High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

fmvsm_l_conf0.5_n_a		99.09 1	99.08 1	99.11 54	99.43 57	97.48 82	98.88 115	99.30 13	98.47 11	99.85 4	99.43 32	96.71 17	99.96 4	99.86 1	99.80 24	99.89 4

SED-MVS		99.09 1	98.91 4	99.63 4	99.71 19	99.24 5	99.02 79	98.87 70	97.65 27	99.73 12	99.48 23	97.53 7	99.94 9	98.43 52	99.81 15	99.70 56

DVP-MVS++		99.08 3	98.89 5	99.64 3	99.17 98	99.23 7	99.69 1	98.88 63	97.32 48	99.53 25	99.47 25	97.81 3	99.94 9	98.47 48	99.72 57	99.74 39

fmvsm_l_conf0.5_n		99.07 4	99.05 2	99.14 50	99.41 59	97.54 80	98.89 110	99.31 12	98.49 10	99.86 2	99.42 33	96.45 24	99.96 4	99.86 1	99.74 51	99.90 3

DVP-MVS		99.03 5	98.83 9	99.63 4	99.72 12	99.25 2	98.97 89	98.58 157	97.62 29	99.45 27	99.46 29	97.42 9	99.94 9	98.47 48	99.81 15	99.69 59
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
APDe-MVS		99.02 6	98.84 8	99.55 9	99.57 33	98.96 16	99.39 10	98.93 51	97.38 45	99.41 30	99.54 13	96.66 18	99.84 72	98.86 27	99.85 6	99.87 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
reproduce_model		98.94 7	98.81 10	99.34 25	99.52 39	98.26 49	98.94 98	98.84 80	98.06 15	99.35 34	99.61 4	96.39 27	99.94 9	98.77 30	99.82 14	99.83 12

reproduce-ours		98.93 8	98.78 11	99.38 18	99.49 46	98.38 35	98.86 121	98.83 82	98.06 15	99.29 38	99.58 9	96.40 25	99.94 9	98.68 32	99.81 15	99.81 17

our_new_method		98.93 8	98.78 11	99.38 18	99.49 46	98.38 35	98.86 121	98.83 82	98.06 15	99.29 38	99.58 9	96.40 25	99.94 9	98.68 32	99.81 15	99.81 17

test_fmvsmconf_n		98.92 10	98.87 6	99.04 58	98.88 131	97.25 97	98.82 133	99.34 10	98.75 4	99.80 5	99.61 4	95.16 73	99.95 7	99.70 7	99.80 24	99.93 1

DPE-MVS		98.92 10	98.67 15	99.65 2	99.58 32	99.20 9	98.42 216	98.91 57	97.58 32	99.54 24	99.46 29	97.10 12	99.94 9	97.64 99	99.84 11	99.83 12
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SteuartSystems-ACMMP		98.90 12	98.75 13	99.36 23	99.22 93	98.43 33	99.10 63	98.87 70	97.38 45	99.35 34	99.40 35	97.78 5	99.87 63	97.77 87	99.85 6	99.78 23
Skip Steuart: Steuart Systems R&D Blog.
test_fmvsm_n_1920		98.87 13	99.01 3	98.45 104	99.42 58	96.43 136	98.96 94	99.36 9	98.63 6	99.86 2	99.51 18	95.91 43	99.97 1	99.72 5	99.75 47	98.94 186

TSAR-MVS + MP.		98.78 14	98.62 16	99.24 39	99.69 24	98.28 48	99.14 54	98.66 137	96.84 77	99.56 22	99.31 55	96.34 28	99.70 124	98.32 58	99.73 54	99.73 44
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CNVR-MVS		98.78 14	98.56 19	99.45 15	99.32 65	98.87 19	98.47 208	98.81 91	97.72 22	98.76 77	99.16 82	97.05 13	99.78 106	98.06 69	99.66 67	99.69 59

MSP-MVS		98.74 16	98.55 20	99.29 32	99.75 3	98.23 50	99.26 27	98.88 63	97.52 35	99.41 30	98.78 139	96.00 39	99.79 103	97.79 86	99.59 82	99.85 9
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
XVS		98.70 17	98.49 24	99.34 25	99.70 22	98.35 44	99.29 22	98.88 63	97.40 42	98.46 95	99.20 72	95.90 45	99.89 52	97.85 82	99.74 51	99.78 23

MCST-MVS		98.65 18	98.37 32	99.48 13	99.60 31	98.87 19	98.41 217	98.68 129	97.04 69	98.52 93	98.80 137	96.78 16	99.83 74	97.93 76	99.61 78	99.74 39

SD-MVS		98.64 19	98.68 14	98.53 95	99.33 62	98.36 43	98.90 106	98.85 79	97.28 51	99.72 14	99.39 36	96.63 20	97.60 366	98.17 64	99.85 6	99.64 74
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
HFP-MVS		98.63 20	98.40 29	99.32 31	99.72 12	98.29 47	99.23 32	98.96 46	96.10 114	98.94 60	99.17 79	96.06 36	99.92 34	97.62 100	99.78 34	99.75 37

ACMMP_NAP		98.61 21	98.30 45	99.55 9	99.62 30	98.95 17	98.82 133	98.81 91	95.80 125	99.16 50	99.47 25	95.37 60	99.92 34	97.89 80	99.75 47	99.79 21

region2R		98.61 21	98.38 31	99.29 32	99.74 7	98.16 56	99.23 32	98.93 51	96.15 111	98.94 60	99.17 79	95.91 43	99.94 9	97.55 107	99.79 30	99.78 23

NCCC		98.61 21	98.35 35	99.38 18	99.28 80	98.61 26	98.45 209	98.76 109	97.82 21	98.45 98	98.93 121	96.65 19	99.83 74	97.38 116	99.41 112	99.71 52

SF-MVS		98.59 24	98.32 44	99.41 17	99.54 35	98.71 22	99.04 73	98.81 91	95.12 161	99.32 37	99.39 36	96.22 30	99.84 72	97.72 90	99.73 54	99.67 68

ACMMPR		98.59 24	98.36 33	99.29 32	99.74 7	98.15 57	99.23 32	98.95 47	96.10 114	98.93 64	99.19 77	95.70 49	99.94 9	97.62 100	99.79 30	99.78 23

test_fmvsmconf0.1_n		98.58 26	98.44 27	98.99 60	97.73 247	97.15 102	98.84 129	98.97 43	98.75 4	99.43 29	99.54 13	93.29 107	99.93 28	99.64 10	99.79 30	99.89 4

SMA-MVS		98.58 26	98.25 48	99.56 8	99.51 40	99.04 15	98.95 95	98.80 98	93.67 244	99.37 33	99.52 16	96.52 22	99.89 52	98.06 69	99.81 15	99.76 36
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
MTAPA		98.58 26	98.29 46	99.46 14	99.76 2	98.64 25	98.90 106	98.74 113	97.27 55	98.02 122	99.39 36	94.81 83	99.96 4	97.91 78	99.79 30	99.77 29

HPM-MVS++		98.58 26	98.25 48	99.55 9	99.50 42	99.08 11	98.72 162	98.66 137	97.51 36	98.15 109	98.83 134	95.70 49	99.92 34	97.53 109	99.67 64	99.66 71

SR-MVS		98.57 30	98.35 35	99.24 39	99.53 36	98.18 54	99.09 64	98.82 85	96.58 93	99.10 52	99.32 53	95.39 58	99.82 81	97.70 95	99.63 75	99.72 48

CP-MVS		98.57 30	98.36 33	99.19 43	99.66 26	97.86 68	99.34 16	98.87 70	95.96 117	98.60 90	99.13 87	96.05 37	99.94 9	97.77 87	99.86 2	99.77 29

MSLP-MVS++		98.56 32	98.57 18	98.55 91	99.26 83	96.80 116	98.71 163	99.05 37	97.28 51	98.84 70	99.28 58	96.47 23	99.40 183	98.52 46	99.70 60	99.47 103

DeepC-MVS_fast	96.70 1	98.55 33	98.34 39	99.18 45	99.25 84	98.04 62	98.50 205	98.78 105	97.72 22	98.92 66	99.28 58	95.27 66	99.82 81	97.55 107	99.77 36	99.69 59
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SR-MVS-dyc-post		98.54 34	98.35 35	99.13 51	99.49 46	97.86 68	99.11 60	98.80 98	96.49 96	99.17 47	99.35 48	95.34 62	99.82 81	97.72 90	99.65 70	99.71 52

APD-MVS_3200maxsize		98.53 35	98.33 43	99.15 49	99.50 42	97.92 67	99.15 51	98.81 91	96.24 107	99.20 44	99.37 42	95.30 64	99.80 93	97.73 89	99.67 64	99.72 48

MM		98.51 36	98.24 50	99.33 29	99.12 106	98.14 59	98.93 101	97.02 352	98.96 1	99.17 47	99.47 25	91.97 137	99.94 9	99.85 3	99.69 61	99.91 2

mPP-MVS		98.51 36	98.26 47	99.25 38	99.75 3	98.04 62	99.28 24	98.81 91	96.24 107	98.35 105	99.23 67	95.46 55	99.94 9	97.42 114	99.81 15	99.77 29

ZNCC-MVS		98.49 38	98.20 56	99.35 24	99.73 11	98.39 34	99.19 44	98.86 76	95.77 127	98.31 108	99.10 91	95.46 55	99.93 28	97.57 106	99.81 15	99.74 39

SPE-MVS-test		98.49 38	98.50 23	98.46 103	99.20 96	97.05 106	99.64 4	98.50 179	97.45 41	98.88 67	99.14 86	95.25 68	99.15 211	98.83 28	99.56 92	99.20 147

PGM-MVS		98.49 38	98.23 52	99.27 37	99.72 12	98.08 61	98.99 86	99.49 5	95.43 143	99.03 53	99.32 53	95.56 52	99.94 9	96.80 145	99.77 36	99.78 23

EI-MVSNet-Vis-set		98.47 41	98.39 30	98.69 80	99.46 52	96.49 133	98.30 228	98.69 126	97.21 58	98.84 70	99.36 46	95.41 57	99.78 106	98.62 35	99.65 70	99.80 20

MVS_111021_HR		98.47 41	98.34 39	98.88 71	99.22 93	97.32 90	97.91 277	99.58 3	97.20 59	98.33 106	99.00 110	95.99 40	99.64 136	98.05 71	99.76 42	99.69 59

balanced_conf03		98.45 43	98.35 35	98.74 76	98.65 158	97.55 78	99.19 44	98.60 148	96.72 87	99.35 34	98.77 141	95.06 78	99.55 159	98.95 24	99.87 1	99.12 162

test_fmvsmvis_n_1920		98.44 44	98.51 21	98.23 124	98.33 188	96.15 150	98.97 89	99.15 29	98.55 9	98.45 98	99.55 11	94.26 96	99.97 1	99.65 8	99.66 67	98.57 223

CS-MVS		98.44 44	98.49 24	98.31 116	99.08 111	96.73 120	99.67 3	98.47 185	97.17 61	98.94 60	99.10 91	95.73 48	99.13 214	98.71 31	99.49 102	99.09 166

GST-MVS		98.43 46	98.12 60	99.34 25	99.72 12	98.38 35	99.09 64	98.82 85	95.71 131	98.73 80	99.06 102	95.27 66	99.93 28	97.07 124	99.63 75	99.72 48

fmvsm_s_conf0.5_n		98.42 47	98.51 21	98.13 133	99.30 71	95.25 196	98.85 125	99.39 7	97.94 19	99.74 11	99.62 3	92.59 116	99.91 43	99.65 8	99.52 98	99.25 140

EI-MVSNet-UG-set		98.41 48	98.34 39	98.61 86	99.45 55	96.32 143	98.28 231	98.68 129	97.17 61	98.74 78	99.37 42	95.25 68	99.79 103	98.57 37	99.54 95	99.73 44

DELS-MVS		98.40 49	98.20 56	98.99 60	99.00 118	97.66 73	97.75 298	98.89 60	97.71 24	98.33 106	98.97 112	94.97 80	99.88 61	98.42 54	99.76 42	99.42 114
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
fmvsm_s_conf0.5_n_a		98.38 50	98.42 28	98.27 118	99.09 110	95.41 186	98.86 121	99.37 8	97.69 26	99.78 7	99.61 4	92.38 119	99.91 43	99.58 12	99.43 110	99.49 99

TSAR-MVS + GP.		98.38 50	98.24 50	98.81 73	99.22 93	97.25 97	98.11 255	98.29 224	97.19 60	98.99 58	99.02 105	96.22 30	99.67 131	98.52 46	98.56 160	99.51 92

HPM-MVS_fast		98.38 50	98.13 59	99.12 53	99.75 3	97.86 68	99.44 9	98.82 85	94.46 200	98.94 60	99.20 72	95.16 73	99.74 116	97.58 103	99.85 6	99.77 29

patch_mono-2		98.36 53	98.87 6	96.82 227	99.53 36	90.68 334	98.64 180	99.29 14	97.88 20	99.19 46	99.52 16	96.80 15	99.97 1	99.11 20	99.86 2	99.82 16

HPM-MVS		98.36 53	98.10 63	99.13 51	99.74 7	97.82 72	99.53 6	98.80 98	94.63 190	98.61 89	98.97 112	95.13 75	99.77 111	97.65 98	99.83 13	99.79 21
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
APD-MVS		98.35 55	98.00 69	99.42 16	99.51 40	98.72 21	98.80 142	98.82 85	94.52 197	99.23 43	99.25 66	95.54 54	99.80 93	96.52 152	99.77 36	99.74 39
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_LR		98.34 56	98.23 52	98.67 82	99.27 81	96.90 112	97.95 272	99.58 3	97.14 64	98.44 100	99.01 109	95.03 79	99.62 143	97.91 78	99.75 47	99.50 94

PHI-MVS		98.34 56	98.06 64	99.18 45	99.15 104	98.12 60	99.04 73	99.09 32	93.32 259	98.83 72	99.10 91	96.54 21	99.83 74	97.70 95	99.76 42	99.59 82

MP-MVS		98.33 58	98.01 68	99.28 35	99.75 3	98.18 54	99.22 36	98.79 103	96.13 112	97.92 133	99.23 67	94.54 86	99.94 9	96.74 148	99.78 34	99.73 44
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MVSMamba_PlusPlus		98.31 59	98.19 58	98.67 82	98.96 125	97.36 88	99.24 30	98.57 159	94.81 182	98.99 58	98.90 125	95.22 71	99.59 146	99.15 19	99.84 11	99.07 174

MP-MVS-pluss		98.31 59	97.92 71	99.49 12	99.72 12	98.88 18	98.43 214	98.78 105	94.10 209	97.69 148	99.42 33	95.25 68	99.92 34	98.09 68	99.80 24	99.67 68
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.5_n_2		98.30 61	98.21 54	98.57 88	99.25 84	97.11 103	98.66 176	99.20 24	98.82 2	99.79 6	99.60 8	89.38 194	99.92 34	99.80 4	99.38 117	98.69 207

MVS_0304		98.23 62	97.91 72	99.21 42	98.06 217	97.96 66	98.58 189	95.51 389	98.58 7	98.87 68	99.26 61	92.99 111	99.95 7	99.62 11	99.67 64	99.73 44

ACMMP		98.23 62	97.95 70	99.09 55	99.74 7	97.62 76	99.03 76	99.41 6	95.98 116	97.60 157	99.36 46	94.45 91	99.93 28	97.14 121	98.85 146	99.70 56
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
EC-MVSNet		98.21 64	98.11 61	98.49 100	98.34 185	97.26 96	99.61 5	98.43 194	96.78 80	98.87 68	98.84 132	93.72 103	99.01 235	98.91 26	99.50 100	99.19 151

fmvsm_s_conf0.1_n		98.18 65	98.21 54	98.11 137	98.54 167	95.24 197	98.87 118	99.24 17	97.50 37	99.70 15	99.67 1	91.33 153	99.89 52	99.47 14	99.54 95	99.21 146

fmvsm_s_conf0.1_n_2		98.14 66	98.02 67	98.53 95	98.88 131	97.07 105	98.69 169	98.82 85	98.78 3	99.77 8	99.61 4	88.83 213	99.91 43	99.71 6	99.07 130	98.61 217

fmvsm_s_conf0.1_n_a		98.08 67	98.04 66	98.21 125	97.66 253	95.39 187	98.89 110	99.17 27	97.24 56	99.76 10	99.67 1	91.13 158	99.88 61	99.39 15	99.41 112	99.35 119

dcpmvs_2		98.08 67	98.59 17	96.56 251	99.57 33	90.34 343	99.15 51	98.38 204	96.82 79	99.29 38	99.49 22	95.78 47	99.57 149	98.94 25	99.86 2	99.77 29

CANet		98.05 69	97.76 75	98.90 70	98.73 144	97.27 92	98.35 219	98.78 105	97.37 47	97.72 145	98.96 117	91.53 149	99.92 34	98.79 29	99.65 70	99.51 92

train_agg		97.97 70	97.52 87	99.33 29	99.31 67	98.50 29	97.92 275	98.73 116	92.98 275	97.74 142	98.68 152	96.20 32	99.80 93	96.59 149	99.57 86	99.68 64

ETV-MVS		97.96 71	97.81 73	98.40 111	98.42 173	97.27 92	98.73 158	98.55 164	96.84 77	98.38 102	97.44 270	95.39 58	99.35 188	97.62 100	98.89 141	98.58 222

UA-Net		97.96 71	97.62 79	98.98 62	98.86 135	97.47 84	98.89 110	99.08 33	96.67 90	98.72 81	99.54 13	93.15 109	99.81 86	94.87 206	98.83 147	99.65 72

CDPH-MVS		97.94 73	97.49 89	99.28 35	99.47 50	98.44 31	97.91 277	98.67 134	92.57 291	98.77 76	98.85 131	95.93 42	99.72 118	95.56 186	99.69 61	99.68 64

DeepPCF-MVS	96.37 2	97.93 74	98.48 26	96.30 276	99.00 118	89.54 357	97.43 320	98.87 70	98.16 13	99.26 42	99.38 41	96.12 35	99.64 136	98.30 59	99.77 36	99.72 48

DeepC-MVS	95.98 3	97.88 75	97.58 81	98.77 74	99.25 84	96.93 110	98.83 131	98.75 111	96.96 73	96.89 182	99.50 20	90.46 171	99.87 63	97.84 84	99.76 42	99.52 89
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_fmvsmconf0.01_n		97.86 76	97.54 86	98.83 72	95.48 370	96.83 115	98.95 95	98.60 148	98.58 7	98.93 64	99.55 11	88.57 218	99.91 43	99.54 13	99.61 78	99.77 29

DP-MVS Recon		97.86 76	97.46 92	99.06 57	99.53 36	98.35 44	98.33 221	98.89 60	92.62 288	98.05 117	98.94 120	95.34 62	99.65 134	96.04 168	99.42 111	99.19 151

CSCG		97.85 78	97.74 76	98.20 127	99.67 25	95.16 200	99.22 36	99.32 11	93.04 273	97.02 175	98.92 123	95.36 61	99.91 43	97.43 113	99.64 74	99.52 89

BP-MVS1		97.82 79	97.51 88	98.76 75	98.25 195	97.39 87	99.15 51	97.68 291	96.69 88	98.47 94	99.10 91	90.29 175	99.51 166	98.60 36	99.35 120	99.37 117

MG-MVS		97.81 80	97.60 80	98.44 106	99.12 106	95.97 159	97.75 298	98.78 105	96.89 76	98.46 95	99.22 69	93.90 102	99.68 130	94.81 210	99.52 98	99.67 68

VNet		97.79 81	97.40 96	98.96 65	98.88 131	97.55 78	98.63 183	98.93 51	96.74 84	99.02 54	98.84 132	90.33 174	99.83 74	98.53 40	96.66 221	99.50 94

EIA-MVS		97.75 82	97.58 81	98.27 118	98.38 177	96.44 135	99.01 81	98.60 148	95.88 121	97.26 164	97.53 264	94.97 80	99.33 191	97.38 116	99.20 126	99.05 175

PS-MVSNAJ		97.73 83	97.77 74	97.62 177	98.68 153	95.58 177	97.34 329	98.51 174	97.29 50	98.66 86	97.88 230	94.51 87	99.90 50	97.87 81	99.17 128	97.39 264

casdiffmvs_mvg		97.72 84	97.48 91	98.44 106	98.42 173	96.59 128	98.92 103	98.44 190	96.20 109	97.76 139	99.20 72	91.66 143	99.23 201	98.27 63	98.41 170	99.49 99
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CPTT-MVS		97.72 84	97.32 100	98.92 67	99.64 28	97.10 104	99.12 58	98.81 91	92.34 299	98.09 114	99.08 100	93.01 110	99.92 34	96.06 167	99.77 36	99.75 37

PVSNet_Blended_VisFu		97.70 86	97.46 92	98.44 106	99.27 81	95.91 167	98.63 183	99.16 28	94.48 199	97.67 149	98.88 128	92.80 113	99.91 43	97.11 122	99.12 129	99.50 94

mvsany_test1		97.69 87	97.70 77	97.66 175	98.24 196	94.18 250	97.53 314	97.53 309	95.52 139	99.66 17	99.51 18	94.30 94	99.56 152	98.38 55	98.62 156	99.23 142

sasdasda		97.67 88	97.23 104	98.98 62	98.70 149	98.38 35	99.34 16	98.39 200	96.76 82	97.67 149	97.40 274	92.26 123	99.49 170	98.28 60	96.28 239	99.08 170

canonicalmvs		97.67 88	97.23 104	98.98 62	98.70 149	98.38 35	99.34 16	98.39 200	96.76 82	97.67 149	97.40 274	92.26 123	99.49 170	98.28 60	96.28 239	99.08 170

xiu_mvs_v2_base		97.66 90	97.70 77	97.56 181	98.61 162	95.46 184	97.44 318	98.46 186	97.15 63	98.65 87	98.15 206	94.33 93	99.80 93	97.84 84	98.66 155	97.41 262

GDP-MVS		97.64 91	97.28 101	98.71 79	98.30 193	97.33 89	99.05 69	98.52 171	96.34 104	98.80 73	99.05 103	89.74 184	99.51 166	96.86 142	98.86 145	99.28 134

baseline		97.64 91	97.44 94	98.25 122	98.35 180	96.20 147	99.00 83	98.32 214	96.33 106	98.03 120	99.17 79	91.35 152	99.16 208	98.10 67	98.29 177	99.39 115

casdiffmvs		97.63 93	97.41 95	98.28 117	98.33 188	96.14 151	98.82 133	98.32 214	96.38 103	97.95 128	99.21 70	91.23 157	99.23 201	98.12 66	98.37 171	99.48 101
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MGCFI-Net		97.62 94	97.19 107	98.92 67	98.66 155	98.20 52	99.32 21	98.38 204	96.69 88	97.58 158	97.42 273	92.10 131	99.50 169	98.28 60	96.25 242	99.08 170

xiu_mvs_v1_base_debu		97.60 95	97.56 83	97.72 165	98.35 180	95.98 154	97.86 287	98.51 174	97.13 65	99.01 55	98.40 179	91.56 145	99.80 93	98.53 40	98.68 151	97.37 266

xiu_mvs_v1_base		97.60 95	97.56 83	97.72 165	98.35 180	95.98 154	97.86 287	98.51 174	97.13 65	99.01 55	98.40 179	91.56 145	99.80 93	98.53 40	98.68 151	97.37 266

xiu_mvs_v1_base_debi		97.60 95	97.56 83	97.72 165	98.35 180	95.98 154	97.86 287	98.51 174	97.13 65	99.01 55	98.40 179	91.56 145	99.80 93	98.53 40	98.68 151	97.37 266

diffmvs		97.58 98	97.40 96	98.13 133	98.32 191	95.81 172	98.06 261	98.37 206	96.20 109	98.74 78	98.89 127	91.31 155	99.25 198	98.16 65	98.52 162	99.34 121
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVSFormer		97.57 99	97.49 89	97.84 152	98.07 214	95.76 173	99.47 7	98.40 198	94.98 171	98.79 74	98.83 134	92.34 120	98.41 308	96.91 130	99.59 82	99.34 121

alignmvs		97.56 100	97.07 113	99.01 59	98.66 155	98.37 42	98.83 131	98.06 271	96.74 84	98.00 126	97.65 252	90.80 165	99.48 175	98.37 56	96.56 225	99.19 151

DPM-MVS		97.55 101	96.99 116	99.23 41	99.04 113	98.55 27	97.17 344	98.35 209	94.85 181	97.93 132	98.58 162	95.07 77	99.71 123	92.60 278	99.34 121	99.43 112

OMC-MVS		97.55 101	97.34 99	98.20 127	99.33 62	95.92 166	98.28 231	98.59 152	95.52 139	97.97 127	99.10 91	93.28 108	99.49 170	95.09 201	98.88 142	99.19 151

PAPM_NR		97.46 103	97.11 110	98.50 98	99.50 42	96.41 138	98.63 183	98.60 148	95.18 158	97.06 173	98.06 212	94.26 96	99.57 149	93.80 246	98.87 144	99.52 89

EPP-MVSNet		97.46 103	97.28 101	97.99 145	98.64 159	95.38 188	99.33 20	98.31 216	93.61 248	97.19 166	99.07 101	94.05 99	99.23 201	96.89 134	98.43 169	99.37 117

3Dnovator	94.51 5	97.46 103	96.93 119	99.07 56	97.78 241	97.64 74	99.35 15	99.06 35	97.02 70	93.75 292	99.16 82	89.25 198	99.92 34	97.22 120	99.75 47	99.64 74

CNLPA		97.45 106	97.03 114	98.73 77	99.05 112	97.44 86	98.07 260	98.53 168	95.32 151	96.80 187	98.53 167	93.32 106	99.72 118	94.31 229	99.31 123	99.02 177

lupinMVS		97.44 107	97.22 106	98.12 136	98.07 214	95.76 173	97.68 303	97.76 288	94.50 198	98.79 74	98.61 157	92.34 120	99.30 194	97.58 103	99.59 82	99.31 127

3Dnovator+	94.38 6	97.43 108	96.78 127	99.38 18	97.83 238	98.52 28	99.37 12	98.71 121	97.09 68	92.99 320	99.13 87	89.36 195	99.89 52	96.97 127	99.57 86	99.71 52

Vis-MVSNet		97.42 109	97.11 110	98.34 114	98.66 155	96.23 146	99.22 36	99.00 40	96.63 92	98.04 119	99.21 70	88.05 234	99.35 188	96.01 170	99.21 125	99.45 109
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
API-MVS		97.41 110	97.25 103	97.91 149	98.70 149	96.80 116	98.82 133	98.69 126	94.53 195	98.11 112	98.28 194	94.50 90	99.57 149	94.12 235	99.49 102	97.37 266

sss		97.39 111	96.98 118	98.61 86	98.60 163	96.61 125	98.22 237	98.93 51	93.97 219	98.01 125	98.48 172	91.98 135	99.85 68	96.45 154	98.15 179	99.39 115

test_cas_vis1_n_1920		97.38 112	97.36 98	97.45 184	98.95 126	93.25 286	99.00 83	98.53 168	97.70 25	99.77 8	99.35 48	84.71 299	99.85 68	98.57 37	99.66 67	99.26 138

PVSNet_Blended		97.38 112	97.12 109	98.14 130	99.25 84	95.35 191	97.28 334	99.26 15	93.13 269	97.94 130	98.21 202	92.74 114	99.81 86	96.88 136	99.40 115	99.27 135

WTY-MVS		97.37 114	96.92 120	98.72 78	98.86 135	96.89 114	98.31 226	98.71 121	95.26 154	97.67 149	98.56 166	92.21 127	99.78 106	95.89 172	96.85 216	99.48 101

jason		97.32 115	97.08 112	98.06 141	97.45 273	95.59 176	97.87 285	97.91 282	94.79 183	98.55 92	98.83 134	91.12 159	99.23 201	97.58 103	99.60 80	99.34 121
jason: jason.
MVS_Test		97.28 116	97.00 115	98.13 133	98.33 188	95.97 159	98.74 154	98.07 266	94.27 205	98.44 100	98.07 211	92.48 117	99.26 197	96.43 155	98.19 178	99.16 157

EPNet		97.28 116	96.87 122	98.51 97	94.98 379	96.14 151	98.90 106	97.02 352	98.28 12	95.99 218	99.11 89	91.36 151	99.89 52	96.98 126	99.19 127	99.50 94
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvsmamba		97.25 118	96.99 116	98.02 143	98.34 185	95.54 181	99.18 48	97.47 315	95.04 167	98.15 109	98.57 165	89.46 191	99.31 193	97.68 97	99.01 135	99.22 144

test_yl		97.22 119	96.78 127	98.54 93	98.73 144	96.60 126	98.45 209	98.31 216	94.70 184	98.02 122	98.42 177	90.80 165	99.70 124	96.81 143	96.79 218	99.34 121

DCV-MVSNet		97.22 119	96.78 127	98.54 93	98.73 144	96.60 126	98.45 209	98.31 216	94.70 184	98.02 122	98.42 177	90.80 165	99.70 124	96.81 143	96.79 218	99.34 121

IS-MVSNet		97.22 119	96.88 121	98.25 122	98.85 137	96.36 141	99.19 44	97.97 276	95.39 145	97.23 165	98.99 111	91.11 160	98.93 247	94.60 217	98.59 158	99.47 103

PLC	95.07 4	97.20 122	96.78 127	98.44 106	99.29 76	96.31 145	98.14 250	98.76 109	92.41 297	96.39 207	98.31 192	94.92 82	99.78 106	94.06 238	98.77 150	99.23 142
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		97.18 123	97.18 108	97.20 197	98.81 140	93.27 283	95.78 389	99.15 29	95.25 155	96.79 188	98.11 209	92.29 122	99.07 225	98.56 39	99.85 6	99.25 140

LS3D		97.16 124	96.66 136	98.68 81	98.53 168	97.19 100	98.93 101	98.90 58	92.83 282	95.99 218	99.37 42	92.12 130	99.87 63	93.67 250	99.57 86	98.97 182

AdaColmap		97.15 125	96.70 132	98.48 101	99.16 102	96.69 122	98.01 266	98.89 60	94.44 201	96.83 183	98.68 152	90.69 168	99.76 112	94.36 225	99.29 124	98.98 181

mamv4		97.13 126	98.11 61	94.17 355	98.97 124	83.70 397	98.66 176	98.71 121	94.63 190	97.83 136	98.90 125	96.25 29	99.55 159	99.27 17	99.76 42	99.27 135

Effi-MVS+		97.12 127	96.69 133	98.39 112	98.19 204	96.72 121	97.37 325	98.43 194	93.71 237	97.65 153	98.02 215	92.20 128	99.25 198	96.87 139	97.79 191	99.19 151

CHOSEN 1792x2688		97.12 127	96.80 124	98.08 139	99.30 71	94.56 234	98.05 262	99.71 1	93.57 249	97.09 169	98.91 124	88.17 228	99.89 52	96.87 139	99.56 92	99.81 17

F-COLMAP		97.09 129	96.80 124	97.97 146	99.45 55	94.95 213	98.55 197	98.62 147	93.02 274	96.17 213	98.58 162	94.01 100	99.81 86	93.95 240	98.90 140	99.14 160

RRT-MVS		97.03 130	96.78 127	97.77 161	97.90 234	94.34 243	99.12 58	98.35 209	95.87 122	98.06 116	98.70 150	86.45 265	99.63 139	98.04 72	98.54 161	99.35 119

TAMVS		97.02 131	96.79 126	97.70 168	98.06 217	95.31 194	98.52 199	98.31 216	93.95 220	97.05 174	98.61 157	93.49 105	98.52 290	95.33 193	97.81 190	99.29 132

CDS-MVSNet		96.99 132	96.69 133	97.90 150	98.05 219	95.98 154	98.20 240	98.33 213	93.67 244	96.95 176	98.49 171	93.54 104	98.42 301	95.24 199	97.74 194	99.31 127
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CANet_DTU		96.96 133	96.55 139	98.21 125	98.17 209	96.07 153	97.98 270	98.21 233	97.24 56	97.13 168	98.93 121	86.88 257	99.91 43	95.00 204	99.37 119	98.66 213

114514_t		96.93 134	96.27 149	98.92 67	99.50 42	97.63 75	98.85 125	98.90 58	84.80 396	97.77 138	99.11 89	92.84 112	99.66 133	94.85 207	99.77 36	99.47 103

MAR-MVS		96.91 135	96.40 145	98.45 104	98.69 152	96.90 112	98.66 176	98.68 129	92.40 298	97.07 172	97.96 222	91.54 148	99.75 114	93.68 248	98.92 139	98.69 207
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
HyFIR lowres test		96.90 136	96.49 142	98.14 130	99.33 62	95.56 178	97.38 323	99.65 2	92.34 299	97.61 156	98.20 203	89.29 197	99.10 222	96.97 127	97.60 199	99.77 29

Vis-MVSNet (Re-imp)		96.87 137	96.55 139	97.83 153	98.73 144	95.46 184	99.20 42	98.30 222	94.96 173	96.60 195	98.87 129	90.05 178	98.59 285	93.67 250	98.60 157	99.46 107

SDMVSNet		96.85 138	96.42 143	98.14 130	99.30 71	96.38 139	99.21 39	99.23 20	95.92 118	95.96 220	98.76 146	85.88 275	99.44 180	97.93 76	95.59 254	98.60 218

PAPR		96.84 139	96.24 151	98.65 84	98.72 148	96.92 111	97.36 327	98.57 159	93.33 258	96.67 190	97.57 261	94.30 94	99.56 152	91.05 319	98.59 158	99.47 103

HY-MVS	93.96 8	96.82 140	96.23 152	98.57 88	98.46 172	97.00 107	98.14 250	98.21 233	93.95 220	96.72 189	97.99 219	91.58 144	99.76 112	94.51 221	96.54 226	98.95 185

UGNet		96.78 141	96.30 148	98.19 129	98.24 196	95.89 169	98.88 115	98.93 51	97.39 44	96.81 186	97.84 234	82.60 326	99.90 50	96.53 151	99.49 102	98.79 196
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
PVSNet_BlendedMVS		96.73 142	96.60 137	97.12 206	99.25 84	95.35 191	98.26 234	99.26 15	94.28 204	97.94 130	97.46 267	92.74 114	99.81 86	96.88 136	93.32 290	96.20 356

test_vis1_n_1920		96.71 143	96.84 123	96.31 275	99.11 108	89.74 351	99.05 69	98.58 157	98.08 14	99.87 1	99.37 42	78.48 357	99.93 28	99.29 16	99.69 61	99.27 135

mvs_anonymous		96.70 144	96.53 141	97.18 200	98.19 204	93.78 259	98.31 226	98.19 237	94.01 216	94.47 251	98.27 197	92.08 133	98.46 296	97.39 115	97.91 186	99.31 127

1112_ss		96.63 145	96.00 159	98.50 98	98.56 164	96.37 140	98.18 248	98.10 259	92.92 278	94.84 240	98.43 175	92.14 129	99.58 148	94.35 226	96.51 227	99.56 88

PMMVS		96.60 146	96.33 147	97.41 188	97.90 234	93.93 255	97.35 328	98.41 196	92.84 281	97.76 139	97.45 269	91.10 161	99.20 205	96.26 160	97.91 186	99.11 164

DP-MVS		96.59 147	95.93 162	98.57 88	99.34 60	96.19 149	98.70 167	98.39 200	89.45 368	94.52 249	99.35 48	91.85 138	99.85 68	92.89 274	98.88 142	99.68 64

PatchMatch-RL		96.59 147	96.03 158	98.27 118	99.31 67	96.51 132	97.91 277	99.06 35	93.72 236	96.92 180	98.06 212	88.50 223	99.65 134	91.77 303	99.00 137	98.66 213

GeoE		96.58 149	96.07 155	98.10 138	98.35 180	95.89 169	99.34 16	98.12 253	93.12 270	96.09 214	98.87 129	89.71 185	98.97 237	92.95 270	98.08 182	99.43 112

XVG-OURS		96.55 150	96.41 144	96.99 213	98.75 143	93.76 260	97.50 317	98.52 171	95.67 133	96.83 183	99.30 56	88.95 211	99.53 162	95.88 173	96.26 241	97.69 255

FIs		96.51 151	96.12 154	97.67 172	97.13 297	97.54 80	99.36 13	99.22 23	95.89 120	94.03 278	98.35 185	91.98 135	98.44 299	96.40 156	92.76 298	97.01 274

XVG-OURS-SEG-HR		96.51 151	96.34 146	97.02 212	98.77 142	93.76 260	97.79 296	98.50 179	95.45 142	96.94 177	99.09 98	87.87 239	99.55 159	96.76 147	95.83 253	97.74 252

PS-MVSNAJss		96.43 153	96.26 150	96.92 222	95.84 359	95.08 205	99.16 50	98.50 179	95.87 122	93.84 287	98.34 189	94.51 87	98.61 282	96.88 136	93.45 287	97.06 272

test_fmvs1		96.42 154	96.67 135	95.66 303	98.82 139	88.53 376	98.80 142	98.20 235	96.39 102	99.64 19	99.20 72	80.35 345	99.67 131	99.04 22	99.57 86	98.78 199

FC-MVSNet-test		96.42 154	96.05 156	97.53 182	96.95 306	97.27 92	99.36 13	99.23 20	95.83 124	93.93 281	98.37 183	92.00 134	98.32 318	96.02 169	92.72 299	97.00 275

ab-mvs		96.42 154	95.71 172	98.55 91	98.63 160	96.75 119	97.88 284	98.74 113	93.84 226	96.54 200	98.18 205	85.34 285	99.75 114	95.93 171	96.35 231	99.15 158

FA-MVS(test-final)		96.41 157	95.94 161	97.82 155	98.21 200	95.20 199	97.80 294	97.58 299	93.21 264	97.36 162	97.70 246	89.47 190	99.56 152	94.12 235	97.99 183	98.71 206

PVSNet	91.96 18	96.35 158	96.15 153	96.96 217	99.17 98	92.05 307	96.08 382	98.68 129	93.69 240	97.75 141	97.80 240	88.86 212	99.69 129	94.26 231	99.01 135	99.15 158

Test_1112_low_res		96.34 159	95.66 177	98.36 113	98.56 164	95.94 162	97.71 301	98.07 266	92.10 308	94.79 244	97.29 282	91.75 140	99.56 152	94.17 233	96.50 228	99.58 86

Effi-MVS+-dtu		96.29 160	96.56 138	95.51 308	97.89 236	90.22 344	98.80 142	98.10 259	96.57 95	96.45 205	96.66 336	90.81 164	98.91 250	95.72 180	97.99 183	97.40 263

QAPM		96.29 160	95.40 182	98.96 65	97.85 237	97.60 77	99.23 32	98.93 51	89.76 362	93.11 317	99.02 105	89.11 203	99.93 28	91.99 297	99.62 77	99.34 121

Fast-Effi-MVS+		96.28 162	95.70 174	98.03 142	98.29 194	95.97 159	98.58 189	98.25 230	91.74 316	95.29 233	97.23 287	91.03 163	99.15 211	92.90 272	97.96 185	98.97 182

nrg030		96.28 162	95.72 169	97.96 148	96.90 311	98.15 57	99.39 10	98.31 216	95.47 141	94.42 257	98.35 185	92.09 132	98.69 274	97.50 111	89.05 347	97.04 273

1314		96.25 164	95.73 168	97.79 157	97.13 297	95.55 180	98.19 243	98.59 152	93.47 253	92.03 345	97.82 238	91.33 153	99.49 170	94.62 216	98.44 167	98.32 236

sd_testset		96.17 165	95.76 167	97.42 187	99.30 71	94.34 243	98.82 133	99.08 33	95.92 118	95.96 220	98.76 146	82.83 325	99.32 192	95.56 186	95.59 254	98.60 218

h-mvs33		96.17 165	95.62 178	97.81 156	99.03 114	94.45 236	98.64 180	98.75 111	97.48 38	98.67 82	98.72 149	89.76 182	99.86 67	97.95 74	81.59 393	99.11 164

HQP_MVS		96.14 167	95.90 163	96.85 225	97.42 275	94.60 232	98.80 142	98.56 162	97.28 51	95.34 229	98.28 194	87.09 252	99.03 230	96.07 164	94.27 262	96.92 281

tttt0517		96.07 168	95.51 180	97.78 158	98.41 175	94.84 217	99.28 24	94.33 402	94.26 206	97.64 154	98.64 156	84.05 314	99.47 177	95.34 192	97.60 199	99.03 176

MVSTER		96.06 169	95.72 169	97.08 209	98.23 198	95.93 165	98.73 158	98.27 225	94.86 179	95.07 235	98.09 210	88.21 227	98.54 288	96.59 149	93.46 285	96.79 299

thisisatest0530		96.01 170	95.36 187	97.97 146	98.38 177	95.52 182	98.88 115	94.19 404	94.04 211	97.64 154	98.31 192	83.82 321	99.46 178	95.29 196	97.70 196	98.93 187

test_djsdf		96.00 171	95.69 175	96.93 219	95.72 361	95.49 183	99.47 7	98.40 198	94.98 171	94.58 247	97.86 231	89.16 201	98.41 308	96.91 130	94.12 270	96.88 290

EI-MVSNet		95.96 172	95.83 165	96.36 271	97.93 232	93.70 266	98.12 253	98.27 225	93.70 239	95.07 235	99.02 105	92.23 126	98.54 288	94.68 212	93.46 285	96.84 296

ECVR-MVS		95.95 173	95.71 172	96.65 237	99.02 115	90.86 329	99.03 76	91.80 414	96.96 73	98.10 113	99.26 61	81.31 332	99.51 166	96.90 133	99.04 132	99.59 82

BH-untuned		95.95 173	95.72 169	96.65 237	98.55 166	92.26 302	98.23 236	97.79 287	93.73 234	94.62 246	98.01 217	88.97 210	99.00 236	93.04 267	98.51 163	98.68 209

test1111		95.94 175	95.78 166	96.41 268	98.99 121	90.12 345	99.04 73	92.45 413	96.99 72	98.03 120	99.27 60	81.40 331	99.48 175	96.87 139	99.04 132	99.63 76

MSDG		95.93 176	95.30 193	97.83 153	98.90 129	95.36 189	96.83 369	98.37 206	91.32 331	94.43 256	98.73 148	90.27 176	99.60 145	90.05 333	98.82 148	98.52 224

BH-RMVSNet		95.92 177	95.32 191	97.69 169	98.32 191	94.64 226	98.19 243	97.45 320	94.56 193	96.03 216	98.61 157	85.02 290	99.12 216	90.68 324	99.06 131	99.30 130

test_fmvs1_n		95.90 178	95.99 160	95.63 304	98.67 154	88.32 380	99.26 27	98.22 232	96.40 101	99.67 16	99.26 61	73.91 391	99.70 124	99.02 23	99.50 100	98.87 190

Fast-Effi-MVS+-dtu		95.87 179	95.85 164	95.91 292	97.74 246	91.74 313	98.69 169	98.15 249	95.56 137	94.92 238	97.68 251	88.98 209	98.79 268	93.19 262	97.78 192	97.20 270

LFMVS		95.86 180	94.98 208	98.47 102	98.87 134	96.32 143	98.84 129	96.02 381	93.40 256	98.62 88	99.20 72	74.99 385	99.63 139	97.72 90	97.20 206	99.46 107

baseline1		95.84 181	95.12 201	98.01 144	98.49 171	95.98 154	98.73 158	97.03 350	95.37 148	96.22 210	98.19 204	89.96 180	99.16 208	94.60 217	87.48 363	98.90 189

OpenMVS	93.04 13	95.83 182	95.00 206	98.32 115	97.18 294	97.32 90	99.21 39	98.97 43	89.96 358	91.14 354	99.05 103	86.64 260	99.92 34	93.38 256	99.47 105	97.73 253

VDD-MVS		95.82 183	95.23 195	97.61 178	98.84 138	93.98 254	98.68 171	97.40 324	95.02 169	97.95 128	99.34 52	74.37 390	99.78 106	98.64 34	96.80 217	99.08 170

UniMVSNet (Re)		95.78 184	95.19 197	97.58 179	96.99 304	97.47 84	98.79 148	99.18 26	95.60 135	93.92 282	97.04 308	91.68 141	98.48 292	95.80 177	87.66 362	96.79 299

VPA-MVSNet		95.75 185	95.11 202	97.69 169	97.24 286	97.27 92	98.94 98	99.23 20	95.13 160	95.51 227	97.32 280	85.73 277	98.91 250	97.33 118	89.55 338	96.89 289

HQP-MVS		95.72 186	95.40 182	96.69 235	97.20 290	94.25 248	98.05 262	98.46 186	96.43 98	94.45 252	97.73 243	86.75 258	98.96 241	95.30 194	94.18 266	96.86 295

hse-mvs2		95.71 187	95.30 193	96.93 219	98.50 169	93.53 271	98.36 218	98.10 259	97.48 38	98.67 82	97.99 219	89.76 182	99.02 233	97.95 74	80.91 398	98.22 239

UniMVSNet_NR-MVSNet		95.71 187	95.15 198	97.40 190	96.84 314	96.97 108	98.74 154	99.24 17	95.16 159	93.88 284	97.72 245	91.68 141	98.31 320	95.81 175	87.25 368	96.92 281

PatchmatchNet		95.71 187	95.52 179	96.29 277	97.58 259	90.72 333	96.84 368	97.52 310	94.06 210	97.08 170	96.96 318	89.24 199	98.90 253	92.03 296	98.37 171	99.26 138
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
OPM-MVS		95.69 190	95.33 190	96.76 230	96.16 347	94.63 227	98.43 214	98.39 200	96.64 91	95.02 237	98.78 139	85.15 289	99.05 226	95.21 200	94.20 265	96.60 322
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMM	93.85 9	95.69 190	95.38 186	96.61 244	97.61 256	93.84 258	98.91 105	98.44 190	95.25 155	94.28 264	98.47 173	86.04 274	99.12 216	95.50 189	93.95 275	96.87 293
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpmrst		95.63 192	95.69 175	95.44 312	97.54 264	88.54 375	96.97 354	97.56 302	93.50 251	97.52 160	96.93 322	89.49 188	99.16 208	95.25 198	96.42 230	98.64 215

FE-MVS		95.62 193	94.90 212	97.78 158	98.37 179	94.92 214	97.17 344	97.38 326	90.95 342	97.73 144	97.70 246	85.32 287	99.63 139	91.18 311	98.33 174	98.79 196

LPG-MVS_test		95.62 193	95.34 188	96.47 262	97.46 270	93.54 269	98.99 86	98.54 166	94.67 188	94.36 260	98.77 141	85.39 282	99.11 218	95.71 181	94.15 268	96.76 302

CLD-MVS		95.62 193	95.34 188	96.46 265	97.52 267	93.75 262	97.27 335	98.46 186	95.53 138	94.42 257	98.00 218	86.21 269	98.97 237	96.25 162	94.37 260	96.66 317
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		95.61 196	94.89 213	97.76 162	98.15 210	95.15 202	96.77 370	94.41 400	92.95 277	97.18 167	97.43 271	84.78 296	99.45 179	94.63 214	97.73 195	98.68 209

MonoMVSNet		95.51 197	95.45 181	95.68 301	95.54 366	90.87 328	98.92 103	97.37 327	95.79 126	95.53 226	97.38 276	89.58 187	97.68 363	96.40 156	92.59 300	98.49 226

thres600view7		95.49 198	94.77 216	97.67 172	98.98 122	95.02 206	98.85 125	96.90 359	95.38 146	96.63 192	96.90 323	84.29 306	99.59 146	88.65 355	96.33 232	98.40 230

test_vis1_n		95.47 199	95.13 199	96.49 259	97.77 242	90.41 341	99.27 26	98.11 256	96.58 93	99.66 17	99.18 78	67.00 404	99.62 143	99.21 18	99.40 115	99.44 110

SCA		95.46 200	95.13 199	96.46 265	97.67 251	91.29 321	97.33 330	97.60 298	94.68 187	96.92 180	97.10 293	83.97 316	98.89 254	92.59 280	98.32 176	99.20 147

IterMVS-LS		95.46 200	95.21 196	96.22 279	98.12 211	93.72 265	98.32 225	98.13 252	93.71 237	94.26 265	97.31 281	92.24 125	98.10 336	94.63 214	90.12 329	96.84 296
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
jajsoiax		95.45 202	95.03 205	96.73 231	95.42 374	94.63 227	99.14 54	98.52 171	95.74 128	93.22 310	98.36 184	83.87 319	98.65 279	96.95 129	94.04 271	96.91 286

CVMVSNet		95.43 203	96.04 157	93.57 360	97.93 232	83.62 398	98.12 253	98.59 152	95.68 132	96.56 196	99.02 105	87.51 245	97.51 371	93.56 254	97.44 202	99.60 80

anonymousdsp		95.42 204	94.91 211	96.94 218	95.10 378	95.90 168	99.14 54	98.41 196	93.75 231	93.16 313	97.46 267	87.50 247	98.41 308	95.63 185	94.03 272	96.50 341

DU-MVS		95.42 204	94.76 217	97.40 190	96.53 330	96.97 108	98.66 176	98.99 42	95.43 143	93.88 284	97.69 248	88.57 218	98.31 320	95.81 175	87.25 368	96.92 281

mvs_tets		95.41 206	95.00 206	96.65 237	95.58 365	94.42 238	99.00 83	98.55 164	95.73 130	93.21 311	98.38 182	83.45 323	98.63 280	97.09 123	94.00 273	96.91 286

thres100view900		95.38 207	94.70 221	97.41 188	98.98 122	94.92 214	98.87 118	96.90 359	95.38 146	96.61 194	96.88 324	84.29 306	99.56 152	88.11 358	96.29 236	97.76 250

thres400		95.38 207	94.62 225	97.65 176	98.94 127	94.98 210	98.68 171	96.93 357	95.33 149	96.55 198	96.53 342	84.23 310	99.56 152	88.11 358	96.29 236	98.40 230

BH-w/o		95.38 207	95.08 203	96.26 278	98.34 185	91.79 310	97.70 302	97.43 322	92.87 280	94.24 267	97.22 288	88.66 216	98.84 260	91.55 307	97.70 196	98.16 242

VDDNet		95.36 210	94.53 229	97.86 151	98.10 213	95.13 203	98.85 125	97.75 289	90.46 349	98.36 103	99.39 36	73.27 393	99.64 136	97.98 73	96.58 224	98.81 195

TAPA-MVS	93.98 7	95.35 211	94.56 228	97.74 164	99.13 105	94.83 219	98.33 221	98.64 142	86.62 384	96.29 209	98.61 157	94.00 101	99.29 195	80.00 399	99.41 112	99.09 166
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ACMP	93.49 10	95.34 212	94.98 208	96.43 267	97.67 251	93.48 273	98.73 158	98.44 190	94.94 177	92.53 333	98.53 167	84.50 305	99.14 213	95.48 190	94.00 273	96.66 317
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
COLMAP_ROB	93.27 12	95.33 213	94.87 214	96.71 232	99.29 76	93.24 287	98.58 189	98.11 256	89.92 359	93.57 296	99.10 91	86.37 267	99.79 103	90.78 322	98.10 181	97.09 271
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
UBG		95.32 214	94.72 220	97.13 204	98.05 219	93.26 284	97.87 285	97.20 338	94.96 173	96.18 212	95.66 373	80.97 337	99.35 188	94.47 223	97.08 208	98.78 199

tfpn200view9		95.32 214	94.62 225	97.43 186	98.94 127	94.98 210	98.68 171	96.93 357	95.33 149	96.55 198	96.53 342	84.23 310	99.56 152	88.11 358	96.29 236	97.76 250

Anonymous202405211		95.28 216	94.49 231	97.67 172	99.00 118	93.75 262	98.70 167	97.04 349	90.66 345	96.49 202	98.80 137	78.13 361	99.83 74	96.21 163	95.36 258	99.44 110

thres200		95.25 217	94.57 227	97.28 194	98.81 140	94.92 214	98.20 240	97.11 342	95.24 157	96.54 200	96.22 353	84.58 303	99.53 162	87.93 363	96.50 228	97.39 264

AllTest		95.24 218	94.65 224	96.99 213	99.25 84	93.21 288	98.59 187	98.18 240	91.36 327	93.52 298	98.77 141	84.67 300	99.72 118	89.70 340	97.87 188	98.02 245

LCM-MVSNet-Re		95.22 219	95.32 191	94.91 328	98.18 206	87.85 386	98.75 151	95.66 388	95.11 162	88.96 373	96.85 327	90.26 177	97.65 364	95.65 184	98.44 167	99.22 144

EPNet_dtu		95.21 220	94.95 210	95.99 287	96.17 345	90.45 339	98.16 249	97.27 334	96.77 81	93.14 316	98.33 190	90.34 173	98.42 301	85.57 376	98.81 149	99.09 166
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
XXY-MVS		95.20 221	94.45 236	97.46 183	96.75 320	96.56 130	98.86 121	98.65 141	93.30 261	93.27 309	98.27 197	84.85 294	98.87 257	94.82 209	91.26 316	96.96 277

D2MVS		95.18 222	95.08 203	95.48 309	97.10 299	92.07 306	98.30 228	99.13 31	94.02 213	92.90 321	96.73 333	89.48 189	98.73 272	94.48 222	93.60 284	95.65 369

WR-MVS		95.15 223	94.46 234	97.22 196	96.67 325	96.45 134	98.21 238	98.81 91	94.15 207	93.16 313	97.69 248	87.51 245	98.30 322	95.29 196	88.62 353	96.90 288

TranMVSNet+NR-MVSNet		95.14 224	94.48 232	97.11 207	96.45 335	96.36 141	99.03 76	99.03 38	95.04 167	93.58 295	97.93 224	88.27 226	98.03 342	94.13 234	86.90 373	96.95 279

baseline2		95.11 225	94.52 230	96.87 224	96.65 326	93.56 268	98.27 233	94.10 406	93.45 254	92.02 346	97.43 271	87.45 249	99.19 206	93.88 243	97.41 204	97.87 248

miper_enhance_ethall		95.10 226	94.75 218	96.12 283	97.53 266	93.73 264	96.61 376	98.08 264	92.20 307	93.89 283	96.65 338	92.44 118	98.30 322	94.21 232	91.16 317	96.34 350

Anonymous20240529		95.10 226	94.22 246	97.75 163	99.01 117	94.26 247	98.87 118	98.83 82	85.79 392	96.64 191	98.97 112	78.73 354	99.85 68	96.27 159	94.89 259	99.12 162

test-LLR		95.10 226	94.87 214	95.80 297	96.77 317	89.70 352	96.91 359	95.21 392	95.11 162	94.83 242	95.72 370	87.71 241	98.97 237	93.06 265	98.50 164	98.72 203

WR-MVS_H		95.05 229	94.46 234	96.81 228	96.86 313	95.82 171	99.24 30	99.24 17	93.87 225	92.53 333	96.84 328	90.37 172	98.24 328	93.24 260	87.93 359	96.38 349

miper_ehance_all_eth		95.01 230	94.69 222	95.97 289	97.70 249	93.31 282	97.02 352	98.07 266	92.23 304	93.51 300	96.96 318	91.85 138	98.15 332	93.68 248	91.16 317	96.44 347

testing11		95.00 231	94.28 243	97.16 202	97.96 229	93.36 281	98.09 258	97.06 348	94.94 177	95.33 232	96.15 355	76.89 375	99.40 183	95.77 179	96.30 235	98.72 203

ADS-MVSNet		95.00 231	94.45 236	96.63 241	98.00 223	91.91 309	96.04 383	97.74 290	90.15 355	96.47 203	96.64 339	87.89 237	98.96 241	90.08 331	97.06 209	99.02 177

VPNet		94.99 233	94.19 248	97.40 190	97.16 295	96.57 129	98.71 163	98.97 43	95.67 133	94.84 240	98.24 201	80.36 344	98.67 278	96.46 153	87.32 367	96.96 277

EPMVS		94.99 233	94.48 232	96.52 257	97.22 288	91.75 312	97.23 336	91.66 415	94.11 208	97.28 163	96.81 330	85.70 278	98.84 260	93.04 267	97.28 205	98.97 182

testing91		94.98 235	94.25 245	97.20 197	97.94 230	93.41 276	98.00 268	97.58 299	94.99 170	95.45 228	96.04 359	77.20 370	99.42 182	94.97 205	96.02 249	98.78 199

NR-MVSNet		94.98 235	94.16 251	97.44 185	96.53 330	97.22 99	98.74 154	98.95 47	94.96 173	89.25 372	97.69 248	89.32 196	98.18 330	94.59 219	87.40 365	96.92 281

FMVSNet3		94.97 237	94.26 244	97.11 207	98.18 206	96.62 123	98.56 196	98.26 229	93.67 244	94.09 274	97.10 293	84.25 308	98.01 343	92.08 292	92.14 303	96.70 311

CostFormer		94.95 238	94.73 219	95.60 306	97.28 284	89.06 365	97.53 314	96.89 361	89.66 364	96.82 185	96.72 334	86.05 272	98.95 246	95.53 188	96.13 247	98.79 196

PAPM		94.95 238	94.00 264	97.78 158	97.04 301	95.65 175	96.03 385	98.25 230	91.23 336	94.19 270	97.80 240	91.27 156	98.86 259	82.61 393	97.61 198	98.84 193

CP-MVSNet		94.94 240	94.30 242	96.83 226	96.72 322	95.56 178	99.11 60	98.95 47	93.89 223	92.42 338	97.90 227	87.19 251	98.12 335	94.32 228	88.21 356	96.82 298

TR-MVS		94.94 240	94.20 247	97.17 201	97.75 243	94.14 251	97.59 311	97.02 352	92.28 303	95.75 224	97.64 255	83.88 318	98.96 241	89.77 337	96.15 246	98.40 230

RPSCF		94.87 242	95.40 182	93.26 366	98.89 130	82.06 404	98.33 221	98.06 271	90.30 354	96.56 196	99.26 61	87.09 252	99.49 170	93.82 245	96.32 233	98.24 237

testing99		94.83 243	94.08 256	97.07 210	97.94 230	93.13 290	98.10 257	97.17 340	94.86 179	95.34 229	96.00 362	76.31 378	99.40 183	95.08 202	95.90 250	98.68 209

GA-MVS		94.81 244	94.03 260	97.14 203	97.15 296	93.86 257	96.76 371	97.58 299	94.00 217	94.76 245	97.04 308	80.91 338	98.48 292	91.79 302	96.25 242	99.09 166

c3_l		94.79 245	94.43 238	95.89 294	97.75 243	93.12 292	97.16 346	98.03 273	92.23 304	93.46 303	97.05 307	91.39 150	98.01 343	93.58 253	89.21 345	96.53 333

V42		94.78 246	94.14 253	96.70 234	96.33 340	95.22 198	98.97 89	98.09 263	92.32 301	94.31 263	97.06 304	88.39 224	98.55 287	92.90 272	88.87 351	96.34 350

reproduce_monomvs		94.77 247	94.67 223	95.08 324	98.40 176	89.48 358	98.80 142	98.64 142	97.57 33	93.21 311	97.65 252	80.57 343	98.83 263	97.72 90	89.47 341	96.93 280

CR-MVSNet		94.76 248	94.15 252	96.59 247	97.00 302	93.43 274	94.96 396	97.56 302	92.46 292	96.93 178	96.24 349	88.15 229	97.88 356	87.38 365	96.65 222	98.46 228

v2v482		94.69 249	94.03 260	96.65 237	96.17 345	94.79 222	98.67 174	98.08 264	92.72 284	94.00 279	97.16 291	87.69 244	98.45 297	92.91 271	88.87 351	96.72 307

pmmvs4		94.69 249	93.99 266	96.81 228	95.74 360	95.94 162	97.40 321	97.67 293	90.42 351	93.37 306	97.59 259	89.08 204	98.20 329	92.97 269	91.67 310	96.30 353

cl22		94.68 251	94.19 248	96.13 282	98.11 212	93.60 267	96.94 356	98.31 216	92.43 296	93.32 308	96.87 326	86.51 261	98.28 326	94.10 237	91.16 317	96.51 339

eth_miper_zixun_eth		94.68 251	94.41 239	95.47 310	97.64 254	91.71 314	96.73 373	98.07 266	92.71 285	93.64 293	97.21 289	90.54 170	98.17 331	93.38 256	89.76 333	96.54 331

PCF-MVS	93.45 11	94.68 251	93.43 302	98.42 110	98.62 161	96.77 118	95.48 393	98.20 235	84.63 397	93.34 307	98.32 191	88.55 221	99.81 86	84.80 385	98.96 138	98.68 209
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS		94.67 254	93.54 297	98.08 139	96.88 312	96.56 130	98.19 243	98.50 179	78.05 408	92.69 328	98.02 215	91.07 162	99.63 139	90.09 330	98.36 173	98.04 244

PS-CasMVS		94.67 254	93.99 266	96.71 232	96.68 324	95.26 195	99.13 57	99.03 38	93.68 242	92.33 339	97.95 223	85.35 284	98.10 336	93.59 252	88.16 358	96.79 299

cascas		94.63 256	93.86 276	96.93 219	96.91 310	94.27 246	96.00 386	98.51 174	85.55 393	94.54 248	96.23 351	84.20 312	98.87 257	95.80 177	96.98 214	97.66 256

tpmvs		94.60 257	94.36 241	95.33 316	97.46 270	88.60 374	96.88 365	97.68 291	91.29 333	93.80 289	96.42 346	88.58 217	99.24 200	91.06 317	96.04 248	98.17 241

LTVRE_ROB	92.95 15	94.60 257	93.90 272	96.68 236	97.41 278	94.42 238	98.52 199	98.59 152	91.69 319	91.21 353	98.35 185	84.87 293	99.04 229	91.06 317	93.44 288	96.60 322
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
v1144		94.59 259	93.92 269	96.60 246	96.21 342	94.78 223	98.59 187	98.14 251	91.86 315	94.21 269	97.02 311	87.97 235	98.41 308	91.72 304	89.57 336	96.61 321

ADS-MVSNet2		94.58 260	94.40 240	95.11 322	98.00 223	88.74 372	96.04 383	97.30 330	90.15 355	96.47 203	96.64 339	87.89 237	97.56 369	90.08 331	97.06 209	99.02 177

WBMVS		94.56 261	94.04 258	96.10 284	98.03 221	93.08 294	97.82 293	98.18 240	94.02 213	93.77 291	96.82 329	81.28 333	98.34 315	95.47 191	91.00 320	96.88 290

ACMH	92.88 16	94.55 262	93.95 268	96.34 273	97.63 255	93.26 284	98.81 141	98.49 184	93.43 255	89.74 367	98.53 167	81.91 328	99.08 224	93.69 247	93.30 291	96.70 311
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		94.54 263	93.85 277	96.63 241	97.98 227	93.06 295	98.77 150	97.84 285	93.67 244	93.80 289	98.04 214	76.88 376	98.96 241	94.79 211	92.86 296	97.86 249

XVG-ACMP-BASELINE		94.54 263	94.14 253	95.75 300	96.55 329	91.65 315	98.11 255	98.44 190	94.96 173	94.22 268	97.90 227	79.18 353	99.11 218	94.05 239	93.85 277	96.48 344

AUN-MVS		94.53 265	93.73 287	96.92 222	98.50 169	93.52 272	98.34 220	98.10 259	93.83 228	95.94 222	97.98 221	85.59 280	99.03 230	94.35 226	80.94 397	98.22 239

DIV-MVS_self_test		94.52 266	94.03 260	95.99 287	97.57 263	93.38 279	97.05 350	97.94 279	91.74 316	92.81 323	97.10 293	89.12 202	98.07 340	92.60 278	90.30 326	96.53 333

cl____		94.51 267	94.01 263	96.02 286	97.58 259	93.40 278	97.05 350	97.96 278	91.73 318	92.76 325	97.08 299	89.06 205	98.13 334	92.61 277	90.29 327	96.52 336

ETVMVS		94.50 268	93.44 301	97.68 171	98.18 206	95.35 191	98.19 243	97.11 342	93.73 234	96.40 206	95.39 376	74.53 387	98.84 260	91.10 313	96.31 234	98.84 193

GBi-Net		94.49 269	93.80 280	96.56 251	98.21 200	95.00 207	98.82 133	98.18 240	92.46 292	94.09 274	97.07 300	81.16 334	97.95 348	92.08 292	92.14 303	96.72 307

test1		94.49 269	93.80 280	96.56 251	98.21 200	95.00 207	98.82 133	98.18 240	92.46 292	94.09 274	97.07 300	81.16 334	97.95 348	92.08 292	92.14 303	96.72 307

dmvs_re		94.48 271	94.18 250	95.37 314	97.68 250	90.11 346	98.54 198	97.08 344	94.56 193	94.42 257	97.24 286	84.25 308	97.76 361	91.02 320	92.83 297	98.24 237

v8		94.47 272	93.77 283	96.57 250	96.36 338	94.83 219	99.05 69	98.19 237	91.92 312	93.16 313	96.97 316	88.82 215	98.48 292	91.69 305	87.79 360	96.39 348

FMVSNet2		94.47 272	93.61 293	97.04 211	98.21 200	96.43 136	98.79 148	98.27 225	92.46 292	93.50 301	97.09 297	81.16 334	98.00 345	91.09 314	91.93 306	96.70 311

test2506		94.44 274	93.91 271	96.04 285	99.02 115	88.99 368	99.06 67	79.47 427	96.96 73	98.36 103	99.26 61	77.21 369	99.52 165	96.78 146	99.04 132	99.59 82

Patchmatch-test		94.42 275	93.68 291	96.63 241	97.60 257	91.76 311	94.83 400	97.49 314	89.45 368	94.14 272	97.10 293	88.99 206	98.83 263	85.37 379	98.13 180	99.29 132

PEN-MVS		94.42 275	93.73 287	96.49 259	96.28 341	94.84 217	99.17 49	99.00 40	93.51 250	92.23 341	97.83 237	86.10 271	97.90 352	92.55 283	86.92 372	96.74 304

v144192		94.39 277	93.70 289	96.48 261	96.06 350	94.35 242	98.58 189	98.16 248	91.45 324	94.33 262	97.02 311	87.50 247	98.45 297	91.08 316	89.11 346	96.63 319

Baseline_NR-MVSNet		94.35 278	93.81 279	95.96 290	96.20 343	94.05 253	98.61 186	96.67 371	91.44 325	93.85 286	97.60 258	88.57 218	98.14 333	94.39 224	86.93 371	95.68 368

miper_lstm_enhance		94.33 279	94.07 257	95.11 322	97.75 243	90.97 325	97.22 337	98.03 273	91.67 320	92.76 325	96.97 316	90.03 179	97.78 360	92.51 285	89.64 335	96.56 328

v1192		94.32 280	93.58 294	96.53 256	96.10 348	94.45 236	98.50 205	98.17 246	91.54 322	94.19 270	97.06 304	86.95 256	98.43 300	90.14 329	89.57 336	96.70 311

UWE-MVS		94.30 281	93.89 274	95.53 307	97.83 238	88.95 369	97.52 316	93.25 408	94.44 201	96.63 192	97.07 300	78.70 355	99.28 196	91.99 297	97.56 201	98.36 233

ACMH+	92.99 14	94.30 281	93.77 283	95.88 295	97.81 240	92.04 308	98.71 163	98.37 206	93.99 218	90.60 360	98.47 173	80.86 340	99.05 226	92.75 276	92.40 302	96.55 330

v148		94.29 283	93.76 285	95.91 292	96.10 348	92.93 296	98.58 189	97.97 276	92.59 290	93.47 302	96.95 320	88.53 222	98.32 318	92.56 282	87.06 370	96.49 342

v10		94.29 283	93.55 296	96.51 258	96.39 337	94.80 221	98.99 86	98.19 237	91.35 329	93.02 319	96.99 314	88.09 231	98.41 308	90.50 326	88.41 355	96.33 352

MVP-Stereo		94.28 285	93.92 269	95.35 315	94.95 380	92.60 299	97.97 271	97.65 294	91.61 321	90.68 359	97.09 297	86.32 268	98.42 301	89.70 340	99.34 121	95.02 382
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UniMVSNet_ETH3D		94.24 286	93.33 304	96.97 216	97.19 293	93.38 279	98.74 154	98.57 159	91.21 338	93.81 288	98.58 162	72.85 394	98.77 270	95.05 203	93.93 276	98.77 202

OurMVSNet-221017-0		94.21 287	94.00 264	94.85 332	95.60 364	89.22 363	98.89 110	97.43 322	95.29 152	92.18 342	98.52 170	82.86 324	98.59 285	93.46 255	91.76 308	96.74 304

v1921920		94.20 288	93.47 300	96.40 270	95.98 353	94.08 252	98.52 199	98.15 249	91.33 330	94.25 266	97.20 290	86.41 266	98.42 301	90.04 334	89.39 343	96.69 316

WB-MVSnew		94.19 289	94.04 258	94.66 339	96.82 316	92.14 303	97.86 287	95.96 384	93.50 251	95.64 225	96.77 332	88.06 233	97.99 346	84.87 382	96.86 215	93.85 399

v7n		94.19 289	93.43 302	96.47 262	95.90 356	94.38 241	99.26 27	98.34 212	91.99 310	92.76 325	97.13 292	88.31 225	98.52 290	89.48 345	87.70 361	96.52 336

tpm2		94.19 289	93.76 285	95.46 311	97.23 287	89.04 366	97.31 332	96.85 365	87.08 383	96.21 211	96.79 331	83.75 322	98.74 271	92.43 288	96.23 244	98.59 220

TESTMET0.1,1		94.18 292	93.69 290	95.63 304	96.92 308	89.12 364	96.91 359	94.78 397	93.17 266	94.88 239	96.45 345	78.52 356	98.92 248	93.09 264	98.50 164	98.85 191

dp		94.15 293	93.90 272	94.90 329	97.31 283	86.82 391	96.97 354	97.19 339	91.22 337	96.02 217	96.61 341	85.51 281	99.02 233	90.00 335	94.30 261	98.85 191

ET-MVSNet_ETH3D		94.13 294	92.98 311	97.58 179	98.22 199	96.20 147	97.31 332	95.37 391	94.53 195	79.56 408	97.63 257	86.51 261	97.53 370	96.91 130	90.74 322	99.02 177

tpm		94.13 294	93.80 280	95.12 321	96.50 332	87.91 385	97.44 318	95.89 387	92.62 288	96.37 208	96.30 348	84.13 313	98.30 322	93.24 260	91.66 311	99.14 160

testing222		94.12 296	93.03 310	97.37 193	98.02 222	94.66 224	97.94 274	96.65 373	94.63 190	95.78 223	95.76 365	71.49 395	98.92 248	91.17 312	95.88 251	98.52 224

IterMVS-SCA-FT		94.11 297	93.87 275	94.85 332	97.98 227	90.56 338	97.18 342	98.11 256	93.75 231	92.58 331	97.48 266	83.97 316	97.41 373	92.48 287	91.30 314	96.58 324

Anonymous20231211		94.10 298	93.26 307	96.61 244	99.11 108	94.28 245	99.01 81	98.88 63	86.43 386	92.81 323	97.57 261	81.66 330	98.68 277	94.83 208	89.02 349	96.88 290

IterMVS		94.09 299	93.85 277	94.80 335	97.99 225	90.35 342	97.18 342	98.12 253	93.68 242	92.46 337	97.34 277	84.05 314	97.41 373	92.51 285	91.33 313	96.62 320
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test-mter		94.08 300	93.51 298	95.80 297	96.77 317	89.70 352	96.91 359	95.21 392	92.89 279	94.83 242	95.72 370	77.69 364	98.97 237	93.06 265	98.50 164	98.72 203

test0.0.03 1		94.08 300	93.51 298	95.80 297	95.53 368	92.89 297	97.38 323	95.97 383	95.11 162	92.51 335	96.66 336	87.71 241	96.94 380	87.03 367	93.67 280	97.57 260

v1240		94.06 302	93.29 306	96.34 273	96.03 352	93.90 256	98.44 212	98.17 246	91.18 339	94.13 273	97.01 313	86.05 272	98.42 301	89.13 350	89.50 340	96.70 311

X-MVStestdata		94.06 302	92.30 326	99.34 25	99.70 22	98.35 44	99.29 22	98.88 63	97.40 42	98.46 95	43.50 422	95.90 45	99.89 52	97.85 82	99.74 51	99.78 23

DTE-MVSNet		93.98 304	93.26 307	96.14 281	96.06 350	94.39 240	99.20 42	98.86 76	93.06 272	91.78 347	97.81 239	85.87 276	97.58 368	90.53 325	86.17 377	96.46 346

pm-mvs1		93.94 305	93.06 309	96.59 247	96.49 333	95.16 200	98.95 95	98.03 273	92.32 301	91.08 355	97.84 234	84.54 304	98.41 308	92.16 290	86.13 380	96.19 357

MS-PatchMatch		93.84 306	93.63 292	94.46 349	96.18 344	89.45 359	97.76 297	98.27 225	92.23 304	92.13 343	97.49 265	79.50 350	98.69 274	89.75 338	99.38 117	95.25 374

tfpnnormal		93.66 307	92.70 317	96.55 255	96.94 307	95.94 162	98.97 89	99.19 25	91.04 340	91.38 352	97.34 277	84.94 292	98.61 282	85.45 378	89.02 349	95.11 378

EU-MVSNet		93.66 307	94.14 253	92.25 376	95.96 355	83.38 400	98.52 199	98.12 253	94.69 186	92.61 330	98.13 208	87.36 250	96.39 392	91.82 301	90.00 331	96.98 276

our_test_3		93.65 309	93.30 305	94.69 337	95.45 372	89.68 354	96.91 359	97.65 294	91.97 311	91.66 350	96.88 324	89.67 186	97.93 351	88.02 361	91.49 312	96.48 344

pmmvs5		93.65 309	92.97 312	95.68 301	95.49 369	92.37 300	98.20 240	97.28 333	89.66 364	92.58 331	97.26 283	82.14 327	98.09 338	93.18 263	90.95 321	96.58 324

test_fmvs2		93.43 311	93.58 294	92.95 370	96.97 305	83.91 396	99.19 44	97.24 336	95.74 128	95.20 234	98.27 197	69.65 397	98.72 273	96.26 160	93.73 279	96.24 354

tpm cat1		93.36 312	92.80 314	95.07 325	97.58 259	87.97 384	96.76 371	97.86 284	82.17 404	93.53 297	96.04 359	86.13 270	99.13 214	89.24 348	95.87 252	98.10 243

JIA-IIPM		93.35 313	92.49 322	95.92 291	96.48 334	90.65 335	95.01 395	96.96 355	85.93 390	96.08 215	87.33 412	87.70 243	98.78 269	91.35 309	95.58 256	98.34 234

SixPastTwentyTwo		93.34 314	92.86 313	94.75 336	95.67 362	89.41 361	98.75 151	96.67 371	93.89 223	90.15 365	98.25 200	80.87 339	98.27 327	90.90 321	90.64 323	96.57 326

USDC		93.33 315	92.71 316	95.21 318	96.83 315	90.83 331	96.91 359	97.50 312	93.84 226	90.72 358	98.14 207	77.69 364	98.82 265	89.51 344	93.21 293	95.97 362

IB-MVS	91.98 17	93.27 316	91.97 330	97.19 199	97.47 269	93.41 276	97.09 349	95.99 382	93.32 259	92.47 336	95.73 368	78.06 362	99.53 162	94.59 219	82.98 388	98.62 216
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
MIMVSNet		93.26 317	92.21 327	96.41 268	97.73 247	93.13 290	95.65 390	97.03 350	91.27 335	94.04 277	96.06 358	75.33 383	97.19 376	86.56 369	96.23 244	98.92 188

ppachtmachnet_test		93.22 318	92.63 318	94.97 327	95.45 372	90.84 330	96.88 365	97.88 283	90.60 346	92.08 344	97.26 283	88.08 232	97.86 357	85.12 381	90.33 325	96.22 355

Patchmtry		93.22 318	92.35 325	95.84 296	96.77 317	93.09 293	94.66 403	97.56 302	87.37 382	92.90 321	96.24 349	88.15 229	97.90 352	87.37 366	90.10 330	96.53 333

testing3		93.19 320	92.48 323	95.30 317	98.07 214	92.27 301	98.64 180	97.17 340	93.94 222	93.98 280	97.04 308	67.97 401	96.01 396	88.40 356	97.14 207	97.63 257

FMVSNet1		93.19 320	92.07 328	96.56 251	97.54 264	95.00 207	98.82 133	98.18 240	90.38 352	92.27 340	97.07 300	73.68 392	97.95 348	89.36 347	91.30 314	96.72 307

LF4IMVS		93.14 322	92.79 315	94.20 353	95.88 357	88.67 373	97.66 305	97.07 346	93.81 229	91.71 348	97.65 252	77.96 363	98.81 266	91.47 308	91.92 307	95.12 377

mmtdpeth		93.12 323	92.61 319	94.63 341	97.60 257	89.68 354	99.21 39	97.32 329	94.02 213	97.72 145	94.42 387	77.01 374	99.44 180	99.05 21	77.18 409	94.78 387

testgi		93.06 324	92.45 324	94.88 331	96.43 336	89.90 347	98.75 151	97.54 308	95.60 135	91.63 351	97.91 226	74.46 389	97.02 378	86.10 372	93.67 280	97.72 254

PatchT		93.06 324	91.97 330	96.35 272	96.69 323	92.67 298	94.48 406	97.08 344	86.62 384	97.08 170	92.23 406	87.94 236	97.90 352	78.89 403	96.69 220	98.49 226

RPMNet		92.81 326	91.34 336	97.24 195	97.00 302	93.43 274	94.96 396	98.80 98	82.27 403	96.93 178	92.12 407	86.98 255	99.82 81	76.32 408	96.65 222	98.46 228

myMVS_eth3d		92.73 327	92.01 329	94.89 330	97.39 279	90.94 326	97.91 277	97.46 316	93.16 267	93.42 304	95.37 377	68.09 400	96.12 394	88.34 357	96.99 211	97.60 258

TransMVSNet (Re)		92.67 328	91.51 335	96.15 280	96.58 328	94.65 225	98.90 106	96.73 367	90.86 343	89.46 371	97.86 231	85.62 279	98.09 338	86.45 370	81.12 395	95.71 367

ttmdpeth		92.61 329	91.96 332	94.55 343	94.10 390	90.60 337	98.52 199	97.29 331	92.67 286	90.18 363	97.92 225	79.75 349	97.79 359	91.09 314	86.15 379	95.26 373

Syy-MVS		92.55 330	92.61 319	92.38 373	97.39 279	83.41 399	97.91 277	97.46 316	93.16 267	93.42 304	95.37 377	84.75 297	96.12 394	77.00 407	96.99 211	97.60 258

K. test v3		92.55 330	91.91 333	94.48 347	95.64 363	89.24 362	99.07 66	94.88 396	94.04 211	86.78 387	97.59 259	77.64 367	97.64 365	92.08 292	89.43 342	96.57 326

DSMNet-mixed		92.52 332	92.58 321	92.33 374	94.15 389	82.65 402	98.30 228	94.26 403	89.08 373	92.65 329	95.73 368	85.01 291	95.76 398	86.24 371	97.76 193	98.59 220

TinyColmap		92.31 333	91.53 334	94.65 340	96.92 308	89.75 350	96.92 357	96.68 370	90.45 350	89.62 368	97.85 233	76.06 381	98.81 266	86.74 368	92.51 301	95.41 371

gg-mvs-nofinetune		92.21 334	90.58 342	97.13 204	96.75 320	95.09 204	95.85 387	89.40 420	85.43 394	94.50 250	81.98 415	80.80 341	98.40 314	92.16 290	98.33 174	97.88 247

FMVSNet5		91.81 335	90.92 338	94.49 346	97.21 289	92.09 305	98.00 268	97.55 307	89.31 371	90.86 357	95.61 374	74.48 388	95.32 402	85.57 376	89.70 334	96.07 360

pmmvs6		91.77 336	90.63 341	95.17 320	94.69 386	91.24 322	98.67 174	97.92 281	86.14 388	89.62 368	97.56 263	75.79 382	98.34 315	90.75 323	84.56 382	95.94 363

Anonymous20231206		91.66 337	91.10 337	93.33 364	94.02 394	87.35 388	98.58 189	97.26 335	90.48 348	90.16 364	96.31 347	83.83 320	96.53 390	79.36 401	89.90 332	96.12 358

Patchmatch-RL test		91.49 338	90.85 339	93.41 362	91.37 405	84.40 394	92.81 410	95.93 386	91.87 314	87.25 383	94.87 383	88.99 206	96.53 390	92.54 284	82.00 390	99.30 130

test_0402		91.32 339	90.27 345	94.48 347	96.60 327	91.12 323	98.50 205	97.22 337	86.10 389	88.30 379	96.98 315	77.65 366	97.99 346	78.13 405	92.94 295	94.34 388

test_vis1_rt		91.29 340	90.65 340	93.19 368	97.45 273	86.25 392	98.57 195	90.90 418	93.30 261	86.94 386	93.59 396	62.07 410	99.11 218	97.48 112	95.58 256	94.22 391

PVSNet_0	88.72 19	91.28 341	90.03 348	95.00 326	97.99 225	87.29 389	94.84 399	98.50 179	92.06 309	89.86 366	95.19 379	79.81 348	99.39 186	92.27 289	69.79 415	98.33 235

mvs5depth		91.23 342	90.17 346	94.41 351	92.09 402	89.79 349	95.26 394	96.50 375	90.73 344	91.69 349	97.06 304	76.12 380	98.62 281	88.02 361	84.11 385	94.82 384

Anonymous20240521		91.18 343	90.44 343	93.42 361	93.70 395	88.47 377	98.94 98	97.56 302	88.46 377	89.56 370	95.08 382	77.15 372	96.97 379	83.92 388	89.55 338	94.82 384

EG-PatchMatch MVS		91.13 344	90.12 347	94.17 355	94.73 385	89.00 367	98.13 252	97.81 286	89.22 372	85.32 397	96.46 344	67.71 402	98.42 301	87.89 364	93.82 278	95.08 379

TDRefinement		91.06 345	89.68 350	95.21 318	85.35 420	91.49 318	98.51 204	97.07 346	91.47 323	88.83 377	97.84 234	77.31 368	99.09 223	92.79 275	77.98 407	95.04 381

UnsupCasMVSNet_eth		90.99 346	89.92 349	94.19 354	94.08 391	89.83 348	97.13 348	98.67 134	93.69 240	85.83 393	96.19 354	75.15 384	96.74 384	89.14 349	79.41 402	96.00 361

test20.03		90.89 347	90.38 344	92.43 372	93.48 396	88.14 383	98.33 221	97.56 302	93.40 256	87.96 380	96.71 335	80.69 342	94.13 407	79.15 402	86.17 377	95.01 383

MDA-MVSNet_test_wron		90.71 348	89.38 353	94.68 338	94.83 382	90.78 332	97.19 341	97.46 316	87.60 380	72.41 415	95.72 370	86.51 261	96.71 387	85.92 374	86.80 374	96.56 328

YYNet1		90.70 349	89.39 352	94.62 342	94.79 384	90.65 335	97.20 339	97.46 316	87.54 381	72.54 414	95.74 366	86.51 261	96.66 388	86.00 373	86.76 375	96.54 331

KD-MVS_self_test		90.38 350	89.38 353	93.40 363	92.85 399	88.94 370	97.95 272	97.94 279	90.35 353	90.25 362	93.96 393	79.82 347	95.94 397	84.62 387	76.69 410	95.33 372

pmmvs-eth3d		90.36 351	89.05 356	94.32 352	91.10 407	92.12 304	97.63 310	96.95 356	88.86 375	84.91 398	93.13 401	78.32 358	96.74 384	88.70 353	81.81 392	94.09 394

CL-MVSNet_self_test		90.11 352	89.14 355	93.02 369	91.86 404	88.23 382	96.51 379	98.07 266	90.49 347	90.49 361	94.41 388	84.75 297	95.34 401	80.79 397	74.95 412	95.50 370

new_pmnet		90.06 353	89.00 357	93.22 367	94.18 388	88.32 380	96.42 381	96.89 361	86.19 387	85.67 394	93.62 395	77.18 371	97.10 377	81.61 395	89.29 344	94.23 390

MDA-MVSNet-bldmvs		89.97 354	88.35 360	94.83 334	95.21 376	91.34 319	97.64 307	97.51 311	88.36 378	71.17 416	96.13 356	79.22 352	96.63 389	83.65 389	86.27 376	96.52 336

CMPMVS	66.06 21	89.70 355	89.67 351	89.78 381	93.19 397	76.56 407	97.00 353	98.35 209	80.97 405	81.57 403	97.75 242	74.75 386	98.61 282	89.85 336	93.63 282	94.17 392
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet1		89.67 356	88.28 361	93.82 358	92.81 400	91.08 324	98.01 266	97.45 320	87.95 379	87.90 381	95.87 364	67.63 403	94.56 406	78.73 404	88.18 357	95.83 365

KD-MVS_2432*1600		89.61 357	87.96 365	94.54 344	94.06 392	91.59 316	95.59 391	97.63 296	89.87 360	88.95 374	94.38 390	78.28 359	96.82 382	84.83 383	68.05 416	95.21 375

miper_refine_blended		89.61 357	87.96 365	94.54 344	94.06 392	91.59 316	95.59 391	97.63 296	89.87 360	88.95 374	94.38 390	78.28 359	96.82 382	84.83 383	68.05 416	95.21 375

MVStest1		89.53 359	87.99 364	94.14 357	94.39 387	90.42 340	98.25 235	96.84 366	82.81 400	81.18 405	97.33 279	77.09 373	96.94 380	85.27 380	78.79 403	95.06 380

MVS-HIRNet		89.46 360	88.40 359	92.64 371	97.58 259	82.15 403	94.16 409	93.05 412	75.73 411	90.90 356	82.52 414	79.42 351	98.33 317	83.53 390	98.68 151	97.43 261

OpenMVS_ROB	86.42 20	89.00 361	87.43 369	93.69 359	93.08 398	89.42 360	97.91 277	96.89 361	78.58 407	85.86 392	94.69 384	69.48 398	98.29 325	77.13 406	93.29 292	93.36 401

mvsany_test3		88.80 362	88.04 362	91.09 380	89.78 410	81.57 405	97.83 292	95.49 390	93.81 229	87.53 382	93.95 394	56.14 413	97.43 372	94.68 212	83.13 387	94.26 389

new-patchmatchnet		88.50 363	87.45 368	91.67 378	90.31 409	85.89 393	97.16 346	97.33 328	89.47 367	83.63 400	92.77 403	76.38 377	95.06 404	82.70 392	77.29 408	94.06 396

APD_test1		88.22 364	88.01 363	88.86 383	95.98 353	74.66 415	97.21 338	96.44 377	83.96 399	86.66 389	97.90 227	60.95 411	97.84 358	82.73 391	90.23 328	94.09 394

PM-MVS		87.77 365	86.55 371	91.40 379	91.03 408	83.36 401	96.92 357	95.18 394	91.28 334	86.48 391	93.42 397	53.27 414	96.74 384	89.43 346	81.97 391	94.11 393

dmvs_testset		87.64 366	88.93 358	83.79 392	95.25 375	63.36 424	97.20 339	91.17 416	93.07 271	85.64 395	95.98 363	85.30 288	91.52 414	69.42 413	87.33 366	96.49 342

test_fmvs3		87.17 367	87.06 370	87.50 385	91.21 406	75.66 410	99.05 69	96.61 374	92.79 283	88.85 376	92.78 402	43.72 417	93.49 408	93.95 240	84.56 382	93.34 402

UnsupCasMVSNet_bld		87.17 367	85.12 374	93.31 365	91.94 403	88.77 371	94.92 398	98.30 222	84.30 398	82.30 401	90.04 409	63.96 408	97.25 375	85.85 375	74.47 414	93.93 398

N_pmnet		87.12 369	87.77 367	85.17 389	95.46 371	61.92 425	97.37 325	70.66 430	85.83 391	88.73 378	96.04 359	85.33 286	97.76 361	80.02 398	90.48 324	95.84 364

pmmvs3		86.67 370	84.86 375	92.11 377	88.16 414	87.19 390	96.63 375	94.75 398	79.88 406	87.22 384	92.75 404	66.56 405	95.20 403	81.24 396	76.56 411	93.96 397

test_f		86.07 371	85.39 372	88.10 384	89.28 412	75.57 411	97.73 300	96.33 379	89.41 370	85.35 396	91.56 408	43.31 419	95.53 399	91.32 310	84.23 384	93.21 403

WB-MVS		84.86 372	85.33 373	83.46 393	89.48 411	69.56 419	98.19 243	96.42 378	89.55 366	81.79 402	94.67 385	84.80 295	90.12 415	52.44 419	80.64 399	90.69 406

SSC-MVS		84.27 373	84.71 376	82.96 397	89.19 413	68.83 420	98.08 259	96.30 380	89.04 374	81.37 404	94.47 386	84.60 302	89.89 416	49.80 421	79.52 401	90.15 407

dongtai		82.47 374	81.88 377	84.22 391	95.19 377	76.03 408	94.59 405	74.14 429	82.63 401	87.19 385	96.09 357	64.10 407	87.85 419	58.91 417	84.11 385	88.78 411

test_vis3_rt		79.22 375	77.40 382	84.67 390	86.44 418	74.85 414	97.66 305	81.43 425	84.98 395	67.12 418	81.91 416	28.09 427	97.60 366	88.96 351	80.04 400	81.55 416

test_method		79.03 376	78.17 378	81.63 398	86.06 419	54.40 430	82.75 418	96.89 361	39.54 422	80.98 406	95.57 375	58.37 412	94.73 405	84.74 386	78.61 404	95.75 366

testf1		79.02 377	77.70 379	82.99 395	88.10 415	66.90 421	94.67 401	93.11 409	71.08 413	74.02 411	93.41 398	34.15 423	93.25 409	72.25 411	78.50 405	88.82 409

APD_test2		79.02 377	77.70 379	82.99 395	88.10 415	66.90 421	94.67 401	93.11 409	71.08 413	74.02 411	93.41 398	34.15 423	93.25 409	72.25 411	78.50 405	88.82 409

LCM-MVSNet		78.70 379	76.24 385	86.08 387	77.26 426	71.99 417	94.34 407	96.72 368	61.62 417	76.53 409	89.33 410	33.91 425	92.78 412	81.85 394	74.60 413	93.46 400

kuosan		78.45 380	77.69 381	80.72 399	92.73 401	75.32 412	94.63 404	74.51 428	75.96 409	80.87 407	93.19 400	63.23 409	79.99 423	42.56 423	81.56 394	86.85 415

Gipuma		78.40 381	76.75 384	83.38 394	95.54 366	80.43 406	79.42 419	97.40 324	64.67 416	73.46 413	80.82 417	45.65 416	93.14 411	66.32 415	87.43 364	76.56 419
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		77.95 382	75.44 386	85.46 388	82.54 421	74.95 413	94.23 408	93.08 411	72.80 412	74.68 410	87.38 411	36.36 422	91.56 413	73.95 409	63.94 418	89.87 408

FPMVS		77.62 383	77.14 383	79.05 401	79.25 424	60.97 426	95.79 388	95.94 385	65.96 415	67.93 417	94.40 389	37.73 421	88.88 418	68.83 414	88.46 354	87.29 412

EGC-MVSNET		75.22 384	69.54 387	92.28 375	94.81 383	89.58 356	97.64 307	96.50 375	1.82 427	5.57 428	95.74 366	68.21 399	96.26 393	73.80 410	91.71 309	90.99 405

ANet_high		69.08 385	65.37 389	80.22 400	65.99 428	71.96 418	90.91 414	90.09 419	82.62 402	49.93 423	78.39 418	29.36 426	81.75 420	62.49 416	38.52 422	86.95 414

tmp_tt		68.90 386	66.97 388	74.68 403	50.78 430	59.95 427	87.13 415	83.47 424	38.80 423	62.21 419	96.23 351	64.70 406	76.91 425	88.91 352	30.49 423	87.19 413

PMVS	61.03 23	65.95 387	63.57 391	73.09 404	57.90 429	51.22 431	85.05 417	93.93 407	54.45 418	44.32 424	83.57 413	13.22 428	89.15 417	58.68 418	81.00 396	78.91 418
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		64.94 388	64.25 390	67.02 405	82.28 422	59.36 428	91.83 413	85.63 422	52.69 419	60.22 420	77.28 419	41.06 420	80.12 422	46.15 422	41.14 420	61.57 421

EMVS		64.07 389	63.26 392	66.53 406	81.73 423	58.81 429	91.85 412	84.75 423	51.93 421	59.09 421	75.13 420	43.32 418	79.09 424	42.03 424	39.47 421	61.69 420

MVE	62.14 22	63.28 390	59.38 393	74.99 402	74.33 427	65.47 423	85.55 416	80.50 426	52.02 420	51.10 422	75.00 421	10.91 431	80.50 421	51.60 420	53.40 419	78.99 417
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		30.17 391	30.18 395	30.16 407	78.61 425	43.29 432	66.79 420	14.21 431	17.31 424	14.82 427	11.93 427	11.55 430	41.43 426	37.08 425	19.30 424	5.76 424

cdsmvs_eth3d_5k		23.98 392	31.98 394	0.00 410	0.00 433	0.00 435	0.00 421	98.59 152	0.00 428	0.00 429	98.61 157	90.60 169	0.00 429	0.00 428	0.00 427	0.00 425

testmvs		21.48 393	24.95 396	11.09 409	14.89 431	6.47 434	96.56 377	9.87 432	7.55 425	17.93 425	39.02 423	9.43 432	5.90 428	16.56 427	12.72 425	20.91 423

test123		20.95 394	23.72 397	12.64 408	13.54 432	8.19 433	96.55 378	6.13 433	7.48 426	16.74 426	37.98 424	12.97 429	6.05 427	16.69 426	5.43 426	23.68 422

ab-mvs-re		8.20 395	10.94 398	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	98.43 175	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

pcd_1.5k_mvsjas		7.88 396	10.50 399	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	94.51 87	0.00 429	0.00 428	0.00 427	0.00 425

mmdepth		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

monomultidepth		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

test_blank		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

uanet_test		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

DCPMVS		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

sosnet-low-res		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

sosnet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

uncertanet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

Regformer		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

uanet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

WAC-MVS						90.94 326								88.66 354

FOURS1					99.82 1	98.66 24	99.69 1	98.95 47	97.46 40	99.39 32

MSC_two_6792asdad				99.62 6	99.17 98	99.08 11		98.63 145					99.94 9	98.53 40	99.80 24	99.86 7

PC_three_1452									95.08 166	99.60 21	99.16 82	97.86 2	98.47 295	97.52 110	99.72 57	99.74 39

No_MVS				99.62 6	99.17 98	99.08 11		98.63 145					99.94 9	98.53 40	99.80 24	99.86 7

test_one_0601					99.66 26	99.25 2		98.86 76	97.55 34	99.20 44	99.47 25	97.57 6

eth-test2					0.00 433

eth-test					0.00 433

ZD-MVS					99.46 52	98.70 23		98.79 103	93.21 264	98.67 82	98.97 112	95.70 49	99.83 74	96.07 164	99.58 85

RE-MVS-def			98.34 39		99.49 46	97.86 68	99.11 60	98.80 98	96.49 96	99.17 47	99.35 48	95.29 65		97.72 90	99.65 70	99.71 52

IU-MVS					99.71 19	99.23 7		98.64 142	95.28 153	99.63 20				98.35 57	99.81 15	99.83 12

OPU-MVS				99.37 22	99.24 91	99.05 14	99.02 79				99.16 82	97.81 3	99.37 187	97.24 119	99.73 54	99.70 56

test_241102_TWO								98.87 70	97.65 27	99.53 25	99.48 23	97.34 11	99.94 9	98.43 52	99.80 24	99.83 12

test_241102_ONE					99.71 19	99.24 5		98.87 70	97.62 29	99.73 12	99.39 36	97.53 7	99.74 116

9.14			98.06 64		99.47 50		98.71 163	98.82 85	94.36 203	99.16 50	99.29 57	96.05 37	99.81 86	97.00 125	99.71 59

save fliter					99.46 52	98.38 35	98.21 238	98.71 121	97.95 18

test_0728_THIRD									97.32 48	99.45 27	99.46 29	97.88 1	99.94 9	98.47 48	99.86 2	99.85 9

test_0728_SECOND				99.71 1	99.72 12	99.35 1	98.97 89	98.88 63					99.94 9	98.47 48	99.81 15	99.84 11

test0726					99.72 12	99.25 2	99.06 67	98.88 63	97.62 29	99.56 22	99.50 20	97.42 9

GSMVS																99.20 147

test_part2					99.63 29	99.18 10				99.27 41

sam_mvs1												89.45 192				99.20 147

sam_mvs												88.99 206

ambc				89.49 382	86.66 417	75.78 409	92.66 411	96.72 368		86.55 390	92.50 405	46.01 415	97.90 352	90.32 327	82.09 389	94.80 386

MTGPA								98.74 113

test_post1							96.68 374				30.43 426	87.85 240	98.69 274	92.59 280

test_post											31.83 425	88.83 213	98.91 250

patchmatchnet-post											95.10 381	89.42 193	98.89 254

GG-mvs-BLEND				96.59 247	96.34 339	94.98 210	96.51 379	88.58 421		93.10 318	94.34 392	80.34 346	98.05 341	89.53 343	96.99 211	96.74 304

MTMP							98.89 110	94.14 405

gm-plane-assit					95.88 357	87.47 387			89.74 363		96.94 321		99.19 206	93.32 259

test9_res														96.39 158	99.57 86	99.69 59

TEST9					99.31 67	98.50 29	97.92 275	98.73 116	92.63 287	97.74 142	98.68 152	96.20 32	99.80 93

test_8					99.29 76	98.44 31	97.89 283	98.72 118	92.98 275	97.70 147	98.66 155	96.20 32	99.80 93

agg_prior2														95.87 174	99.57 86	99.68 64

agg_prior					99.30 71	98.38 35		98.72 118		97.57 159			99.81 86

TestCases				96.99 213	99.25 84	93.21 288		98.18 240	91.36 327	93.52 298	98.77 141	84.67 300	99.72 118	89.70 340	97.87 188	98.02 245

test_prior4						98.01 64	97.86 287

test_prior2							97.80 294		96.12 113	97.89 135	98.69 151	95.96 41		96.89 134	99.60 80

test_prior				99.19 43	99.31 67	98.22 51		98.84 80					99.70 124			99.65 72

旧先验2							97.57 313		91.30 332	98.67 82			99.80 93	95.70 183

新几何2							97.64 307

新几何1				99.16 48	99.34 60	98.01 64		98.69 126	90.06 357	98.13 111	98.95 119	94.60 85	99.89 52	91.97 299	99.47 105	99.59 82

旧先验1					99.29 76	97.48 82		98.70 125			99.09 98	95.56 52			99.47 105	99.61 78

无先验							97.58 312	98.72 118	91.38 326				99.87 63	93.36 258		99.60 80

原ACMM2							97.67 304

原ACMM1				98.65 84	99.32 65	96.62 123		98.67 134	93.27 263	97.81 137	98.97 112	95.18 72	99.83 74	93.84 244	99.46 108	99.50 94

test222					99.23 92	97.17 101	97.40 321	98.66 137	88.68 376	98.05 117	98.96 117	94.14 98			99.53 97	99.61 78

testdata2													99.89 52	91.65 306

segment_acmp												96.85 14

testdata				98.26 121	99.20 96	95.36 189		98.68 129	91.89 313	98.60 90	99.10 91	94.44 92	99.82 81	94.27 230	99.44 109	99.58 86

testdata1							97.32 331		96.34 104

test12				99.18 45	99.16 102	98.19 53		98.53 168		98.07 115		95.13 75	99.72 118		99.56 92	99.63 76

plane_prior7					97.42 275	94.63 227

plane_prior6					97.35 282	94.61 230						87.09 252

plane_prior5								98.56 162					99.03 230	96.07 164	94.27 262	96.92 281

plane_prior4											98.28 194

plane_prior3						94.61 230			97.02 70	95.34 229

plane_prior2							98.80 142		97.28 51

plane_prior1					97.37 281

plane_prior						94.60 232	98.44 212		96.74 84						94.22 264

n2								0.00 434

nn								0.00 434

door-mid								94.37 401

lessismore_v0				94.45 350	94.93 381	88.44 378		91.03 417		86.77 388	97.64 255	76.23 379	98.42 301	90.31 328	85.64 381	96.51 339

LGP-MVS_train				96.47 262	97.46 270	93.54 269		98.54 166	94.67 188	94.36 260	98.77 141	85.39 282	99.11 218	95.71 181	94.15 268	96.76 302

test11								98.66 137

door								94.64 399

HQP5-MVS						94.25 248

HQP-NCC					97.20 290		98.05 262		96.43 98	94.45 252

ACMP_Plane					97.20 290		98.05 262		96.43 98	94.45 252

BP-MVS														95.30 194

HQP4-MVS										94.45 252			98.96 241			96.87 293

HQP3-MVS								98.46 186							94.18 266

HQP2-MVS												86.75 258

NP-MVS					97.28 284	94.51 235					97.73 243

MDTV_nov1_ep13_2view						84.26 395	96.89 364		90.97 341	97.90 134		89.89 181		93.91 242		99.18 156

MDTV_nov1_ep13			95.40 182		97.48 268	88.34 379	96.85 367	97.29 331	93.74 233	97.48 161	97.26 283	89.18 200	99.05 226	91.92 300	97.43 203

ACMMP++_ref															92.97 294

ACMMP++															93.61 283

Test By Simon												94.64 84

ITE_SJBPF				95.44 312	97.42 275	91.32 320		97.50 312	95.09 165	93.59 294	98.35 185	81.70 329	98.88 256	89.71 339	93.39 289	96.12 358

DeepMVS_CX				86.78 386	97.09 300	72.30 416		95.17 395	75.92 410	84.34 399	95.19 379	70.58 396	95.35 400	79.98 400	89.04 348	92.68 404

High-resolution multi-view benchmark