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 17	98.69 72	98.20 8	99.93 1	99.98 2	96.82 24	100.00 1	99.75 34	100.00 1	99.99 23

NCCC		99.37 2	99.25 2	99.71 15	99.96 8	99.15 22	99.97 33	98.62 86	98.02 17	99.90 3	99.95 3	97.33 17	100.00 1	99.54 48	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 33	98.64 80	98.47 3	99.13 95	99.92 13	96.38 34	100.00 1	99.74 36	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 60	98.32 184	97.28 38	99.83 17	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 41	98.43 143	97.27 40	99.80 21	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 60	98.43 143	96.48 69	99.80 21	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	99.87 116	98.44 135	97.48 32	99.64 49	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 17	98.86 54	97.10 46	99.80 21	99.94 4	95.92 40	100.00 1	99.51 49	100.00 1	100.00 1

MSP-MVS		99.09 9	99.12 5	98.98 82	99.93 24	97.24 111	99.95 60	98.42 155	97.50 31	99.52 66	99.88 24	97.43 16	99.71 147	99.50 50	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 60	98.56 100	97.56 30	99.44 72	99.85 33	95.38 52	100.00 1	99.31 60	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 72	99.75 74	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 95	98.39 167	97.20 44	99.46 70	99.85 33	95.53 48	99.79 132	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	98.72 150	97.71 89	99.98 17	98.44 135	96.85 55	99.80 21	99.91 14	97.57 8	99.85 117	99.44 55	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
CHOSEN 280x420		99.01 14	99.03 10	98.95 85	99.38 100	98.87 33	98.46 334	99.42 21	97.03 50	99.02 102	99.09 158	99.35 2	98.21 261	99.73 38	99.78 84	99.77 106

fmvsm_l_conf0.5_n_a		99.00 15	98.91 14	99.28 46	99.21 107	97.91 83	99.98 17	98.85 57	98.25 5	99.92 2	99.75 74	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 17	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	99.77 157	98.38 171	96.73 62	99.88 8	99.74 81	94.89 66	99.59 159	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 77	98.34 181	96.38 75	99.81 19	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	99.64 198	99.44 19	97.33 37	99.00 103	99.72 86	94.03 99	99.98 47	98.73 97	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 41	98.43 143	94.35 136	99.71 40	99.86 29	95.94 38	99.85 117	99.69 42	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 80	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 41	98.44 135	97.96 18	99.55 61	99.94 4	97.18 21	100.00 1	93.81 234	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	99.24 261	98.47 127	98.14 12	99.08 98	99.91 14	93.09 127	100.00 1	99.04 73	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 70	99.70 78	97.30 108	99.74 169	98.25 195	97.10 46	99.10 96	99.90 18	94.59 74	99.99 36	99.77 30	99.91 67	99.99 23

our_new_method		98.78 24	98.67 21	99.09 70	99.70 78	97.30 108	99.74 169	98.25 195	97.10 46	99.10 96	99.90 18	94.59 74	99.99 36	99.77 30	99.91 67	99.99 23

SMA-MVS		98.76 26	98.48 32	99.62 20	99.87 51	98.87 33	99.86 127	98.38 171	93.19 184	99.77 31	99.94 4	95.54 46	100.00 1	99.74 36	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 75	99.71 76	97.10 120	99.73 176	98.23 199	97.02 51	99.18 93	99.90 18	94.54 78	99.99 36	99.77 30	99.90 69	99.99 23

MVS_111021_HR		98.72 28	98.62 26	99.01 79	99.36 101	97.18 114	99.93 84	99.90 1	96.81 60	98.67 121	99.77 64	93.92 101	99.89 105	99.27 62	99.94 55	99.96 67

XVS		98.70 29	98.55 28	99.15 61	99.94 13	97.50 100	99.94 77	98.42 155	96.22 81	99.41 76	99.78 62	94.34 86	99.96 67	98.92 83	99.95 50	99.99 23

SF-MVS		98.67 30	98.40 35	99.50 30	99.77 65	98.67 49	99.90 101	98.21 201	93.53 173	99.81 19	99.89 22	94.70 73	99.86 116	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	99.87 116	98.33 182	93.97 156	99.76 32	99.87 27	94.99 64	99.75 141	98.55 107	100.00 1	99.98 51

APD-MVS		98.62 32	98.35 42	99.41 38	99.90 42	98.51 59	99.87 116	98.36 175	94.08 149	99.74 36	99.73 83	94.08 97	99.74 143	99.42 56	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 89	99.73 73	96.63 136	99.97 33	97.92 235	98.07 14	98.76 117	99.55 119	95.00 63	99.94 84	99.91 16	97.68 178	99.99 23

PAPM		98.60 33	98.42 34	99.14 63	96.05 297	98.96 26	99.90 101	99.35 24	96.68 64	98.35 138	99.66 103	96.45 33	98.51 228	99.45 54	99.89 70	99.96 67

HFP-MVS		98.56 35	98.37 39	99.14 63	99.96 8	97.43 104	99.95 60	98.61 87	94.77 116	99.31 84	99.85 33	94.22 92	100.00 1	98.70 98	99.98 32	99.98 51

region2R		98.54 36	98.37 39	99.05 73	99.96 8	97.18 114	99.96 41	98.55 106	94.87 114	99.45 71	99.85 33	94.07 98	100.00 1	98.67 100	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 93	97.70 25	98.21 146	99.24 150	92.58 142	99.94 84	98.63 105	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 60	98.43 143	95.35 101	98.03 150	99.75 74	94.03 99	99.98 47	98.11 131	99.83 77	99.99 23

ACMMPR		98.50 39	98.32 43	99.05 73	99.96 8	97.18 114	99.95 60	98.60 89	94.77 116	99.31 84	99.84 44	93.73 108	100.00 1	98.70 98	99.98 32	99.98 51

ACMMP_NAP		98.49 40	98.14 54	99.54 27	99.66 82	98.62 55	99.85 130	98.37 174	94.68 121	99.53 64	99.83 46	92.87 133	100.00 1	98.66 102	99.84 76	99.99 23

EPNet		98.49 40	98.40 35	98.77 95	99.62 84	96.80 132	99.90 101	99.51 16	97.60 27	99.20 90	99.36 139	93.71 109	99.91 98	97.99 138	98.71 150	99.61 136
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 86	99.88 49	97.04 122	99.84 135	98.35 177	94.92 111	99.32 83	99.80 54	93.35 116	99.78 134	99.30 61	99.95 50	99.96 67

CP-MVS		98.45 43	98.32 43	98.87 88	99.96 8	96.62 137	99.97 33	98.39 167	94.43 131	98.90 107	99.87 27	94.30 89	100.00 1	99.04 73	99.99 21	99.99 23

test_fmvsm_n_1920		98.44 44	98.61 27	97.92 157	99.27 106	95.18 200	100.00 1	98.90 48	98.05 15	99.80 21	99.73 83	92.64 139	99.99 36	99.58 47	99.51 109	98.59 237

PS-MVSNAJ		98.44 44	98.20 49	99.16 59	98.80 146	98.92 29	99.54 216	98.17 206	97.34 35	99.85 13	99.85 33	91.20 167	99.89 105	99.41 57	99.67 90	98.69 234

test_fmvsmconf_n		98.43 46	98.32 43	98.78 93	98.12 201	96.41 145	99.99 5	98.83 61	98.22 7	99.67 44	99.64 106	91.11 171	99.94 84	99.67 43	99.62 95	99.98 51

MVS_111021_LR		98.42 47	98.38 37	98.53 119	99.39 99	95.79 170	99.87 116	99.86 2	96.70 63	98.78 113	99.79 58	92.03 157	99.90 100	99.17 66	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 17	98.64 80	98.14 12	99.86 10	99.76 66	87.99 217	99.97 57	99.72 39	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 87	98.44 135	92.06 234	98.40 136	99.84 44	95.68 44	100.00 1	98.19 126	99.71 88	99.97 61

PHI-MVS		98.41 48	98.21 48	99.03 75	99.86 53	97.10 120	99.98 17	98.80 65	90.78 275	99.62 53	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 83	99.97 3	96.92 127	99.95 60	98.38 171	95.04 107	98.61 125	99.80 54	93.39 114	100.00 1	98.64 103	100.00 1	99.98 51

PGM-MVS		98.34 52	98.13 55	98.99 80	99.92 31	97.00 123	99.75 166	99.50 17	93.90 162	99.37 81	99.76 66	93.24 123	100.00 1	97.75 155	99.96 46	99.98 51

BP-MVS1		98.33 53	98.18 51	98.81 91	97.44 246	97.98 78	99.96 41	98.17 206	94.88 113	98.77 114	99.59 112	97.59 7	99.08 194	98.24 124	98.93 141	99.36 181

SR-MVS-dyc-post		98.31 54	98.17 52	98.71 98	99.79 62	96.37 149	99.76 162	98.31 186	94.43 131	99.40 78	99.75 74	93.28 121	99.78 134	98.90 86	99.92 64	99.97 61

ZNCC-MVS		98.31 54	98.03 61	99.17 56	99.88 49	97.59 95	99.94 77	98.44 135	94.31 139	98.50 130	99.82 49	93.06 128	99.99 36	98.30 123	99.99 21	99.93 79

MTAPA		98.29 56	97.96 68	99.30 45	99.85 54	97.93 82	99.39 240	98.28 191	95.76 90	97.18 178	99.88 24	92.74 137	100.00 1	98.67 100	99.88 73	99.99 23

balanced_conf03		98.27 57	97.99 63	99.11 68	98.64 158	98.43 62	99.47 228	97.79 246	94.56 124	99.74 36	98.35 230	94.33 88	99.25 179	99.12 67	99.96 46	99.64 126

GST-MVS		98.27 57	97.97 65	99.17 56	99.92 31	97.57 96	99.93 84	98.39 167	94.04 154	98.80 112	99.74 81	92.98 130	100.00 1	98.16 128	99.76 85	99.93 79

CANet		98.27 57	97.82 76	99.63 17	99.72 75	99.10 23	99.98 17	98.51 118	97.00 52	98.52 127	99.71 88	87.80 218	99.95 76	99.75 34	99.38 121	99.83 96

EI-MVSNet-Vis-set		98.27 57	98.11 57	98.75 96	99.83 57	96.59 140	99.40 236	98.51 118	95.29 103	98.51 129	99.76 66	93.60 112	99.71 147	98.53 110	99.52 106	99.95 74

APD-MVS_3200maxsize		98.25 61	98.08 59	98.78 93	99.81 60	96.60 138	99.82 145	98.30 189	93.95 158	99.37 81	99.77 64	92.84 134	99.76 140	98.95 79	99.92 64	99.97 61

patch_mono-2		98.24 62	99.12 5	95.59 244	99.67 81	86.91 365	99.95 60	98.89 50	97.60 27	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 78	98.69 151	98.66 51	99.52 218	98.08 219	97.05 49	99.86 10	99.86 29	90.65 180	99.71 147	99.39 59	98.63 151	98.69 234

MP-MVS		98.23 63	97.97 65	99.03 75	99.94 13	97.17 117	99.95 60	98.39 167	94.70 120	98.26 143	99.81 53	91.84 161	100.00 1	98.85 89	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	98.60 108	99.80 61	96.27 151	99.36 246	98.50 124	95.21 105	98.30 140	99.75 74	93.29 120	99.73 146	98.37 119	99.30 125	99.81 99

PAPM_NR		98.12 66	97.93 70	98.70 99	99.94 13	96.13 161	99.82 145	98.43 143	94.56 124	97.52 165	99.70 90	94.40 81	99.98 47	97.00 170	99.98 32	99.99 23

WTY-MVS		98.10 67	97.60 86	99.60 22	98.92 134	99.28 17	99.89 110	99.52 14	95.58 95	98.24 145	99.39 136	93.33 117	99.74 143	97.98 140	95.58 228	99.78 105

fmvsm_s_conf0.5_n_5		98.08 68	97.71 80	99.17 56	98.67 153	97.69 93	99.99 5	98.57 95	97.40 33	99.89 6	99.69 93	85.99 242	99.96 67	99.80 25	99.40 120	99.85 94

MP-MVS-pluss		98.07 69	97.64 84	99.38 43	99.74 70	98.41 63	99.74 169	98.18 205	93.35 178	96.45 197	99.85 33	92.64 139	99.97 57	98.91 85	99.89 70	99.77 106
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HPM-MVS		97.96 70	97.72 78	98.68 100	99.84 56	96.39 148	99.90 101	98.17 206	92.61 212	98.62 124	99.57 118	91.87 160	99.67 155	98.87 88	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 71	97.66 82	98.81 91	98.99 124	98.07 72	99.98 17	98.81 62	98.18 9	99.89 6	99.70 90	84.15 260	99.97 57	99.76 33	99.50 111	98.39 241

PVSNet_Blended		97.94 72	97.64 84	98.83 90	99.59 85	96.99 124	100.00 1	99.10 32	95.38 100	98.27 141	99.08 159	89.00 207	99.95 76	99.12 67	99.25 127	99.57 147

PLC	95.54 3	97.93 73	97.89 73	98.05 150	99.82 58	94.77 212	99.92 87	98.46 129	93.93 159	97.20 176	99.27 145	95.44 51	99.97 57	97.41 160	99.51 109	99.41 175
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ETV-MVS		97.92 74	97.80 77	98.25 138	98.14 199	96.48 142	99.98 17	97.63 259	95.61 94	99.29 87	99.46 127	92.55 143	98.82 206	99.02 77	98.54 153	99.46 168

GDP-MVS		97.88 75	97.59 88	98.75 96	97.59 238	97.81 86	99.95 60	97.37 292	94.44 130	99.08 98	99.58 115	97.13 23	99.08 194	94.99 202	98.17 164	99.37 179

SPE-MVS-test		97.88 75	97.94 69	97.70 172	99.28 105	95.20 199	99.98 17	97.15 316	95.53 97	99.62 53	99.79 58	92.08 156	98.38 244	98.75 96	99.28 126	99.52 159

myMVS_eth3d28		97.86 77	97.59 88	98.68 100	98.50 171	97.26 110	99.92 87	98.55 106	93.79 165	98.26 143	98.75 197	95.20 54	99.48 171	98.93 81	96.40 206	99.29 193

API-MVS		97.86 77	97.66 82	98.47 123	99.52 92	95.41 189	99.47 228	98.87 53	91.68 245	98.84 109	99.85 33	92.34 150	99.99 36	98.44 115	99.96 46	100.00 1

lupinMVS		97.85 79	97.60 86	98.62 106	97.28 259	97.70 91	99.99 5	97.55 271	95.50 99	99.43 74	99.67 101	90.92 175	98.71 217	98.40 116	99.62 95	99.45 170

UBG		97.84 80	97.69 81	98.29 136	98.38 177	96.59 140	99.90 101	98.53 113	93.91 161	98.52 127	98.42 228	96.77 25	99.17 188	98.54 108	96.20 209	99.11 209

MVSMamba_PlusPlus		97.83 81	97.45 93	98.99 80	98.60 160	98.15 66	99.58 207	97.74 250	90.34 284	99.26 89	98.32 233	94.29 90	99.23 180	99.03 76	99.89 70	99.58 145

test_yl		97.83 81	97.37 98	99.21 50	99.18 108	97.98 78	99.64 198	99.27 27	91.43 254	97.88 157	98.99 168	95.84 42	99.84 125	98.82 90	95.32 234	99.79 102

DCV-MVSNet		97.83 81	97.37 98	99.21 50	99.18 108	97.98 78	99.64 198	99.27 27	91.43 254	97.88 157	98.99 168	95.84 42	99.84 125	98.82 90	95.32 234	99.79 102

mvsany_test1		97.82 84	97.90 72	97.55 180	98.77 148	93.04 257	99.80 151	97.93 232	96.95 54	99.61 59	99.68 100	90.92 175	99.83 127	99.18 65	98.29 162	99.80 101

alignmvs		97.81 85	97.33 100	99.25 47	98.77 148	98.66 51	99.99 5	98.44 135	94.40 135	98.41 134	99.47 125	93.65 110	99.42 175	98.57 106	94.26 249	99.67 120

fmvsm_s_conf0.5_n		97.80 86	97.85 75	97.67 173	99.06 116	94.41 219	99.98 17	98.97 41	97.34 35	99.63 50	99.69 93	87.27 225	99.97 57	99.62 45	99.06 137	98.62 236

HPM-MVS_fast		97.80 86	97.50 91	98.68 100	99.79 62	96.42 144	99.88 113	98.16 211	91.75 244	98.94 105	99.54 121	91.82 162	99.65 157	97.62 158	99.99 21	99.99 23

CS-MVS		97.79 88	97.91 71	97.43 188	99.10 114	94.42 218	99.99 5	97.10 321	95.07 106	99.68 43	99.75 74	92.95 131	98.34 248	98.38 117	99.14 132	99.54 153

HY-MVS	92.50 7	97.79 88	97.17 109	99.63 17	98.98 126	99.32 9	97.49 365	99.52 14	95.69 92	98.32 139	97.41 261	93.32 118	99.77 137	98.08 134	95.75 225	99.81 99

CNLPA		97.76 90	97.38 97	98.92 87	99.53 91	96.84 129	99.87 116	98.14 215	93.78 166	96.55 195	99.69 93	92.28 151	99.98 47	97.13 166	99.44 116	99.93 79

fmvsm_s_conf0.5_n_4		97.75 91	97.86 74	97.42 189	99.01 119	94.69 213	99.97 33	98.76 66	97.91 19	99.87 9	99.76 66	86.70 234	99.93 92	99.67 43	99.12 135	97.64 258

test_fmvsmconf0.1_n		97.74 92	97.44 94	98.64 105	95.76 308	96.20 157	99.94 77	98.05 222	98.17 10	98.89 108	99.42 129	87.65 220	99.90 100	99.50 50	99.60 101	99.82 97

ACMMP		97.74 92	97.44 94	98.66 103	99.92 31	96.13 161	99.18 266	99.45 18	94.84 115	96.41 200	99.71 88	91.40 164	99.99 36	97.99 138	98.03 173	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 94	97.72 78	97.77 167	98.63 159	94.26 225	99.96 41	98.92 47	97.18 45	99.75 33	99.69 93	87.00 230	99.97 57	99.46 53	98.89 142	99.08 212

testing3-2		97.72 95	97.43 96	98.60 108	98.55 164	97.11 119	100.00 1	99.23 29	93.78 166	97.90 154	98.73 199	95.50 49	99.69 151	98.53 110	94.63 241	98.99 218

DeepPCF-MVS	95.94 2	97.71 96	98.98 12	93.92 308	99.63 83	81.76 396	99.96 41	98.56 100	99.47 1	99.19 92	99.99 1	94.16 96	100.00 1	99.92 13	99.93 61	100.00 1

test_fmvsmvis_n_1920		97.67 97	97.59 88	97.91 159	97.02 266	95.34 191	99.95 60	98.45 130	97.87 20	97.02 182	99.59 112	89.64 195	99.98 47	99.41 57	99.34 124	98.42 240

CPTT-MVS		97.64 98	97.32 101	98.58 112	99.97 3	95.77 171	99.96 41	98.35 177	89.90 293	98.36 137	99.79 58	91.18 170	99.99 36	98.37 119	99.99 21	99.99 23

fmvsm_s_conf0.5_n_2		97.59 99	97.28 102	98.53 119	99.01 119	98.15 66	99.98 17	98.59 91	98.17 10	99.75 33	99.63 109	81.83 277	99.94 84	99.78 28	98.79 148	97.51 265

sss		97.57 100	97.03 114	99.18 53	98.37 179	98.04 75	99.73 176	99.38 22	93.46 175	98.76 117	99.06 161	91.21 166	99.89 105	96.33 182	97.01 195	99.62 132

test2506		97.53 101	97.19 107	98.58 112	98.66 155	96.90 128	98.81 311	99.77 5	94.93 109	97.95 152	98.96 174	92.51 144	99.20 185	94.93 204	98.15 166	99.64 126

EIA-MVS		97.53 101	97.46 92	97.76 169	98.04 205	94.84 208	99.98 17	97.61 265	94.41 134	97.90 154	99.59 112	92.40 148	98.87 203	98.04 135	99.13 133	99.59 139

testing11		97.48 103	97.27 103	98.10 146	98.36 180	96.02 164	99.92 87	98.45 130	93.45 177	98.15 148	98.70 202	95.48 50	99.22 181	97.85 146	95.05 238	99.07 213

xiu_mvs_v1_base_debu		97.43 104	97.06 110	98.55 114	97.74 223	98.14 68	99.31 251	97.86 241	96.43 72	99.62 53	99.69 93	85.56 245	99.68 152	99.05 70	98.31 159	97.83 253

xiu_mvs_v1_base		97.43 104	97.06 110	98.55 114	97.74 223	98.14 68	99.31 251	97.86 241	96.43 72	99.62 53	99.69 93	85.56 245	99.68 152	99.05 70	98.31 159	97.83 253

xiu_mvs_v1_base_debi		97.43 104	97.06 110	98.55 114	97.74 223	98.14 68	99.31 251	97.86 241	96.43 72	99.62 53	99.69 93	85.56 245	99.68 152	99.05 70	98.31 159	97.83 253

MAR-MVS		97.43 104	97.19 107	98.15 144	99.47 96	94.79 211	99.05 282	98.76 66	92.65 210	98.66 122	99.82 49	88.52 212	99.98 47	98.12 130	99.63 94	99.67 120
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		97.42 108	98.09 58	95.42 249	99.58 89	87.24 361	99.23 262	96.95 339	94.28 142	98.93 106	99.73 83	94.39 84	99.16 190	99.89 17	99.82 81	99.86 93

thisisatest0515		97.41 109	97.02 115	98.59 111	97.71 230	97.52 98	99.97 33	98.54 110	91.83 240	97.45 168	99.04 162	97.50 9	99.10 193	94.75 212	96.37 208	99.16 203

114514_t		97.41 109	96.83 123	99.14 63	99.51 94	97.83 84	99.89 110	98.27 193	88.48 321	99.06 100	99.66 103	90.30 188	99.64 158	96.32 183	99.97 42	99.96 67

EC-MVSNet		97.38 111	97.24 104	97.80 162	97.41 248	95.64 180	99.99 5	97.06 327	94.59 123	99.63 50	99.32 141	89.20 205	98.14 264	98.76 95	99.23 129	99.62 132

fmvsm_s_conf0.1_n		97.30 112	97.21 106	97.60 179	97.38 250	94.40 221	99.90 101	98.64 80	96.47 71	99.51 68	99.65 105	84.99 253	99.93 92	99.22 64	99.09 136	98.46 238

OMC-MVS		97.28 113	97.23 105	97.41 190	99.76 66	93.36 252	99.65 194	97.95 230	96.03 85	97.41 170	99.70 90	89.61 196	99.51 163	96.73 179	98.25 163	99.38 177

PVSNet_Blended_VisFu		97.27 114	96.81 124	98.66 103	98.81 145	96.67 135	99.92 87	98.64 80	94.51 126	96.38 201	98.49 221	89.05 206	99.88 111	97.10 168	98.34 157	99.43 173

fmvsm_s_conf0.1_n_2		97.25 115	96.85 122	98.43 127	98.08 202	98.08 71	99.92 87	97.76 249	98.05 15	99.65 46	99.58 115	80.88 290	99.93 92	99.59 46	98.17 164	97.29 266

jason		97.24 116	96.86 121	98.38 132	95.73 311	97.32 107	99.97 33	97.40 289	95.34 102	98.60 126	99.54 121	87.70 219	98.56 225	97.94 141	99.47 112	99.25 198
jason: jason.
AdaColmap		97.23 117	96.80 125	98.51 121	99.99 1	95.60 182	99.09 271	98.84 60	93.32 180	96.74 190	99.72 86	86.04 241	100.00 1	98.01 136	99.43 117	99.94 78

VNet		97.21 118	96.57 136	99.13 67	98.97 127	97.82 85	99.03 285	99.21 30	94.31 139	99.18 93	98.88 185	86.26 240	99.89 105	98.93 81	94.32 247	99.69 117

testing99		97.17 119	96.91 117	97.95 153	98.35 182	95.70 176	99.91 95	98.43 143	92.94 193	97.36 171	98.72 200	94.83 67	99.21 182	97.00 170	94.64 240	98.95 219

testing91		97.16 120	96.90 118	97.97 152	98.35 182	95.67 179	99.91 95	98.42 155	92.91 195	97.33 172	98.72 200	94.81 68	99.21 182	96.98 172	94.63 241	99.03 215

PVSNet	91.05 13	97.13 121	96.69 131	98.45 125	99.52 92	95.81 169	99.95 60	99.65 12	94.73 118	99.04 101	99.21 152	84.48 257	99.95 76	94.92 205	98.74 149	99.58 145

thisisatest0530		97.10 122	96.72 129	98.22 139	97.60 237	96.70 133	99.92 87	98.54 110	91.11 264	97.07 181	98.97 172	97.47 12	99.03 196	93.73 239	96.09 212	98.92 220

CSCG		97.10 122	97.04 113	97.27 199	99.89 45	91.92 283	99.90 101	99.07 35	88.67 317	95.26 223	99.82 49	93.17 126	99.98 47	98.15 129	99.47 112	99.90 87

sasdasda		97.09 124	96.32 143	99.39 40	98.93 131	98.95 27	99.72 180	97.35 293	94.45 127	97.88 157	99.42 129	86.71 232	99.52 161	98.48 112	93.97 253	99.72 112

fmvsm_s_conf0.1_n_a		97.09 124	96.90 118	97.63 177	95.65 318	94.21 227	99.83 142	98.50 124	96.27 80	99.65 46	99.64 106	84.72 254	99.93 92	99.04 73	98.84 145	98.74 231

canonicalmvs		97.09 124	96.32 143	99.39 40	98.93 131	98.95 27	99.72 180	97.35 293	94.45 127	97.88 157	99.42 129	86.71 232	99.52 161	98.48 112	93.97 253	99.72 112

testing222		97.08 127	96.75 127	98.06 149	98.56 161	96.82 130	99.85 130	98.61 87	92.53 218	98.84 109	98.84 194	93.36 115	98.30 252	95.84 191	94.30 248	99.05 214

ETVMVS		97.03 128	96.64 132	98.20 140	98.67 153	97.12 118	99.89 110	98.57 95	91.10 265	98.17 147	98.59 212	93.86 105	98.19 262	95.64 194	95.24 236	99.28 195

MGCFI-Net		97.00 129	96.22 147	99.34 44	98.86 142	98.80 39	99.67 192	97.30 300	94.31 139	97.77 161	99.41 133	86.36 239	99.50 165	98.38 117	93.90 255	99.72 112

diffmvs		97.00 129	96.64 132	98.09 147	97.64 235	96.17 160	99.81 147	97.19 310	94.67 122	98.95 104	99.28 142	86.43 237	98.76 211	98.37 119	97.42 184	99.33 187
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		96.96 131	96.21 148	99.22 49	98.97 127	98.84 36	99.85 130	99.71 7	93.17 185	96.26 203	98.88 185	89.87 193	99.51 163	94.26 224	94.91 239	99.31 189

mvsmamba		96.94 132	96.73 128	97.55 180	97.99 207	94.37 222	99.62 201	97.70 252	93.13 188	98.42 133	97.92 249	88.02 216	98.75 213	98.78 93	99.01 139	99.52 159

MVSFormer		96.94 132	96.60 134	97.95 153	97.28 259	97.70 91	99.55 214	97.27 305	91.17 261	99.43 74	99.54 121	90.92 175	96.89 331	94.67 215	99.62 95	99.25 198

F-COLMAP		96.93 134	96.95 116	96.87 209	99.71 76	91.74 288	99.85 130	97.95 230	93.11 190	95.72 216	99.16 156	92.35 149	99.94 84	95.32 197	99.35 123	98.92 220

DeepC-MVS	94.51 4	96.92 135	96.40 142	98.45 125	99.16 111	95.90 167	99.66 193	98.06 220	96.37 78	94.37 232	99.49 124	83.29 267	99.90 100	97.63 157	99.61 99	99.55 149
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
tttt0517		96.85 136	96.49 138	97.92 157	97.48 245	95.89 168	99.85 130	98.54 110	90.72 277	96.63 192	98.93 183	97.47 12	99.02 197	93.03 252	95.76 224	98.85 224

1314		96.84 137	95.96 159	99.48 34	96.74 284	98.52 58	98.31 343	98.86 54	95.82 88	89.91 283	98.98 170	87.49 222	99.96 67	97.80 148	99.73 87	99.96 67

CHOSEN 1792x2688		96.81 138	96.53 137	97.64 175	98.91 138	93.07 254	99.65 194	99.80 3	95.64 93	95.39 220	98.86 190	84.35 259	99.90 100	96.98 172	99.16 131	99.95 74

UWE-MVS		96.79 139	96.72 129	97.00 204	98.51 169	93.70 240	99.71 183	98.60 89	92.96 192	97.09 179	98.34 232	96.67 31	98.85 205	92.11 261	96.50 203	98.44 239

tfpn200view9		96.79 139	95.99 153	99.19 52	98.94 129	98.82 37	99.78 154	99.71 7	92.86 196	96.02 208	98.87 188	89.33 200	99.50 165	93.84 231	94.57 243	99.27 196

thres400		96.78 141	95.99 153	99.16 59	98.94 129	98.82 37	99.78 154	99.71 7	92.86 196	96.02 208	98.87 188	89.33 200	99.50 165	93.84 231	94.57 243	99.16 203

CANet_DTU		96.76 142	96.15 149	98.60 108	98.78 147	97.53 97	99.84 135	97.63 259	97.25 43	99.20 90	99.64 106	81.36 283	99.98 47	92.77 255	98.89 142	98.28 245

PMMVS		96.76 142	96.76 126	96.76 212	98.28 187	92.10 278	99.91 95	97.98 227	94.12 147	99.53 64	99.39 136	86.93 231	98.73 214	96.95 175	97.73 176	99.45 170

thres100view900		96.74 144	95.92 163	99.18 53	98.90 139	98.77 42	99.74 169	99.71 7	92.59 214	95.84 212	98.86 190	89.25 202	99.50 165	93.84 231	94.57 243	99.27 196

TESTMET0.1,1		96.74 144	96.26 145	98.16 141	97.36 252	96.48 142	99.96 41	98.29 190	91.93 237	95.77 215	98.07 242	95.54 46	98.29 253	90.55 287	98.89 142	99.70 115

baseline2		96.71 146	96.49 138	97.37 193	95.63 320	95.96 166	99.74 169	98.88 52	92.94 193	91.61 264	98.97 172	97.72 6	98.62 223	94.83 209	98.08 172	97.53 264

thres600view7		96.69 147	95.87 166	99.14 63	98.90 139	98.78 41	99.74 169	99.71 7	92.59 214	95.84 212	98.86 190	89.25 202	99.50 165	93.44 244	94.50 246	99.16 203

EPP-MVSNet		96.69 147	96.60 134	96.96 206	97.74 223	93.05 256	99.37 244	98.56 100	88.75 315	95.83 214	99.01 165	96.01 36	98.56 225	96.92 176	97.20 189	99.25 198

HyFIR lowres test		96.66 149	96.43 141	97.36 195	99.05 117	93.91 235	99.70 187	99.80 3	90.54 279	96.26 203	98.08 241	92.15 154	98.23 260	96.84 178	95.46 229	99.93 79

MVS		96.60 150	95.56 175	99.72 13	96.85 277	99.22 20	98.31 343	98.94 42	91.57 247	90.90 272	99.61 111	86.66 235	99.96 67	97.36 161	99.88 73	99.99 23

test_cas_vis1_n_1920		96.59 151	96.23 146	97.65 174	98.22 191	94.23 226	99.99 5	97.25 307	97.77 22	99.58 60	99.08 159	77.10 321	99.97 57	97.64 156	99.45 115	98.74 231

UA-Net		96.54 152	95.96 159	98.27 137	98.23 190	95.71 175	98.00 358	98.45 130	93.72 170	98.41 134	99.27 145	88.71 211	99.66 156	91.19 272	97.69 177	99.44 172

EPMVS		96.53 153	96.01 152	98.09 147	98.43 175	96.12 163	96.36 386	99.43 20	93.53 173	97.64 163	95.04 351	94.41 80	98.38 244	91.13 273	98.11 169	99.75 108

test-LLR		96.47 154	96.04 151	97.78 165	97.02 266	95.44 186	99.96 41	98.21 201	94.07 150	95.55 217	96.38 295	93.90 103	98.27 257	90.42 290	98.83 146	99.64 126

MVS_Test		96.46 155	95.74 168	98.61 107	98.18 195	97.23 112	99.31 251	97.15 316	91.07 266	98.84 109	97.05 274	88.17 215	98.97 198	94.39 219	97.50 181	99.61 136

casdiffmvs_mvg		96.43 156	95.94 161	97.89 161	97.44 246	95.47 185	99.86 127	97.29 303	93.35 178	96.03 207	99.19 153	85.39 248	98.72 216	97.89 145	97.04 193	99.49 166
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		96.43 156	95.98 155	97.76 169	97.34 253	95.17 201	99.51 220	97.17 313	93.92 160	96.90 185	99.28 142	85.37 249	98.64 222	97.50 159	96.86 199	99.46 168

casdiffmvs		96.42 158	95.97 158	97.77 167	97.30 257	94.98 203	99.84 135	97.09 324	93.75 169	96.58 194	99.26 148	85.07 251	98.78 209	97.77 153	97.04 193	99.54 153
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		96.39 159	95.74 168	98.32 134	91.47 389	95.56 183	99.84 135	97.30 300	97.74 23	97.89 156	99.35 140	79.62 303	99.85 117	99.25 63	99.24 128	99.55 149

test-mter		96.39 159	95.93 162	97.78 165	97.02 266	95.44 186	99.96 41	98.21 201	91.81 242	95.55 217	96.38 295	95.17 55	98.27 257	90.42 290	98.83 146	99.64 126

CDS-MVSNet		96.34 161	96.07 150	97.13 201	97.37 251	94.96 204	99.53 217	97.91 236	91.55 248	95.37 221	98.32 233	95.05 60	97.13 313	93.80 235	95.75 225	99.30 191
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Vis-MVSNet (Re-imp)		96.32 162	95.98 155	97.35 196	97.93 211	94.82 209	99.47 228	98.15 214	91.83 240	95.09 224	99.11 157	91.37 165	97.47 295	93.47 243	97.43 182	99.74 109

3Dnovator+	91.53 11	96.31 163	95.24 183	99.52 28	96.88 276	98.64 54	99.72 180	98.24 197	95.27 104	88.42 324	98.98 170	82.76 270	99.94 84	97.10 168	99.83 77	99.96 67

Effi-MVS+		96.30 164	95.69 170	98.16 141	97.85 216	96.26 152	97.41 367	97.21 309	90.37 282	98.65 123	98.58 215	86.61 236	98.70 218	97.11 167	97.37 186	99.52 159

IS-MVSNet		96.29 165	95.90 164	97.45 186	98.13 200	94.80 210	99.08 273	97.61 265	92.02 236	95.54 219	98.96 174	90.64 181	98.08 268	93.73 239	97.41 185	99.47 167

3Dnovator	91.47 12	96.28 166	95.34 180	99.08 72	96.82 279	97.47 103	99.45 233	98.81 62	95.52 98	89.39 298	99.00 167	81.97 274	99.95 76	97.27 163	99.83 77	99.84 95

tpmrst		96.27 167	95.98 155	97.13 201	97.96 209	93.15 253	96.34 387	98.17 206	92.07 232	98.71 120	95.12 348	93.91 102	98.73 214	94.91 207	96.62 200	99.50 164

RRT-MVS		96.24 168	95.68 172	97.94 156	97.65 234	94.92 206	99.27 259	97.10 321	92.79 202	97.43 169	97.99 246	81.85 276	99.37 176	98.46 114	98.57 152	99.53 157

CostFormer		96.10 169	95.88 165	96.78 211	97.03 265	92.55 270	97.08 375	97.83 244	90.04 291	98.72 119	94.89 358	95.01 62	98.29 253	96.54 181	95.77 223	99.50 164

PVSNet_BlendedMVS		96.05 170	95.82 167	96.72 214	99.59 85	96.99 124	99.95 60	99.10 32	94.06 152	98.27 141	95.80 312	89.00 207	99.95 76	99.12 67	87.53 305	93.24 365

PatchMatch-RL		96.04 171	95.40 177	97.95 153	99.59 85	95.22 198	99.52 218	99.07 35	93.96 157	96.49 196	98.35 230	82.28 272	99.82 129	90.15 295	99.22 130	98.81 227

1112_ss		96.01 172	95.20 185	98.42 129	97.80 219	96.41 145	99.65 194	96.66 361	92.71 205	92.88 252	99.40 134	92.16 153	99.30 177	91.92 264	93.66 256	99.55 149

UWE-MVS-28		95.95 173	96.49 138	94.34 293	98.51 169	89.99 327	99.39 240	98.57 95	93.14 187	97.33 172	98.31 235	93.44 113	94.68 390	93.69 241	95.98 215	98.34 244

PatchmatchNet		95.94 174	95.45 176	97.39 192	97.83 217	94.41 219	96.05 393	98.40 164	92.86 196	97.09 179	95.28 343	94.21 94	98.07 270	89.26 303	98.11 169	99.70 115
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
FA-MVS(test-final)		95.86 175	95.09 189	98.15 144	97.74 223	95.62 181	96.31 388	98.17 206	91.42 256	96.26 203	96.13 305	90.56 183	99.47 173	92.18 260	97.07 191	99.35 184

TAMVS		95.85 176	95.58 174	96.65 217	97.07 263	93.50 246	99.17 267	97.82 245	91.39 258	95.02 225	98.01 243	92.20 152	97.30 303	93.75 238	95.83 222	99.14 206

LS3D		95.84 177	95.11 188	98.02 151	99.85 54	95.10 202	98.74 316	98.50 124	87.22 339	93.66 241	99.86 29	87.45 223	99.95 76	90.94 279	99.81 83	99.02 216

baseline1		95.78 178	94.86 196	98.54 117	98.47 174	98.07 72	99.06 278	97.99 225	92.68 208	94.13 237	98.62 211	93.28 121	98.69 219	93.79 236	85.76 313	98.84 225

Test_1112_low_res		95.72 179	94.83 197	98.42 129	97.79 220	96.41 145	99.65 194	96.65 362	92.70 206	92.86 253	96.13 305	92.15 154	99.30 177	91.88 265	93.64 257	99.55 149

Vis-MVSNet		95.72 179	95.15 187	97.45 186	97.62 236	94.28 224	99.28 257	98.24 197	94.27 144	96.84 187	98.94 181	79.39 305	98.76 211	93.25 245	98.49 154	99.30 191
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
EPNet_dtu		95.71 181	95.39 178	96.66 216	98.92 134	93.41 249	99.57 210	98.90 48	96.19 83	97.52 165	98.56 217	92.65 138	97.36 297	77.89 388	98.33 158	99.20 201
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
BH-w/o		95.71 181	95.38 179	96.68 215	98.49 173	92.28 274	99.84 135	97.50 279	92.12 231	92.06 262	98.79 195	84.69 255	98.67 221	95.29 198	99.66 91	99.09 210

FE-MVS		95.70 183	95.01 193	97.79 164	98.21 192	94.57 214	95.03 400	98.69 72	88.90 311	97.50 167	96.19 302	92.60 141	99.49 170	89.99 297	97.94 175	99.31 189

ECVR-MVS		95.66 184	95.05 191	97.51 184	98.66 155	93.71 239	98.85 308	98.45 130	94.93 109	96.86 186	98.96 174	75.22 344	99.20 185	95.34 196	98.15 166	99.64 126

mvs_anonymous		95.65 185	95.03 192	97.53 182	98.19 194	95.74 173	99.33 248	97.49 280	90.87 270	90.47 276	97.10 270	88.23 214	97.16 310	95.92 189	97.66 179	99.68 118

test1111		95.57 186	94.98 194	97.37 193	98.56 161	93.37 251	98.86 306	98.45 130	94.95 108	96.63 192	98.95 179	75.21 345	99.11 191	95.02 201	98.14 168	99.64 126

MVSTER		95.53 187	95.22 184	96.45 221	98.56 161	97.72 88	99.91 95	97.67 255	92.38 225	91.39 266	97.14 268	97.24 18	97.30 303	94.80 210	87.85 300	94.34 301

tpm2		95.47 188	95.18 186	96.35 226	96.91 272	91.70 292	96.96 378	97.93 232	88.04 328	98.44 132	95.40 332	93.32 118	97.97 274	94.00 227	95.61 227	99.38 177

test_vis1_n_1920		95.44 189	95.31 181	95.82 240	98.50 171	88.74 343	99.98 17	97.30 300	97.84 21	99.85 13	99.19 153	66.82 382	99.97 57	98.82 90	99.46 114	98.76 229

QAPM		95.40 190	94.17 212	99.10 69	96.92 271	97.71 89	99.40 236	98.68 74	89.31 299	88.94 311	98.89 184	82.48 271	99.96 67	93.12 251	99.83 77	99.62 132

reproduce_monomvs		95.38 191	95.07 190	96.32 227	99.32 104	96.60 138	99.76 162	98.85 57	96.65 65	87.83 330	96.05 309	99.52 1	98.11 266	96.58 180	81.07 354	94.25 306

test_fmvs1		95.35 192	95.68 172	94.36 292	98.99 124	84.98 376	99.96 41	96.65 362	97.60 27	99.73 38	98.96 174	71.58 361	99.93 92	98.31 122	99.37 122	98.17 246

UGNet		95.33 193	94.57 202	97.62 178	98.55 164	94.85 207	98.67 324	99.32 26	95.75 91	96.80 189	96.27 300	72.18 358	99.96 67	94.58 217	99.05 138	98.04 250
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		95.24 194	96.90 118	90.25 366	98.65 157	72.11 413	98.28 345	97.64 258	89.99 292	95.93 210	98.25 236	94.74 70	99.11 191	99.01 78	99.64 92	99.53 157

BH-untuned		95.18 195	94.83 197	96.22 229	98.36 180	91.22 300	99.80 151	97.32 298	90.91 269	91.08 269	98.67 204	83.51 264	98.54 227	94.23 225	99.61 99	98.92 220

BH-RMVSNet		95.18 195	94.31 209	97.80 162	98.17 196	95.23 197	99.76 162	97.53 275	92.52 219	94.27 235	99.25 149	76.84 326	98.80 207	90.89 281	99.54 104	99.35 184

PCF-MVS	94.20 5	95.18 195	94.10 213	98.43 127	98.55 164	95.99 165	97.91 360	97.31 299	90.35 283	89.48 297	99.22 151	85.19 250	99.89 105	90.40 292	98.47 155	99.41 175
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
dp		95.05 198	94.43 204	96.91 207	97.99 207	92.73 264	96.29 389	97.98 227	89.70 296	95.93 210	94.67 364	93.83 107	98.45 233	86.91 335	96.53 202	99.54 153

Fast-Effi-MVS+		95.02 199	94.19 211	97.52 183	97.88 213	94.55 215	99.97 33	97.08 325	88.85 313	94.47 231	97.96 248	84.59 256	98.41 236	89.84 299	97.10 190	99.59 139

IB-MVS	92.85 6	94.99 200	93.94 219	98.16 141	97.72 228	95.69 178	99.99 5	98.81 62	94.28 142	92.70 254	96.90 278	95.08 58	99.17 188	96.07 186	73.88 393	99.60 138
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		94.92 201	94.36 206	96.59 218	98.85 143	91.29 299	98.93 296	98.94 42	95.90 86	98.77 114	98.42 228	90.89 178	99.77 137	97.80 148	70.76 399	98.72 233

MonoMVSNet		94.82 202	94.43 204	95.98 234	94.54 336	90.73 309	99.03 285	97.06 327	93.16 186	93.15 247	95.47 329	88.29 213	97.57 291	97.85 146	91.33 270	99.62 132

XVG-OURS		94.82 202	94.74 200	95.06 260	98.00 206	89.19 337	99.08 273	97.55 271	94.10 148	94.71 227	99.62 110	80.51 296	99.74 143	96.04 187	93.06 265	96.25 275

SDMVSNet		94.80 204	93.96 218	97.33 197	98.92 134	95.42 188	99.59 205	98.99 38	92.41 223	92.55 256	97.85 252	75.81 338	98.93 202	97.90 144	91.62 268	97.64 258

ADS-MVSNet		94.79 205	94.02 216	97.11 203	97.87 214	93.79 236	94.24 401	98.16 211	90.07 289	96.43 198	94.48 369	90.29 189	98.19 262	87.44 322	97.23 187	99.36 181

XVG-OURS-SEG-HR		94.79 205	94.70 201	95.08 259	98.05 204	89.19 337	99.08 273	97.54 273	93.66 171	94.87 226	99.58 115	78.78 312	99.79 132	97.31 162	93.40 260	96.25 275

OpenMVS	90.15 15	94.77 207	93.59 227	98.33 133	96.07 296	97.48 102	99.56 212	98.57 95	90.46 280	86.51 348	98.95 179	78.57 315	99.94 84	93.86 230	99.74 86	97.57 263

LFMVS		94.75 208	93.56 229	98.30 135	99.03 118	95.70 176	98.74 316	97.98 227	87.81 332	98.47 131	99.39 136	67.43 380	99.53 160	98.01 136	95.20 237	99.67 120

SCA		94.69 209	93.81 223	97.33 197	97.10 262	94.44 216	98.86 306	98.32 184	93.30 181	96.17 206	95.59 321	76.48 331	97.95 277	91.06 275	97.43 182	99.59 139

ab-mvs		94.69 209	93.42 233	98.51 121	98.07 203	96.26 152	96.49 384	98.68 74	90.31 285	94.54 228	97.00 276	76.30 333	99.71 147	95.98 188	93.38 261	99.56 148

CVMVSNet		94.68 211	94.94 195	93.89 311	96.80 280	86.92 364	99.06 278	98.98 39	94.45 127	94.23 236	99.02 163	85.60 244	95.31 381	90.91 280	95.39 232	99.43 173

cascas		94.64 212	93.61 224	97.74 171	97.82 218	96.26 152	99.96 41	97.78 248	85.76 357	94.00 238	97.54 258	76.95 325	99.21 182	97.23 164	95.43 231	97.76 257

HQP-MVS		94.61 213	94.50 203	94.92 265	95.78 304	91.85 284	99.87 116	97.89 237	96.82 57	93.37 243	98.65 207	80.65 294	98.39 240	97.92 142	89.60 273	94.53 283

TR-MVS		94.54 214	93.56 229	97.49 185	97.96 209	94.34 223	98.71 319	97.51 278	90.30 286	94.51 230	98.69 203	75.56 339	98.77 210	92.82 254	95.99 214	99.35 184

DP-MVS		94.54 214	93.42 233	97.91 159	99.46 98	94.04 230	98.93 296	97.48 281	81.15 392	90.04 280	99.55 119	87.02 229	99.95 76	88.97 305	98.11 169	99.73 110

Effi-MVS+-dtu		94.53 216	95.30 182	92.22 345	97.77 221	82.54 389	99.59 205	97.06 327	94.92 111	95.29 222	95.37 336	85.81 243	97.89 280	94.80 210	97.07 191	96.23 277

WBMVS		94.52 217	94.03 215	95.98 234	98.38 177	96.68 134	99.92 87	97.63 259	90.75 276	89.64 293	95.25 344	96.77 25	96.90 330	94.35 222	83.57 332	94.35 299

HQP_MVS		94.49 218	94.36 206	94.87 266	95.71 314	91.74 288	99.84 135	97.87 239	96.38 75	93.01 248	98.59 212	80.47 298	98.37 246	97.79 151	89.55 276	94.52 285

myMVS_eth3d		94.46 219	94.76 199	93.55 321	97.68 231	90.97 302	99.71 183	98.35 177	90.79 273	92.10 260	98.67 204	92.46 147	93.09 404	87.13 328	95.95 218	96.59 273

TAPA-MVS	92.12 8	94.42 220	93.60 226	96.90 208	99.33 102	91.78 287	99.78 154	98.00 224	89.89 294	94.52 229	99.47 125	91.97 158	99.18 187	69.90 407	99.52 106	99.73 110
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
hse-mvs2		94.38 221	94.08 214	95.31 254	98.27 188	90.02 326	99.29 256	98.56 100	95.90 86	98.77 114	98.00 244	90.89 178	98.26 259	97.80 148	69.20 405	97.64 258

ET-MVSNet_ETH3D		94.37 222	93.28 239	97.64 175	98.30 184	97.99 77	99.99 5	97.61 265	94.35 136	71.57 411	99.45 128	96.23 35	95.34 380	96.91 177	85.14 320	99.59 139

MSDG		94.37 222	93.36 237	97.40 191	98.88 141	93.95 234	99.37 244	97.38 290	85.75 359	90.80 273	99.17 155	84.11 262	99.88 111	86.35 336	98.43 156	98.36 243

GeoE		94.36 224	93.48 231	96.99 205	97.29 258	93.54 245	99.96 41	96.72 359	88.35 324	93.43 242	98.94 181	82.05 273	98.05 271	88.12 317	96.48 205	99.37 179

miper_enhance_ethall		94.36 224	93.98 217	95.49 245	98.68 152	95.24 196	99.73 176	97.29 303	93.28 182	89.86 285	95.97 310	94.37 85	97.05 319	92.20 259	84.45 325	94.19 311

tpmvs		94.28 226	93.57 228	96.40 223	98.55 164	91.50 297	95.70 399	98.55 106	87.47 334	92.15 259	94.26 374	91.42 163	98.95 201	88.15 315	95.85 221	98.76 229

test_fmvs1_n		94.25 227	94.36 206	93.92 308	97.68 231	83.70 383	99.90 101	96.57 365	97.40 33	99.67 44	98.88 185	61.82 401	99.92 97	98.23 125	99.13 133	98.14 249

FIs		94.10 228	93.43 232	96.11 231	94.70 333	96.82 130	99.58 207	98.93 46	92.54 217	89.34 300	97.31 264	87.62 221	97.10 316	94.22 226	86.58 309	94.40 294

CLD-MVS		94.06 229	93.90 220	94.55 281	96.02 298	90.69 310	99.98 17	97.72 251	96.62 68	91.05 271	98.85 193	77.21 320	98.47 229	98.11 131	89.51 278	94.48 287
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
testing3		93.92 230	94.23 210	92.99 335	97.54 240	90.23 321	99.99 5	99.16 31	90.57 278	91.33 268	98.63 210	92.99 129	92.52 408	82.46 364	95.39 232	96.22 278

test0.0.03 1		93.86 231	93.61 224	94.64 275	95.02 329	92.18 277	99.93 84	98.58 93	94.07 150	87.96 328	98.50 220	93.90 103	94.96 385	81.33 371	93.17 262	96.78 270

X-MVStestdata		93.83 232	92.06 265	99.15 61	99.94 13	97.50 100	99.94 77	98.42 155	96.22 81	99.41 76	41.37 434	94.34 86	99.96 67	98.92 83	99.95 50	99.99 23

GA-MVS		93.83 232	92.84 245	96.80 210	95.73 311	93.57 243	99.88 113	97.24 308	92.57 216	92.92 250	96.66 287	78.73 313	97.67 288	87.75 320	94.06 252	99.17 202

FC-MVSNet-test		93.81 234	93.15 241	95.80 241	94.30 341	96.20 157	99.42 235	98.89 50	92.33 227	89.03 310	97.27 266	87.39 224	96.83 337	93.20 246	86.48 310	94.36 296

ADS-MVSNet2		93.80 235	93.88 221	93.55 321	97.87 214	85.94 370	94.24 401	96.84 350	90.07 289	96.43 198	94.48 369	90.29 189	95.37 379	87.44 322	97.23 187	99.36 181

cl22		93.77 236	93.25 240	95.33 253	99.49 95	94.43 217	99.61 203	98.09 217	90.38 281	89.16 308	95.61 319	90.56 183	97.34 299	91.93 263	84.45 325	94.21 310

VDD-MVS		93.77 236	92.94 244	96.27 228	98.55 164	90.22 322	98.77 315	97.79 246	90.85 271	96.82 188	99.42 129	61.18 404	99.77 137	98.95 79	94.13 250	98.82 226

EI-MVSNet		93.73 238	93.40 236	94.74 271	96.80 280	92.69 265	99.06 278	97.67 255	88.96 308	91.39 266	99.02 163	88.75 210	97.30 303	91.07 274	87.85 300	94.22 308

Fast-Effi-MVS+-dtu		93.72 239	93.86 222	93.29 326	97.06 264	86.16 367	99.80 151	96.83 351	92.66 209	92.58 255	97.83 254	81.39 282	97.67 288	89.75 300	96.87 198	96.05 280

tpm		93.70 240	93.41 235	94.58 279	95.36 324	87.41 359	97.01 376	96.90 346	90.85 271	96.72 191	94.14 375	90.40 186	96.84 335	90.75 284	88.54 292	99.51 162

PS-MVSNAJss		93.64 241	93.31 238	94.61 276	92.11 380	92.19 276	99.12 269	97.38 290	92.51 220	88.45 319	96.99 277	91.20 167	97.29 306	94.36 220	87.71 302	94.36 296

test_vis1_n		93.61 242	93.03 243	95.35 251	95.86 303	86.94 363	99.87 116	96.36 371	96.85 55	99.54 63	98.79 195	52.41 414	99.83 127	98.64 103	98.97 140	99.29 193

sd_testset		93.55 243	92.83 246	95.74 242	98.92 134	90.89 307	98.24 347	98.85 57	92.41 223	92.55 256	97.85 252	71.07 366	98.68 220	93.93 228	91.62 268	97.64 258

gg-mvs-nofinetune		93.51 244	91.86 270	98.47 123	97.72 228	97.96 81	92.62 409	98.51 118	74.70 411	97.33 172	69.59 425	98.91 4	97.79 283	97.77 153	99.56 103	99.67 120

nrg030		93.51 244	92.53 257	96.45 221	94.36 339	97.20 113	99.81 147	97.16 315	91.60 246	89.86 285	97.46 259	86.37 238	97.68 287	95.88 190	80.31 362	94.46 288

tpm cat1		93.51 244	92.52 258	96.47 219	97.77 221	91.47 298	96.13 391	98.06 220	80.98 393	92.91 251	93.78 378	89.66 194	98.87 203	87.03 331	96.39 207	99.09 210

CR-MVSNet		93.45 247	92.62 251	95.94 236	96.29 290	92.66 266	92.01 412	96.23 373	92.62 211	96.94 183	93.31 383	91.04 172	96.03 369	79.23 380	95.96 216	99.13 207

AUN-MVS		93.28 248	92.60 252	95.34 252	98.29 185	90.09 325	99.31 251	98.56 100	91.80 243	96.35 202	98.00 244	89.38 199	98.28 255	92.46 256	69.22 404	97.64 258

OPM-MVS		93.21 249	92.80 247	94.44 288	93.12 362	90.85 308	99.77 157	97.61 265	96.19 83	91.56 265	98.65 207	75.16 346	98.47 229	93.78 237	89.39 279	93.99 334
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
dmvs_re		93.20 250	93.15 241	93.34 324	96.54 288	83.81 382	98.71 319	98.51 118	91.39 258	92.37 258	98.56 217	78.66 314	97.83 282	93.89 229	89.74 272	98.38 242

kuosan		93.17 251	92.60 252	94.86 269	98.40 176	89.54 335	98.44 336	98.53 113	84.46 372	88.49 318	97.92 249	90.57 182	97.05 319	83.10 360	93.49 258	97.99 251

miper_ehance_all_eth		93.16 252	92.60 252	94.82 270	97.57 239	93.56 244	99.50 222	97.07 326	88.75 315	88.85 312	95.52 325	90.97 174	96.74 340	90.77 283	84.45 325	94.17 312

VDDNet		93.12 253	91.91 268	96.76 212	96.67 287	92.65 268	98.69 322	98.21 201	82.81 385	97.75 162	99.28 142	61.57 402	99.48 171	98.09 133	94.09 251	98.15 247

Anonymous202405211		93.10 254	91.99 266	96.40 223	99.10 114	89.65 333	98.88 302	97.93 232	83.71 377	94.00 238	98.75 197	68.79 371	99.88 111	95.08 200	91.71 267	99.68 118

UniMVSNet (Re)		93.07 255	92.13 262	95.88 237	94.84 330	96.24 156	99.88 113	98.98 39	92.49 221	89.25 302	95.40 332	87.09 228	97.14 312	93.13 250	78.16 373	94.26 304

LPG-MVS_test		92.96 256	92.71 250	93.71 315	95.43 322	88.67 345	99.75 166	97.62 262	92.81 199	90.05 278	98.49 221	75.24 342	98.40 238	95.84 191	89.12 280	94.07 326

UniMVSNet_NR-MVSNet		92.95 257	92.11 263	95.49 245	94.61 335	95.28 194	99.83 142	99.08 34	91.49 249	89.21 305	96.86 281	87.14 227	96.73 341	93.20 246	77.52 378	94.46 288

WB-MVSnew		92.90 258	92.77 249	93.26 328	96.95 270	93.63 242	99.71 183	98.16 211	91.49 249	94.28 234	98.14 239	81.33 284	96.48 350	79.47 379	95.46 229	89.68 405

ACMM	91.95 10	92.88 259	92.52 258	93.98 307	95.75 310	89.08 341	99.77 157	97.52 277	93.00 191	89.95 282	97.99 246	76.17 335	98.46 232	93.63 242	88.87 284	94.39 295
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_djsdf		92.83 260	92.29 261	94.47 286	91.90 383	92.46 271	99.55 214	97.27 305	91.17 261	89.96 281	96.07 308	81.10 286	96.89 331	94.67 215	88.91 282	94.05 328

D2MVS		92.76 261	92.59 256	93.27 327	95.13 325	89.54 335	99.69 188	99.38 22	92.26 228	87.59 333	94.61 366	85.05 252	97.79 283	91.59 268	88.01 298	92.47 378

ACMP	92.05 9	92.74 262	92.42 260	93.73 313	95.91 302	88.72 344	99.81 147	97.53 275	94.13 146	87.00 342	98.23 237	74.07 352	98.47 229	96.22 185	88.86 285	93.99 334
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
VPA-MVSNet		92.70 263	91.55 275	96.16 230	95.09 326	96.20 157	98.88 302	99.00 37	91.02 268	91.82 263	95.29 342	76.05 337	97.96 276	95.62 195	81.19 349	94.30 302

FMVSNet3		92.69 264	91.58 273	95.99 233	98.29 185	97.42 105	99.26 260	97.62 262	89.80 295	89.68 289	95.32 338	81.62 281	96.27 359	87.01 332	85.65 314	94.29 303

IterMVS-LS		92.69 264	92.11 263	94.43 290	96.80 280	92.74 262	99.45 233	96.89 347	88.98 306	89.65 292	95.38 335	88.77 209	96.34 356	90.98 278	82.04 343	94.22 308
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Patchmatch-test		92.65 266	91.50 276	96.10 232	96.85 277	90.49 316	91.50 414	97.19 310	82.76 386	90.23 277	95.59 321	95.02 61	98.00 273	77.41 390	96.98 196	99.82 97

c3_l		92.53 267	91.87 269	94.52 282	97.40 249	92.99 258	99.40 236	96.93 344	87.86 330	88.69 315	95.44 330	89.95 192	96.44 352	90.45 289	80.69 359	94.14 321

AllTest		92.48 268	91.64 271	95.00 262	99.01 119	88.43 349	98.94 294	96.82 353	86.50 348	88.71 313	98.47 225	74.73 348	99.88 111	85.39 344	96.18 210	96.71 271

DU-MVS		92.46 269	91.45 278	95.49 245	94.05 345	95.28 194	99.81 147	98.74 68	92.25 229	89.21 305	96.64 289	81.66 279	96.73 341	93.20 246	77.52 378	94.46 288

eth_miper_zixun_eth		92.41 270	91.93 267	93.84 312	97.28 259	90.68 311	98.83 309	96.97 338	88.57 320	89.19 307	95.73 316	89.24 204	96.69 343	89.97 298	81.55 346	94.15 318

DIV-MVS_self_test		92.32 271	91.60 272	94.47 286	97.31 256	92.74 262	99.58 207	96.75 357	86.99 343	87.64 332	95.54 323	89.55 197	96.50 349	88.58 309	82.44 340	94.17 312

cl____		92.31 272	91.58 273	94.52 282	97.33 255	92.77 260	99.57 210	96.78 356	86.97 344	87.56 334	95.51 326	89.43 198	96.62 345	88.60 308	82.44 340	94.16 317

LCM-MVSNet-Re		92.31 272	92.60 252	91.43 354	97.53 241	79.27 406	99.02 287	91.83 421	92.07 232	80.31 386	94.38 372	83.50 265	95.48 377	97.22 165	97.58 180	99.54 153

WR-MVS		92.31 272	91.25 280	95.48 248	94.45 338	95.29 193	99.60 204	98.68 74	90.10 288	88.07 327	96.89 279	80.68 293	96.80 339	93.14 249	79.67 366	94.36 296

COLMAP_ROB	90.47 14	92.18 275	91.49 277	94.25 296	99.00 123	88.04 355	98.42 340	96.70 360	82.30 388	88.43 322	99.01 165	76.97 324	99.85 117	86.11 340	96.50 203	94.86 282
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Anonymous20240529		92.10 276	90.65 288	96.47 219	98.82 144	90.61 313	98.72 318	98.67 77	75.54 408	93.90 240	98.58 215	66.23 384	99.90 100	94.70 214	90.67 271	98.90 223

pmmvs4		92.10 276	91.07 284	95.18 257	92.82 371	94.96 204	99.48 227	96.83 351	87.45 335	88.66 316	96.56 293	83.78 263	96.83 337	89.29 302	84.77 323	93.75 350

jajsoiax		91.92 278	91.18 281	94.15 297	91.35 390	90.95 305	99.00 288	97.42 286	92.61 212	87.38 338	97.08 271	72.46 357	97.36 297	94.53 218	88.77 286	94.13 323

XXY-MVS		91.82 279	90.46 291	95.88 237	93.91 348	95.40 190	98.87 305	97.69 254	88.63 319	87.87 329	97.08 271	74.38 351	97.89 280	91.66 267	84.07 329	94.35 299

miper_lstm_enhance		91.81 280	91.39 279	93.06 334	97.34 253	89.18 339	99.38 242	96.79 355	86.70 347	87.47 336	95.22 345	90.00 191	95.86 373	88.26 313	81.37 348	94.15 318

mvs_tets		91.81 280	91.08 283	94.00 305	91.63 387	90.58 314	98.67 324	97.43 284	92.43 222	87.37 339	97.05 274	71.76 359	97.32 301	94.75 212	88.68 288	94.11 324

VPNet		91.81 280	90.46 291	95.85 239	94.74 332	95.54 184	98.98 289	98.59 91	92.14 230	90.77 274	97.44 260	68.73 373	97.54 293	94.89 208	77.89 375	94.46 288

RPSCF		91.80 283	92.79 248	88.83 377	98.15 198	69.87 415	98.11 354	96.60 364	83.93 375	94.33 233	99.27 145	79.60 304	99.46 174	91.99 262	93.16 263	97.18 268

PVSNet_0	88.03 19	91.80 283	90.27 297	96.38 225	98.27 188	90.46 317	99.94 77	99.61 13	93.99 155	86.26 354	97.39 263	71.13 365	99.89 105	98.77 94	67.05 410	98.79 228

anonymousdsp		91.79 285	90.92 285	94.41 291	90.76 395	92.93 259	98.93 296	97.17 313	89.08 301	87.46 337	95.30 339	78.43 318	96.92 329	92.38 257	88.73 287	93.39 361

JIA-IIPM		91.76 286	90.70 287	94.94 264	96.11 295	87.51 358	93.16 408	98.13 216	75.79 407	97.58 164	77.68 422	92.84 134	97.97 274	88.47 312	96.54 201	99.33 187

TranMVSNet+NR-MVSNet		91.68 287	90.61 290	94.87 266	93.69 352	93.98 233	99.69 188	98.65 78	91.03 267	88.44 320	96.83 285	80.05 301	96.18 362	90.26 294	76.89 386	94.45 293

NR-MVSNet		91.56 288	90.22 298	95.60 243	94.05 345	95.76 172	98.25 346	98.70 71	91.16 263	80.78 385	96.64 289	83.23 268	96.57 347	91.41 269	77.73 377	94.46 288

dongtai		91.55 289	91.13 282	92.82 338	98.16 197	86.35 366	99.47 228	98.51 118	83.24 380	85.07 363	97.56 257	90.33 187	94.94 386	76.09 396	91.73 266	97.18 268

v2v482		91.30 290	90.07 304	95.01 261	93.13 360	93.79 236	99.77 157	97.02 331	88.05 327	89.25 302	95.37 336	80.73 292	97.15 311	87.28 326	80.04 365	94.09 325

WR-MVS_H		91.30 290	90.35 294	94.15 297	94.17 344	92.62 269	99.17 267	98.94 42	88.87 312	86.48 350	94.46 371	84.36 258	96.61 346	88.19 314	78.51 371	93.21 366

tt0805		91.28 292	90.18 300	94.60 277	96.26 292	87.55 357	98.39 341	98.72 69	89.00 305	89.22 304	98.47 225	62.98 397	98.96 200	90.57 286	88.00 299	97.28 267

V42		91.28 292	90.12 303	94.74 271	93.42 357	93.46 247	99.68 190	97.02 331	87.36 336	89.85 287	95.05 350	81.31 285	97.34 299	87.34 325	80.07 364	93.40 360

CP-MVSNet		91.23 294	90.22 298	94.26 295	93.96 347	92.39 273	99.09 271	98.57 95	88.95 309	86.42 351	96.57 292	79.19 308	96.37 354	90.29 293	78.95 368	94.02 329

XVG-ACMP-BASELINE		91.22 295	90.75 286	92.63 341	93.73 351	85.61 371	98.52 333	97.44 283	92.77 203	89.90 284	96.85 282	66.64 383	98.39 240	92.29 258	88.61 289	93.89 342

v1144		91.09 296	89.83 305	94.87 266	93.25 359	93.69 241	99.62 201	96.98 336	86.83 346	89.64 293	94.99 355	80.94 288	97.05 319	85.08 348	81.16 350	93.87 344

FMVSNet2		91.02 297	89.56 311	95.41 250	97.53 241	95.74 173	98.98 289	97.41 288	87.05 340	88.43 322	95.00 354	71.34 362	96.24 361	85.12 347	85.21 319	94.25 306

MVP-Stereo		90.93 298	90.45 293	92.37 344	91.25 392	88.76 342	98.05 357	96.17 375	87.27 338	84.04 367	95.30 339	78.46 317	97.27 308	83.78 356	99.70 89	91.09 389
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
IterMVS		90.91 299	90.17 301	93.12 331	96.78 283	90.42 319	98.89 300	97.05 330	89.03 303	86.49 349	95.42 331	76.59 329	95.02 383	87.22 327	84.09 328	93.93 339
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		90.88 300	89.82 306	94.08 300	97.53 241	91.97 279	98.43 337	96.95 339	87.05 340	89.68 289	94.72 360	71.34 362	96.11 364	87.01 332	85.65 314	94.17 312

test1		90.88 300	89.82 306	94.08 300	97.53 241	91.97 279	98.43 337	96.95 339	87.05 340	89.68 289	94.72 360	71.34 362	96.11 364	87.01 332	85.65 314	94.17 312

IterMVS-SCA-FT		90.85 302	90.16 302	92.93 336	96.72 285	89.96 328	98.89 300	96.99 334	88.95 309	86.63 346	95.67 317	76.48 331	95.00 384	87.04 330	84.04 331	93.84 346

v144192		90.79 303	89.52 313	94.59 278	93.11 363	92.77 260	99.56 212	96.99 334	86.38 350	89.82 288	94.95 357	80.50 297	97.10 316	83.98 354	80.41 360	93.90 341

v148		90.70 304	89.63 309	93.92 308	92.97 366	90.97 302	99.75 166	96.89 347	87.51 333	88.27 325	95.01 352	81.67 278	97.04 322	87.40 324	77.17 383	93.75 350

MS-PatchMatch		90.65 305	90.30 296	91.71 353	94.22 343	85.50 373	98.24 347	97.70 252	88.67 317	86.42 351	96.37 297	67.82 378	98.03 272	83.62 357	99.62 95	91.60 386

ACMH	89.72 17	90.64 306	89.63 309	93.66 319	95.64 319	88.64 347	98.55 329	97.45 282	89.03 303	81.62 380	97.61 256	69.75 369	98.41 236	89.37 301	87.62 304	93.92 340
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PS-CasMVS		90.63 307	89.51 314	93.99 306	93.83 349	91.70 292	98.98 289	98.52 115	88.48 321	86.15 355	96.53 294	75.46 340	96.31 358	88.83 306	78.86 370	93.95 337

v1192		90.62 308	89.25 318	94.72 273	93.13 360	93.07 254	99.50 222	97.02 331	86.33 351	89.56 296	95.01 352	79.22 307	97.09 318	82.34 366	81.16 350	94.01 331

v8		90.54 309	89.17 319	94.66 274	93.43 356	93.40 250	99.20 264	96.94 343	85.76 357	87.56 334	94.51 367	81.96 275	97.19 309	84.94 349	78.25 372	93.38 362

v1921920		90.46 310	89.12 320	94.50 284	92.96 367	92.46 271	99.49 224	96.98 336	86.10 353	89.61 295	95.30 339	78.55 316	97.03 324	82.17 367	80.89 358	94.01 331

our_test_3		90.39 311	89.48 316	93.12 331	92.40 376	89.57 334	99.33 248	96.35 372	87.84 331	85.30 360	94.99 355	84.14 261	96.09 367	80.38 375	84.56 324	93.71 355

PatchT		90.38 312	88.75 328	95.25 256	95.99 299	90.16 323	91.22 416	97.54 273	76.80 403	97.26 175	86.01 416	91.88 159	96.07 368	66.16 415	95.91 220	99.51 162

ACMH+	89.98 16	90.35 313	89.54 312	92.78 340	95.99 299	86.12 368	98.81 311	97.18 312	89.38 298	83.14 373	97.76 255	68.42 375	98.43 234	89.11 304	86.05 312	93.78 349

Baseline_NR-MVSNet		90.33 314	89.51 314	92.81 339	92.84 369	89.95 329	99.77 157	93.94 411	84.69 371	89.04 309	95.66 318	81.66 279	96.52 348	90.99 277	76.98 384	91.97 384

MIMVSNet		90.30 315	88.67 329	95.17 258	96.45 289	91.64 294	92.39 410	97.15 316	85.99 354	90.50 275	93.19 385	66.95 381	94.86 388	82.01 368	93.43 259	99.01 217

LTVRE_ROB	88.28 18	90.29 316	89.05 323	94.02 303	95.08 327	90.15 324	97.19 371	97.43 284	84.91 369	83.99 369	97.06 273	74.00 353	98.28 255	84.08 352	87.71 302	93.62 356
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		90.25 317	88.82 326	94.57 280	93.53 354	93.43 248	99.08 273	96.87 349	85.00 366	87.34 340	94.51 367	80.93 289	97.02 326	82.85 362	79.23 367	93.26 364

v1240		90.20 318	88.79 327	94.44 288	93.05 365	92.27 275	99.38 242	96.92 345	85.89 355	89.36 299	94.87 359	77.89 319	97.03 324	80.66 374	81.08 353	94.01 331

PEN-MVS		90.19 319	89.06 322	93.57 320	93.06 364	90.90 306	99.06 278	98.47 127	88.11 326	85.91 357	96.30 299	76.67 327	95.94 372	87.07 329	76.91 385	93.89 342

pmmvs5		90.17 320	89.09 321	93.40 323	92.10 381	89.77 332	99.74 169	95.58 388	85.88 356	87.24 341	95.74 314	73.41 355	96.48 350	88.54 310	83.56 333	93.95 337

EU-MVSNet		90.14 321	90.34 295	89.54 372	92.55 374	81.06 400	98.69 322	98.04 223	91.41 257	86.59 347	96.84 284	80.83 291	93.31 403	86.20 338	81.91 344	94.26 304

UniMVSNet_ETH3D		90.06 322	88.58 331	94.49 285	94.67 334	88.09 354	97.81 363	97.57 270	83.91 376	88.44 320	97.41 261	57.44 408	97.62 290	91.41 269	88.59 291	97.77 256

Syy-MVS		90.00 323	90.63 289	88.11 384	97.68 231	74.66 411	99.71 183	98.35 177	90.79 273	92.10 260	98.67 204	79.10 310	93.09 404	63.35 418	95.95 218	96.59 273

USDC		90.00 323	88.96 324	93.10 333	94.81 331	88.16 353	98.71 319	95.54 389	93.66 171	83.75 371	97.20 267	65.58 386	98.31 251	83.96 355	87.49 306	92.85 372

Anonymous20231211		89.86 325	88.44 333	94.13 299	98.93 131	90.68 311	98.54 331	98.26 194	76.28 404	86.73 344	95.54 323	70.60 367	97.56 292	90.82 282	80.27 363	94.15 318

OurMVSNet-221017-0		89.81 326	89.48 316	90.83 360	91.64 386	81.21 398	98.17 352	95.38 392	91.48 251	85.65 359	97.31 264	72.66 356	97.29 306	88.15 315	84.83 322	93.97 336

RPMNet		89.76 327	87.28 344	97.19 200	96.29 290	92.66 266	92.01 412	98.31 186	70.19 418	96.94 183	85.87 417	87.25 226	99.78 134	62.69 419	95.96 216	99.13 207

Patchmtry		89.70 328	88.49 332	93.33 325	96.24 293	89.94 331	91.37 415	96.23 373	78.22 401	87.69 331	93.31 383	91.04 172	96.03 369	80.18 378	82.10 342	94.02 329

v7n		89.65 329	88.29 335	93.72 314	92.22 378	90.56 315	99.07 277	97.10 321	85.42 364	86.73 344	94.72 360	80.06 300	97.13 313	81.14 372	78.12 374	93.49 358

SSC-MVS3.2		89.59 330	88.66 330	92.38 342	94.29 342	86.12 368	99.49 224	97.66 257	90.28 287	88.63 317	95.18 346	64.46 391	96.88 333	85.30 346	82.66 337	94.14 321

ppachtmachnet_test		89.58 331	88.35 334	93.25 329	92.40 376	90.44 318	99.33 248	96.73 358	85.49 362	85.90 358	95.77 313	81.09 287	96.00 371	76.00 397	82.49 339	93.30 363

test_fmvs2		89.47 332	89.70 308	88.77 380	94.54 336	75.74 408	99.83 142	94.70 404	94.71 119	91.08 269	96.82 286	54.46 411	97.78 285	92.87 253	88.27 295	92.80 373

DTE-MVSNet		89.40 333	88.24 336	92.88 337	92.66 373	89.95 329	99.10 270	98.22 200	87.29 337	85.12 362	96.22 301	76.27 334	95.30 382	83.56 358	75.74 390	93.41 359

pm-mvs1		89.36 334	87.81 340	94.01 304	93.40 358	91.93 282	98.62 327	96.48 369	86.25 352	83.86 370	96.14 304	73.68 354	97.04 322	86.16 339	75.73 391	93.04 369

tfpnnormal		89.29 335	87.61 342	94.34 293	94.35 340	94.13 229	98.95 293	98.94 42	83.94 374	84.47 366	95.51 326	74.84 347	97.39 296	77.05 393	80.41 360	91.48 388

LF4IMVS		89.25 336	88.85 325	90.45 365	92.81 372	81.19 399	98.12 353	94.79 401	91.44 253	86.29 353	97.11 269	65.30 389	98.11 266	88.53 311	85.25 318	92.07 381

testgi		89.01 337	88.04 338	91.90 349	93.49 355	84.89 377	99.73 176	95.66 386	93.89 164	85.14 361	98.17 238	59.68 405	94.66 391	77.73 389	88.88 283	96.16 279

SixPastTwentyTwo		88.73 338	88.01 339	90.88 357	91.85 384	82.24 391	98.22 350	95.18 397	88.97 307	82.26 376	96.89 279	71.75 360	96.67 344	84.00 353	82.98 334	93.72 354

mmtdpeth		88.52 339	87.75 341	90.85 359	95.71 314	83.47 385	98.94 294	94.85 399	88.78 314	97.19 177	89.58 402	63.29 395	98.97 198	98.54 108	62.86 418	90.10 401

FMVSNet1		88.50 340	86.64 347	94.08 300	95.62 321	91.97 279	98.43 337	96.95 339	83.00 383	86.08 356	94.72 360	59.09 406	96.11 364	81.82 370	84.07 329	94.17 312

FMVSNet5		88.32 341	87.47 343	90.88 357	96.90 275	88.39 351	97.28 369	95.68 385	82.60 387	84.67 365	92.40 391	79.83 302	91.16 413	76.39 395	81.51 347	93.09 367

DSMNet-mixed		88.28 342	88.24 336	88.42 382	89.64 403	75.38 410	98.06 356	89.86 425	85.59 361	88.20 326	92.14 393	76.15 336	91.95 411	78.46 386	96.05 213	97.92 252

ttmdpeth		88.23 343	87.06 346	91.75 352	89.91 402	87.35 360	98.92 299	95.73 383	87.92 329	84.02 368	96.31 298	68.23 377	96.84 335	86.33 337	76.12 388	91.06 390

K. test v3		88.05 344	87.24 345	90.47 364	91.82 385	82.23 392	98.96 292	97.42 286	89.05 302	76.93 401	95.60 320	68.49 374	95.42 378	85.87 343	81.01 356	93.75 350

KD-MVS_2432*1600		88.00 345	86.10 349	93.70 317	96.91 272	94.04 230	97.17 372	97.12 319	84.93 367	81.96 377	92.41 389	92.48 145	94.51 392	79.23 380	52.68 424	92.56 375

miper_refine_blended		88.00 345	86.10 349	93.70 317	96.91 272	94.04 230	97.17 372	97.12 319	84.93 367	81.96 377	92.41 389	92.48 145	94.51 392	79.23 380	52.68 424	92.56 375

TinyColmap		87.87 347	86.51 348	91.94 348	95.05 328	85.57 372	97.65 364	94.08 408	84.40 373	81.82 379	96.85 282	62.14 400	98.33 249	80.25 377	86.37 311	91.91 385

TransMVSNet (Re)		87.25 348	85.28 355	93.16 330	93.56 353	91.03 301	98.54 331	94.05 410	83.69 378	81.09 383	96.16 303	75.32 341	96.40 353	76.69 394	68.41 406	92.06 382

Patchmatch-RL test		86.90 349	85.98 353	89.67 371	84.45 414	75.59 409	89.71 420	92.43 418	86.89 345	77.83 398	90.94 397	94.22 92	93.63 400	87.75 320	69.61 401	99.79 102

test_vis1_rt		86.87 350	86.05 352	89.34 373	96.12 294	78.07 407	99.87 116	83.54 432	92.03 235	78.21 396	89.51 403	45.80 418	99.91 98	96.25 184	93.11 264	90.03 402

Anonymous20231206		86.32 351	85.42 354	89.02 376	89.11 405	80.53 404	99.05 282	95.28 393	85.43 363	82.82 374	93.92 376	74.40 350	93.44 402	66.99 412	81.83 345	93.08 368

MVS-HIRNet		86.22 352	83.19 365	95.31 254	96.71 286	90.29 320	92.12 411	97.33 297	62.85 419	86.82 343	70.37 424	69.37 370	97.49 294	75.12 398	97.99 174	98.15 247

pmmvs6		85.69 353	83.84 360	91.26 356	90.00 401	84.41 380	97.82 362	96.15 376	75.86 406	81.29 382	95.39 334	61.21 403	96.87 334	83.52 359	73.29 394	92.50 377

test_0402		85.58 354	83.94 359	90.50 363	93.81 350	85.04 375	98.55 329	95.20 396	76.01 405	79.72 390	95.13 347	64.15 393	96.26 360	66.04 416	86.88 308	90.21 399

UnsupCasMVSNet_eth		85.52 355	83.99 357	90.10 368	89.36 404	83.51 384	96.65 382	97.99 225	89.14 300	75.89 405	93.83 377	63.25 396	93.92 396	81.92 369	67.90 409	92.88 371

MDA-MVSNet_test_wron		85.51 356	83.32 364	92.10 346	90.96 393	88.58 348	99.20 264	96.52 367	79.70 398	57.12 424	92.69 387	79.11 309	93.86 398	77.10 392	77.46 380	93.86 345

YYNet1		85.50 357	83.33 363	92.00 347	90.89 394	88.38 352	99.22 263	96.55 366	79.60 399	57.26 423	92.72 386	79.09 311	93.78 399	77.25 391	77.37 381	93.84 346

EG-PatchMatch MVS		85.35 358	83.81 361	89.99 370	90.39 397	81.89 394	98.21 351	96.09 377	81.78 390	74.73 407	93.72 379	51.56 416	97.12 315	79.16 383	88.61 289	90.96 392

Anonymous20240521		85.15 359	83.81 361	89.16 375	88.32 406	82.69 387	98.80 313	95.74 382	79.72 397	81.53 381	90.99 396	65.38 388	94.16 394	72.69 402	81.11 352	90.63 396

MVStest1		85.03 360	82.76 369	91.83 350	92.95 368	89.16 340	98.57 328	94.82 400	71.68 416	68.54 416	95.11 349	83.17 269	95.66 375	74.69 399	65.32 413	90.65 395

mvs5depth		84.87 361	82.90 368	90.77 361	85.59 413	84.84 378	91.10 417	93.29 416	83.14 381	85.07 363	94.33 373	62.17 399	97.32 301	78.83 385	72.59 397	90.14 400

TDRefinement		84.76 362	82.56 370	91.38 355	74.58 428	84.80 379	97.36 368	94.56 405	84.73 370	80.21 387	96.12 307	63.56 394	98.39 240	87.92 318	63.97 416	90.95 393

CMPMVS	61.59 21	84.75 363	85.14 356	83.57 392	90.32 398	62.54 420	96.98 377	97.59 269	74.33 412	69.95 413	96.66 287	64.17 392	98.32 250	87.88 319	88.41 294	89.84 404
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test20.03		84.72 364	83.99 357	86.91 386	88.19 408	80.62 403	98.88 302	95.94 379	88.36 323	78.87 391	94.62 365	68.75 372	89.11 417	66.52 414	75.82 389	91.00 391

CL-MVSNet_self_test		84.50 365	83.15 366	88.53 381	86.00 411	81.79 395	98.82 310	97.35 293	85.12 365	83.62 372	90.91 398	76.66 328	91.40 412	69.53 408	60.36 421	92.40 379

new_pmnet		84.49 366	82.92 367	89.21 374	90.03 400	82.60 388	96.89 380	95.62 387	80.59 394	75.77 406	89.17 404	65.04 390	94.79 389	72.12 404	81.02 355	90.23 398

MDA-MVSNet-bldmvs		84.09 367	81.52 374	91.81 351	91.32 391	88.00 356	98.67 324	95.92 380	80.22 396	55.60 425	93.32 382	68.29 376	93.60 401	73.76 400	76.61 387	93.82 348

pmmvs-eth3d		84.03 368	81.97 372	90.20 367	84.15 415	87.09 362	98.10 355	94.73 403	83.05 382	74.10 409	87.77 411	65.56 387	94.01 395	81.08 373	69.24 403	89.49 408

dmvs_testset		83.79 369	86.07 351	76.94 399	92.14 379	48.60 434	96.75 381	90.27 424	89.48 297	78.65 393	98.55 219	79.25 306	86.65 422	66.85 413	82.69 336	95.57 281

OpenMVS_ROB	79.82 20	83.77 370	81.68 373	90.03 369	88.30 407	82.82 386	98.46 334	95.22 395	73.92 413	76.00 404	91.29 395	55.00 410	96.94 328	68.40 410	88.51 293	90.34 397

KD-MVS_self_test		83.59 371	82.06 371	88.20 383	86.93 409	80.70 402	97.21 370	96.38 370	82.87 384	82.49 375	88.97 405	67.63 379	92.32 409	73.75 401	62.30 420	91.58 387

MIMVSNet1		82.58 372	80.51 378	88.78 378	86.68 410	84.20 381	96.65 382	95.41 391	78.75 400	78.59 394	92.44 388	51.88 415	89.76 416	65.26 417	78.95 368	92.38 380

mvsany_test3		82.12 373	81.14 375	85.06 390	81.87 419	70.41 414	97.09 374	92.14 419	91.27 260	77.84 397	88.73 406	39.31 421	95.49 376	90.75 284	71.24 398	89.29 410

new-patchmatchnet		81.19 374	79.34 381	86.76 387	82.86 418	80.36 405	97.92 359	95.27 394	82.09 389	72.02 410	86.87 413	62.81 398	90.74 415	71.10 405	63.08 417	89.19 411

APD_test1		81.15 375	80.92 376	81.86 395	92.45 375	59.76 424	96.04 394	93.61 414	73.29 414	77.06 399	96.64 289	44.28 420	96.16 363	72.35 403	82.52 338	89.67 406

test_method		80.79 376	79.70 380	84.08 391	92.83 370	67.06 417	99.51 220	95.42 390	54.34 423	81.07 384	93.53 380	44.48 419	92.22 410	78.90 384	77.23 382	92.94 370

PM-MVS		80.47 377	78.88 382	85.26 389	83.79 417	72.22 412	95.89 397	91.08 422	85.71 360	76.56 403	88.30 407	36.64 422	93.90 397	82.39 365	69.57 402	89.66 407

pmmvs3		80.27 378	77.77 383	87.76 385	80.32 423	82.43 390	98.23 349	91.97 420	72.74 415	78.75 392	87.97 410	57.30 409	90.99 414	70.31 406	62.37 419	89.87 403

N_pmnet		80.06 379	80.78 377	77.89 398	91.94 382	45.28 436	98.80 313	56.82 438	78.10 402	80.08 388	93.33 381	77.03 322	95.76 374	68.14 411	82.81 335	92.64 374

test_fmvs3		79.99 380	80.17 379	79.45 397	84.02 416	62.83 418	99.05 282	93.49 415	88.29 325	80.06 389	86.65 414	28.09 426	88.00 418	88.63 307	73.27 395	87.54 414

UnsupCasMVSNet_bld		79.97 381	77.03 386	88.78 378	85.62 412	81.98 393	93.66 406	97.35 293	75.51 409	70.79 412	83.05 419	48.70 417	94.91 387	78.31 387	60.29 422	89.46 409

test_f		78.40 382	77.59 384	80.81 396	80.82 421	62.48 421	96.96 378	93.08 417	83.44 379	74.57 408	84.57 418	27.95 427	92.63 407	84.15 351	72.79 396	87.32 415

WB-MVS		76.28 383	77.28 385	73.29 403	81.18 420	54.68 428	97.87 361	94.19 407	81.30 391	69.43 414	90.70 399	77.02 323	82.06 426	35.71 431	68.11 408	83.13 417

SSC-MVS		75.42 384	76.40 387	72.49 407	80.68 422	53.62 429	97.42 366	94.06 409	80.42 395	68.75 415	90.14 401	76.54 330	81.66 427	33.25 432	66.34 412	82.19 418

EGC-MVSNET		69.38 385	63.76 395	86.26 388	90.32 398	81.66 397	96.24 390	93.85 412	0.99 435	3.22 436	92.33 392	52.44 413	92.92 406	59.53 422	84.90 321	84.21 416

test_vis3_rt		68.82 386	66.69 391	75.21 402	76.24 427	60.41 423	96.44 385	68.71 437	75.13 410	50.54 428	69.52 426	16.42 436	96.32 357	80.27 376	66.92 411	68.89 424

FPMVS		68.72 387	68.72 388	68.71 409	65.95 432	44.27 438	95.97 396	94.74 402	51.13 424	53.26 426	90.50 400	25.11 429	83.00 425	60.80 420	80.97 357	78.87 422

testf1		68.38 388	66.92 389	72.78 405	78.80 424	50.36 431	90.95 418	87.35 430	55.47 421	58.95 420	88.14 408	20.64 431	87.60 419	57.28 423	64.69 414	80.39 420

APD_test2		68.38 388	66.92 389	72.78 405	78.80 424	50.36 431	90.95 418	87.35 430	55.47 421	58.95 420	88.14 408	20.64 431	87.60 419	57.28 423	64.69 414	80.39 420

LCM-MVSNet		67.77 390	64.73 393	76.87 400	62.95 434	56.25 427	89.37 421	93.74 413	44.53 426	61.99 418	80.74 420	20.42 433	86.53 423	69.37 409	59.50 423	87.84 412

PMMVS2		67.15 391	64.15 394	76.14 401	70.56 431	62.07 422	93.89 404	87.52 429	58.09 420	60.02 419	78.32 421	22.38 430	84.54 424	59.56 421	47.03 426	81.80 419

Gipuma		66.95 392	65.00 392	72.79 404	91.52 388	67.96 416	66.16 427	95.15 398	47.89 425	58.54 422	67.99 427	29.74 424	87.54 421	50.20 426	77.83 376	62.87 427
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tmp_tt		65.23 393	62.94 396	72.13 408	44.90 437	50.03 433	81.05 424	89.42 428	38.45 427	48.51 429	99.90 18	54.09 412	78.70 429	91.84 266	18.26 431	87.64 413

ANet_high		56.10 394	52.24 397	67.66 410	49.27 436	56.82 426	83.94 423	82.02 433	70.47 417	33.28 433	64.54 428	17.23 435	69.16 431	45.59 428	23.85 430	77.02 423

PMVS	49.05 23	53.75 395	51.34 399	60.97 412	40.80 438	34.68 439	74.82 426	89.62 427	37.55 428	28.67 434	72.12 423	7.09 438	81.63 428	43.17 429	68.21 407	66.59 426
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		52.30 396	52.18 398	52.67 413	71.51 429	45.40 435	93.62 407	76.60 435	36.01 429	43.50 430	64.13 429	27.11 428	67.31 432	31.06 433	26.06 428	45.30 431

MVE	53.74 22	51.54 397	47.86 401	62.60 411	59.56 435	50.93 430	79.41 425	77.69 434	35.69 430	36.27 432	61.76 431	5.79 440	69.63 430	37.97 430	36.61 427	67.24 425
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		51.44 398	51.22 400	52.11 414	70.71 430	44.97 437	94.04 403	75.66 436	35.34 431	42.40 431	61.56 432	28.93 425	65.87 433	27.64 434	24.73 429	45.49 430

testmvs		40.60 399	44.45 402	29.05 416	19.49 440	14.11 442	99.68 190	18.47 439	20.74 432	64.59 417	98.48 224	10.95 437	17.09 436	56.66 425	11.01 432	55.94 429

test123		37.68 400	39.14 403	33.31 415	19.94 439	24.83 441	98.36 342	9.75 440	15.53 433	51.31 427	87.14 412	19.62 434	17.74 435	47.10 427	3.47 434	57.36 428

cdsmvs_eth3d_5k		23.43 401	31.24 404	0.00 418	0.00 441	0.00 443	0.00 429	98.09 217	0.00 436	0.00 437	99.67 101	83.37 266	0.00 437	0.00 436	0.00 435	0.00 433

wuyk23d		20.37 402	20.84 405	18.99 417	65.34 433	27.73 440	50.43 428	7.67 441	9.50 434	8.01 435	6.34 435	6.13 439	26.24 434	23.40 435	10.69 433	2.99 432

ab-mvs-re		8.28 403	11.04 406	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	99.40 134	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

pcd_1.5k_mvsjas		7.60 404	10.13 407	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 437	91.20 167	0.00 437	0.00 436	0.00 435	0.00 433

mmdepth		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 437	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

monomultidepth		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 437	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

test_blank		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.02 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uanet_test		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 437	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

DCPMVS		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 437	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

sosnet-low-res		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 437	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

sosnet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 437	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uncertanet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 437	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

Regformer		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 437	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uanet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 437	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

WAC-MVS						90.97 302								86.10 341

FOURS1					99.92 31	97.66 94	99.95 60	98.36 175	95.58 95	99.52 66

MSC_two_6792asdad				99.93 2	99.91 39	99.80 2		98.41 160					100.00 1	99.96 9	100.00 1	100.00 1

PC_three_1452									96.96 53	99.80 21	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		98.41 160					100.00 1	99.96 9	100.00 1	100.00 1

test_one_0601					99.94 13	99.30 12		98.41 160	96.63 66	99.75 33	99.93 11	97.49 10

eth-test2					0.00 441

eth-test					0.00 441

ZD-MVS					99.92 31	98.57 56		98.52 115	92.34 226	99.31 84	99.83 46	95.06 59	99.80 130	99.70 41	99.97 42

RE-MVS-def			98.13 55		99.79 62	96.37 149	99.76 162	98.31 186	94.43 131	99.40 78	99.75 74	92.95 131		98.90 86	99.92 64	99.97 61

IU-MVS					99.93 24	99.31 10		98.41 160	97.71 24	99.84 16				100.00 1	100.00 1	100.00 1

OPU-MVS				99.93 2	99.89 45	99.80 2	99.96 41				99.80 54	97.44 14	100.00 1	100.00 1	99.98 32	100.00 1

test_241102_TWO								98.43 143	97.27 40	99.80 21	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		98.43 143	97.26 42	99.80 21	99.88 24	96.71 27	100.00 1

9.14			98.38 37		99.87 51		99.91 95	98.33 182	93.22 183	99.78 30	99.89 22	94.57 77	99.85 117	99.84 22	99.97 42

save fliter					99.82 58	98.79 40	99.96 41	98.40 164	97.66 26

test_0728_THIRD									96.48 69	99.83 17	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 60	98.43 143					100.00 1	99.99 5	100.00 1	100.00 1

test0726					99.93 24	99.29 15	99.96 41	98.42 155	97.28 38	99.86 10	99.94 4	97.22 19

GSMVS																99.59 139

test_part2					99.89 45	99.25 18				99.49 69

sam_mvs1												94.72 71				99.59 139

sam_mvs												94.25 91

ambc				83.23 393	77.17 426	62.61 419	87.38 422	94.55 406		76.72 402	86.65 414	30.16 423	96.36 355	84.85 350	69.86 400	90.73 394

MTGPA								98.28 191

test_post1							95.78 398				59.23 433	93.20 125	97.74 286	91.06 275

test_post											63.35 430	94.43 79	98.13 265

patchmatchnet-post											91.70 394	95.12 56	97.95 277

GG-mvs-BLEND				98.54 117	98.21 192	98.01 76	93.87 405	98.52 115		97.92 153	97.92 249	99.02 3	97.94 279	98.17 127	99.58 102	99.67 120

MTMP							99.87 116	96.49 368

gm-plane-assit					96.97 269	93.76 238			91.47 252		98.96 174		98.79 208	94.92 205

test9_res														99.71 40	99.99 21	100.00 1

TEST9					99.92 31	98.92 29	99.96 41	98.43 143	93.90 162	99.71 40	99.86 29	95.88 41	99.85 117

test_8					99.92 31	98.88 32	99.96 41	98.43 143	94.35 136	99.69 42	99.85 33	95.94 38	99.85 117

agg_prior2														99.48 52	100.00 1	100.00 1

agg_prior					99.93 24	98.77 42		98.43 143		99.63 50			99.85 117

TestCases				95.00 262	99.01 119	88.43 349		96.82 353	86.50 348	88.71 313	98.47 225	74.73 348	99.88 111	85.39 344	96.18 210	96.71 271

test_prior4						98.05 74	99.94 77

test_prior2							99.95 60		95.78 89	99.73 38	99.76 66	96.00 37		99.78 28	100.00 1

test_prior				99.43 35	99.94 13	98.49 60		98.65 78					99.80 130			99.99 23

旧先验2							99.46 232		94.21 145	99.85 13			99.95 76	96.96 174

新几何2							99.40 236

新几何1				99.42 37	99.75 69	98.27 65		98.63 85	92.69 207	99.55 61	99.82 49	94.40 81	100.00 1	91.21 271	99.94 55	99.99 23

旧先验1					99.76 66	97.52 98		98.64 80			99.85 33	95.63 45			99.94 55	99.99 23

无先验							99.49 224	98.71 70	93.46 175				100.00 1	94.36 220		99.99 23

原ACMM2							99.90 101

原ACMM1				98.96 84	99.73 73	96.99 124		98.51 118	94.06 152	99.62 53	99.85 33	94.97 65	99.96 67	95.11 199	99.95 50	99.92 84

test222					99.55 90	97.41 106	99.34 247	98.55 106	91.86 239	99.27 88	99.83 46	93.84 106			99.95 50	99.99 23

testdata2													99.99 36	90.54 288

segment_acmp												96.68 29

testdata				98.42 129	99.47 96	95.33 192		98.56 100	93.78 166	99.79 29	99.85 33	93.64 111	99.94 84	94.97 203	99.94 55	100.00 1

testdata1							99.28 257		96.35 79

test12				99.43 35	99.74 70	98.56 57		98.40 164		99.65 46		94.76 69	99.75 141		99.98 32	99.99 23

plane_prior7					95.71 314	91.59 296

plane_prior6					95.76 308	91.72 291						80.47 298

plane_prior5								97.87 239					98.37 246	97.79 151	89.55 276	94.52 285

plane_prior4											98.59 212

plane_prior3						91.64 294			96.63 66	93.01 248

plane_prior2							99.84 135		96.38 75

plane_prior1					95.73 311

plane_prior						91.74 288	99.86 127		96.76 61						89.59 275

n2								0.00 442

nn								0.00 442

door-mid								89.69 426

lessismore_v0				90.53 362	90.58 396	80.90 401		95.80 381		77.01 400	95.84 311	66.15 385	96.95 327	83.03 361	75.05 392	93.74 353

LGP-MVS_train				93.71 315	95.43 322	88.67 345		97.62 262	92.81 199	90.05 278	98.49 221	75.24 342	98.40 238	95.84 191	89.12 280	94.07 326

test11								98.44 135

door								90.31 423

HQP5-MVS						91.85 284

HQP-NCC					95.78 304		99.87 116		96.82 57	93.37 243

ACMP_Plane					95.78 304		99.87 116		96.82 57	93.37 243

BP-MVS														97.92 142

HQP4-MVS										93.37 243			98.39 240			94.53 283

HQP3-MVS								97.89 237							89.60 273

HQP2-MVS												80.65 294

NP-MVS					95.77 307	91.79 286					98.65 207

MDTV_nov1_ep13_2view						96.26 152	96.11 392		91.89 238	98.06 149		94.40 81		94.30 223		99.67 120

MDTV_nov1_ep13			95.69 170		97.90 212	94.15 228	95.98 395	98.44 135	93.12 189	97.98 151	95.74 314	95.10 57	98.58 224	90.02 296	96.92 197

ACMMP++_ref															87.04 307

ACMMP++															88.23 296

Test By Simon												92.82 136

ITE_SJBPF				92.38 342	95.69 317	85.14 374		95.71 384	92.81 199	89.33 301	98.11 240	70.23 368	98.42 235	85.91 342	88.16 297	93.59 357

DeepMVS_CX				82.92 394	95.98 301	58.66 425		96.01 378	92.72 204	78.34 395	95.51 326	58.29 407	98.08 268	82.57 363	85.29 317	92.03 383

High-resolution multi-view benchmark