.64 157	97.57 45	93.21 358	97.65 296	80.57 386	98.83 303	97.72 108	89.47 388	96.93 327

CR-MVSNet		94.76 291	94.15 296	96.59 289	97.00 347	93.43 310	94.96 448	97.56 346	92.46 339	96.93 216	96.24 397	88.15 265	97.88 402	87.38 413	96.65 265	98.46 273

v2v482		94.69 292	94.03 304	96.65 278	96.17 393	94.79 254	98.67 197	98.08 305	92.72 331	94.00 324	97.16 336	87.69 280	98.45 338	92.91 315	88.87 398	96.72 355

pmmvs4		94.69 292	93.99 310	96.81 265	95.74 410	95.94 180	97.40 369	97.67 335	90.42 398	93.37 353	97.59 303	89.08 239	98.20 372	92.97 313	91.67 356	96.30 401

cl22		94.68 294	94.19 292	96.13 325	98.11 247	93.60 303	96.94 406	98.31 251	92.43 343	93.32 355	96.87 373	86.51 298	98.28 369	94.10 281	91.16 363	96.51 387

eth_miper_zixun_eth		94.68 294	94.41 283	95.47 355	97.64 298	91.71 357	96.73 423	98.07 307	92.71 332	93.64 338	97.21 334	90.54 198	98.17 374	93.38 300	89.76 380	96.54 379

PCF-MVS	93.45 11	94.68 294	93.43 346	98.42 127	98.62 177	96.77 133	95.48 445	98.20 276	84.63 445	93.34 354	98.32 232	88.55 257	99.81 100	84.80 433	98.96 156	98.68 252
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS		94.67 297	93.54 341	98.08 163	96.88 357	96.56 147	98.19 283	98.50 197	78.05 457	92.69 375	98.02 257	91.07 185	99.63 157	90.09 376	98.36 203	98.04 290

PS-CasMVS		94.67 297	93.99 310	96.71 273	96.68 370	95.26 225	99.13 61	99.03 50	93.68 288	92.33 386	97.95 265	85.35 324	98.10 379	93.59 296	88.16 405	96.79 347

cascas		94.63 299	93.86 320	96.93 256	96.91 355	94.27 279	96.00 436	98.51 192	85.55 441	94.54 291	96.23 399	84.20 352	98.87 297	95.80 213	96.98 255	97.66 302

tpmvs		94.60 300	94.36 285	95.33 361	97.46 315	88.60 423	96.88 415	97.68 332	91.29 380	93.80 334	96.42 394	88.58 253	99.24 231	91.06 363	96.04 291	98.17 286

LTVRE_ROB	92.95 15	94.60 300	93.90 316	96.68 277	97.41 323	94.42 270	98.52 229	98.59 170	91.69 366	91.21 401	98.35 226	84.87 333	99.04 269	91.06 363	93.44 331	96.60 370
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		94.59 302	93.92 313	96.60 288	96.21 389	94.78 255	98.59 212	98.14 292	91.86 362	94.21 314	97.02 357	87.97 271	98.41 349	91.72 348	89.57 383	96.61 369

ADS-MVSNet2		94.58 303	94.40 284	95.11 367	98.00 263	88.74 421	96.04 433	97.30 375	90.15 402	96.47 244	96.64 387	87.89 273	97.56 417	90.08 377	97.06 250	99.02 213

WBMVS		94.56 304	94.04 302	96.10 327	98.03 260	93.08 330	97.82 341	98.18 281	94.02 259	93.77 336	96.82 376	81.28 375	98.34 358	95.47 227	91.00 366	96.88 337

ACMH	92.88 16	94.55 305	93.95 312	96.34 316	97.63 299	93.26 320	98.81 153	98.49 202	93.43 302	89.74 415	98.53 208	81.91 370	99.08 263	93.69 291	93.30 336	96.70 359
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		94.54 306	93.85 321	96.63 283	97.98 271	93.06 331	98.77 166	97.84 326	93.67 290	93.80 334	98.04 256	76.88 422	98.96 281	94.79 249	92.86 341	97.86 295

XVG-ACMP-BASELINE		94.54 306	94.14 297	95.75 345	96.55 375	91.65 358	98.11 300	98.44 209	94.96 210	94.22 313	97.90 270	79.18 396	99.11 256	94.05 283	93.85 320	96.48 392

AUN-MVS		94.53 308	93.73 331	96.92 259	98.50 185	93.52 308	98.34 259	98.10 300	93.83 274	95.94 264	97.98 263	85.59 320	99.03 270	94.35 268	80.94 448	98.22 284

DIV-MVS_self_test		94.52 309	94.03 304	95.99 330	97.57 307	93.38 315	97.05 400	97.94 320	91.74 363	92.81 370	97.10 339	89.12 237	98.07 385	92.60 322	90.30 373	96.53 381

cl____		94.51 310	94.01 307	96.02 329	97.58 303	93.40 314	97.05 400	97.96 319	91.73 365	92.76 372	97.08 345	89.06 240	98.13 377	92.61 321	90.29 374	96.52 384

ETVMVS		94.50 311	93.44 345	97.68 202	98.18 239	95.35 221	98.19 283	97.11 389	93.73 280	96.40 247	95.39 426	74.53 434	98.84 300	91.10 359	96.31 277	98.84 230

GBi-Net		94.49 312	93.80 324	96.56 293	98.21 229	95.00 238	98.82 145	98.18 281	92.46 339	94.09 319	97.07 346	81.16 376	97.95 394	92.08 336	92.14 348	96.72 355

test1		94.49 312	93.80 324	96.56 293	98.21 229	95.00 238	98.82 145	98.18 281	92.46 339	94.09 319	97.07 346	81.16 376	97.95 394	92.08 336	92.14 348	96.72 355

dmvs_re		94.48 314	94.18 294	95.37 359	97.68 294	90.11 392	98.54 228	97.08 391	94.56 235	94.42 300	97.24 331	84.25 348	97.76 408	91.02 366	92.83 342	98.24 282

v8		94.47 315	93.77 327	96.57 292	96.36 385	94.83 251	99.05 73	98.19 278	91.92 359	93.16 360	96.97 362	88.82 251	98.48 333	91.69 349	87.79 407	96.39 396

FMVSNet2		94.47 315	93.61 337	97.04 248	98.21 229	96.43 153	98.79 162	98.27 261	92.46 339	93.50 347	97.09 343	81.16 376	98.00 391	91.09 360	91.93 351	96.70 359

test2506		94.44 317	93.91 315	96.04 328	99.02 128	88.99 416	99.06 71	79.47 478	96.96 90	98.36 124	99.26 78	77.21 415	99.52 183	96.78 178	99.04 150	99.59 93

Patchmatch-test		94.42 318	93.68 335	96.63 283	97.60 301	91.76 354	94.83 452	97.49 358	89.45 415	94.14 317	97.10 339	88.99 242	98.83 303	85.37 427	98.13 213	99.29 157

PEN-MVS		94.42 318	93.73 331	96.49 301	96.28 388	94.84 249	99.17 53	99.00 52	93.51 297	92.23 388	97.83 280	86.10 310	97.90 398	92.55 327	86.92 419	96.74 352

v144192		94.39 320	93.70 333	96.48 303	96.06 399	94.35 274	98.58 215	98.16 289	91.45 371	94.33 305	97.02 357	87.50 283	98.45 338	91.08 362	89.11 393	96.63 367

Baseline_NR-MVSNet		94.35 321	93.81 323	95.96 333	96.20 390	94.05 288	98.61 211	96.67 419	91.44 372	93.85 331	97.60 302	88.57 254	98.14 376	94.39 266	86.93 418	95.68 418

miper_lstm_enhance		94.33 322	94.07 301	95.11 367	97.75 287	90.97 368	97.22 386	98.03 314	91.67 367	92.76 372	96.97 362	90.03 209	97.78 407	92.51 329	89.64 382	96.56 376

v1192		94.32 323	93.58 338	96.53 298	96.10 397	94.45 268	98.50 237	98.17 287	91.54 369	94.19 315	97.06 350	86.95 293	98.43 341	90.14 375	89.57 383	96.70 359

UWE-MVS		94.30 324	93.89 318	95.53 352	97.83 282	88.95 417	97.52 364	93.25 458	94.44 245	96.63 233	97.07 346	78.70 398	99.28 222	91.99 341	97.56 236	98.36 278

ACMH+	92.99 14	94.30 324	93.77 327	95.88 338	97.81 284	92.04 351	98.71 182	98.37 236	93.99 264	90.60 408	98.47 214	80.86 383	99.05 266	92.75 320	92.40 347	96.55 378

v148		94.29 326	93.76 329	95.91 335	96.10 397	92.93 332	98.58 215	97.97 317	92.59 337	93.47 349	96.95 366	88.53 258	98.32 361	92.56 326	87.06 417	96.49 390

v10		94.29 326	93.55 340	96.51 300	96.39 384	94.80 253	98.99 90	98.19 278	91.35 376	93.02 366	96.99 360	88.09 267	98.41 349	90.50 372	88.41 402	96.33 400

SD_0403		94.28 328	94.46 277	93.73 407	98.02 261	85.32 444	98.31 265	98.40 225	94.75 224	93.59 339	98.16 247	89.01 241	96.54 438	82.32 442	97.58 235	99.34 142

MVP-Stereo		94.28 328	93.92 313	95.35 360	94.95 430	92.60 339	97.97 317	97.65 336	91.61 368	90.68 407	97.09 343	86.32 307	98.42 342	89.70 386	99.34 136	95.02 432
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UniMVSNet_ETH3D		94.24 330	93.33 348	96.97 253	97.19 338	93.38 315	98.74 171	98.57 177	91.21 385	93.81 333	98.58 203	72.85 441	98.77 310	95.05 241	93.93 319	98.77 241

OurMVSNet-221017-0		94.21 331	94.00 308	94.85 379	95.60 414	89.22 411	98.89 118	97.43 366	95.29 183	92.18 390	98.52 211	82.86 366	98.59 326	93.46 299	91.76 354	96.74 352

v1921920		94.20 332	93.47 344	96.40 313	95.98 403	94.08 287	98.52 229	98.15 290	91.33 377	94.25 311	97.20 335	86.41 303	98.42 342	90.04 380	89.39 390	96.69 364

WB-MVSnew		94.19 333	94.04 302	94.66 387	96.82 361	92.14 344	97.86 335	95.96 433	93.50 298	95.64 267	96.77 379	88.06 269	97.99 392	84.87 430	96.86 256	93.85 450

v7n		94.19 333	93.43 346	96.47 304	95.90 406	94.38 273	99.26 31	98.34 244	91.99 357	92.76 372	97.13 338	88.31 261	98.52 331	89.48 391	87.70 408	96.52 384

tpm2		94.19 333	93.76 329	95.46 356	97.23 332	89.04 414	97.31 380	96.85 413	87.08 431	96.21 253	96.79 378	83.75 362	98.74 311	92.43 332	96.23 287	98.59 264

TESTMET0.1,1		94.18 336	93.69 334	95.63 349	96.92 353	89.12 412	96.91 409	94.78 447	93.17 313	94.88 281	96.45 393	78.52 399	98.92 288	93.09 308	98.50 187	98.85 228

dp		94.15 337	93.90 316	94.90 375	97.31 328	86.82 440	96.97 404	97.19 386	91.22 384	96.02 259	96.61 389	85.51 321	99.02 273	90.00 381	94.30 304	98.85 228

ET-MVSNet_ETH3D		94.13 338	92.98 356	97.58 213	98.22 228	96.20 164	97.31 380	95.37 441	94.53 237	79.56 459	97.63 301	86.51 298	97.53 418	96.91 161	90.74 368	99.02 213

tpm		94.13 338	93.80 324	95.12 366	96.50 378	87.91 434	97.44 366	95.89 436	92.62 335	96.37 249	96.30 396	84.13 353	98.30 365	93.24 304	91.66 357	99.14 190

testing222		94.12 340	93.03 355	97.37 228	98.02 261	94.66 256	97.94 321	96.65 421	94.63 231	95.78 265	95.76 415	71.49 442	98.92 288	91.17 358	95.88 294	98.52 269

IterMVS-SCA-FT		94.11 341	93.87 319	94.85 379	97.98 271	90.56 383	97.18 391	98.11 297	93.75 277	92.58 378	97.48 311	83.97 356	97.41 421	92.48 331	91.30 360	96.58 372

Anonymous20231211		94.10 342	93.26 351	96.61 286	99.11 120	94.28 278	99.01 85	98.88 77	86.43 434	92.81 370	97.57 305	81.66 372	98.68 317	94.83 246	89.02 396	96.88 337

IterMVS		94.09 343	93.85 321	94.80 383	97.99 265	90.35 388	97.18 391	98.12 294	93.68 288	92.46 384	97.34 322	84.05 354	97.41 421	92.51 329	91.33 359	96.62 368
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test-mter		94.08 344	93.51 342	95.80 341	96.77 363	89.70 400	96.91 409	95.21 442	92.89 326	94.83 284	95.72 420	77.69 410	98.97 277	93.06 309	98.50 187	98.72 245

test0.0.03 1		94.08 344	93.51 342	95.80 341	95.53 418	92.89 333	97.38 371	95.97 432	95.11 197	92.51 382	96.66 384	87.71 277	96.94 428	87.03 415	93.67 323	97.57 306

v1240		94.06 346	93.29 350	96.34 316	96.03 401	93.90 292	98.44 249	98.17 287	91.18 386	94.13 318	97.01 359	86.05 311	98.42 342	89.13 397	89.50 387	96.70 359

X-MVStestdata		94.06 346	92.30 372	99.34 30	99.70 26	98.35 48	99.29 26	98.88 77	97.40 56	98.46 116	43.50 473	95.90 47	99.89 66	97.85 100	99.74 57	99.78 32

DTE-MVSNet		93.98 348	93.26 351	96.14 324	96.06 399	94.39 272	99.20 46	98.86 90	93.06 319	91.78 395	97.81 282	85.87 315	97.58 416	90.53 371	86.17 424	96.46 394

pm-mvs1		93.94 349	93.06 354	96.59 289	96.49 379	95.16 230	98.95 100	98.03 314	92.32 348	91.08 403	97.84 277	84.54 344	98.41 349	92.16 334	86.13 427	96.19 406

MS-PatchMatch		93.84 350	93.63 336	94.46 397	96.18 392	89.45 407	97.76 345	98.27 261	92.23 351	92.13 391	97.49 310	79.50 393	98.69 314	89.75 384	99.38 132	95.25 424

tfpnnormal		93.66 351	92.70 362	96.55 297	96.94 352	95.94 180	98.97 94	99.19 35	91.04 387	91.38 400	97.34 322	84.94 332	98.61 322	85.45 426	89.02 396	95.11 428

EU-MVSNet		93.66 351	94.14 297	92.25 427	95.96 405	83.38 451	98.52 229	98.12 294	94.69 227	92.61 377	98.13 250	87.36 287	96.39 442	91.82 345	90.00 378	96.98 322

our_test_3		93.65 353	93.30 349	94.69 385	95.45 422	89.68 402	96.91 409	97.65 336	91.97 358	91.66 398	96.88 371	89.67 218	97.93 397	88.02 409	91.49 358	96.48 392

pmmvs5		93.65 353	92.97 357	95.68 346	95.49 419	92.37 340	98.20 280	97.28 378	89.66 411	92.58 378	97.26 328	82.14 369	98.09 383	93.18 307	90.95 367	96.58 372

SSC-MVS3.2		93.59 355	93.13 353	94.97 372	96.81 362	89.71 399	97.95 318	98.49 202	94.59 234	93.50 347	96.91 369	77.74 409	98.37 356	91.69 349	90.47 371	96.83 345

test_fmvs2		93.43 356	93.58 338	92.95 421	96.97 350	83.91 447	99.19 48	97.24 381	95.74 153	95.20 276	98.27 238	69.65 444	98.72 313	96.26 194	93.73 322	96.24 403

tpm cat1		93.36 357	92.80 359	95.07 370	97.58 303	87.97 433	96.76 421	97.86 325	82.17 452	93.53 343	96.04 408	86.13 309	99.13 251	89.24 395	95.87 295	98.10 289

JIA-IIPM		93.35 358	92.49 368	95.92 334	96.48 380	90.65 378	95.01 447	96.96 403	85.93 438	96.08 257	87.33 463	87.70 279	98.78 309	91.35 355	95.58 299	98.34 279

SixPastTwentyTwo		93.34 359	92.86 358	94.75 384	95.67 412	89.41 409	98.75 167	96.67 419	93.89 269	90.15 413	98.25 241	80.87 382	98.27 370	90.90 367	90.64 369	96.57 374

USDC		93.33 360	92.71 361	95.21 363	96.83 360	90.83 374	96.91 409	97.50 356	93.84 272	90.72 406	98.14 249	77.69 410	98.82 305	89.51 390	93.21 338	95.97 412

IB-MVS	91.98 17	93.27 361	91.97 376	97.19 234	97.47 314	93.41 312	97.09 399	95.99 431	93.32 306	92.47 383	95.73 418	78.06 405	99.53 180	94.59 261	82.98 438	98.62 259
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		93.26 362	92.21 373	96.41 311	97.73 291	93.13 326	95.65 442	97.03 397	91.27 382	94.04 322	96.06 406	75.33 429	97.19 424	86.56 417	96.23 287	98.92 224

ppachtmachnet_test		93.22 363	92.63 363	94.97 372	95.45 422	90.84 373	96.88 415	97.88 324	90.60 393	92.08 392	97.26 328	88.08 268	97.86 403	85.12 429	90.33 372	96.22 404

Patchmtry		93.22 363	92.35 371	95.84 340	96.77 363	93.09 329	94.66 455	97.56 346	87.37 430	92.90 368	96.24 397	88.15 265	97.90 398	87.37 414	90.10 377	96.53 381

testing3		93.19 365	92.48 369	95.30 362	98.07 251	92.27 341	98.64 203	97.17 387	93.94 268	93.98 325	97.04 354	67.97 449	96.01 446	88.40 404	97.14 248	97.63 303

FMVSNet1		93.19 365	92.07 374	96.56 293	97.54 308	95.00 238	98.82 145	98.18 281	90.38 399	92.27 387	97.07 346	73.68 439	97.95 394	89.36 393	91.30 360	96.72 355

LF4IMVS		93.14 367	92.79 360	94.20 401	95.88 407	88.67 422	97.66 353	97.07 393	93.81 275	91.71 396	97.65 296	77.96 407	98.81 306	91.47 354	91.92 353	95.12 427

mmtdpeth		93.12 368	92.61 364	94.63 389	97.60 301	89.68 402	99.21 43	97.32 373	94.02 259	97.72 173	94.42 437	77.01 420	99.44 200	99.05 31	77.18 460	94.78 437

testgi		93.06 369	92.45 370	94.88 377	96.43 383	89.90 394	98.75 167	97.54 352	95.60 161	91.63 399	97.91 269	74.46 436	97.02 426	86.10 420	93.67 323	97.72 300

PatchT		93.06 369	91.97 376	96.35 315	96.69 369	92.67 338	94.48 458	97.08 391	86.62 432	97.08 208	92.23 457	87.94 272	97.90 398	78.89 453	96.69 263	98.49 271

RPMNet		92.81 371	91.34 382	97.24 230	97.00 347	93.43 310	94.96 448	98.80 112	82.27 451	96.93 216	92.12 458	86.98 292	99.82 95	76.32 459	96.65 265	98.46 273

UWE-MVS-28		92.79 372	92.51 367	93.62 409	96.46 381	86.28 441	97.93 322	92.71 463	94.17 252	94.78 287	97.16 336	81.05 379	96.43 441	81.45 445	96.86 256	98.14 288

myMVS_eth3d		92.73 373	92.01 375	94.89 376	97.39 324	90.94 369	97.91 325	97.46 360	93.16 314	93.42 351	95.37 427	68.09 448	96.12 444	88.34 405	96.99 252	97.60 304

TransMVSNet (Re)		92.67 374	91.51 381	96.15 323	96.58 374	94.65 257	98.90 114	96.73 415	90.86 390	89.46 420	97.86 274	85.62 319	98.09 383	86.45 418	81.12 446	95.71 417

ttmdpeth		92.61 375	91.96 378	94.55 391	94.10 440	90.60 382	98.52 229	97.29 376	92.67 333	90.18 411	97.92 268	79.75 392	97.79 405	91.09 360	86.15 426	95.26 423

Syy-MVS		92.55 376	92.61 364	92.38 424	97.39 324	83.41 450	97.91 325	97.46 360	93.16 314	93.42 351	95.37 427	84.75 337	96.12 444	77.00 458	96.99 252	97.60 304

K. test v3		92.55 376	91.91 379	94.48 395	95.64 413	89.24 410	99.07 70	94.88 446	94.04 257	86.78 437	97.59 303	77.64 413	97.64 412	92.08 336	89.43 389	96.57 374

DSMNet-mixed		92.52 378	92.58 366	92.33 425	94.15 439	82.65 453	98.30 268	94.26 453	89.08 420	92.65 376	95.73 418	85.01 331	95.76 448	86.24 419	97.76 227	98.59 264

TinyColmap		92.31 379	91.53 380	94.65 388	96.92 353	89.75 397	96.92 407	96.68 418	90.45 397	89.62 417	97.85 276	76.06 427	98.81 306	86.74 416	92.51 346	95.41 421

gg-mvs-nofinetune		92.21 380	90.58 388	97.13 239	96.75 366	95.09 234	95.85 437	89.40 471	85.43 442	94.50 293	81.98 466	80.80 384	98.40 355	92.16 334	98.33 204	97.88 293

FMVSNet5		91.81 381	90.92 384	94.49 394	97.21 334	92.09 348	98.00 314	97.55 351	89.31 418	90.86 405	95.61 424	74.48 435	95.32 452	85.57 424	89.70 381	96.07 410

pmmvs6		91.77 382	90.63 387	95.17 365	94.69 436	91.24 365	98.67 197	97.92 322	86.14 436	89.62 417	97.56 308	75.79 428	98.34 358	90.75 369	84.56 431	95.94 413

Anonymous20231206		91.66 383	91.10 383	93.33 414	94.02 444	87.35 437	98.58 215	97.26 380	90.48 395	90.16 412	96.31 395	83.83 360	96.53 439	79.36 451	89.90 379	96.12 408

Patchmatch-RL test		91.49 384	90.85 385	93.41 412	91.37 455	84.40 445	92.81 462	95.93 435	91.87 361	87.25 433	94.87 433	88.99 242	96.53 439	92.54 328	82.00 440	99.30 154

test_0402		91.32 385	90.27 391	94.48 395	96.60 373	91.12 366	98.50 237	97.22 382	86.10 437	88.30 429	96.98 361	77.65 412	97.99 392	78.13 455	92.94 340	94.34 438

test_vis1_rt		91.29 386	90.65 386	93.19 418	97.45 318	86.25 442	98.57 223	90.90 469	93.30 308	86.94 436	93.59 446	62.07 460	99.11 256	97.48 135	95.58 299	94.22 441

PVSNet_0	88.72 19	91.28 387	90.03 394	95.00 371	97.99 265	87.29 438	94.84 451	98.50 197	92.06 356	89.86 414	95.19 429	79.81 391	99.39 207	92.27 333	69.79 466	98.33 280

mvs5depth		91.23 388	90.17 392	94.41 399	92.09 452	89.79 396	95.26 446	96.50 423	90.73 391	91.69 397	97.06 350	76.12 426	98.62 321	88.02 409	84.11 434	94.82 434

Anonymous20240521		91.18 389	90.44 389	93.42 411	93.70 445	88.47 426	98.94 103	97.56 346	88.46 424	89.56 419	95.08 432	77.15 418	96.97 427	83.92 436	89.55 385	94.82 434

EG-PatchMatch MVS		91.13 390	90.12 393	94.17 403	94.73 435	89.00 415	98.13 296	97.81 327	89.22 419	85.32 447	96.46 392	67.71 450	98.42 342	87.89 412	93.82 321	95.08 429

TDRefinement		91.06 391	89.68 396	95.21 363	85.35 471	91.49 361	98.51 236	97.07 393	91.47 370	88.83 426	97.84 277	77.31 414	99.09 261	92.79 319	77.98 458	95.04 431

sc_t1		91.01 392	89.39 398	95.85 339	95.99 402	90.39 387	98.43 251	97.64 338	78.79 455	92.20 389	97.94 266	66.00 454	98.60 325	91.59 352	85.94 428	98.57 267

UnsupCasMVSNet_eth		90.99 393	89.92 395	94.19 402	94.08 441	89.83 395	97.13 398	98.67 149	93.69 286	85.83 443	96.19 402	75.15 430	96.74 432	89.14 396	79.41 453	96.00 411

test20.03		90.89 394	90.38 390	92.43 423	93.48 446	88.14 432	98.33 260	97.56 346	93.40 303	87.96 430	96.71 382	80.69 385	94.13 458	79.15 452	86.17 424	95.01 433

MDA-MVSNet_test_wron		90.71 395	89.38 400	94.68 386	94.83 432	90.78 375	97.19 390	97.46 360	87.60 428	72.41 466	95.72 420	86.51 298	96.71 435	85.92 422	86.80 421	96.56 376

YYNet1		90.70 396	89.39 398	94.62 390	94.79 434	90.65 378	97.20 388	97.46 360	87.54 429	72.54 465	95.74 416	86.51 298	96.66 436	86.00 421	86.76 422	96.54 379

KD-MVS_self_test		90.38 397	89.38 400	93.40 413	92.85 449	88.94 418	97.95 318	97.94 320	90.35 400	90.25 410	93.96 443	79.82 390	95.94 447	84.62 435	76.69 461	95.33 422

pmmvs-eth3d		90.36 398	89.05 403	94.32 400	91.10 457	92.12 345	97.63 358	96.95 404	88.86 422	84.91 448	93.13 451	78.32 401	96.74 432	88.70 401	81.81 442	94.09 444

tt0320		90.26 399	88.73 406	94.86 378	96.12 396	90.62 380	98.17 289	97.63 339	77.46 458	89.68 416	96.04 408	69.19 446	97.79 405	88.98 398	85.29 430	96.16 407

CL-MVSNet_self_test		90.11 400	89.14 402	93.02 419	91.86 454	88.23 431	96.51 429	98.07 307	90.49 394	90.49 409	94.41 438	84.75 337	95.34 451	80.79 447	74.95 463	95.50 420

new_pmnet		90.06 401	89.00 404	93.22 417	94.18 438	88.32 429	96.42 431	96.89 409	86.19 435	85.67 444	93.62 445	77.18 417	97.10 425	81.61 444	89.29 391	94.23 440

MDA-MVSNet-bldmvs		89.97 402	88.35 408	94.83 382	95.21 426	91.34 362	97.64 355	97.51 355	88.36 426	71.17 467	96.13 404	79.22 395	96.63 437	83.65 437	86.27 423	96.52 384

tt0320-xc		89.79 403	88.11 410	94.84 381	96.19 391	90.61 381	98.16 290	97.22 382	77.35 459	88.75 427	96.70 383	65.94 455	97.63 413	89.31 394	83.39 436	96.28 402

CMPMVS	66.06 21	89.70 404	89.67 397	89.78 432	93.19 447	76.56 458	97.00 403	98.35 241	80.97 453	81.57 454	97.75 285	74.75 433	98.61 322	89.85 382	93.63 325	94.17 442
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet1		89.67 405	88.28 409	93.82 406	92.81 450	91.08 367	98.01 312	97.45 364	87.95 427	87.90 431	95.87 414	67.63 451	94.56 457	78.73 454	88.18 404	95.83 415

KD-MVS_2432*1600		89.61 406	87.96 414	94.54 392	94.06 442	91.59 359	95.59 443	97.63 339	89.87 407	88.95 423	94.38 440	78.28 402	96.82 430	84.83 431	68.05 467	95.21 425

miper_refine_blended		89.61 406	87.96 414	94.54 392	94.06 442	91.59 359	95.59 443	97.63 339	89.87 407	88.95 423	94.38 440	78.28 402	96.82 430	84.83 431	68.05 467	95.21 425

MVStest1		89.53 408	87.99 413	94.14 405	94.39 437	90.42 385	98.25 275	96.84 414	82.81 448	81.18 456	97.33 324	77.09 419	96.94 428	85.27 428	78.79 454	95.06 430

MVS-HIRNet		89.46 409	88.40 407	92.64 422	97.58 303	82.15 454	94.16 461	93.05 462	75.73 462	90.90 404	82.52 465	79.42 394	98.33 360	83.53 438	98.68 171	97.43 307

OpenMVS_ROB	86.42 20	89.00 410	87.43 418	93.69 408	93.08 448	89.42 408	97.91 325	96.89 409	78.58 456	85.86 442	94.69 434	69.48 445	98.29 368	77.13 457	93.29 337	93.36 452

mvsany_test3		88.80 411	88.04 411	91.09 431	89.78 461	81.57 456	97.83 340	95.49 440	93.81 275	87.53 432	93.95 444	56.14 463	97.43 420	94.68 254	83.13 437	94.26 439

FE-MVSNET		88.56 412	87.09 419	92.99 420	89.93 460	89.99 393	98.15 293	95.59 438	88.42 425	84.87 449	92.90 452	74.82 432	94.99 455	77.88 456	81.21 445	93.99 447

new-patchmatchnet		88.50 413	87.45 417	91.67 429	90.31 459	85.89 443	97.16 396	97.33 372	89.47 414	83.63 451	92.77 454	76.38 423	95.06 454	82.70 440	77.29 459	94.06 446

APD_test1		88.22 414	88.01 412	88.86 434	95.98 403	74.66 466	97.21 387	96.44 425	83.96 447	86.66 439	97.90 270	60.95 461	97.84 404	82.73 439	90.23 375	94.09 444

PM-MVS		87.77 415	86.55 421	91.40 430	91.03 458	83.36 452	96.92 407	95.18 444	91.28 381	86.48 441	93.42 447	53.27 464	96.74 432	89.43 392	81.97 441	94.11 443

dmvs_testset		87.64 416	88.93 405	83.79 443	95.25 425	63.36 475	97.20 388	91.17 467	93.07 318	85.64 445	95.98 413	85.30 328	91.52 465	69.42 464	87.33 413	96.49 390

test_fmvs3		87.17 417	87.06 420	87.50 436	91.21 456	75.66 461	99.05 73	96.61 422	92.79 330	88.85 425	92.78 453	43.72 467	93.49 459	93.95 284	84.56 431	93.34 453

UnsupCasMVSNet_bld		87.17 417	85.12 424	93.31 415	91.94 453	88.77 419	94.92 450	98.30 258	84.30 446	82.30 452	90.04 460	63.96 458	97.25 423	85.85 423	74.47 465	93.93 449

N_pmnet		87.12 419	87.77 416	85.17 440	95.46 421	61.92 476	97.37 373	70.66 481	85.83 439	88.73 428	96.04 408	85.33 326	97.76 408	80.02 448	90.48 370	95.84 414

pmmvs3		86.67 420	84.86 425	92.11 428	88.16 465	87.19 439	96.63 425	94.75 448	79.88 454	87.22 434	92.75 455	66.56 453	95.20 453	81.24 446	76.56 462	93.96 448

test_f		86.07 421	85.39 422	88.10 435	89.28 463	75.57 462	97.73 348	96.33 427	89.41 417	85.35 446	91.56 459	43.31 469	95.53 449	91.32 356	84.23 433	93.21 454

WB-MVS		84.86 422	85.33 423	83.46 444	89.48 462	69.56 470	98.19 283	96.42 426	89.55 413	81.79 453	94.67 435	84.80 335	90.12 466	52.44 470	80.64 450	90.69 457

SSC-MVS		84.27 423	84.71 426	82.96 448	89.19 464	68.83 471	98.08 304	96.30 428	89.04 421	81.37 455	94.47 436	84.60 342	89.89 467	49.80 472	79.52 452	90.15 458

dongtai		82.47 424	81.88 427	84.22 442	95.19 427	76.03 459	94.59 457	74.14 480	82.63 449	87.19 435	96.09 405	64.10 457	87.85 470	58.91 468	84.11 434	88.78 462

test_vis3_rt		79.22 425	77.40 432	84.67 441	86.44 469	74.85 465	97.66 353	81.43 476	84.98 443	67.12 469	81.91 467	28.09 477	97.60 414	88.96 399	80.04 451	81.55 467

test_method		79.03 426	78.17 428	81.63 449	86.06 470	54.40 481	82.75 470	96.89 409	39.54 473	80.98 457	95.57 425	58.37 462	94.73 456	84.74 434	78.61 455	95.75 416

testf1		79.02 427	77.70 429	82.99 446	88.10 466	66.90 472	94.67 453	93.11 459	71.08 464	74.02 462	93.41 448	34.15 473	93.25 460	72.25 462	78.50 456	88.82 460

APD_test2		79.02 427	77.70 429	82.99 446	88.10 466	66.90 472	94.67 453	93.11 459	71.08 464	74.02 462	93.41 448	34.15 473	93.25 460	72.25 462	78.50 456	88.82 460

LCM-MVSNet		78.70 429	76.24 435	86.08 438	77.26 477	71.99 468	94.34 459	96.72 416	61.62 468	76.53 460	89.33 461	33.91 475	92.78 463	81.85 443	74.60 464	93.46 451

kuosan		78.45 430	77.69 431	80.72 450	92.73 451	75.32 463	94.63 456	74.51 479	75.96 460	80.87 458	93.19 450	63.23 459	79.99 474	42.56 474	81.56 444	86.85 466

Gipuma		78.40 431	76.75 434	83.38 445	95.54 416	80.43 457	79.42 471	97.40 368	64.67 467	73.46 464	80.82 468	45.65 466	93.14 462	66.32 466	87.43 411	76.56 470
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		77.95 432	75.44 436	85.46 439	82.54 472	74.95 464	94.23 460	93.08 461	72.80 463	74.68 461	87.38 462	36.36 472	91.56 464	73.95 460	63.94 469	89.87 459

FPMVS		77.62 433	77.14 433	79.05 452	79.25 475	60.97 477	95.79 438	95.94 434	65.96 466	67.93 468	94.40 439	37.73 471	88.88 469	68.83 465	88.46 401	87.29 463

EGC-MVSNET		75.22 434	69.54 437	92.28 426	94.81 433	89.58 404	97.64 355	96.50 423	1.82 478	5.57 479	95.74 416	68.21 447	96.26 443	73.80 461	91.71 355	90.99 456

ANet_high		69.08 435	65.37 439	80.22 451	65.99 479	71.96 469	90.91 466	90.09 470	82.62 450	49.93 474	78.39 469	29.36 476	81.75 471	62.49 467	38.52 473	86.95 465

tmp_tt		68.90 436	66.97 438	74.68 454	50.78 481	59.95 478	87.13 467	83.47 475	38.80 474	62.21 470	96.23 399	64.70 456	76.91 476	88.91 400	30.49 474	87.19 464

PMVS	61.03 23	65.95 437	63.57 441	73.09 455	57.90 480	51.22 482	85.05 469	93.93 457	54.45 469	44.32 475	83.57 464	13.22 478	89.15 468	58.68 469	81.00 447	78.91 469
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		64.94 438	64.25 440	67.02 456	82.28 473	59.36 479	91.83 465	85.63 473	52.69 470	60.22 471	77.28 470	41.06 470	80.12 473	46.15 473	41.14 471	61.57 472

EMVS		64.07 439	63.26 442	66.53 457	81.73 474	58.81 480	91.85 464	84.75 474	51.93 472	59.09 472	75.13 471	43.32 468	79.09 475	42.03 475	39.47 472	61.69 471

MVE	62.14 22	63.28 440	59.38 443	74.99 453	74.33 478	65.47 474	85.55 468	80.50 477	52.02 471	51.10 473	75.00 472	10.91 481	80.50 472	51.60 471	53.40 470	78.99 468
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		30.17 441	30.18 445	30.16 458	78.61 476	43.29 483	66.79 472	14.21 482	17.31 475	14.82 478	11.93 478	11.55 480	41.43 477	37.08 476	19.30 475	5.76 475

cdsmvs_eth3d_5k		23.98 442	31.98 444	0.00 461	0.00 484	0.00 486	0.00 473	98.59 170	0.00 479	0.00 480	98.61 198	90.60 197	0.00 480	0.00 479	0.00 478	0.00 476

testmvs		21.48 443	24.95 446	11.09 460	14.89 482	6.47 485	96.56 427	9.87 483	7.55 476	17.93 476	39.02 474	9.43 482	5.90 479	16.56 478	12.72 476	20.91 474

test123		20.95 444	23.72 447	12.64 459	13.54 483	8.19 484	96.55 428	6.13 484	7.48 477	16.74 477	37.98 475	12.97 479	6.05 478	16.69 477	5.43 477	23.68 473

ab-mvs-re		8.20 445	10.94 448	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	98.43 216	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

pcd_1.5k_mvsjas		7.88 446	10.50 449	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	94.51 90	0.00 480	0.00 479	0.00 478	0.00 476

mmdepth		0.00 447	0.00 450	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

monomultidepth		0.00 447	0.00 450	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

test_blank		0.00 447	0.00 450	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

uanet_test		0.00 447	0.00 450	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

DCPMVS		0.00 447	0.00 450	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

sosnet-low-res		0.00 447	0.00 450	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

sosnet		0.00 447	0.00 450	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

uncertanet		0.00 447	0.00 450	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

Regformer		0.00 447	0.00 450	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

uanet		0.00 447	0.00 450	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

MED-MVS test				99.52 13	99.77 2	98.86 22	99.32 22	99.24 20	96.41 119	99.30 49	99.35 59		99.92 42	98.30 74	99.80 24	99.79 28

TestfortrainingZip							99.32 22

WAC-MVS						90.94 369								88.66 402

FOURS1					99.82 1	98.66 27	99.69 1	98.95 60	97.46 54	99.39 43

MSC_two_6792asdad				99.62 7	99.17 109	99.08 12		98.63 160					99.94 13	98.53 54	99.80 24	99.86 12

PC_three_1452									95.08 201	99.60 31	99.16 100	97.86 2	98.47 336	97.52 129	99.72 66	99.74 49

No_MVS				99.62 7	99.17 109	99.08 12		98.63 160					99.94 13	98.53 54	99.80 24	99.86 12

test_one_0601					99.66 30	99.25 3		98.86 90	97.55 46	99.20 57	99.47 34	97.57 7

eth-test2					0.00 484

eth-test					0.00 484

ZD-MVS					99.46 57	98.70 26		98.79 117	93.21 311	98.67 102	98.97 139	95.70 51	99.83 88	96.07 198	99.58 97

RE-MVS-def			98.34 52		99.49 51	97.86 73	99.11 64	98.80 112	96.49 114	99.17 60	99.35 59	95.29 68		97.72 108	99.65 80	99.71 62

IU-MVS					99.71 23	99.23 8		98.64 157	95.28 184	99.63 30				98.35 71	99.81 15	99.83 18

OPU-MVS				99.37 26	99.24 101	99.05 15	99.02 83				99.16 100	97.81 3	99.37 208	97.24 148	99.73 61	99.70 66

test_241102_TWO								98.87 84	97.65 38	99.53 36	99.48 32	97.34 12	99.94 13	98.43 66	99.80 24	99.83 18

test_241102_ONE					99.71 23	99.24 6		98.87 84	97.62 40	99.73 21	99.39 47	97.53 8	99.74 132

9.14			98.06 77		99.47 55		98.71 182	98.82 99	94.36 247	99.16 64	99.29 73	96.05 39	99.81 100	97.00 155	99.71 68

save fliter					99.46 57	98.38 39	98.21 278	98.71 135	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 15

test_0728_SECOND				99.71 1	99.72 16	99.35 1	98.97 94	98.88 77					99.94 13	98.47 62	99.81 15	99.84 17

test0726					99.72 16	99.25 3	99.06 71	98.88 77	97.62 40	99.56 33	99.50 28	97.42 10

GSMVS																99.20 176

test_part2					99.63 33	99.18 11				99.27 54

sam_mvs1												89.45 226				99.20 176

sam_mvs												88.99 242

ambc				89.49 433	86.66 468	75.78 460	92.66 463	96.72 416		86.55 440	92.50 456	46.01 465	97.90 398	90.32 373	82.09 439	94.80 436

MTGPA								98.74 127

test_post1							96.68 424				30.43 477	87.85 276	98.69 314	92.59 324

test_post											31.83 476	88.83 249	98.91 290

patchmatchnet-post											95.10 431	89.42 227	98.89 294

GG-mvs-BLEND				96.59 289	96.34 386	94.98 242	96.51 429	88.58 472		93.10 365	94.34 442	80.34 389	98.05 386	89.53 389	96.99 252	96.74 352

MTMP							98.89 118	94.14 455

gm-plane-assit					95.88 407	87.47 436			89.74 410		96.94 367		99.19 239	93.32 303

test9_res														96.39 192	99.57 98	99.69 69

TEST9					99.31 77	98.50 33	97.92 323	98.73 130	92.63 334	97.74 170	98.68 193	96.20 34	99.80 107

test_8					99.29 86	98.44 35	97.89 331	98.72 132	92.98 322	97.70 175	98.66 196	96.20 34	99.80 107

agg_prior2														95.87 208	99.57 98	99.68 74

agg_prior					99.30 81	98.38 39		98.72 132		97.57 191			99.81 100

TestCases				96.99 250	99.25 94	93.21 324		98.18 281	91.36 374	93.52 344	98.77 180	84.67 340	99.72 134	89.70 386	97.87 222	98.02 291

test_prior4						98.01 69	97.86 335

test_prior2							97.80 342		96.12 135	97.89 161	98.69 192	95.96 43		96.89 165	99.60 92

test_prior				99.19 49	99.31 77	98.22 56		98.84 94					99.70 140			99.65 82

旧先验2							97.57 361		91.30 379	98.67 102			99.80 107	95.70 219

新几何2							97.64 355

新几何1				99.16 54	99.34 69	98.01 69		98.69 141	90.06 404	98.13 132	98.95 146	94.60 88	99.89 66	91.97 343	99.47 120	99.59 93

旧先验1					99.29 86	97.48 88		98.70 139			99.09 121	95.56 54			99.47 120	99.61 89

无先验							97.58 360	98.72 132	91.38 373				99.87 77	93.36 302		99.60 91

原ACMM2							97.67 352

原ACMM1				98.65 96	99.32 75	96.62 138		98.67 149	93.27 310	97.81 164	98.97 139	95.18 75	99.83 88	93.84 288	99.46 123	99.50 105

test222					99.23 102	97.17 115	97.40 369	98.66 152	88.68 423	98.05 139	98.96 144	94.14 101			99.53 111	99.61 89

testdata2													99.89 66	91.65 351

segment_acmp												96.85 15

testdata				98.26 139	99.20 107	95.36 219		98.68 144	91.89 360	98.60 110	99.10 113	94.44 95	99.82 95	94.27 272	99.44 124	99.58 97

testdata1							97.32 379		96.34 125

test12				99.18 51	99.16 113	98.19 58		98.53 186		98.07 136		95.13 78	99.72 134		99.56 106	99.63 87

plane_prior7					97.42 320	94.63 259

plane_prior6					97.35 327	94.61 262						87.09 289

plane_prior5								98.56 180					99.03 270	96.07 198	94.27 305	96.92 328

plane_prior4											98.28 235

plane_prior3						94.61 262			97.02 86	95.34 271

plane_prior2							98.80 154		97.28 66

plane_prior1					97.37 326

plane_prior						94.60 264	98.44 249		96.74 101						94.22 307

n2								0.00 485

nn								0.00 485

door-mid								94.37 451

lessismore_v0				94.45 398	94.93 431	88.44 427		91.03 468		86.77 438	97.64 299	76.23 425	98.42 342	90.31 374	85.64 429	96.51 387

LGP-MVS_train				96.47 304	97.46 315	93.54 305		98.54 184	94.67 229	94.36 303	98.77 180	85.39 322	99.11 256	95.71 217	94.15 311	96.76 350

test11								98.66 152

door								94.64 449

HQP5-MVS						94.25 281

HQP-NCC					97.20 335		98.05 307		96.43 116	94.45 295

ACMP_Plane					97.20 335		98.05 307		96.43 116	94.45 295

BP-MVS														95.30 231

HQP4-MVS										94.45 295			98.96 281			96.87 340

HQP3-MVS								98.46 205							94.18 309

HQP2-MVS												86.75 295

NP-MVS					97.28 329	94.51 267					97.73 286

MDTV_nov1_ep13_2view						84.26 446	96.89 414		90.97 388	97.90 160		89.89 212		93.91 286		99.18 185

MDTV_nov1_ep13			95.40 223		97.48 313	88.34 428	96.85 417	97.29 376	93.74 279	97.48 193	97.26 328	89.18 235	99.05 266	91.92 344	97.43 243

ACMMP++_ref															92.97 339

ACMMP++															93.61 326

Test By Simon												94.64 87

ITE_SJBPF				95.44 357	97.42 320	91.32 363		97.50 356	95.09 200	93.59 339	98.35 226	81.70 371	98.88 296	89.71 385	93.39 332	96.12 408

DeepMVS_CX				86.78 437	97.09 345	72.30 467		95.17 445	75.92 461	84.34 450	95.19 429	70.58 443	95.35 450	79.98 450	89.04 395	92.68 455

High-resolution multi-view benchmark