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.

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 16	98.69 71	98.20 8	99.93 1	99.98 2	96.82 24	100.00 1	99.75 33	100.00 1	99.99 23

NCCC		99.37 2	99.25 2	99.71 15	99.96 8	99.15 22	99.97 32	98.62 85	98.02 17	99.90 3	99.95 3	97.33 17	100.00 1	99.54 46	100.00 1	100.00 1

MCST-MVS		99.32 3	99.14 4	99.86 5	99.97 3	99.59 5	99.97 32	98.64 79	98.47 3	99.13 93	99.92 13	96.38 34	100.00 1	99.74 35	100.00 1	100.00 1

DVP-MVS		99.30 4	99.16 3	99.73 12	99.93 24	99.29 15	99.95 58	98.32 182	97.28 36	99.83 15	99.91 14	97.22 19	100.00 1	99.99 5	100.00 1	99.89 88
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
SED-MVS		99.28 5	99.11 7	99.77 8	99.93 24	99.30 12	99.96 39	98.43 141	97.27 38	99.80 19	99.94 4	96.71 27	100.00 1	100.00 1	100.00 1	100.00 1

DVP-MVS++		99.26 6	99.09 9	99.77 8	99.91 39	99.31 10	99.95 58	98.43 141	96.48 67	99.80 19	99.93 11	97.44 14	100.00 1	99.92 13	99.98 32	100.00 1

DPE-MVS		99.26 6	99.10 8	99.74 11	99.89 45	99.24 19	99.87 114	98.44 133	97.48 31	99.64 47	99.94 4	96.68 29	99.99 36	99.99 5	100.00 1	99.99 23
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSLP-MVS++		99.13 8	99.01 11	99.49 32	99.94 13	98.46 61	99.98 16	98.86 54	97.10 44	99.80 19	99.94 4	95.92 40	100.00 1	99.51 47	100.00 1	100.00 1

MSP-MVS		99.09 9	99.12 5	98.98 81	99.93 24	97.24 110	99.95 58	98.42 153	97.50 30	99.52 64	99.88 24	97.43 16	99.71 145	99.50 48	99.98 32	100.00 1
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
HPM-MVS++		99.07 10	98.88 16	99.63 17	99.90 42	99.02 25	99.95 58	98.56 98	97.56 29	99.44 70	99.85 33	95.38 52	100.00 1	99.31 58	99.99 21	99.87 91

MVS_0304		99.06 11	98.84 17	99.72 13	99.76 66	99.21 21	99.99 5	99.34 25	98.70 2	99.44 70	99.75 73	93.24 123	99.99 36	99.94 11	99.41 119	99.95 74

APDe-MVS		99.06 11	98.91 14	99.51 29	99.94 13	98.76 45	99.91 93	98.39 165	97.20 42	99.46 68	99.85 33	95.53 48	99.79 130	99.86 21	100.00 1	99.99 23
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SteuartSystems-ACMMP		99.02 13	98.97 13	99.18 53	98.72 149	97.71 89	99.98 16	98.44 133	96.85 53	99.80 19	99.91 14	97.57 8	99.85 115	99.44 53	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
CHOSEN 280x420		99.01 14	99.03 10	98.95 84	99.38 100	98.87 33	98.46 332	99.42 21	97.03 48	99.02 100	99.09 156	99.35 2	98.21 259	99.73 37	99.78 84	99.77 105

fmvsm_l_conf0.5_n_a		99.00 15	98.91 14	99.28 46	99.21 107	97.91 83	99.98 16	98.85 57	98.25 5	99.92 2	99.75 73	94.72 71	99.97 57	99.87 19	99.64 92	99.95 74

fmvsm_l_conf0.5_n		98.94 16	98.84 17	99.25 47	99.17 110	97.81 86	99.98 16	98.86 54	98.25 5	99.90 3	99.76 66	94.21 94	99.97 57	99.87 19	99.52 106	99.98 51

TSAR-MVS + MP.		98.93 17	98.77 19	99.41 38	99.74 70	98.67 49	99.77 155	98.38 169	96.73 60	99.88 7	99.74 80	94.89 66	99.59 157	99.80 25	99.98 32	99.97 61
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SD-MVS		98.92 18	98.70 20	99.56 25	99.70 78	98.73 46	99.94 75	98.34 179	96.38 73	99.81 17	99.76 66	94.59 74	99.98 47	99.84 22	99.96 46	99.97 61
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
MG-MVS		98.91 19	98.65 24	99.68 16	99.94 13	99.07 24	99.64 196	99.44 19	97.33 35	99.00 101	99.72 85	94.03 99	99.98 47	98.73 95	100.00 1	100.00 1

train_agg		98.88 20	98.65 24	99.59 23	99.92 31	98.92 29	99.96 39	98.43 141	94.35 134	99.71 38	99.86 29	95.94 38	99.85 115	99.69 41	99.98 32	99.99 23

MM		98.83 21	98.53 30	99.76 10	99.59 85	99.33 8	99.99 5	99.76 6	98.39 4	99.39 78	99.80 54	90.49 185	99.96 67	99.89 17	99.43 117	99.98 51

DPM-MVS		98.83 21	98.46 33	99.97 1	99.33 102	99.92 1	99.96 39	98.44 133	97.96 18	99.55 59	99.94 4	97.18 21	100.00 1	93.81 232	99.94 55	99.98 51

DeepC-MVS_fast	96.59 1	98.81 23	98.54 29	99.62 20	99.90 42	98.85 35	99.24 259	98.47 125	98.14 12	99.08 96	99.91 14	93.09 127	100.00 1	99.04 71	99.99 21	100.00 1
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
reproduce-ours		98.78 24	98.67 21	99.09 69	99.70 78	97.30 107	99.74 167	98.25 193	97.10 44	99.10 94	99.90 18	94.59 74	99.99 36	99.77 29	99.91 67	99.99 23

our_new_method		98.78 24	98.67 21	99.09 69	99.70 78	97.30 107	99.74 167	98.25 193	97.10 44	99.10 94	99.90 18	94.59 74	99.99 36	99.77 29	99.91 67	99.99 23

SMA-MVS		98.76 26	98.48 32	99.62 20	99.87 51	98.87 33	99.86 125	98.38 169	93.19 182	99.77 29	99.94 4	95.54 46	100.00 1	99.74 35	99.99 21	100.00 1
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
reproduce_model		98.75 27	98.66 23	99.03 74	99.71 76	97.10 119	99.73 174	98.23 197	97.02 49	99.18 91	99.90 18	94.54 78	99.99 36	99.77 29	99.90 69	99.99 23

MVS_111021_HR		98.72 28	98.62 26	99.01 78	99.36 101	97.18 113	99.93 82	99.90 1	96.81 58	98.67 119	99.77 64	93.92 101	99.89 103	99.27 60	99.94 55	99.96 67

XVS		98.70 29	98.55 28	99.15 60	99.94 13	97.50 99	99.94 75	98.42 153	96.22 79	99.41 74	99.78 62	94.34 86	99.96 67	98.92 81	99.95 50	99.99 23

SF-MVS		98.67 30	98.40 35	99.50 30	99.77 65	98.67 49	99.90 99	98.21 199	93.53 171	99.81 17	99.89 22	94.70 73	99.86 114	99.84 22	99.93 61	99.96 67

CDPH-MVS		98.65 31	98.36 41	99.49 32	99.94 13	98.73 46	99.87 114	98.33 180	93.97 154	99.76 30	99.87 27	94.99 64	99.75 139	98.55 105	100.00 1	99.98 51

APD-MVS		98.62 32	98.35 42	99.41 38	99.90 42	98.51 59	99.87 114	98.36 173	94.08 147	99.74 34	99.73 82	94.08 97	99.74 141	99.42 54	99.99 21	99.99 23
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TSAR-MVS + GP.		98.60 33	98.51 31	98.86 88	99.73 73	96.63 135	99.97 32	97.92 233	98.07 14	98.76 115	99.55 117	95.00 63	99.94 83	99.91 16	97.68 176	99.99 23

PAPM		98.60 33	98.42 34	99.14 62	96.05 295	98.96 26	99.90 99	99.35 24	96.68 62	98.35 136	99.66 101	96.45 33	98.51 226	99.45 52	99.89 70	99.96 67

HFP-MVS		98.56 35	98.37 39	99.14 62	99.96 8	97.43 103	99.95 58	98.61 86	94.77 114	99.31 82	99.85 33	94.22 92	100.00 1	98.70 96	99.98 32	99.98 51

region2R		98.54 36	98.37 39	99.05 72	99.96 8	97.18 113	99.96 39	98.55 104	94.87 112	99.45 69	99.85 33	94.07 98	100.00 1	98.67 98	100.00 1	99.98 51

DELS-MVS		98.54 36	98.22 47	99.50 30	99.15 112	98.65 53	100.00 1	98.58 92	97.70 24	98.21 144	99.24 148	92.58 142	99.94 83	98.63 103	99.94 55	99.92 84
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
PAPR		98.52 38	98.16 53	99.58 24	99.97 3	98.77 42	99.95 58	98.43 141	95.35 99	98.03 148	99.75 73	94.03 99	99.98 47	98.11 129	99.83 77	99.99 23

ACMMPR		98.50 39	98.32 43	99.05 72	99.96 8	97.18 113	99.95 58	98.60 88	94.77 114	99.31 82	99.84 44	93.73 108	100.00 1	98.70 96	99.98 32	99.98 51

ACMMP_NAP		98.49 40	98.14 54	99.54 27	99.66 82	98.62 55	99.85 128	98.37 172	94.68 119	99.53 62	99.83 46	92.87 133	100.00 1	98.66 100	99.84 76	99.99 23

EPNet		98.49 40	98.40 35	98.77 94	99.62 84	96.80 131	99.90 99	99.51 16	97.60 26	99.20 88	99.36 137	93.71 109	99.91 96	97.99 136	98.71 148	99.61 135
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SR-MVS		98.46 42	98.30 46	98.93 85	99.88 49	97.04 121	99.84 133	98.35 175	94.92 109	99.32 81	99.80 54	93.35 116	99.78 132	99.30 59	99.95 50	99.96 67

CP-MVS		98.45 43	98.32 43	98.87 87	99.96 8	96.62 136	99.97 32	98.39 165	94.43 129	98.90 105	99.87 27	94.30 89	100.00 1	99.04 71	99.99 21	99.99 23

test_fmvsm_n_1920		98.44 44	98.61 27	97.92 156	99.27 106	95.18 199	100.00 1	98.90 48	98.05 15	99.80 19	99.73 82	92.64 139	99.99 36	99.58 45	99.51 109	98.59 236

PS-MVSNAJ		98.44 44	98.20 49	99.16 58	98.80 145	98.92 29	99.54 214	98.17 204	97.34 33	99.85 11	99.85 33	91.20 167	99.89 103	99.41 55	99.67 90	98.69 233

test_fmvsmconf_n		98.43 46	98.32 43	98.78 92	98.12 199	96.41 144	99.99 5	98.83 61	98.22 7	99.67 42	99.64 104	91.11 171	99.94 83	99.67 42	99.62 95	99.98 51

MVS_111021_LR		98.42 47	98.38 37	98.53 118	99.39 99	95.79 169	99.87 114	99.86 2	96.70 61	98.78 111	99.79 58	92.03 157	99.90 98	99.17 64	99.86 75	99.88 89

fmvsm_l_conf0.5_n_3		98.41 48	98.08 59	99.39 40	99.12 113	98.29 64	99.98 16	98.64 79	98.14 12	99.86 8	99.76 66	87.99 217	99.97 57	99.72 38	99.54 104	99.91 86

DP-MVS Recon		98.41 48	98.02 62	99.56 25	99.97 3	98.70 48	99.92 85	98.44 133	92.06 232	98.40 134	99.84 44	95.68 44	100.00 1	98.19 124	99.71 88	99.97 61

PHI-MVS		98.41 48	98.21 48	99.03 74	99.86 53	97.10 119	99.98 16	98.80 65	90.78 273	99.62 51	99.78 62	95.30 53	100.00 1	99.80 25	99.93 61	99.99 23

mPP-MVS		98.39 51	98.20 49	98.97 82	99.97 3	96.92 126	99.95 58	98.38 169	95.04 105	98.61 123	99.80 54	93.39 114	100.00 1	98.64 101	100.00 1	99.98 51

PGM-MVS		98.34 52	98.13 55	98.99 79	99.92 31	97.00 122	99.75 164	99.50 17	93.90 160	99.37 79	99.76 66	93.24 123	100.00 1	97.75 153	99.96 46	99.98 51

BP-MVS1		98.33 53	98.18 51	98.81 90	97.44 244	97.98 78	99.96 39	98.17 204	94.88 111	98.77 112	99.59 110	97.59 7	99.08 192	98.24 122	98.93 139	99.36 180

SR-MVS-dyc-post		98.31 54	98.17 52	98.71 97	99.79 62	96.37 148	99.76 160	98.31 184	94.43 129	99.40 76	99.75 73	93.28 121	99.78 132	98.90 84	99.92 64	99.97 61

ZNCC-MVS		98.31 54	98.03 61	99.17 56	99.88 49	97.59 94	99.94 75	98.44 133	94.31 137	98.50 128	99.82 49	93.06 128	99.99 36	98.30 121	99.99 21	99.93 79

MTAPA		98.29 56	97.96 68	99.30 45	99.85 54	97.93 82	99.39 238	98.28 189	95.76 88	97.18 176	99.88 24	92.74 137	100.00 1	98.67 98	99.88 73	99.99 23

balanced_conf03		98.27 57	97.99 63	99.11 67	98.64 156	98.43 62	99.47 226	97.79 244	94.56 122	99.74 34	98.35 228	94.33 88	99.25 177	99.12 65	99.96 46	99.64 125

GST-MVS		98.27 57	97.97 65	99.17 56	99.92 31	97.57 95	99.93 82	98.39 165	94.04 152	98.80 110	99.74 80	92.98 130	100.00 1	98.16 126	99.76 85	99.93 79

CANet		98.27 57	97.82 75	99.63 17	99.72 75	99.10 23	99.98 16	98.51 116	97.00 50	98.52 125	99.71 87	87.80 218	99.95 75	99.75 33	99.38 120	99.83 95

EI-MVSNet-Vis-set		98.27 57	98.11 57	98.75 95	99.83 57	96.59 139	99.40 234	98.51 116	95.29 101	98.51 127	99.76 66	93.60 112	99.71 145	98.53 108	99.52 106	99.95 74

APD-MVS_3200maxsize		98.25 61	98.08 59	98.78 92	99.81 60	96.60 137	99.82 143	98.30 187	93.95 156	99.37 79	99.77 64	92.84 134	99.76 138	98.95 77	99.92 64	99.97 61

patch_mono-2		98.24 62	99.12 5	95.59 242	99.67 81	86.91 363	99.95 58	98.89 50	97.60 26	99.90 3	99.76 66	96.54 32	99.98 47	99.94 11	99.82 81	99.88 89

xiu_mvs_v2_base		98.23 63	97.97 65	99.02 77	98.69 150	98.66 51	99.52 216	98.08 217	97.05 47	99.86 8	99.86 29	90.65 180	99.71 145	99.39 57	98.63 149	98.69 233

MP-MVS		98.23 63	97.97 65	99.03 74	99.94 13	97.17 116	99.95 58	98.39 165	94.70 118	98.26 141	99.81 53	91.84 161	100.00 1	98.85 87	99.97 42	99.93 79
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
EI-MVSNet-UG-set		98.14 65	97.99 63	98.60 107	99.80 61	96.27 150	99.36 244	98.50 122	95.21 103	98.30 138	99.75 73	93.29 120	99.73 144	98.37 117	99.30 124	99.81 98

PAPM_NR		98.12 66	97.93 70	98.70 98	99.94 13	96.13 160	99.82 143	98.43 141	94.56 122	97.52 163	99.70 89	94.40 81	99.98 47	97.00 168	99.98 32	99.99 23

WTY-MVS		98.10 67	97.60 84	99.60 22	98.92 133	99.28 17	99.89 108	99.52 14	95.58 93	98.24 143	99.39 134	93.33 117	99.74 141	97.98 138	95.58 226	99.78 104

MP-MVS-pluss		98.07 68	97.64 82	99.38 43	99.74 70	98.41 63	99.74 167	98.18 203	93.35 176	96.45 195	99.85 33	92.64 139	99.97 57	98.91 83	99.89 70	99.77 105
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HPM-MVS		97.96 69	97.72 77	98.68 99	99.84 56	96.39 147	99.90 99	98.17 204	92.61 210	98.62 122	99.57 116	91.87 160	99.67 153	98.87 86	99.99 21	99.99 23
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
fmvsm_s_conf0.5_n_3		97.95 70	97.66 80	98.81 90	98.99 123	98.07 72	99.98 16	98.81 62	98.18 9	99.89 6	99.70 89	84.15 258	99.97 57	99.76 32	99.50 111	98.39 240

PVSNet_Blended		97.94 71	97.64 82	98.83 89	99.59 85	96.99 123	100.00 1	99.10 32	95.38 98	98.27 139	99.08 157	89.00 207	99.95 75	99.12 65	99.25 126	99.57 146

PLC	95.54 3	97.93 72	97.89 73	98.05 149	99.82 58	94.77 211	99.92 85	98.46 127	93.93 157	97.20 174	99.27 143	95.44 51	99.97 57	97.41 158	99.51 109	99.41 174
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ETV-MVS		97.92 73	97.80 76	98.25 137	98.14 197	96.48 141	99.98 16	97.63 257	95.61 92	99.29 85	99.46 125	92.55 143	98.82 204	99.02 75	98.54 151	99.46 167

GDP-MVS		97.88 74	97.59 86	98.75 95	97.59 236	97.81 86	99.95 58	97.37 290	94.44 128	99.08 96	99.58 113	97.13 23	99.08 192	94.99 200	98.17 162	99.37 178

SPE-MVS-test		97.88 74	97.94 69	97.70 171	99.28 105	95.20 198	99.98 16	97.15 314	95.53 95	99.62 51	99.79 58	92.08 156	98.38 242	98.75 94	99.28 125	99.52 158

myMVS_eth3d28		97.86 76	97.59 86	98.68 99	98.50 169	97.26 109	99.92 85	98.55 104	93.79 163	98.26 141	98.75 195	95.20 54	99.48 169	98.93 79	96.40 204	99.29 192

API-MVS		97.86 76	97.66 80	98.47 122	99.52 92	95.41 188	99.47 226	98.87 53	91.68 243	98.84 107	99.85 33	92.34 150	99.99 36	98.44 113	99.96 46	100.00 1

lupinMVS		97.85 78	97.60 84	98.62 105	97.28 257	97.70 91	99.99 5	97.55 269	95.50 97	99.43 72	99.67 99	90.92 175	98.71 215	98.40 114	99.62 95	99.45 169

UBG		97.84 79	97.69 79	98.29 135	98.38 175	96.59 139	99.90 99	98.53 111	93.91 159	98.52 125	98.42 226	96.77 25	99.17 186	98.54 106	96.20 207	99.11 208

MVSMamba_PlusPlus		97.83 80	97.45 91	98.99 79	98.60 158	98.15 66	99.58 205	97.74 248	90.34 282	99.26 87	98.32 231	94.29 90	99.23 178	99.03 74	99.89 70	99.58 144

test_yl		97.83 80	97.37 96	99.21 50	99.18 108	97.98 78	99.64 196	99.27 27	91.43 252	97.88 155	98.99 166	95.84 42	99.84 123	98.82 88	95.32 232	99.79 101

DCV-MVSNet		97.83 80	97.37 96	99.21 50	99.18 108	97.98 78	99.64 196	99.27 27	91.43 252	97.88 155	98.99 166	95.84 42	99.84 123	98.82 88	95.32 232	99.79 101

mvsany_test1		97.82 83	97.90 72	97.55 179	98.77 147	93.04 255	99.80 149	97.93 230	96.95 52	99.61 57	99.68 98	90.92 175	99.83 125	99.18 63	98.29 160	99.80 100

alignmvs		97.81 84	97.33 98	99.25 47	98.77 147	98.66 51	99.99 5	98.44 133	94.40 133	98.41 132	99.47 123	93.65 110	99.42 173	98.57 104	94.26 247	99.67 119

fmvsm_s_conf0.5_n		97.80 85	97.85 74	97.67 172	99.06 116	94.41 217	99.98 16	98.97 41	97.34 33	99.63 48	99.69 92	87.27 225	99.97 57	99.62 43	99.06 135	98.62 235

HPM-MVS_fast		97.80 85	97.50 89	98.68 99	99.79 62	96.42 143	99.88 111	98.16 209	91.75 242	98.94 103	99.54 119	91.82 162	99.65 155	97.62 156	99.99 21	99.99 23

CS-MVS		97.79 87	97.91 71	97.43 187	99.10 114	94.42 216	99.99 5	97.10 319	95.07 104	99.68 41	99.75 73	92.95 131	98.34 246	98.38 115	99.14 131	99.54 152

HY-MVS	92.50 7	97.79 87	97.17 107	99.63 17	98.98 125	99.32 9	97.49 363	99.52 14	95.69 90	98.32 137	97.41 259	93.32 118	99.77 135	98.08 132	95.75 223	99.81 98

CNLPA		97.76 89	97.38 95	98.92 86	99.53 91	96.84 128	99.87 114	98.14 213	93.78 164	96.55 193	99.69 92	92.28 151	99.98 47	97.13 164	99.44 116	99.93 79

test_fmvsmconf0.1_n		97.74 90	97.44 92	98.64 104	95.76 306	96.20 156	99.94 75	98.05 220	98.17 10	98.89 106	99.42 127	87.65 220	99.90 98	99.50 48	99.60 101	99.82 96

ACMMP		97.74 90	97.44 92	98.66 102	99.92 31	96.13 160	99.18 264	99.45 18	94.84 113	96.41 198	99.71 87	91.40 164	99.99 36	97.99 136	98.03 171	99.87 91
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
fmvsm_s_conf0.5_n_a		97.73 92	97.72 77	97.77 166	98.63 157	94.26 223	99.96 39	98.92 47	97.18 43	99.75 31	99.69 92	87.00 230	99.97 57	99.46 51	98.89 140	99.08 211

testing3-2		97.72 93	97.43 94	98.60 107	98.55 162	97.11 118	100.00 1	99.23 29	93.78 164	97.90 152	98.73 197	95.50 49	99.69 149	98.53 108	94.63 239	98.99 217

DeepPCF-MVS	95.94 2	97.71 94	98.98 12	93.92 306	99.63 83	81.76 394	99.96 39	98.56 98	99.47 1	99.19 90	99.99 1	94.16 96	100.00 1	99.92 13	99.93 61	100.00 1

test_fmvsmvis_n_1920		97.67 95	97.59 86	97.91 158	97.02 264	95.34 190	99.95 58	98.45 128	97.87 19	97.02 180	99.59 110	89.64 195	99.98 47	99.41 55	99.34 123	98.42 239

CPTT-MVS		97.64 96	97.32 99	98.58 111	99.97 3	95.77 170	99.96 39	98.35 175	89.90 291	98.36 135	99.79 58	91.18 170	99.99 36	98.37 117	99.99 21	99.99 23

fmvsm_s_conf0.5_n_2		97.59 97	97.28 100	98.53 118	99.01 119	98.15 66	99.98 16	98.59 90	98.17 10	99.75 31	99.63 107	81.83 275	99.94 83	99.78 27	98.79 146	97.51 263

sss		97.57 98	97.03 112	99.18 53	98.37 177	98.04 75	99.73 174	99.38 22	93.46 173	98.76 115	99.06 159	91.21 166	99.89 103	96.33 180	97.01 193	99.62 131

test2506		97.53 99	97.19 105	98.58 111	98.66 153	96.90 127	98.81 309	99.77 5	94.93 107	97.95 150	98.96 172	92.51 144	99.20 183	94.93 202	98.15 164	99.64 125

EIA-MVS		97.53 99	97.46 90	97.76 168	98.04 203	94.84 207	99.98 16	97.61 263	94.41 132	97.90 152	99.59 110	92.40 148	98.87 201	98.04 133	99.13 132	99.59 138

testing11		97.48 101	97.27 101	98.10 145	98.36 178	96.02 163	99.92 85	98.45 128	93.45 175	98.15 146	98.70 200	95.48 50	99.22 179	97.85 144	95.05 236	99.07 212

xiu_mvs_v1_base_debu		97.43 102	97.06 108	98.55 113	97.74 221	98.14 68	99.31 249	97.86 239	96.43 70	99.62 51	99.69 92	85.56 243	99.68 150	99.05 68	98.31 157	97.83 252

xiu_mvs_v1_base		97.43 102	97.06 108	98.55 113	97.74 221	98.14 68	99.31 249	97.86 239	96.43 70	99.62 51	99.69 92	85.56 243	99.68 150	99.05 68	98.31 157	97.83 252

xiu_mvs_v1_base_debi		97.43 102	97.06 108	98.55 113	97.74 221	98.14 68	99.31 249	97.86 239	96.43 70	99.62 51	99.69 92	85.56 243	99.68 150	99.05 68	98.31 157	97.83 252

MAR-MVS		97.43 102	97.19 105	98.15 143	99.47 96	94.79 210	99.05 280	98.76 66	92.65 208	98.66 120	99.82 49	88.52 212	99.98 47	98.12 128	99.63 94	99.67 119
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
dcpmvs_2		97.42 106	98.09 58	95.42 247	99.58 89	87.24 359	99.23 260	96.95 337	94.28 140	98.93 104	99.73 82	94.39 84	99.16 188	99.89 17	99.82 81	99.86 93

thisisatest0515		97.41 107	97.02 113	98.59 110	97.71 228	97.52 97	99.97 32	98.54 108	91.83 238	97.45 166	99.04 160	97.50 9	99.10 191	94.75 210	96.37 206	99.16 202

114514_t		97.41 107	96.83 121	99.14 62	99.51 94	97.83 84	99.89 108	98.27 191	88.48 319	99.06 98	99.66 101	90.30 188	99.64 156	96.32 181	99.97 42	99.96 67

EC-MVSNet		97.38 109	97.24 102	97.80 161	97.41 246	95.64 179	99.99 5	97.06 325	94.59 121	99.63 48	99.32 139	89.20 205	98.14 262	98.76 93	99.23 128	99.62 131

fmvsm_s_conf0.1_n		97.30 110	97.21 104	97.60 178	97.38 248	94.40 219	99.90 99	98.64 79	96.47 69	99.51 66	99.65 103	84.99 251	99.93 91	99.22 62	99.09 134	98.46 237

OMC-MVS		97.28 111	97.23 103	97.41 188	99.76 66	93.36 250	99.65 192	97.95 228	96.03 83	97.41 168	99.70 89	89.61 196	99.51 161	96.73 177	98.25 161	99.38 176

PVSNet_Blended_VisFu		97.27 112	96.81 122	98.66 102	98.81 144	96.67 134	99.92 85	98.64 79	94.51 124	96.38 199	98.49 219	89.05 206	99.88 109	97.10 166	98.34 155	99.43 172

fmvsm_s_conf0.1_n_2		97.25 113	96.85 120	98.43 126	98.08 200	98.08 71	99.92 85	97.76 247	98.05 15	99.65 44	99.58 113	80.88 288	99.93 91	99.59 44	98.17 162	97.29 264

jason		97.24 114	96.86 119	98.38 131	95.73 309	97.32 106	99.97 32	97.40 287	95.34 100	98.60 124	99.54 119	87.70 219	98.56 223	97.94 139	99.47 112	99.25 197
jason: jason.
AdaColmap		97.23 115	96.80 123	98.51 120	99.99 1	95.60 181	99.09 269	98.84 60	93.32 178	96.74 188	99.72 85	86.04 240	100.00 1	98.01 134	99.43 117	99.94 78

VNet		97.21 116	96.57 134	99.13 66	98.97 126	97.82 85	99.03 283	99.21 30	94.31 137	99.18 91	98.88 183	86.26 239	99.89 103	98.93 79	94.32 245	99.69 116

testing99		97.17 117	96.91 115	97.95 152	98.35 180	95.70 175	99.91 93	98.43 141	92.94 191	97.36 169	98.72 198	94.83 67	99.21 180	97.00 168	94.64 238	98.95 218

testing91		97.16 118	96.90 116	97.97 151	98.35 180	95.67 178	99.91 93	98.42 153	92.91 193	97.33 170	98.72 198	94.81 68	99.21 180	96.98 170	94.63 239	99.03 214

PVSNet	91.05 13	97.13 119	96.69 129	98.45 124	99.52 92	95.81 168	99.95 58	99.65 12	94.73 116	99.04 99	99.21 150	84.48 255	99.95 75	94.92 203	98.74 147	99.58 144

thisisatest0530		97.10 120	96.72 127	98.22 138	97.60 235	96.70 132	99.92 85	98.54 108	91.11 262	97.07 179	98.97 170	97.47 12	99.03 194	93.73 237	96.09 210	98.92 219

CSCG		97.10 120	97.04 111	97.27 197	99.89 45	91.92 281	99.90 99	99.07 35	88.67 315	95.26 221	99.82 49	93.17 126	99.98 47	98.15 127	99.47 112	99.90 87

sasdasda		97.09 122	96.32 141	99.39 40	98.93 130	98.95 27	99.72 178	97.35 291	94.45 125	97.88 155	99.42 127	86.71 232	99.52 159	98.48 110	93.97 251	99.72 111

fmvsm_s_conf0.1_n_a		97.09 122	96.90 116	97.63 176	95.65 316	94.21 225	99.83 140	98.50 122	96.27 78	99.65 44	99.64 104	84.72 252	99.93 91	99.04 71	98.84 143	98.74 230

canonicalmvs		97.09 122	96.32 141	99.39 40	98.93 130	98.95 27	99.72 178	97.35 291	94.45 125	97.88 155	99.42 127	86.71 232	99.52 159	98.48 110	93.97 251	99.72 111

testing222		97.08 125	96.75 125	98.06 148	98.56 159	96.82 129	99.85 128	98.61 86	92.53 216	98.84 107	98.84 192	93.36 115	98.30 250	95.84 189	94.30 246	99.05 213

ETVMVS		97.03 126	96.64 130	98.20 139	98.67 152	97.12 117	99.89 108	98.57 94	91.10 263	98.17 145	98.59 210	93.86 105	98.19 260	95.64 192	95.24 234	99.28 194

MGCFI-Net		97.00 127	96.22 145	99.34 44	98.86 141	98.80 39	99.67 190	97.30 298	94.31 137	97.77 159	99.41 131	86.36 238	99.50 163	98.38 115	93.90 253	99.72 111

diffmvs		97.00 127	96.64 130	98.09 146	97.64 233	96.17 159	99.81 145	97.19 308	94.67 120	98.95 102	99.28 140	86.43 236	98.76 209	98.37 117	97.42 182	99.33 186
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
thres200		96.96 129	96.21 146	99.22 49	98.97 126	98.84 36	99.85 128	99.71 7	93.17 183	96.26 201	98.88 183	89.87 193	99.51 161	94.26 222	94.91 237	99.31 188

mvsmamba		96.94 130	96.73 126	97.55 179	97.99 205	94.37 220	99.62 199	97.70 250	93.13 186	98.42 131	97.92 247	88.02 216	98.75 211	98.78 91	99.01 137	99.52 158

MVSFormer		96.94 130	96.60 132	97.95 152	97.28 257	97.70 91	99.55 212	97.27 303	91.17 259	99.43 72	99.54 119	90.92 175	96.89 329	94.67 213	99.62 95	99.25 197

F-COLMAP		96.93 132	96.95 114	96.87 207	99.71 76	91.74 286	99.85 128	97.95 228	93.11 188	95.72 214	99.16 154	92.35 149	99.94 83	95.32 195	99.35 122	98.92 219

DeepC-MVS	94.51 4	96.92 133	96.40 140	98.45 124	99.16 111	95.90 166	99.66 191	98.06 218	96.37 76	94.37 230	99.49 122	83.29 265	99.90 98	97.63 155	99.61 99	99.55 148
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
tttt0517		96.85 134	96.49 136	97.92 156	97.48 243	95.89 167	99.85 128	98.54 108	90.72 275	96.63 190	98.93 181	97.47 12	99.02 195	93.03 250	95.76 222	98.85 223

1314		96.84 135	95.96 157	99.48 34	96.74 282	98.52 58	98.31 341	98.86 54	95.82 86	89.91 281	98.98 168	87.49 222	99.96 67	97.80 146	99.73 87	99.96 67

CHOSEN 1792x2688		96.81 136	96.53 135	97.64 174	98.91 137	93.07 252	99.65 192	99.80 3	95.64 91	95.39 218	98.86 188	84.35 257	99.90 98	96.98 170	99.16 130	99.95 74

UWE-MVS		96.79 137	96.72 127	97.00 202	98.51 167	93.70 238	99.71 181	98.60 88	92.96 190	97.09 177	98.34 230	96.67 31	98.85 203	92.11 259	96.50 201	98.44 238

tfpn200view9		96.79 137	95.99 151	99.19 52	98.94 128	98.82 37	99.78 152	99.71 7	92.86 194	96.02 206	98.87 186	89.33 200	99.50 163	93.84 229	94.57 241	99.27 195

thres400		96.78 139	95.99 151	99.16 58	98.94 128	98.82 37	99.78 152	99.71 7	92.86 194	96.02 206	98.87 186	89.33 200	99.50 163	93.84 229	94.57 241	99.16 202

CANet_DTU		96.76 140	96.15 147	98.60 107	98.78 146	97.53 96	99.84 133	97.63 257	97.25 41	99.20 88	99.64 104	81.36 281	99.98 47	92.77 253	98.89 140	98.28 244

PMMVS		96.76 140	96.76 124	96.76 210	98.28 185	92.10 276	99.91 93	97.98 225	94.12 145	99.53 62	99.39 134	86.93 231	98.73 212	96.95 173	97.73 174	99.45 169

thres100view900		96.74 142	95.92 161	99.18 53	98.90 138	98.77 42	99.74 167	99.71 7	92.59 212	95.84 210	98.86 188	89.25 202	99.50 163	93.84 229	94.57 241	99.27 195

TESTMET0.1,1		96.74 142	96.26 143	98.16 140	97.36 250	96.48 141	99.96 39	98.29 188	91.93 235	95.77 213	98.07 240	95.54 46	98.29 251	90.55 285	98.89 140	99.70 114

baseline2		96.71 144	96.49 136	97.37 191	95.63 318	95.96 165	99.74 167	98.88 52	92.94 191	91.61 262	98.97 170	97.72 6	98.62 221	94.83 207	98.08 170	97.53 262

thres600view7		96.69 145	95.87 164	99.14 62	98.90 138	98.78 41	99.74 167	99.71 7	92.59 212	95.84 210	98.86 188	89.25 202	99.50 163	93.44 242	94.50 244	99.16 202

EPP-MVSNet		96.69 145	96.60 132	96.96 204	97.74 221	93.05 254	99.37 242	98.56 98	88.75 313	95.83 212	99.01 163	96.01 36	98.56 223	96.92 174	97.20 187	99.25 197

HyFIR lowres test		96.66 147	96.43 139	97.36 193	99.05 117	93.91 233	99.70 185	99.80 3	90.54 277	96.26 201	98.08 239	92.15 154	98.23 258	96.84 176	95.46 227	99.93 79

MVS		96.60 148	95.56 173	99.72 13	96.85 275	99.22 20	98.31 341	98.94 42	91.57 245	90.90 270	99.61 109	86.66 234	99.96 67	97.36 159	99.88 73	99.99 23

test_cas_vis1_n_1920		96.59 149	96.23 144	97.65 173	98.22 189	94.23 224	99.99 5	97.25 305	97.77 21	99.58 58	99.08 157	77.10 319	99.97 57	97.64 154	99.45 115	98.74 230

UA-Net		96.54 150	95.96 157	98.27 136	98.23 188	95.71 174	98.00 356	98.45 128	93.72 168	98.41 132	99.27 143	88.71 211	99.66 154	91.19 270	97.69 175	99.44 171

EPMVS		96.53 151	96.01 150	98.09 146	98.43 173	96.12 162	96.36 384	99.43 20	93.53 171	97.64 161	95.04 349	94.41 80	98.38 242	91.13 271	98.11 167	99.75 107

test-LLR		96.47 152	96.04 149	97.78 164	97.02 264	95.44 185	99.96 39	98.21 199	94.07 148	95.55 215	96.38 293	93.90 103	98.27 255	90.42 288	98.83 144	99.64 125

MVS_Test		96.46 153	95.74 166	98.61 106	98.18 193	97.23 111	99.31 249	97.15 314	91.07 264	98.84 107	97.05 272	88.17 215	98.97 196	94.39 217	97.50 179	99.61 135

casdiffmvs_mvg		96.43 154	95.94 159	97.89 160	97.44 244	95.47 184	99.86 125	97.29 301	93.35 176	96.03 205	99.19 151	85.39 246	98.72 214	97.89 143	97.04 191	99.49 165
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		96.43 154	95.98 153	97.76 168	97.34 251	95.17 200	99.51 218	97.17 311	93.92 158	96.90 183	99.28 140	85.37 247	98.64 220	97.50 157	96.86 197	99.46 167

casdiffmvs		96.42 156	95.97 156	97.77 166	97.30 255	94.98 202	99.84 133	97.09 322	93.75 167	96.58 192	99.26 146	85.07 249	98.78 207	97.77 151	97.04 191	99.54 152
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_fmvsmconf0.01_n		96.39 157	95.74 166	98.32 133	91.47 387	95.56 182	99.84 133	97.30 298	97.74 22	97.89 154	99.35 138	79.62 301	99.85 115	99.25 61	99.24 127	99.55 148

test-mter		96.39 157	95.93 160	97.78 164	97.02 264	95.44 185	99.96 39	98.21 199	91.81 240	95.55 215	96.38 293	95.17 55	98.27 255	90.42 288	98.83 144	99.64 125

CDS-MVSNet		96.34 159	96.07 148	97.13 199	97.37 249	94.96 203	99.53 215	97.91 234	91.55 246	95.37 219	98.32 231	95.05 60	97.13 311	93.80 233	95.75 223	99.30 190
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Vis-MVSNet (Re-imp)		96.32 160	95.98 153	97.35 194	97.93 209	94.82 208	99.47 226	98.15 212	91.83 238	95.09 222	99.11 155	91.37 165	97.47 293	93.47 241	97.43 180	99.74 108

3Dnovator+	91.53 11	96.31 161	95.24 181	99.52 28	96.88 274	98.64 54	99.72 178	98.24 195	95.27 102	88.42 322	98.98 168	82.76 268	99.94 83	97.10 166	99.83 77	99.96 67

Effi-MVS+		96.30 162	95.69 168	98.16 140	97.85 214	96.26 151	97.41 365	97.21 307	90.37 280	98.65 121	98.58 213	86.61 235	98.70 216	97.11 165	97.37 184	99.52 158

IS-MVSNet		96.29 163	95.90 162	97.45 185	98.13 198	94.80 209	99.08 271	97.61 263	92.02 234	95.54 217	98.96 172	90.64 181	98.08 266	93.73 237	97.41 183	99.47 166

3Dnovator	91.47 12	96.28 164	95.34 178	99.08 71	96.82 277	97.47 102	99.45 231	98.81 62	95.52 96	89.39 296	99.00 165	81.97 272	99.95 75	97.27 161	99.83 77	99.84 94

tpmrst		96.27 165	95.98 153	97.13 199	97.96 207	93.15 251	96.34 385	98.17 204	92.07 230	98.71 118	95.12 346	93.91 102	98.73 212	94.91 205	96.62 198	99.50 163

RRT-MVS		96.24 166	95.68 170	97.94 155	97.65 232	94.92 205	99.27 257	97.10 319	92.79 200	97.43 167	97.99 244	81.85 274	99.37 174	98.46 112	98.57 150	99.53 156

CostFormer		96.10 167	95.88 163	96.78 209	97.03 263	92.55 268	97.08 373	97.83 242	90.04 289	98.72 117	94.89 356	95.01 62	98.29 251	96.54 179	95.77 221	99.50 163

PVSNet_BlendedMVS		96.05 168	95.82 165	96.72 212	99.59 85	96.99 123	99.95 58	99.10 32	94.06 150	98.27 139	95.80 310	89.00 207	99.95 75	99.12 65	87.53 303	93.24 363

PatchMatch-RL		96.04 169	95.40 175	97.95 152	99.59 85	95.22 197	99.52 216	99.07 35	93.96 155	96.49 194	98.35 228	82.28 270	99.82 127	90.15 293	99.22 129	98.81 226

1112_ss		96.01 170	95.20 183	98.42 128	97.80 217	96.41 144	99.65 192	96.66 359	92.71 203	92.88 250	99.40 132	92.16 153	99.30 175	91.92 262	93.66 254	99.55 148

UWE-MVS-28		95.95 171	96.49 136	94.34 291	98.51 167	89.99 325	99.39 238	98.57 94	93.14 185	97.33 170	98.31 233	93.44 113	94.68 388	93.69 239	95.98 213	98.34 243

PatchmatchNet		95.94 172	95.45 174	97.39 190	97.83 215	94.41 217	96.05 391	98.40 162	92.86 194	97.09 177	95.28 341	94.21 94	98.07 268	89.26 301	98.11 167	99.70 114
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
FA-MVS(test-final)		95.86 173	95.09 187	98.15 143	97.74 221	95.62 180	96.31 386	98.17 204	91.42 254	96.26 201	96.13 303	90.56 183	99.47 171	92.18 258	97.07 189	99.35 183

TAMVS		95.85 174	95.58 172	96.65 215	97.07 261	93.50 244	99.17 265	97.82 243	91.39 256	95.02 223	98.01 241	92.20 152	97.30 301	93.75 236	95.83 220	99.14 205

LS3D		95.84 175	95.11 186	98.02 150	99.85 54	95.10 201	98.74 314	98.50 122	87.22 337	93.66 239	99.86 29	87.45 223	99.95 75	90.94 277	99.81 83	99.02 215

baseline1		95.78 176	94.86 194	98.54 116	98.47 172	98.07 72	99.06 276	97.99 223	92.68 206	94.13 235	98.62 209	93.28 121	98.69 217	93.79 234	85.76 311	98.84 224

Test_1112_low_res		95.72 177	94.83 195	98.42 128	97.79 218	96.41 144	99.65 192	96.65 360	92.70 204	92.86 251	96.13 303	92.15 154	99.30 175	91.88 263	93.64 255	99.55 148

Vis-MVSNet		95.72 177	95.15 185	97.45 185	97.62 234	94.28 222	99.28 255	98.24 195	94.27 142	96.84 185	98.94 179	79.39 303	98.76 209	93.25 243	98.49 152	99.30 190
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
EPNet_dtu		95.71 179	95.39 176	96.66 214	98.92 133	93.41 247	99.57 208	98.90 48	96.19 81	97.52 163	98.56 215	92.65 138	97.36 295	77.89 386	98.33 156	99.20 200
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
BH-w/o		95.71 179	95.38 177	96.68 213	98.49 171	92.28 272	99.84 133	97.50 277	92.12 229	92.06 260	98.79 193	84.69 253	98.67 219	95.29 196	99.66 91	99.09 209

FE-MVS		95.70 181	95.01 191	97.79 163	98.21 190	94.57 212	95.03 398	98.69 71	88.90 309	97.50 165	96.19 300	92.60 141	99.49 168	89.99 295	97.94 173	99.31 188

ECVR-MVS		95.66 182	95.05 189	97.51 183	98.66 153	93.71 237	98.85 306	98.45 128	94.93 107	96.86 184	98.96 172	75.22 342	99.20 183	95.34 194	98.15 164	99.64 125

mvs_anonymous		95.65 183	95.03 190	97.53 181	98.19 192	95.74 172	99.33 246	97.49 278	90.87 268	90.47 274	97.10 268	88.23 214	97.16 308	95.92 187	97.66 177	99.68 117

test1111		95.57 184	94.98 192	97.37 191	98.56 159	93.37 249	98.86 304	98.45 128	94.95 106	96.63 190	98.95 177	75.21 343	99.11 189	95.02 199	98.14 166	99.64 125

MVSTER		95.53 185	95.22 182	96.45 219	98.56 159	97.72 88	99.91 93	97.67 253	92.38 223	91.39 264	97.14 266	97.24 18	97.30 301	94.80 208	87.85 298	94.34 299

tpm2		95.47 186	95.18 184	96.35 224	96.91 270	91.70 290	96.96 376	97.93 230	88.04 326	98.44 130	95.40 330	93.32 118	97.97 272	94.00 225	95.61 225	99.38 176

test_vis1_n_1920		95.44 187	95.31 179	95.82 238	98.50 169	88.74 341	99.98 16	97.30 298	97.84 20	99.85 11	99.19 151	66.82 380	99.97 57	98.82 88	99.46 114	98.76 228

QAPM		95.40 188	94.17 210	99.10 68	96.92 269	97.71 89	99.40 234	98.68 73	89.31 297	88.94 309	98.89 182	82.48 269	99.96 67	93.12 249	99.83 77	99.62 131

reproduce_monomvs		95.38 189	95.07 188	96.32 225	99.32 104	96.60 137	99.76 160	98.85 57	96.65 63	87.83 328	96.05 307	99.52 1	98.11 264	96.58 178	81.07 352	94.25 304

test_fmvs1		95.35 190	95.68 170	94.36 290	98.99 123	84.98 374	99.96 39	96.65 360	97.60 26	99.73 36	98.96 172	71.58 359	99.93 91	98.31 120	99.37 121	98.17 245

UGNet		95.33 191	94.57 200	97.62 177	98.55 162	94.85 206	98.67 322	99.32 26	95.75 89	96.80 187	96.27 298	72.18 356	99.96 67	94.58 215	99.05 136	98.04 249
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
mamv4		95.24 192	96.90 116	90.25 364	98.65 155	72.11 411	98.28 343	97.64 256	89.99 290	95.93 208	98.25 234	94.74 70	99.11 189	99.01 76	99.64 92	99.53 156

BH-untuned		95.18 193	94.83 195	96.22 227	98.36 178	91.22 298	99.80 149	97.32 296	90.91 267	91.08 267	98.67 202	83.51 262	98.54 225	94.23 223	99.61 99	98.92 219

BH-RMVSNet		95.18 193	94.31 207	97.80 161	98.17 194	95.23 196	99.76 160	97.53 273	92.52 217	94.27 233	99.25 147	76.84 324	98.80 205	90.89 279	99.54 104	99.35 183

PCF-MVS	94.20 5	95.18 193	94.10 211	98.43 126	98.55 162	95.99 164	97.91 358	97.31 297	90.35 281	89.48 295	99.22 149	85.19 248	99.89 103	90.40 290	98.47 153	99.41 174
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
dp		95.05 196	94.43 202	96.91 205	97.99 205	92.73 262	96.29 387	97.98 225	89.70 294	95.93 208	94.67 362	93.83 107	98.45 231	86.91 333	96.53 200	99.54 152

Fast-Effi-MVS+		95.02 197	94.19 209	97.52 182	97.88 211	94.55 213	99.97 32	97.08 323	88.85 311	94.47 229	97.96 246	84.59 254	98.41 234	89.84 297	97.10 188	99.59 138

IB-MVS	92.85 6	94.99 198	93.94 217	98.16 140	97.72 226	95.69 177	99.99 5	98.81 62	94.28 140	92.70 252	96.90 276	95.08 58	99.17 186	96.07 184	73.88 391	99.60 137
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
h-mvs33		94.92 199	94.36 204	96.59 216	98.85 142	91.29 297	98.93 294	98.94 42	95.90 84	98.77 112	98.42 226	90.89 178	99.77 135	97.80 146	70.76 397	98.72 232

MonoMVSNet		94.82 200	94.43 202	95.98 232	94.54 334	90.73 307	99.03 283	97.06 325	93.16 184	93.15 245	95.47 327	88.29 213	97.57 289	97.85 144	91.33 268	99.62 131

XVG-OURS		94.82 200	94.74 198	95.06 258	98.00 204	89.19 335	99.08 271	97.55 269	94.10 146	94.71 225	99.62 108	80.51 294	99.74 141	96.04 185	93.06 263	96.25 273

SDMVSNet		94.80 202	93.96 216	97.33 195	98.92 133	95.42 187	99.59 203	98.99 38	92.41 221	92.55 254	97.85 250	75.81 336	98.93 200	97.90 142	91.62 266	97.64 257

ADS-MVSNet		94.79 203	94.02 214	97.11 201	97.87 212	93.79 234	94.24 399	98.16 209	90.07 287	96.43 196	94.48 367	90.29 189	98.19 260	87.44 320	97.23 185	99.36 180

XVG-OURS-SEG-HR		94.79 203	94.70 199	95.08 257	98.05 202	89.19 335	99.08 271	97.54 271	93.66 169	94.87 224	99.58 113	78.78 310	99.79 130	97.31 160	93.40 258	96.25 273

OpenMVS	90.15 15	94.77 205	93.59 225	98.33 132	96.07 294	97.48 101	99.56 210	98.57 94	90.46 278	86.51 346	98.95 177	78.57 313	99.94 83	93.86 228	99.74 86	97.57 261

LFMVS		94.75 206	93.56 227	98.30 134	99.03 118	95.70 175	98.74 314	97.98 225	87.81 330	98.47 129	99.39 134	67.43 378	99.53 158	98.01 134	95.20 235	99.67 119

SCA		94.69 207	93.81 221	97.33 195	97.10 260	94.44 214	98.86 304	98.32 182	93.30 179	96.17 204	95.59 319	76.48 329	97.95 275	91.06 273	97.43 180	99.59 138

ab-mvs		94.69 207	93.42 231	98.51 120	98.07 201	96.26 151	96.49 382	98.68 73	90.31 283	94.54 226	97.00 274	76.30 331	99.71 145	95.98 186	93.38 259	99.56 147

CVMVSNet		94.68 209	94.94 193	93.89 309	96.80 278	86.92 362	99.06 276	98.98 39	94.45 125	94.23 234	99.02 161	85.60 242	95.31 379	90.91 278	95.39 230	99.43 172

cascas		94.64 210	93.61 222	97.74 170	97.82 216	96.26 151	99.96 39	97.78 246	85.76 355	94.00 236	97.54 256	76.95 323	99.21 180	97.23 162	95.43 229	97.76 256

HQP-MVS		94.61 211	94.50 201	94.92 263	95.78 302	91.85 282	99.87 114	97.89 235	96.82 55	93.37 241	98.65 205	80.65 292	98.39 238	97.92 140	89.60 271	94.53 281

TR-MVS		94.54 212	93.56 227	97.49 184	97.96 207	94.34 221	98.71 317	97.51 276	90.30 284	94.51 228	98.69 201	75.56 337	98.77 208	92.82 252	95.99 212	99.35 183

DP-MVS		94.54 212	93.42 231	97.91 158	99.46 98	94.04 228	98.93 294	97.48 279	81.15 390	90.04 278	99.55 117	87.02 229	99.95 75	88.97 303	98.11 167	99.73 109

Effi-MVS+-dtu		94.53 214	95.30 180	92.22 343	97.77 219	82.54 387	99.59 203	97.06 325	94.92 109	95.29 220	95.37 334	85.81 241	97.89 278	94.80 208	97.07 189	96.23 275

WBMVS		94.52 215	94.03 213	95.98 232	98.38 175	96.68 133	99.92 85	97.63 257	90.75 274	89.64 291	95.25 342	96.77 25	96.90 328	94.35 220	83.57 330	94.35 297

HQP_MVS		94.49 216	94.36 204	94.87 264	95.71 312	91.74 286	99.84 133	97.87 237	96.38 73	93.01 246	98.59 210	80.47 296	98.37 244	97.79 149	89.55 274	94.52 283

myMVS_eth3d		94.46 217	94.76 197	93.55 319	97.68 229	90.97 300	99.71 181	98.35 175	90.79 271	92.10 258	98.67 202	92.46 147	93.09 402	87.13 326	95.95 216	96.59 271

TAPA-MVS	92.12 8	94.42 218	93.60 224	96.90 206	99.33 102	91.78 285	99.78 152	98.00 222	89.89 292	94.52 227	99.47 123	91.97 158	99.18 185	69.90 405	99.52 106	99.73 109
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
hse-mvs2		94.38 219	94.08 212	95.31 252	98.27 186	90.02 324	99.29 254	98.56 98	95.90 84	98.77 112	98.00 242	90.89 178	98.26 257	97.80 146	69.20 403	97.64 257

ET-MVSNet_ETH3D		94.37 220	93.28 237	97.64 174	98.30 182	97.99 77	99.99 5	97.61 263	94.35 134	71.57 409	99.45 126	96.23 35	95.34 378	96.91 175	85.14 318	99.59 138

MSDG		94.37 220	93.36 235	97.40 189	98.88 140	93.95 232	99.37 242	97.38 288	85.75 357	90.80 271	99.17 153	84.11 260	99.88 109	86.35 334	98.43 154	98.36 242

GeoE		94.36 222	93.48 229	96.99 203	97.29 256	93.54 243	99.96 39	96.72 357	88.35 322	93.43 240	98.94 179	82.05 271	98.05 269	88.12 315	96.48 203	99.37 178

miper_enhance_ethall		94.36 222	93.98 215	95.49 243	98.68 151	95.24 195	99.73 174	97.29 301	93.28 180	89.86 283	95.97 308	94.37 85	97.05 317	92.20 257	84.45 323	94.19 309

tpmvs		94.28 224	93.57 226	96.40 221	98.55 162	91.50 295	95.70 397	98.55 104	87.47 332	92.15 257	94.26 372	91.42 163	98.95 199	88.15 313	95.85 219	98.76 228

test_fmvs1_n		94.25 225	94.36 204	93.92 306	97.68 229	83.70 381	99.90 99	96.57 363	97.40 32	99.67 42	98.88 183	61.82 399	99.92 95	98.23 123	99.13 132	98.14 248

FIs		94.10 226	93.43 230	96.11 229	94.70 331	96.82 129	99.58 205	98.93 46	92.54 215	89.34 298	97.31 262	87.62 221	97.10 314	94.22 224	86.58 307	94.40 292

CLD-MVS		94.06 227	93.90 218	94.55 279	96.02 296	90.69 308	99.98 16	97.72 249	96.62 66	91.05 269	98.85 191	77.21 318	98.47 227	98.11 129	89.51 276	94.48 285
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
testing3		93.92 228	94.23 208	92.99 333	97.54 238	90.23 319	99.99 5	99.16 31	90.57 276	91.33 266	98.63 208	92.99 129	92.52 406	82.46 362	95.39 230	96.22 276

test0.0.03 1		93.86 229	93.61 222	94.64 273	95.02 327	92.18 275	99.93 82	98.58 92	94.07 148	87.96 326	98.50 218	93.90 103	94.96 383	81.33 369	93.17 260	96.78 268

X-MVStestdata		93.83 230	92.06 263	99.15 60	99.94 13	97.50 99	99.94 75	98.42 153	96.22 79	99.41 74	41.37 432	94.34 86	99.96 67	98.92 81	99.95 50	99.99 23

GA-MVS		93.83 230	92.84 243	96.80 208	95.73 309	93.57 241	99.88 111	97.24 306	92.57 214	92.92 248	96.66 285	78.73 311	97.67 286	87.75 318	94.06 250	99.17 201

FC-MVSNet-test		93.81 232	93.15 239	95.80 239	94.30 339	96.20 156	99.42 233	98.89 50	92.33 225	89.03 308	97.27 264	87.39 224	96.83 335	93.20 244	86.48 308	94.36 294

ADS-MVSNet2		93.80 233	93.88 219	93.55 319	97.87 212	85.94 368	94.24 399	96.84 348	90.07 287	96.43 196	94.48 367	90.29 189	95.37 377	87.44 320	97.23 185	99.36 180

cl22		93.77 234	93.25 238	95.33 251	99.49 95	94.43 215	99.61 201	98.09 215	90.38 279	89.16 306	95.61 317	90.56 183	97.34 297	91.93 261	84.45 323	94.21 308

VDD-MVS		93.77 234	92.94 242	96.27 226	98.55 162	90.22 320	98.77 313	97.79 244	90.85 269	96.82 186	99.42 127	61.18 402	99.77 135	98.95 77	94.13 248	98.82 225

EI-MVSNet		93.73 236	93.40 234	94.74 269	96.80 278	92.69 263	99.06 276	97.67 253	88.96 306	91.39 264	99.02 161	88.75 210	97.30 301	91.07 272	87.85 298	94.22 306

Fast-Effi-MVS+-dtu		93.72 237	93.86 220	93.29 324	97.06 262	86.16 365	99.80 149	96.83 349	92.66 207	92.58 253	97.83 252	81.39 280	97.67 286	89.75 298	96.87 196	96.05 278

tpm		93.70 238	93.41 233	94.58 277	95.36 322	87.41 357	97.01 374	96.90 344	90.85 269	96.72 189	94.14 373	90.40 186	96.84 333	90.75 282	88.54 290	99.51 161

PS-MVSNAJss		93.64 239	93.31 236	94.61 274	92.11 378	92.19 274	99.12 267	97.38 288	92.51 218	88.45 317	96.99 275	91.20 167	97.29 304	94.36 218	87.71 300	94.36 294

test_vis1_n		93.61 240	93.03 241	95.35 249	95.86 301	86.94 361	99.87 114	96.36 369	96.85 53	99.54 61	98.79 193	52.41 412	99.83 125	98.64 101	98.97 138	99.29 192

sd_testset		93.55 241	92.83 244	95.74 240	98.92 133	90.89 305	98.24 345	98.85 57	92.41 221	92.55 254	97.85 250	71.07 364	98.68 218	93.93 226	91.62 266	97.64 257

gg-mvs-nofinetune		93.51 242	91.86 268	98.47 122	97.72 226	97.96 81	92.62 407	98.51 116	74.70 409	97.33 170	69.59 423	98.91 4	97.79 281	97.77 151	99.56 103	99.67 119

nrg030		93.51 242	92.53 255	96.45 219	94.36 337	97.20 112	99.81 145	97.16 313	91.60 244	89.86 283	97.46 257	86.37 237	97.68 285	95.88 188	80.31 360	94.46 286

tpm cat1		93.51 242	92.52 256	96.47 217	97.77 219	91.47 296	96.13 389	98.06 218	80.98 391	92.91 249	93.78 376	89.66 194	98.87 201	87.03 329	96.39 205	99.09 209

CR-MVSNet		93.45 245	92.62 249	95.94 234	96.29 288	92.66 264	92.01 410	96.23 371	92.62 209	96.94 181	93.31 381	91.04 172	96.03 367	79.23 378	95.96 214	99.13 206

AUN-MVS		93.28 246	92.60 250	95.34 250	98.29 183	90.09 323	99.31 249	98.56 98	91.80 241	96.35 200	98.00 242	89.38 199	98.28 253	92.46 254	69.22 402	97.64 257

OPM-MVS		93.21 247	92.80 245	94.44 286	93.12 360	90.85 306	99.77 155	97.61 263	96.19 81	91.56 263	98.65 205	75.16 344	98.47 227	93.78 235	89.39 277	93.99 332
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
dmvs_re		93.20 248	93.15 239	93.34 322	96.54 286	83.81 380	98.71 317	98.51 116	91.39 256	92.37 256	98.56 215	78.66 312	97.83 280	93.89 227	89.74 270	98.38 241

kuosan		93.17 249	92.60 250	94.86 267	98.40 174	89.54 333	98.44 334	98.53 111	84.46 370	88.49 316	97.92 247	90.57 182	97.05 317	83.10 358	93.49 256	97.99 250

miper_ehance_all_eth		93.16 250	92.60 250	94.82 268	97.57 237	93.56 242	99.50 220	97.07 324	88.75 313	88.85 310	95.52 323	90.97 174	96.74 338	90.77 281	84.45 323	94.17 310

VDDNet		93.12 251	91.91 266	96.76 210	96.67 285	92.65 266	98.69 320	98.21 199	82.81 383	97.75 160	99.28 140	61.57 400	99.48 169	98.09 131	94.09 249	98.15 246

Anonymous202405211		93.10 252	91.99 264	96.40 221	99.10 114	89.65 331	98.88 300	97.93 230	83.71 375	94.00 236	98.75 195	68.79 369	99.88 109	95.08 198	91.71 265	99.68 117

UniMVSNet (Re)		93.07 253	92.13 260	95.88 235	94.84 328	96.24 155	99.88 111	98.98 39	92.49 219	89.25 300	95.40 330	87.09 228	97.14 310	93.13 248	78.16 371	94.26 302

LPG-MVS_test		92.96 254	92.71 248	93.71 313	95.43 320	88.67 343	99.75 164	97.62 260	92.81 197	90.05 276	98.49 219	75.24 340	98.40 236	95.84 189	89.12 278	94.07 324

UniMVSNet_NR-MVSNet		92.95 255	92.11 261	95.49 243	94.61 333	95.28 193	99.83 140	99.08 34	91.49 247	89.21 303	96.86 279	87.14 227	96.73 339	93.20 244	77.52 376	94.46 286

WB-MVSnew		92.90 256	92.77 247	93.26 326	96.95 268	93.63 240	99.71 181	98.16 209	91.49 247	94.28 232	98.14 237	81.33 282	96.48 348	79.47 377	95.46 227	89.68 403

ACMM	91.95 10	92.88 257	92.52 256	93.98 305	95.75 308	89.08 339	99.77 155	97.52 275	93.00 189	89.95 280	97.99 244	76.17 333	98.46 230	93.63 240	88.87 282	94.39 293
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_djsdf		92.83 258	92.29 259	94.47 284	91.90 381	92.46 269	99.55 212	97.27 303	91.17 259	89.96 279	96.07 306	81.10 284	96.89 329	94.67 213	88.91 280	94.05 326

D2MVS		92.76 259	92.59 254	93.27 325	95.13 323	89.54 333	99.69 186	99.38 22	92.26 226	87.59 331	94.61 364	85.05 250	97.79 281	91.59 266	88.01 296	92.47 376

ACMP	92.05 9	92.74 260	92.42 258	93.73 311	95.91 300	88.72 342	99.81 145	97.53 273	94.13 144	87.00 340	98.23 235	74.07 350	98.47 227	96.22 183	88.86 283	93.99 332
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
VPA-MVSNet		92.70 261	91.55 273	96.16 228	95.09 324	96.20 156	98.88 300	99.00 37	91.02 266	91.82 261	95.29 340	76.05 335	97.96 274	95.62 193	81.19 347	94.30 300

FMVSNet3		92.69 262	91.58 271	95.99 231	98.29 183	97.42 104	99.26 258	97.62 260	89.80 293	89.68 287	95.32 336	81.62 279	96.27 357	87.01 330	85.65 312	94.29 301

IterMVS-LS		92.69 262	92.11 261	94.43 288	96.80 278	92.74 260	99.45 231	96.89 345	88.98 304	89.65 290	95.38 333	88.77 209	96.34 354	90.98 276	82.04 341	94.22 306
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Patchmatch-test		92.65 264	91.50 274	96.10 230	96.85 275	90.49 314	91.50 412	97.19 308	82.76 384	90.23 275	95.59 319	95.02 61	98.00 271	77.41 388	96.98 194	99.82 96

c3_l		92.53 265	91.87 267	94.52 280	97.40 247	92.99 256	99.40 234	96.93 342	87.86 328	88.69 313	95.44 328	89.95 192	96.44 350	90.45 287	80.69 357	94.14 319

AllTest		92.48 266	91.64 269	95.00 260	99.01 119	88.43 347	98.94 292	96.82 351	86.50 346	88.71 311	98.47 223	74.73 346	99.88 109	85.39 342	96.18 208	96.71 269

DU-MVS		92.46 267	91.45 276	95.49 243	94.05 343	95.28 193	99.81 145	98.74 67	92.25 227	89.21 303	96.64 287	81.66 277	96.73 339	93.20 244	77.52 376	94.46 286

eth_miper_zixun_eth		92.41 268	91.93 265	93.84 310	97.28 257	90.68 309	98.83 307	96.97 336	88.57 318	89.19 305	95.73 314	89.24 204	96.69 341	89.97 296	81.55 344	94.15 316

DIV-MVS_self_test		92.32 269	91.60 270	94.47 284	97.31 254	92.74 260	99.58 205	96.75 355	86.99 341	87.64 330	95.54 321	89.55 197	96.50 347	88.58 307	82.44 338	94.17 310

cl____		92.31 270	91.58 271	94.52 280	97.33 253	92.77 258	99.57 208	96.78 354	86.97 342	87.56 332	95.51 324	89.43 198	96.62 343	88.60 306	82.44 338	94.16 315

LCM-MVSNet-Re		92.31 270	92.60 250	91.43 352	97.53 239	79.27 404	99.02 285	91.83 419	92.07 230	80.31 384	94.38 370	83.50 263	95.48 375	97.22 163	97.58 178	99.54 152

WR-MVS		92.31 270	91.25 278	95.48 246	94.45 336	95.29 192	99.60 202	98.68 73	90.10 286	88.07 325	96.89 277	80.68 291	96.80 337	93.14 247	79.67 364	94.36 294

COLMAP_ROB	90.47 14	92.18 273	91.49 275	94.25 294	99.00 122	88.04 353	98.42 338	96.70 358	82.30 386	88.43 320	99.01 163	76.97 322	99.85 115	86.11 338	96.50 201	94.86 280
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Anonymous20240529		92.10 274	90.65 286	96.47 217	98.82 143	90.61 311	98.72 316	98.67 76	75.54 406	93.90 238	98.58 213	66.23 382	99.90 98	94.70 212	90.67 269	98.90 222

pmmvs4		92.10 274	91.07 282	95.18 255	92.82 369	94.96 203	99.48 225	96.83 349	87.45 333	88.66 314	96.56 291	83.78 261	96.83 335	89.29 300	84.77 321	93.75 348

jajsoiax		91.92 276	91.18 279	94.15 295	91.35 388	90.95 303	99.00 286	97.42 284	92.61 210	87.38 336	97.08 269	72.46 355	97.36 295	94.53 216	88.77 284	94.13 321

XXY-MVS		91.82 277	90.46 289	95.88 235	93.91 346	95.40 189	98.87 303	97.69 252	88.63 317	87.87 327	97.08 269	74.38 349	97.89 278	91.66 265	84.07 327	94.35 297

miper_lstm_enhance		91.81 278	91.39 277	93.06 332	97.34 251	89.18 337	99.38 240	96.79 353	86.70 345	87.47 334	95.22 343	90.00 191	95.86 371	88.26 311	81.37 346	94.15 316

mvs_tets		91.81 278	91.08 281	94.00 303	91.63 385	90.58 312	98.67 322	97.43 282	92.43 220	87.37 337	97.05 272	71.76 357	97.32 299	94.75 210	88.68 286	94.11 322

VPNet		91.81 278	90.46 289	95.85 237	94.74 330	95.54 183	98.98 287	98.59 90	92.14 228	90.77 272	97.44 258	68.73 371	97.54 291	94.89 206	77.89 373	94.46 286

RPSCF		91.80 281	92.79 246	88.83 375	98.15 196	69.87 413	98.11 352	96.60 362	83.93 373	94.33 231	99.27 143	79.60 302	99.46 172	91.99 260	93.16 261	97.18 266

PVSNet_0	88.03 19	91.80 281	90.27 295	96.38 223	98.27 186	90.46 315	99.94 75	99.61 13	93.99 153	86.26 352	97.39 261	71.13 363	99.89 103	98.77 92	67.05 408	98.79 227

anonymousdsp		91.79 283	90.92 283	94.41 289	90.76 393	92.93 257	98.93 294	97.17 311	89.08 299	87.46 335	95.30 337	78.43 316	96.92 327	92.38 255	88.73 285	93.39 359

JIA-IIPM		91.76 284	90.70 285	94.94 262	96.11 293	87.51 356	93.16 406	98.13 214	75.79 405	97.58 162	77.68 420	92.84 134	97.97 272	88.47 310	96.54 199	99.33 186

TranMVSNet+NR-MVSNet		91.68 285	90.61 288	94.87 264	93.69 350	93.98 231	99.69 186	98.65 77	91.03 265	88.44 318	96.83 283	80.05 299	96.18 360	90.26 292	76.89 384	94.45 291

NR-MVSNet		91.56 286	90.22 296	95.60 241	94.05 343	95.76 171	98.25 344	98.70 70	91.16 261	80.78 383	96.64 287	83.23 266	96.57 345	91.41 267	77.73 375	94.46 286

dongtai		91.55 287	91.13 280	92.82 336	98.16 195	86.35 364	99.47 226	98.51 116	83.24 378	85.07 361	97.56 255	90.33 187	94.94 384	76.09 394	91.73 264	97.18 266

v2v482		91.30 288	90.07 302	95.01 259	93.13 358	93.79 234	99.77 155	97.02 329	88.05 325	89.25 300	95.37 334	80.73 290	97.15 309	87.28 324	80.04 363	94.09 323

WR-MVS_H		91.30 288	90.35 292	94.15 295	94.17 342	92.62 267	99.17 265	98.94 42	88.87 310	86.48 348	94.46 369	84.36 256	96.61 344	88.19 312	78.51 369	93.21 364

tt0805		91.28 290	90.18 298	94.60 275	96.26 290	87.55 355	98.39 339	98.72 68	89.00 303	89.22 302	98.47 223	62.98 395	98.96 198	90.57 284	88.00 297	97.28 265

V42		91.28 290	90.12 301	94.74 269	93.42 355	93.46 245	99.68 188	97.02 329	87.36 334	89.85 285	95.05 348	81.31 283	97.34 297	87.34 323	80.07 362	93.40 358

CP-MVSNet		91.23 292	90.22 296	94.26 293	93.96 345	92.39 271	99.09 269	98.57 94	88.95 307	86.42 349	96.57 290	79.19 306	96.37 352	90.29 291	78.95 366	94.02 327

XVG-ACMP-BASELINE		91.22 293	90.75 284	92.63 339	93.73 349	85.61 369	98.52 331	97.44 281	92.77 201	89.90 282	96.85 280	66.64 381	98.39 238	92.29 256	88.61 287	93.89 340

v1144		91.09 294	89.83 303	94.87 264	93.25 357	93.69 239	99.62 199	96.98 334	86.83 344	89.64 291	94.99 353	80.94 286	97.05 317	85.08 346	81.16 348	93.87 342

FMVSNet2		91.02 295	89.56 309	95.41 248	97.53 239	95.74 172	98.98 287	97.41 286	87.05 338	88.43 320	95.00 352	71.34 360	96.24 359	85.12 345	85.21 317	94.25 304

MVP-Stereo		90.93 296	90.45 291	92.37 342	91.25 390	88.76 340	98.05 355	96.17 373	87.27 336	84.04 365	95.30 337	78.46 315	97.27 306	83.78 354	99.70 89	91.09 387
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
IterMVS		90.91 297	90.17 299	93.12 329	96.78 281	90.42 317	98.89 298	97.05 328	89.03 301	86.49 347	95.42 329	76.59 327	95.02 381	87.22 325	84.09 326	93.93 337
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		90.88 298	89.82 304	94.08 298	97.53 239	91.97 277	98.43 335	96.95 337	87.05 338	89.68 287	94.72 358	71.34 360	96.11 362	87.01 330	85.65 312	94.17 310

test1		90.88 298	89.82 304	94.08 298	97.53 239	91.97 277	98.43 335	96.95 337	87.05 338	89.68 287	94.72 358	71.34 360	96.11 362	87.01 330	85.65 312	94.17 310

IterMVS-SCA-FT		90.85 300	90.16 300	92.93 334	96.72 283	89.96 326	98.89 298	96.99 332	88.95 307	86.63 344	95.67 315	76.48 329	95.00 382	87.04 328	84.04 329	93.84 344

v144192		90.79 301	89.52 311	94.59 276	93.11 361	92.77 258	99.56 210	96.99 332	86.38 348	89.82 286	94.95 355	80.50 295	97.10 314	83.98 352	80.41 358	93.90 339

v148		90.70 302	89.63 307	93.92 306	92.97 364	90.97 300	99.75 164	96.89 345	87.51 331	88.27 323	95.01 350	81.67 276	97.04 320	87.40 322	77.17 381	93.75 348

MS-PatchMatch		90.65 303	90.30 294	91.71 351	94.22 341	85.50 371	98.24 345	97.70 250	88.67 315	86.42 349	96.37 295	67.82 376	98.03 270	83.62 355	99.62 95	91.60 384

ACMH	89.72 17	90.64 304	89.63 307	93.66 317	95.64 317	88.64 345	98.55 327	97.45 280	89.03 301	81.62 378	97.61 254	69.75 367	98.41 234	89.37 299	87.62 302	93.92 338
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PS-CasMVS		90.63 305	89.51 312	93.99 304	93.83 347	91.70 290	98.98 287	98.52 113	88.48 319	86.15 353	96.53 292	75.46 338	96.31 356	88.83 304	78.86 368	93.95 335

v1192		90.62 306	89.25 316	94.72 271	93.13 358	93.07 252	99.50 220	97.02 329	86.33 349	89.56 294	95.01 350	79.22 305	97.09 316	82.34 364	81.16 348	94.01 329

v8		90.54 307	89.17 317	94.66 272	93.43 354	93.40 248	99.20 262	96.94 341	85.76 355	87.56 332	94.51 365	81.96 273	97.19 307	84.94 347	78.25 370	93.38 360

v1921920		90.46 308	89.12 318	94.50 282	92.96 365	92.46 269	99.49 222	96.98 334	86.10 351	89.61 293	95.30 337	78.55 314	97.03 322	82.17 365	80.89 356	94.01 329

our_test_3		90.39 309	89.48 314	93.12 329	92.40 374	89.57 332	99.33 246	96.35 370	87.84 329	85.30 358	94.99 353	84.14 259	96.09 365	80.38 373	84.56 322	93.71 353

PatchT		90.38 310	88.75 326	95.25 254	95.99 297	90.16 321	91.22 414	97.54 271	76.80 401	97.26 173	86.01 414	91.88 159	96.07 366	66.16 413	95.91 218	99.51 161

ACMH+	89.98 16	90.35 311	89.54 310	92.78 338	95.99 297	86.12 366	98.81 309	97.18 310	89.38 296	83.14 371	97.76 253	68.42 373	98.43 232	89.11 302	86.05 310	93.78 347

Baseline_NR-MVSNet		90.33 312	89.51 312	92.81 337	92.84 367	89.95 327	99.77 155	93.94 409	84.69 369	89.04 307	95.66 316	81.66 277	96.52 346	90.99 275	76.98 382	91.97 382

MIMVSNet		90.30 313	88.67 327	95.17 256	96.45 287	91.64 292	92.39 408	97.15 314	85.99 352	90.50 273	93.19 383	66.95 379	94.86 386	82.01 366	93.43 257	99.01 216

LTVRE_ROB	88.28 18	90.29 314	89.05 321	94.02 301	95.08 325	90.15 322	97.19 369	97.43 282	84.91 367	83.99 367	97.06 271	74.00 351	98.28 253	84.08 350	87.71 300	93.62 354
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
v10		90.25 315	88.82 324	94.57 278	93.53 352	93.43 246	99.08 271	96.87 347	85.00 364	87.34 338	94.51 365	80.93 287	97.02 324	82.85 360	79.23 365	93.26 362

v1240		90.20 316	88.79 325	94.44 286	93.05 363	92.27 273	99.38 240	96.92 343	85.89 353	89.36 297	94.87 357	77.89 317	97.03 322	80.66 372	81.08 351	94.01 329

PEN-MVS		90.19 317	89.06 320	93.57 318	93.06 362	90.90 304	99.06 276	98.47 125	88.11 324	85.91 355	96.30 297	76.67 325	95.94 370	87.07 327	76.91 383	93.89 340

pmmvs5		90.17 318	89.09 319	93.40 321	92.10 379	89.77 330	99.74 167	95.58 386	85.88 354	87.24 339	95.74 312	73.41 353	96.48 348	88.54 308	83.56 331	93.95 335

EU-MVSNet		90.14 319	90.34 293	89.54 370	92.55 372	81.06 398	98.69 320	98.04 221	91.41 255	86.59 345	96.84 282	80.83 289	93.31 401	86.20 336	81.91 342	94.26 302

UniMVSNet_ETH3D		90.06 320	88.58 329	94.49 283	94.67 332	88.09 352	97.81 361	97.57 268	83.91 374	88.44 318	97.41 259	57.44 406	97.62 288	91.41 267	88.59 289	97.77 255

Syy-MVS		90.00 321	90.63 287	88.11 382	97.68 229	74.66 409	99.71 181	98.35 175	90.79 271	92.10 258	98.67 202	79.10 308	93.09 402	63.35 416	95.95 216	96.59 271

USDC		90.00 321	88.96 322	93.10 331	94.81 329	88.16 351	98.71 317	95.54 387	93.66 169	83.75 369	97.20 265	65.58 384	98.31 249	83.96 353	87.49 304	92.85 370

Anonymous20231211		89.86 323	88.44 331	94.13 297	98.93 130	90.68 309	98.54 329	98.26 192	76.28 402	86.73 342	95.54 321	70.60 365	97.56 290	90.82 280	80.27 361	94.15 316

OurMVSNet-221017-0		89.81 324	89.48 314	90.83 358	91.64 384	81.21 396	98.17 350	95.38 390	91.48 249	85.65 357	97.31 262	72.66 354	97.29 304	88.15 313	84.83 320	93.97 334

RPMNet		89.76 325	87.28 342	97.19 198	96.29 288	92.66 264	92.01 410	98.31 184	70.19 416	96.94 181	85.87 415	87.25 226	99.78 132	62.69 417	95.96 214	99.13 206

Patchmtry		89.70 326	88.49 330	93.33 323	96.24 291	89.94 329	91.37 413	96.23 371	78.22 399	87.69 329	93.31 381	91.04 172	96.03 367	80.18 376	82.10 340	94.02 327

v7n		89.65 327	88.29 333	93.72 312	92.22 376	90.56 313	99.07 275	97.10 319	85.42 362	86.73 342	94.72 358	80.06 298	97.13 311	81.14 370	78.12 372	93.49 356

SSC-MVS3.2		89.59 328	88.66 328	92.38 340	94.29 340	86.12 366	99.49 222	97.66 255	90.28 285	88.63 315	95.18 344	64.46 389	96.88 331	85.30 344	82.66 335	94.14 319

ppachtmachnet_test		89.58 329	88.35 332	93.25 327	92.40 374	90.44 316	99.33 246	96.73 356	85.49 360	85.90 356	95.77 311	81.09 285	96.00 369	76.00 395	82.49 337	93.30 361

test_fmvs2		89.47 330	89.70 306	88.77 378	94.54 334	75.74 406	99.83 140	94.70 402	94.71 117	91.08 267	96.82 284	54.46 409	97.78 283	92.87 251	88.27 293	92.80 371

DTE-MVSNet		89.40 331	88.24 334	92.88 335	92.66 371	89.95 327	99.10 268	98.22 198	87.29 335	85.12 360	96.22 299	76.27 332	95.30 380	83.56 356	75.74 388	93.41 357

pm-mvs1		89.36 332	87.81 338	94.01 302	93.40 356	91.93 280	98.62 325	96.48 367	86.25 350	83.86 368	96.14 302	73.68 352	97.04 320	86.16 337	75.73 389	93.04 367

tfpnnormal		89.29 333	87.61 340	94.34 291	94.35 338	94.13 227	98.95 291	98.94 42	83.94 372	84.47 364	95.51 324	74.84 345	97.39 294	77.05 391	80.41 358	91.48 386

LF4IMVS		89.25 334	88.85 323	90.45 363	92.81 370	81.19 397	98.12 351	94.79 399	91.44 251	86.29 351	97.11 267	65.30 387	98.11 264	88.53 309	85.25 316	92.07 379

testgi		89.01 335	88.04 336	91.90 347	93.49 353	84.89 375	99.73 174	95.66 384	93.89 162	85.14 359	98.17 236	59.68 403	94.66 389	77.73 387	88.88 281	96.16 277

SixPastTwentyTwo		88.73 336	88.01 337	90.88 355	91.85 382	82.24 389	98.22 348	95.18 395	88.97 305	82.26 374	96.89 277	71.75 358	96.67 342	84.00 351	82.98 332	93.72 352

mmtdpeth		88.52 337	87.75 339	90.85 357	95.71 312	83.47 383	98.94 292	94.85 397	88.78 312	97.19 175	89.58 400	63.29 393	98.97 196	98.54 106	62.86 416	90.10 399

FMVSNet1		88.50 338	86.64 345	94.08 298	95.62 319	91.97 277	98.43 335	96.95 337	83.00 381	86.08 354	94.72 358	59.09 404	96.11 362	81.82 368	84.07 327	94.17 310

FMVSNet5		88.32 339	87.47 341	90.88 355	96.90 273	88.39 349	97.28 367	95.68 383	82.60 385	84.67 363	92.40 389	79.83 300	91.16 411	76.39 393	81.51 345	93.09 365

DSMNet-mixed		88.28 340	88.24 334	88.42 380	89.64 401	75.38 408	98.06 354	89.86 423	85.59 359	88.20 324	92.14 391	76.15 334	91.95 409	78.46 384	96.05 211	97.92 251

ttmdpeth		88.23 341	87.06 344	91.75 350	89.91 400	87.35 358	98.92 297	95.73 381	87.92 327	84.02 366	96.31 296	68.23 375	96.84 333	86.33 335	76.12 386	91.06 388

K. test v3		88.05 342	87.24 343	90.47 362	91.82 383	82.23 390	98.96 290	97.42 284	89.05 300	76.93 399	95.60 318	68.49 372	95.42 376	85.87 341	81.01 354	93.75 348

KD-MVS_2432*1600		88.00 343	86.10 347	93.70 315	96.91 270	94.04 228	97.17 370	97.12 317	84.93 365	81.96 375	92.41 387	92.48 145	94.51 390	79.23 378	52.68 422	92.56 373

miper_refine_blended		88.00 343	86.10 347	93.70 315	96.91 270	94.04 228	97.17 370	97.12 317	84.93 365	81.96 375	92.41 387	92.48 145	94.51 390	79.23 378	52.68 422	92.56 373

TinyColmap		87.87 345	86.51 346	91.94 346	95.05 326	85.57 370	97.65 362	94.08 406	84.40 371	81.82 377	96.85 280	62.14 398	98.33 247	80.25 375	86.37 309	91.91 383

TransMVSNet (Re)		87.25 346	85.28 353	93.16 328	93.56 351	91.03 299	98.54 329	94.05 408	83.69 376	81.09 381	96.16 301	75.32 339	96.40 351	76.69 392	68.41 404	92.06 380

Patchmatch-RL test		86.90 347	85.98 351	89.67 369	84.45 412	75.59 407	89.71 418	92.43 416	86.89 343	77.83 396	90.94 395	94.22 92	93.63 398	87.75 318	69.61 399	99.79 101

test_vis1_rt		86.87 348	86.05 350	89.34 371	96.12 292	78.07 405	99.87 114	83.54 430	92.03 233	78.21 394	89.51 401	45.80 416	99.91 96	96.25 182	93.11 262	90.03 400

Anonymous20231206		86.32 349	85.42 352	89.02 374	89.11 403	80.53 402	99.05 280	95.28 391	85.43 361	82.82 372	93.92 374	74.40 348	93.44 400	66.99 410	81.83 343	93.08 366

MVS-HIRNet		86.22 350	83.19 363	95.31 252	96.71 284	90.29 318	92.12 409	97.33 295	62.85 417	86.82 341	70.37 422	69.37 368	97.49 292	75.12 396	97.99 172	98.15 246

pmmvs6		85.69 351	83.84 358	91.26 354	90.00 399	84.41 378	97.82 360	96.15 374	75.86 404	81.29 380	95.39 332	61.21 401	96.87 332	83.52 357	73.29 392	92.50 375

test_0402		85.58 352	83.94 357	90.50 361	93.81 348	85.04 373	98.55 327	95.20 394	76.01 403	79.72 388	95.13 345	64.15 391	96.26 358	66.04 414	86.88 306	90.21 397

UnsupCasMVSNet_eth		85.52 353	83.99 355	90.10 366	89.36 402	83.51 382	96.65 380	97.99 223	89.14 298	75.89 403	93.83 375	63.25 394	93.92 394	81.92 367	67.90 407	92.88 369

MDA-MVSNet_test_wron		85.51 354	83.32 362	92.10 344	90.96 391	88.58 346	99.20 262	96.52 365	79.70 396	57.12 422	92.69 385	79.11 307	93.86 396	77.10 390	77.46 378	93.86 343

YYNet1		85.50 355	83.33 361	92.00 345	90.89 392	88.38 350	99.22 261	96.55 364	79.60 397	57.26 421	92.72 384	79.09 309	93.78 397	77.25 389	77.37 379	93.84 344

EG-PatchMatch MVS		85.35 356	83.81 359	89.99 368	90.39 395	81.89 392	98.21 349	96.09 375	81.78 388	74.73 405	93.72 377	51.56 414	97.12 313	79.16 381	88.61 287	90.96 390

Anonymous20240521		85.15 357	83.81 359	89.16 373	88.32 404	82.69 385	98.80 311	95.74 380	79.72 395	81.53 379	90.99 394	65.38 386	94.16 392	72.69 400	81.11 350	90.63 394

MVStest1		85.03 358	82.76 367	91.83 348	92.95 366	89.16 338	98.57 326	94.82 398	71.68 414	68.54 414	95.11 347	83.17 267	95.66 373	74.69 397	65.32 411	90.65 393

mvs5depth		84.87 359	82.90 366	90.77 359	85.59 411	84.84 376	91.10 415	93.29 414	83.14 379	85.07 361	94.33 371	62.17 397	97.32 299	78.83 383	72.59 395	90.14 398

TDRefinement		84.76 360	82.56 368	91.38 353	74.58 426	84.80 377	97.36 366	94.56 403	84.73 368	80.21 385	96.12 305	63.56 392	98.39 238	87.92 316	63.97 414	90.95 391

CMPMVS	61.59 21	84.75 361	85.14 354	83.57 390	90.32 396	62.54 418	96.98 375	97.59 267	74.33 410	69.95 411	96.66 285	64.17 390	98.32 248	87.88 317	88.41 292	89.84 402
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test20.03		84.72 362	83.99 355	86.91 384	88.19 406	80.62 401	98.88 300	95.94 377	88.36 321	78.87 389	94.62 363	68.75 370	89.11 415	66.52 412	75.82 387	91.00 389

CL-MVSNet_self_test		84.50 363	83.15 364	88.53 379	86.00 409	81.79 393	98.82 308	97.35 291	85.12 363	83.62 370	90.91 396	76.66 326	91.40 410	69.53 406	60.36 419	92.40 377

new_pmnet		84.49 364	82.92 365	89.21 372	90.03 398	82.60 386	96.89 378	95.62 385	80.59 392	75.77 404	89.17 402	65.04 388	94.79 387	72.12 402	81.02 353	90.23 396

MDA-MVSNet-bldmvs		84.09 365	81.52 372	91.81 349	91.32 389	88.00 354	98.67 322	95.92 378	80.22 394	55.60 423	93.32 380	68.29 374	93.60 399	73.76 398	76.61 385	93.82 346

pmmvs-eth3d		84.03 366	81.97 370	90.20 365	84.15 413	87.09 360	98.10 353	94.73 401	83.05 380	74.10 407	87.77 409	65.56 385	94.01 393	81.08 371	69.24 401	89.49 406

dmvs_testset		83.79 367	86.07 349	76.94 397	92.14 377	48.60 432	96.75 379	90.27 422	89.48 295	78.65 391	98.55 217	79.25 304	86.65 420	66.85 411	82.69 334	95.57 279

OpenMVS_ROB	79.82 20	83.77 368	81.68 371	90.03 367	88.30 405	82.82 384	98.46 332	95.22 393	73.92 411	76.00 402	91.29 393	55.00 408	96.94 326	68.40 408	88.51 291	90.34 395

KD-MVS_self_test		83.59 369	82.06 369	88.20 381	86.93 407	80.70 400	97.21 368	96.38 368	82.87 382	82.49 373	88.97 403	67.63 377	92.32 407	73.75 399	62.30 418	91.58 385

MIMVSNet1		82.58 370	80.51 376	88.78 376	86.68 408	84.20 379	96.65 380	95.41 389	78.75 398	78.59 392	92.44 386	51.88 413	89.76 414	65.26 415	78.95 366	92.38 378

mvsany_test3		82.12 371	81.14 373	85.06 388	81.87 417	70.41 412	97.09 372	92.14 417	91.27 258	77.84 395	88.73 404	39.31 419	95.49 374	90.75 282	71.24 396	89.29 408

new-patchmatchnet		81.19 372	79.34 379	86.76 385	82.86 416	80.36 403	97.92 357	95.27 392	82.09 387	72.02 408	86.87 411	62.81 396	90.74 413	71.10 403	63.08 415	89.19 409

APD_test1		81.15 373	80.92 374	81.86 393	92.45 373	59.76 422	96.04 392	93.61 412	73.29 412	77.06 397	96.64 287	44.28 418	96.16 361	72.35 401	82.52 336	89.67 404

test_method		80.79 374	79.70 378	84.08 389	92.83 368	67.06 415	99.51 218	95.42 388	54.34 421	81.07 382	93.53 378	44.48 417	92.22 408	78.90 382	77.23 380	92.94 368

PM-MVS		80.47 375	78.88 380	85.26 387	83.79 415	72.22 410	95.89 395	91.08 420	85.71 358	76.56 401	88.30 405	36.64 420	93.90 395	82.39 363	69.57 400	89.66 405

pmmvs3		80.27 376	77.77 381	87.76 383	80.32 421	82.43 388	98.23 347	91.97 418	72.74 413	78.75 390	87.97 408	57.30 407	90.99 412	70.31 404	62.37 417	89.87 401

N_pmnet		80.06 377	80.78 375	77.89 396	91.94 380	45.28 434	98.80 311	56.82 436	78.10 400	80.08 386	93.33 379	77.03 320	95.76 372	68.14 409	82.81 333	92.64 372

test_fmvs3		79.99 378	80.17 377	79.45 395	84.02 414	62.83 416	99.05 280	93.49 413	88.29 323	80.06 387	86.65 412	28.09 424	88.00 416	88.63 305	73.27 393	87.54 412

UnsupCasMVSNet_bld		79.97 379	77.03 384	88.78 376	85.62 410	81.98 391	93.66 404	97.35 291	75.51 407	70.79 410	83.05 417	48.70 415	94.91 385	78.31 385	60.29 420	89.46 407

test_f		78.40 380	77.59 382	80.81 394	80.82 419	62.48 419	96.96 376	93.08 415	83.44 377	74.57 406	84.57 416	27.95 425	92.63 405	84.15 349	72.79 394	87.32 413

WB-MVS		76.28 381	77.28 383	73.29 401	81.18 418	54.68 426	97.87 359	94.19 405	81.30 389	69.43 412	90.70 397	77.02 321	82.06 424	35.71 429	68.11 406	83.13 415

SSC-MVS		75.42 382	76.40 385	72.49 405	80.68 420	53.62 427	97.42 364	94.06 407	80.42 393	68.75 413	90.14 399	76.54 328	81.66 425	33.25 430	66.34 410	82.19 416

EGC-MVSNET		69.38 383	63.76 393	86.26 386	90.32 396	81.66 395	96.24 388	93.85 410	0.99 433	3.22 434	92.33 390	52.44 411	92.92 404	59.53 420	84.90 319	84.21 414

test_vis3_rt		68.82 384	66.69 389	75.21 400	76.24 425	60.41 421	96.44 383	68.71 435	75.13 408	50.54 426	69.52 424	16.42 434	96.32 355	80.27 374	66.92 409	68.89 422

FPMVS		68.72 385	68.72 386	68.71 407	65.95 430	44.27 436	95.97 394	94.74 400	51.13 422	53.26 424	90.50 398	25.11 427	83.00 423	60.80 418	80.97 355	78.87 420

testf1		68.38 386	66.92 387	72.78 403	78.80 422	50.36 429	90.95 416	87.35 428	55.47 419	58.95 418	88.14 406	20.64 429	87.60 417	57.28 421	64.69 412	80.39 418

APD_test2		68.38 386	66.92 387	72.78 403	78.80 422	50.36 429	90.95 416	87.35 428	55.47 419	58.95 418	88.14 406	20.64 429	87.60 417	57.28 421	64.69 412	80.39 418

LCM-MVSNet		67.77 388	64.73 391	76.87 398	62.95 432	56.25 425	89.37 419	93.74 411	44.53 424	61.99 416	80.74 418	20.42 431	86.53 421	69.37 407	59.50 421	87.84 410

PMMVS2		67.15 389	64.15 392	76.14 399	70.56 429	62.07 420	93.89 402	87.52 427	58.09 418	60.02 417	78.32 419	22.38 428	84.54 422	59.56 419	47.03 424	81.80 417

Gipuma		66.95 390	65.00 390	72.79 402	91.52 386	67.96 414	66.16 425	95.15 396	47.89 423	58.54 420	67.99 425	29.74 422	87.54 419	50.20 424	77.83 374	62.87 425
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tmp_tt		65.23 391	62.94 394	72.13 406	44.90 435	50.03 431	81.05 422	89.42 426	38.45 425	48.51 427	99.90 18	54.09 410	78.70 427	91.84 264	18.26 429	87.64 411

ANet_high		56.10 392	52.24 395	67.66 408	49.27 434	56.82 424	83.94 421	82.02 431	70.47 415	33.28 431	64.54 426	17.23 433	69.16 429	45.59 426	23.85 428	77.02 421

PMVS	49.05 23	53.75 393	51.34 397	60.97 410	40.80 436	34.68 437	74.82 424	89.62 425	37.55 426	28.67 432	72.12 421	7.09 436	81.63 426	43.17 427	68.21 405	66.59 424
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		52.30 394	52.18 396	52.67 411	71.51 427	45.40 433	93.62 405	76.60 433	36.01 427	43.50 428	64.13 427	27.11 426	67.31 430	31.06 431	26.06 426	45.30 429

MVE	53.74 22	51.54 395	47.86 399	62.60 409	59.56 433	50.93 428	79.41 423	77.69 432	35.69 428	36.27 430	61.76 429	5.79 438	69.63 428	37.97 428	36.61 425	67.24 423
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		51.44 396	51.22 398	52.11 412	70.71 428	44.97 435	94.04 401	75.66 434	35.34 429	42.40 429	61.56 430	28.93 423	65.87 431	27.64 432	24.73 427	45.49 428

testmvs		40.60 397	44.45 400	29.05 414	19.49 438	14.11 440	99.68 188	18.47 437	20.74 430	64.59 415	98.48 222	10.95 435	17.09 434	56.66 423	11.01 430	55.94 427

test123		37.68 398	39.14 401	33.31 413	19.94 437	24.83 439	98.36 340	9.75 438	15.53 431	51.31 425	87.14 410	19.62 432	17.74 433	47.10 425	3.47 432	57.36 426

cdsmvs_eth3d_5k		23.43 399	31.24 402	0.00 416	0.00 439	0.00 441	0.00 427	98.09 215	0.00 434	0.00 435	99.67 99	83.37 264	0.00 435	0.00 434	0.00 433	0.00 431

wuyk23d		20.37 400	20.84 403	18.99 415	65.34 431	27.73 438	50.43 426	7.67 439	9.50 432	8.01 433	6.34 433	6.13 437	26.24 432	23.40 433	10.69 431	2.99 430

ab-mvs-re		8.28 401	11.04 404	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	99.40 132	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

pcd_1.5k_mvsjas		7.60 402	10.13 405	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 435	91.20 167	0.00 435	0.00 434	0.00 433	0.00 431

mmdepth		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 435	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

monomultidepth		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 435	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

test_blank		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.02 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uanet_test		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 435	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

DCPMVS		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 435	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

sosnet-low-res		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 435	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

sosnet		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 435	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uncertanet		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 435	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

Regformer		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 435	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uanet		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 435	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

WAC-MVS						90.97 300								86.10 339

FOURS1					99.92 31	97.66 93	99.95 58	98.36 173	95.58 93	99.52 64

MSC_two_6792asdad				99.93 2	99.91 39	99.80 2		98.41 158					100.00 1	99.96 9	100.00 1	100.00 1

PC_three_1452									96.96 51	99.80 19	99.79 58	97.49 10	100.00 1	99.99 5	99.98 32	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 158					100.00 1	99.96 9	100.00 1	100.00 1

test_one_0601					99.94 13	99.30 12		98.41 158	96.63 64	99.75 31	99.93 11	97.49 10

eth-test2					0.00 439

eth-test					0.00 439

ZD-MVS					99.92 31	98.57 56		98.52 113	92.34 224	99.31 82	99.83 46	95.06 59	99.80 128	99.70 40	99.97 42

RE-MVS-def			98.13 55		99.79 62	96.37 148	99.76 160	98.31 184	94.43 129	99.40 76	99.75 73	92.95 131		98.90 84	99.92 64	99.97 61

IU-MVS					99.93 24	99.31 10		98.41 158	97.71 23	99.84 14				100.00 1	100.00 1	100.00 1

OPU-MVS				99.93 2	99.89 45	99.80 2	99.96 39				99.80 54	97.44 14	100.00 1	100.00 1	99.98 32	100.00 1

test_241102_TWO								98.43 141	97.27 38	99.80 19	99.94 4	97.18 21	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 24	99.30 12		98.43 141	97.26 40	99.80 19	99.88 24	96.71 27	100.00 1

9.14			98.38 37		99.87 51		99.91 93	98.33 180	93.22 181	99.78 28	99.89 22	94.57 77	99.85 115	99.84 22	99.97 42

save fliter					99.82 58	98.79 40	99.96 39	98.40 162	97.66 25

test_0728_THIRD									96.48 67	99.83 15	99.91 14	97.87 5	100.00 1	99.92 13	100.00 1	100.00 1

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 58	98.43 141					100.00 1	99.99 5	100.00 1	100.00 1

test0726					99.93 24	99.29 15	99.96 39	98.42 153	97.28 36	99.86 8	99.94 4	97.22 19

GSMVS																99.59 138

test_part2					99.89 45	99.25 18				99.49 67

sam_mvs1												94.72 71				99.59 138

sam_mvs												94.25 91

ambc				83.23 391	77.17 424	62.61 417	87.38 420	94.55 404		76.72 400	86.65 412	30.16 421	96.36 353	84.85 348	69.86 398	90.73 392

MTGPA								98.28 189

test_post1							95.78 396				59.23 431	93.20 125	97.74 284	91.06 273

test_post											63.35 428	94.43 79	98.13 263

patchmatchnet-post											91.70 392	95.12 56	97.95 275

GG-mvs-BLEND				98.54 116	98.21 190	98.01 76	93.87 403	98.52 113		97.92 151	97.92 247	99.02 3	97.94 277	98.17 125	99.58 102	99.67 119

MTMP							99.87 114	96.49 366

gm-plane-assit					96.97 267	93.76 236			91.47 250		98.96 172		98.79 206	94.92 203

test9_res														99.71 39	99.99 21	100.00 1

TEST9					99.92 31	98.92 29	99.96 39	98.43 141	93.90 160	99.71 38	99.86 29	95.88 41	99.85 115

test_8					99.92 31	98.88 32	99.96 39	98.43 141	94.35 134	99.69 40	99.85 33	95.94 38	99.85 115

agg_prior2														99.48 50	100.00 1	100.00 1

agg_prior					99.93 24	98.77 42		98.43 141		99.63 48			99.85 115

TestCases				95.00 260	99.01 119	88.43 347		96.82 351	86.50 346	88.71 311	98.47 223	74.73 346	99.88 109	85.39 342	96.18 208	96.71 269

test_prior4						98.05 74	99.94 75

test_prior2							99.95 58		95.78 87	99.73 36	99.76 66	96.00 37		99.78 27	100.00 1

test_prior				99.43 35	99.94 13	98.49 60		98.65 77					99.80 128			99.99 23

旧先验2							99.46 230		94.21 143	99.85 11			99.95 75	96.96 172

新几何2							99.40 234

新几何1				99.42 37	99.75 69	98.27 65		98.63 84	92.69 205	99.55 59	99.82 49	94.40 81	100.00 1	91.21 269	99.94 55	99.99 23

旧先验1					99.76 66	97.52 97		98.64 79			99.85 33	95.63 45			99.94 55	99.99 23

无先验							99.49 222	98.71 69	93.46 173				100.00 1	94.36 218		99.99 23

原ACMM2							99.90 99

原ACMM1				98.96 83	99.73 73	96.99 123		98.51 116	94.06 150	99.62 51	99.85 33	94.97 65	99.96 67	95.11 197	99.95 50	99.92 84

test222					99.55 90	97.41 105	99.34 245	98.55 104	91.86 237	99.27 86	99.83 46	93.84 106			99.95 50	99.99 23

testdata2													99.99 36	90.54 286

segment_acmp												96.68 29

testdata				98.42 128	99.47 96	95.33 191		98.56 98	93.78 164	99.79 27	99.85 33	93.64 111	99.94 83	94.97 201	99.94 55	100.00 1

testdata1							99.28 255		96.35 77

test12				99.43 35	99.74 70	98.56 57		98.40 162		99.65 44		94.76 69	99.75 139		99.98 32	99.99 23

plane_prior7					95.71 312	91.59 294

plane_prior6					95.76 306	91.72 289						80.47 296

plane_prior5								97.87 237					98.37 244	97.79 149	89.55 274	94.52 283

plane_prior4											98.59 210

plane_prior3						91.64 292			96.63 64	93.01 246

plane_prior2							99.84 133		96.38 73

plane_prior1					95.73 309

plane_prior						91.74 286	99.86 125		96.76 59						89.59 273

n2								0.00 440

nn								0.00 440

door-mid								89.69 424

lessismore_v0				90.53 360	90.58 394	80.90 399		95.80 379		77.01 398	95.84 309	66.15 383	96.95 325	83.03 359	75.05 390	93.74 351

LGP-MVS_train				93.71 313	95.43 320	88.67 343		97.62 260	92.81 197	90.05 276	98.49 219	75.24 340	98.40 236	95.84 189	89.12 278	94.07 324

test11								98.44 133

door								90.31 421

HQP5-MVS						91.85 282

HQP-NCC					95.78 302		99.87 114		96.82 55	93.37 241

ACMP_Plane					95.78 302		99.87 114		96.82 55	93.37 241

BP-MVS														97.92 140

HQP4-MVS										93.37 241			98.39 238			94.53 281

HQP3-MVS								97.89 235							89.60 271

HQP2-MVS												80.65 292

NP-MVS					95.77 305	91.79 284					98.65 205

MDTV_nov1_ep13_2view						96.26 151	96.11 390		91.89 236	98.06 147		94.40 81		94.30 221		99.67 119

MDTV_nov1_ep13			95.69 168		97.90 210	94.15 226	95.98 393	98.44 133	93.12 187	97.98 149	95.74 312	95.10 57	98.58 222	90.02 294	96.92 195

ACMMP++_ref															87.04 305

ACMMP++															88.23 294

Test By Simon												92.82 136

ITE_SJBPF				92.38 340	95.69 315	85.14 372		95.71 382	92.81 197	89.33 299	98.11 238	70.23 366	98.42 233	85.91 340	88.16 295	93.59 355

DeepMVS_CX				82.92 392	95.98 299	58.66 423		96.01 376	92.72 202	78.34 393	95.51 324	58.29 405	98.08 266	82.57 361	85.29 315	92.03 381

High-resolution multi-view benchmark