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 55	99.43 57	97.48 83	98.88 116	99.30 13	98.47 14	99.85 8	99.43 38	96.71 17	99.96 4	99.86 1	99.80 24	99.89 5

SED-MVS		99.09 1	98.91 4	99.63 4	99.71 19	99.24 5	99.02 79	98.87 77	97.65 33	99.73 18	99.48 29	97.53 7	99.94 12	98.43 59	99.81 15	99.70 59

DVP-MVS++		99.08 3	98.89 5	99.64 3	99.17 101	99.23 7	99.69 1	98.88 70	97.32 55	99.53 32	99.47 31	97.81 3	99.94 12	98.47 55	99.72 60	99.74 42

fmvsm_l_conf0.5_n		99.07 4	99.05 2	99.14 51	99.41 59	97.54 81	98.89 110	99.31 12	98.49 13	99.86 5	99.42 39	96.45 24	99.96 4	99.86 1	99.74 52	99.90 4

DVP-MVS		99.03 5	98.83 9	99.63 4	99.72 12	99.25 2	98.97 89	98.58 164	97.62 35	99.45 34	99.46 35	97.42 9	99.94 12	98.47 55	99.81 15	99.69 62
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 58	97.38 52	99.41 37	99.54 17	96.66 18	99.84 79	98.86 34	99.85 6	99.87 8
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 26	99.52 39	98.26 49	98.94 98	98.84 87	98.06 21	99.35 41	99.61 4	96.39 27	99.94 12	98.77 37	99.82 14	99.83 14

reproduce-ours		98.93 8	98.78 11	99.38 18	99.49 46	98.38 35	98.86 123	98.83 89	98.06 21	99.29 45	99.58 13	96.40 25	99.94 12	98.68 39	99.81 15	99.81 20

our_new_method		98.93 8	98.78 11	99.38 18	99.49 46	98.38 35	98.86 123	98.83 89	98.06 21	99.29 45	99.58 13	96.40 25	99.94 12	98.68 39	99.81 15	99.81 20

test_fmvsmconf_n		98.92 10	98.87 6	99.04 61	98.88 136	97.25 102	98.82 135	99.34 10	98.75 7	99.80 10	99.61 4	95.16 73	99.95 9	99.70 13	99.80 24	99.93 1

DPE-MVS		98.92 10	98.67 16	99.65 2	99.58 32	99.20 9	98.42 224	98.91 64	97.58 38	99.54 31	99.46 35	97.10 12	99.94 12	97.64 106	99.84 11	99.83 14
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
fmvsm_l_conf0.5_n_3		98.90 12	98.74 14	99.37 22	99.36 60	98.25 50	98.89 110	99.24 18	98.77 6	99.89 1	99.59 11	93.39 107	99.96 4	99.78 6	99.76 42	99.89 5

SteuartSystems-ACMMP		98.90 12	98.75 13	99.36 24	99.22 96	98.43 33	99.10 63	98.87 77	97.38 52	99.35 41	99.40 42	97.78 5	99.87 70	97.77 94	99.85 6	99.78 26
Skip Steuart: Steuart Systems R&D Blog.
test_fmvsm_n_1920		98.87 14	99.01 3	98.45 109	99.42 58	96.43 141	98.96 94	99.36 9	98.63 9	99.86 5	99.51 23	95.91 43	99.97 1	99.72 10	99.75 48	98.94 191

TSAR-MVS + MP.		98.78 15	98.62 17	99.24 40	99.69 24	98.28 48	99.14 54	98.66 144	96.84 84	99.56 29	99.31 62	96.34 28	99.70 131	98.32 65	99.73 55	99.73 47
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 15	98.56 21	99.45 15	99.32 67	98.87 19	98.47 216	98.81 98	97.72 28	98.76 84	99.16 89	97.05 13	99.78 113	98.06 76	99.66 71	99.69 62

MSP-MVS		98.74 17	98.55 22	99.29 33	99.75 3	98.23 51	99.26 27	98.88 70	97.52 41	99.41 37	98.78 146	96.00 39	99.79 110	97.79 93	99.59 88	99.85 11
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
fmvsm_s_conf0.5_n_8		98.73 18	98.62 17	99.05 60	99.35 61	97.27 96	98.80 144	99.23 23	98.93 2	99.79 11	99.59 11	92.34 123	99.95 9	99.82 4	99.71 62	99.92 2

XVS		98.70 19	98.49 28	99.34 26	99.70 22	98.35 44	99.29 22	98.88 70	97.40 49	98.46 102	99.20 79	95.90 45	99.89 59	97.85 89	99.74 52	99.78 26

fmvsm_s_conf0.5_n_6		98.65 20	98.55 22	98.95 70	98.50 176	97.30 95	98.79 152	99.16 33	98.14 19	99.86 5	99.41 41	93.71 104	99.91 48	99.71 11	99.64 79	99.65 75

MCST-MVS		98.65 20	98.37 37	99.48 13	99.60 31	98.87 19	98.41 225	98.68 136	97.04 76	98.52 100	98.80 144	96.78 16	99.83 81	97.93 83	99.61 84	99.74 42

SD-MVS		98.64 22	98.68 15	98.53 100	99.33 64	98.36 43	98.90 106	98.85 86	97.28 58	99.72 21	99.39 43	96.63 20	97.60 376	98.17 71	99.85 6	99.64 78
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 23	98.40 34	99.32 32	99.72 12	98.29 47	99.23 32	98.96 53	96.10 122	98.94 67	99.17 86	96.06 36	99.92 38	97.62 107	99.78 34	99.75 40

ACMMP_NAP		98.61 24	98.30 52	99.55 9	99.62 30	98.95 17	98.82 135	98.81 98	95.80 133	99.16 57	99.47 31	95.37 60	99.92 38	97.89 87	99.75 48	99.79 24

region2R		98.61 24	98.38 36	99.29 33	99.74 7	98.16 57	99.23 32	98.93 58	96.15 118	98.94 67	99.17 86	95.91 43	99.94 12	97.55 115	99.79 30	99.78 26

NCCC		98.61 24	98.35 40	99.38 18	99.28 82	98.61 26	98.45 217	98.76 116	97.82 27	98.45 105	98.93 128	96.65 19	99.83 81	97.38 124	99.41 119	99.71 55

SF-MVS		98.59 27	98.32 51	99.41 17	99.54 35	98.71 22	99.04 73	98.81 98	95.12 170	99.32 44	99.39 43	96.22 30	99.84 79	97.72 97	99.73 55	99.67 71

ACMMPR		98.59 27	98.36 38	99.29 33	99.74 7	98.15 58	99.23 32	98.95 54	96.10 122	98.93 71	99.19 84	95.70 49	99.94 12	97.62 107	99.79 30	99.78 26

test_fmvsmconf0.1_n		98.58 29	98.44 32	98.99 63	97.73 256	97.15 107	98.84 131	98.97 50	98.75 7	99.43 36	99.54 17	93.29 109	99.93 31	99.64 16	99.79 30	99.89 5

SMA-MVS		98.58 29	98.25 55	99.56 8	99.51 40	99.04 15	98.95 95	98.80 105	93.67 255	99.37 40	99.52 20	96.52 22	99.89 59	98.06 76	99.81 15	99.76 39
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 29	98.29 53	99.46 14	99.76 2	98.64 25	98.90 106	98.74 120	97.27 62	98.02 129	99.39 43	94.81 83	99.96 4	97.91 85	99.79 30	99.77 32

HPM-MVS++		98.58 29	98.25 55	99.55 9	99.50 42	99.08 11	98.72 168	98.66 144	97.51 42	98.15 116	98.83 141	95.70 49	99.92 38	97.53 117	99.67 68	99.66 74

SR-MVS		98.57 33	98.35 40	99.24 40	99.53 36	98.18 55	99.09 64	98.82 92	96.58 100	99.10 59	99.32 60	95.39 58	99.82 88	97.70 102	99.63 81	99.72 51

CP-MVS		98.57 33	98.36 38	99.19 44	99.66 26	97.86 69	99.34 16	98.87 77	95.96 125	98.60 97	99.13 94	96.05 37	99.94 12	97.77 94	99.86 2	99.77 32

MSLP-MVS++		98.56 35	98.57 20	98.55 96	99.26 85	96.80 121	98.71 169	99.05 43	97.28 58	98.84 77	99.28 65	96.47 23	99.40 191	98.52 53	99.70 64	99.47 107

DeepC-MVS_fast	96.70 1	98.55 36	98.34 46	99.18 46	99.25 86	98.04 63	98.50 213	98.78 112	97.72 28	98.92 73	99.28 65	95.27 66	99.82 88	97.55 115	99.77 36	99.69 62
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 37	98.35 40	99.13 52	99.49 46	97.86 69	99.11 60	98.80 105	96.49 103	99.17 54	99.35 55	95.34 62	99.82 88	97.72 97	99.65 74	99.71 55

fmvsm_s_conf0.5_n_5		98.53 38	98.35 40	99.08 57	99.07 116	97.46 87	98.68 177	99.20 28	97.50 43	99.87 2	99.50 25	91.96 142	99.96 4	99.76 7	99.65 74	99.82 18

fmvsm_s_conf0.5_n_3		98.53 38	98.45 31	98.79 78	99.23 94	97.32 92	98.80 144	99.26 15	98.82 3	99.87 2	99.60 8	90.95 170	99.93 31	99.76 7	99.73 55	99.12 166

APD-MVS_3200maxsize		98.53 38	98.33 50	99.15 50	99.50 42	97.92 68	99.15 51	98.81 98	96.24 114	99.20 51	99.37 49	95.30 64	99.80 100	97.73 96	99.67 68	99.72 51

MM		98.51 41	98.24 57	99.33 30	99.12 110	98.14 60	98.93 101	97.02 362	98.96 1	99.17 54	99.47 31	91.97 141	99.94 12	99.85 3	99.69 65	99.91 3

mPP-MVS		98.51 41	98.26 54	99.25 39	99.75 3	98.04 63	99.28 24	98.81 98	96.24 114	98.35 112	99.23 74	95.46 55	99.94 12	97.42 122	99.81 15	99.77 32

ZNCC-MVS		98.49 43	98.20 63	99.35 25	99.73 11	98.39 34	99.19 44	98.86 83	95.77 135	98.31 115	99.10 98	95.46 55	99.93 31	97.57 114	99.81 15	99.74 42

SPE-MVS-test		98.49 43	98.50 26	98.46 108	99.20 99	97.05 111	99.64 4	98.50 186	97.45 48	98.88 74	99.14 93	95.25 68	99.15 219	98.83 35	99.56 98	99.20 151

PGM-MVS		98.49 43	98.23 59	99.27 38	99.72 12	98.08 62	98.99 86	99.49 5	95.43 151	99.03 60	99.32 60	95.56 52	99.94 12	96.80 153	99.77 36	99.78 26

EI-MVSNet-Vis-set		98.47 46	98.39 35	98.69 85	99.46 52	96.49 138	98.30 236	98.69 133	97.21 65	98.84 77	99.36 53	95.41 57	99.78 113	98.62 42	99.65 74	99.80 23

MVS_111021_HR		98.47 46	98.34 46	98.88 75	99.22 96	97.32 92	97.91 288	99.58 3	97.20 66	98.33 113	99.00 117	95.99 40	99.64 144	98.05 78	99.76 42	99.69 62

balanced_conf03		98.45 48	98.35 40	98.74 81	98.65 165	97.55 79	99.19 44	98.60 155	96.72 94	99.35 41	98.77 148	95.06 78	99.55 167	98.95 31	99.87 1	99.12 166

test_fmvsmvis_n_1920		98.44 49	98.51 24	98.23 129	98.33 196	96.15 155	98.97 89	99.15 35	98.55 12	98.45 105	99.55 15	94.26 96	99.97 1	99.65 14	99.66 71	98.57 232

CS-MVS		98.44 49	98.49 28	98.31 121	99.08 115	96.73 125	99.67 3	98.47 193	97.17 68	98.94 67	99.10 98	95.73 48	99.13 222	98.71 38	99.49 109	99.09 171

GST-MVS		98.43 51	98.12 67	99.34 26	99.72 12	98.38 35	99.09 64	98.82 92	95.71 139	98.73 87	99.06 109	95.27 66	99.93 31	97.07 132	99.63 81	99.72 51

fmvsm_s_conf0.5_n		98.42 52	98.51 24	98.13 138	99.30 73	95.25 201	98.85 127	99.39 7	97.94 25	99.74 17	99.62 3	92.59 118	99.91 48	99.65 14	99.52 104	99.25 144

EI-MVSNet-UG-set		98.41 53	98.34 46	98.61 91	99.45 55	96.32 148	98.28 239	98.68 136	97.17 68	98.74 85	99.37 49	95.25 68	99.79 110	98.57 44	99.54 101	99.73 47

DELS-MVS		98.40 54	98.20 63	98.99 63	99.00 123	97.66 74	97.75 309	98.89 67	97.71 30	98.33 113	98.97 119	94.97 80	99.88 68	98.42 61	99.76 42	99.42 118
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 55	98.42 33	98.27 123	99.09 114	95.41 191	98.86 123	99.37 8	97.69 32	99.78 13	99.61 4	92.38 121	99.91 48	99.58 19	99.43 117	99.49 103

TSAR-MVS + GP.		98.38 55	98.24 57	98.81 77	99.22 96	97.25 102	98.11 263	98.29 232	97.19 67	98.99 65	99.02 112	96.22 30	99.67 138	98.52 53	98.56 167	99.51 96

HPM-MVS_fast		98.38 55	98.13 66	99.12 54	99.75 3	97.86 69	99.44 9	98.82 92	94.46 210	98.94 67	99.20 79	95.16 73	99.74 123	97.58 110	99.85 6	99.77 32

patch_mono-2		98.36 58	98.87 6	96.82 234	99.53 36	90.68 342	98.64 187	99.29 14	97.88 26	99.19 53	99.52 20	96.80 15	99.97 1	99.11 27	99.86 2	99.82 18

HPM-MVS		98.36 58	98.10 70	99.13 52	99.74 7	97.82 73	99.53 6	98.80 105	94.63 199	98.61 96	98.97 119	95.13 75	99.77 118	97.65 105	99.83 13	99.79 24
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
fmvsm_s_conf0.5_n_4		98.35 60	98.50 26	97.90 155	99.16 105	95.08 210	98.75 156	99.24 18	98.39 15	99.81 9	99.52 20	92.35 122	99.90 56	99.74 9	99.51 106	98.71 213

APD-MVS		98.35 60	98.00 76	99.42 16	99.51 40	98.72 21	98.80 144	98.82 92	94.52 207	99.23 50	99.25 73	95.54 54	99.80 100	96.52 160	99.77 36	99.74 42
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_LR		98.34 62	98.23 59	98.67 87	99.27 83	96.90 117	97.95 281	99.58 3	97.14 71	98.44 107	99.01 116	95.03 79	99.62 151	97.91 85	99.75 48	99.50 98

PHI-MVS		98.34 62	98.06 71	99.18 46	99.15 108	98.12 61	99.04 73	99.09 38	93.32 270	98.83 79	99.10 98	96.54 21	99.83 81	97.70 102	99.76 42	99.59 86

MP-MVS		98.33 64	98.01 75	99.28 36	99.75 3	98.18 55	99.22 36	98.79 110	96.13 119	97.92 140	99.23 74	94.54 86	99.94 12	96.74 156	99.78 34	99.73 47
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MVSMamba_PlusPlus		98.31 65	98.19 65	98.67 87	98.96 130	97.36 90	99.24 30	98.57 166	94.81 191	98.99 65	98.90 132	95.22 71	99.59 154	99.15 26	99.84 11	99.07 179

MP-MVS-pluss		98.31 65	97.92 78	99.49 12	99.72 12	98.88 18	98.43 222	98.78 112	94.10 220	97.69 155	99.42 39	95.25 68	99.92 38	98.09 75	99.80 24	99.67 71
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.5_n_2		98.30 67	98.21 61	98.57 93	99.25 86	97.11 108	98.66 183	99.20 28	98.82 3	99.79 11	99.60 8	89.38 201	99.92 38	99.80 5	99.38 124	98.69 215

fmvsm_s_conf0.5_n_7		98.23 68	98.35 40	97.89 157	98.86 140	94.99 216	98.58 196	99.00 46	98.29 16	99.73 18	99.60 8	91.70 146	99.92 38	99.63 17	99.73 55	98.76 209

MVS_0304		98.23 68	97.91 79	99.21 43	98.06 226	97.96 67	98.58 196	95.51 399	98.58 10	98.87 75	99.26 68	92.99 113	99.95 9	99.62 18	99.67 68	99.73 47

ACMMP		98.23 68	97.95 77	99.09 56	99.74 7	97.62 77	99.03 76	99.41 6	95.98 124	97.60 164	99.36 53	94.45 91	99.93 31	97.14 129	98.85 153	99.70 59
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 71	98.11 68	98.49 105	98.34 193	97.26 101	99.61 5	98.43 202	96.78 87	98.87 75	98.84 139	93.72 103	99.01 244	98.91 33	99.50 107	99.19 155

fmvsm_s_conf0.1_n		98.18 72	98.21 61	98.11 142	98.54 174	95.24 202	98.87 119	99.24 18	97.50 43	99.70 22	99.67 1	91.33 159	99.89 59	99.47 21	99.54 101	99.21 150

fmvsm_s_conf0.1_n_2		98.14 73	98.02 74	98.53 100	98.88 136	97.07 110	98.69 175	98.82 92	98.78 5	99.77 14	99.61 4	88.83 220	99.91 48	99.71 11	99.07 137	98.61 225

fmvsm_s_conf0.1_n_a		98.08 74	98.04 73	98.21 130	97.66 262	95.39 192	98.89 110	99.17 32	97.24 63	99.76 16	99.67 1	91.13 164	99.88 68	99.39 22	99.41 119	99.35 123

dcpmvs_2		98.08 74	98.59 19	96.56 259	99.57 33	90.34 351	99.15 51	98.38 212	96.82 86	99.29 45	99.49 28	95.78 47	99.57 157	98.94 32	99.86 2	99.77 32

CANet		98.05 76	97.76 82	98.90 74	98.73 150	97.27 96	98.35 227	98.78 112	97.37 54	97.72 152	98.96 124	91.53 155	99.92 38	98.79 36	99.65 74	99.51 96

train_agg		97.97 77	97.52 94	99.33 30	99.31 69	98.50 29	97.92 286	98.73 123	92.98 286	97.74 149	98.68 159	96.20 32	99.80 100	96.59 157	99.57 92	99.68 67

ETV-MVS		97.96 78	97.81 80	98.40 116	98.42 181	97.27 96	98.73 164	98.55 171	96.84 84	98.38 109	97.44 278	95.39 58	99.35 196	97.62 107	98.89 148	98.58 231

UA-Net		97.96 78	97.62 86	98.98 65	98.86 140	97.47 85	98.89 110	99.08 39	96.67 97	98.72 88	99.54 17	93.15 111	99.81 93	94.87 215	98.83 154	99.65 75

CDPH-MVS		97.94 80	97.49 96	99.28 36	99.47 50	98.44 31	97.91 288	98.67 141	92.57 302	98.77 83	98.85 138	95.93 42	99.72 125	95.56 194	99.69 65	99.68 67

DeepPCF-MVS	96.37 2	97.93 81	98.48 30	96.30 284	99.00 123	89.54 366	97.43 331	98.87 77	98.16 18	99.26 49	99.38 48	96.12 35	99.64 144	98.30 66	99.77 36	99.72 51

DeepC-MVS	95.98 3	97.88 82	97.58 88	98.77 79	99.25 86	96.93 115	98.83 133	98.75 118	96.96 80	96.89 190	99.50 25	90.46 178	99.87 70	97.84 91	99.76 42	99.52 93
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 83	97.54 93	98.83 76	95.48 381	96.83 120	98.95 95	98.60 155	98.58 10	98.93 71	99.55 15	88.57 225	99.91 48	99.54 20	99.61 84	99.77 32

DP-MVS Recon		97.86 83	97.46 99	99.06 59	99.53 36	98.35 44	98.33 229	98.89 67	92.62 299	98.05 124	98.94 127	95.34 62	99.65 141	96.04 176	99.42 118	99.19 155

CSCG		97.85 85	97.74 83	98.20 132	99.67 25	95.16 205	99.22 36	99.32 11	93.04 284	97.02 183	98.92 130	95.36 61	99.91 48	97.43 121	99.64 79	99.52 93

BP-MVS1		97.82 86	97.51 95	98.76 80	98.25 203	97.39 89	99.15 51	97.68 299	96.69 95	98.47 101	99.10 98	90.29 182	99.51 174	98.60 43	99.35 127	99.37 121

MG-MVS		97.81 87	97.60 87	98.44 111	99.12 110	95.97 164	97.75 309	98.78 112	96.89 83	98.46 102	99.22 76	93.90 102	99.68 137	94.81 219	99.52 104	99.67 71

VNet		97.79 88	97.40 103	98.96 68	98.88 136	97.55 79	98.63 190	98.93 58	96.74 91	99.02 61	98.84 139	90.33 181	99.83 81	98.53 47	96.66 231	99.50 98

EIA-MVS		97.75 89	97.58 88	98.27 123	98.38 185	96.44 140	99.01 81	98.60 155	95.88 129	97.26 171	97.53 272	94.97 80	99.33 199	97.38 124	99.20 133	99.05 180

PS-MVSNAJ		97.73 90	97.77 81	97.62 184	98.68 160	95.58 182	97.34 340	98.51 181	97.29 57	98.66 93	97.88 237	94.51 87	99.90 56	97.87 88	99.17 135	97.39 274

casdiffmvs_mvg		97.72 91	97.48 98	98.44 111	98.42 181	96.59 133	98.92 103	98.44 198	96.20 116	97.76 146	99.20 79	91.66 149	99.23 209	98.27 70	98.41 177	99.49 103
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 91	97.32 107	98.92 71	99.64 28	97.10 109	99.12 58	98.81 98	92.34 310	98.09 121	99.08 107	93.01 112	99.92 38	96.06 175	99.77 36	99.75 40

PVSNet_Blended_VisFu		97.70 93	97.46 99	98.44 111	99.27 83	95.91 172	98.63 190	99.16 33	94.48 209	97.67 156	98.88 135	92.80 115	99.91 48	97.11 130	99.12 136	99.50 98

mvsany_test1		97.69 94	97.70 84	97.66 182	98.24 204	94.18 257	97.53 325	97.53 317	95.52 147	99.66 24	99.51 23	94.30 94	99.56 160	98.38 62	98.62 163	99.23 146

sasdasda		97.67 95	97.23 111	98.98 65	98.70 155	98.38 35	99.34 16	98.39 208	96.76 89	97.67 156	97.40 282	92.26 127	99.49 178	98.28 67	96.28 249	99.08 175

canonicalmvs		97.67 95	97.23 111	98.98 65	98.70 155	98.38 35	99.34 16	98.39 208	96.76 89	97.67 156	97.40 282	92.26 127	99.49 178	98.28 67	96.28 249	99.08 175

xiu_mvs_v2_base		97.66 97	97.70 84	97.56 188	98.61 169	95.46 189	97.44 329	98.46 194	97.15 70	98.65 94	98.15 213	94.33 93	99.80 100	97.84 91	98.66 162	97.41 272

GDP-MVS		97.64 98	97.28 108	98.71 84	98.30 201	97.33 91	99.05 69	98.52 178	96.34 111	98.80 80	99.05 110	89.74 191	99.51 174	96.86 150	98.86 152	99.28 138

baseline		97.64 98	97.44 101	98.25 127	98.35 188	96.20 152	99.00 83	98.32 222	96.33 113	98.03 127	99.17 86	91.35 158	99.16 216	98.10 74	98.29 184	99.39 119

casdiffmvs		97.63 100	97.41 102	98.28 122	98.33 196	96.14 156	98.82 135	98.32 222	96.38 110	97.95 135	99.21 77	91.23 163	99.23 209	98.12 73	98.37 178	99.48 105
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		97.62 101	97.19 114	98.92 71	98.66 162	98.20 53	99.32 21	98.38 212	96.69 95	97.58 165	97.42 281	92.10 135	99.50 177	98.28 67	96.25 252	99.08 175

xiu_mvs_v1_base_debu		97.60 102	97.56 90	97.72 172	98.35 188	95.98 159	97.86 298	98.51 181	97.13 72	99.01 62	98.40 186	91.56 151	99.80 100	98.53 47	98.68 158	97.37 276

xiu_mvs_v1_base		97.60 102	97.56 90	97.72 172	98.35 188	95.98 159	97.86 298	98.51 181	97.13 72	99.01 62	98.40 186	91.56 151	99.80 100	98.53 47	98.68 158	97.37 276

xiu_mvs_v1_base_debi		97.60 102	97.56 90	97.72 172	98.35 188	95.98 159	97.86 298	98.51 181	97.13 72	99.01 62	98.40 186	91.56 151	99.80 100	98.53 47	98.68 158	97.37 276

diffmvs		97.58 105	97.40 103	98.13 138	98.32 199	95.81 177	98.06 269	98.37 214	96.20 116	98.74 85	98.89 134	91.31 161	99.25 206	98.16 72	98.52 169	99.34 125
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		97.57 106	97.49 96	97.84 159	98.07 223	95.76 178	99.47 7	98.40 206	94.98 180	98.79 81	98.83 141	92.34 123	98.41 317	96.91 138	99.59 88	99.34 125

alignmvs		97.56 107	97.07 120	99.01 62	98.66 162	98.37 42	98.83 133	98.06 279	96.74 91	98.00 133	97.65 260	90.80 172	99.48 183	98.37 63	96.56 235	99.19 155

DPM-MVS		97.55 108	96.99 123	99.23 42	99.04 118	98.55 27	97.17 355	98.35 217	94.85 190	97.93 139	98.58 169	95.07 77	99.71 130	92.60 287	99.34 128	99.43 116

OMC-MVS		97.55 108	97.34 106	98.20 132	99.33 64	95.92 171	98.28 239	98.59 159	95.52 147	97.97 134	99.10 98	93.28 110	99.49 178	95.09 210	98.88 149	99.19 155

PAPM_NR		97.46 110	97.11 117	98.50 103	99.50 42	96.41 143	98.63 190	98.60 155	95.18 167	97.06 181	98.06 219	94.26 96	99.57 157	93.80 255	98.87 151	99.52 93

EPP-MVSNet		97.46 110	97.28 108	97.99 150	98.64 166	95.38 193	99.33 20	98.31 224	93.61 259	97.19 174	99.07 108	94.05 99	99.23 209	96.89 142	98.43 176	99.37 121

3Dnovator	94.51 5	97.46 110	96.93 126	99.07 58	97.78 250	97.64 75	99.35 15	99.06 41	97.02 77	93.75 302	99.16 89	89.25 205	99.92 38	97.22 128	99.75 48	99.64 78

CNLPA		97.45 113	97.03 121	98.73 82	99.05 117	97.44 88	98.07 268	98.53 175	95.32 160	96.80 195	98.53 174	93.32 108	99.72 125	94.31 238	99.31 130	99.02 182

lupinMVS		97.44 114	97.22 113	98.12 141	98.07 223	95.76 178	97.68 314	97.76 296	94.50 208	98.79 81	98.61 164	92.34 123	99.30 202	97.58 110	99.59 88	99.31 131

3Dnovator+	94.38 6	97.43 115	96.78 134	99.38 18	97.83 247	98.52 28	99.37 12	98.71 128	97.09 75	92.99 331	99.13 94	89.36 202	99.89 59	96.97 135	99.57 92	99.71 55

Vis-MVSNet		97.42 116	97.11 117	98.34 119	98.66 162	96.23 151	99.22 36	99.00 46	96.63 99	98.04 126	99.21 77	88.05 241	99.35 196	96.01 178	99.21 132	99.45 113
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
API-MVS		97.41 117	97.25 110	97.91 154	98.70 155	96.80 121	98.82 135	98.69 133	94.53 205	98.11 119	98.28 201	94.50 90	99.57 157	94.12 244	99.49 109	97.37 276

sss		97.39 118	96.98 125	98.61 91	98.60 170	96.61 130	98.22 245	98.93 58	93.97 230	98.01 132	98.48 179	91.98 139	99.85 75	96.45 162	98.15 186	99.39 119

test_cas_vis1_n_1920		97.38 119	97.36 105	97.45 191	98.95 131	93.25 293	99.00 83	98.53 175	97.70 31	99.77 14	99.35 55	84.71 306	99.85 75	98.57 44	99.66 71	99.26 142

PVSNet_Blended		97.38 119	97.12 116	98.14 135	99.25 86	95.35 196	97.28 345	99.26 15	93.13 280	97.94 137	98.21 209	92.74 116	99.81 93	96.88 144	99.40 122	99.27 139

WTY-MVS		97.37 121	96.92 127	98.72 83	98.86 140	96.89 119	98.31 234	98.71 128	95.26 163	97.67 156	98.56 173	92.21 131	99.78 113	95.89 180	96.85 225	99.48 105

jason		97.32 122	97.08 119	98.06 146	97.45 282	95.59 181	97.87 296	97.91 290	94.79 192	98.55 99	98.83 141	91.12 165	99.23 209	97.58 110	99.60 86	99.34 125
jason: jason.
MVS_Test		97.28 123	97.00 122	98.13 138	98.33 196	95.97 164	98.74 160	98.07 274	94.27 215	98.44 107	98.07 218	92.48 119	99.26 205	96.43 163	98.19 185	99.16 161

EPNet		97.28 123	96.87 129	98.51 102	94.98 390	96.14 156	98.90 106	97.02 362	98.28 17	95.99 227	99.11 96	91.36 157	99.89 59	96.98 134	99.19 134	99.50 98
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvsmamba		97.25 125	96.99 123	98.02 148	98.34 193	95.54 186	99.18 48	97.47 323	95.04 176	98.15 116	98.57 172	89.46 198	99.31 201	97.68 104	99.01 142	99.22 148

test_yl		97.22 126	96.78 134	98.54 98	98.73 150	96.60 131	98.45 217	98.31 224	94.70 193	98.02 129	98.42 184	90.80 172	99.70 131	96.81 151	96.79 227	99.34 125

DCV-MVSNet		97.22 126	96.78 134	98.54 98	98.73 150	96.60 131	98.45 217	98.31 224	94.70 193	98.02 129	98.42 184	90.80 172	99.70 131	96.81 151	96.79 227	99.34 125

IS-MVSNet		97.22 126	96.88 128	98.25 127	98.85 143	96.36 146	99.19 44	97.97 284	95.39 154	97.23 172	98.99 118	91.11 166	98.93 256	94.60 226	98.59 165	99.47 107

PLC	95.07 4	97.20 129	96.78 134	98.44 111	99.29 78	96.31 150	98.14 258	98.76 116	92.41 308	96.39 215	98.31 199	94.92 82	99.78 113	94.06 247	98.77 157	99.23 146
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		97.18 130	97.18 115	97.20 204	98.81 146	93.27 290	95.78 400	99.15 35	95.25 164	96.79 196	98.11 216	92.29 126	99.07 234	98.56 46	99.85 6	99.25 144

LS3D		97.16 131	96.66 143	98.68 86	98.53 175	97.19 105	98.93 101	98.90 65	92.83 293	95.99 227	99.37 49	92.12 134	99.87 70	93.67 259	99.57 92	98.97 187

AdaColmap		97.15 132	96.70 139	98.48 106	99.16 105	96.69 127	98.01 275	98.89 67	94.44 211	96.83 191	98.68 159	90.69 175	99.76 119	94.36 234	99.29 131	98.98 186

mamv4		97.13 133	98.11 68	94.17 365	98.97 129	83.70 408	98.66 183	98.71 128	94.63 199	97.83 143	98.90 132	96.25 29	99.55 167	99.27 24	99.76 42	99.27 139

Effi-MVS+		97.12 134	96.69 140	98.39 117	98.19 212	96.72 126	97.37 336	98.43 202	93.71 248	97.65 160	98.02 222	92.20 132	99.25 206	96.87 147	97.79 198	99.19 155

CHOSEN 1792x2688		97.12 134	96.80 131	98.08 144	99.30 73	94.56 241	98.05 270	99.71 1	93.57 260	97.09 177	98.91 131	88.17 235	99.89 59	96.87 147	99.56 98	99.81 20

F-COLMAP		97.09 136	96.80 131	97.97 151	99.45 55	94.95 220	98.55 205	98.62 154	93.02 285	96.17 222	98.58 169	94.01 100	99.81 93	93.95 249	98.90 147	99.14 164

RRT-MVS		97.03 137	96.78 134	97.77 168	97.90 243	94.34 250	99.12 58	98.35 217	95.87 130	98.06 123	98.70 157	86.45 272	99.63 147	98.04 79	98.54 168	99.35 123

TAMVS		97.02 138	96.79 133	97.70 175	98.06 226	95.31 199	98.52 207	98.31 224	93.95 231	97.05 182	98.61 164	93.49 106	98.52 299	95.33 201	97.81 197	99.29 136

CDS-MVSNet		96.99 139	96.69 140	97.90 155	98.05 228	95.98 159	98.20 248	98.33 221	93.67 255	96.95 184	98.49 178	93.54 105	98.42 310	95.24 207	97.74 201	99.31 131
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CANet_DTU		96.96 140	96.55 146	98.21 130	98.17 217	96.07 158	97.98 279	98.21 241	97.24 63	97.13 176	98.93 128	86.88 264	99.91 48	95.00 213	99.37 126	98.66 221

114514_t		96.93 141	96.27 156	98.92 71	99.50 42	97.63 76	98.85 127	98.90 65	84.80 407	97.77 145	99.11 96	92.84 114	99.66 140	94.85 216	99.77 36	99.47 107

MAR-MVS		96.91 142	96.40 152	98.45 109	98.69 158	96.90 117	98.66 183	98.68 136	92.40 309	97.07 180	97.96 229	91.54 154	99.75 121	93.68 257	98.92 146	98.69 215
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		96.90 143	96.49 149	98.14 135	99.33 64	95.56 183	97.38 334	99.65 2	92.34 310	97.61 163	98.20 210	89.29 204	99.10 231	96.97 135	97.60 206	99.77 32

Vis-MVSNet (Re-imp)		96.87 144	96.55 146	97.83 160	98.73 150	95.46 189	99.20 42	98.30 230	94.96 182	96.60 203	98.87 136	90.05 185	98.59 294	93.67 259	98.60 164	99.46 111

SDMVSNet		96.85 145	96.42 150	98.14 135	99.30 73	96.38 144	99.21 39	99.23 23	95.92 126	95.96 229	98.76 153	85.88 282	99.44 188	97.93 83	95.59 264	98.60 226

PAPR		96.84 146	96.24 158	98.65 89	98.72 154	96.92 116	97.36 338	98.57 166	93.33 269	96.67 198	97.57 269	94.30 94	99.56 160	91.05 329	98.59 165	99.47 107

HY-MVS	93.96 8	96.82 147	96.23 159	98.57 93	98.46 180	97.00 112	98.14 258	98.21 241	93.95 231	96.72 197	97.99 226	91.58 150	99.76 119	94.51 230	96.54 236	98.95 190

UGNet		96.78 148	96.30 155	98.19 134	98.24 204	95.89 174	98.88 116	98.93 58	97.39 51	96.81 194	97.84 241	82.60 333	99.90 56	96.53 159	99.49 109	98.79 202
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		96.73 149	96.60 144	97.12 213	99.25 86	95.35 196	98.26 242	99.26 15	94.28 214	97.94 137	97.46 275	92.74 116	99.81 93	96.88 144	93.32 300	96.20 367

test_vis1_n_1920		96.71 150	96.84 130	96.31 283	99.11 112	89.74 359	99.05 69	98.58 164	98.08 20	99.87 2	99.37 49	78.48 365	99.93 31	99.29 23	99.69 65	99.27 139

mvs_anonymous		96.70 151	96.53 148	97.18 207	98.19 212	93.78 266	98.31 234	98.19 245	94.01 227	94.47 261	98.27 204	92.08 137	98.46 305	97.39 123	97.91 193	99.31 131

1112_ss		96.63 152	96.00 166	98.50 103	98.56 171	96.37 145	98.18 256	98.10 267	92.92 289	94.84 249	98.43 182	92.14 133	99.58 156	94.35 235	96.51 237	99.56 92

PMMVS		96.60 153	96.33 154	97.41 195	97.90 243	93.93 262	97.35 339	98.41 204	92.84 292	97.76 146	97.45 277	91.10 167	99.20 213	96.26 168	97.91 193	99.11 169

DP-MVS		96.59 154	95.93 169	98.57 93	99.34 62	96.19 154	98.70 173	98.39 208	89.45 379	94.52 259	99.35 55	91.85 143	99.85 75	92.89 283	98.88 149	99.68 67

PatchMatch-RL		96.59 154	96.03 165	98.27 123	99.31 69	96.51 137	97.91 288	99.06 41	93.72 247	96.92 188	98.06 219	88.50 230	99.65 141	91.77 312	99.00 144	98.66 221

GeoE		96.58 156	96.07 162	98.10 143	98.35 188	95.89 174	99.34 16	98.12 261	93.12 281	96.09 223	98.87 136	89.71 192	98.97 246	92.95 279	98.08 189	99.43 116

XVG-OURS		96.55 157	96.41 151	96.99 220	98.75 149	93.76 267	97.50 328	98.52 178	95.67 141	96.83 191	99.30 63	88.95 218	99.53 170	95.88 181	96.26 251	97.69 265

FIs		96.51 158	96.12 161	97.67 179	97.13 306	97.54 81	99.36 13	99.22 27	95.89 128	94.03 288	98.35 192	91.98 139	98.44 308	96.40 164	92.76 308	97.01 284

XVG-OURS-SEG-HR		96.51 158	96.34 153	97.02 219	98.77 148	93.76 267	97.79 307	98.50 186	95.45 150	96.94 185	99.09 105	87.87 246	99.55 167	96.76 155	95.83 263	97.74 262

PS-MVSNAJss		96.43 160	96.26 157	96.92 229	95.84 370	95.08 210	99.16 50	98.50 186	95.87 130	93.84 297	98.34 196	94.51 87	98.61 291	96.88 144	93.45 297	97.06 282

test_fmvs1		96.42 161	96.67 142	95.66 312	98.82 145	88.53 386	98.80 144	98.20 243	96.39 109	99.64 26	99.20 79	80.35 353	99.67 138	99.04 29	99.57 92	98.78 205

FC-MVSNet-test		96.42 161	96.05 163	97.53 189	96.95 315	97.27 96	99.36 13	99.23 23	95.83 132	93.93 291	98.37 190	92.00 138	98.32 328	96.02 177	92.72 309	97.00 285

ab-mvs		96.42 161	95.71 179	98.55 96	98.63 167	96.75 124	97.88 295	98.74 120	93.84 237	96.54 208	98.18 212	85.34 292	99.75 121	95.93 179	96.35 241	99.15 162

FA-MVS(test-final)		96.41 164	95.94 168	97.82 162	98.21 208	95.20 204	97.80 305	97.58 307	93.21 275	97.36 169	97.70 253	89.47 197	99.56 160	94.12 244	97.99 190	98.71 213

PVSNet	91.96 18	96.35 165	96.15 160	96.96 224	99.17 101	92.05 315	96.08 393	98.68 136	93.69 251	97.75 148	97.80 247	88.86 219	99.69 136	94.26 240	99.01 142	99.15 162

Test_1112_low_res		96.34 166	95.66 184	98.36 118	98.56 171	95.94 167	97.71 312	98.07 274	92.10 319	94.79 253	97.29 290	91.75 145	99.56 160	94.17 242	96.50 238	99.58 90

Effi-MVS+-dtu		96.29 167	96.56 145	95.51 317	97.89 245	90.22 352	98.80 144	98.10 267	96.57 102	96.45 213	96.66 346	90.81 171	98.91 259	95.72 188	97.99 190	97.40 273

QAPM		96.29 167	95.40 189	98.96 68	97.85 246	97.60 78	99.23 32	98.93 58	89.76 373	93.11 328	99.02 112	89.11 210	99.93 31	91.99 306	99.62 83	99.34 125

Fast-Effi-MVS+		96.28 169	95.70 181	98.03 147	98.29 202	95.97 164	98.58 196	98.25 238	91.74 327	95.29 242	97.23 295	91.03 169	99.15 219	92.90 281	97.96 192	98.97 187

nrg030		96.28 169	95.72 176	97.96 153	96.90 320	98.15 58	99.39 10	98.31 224	95.47 149	94.42 267	98.35 192	92.09 136	98.69 283	97.50 119	89.05 358	97.04 283

1314		96.25 171	95.73 175	97.79 164	97.13 306	95.55 185	98.19 251	98.59 159	93.47 264	92.03 356	97.82 245	91.33 159	99.49 178	94.62 225	98.44 174	98.32 245

sd_testset		96.17 172	95.76 174	97.42 194	99.30 73	94.34 250	98.82 135	99.08 39	95.92 126	95.96 229	98.76 153	82.83 332	99.32 200	95.56 194	95.59 264	98.60 226

h-mvs33		96.17 172	95.62 185	97.81 163	99.03 119	94.45 243	98.64 187	98.75 118	97.48 45	98.67 89	98.72 156	89.76 189	99.86 74	97.95 81	81.59 404	99.11 169

HQP_MVS		96.14 174	95.90 170	96.85 232	97.42 284	94.60 239	98.80 144	98.56 169	97.28 58	95.34 238	98.28 201	87.09 259	99.03 239	96.07 172	94.27 272	96.92 291

tttt0517		96.07 175	95.51 187	97.78 165	98.41 183	94.84 224	99.28 24	94.33 412	94.26 216	97.64 161	98.64 163	84.05 321	99.47 185	95.34 200	97.60 206	99.03 181

MVSTER		96.06 176	95.72 176	97.08 216	98.23 206	95.93 170	98.73 164	98.27 233	94.86 188	95.07 244	98.09 217	88.21 234	98.54 297	96.59 157	93.46 295	96.79 310

thisisatest0530		96.01 177	95.36 194	97.97 151	98.38 185	95.52 187	98.88 116	94.19 414	94.04 222	97.64 161	98.31 199	83.82 328	99.46 186	95.29 204	97.70 203	98.93 192

test_djsdf		96.00 178	95.69 182	96.93 226	95.72 372	95.49 188	99.47 7	98.40 206	94.98 180	94.58 257	97.86 238	89.16 208	98.41 317	96.91 138	94.12 280	96.88 300

EI-MVSNet		95.96 179	95.83 172	96.36 279	97.93 241	93.70 273	98.12 261	98.27 233	93.70 250	95.07 244	99.02 112	92.23 130	98.54 297	94.68 221	93.46 295	96.84 306

ECVR-MVS		95.95 180	95.71 179	96.65 244	99.02 120	90.86 337	99.03 76	91.80 425	96.96 80	98.10 120	99.26 68	81.31 339	99.51 174	96.90 141	99.04 139	99.59 86

BH-untuned		95.95 180	95.72 176	96.65 244	98.55 173	92.26 309	98.23 244	97.79 295	93.73 245	94.62 256	98.01 224	88.97 217	99.00 245	93.04 276	98.51 170	98.68 217

test1111		95.94 182	95.78 173	96.41 276	98.99 126	90.12 353	99.04 73	92.45 424	96.99 79	98.03 127	99.27 67	81.40 338	99.48 183	96.87 147	99.04 139	99.63 80

MSDG		95.93 183	95.30 201	97.83 160	98.90 134	95.36 194	96.83 380	98.37 214	91.32 342	94.43 266	98.73 155	90.27 183	99.60 153	90.05 343	98.82 155	98.52 233

BH-RMVSNet		95.92 184	95.32 199	97.69 176	98.32 199	94.64 233	98.19 251	97.45 328	94.56 203	96.03 225	98.61 164	85.02 297	99.12 225	90.68 334	99.06 138	99.30 134

test_fmvs1_n		95.90 185	95.99 167	95.63 313	98.67 161	88.32 390	99.26 27	98.22 240	96.40 108	99.67 23	99.26 68	73.91 402	99.70 131	99.02 30	99.50 107	98.87 196

Fast-Effi-MVS+-dtu		95.87 186	95.85 171	95.91 300	97.74 255	91.74 321	98.69 175	98.15 257	95.56 145	94.92 247	97.68 258	88.98 216	98.79 277	93.19 271	97.78 199	97.20 280

LFMVS		95.86 187	94.98 216	98.47 107	98.87 139	96.32 148	98.84 131	96.02 391	93.40 267	98.62 95	99.20 79	74.99 396	99.63 147	97.72 97	97.20 213	99.46 111

baseline1		95.84 188	95.12 209	98.01 149	98.49 179	95.98 159	98.73 164	97.03 360	95.37 157	96.22 218	98.19 211	89.96 187	99.16 216	94.60 226	87.48 374	98.90 195

OpenMVS	93.04 13	95.83 189	95.00 214	98.32 120	97.18 303	97.32 92	99.21 39	98.97 50	89.96 369	91.14 365	99.05 110	86.64 267	99.92 38	93.38 265	99.47 112	97.73 263

VDD-MVS		95.82 190	95.23 203	97.61 185	98.84 144	93.98 261	98.68 177	97.40 332	95.02 178	97.95 135	99.34 59	74.37 401	99.78 113	98.64 41	96.80 226	99.08 175

UniMVSNet (Re)		95.78 191	95.19 205	97.58 186	96.99 313	97.47 85	98.79 152	99.18 31	95.60 143	93.92 292	97.04 317	91.68 147	98.48 301	95.80 185	87.66 373	96.79 310

VPA-MVSNet		95.75 192	95.11 210	97.69 176	97.24 295	97.27 96	98.94 98	99.23 23	95.13 169	95.51 236	97.32 288	85.73 284	98.91 259	97.33 126	89.55 349	96.89 299

HQP-MVS		95.72 193	95.40 189	96.69 242	97.20 299	94.25 255	98.05 270	98.46 194	96.43 105	94.45 262	97.73 250	86.75 265	98.96 250	95.30 202	94.18 276	96.86 305

hse-mvs2		95.71 194	95.30 201	96.93 226	98.50 176	93.53 278	98.36 226	98.10 267	97.48 45	98.67 89	97.99 226	89.76 189	99.02 242	97.95 81	80.91 409	98.22 248

UniMVSNet_NR-MVSNet		95.71 194	95.15 206	97.40 197	96.84 323	96.97 113	98.74 160	99.24 18	95.16 168	93.88 294	97.72 252	91.68 147	98.31 330	95.81 183	87.25 379	96.92 291

PatchmatchNet		95.71 194	95.52 186	96.29 285	97.58 268	90.72 341	96.84 379	97.52 318	94.06 221	97.08 178	96.96 327	89.24 206	98.90 262	92.03 305	98.37 178	99.26 142
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
OPM-MVS		95.69 197	95.33 198	96.76 237	96.16 358	94.63 234	98.43 222	98.39 208	96.64 98	95.02 246	98.78 146	85.15 296	99.05 235	95.21 209	94.20 275	96.60 333
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMM	93.85 9	95.69 197	95.38 193	96.61 252	97.61 265	93.84 265	98.91 105	98.44 198	95.25 164	94.28 274	98.47 180	86.04 281	99.12 225	95.50 197	93.95 285	96.87 303
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpmrst		95.63 199	95.69 182	95.44 321	97.54 273	88.54 385	96.97 365	97.56 310	93.50 262	97.52 167	96.93 331	89.49 195	99.16 216	95.25 206	96.42 240	98.64 223

FE-MVS		95.62 200	94.90 220	97.78 165	98.37 187	94.92 221	97.17 355	97.38 334	90.95 353	97.73 151	97.70 253	85.32 294	99.63 147	91.18 321	98.33 181	98.79 202

LPG-MVS_test		95.62 200	95.34 195	96.47 270	97.46 279	93.54 276	98.99 86	98.54 173	94.67 197	94.36 270	98.77 148	85.39 289	99.11 227	95.71 189	94.15 278	96.76 313

CLD-MVS		95.62 200	95.34 195	96.46 273	97.52 276	93.75 269	97.27 346	98.46 194	95.53 146	94.42 267	98.00 225	86.21 276	98.97 246	96.25 170	94.37 270	96.66 328
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		95.61 203	94.89 221	97.76 169	98.15 219	95.15 207	96.77 381	94.41 410	92.95 288	97.18 175	97.43 279	84.78 303	99.45 187	94.63 223	97.73 202	98.68 217

MonoMVSNet		95.51 204	95.45 188	95.68 310	95.54 377	90.87 336	98.92 103	97.37 335	95.79 134	95.53 235	97.38 284	89.58 194	97.68 373	96.40 164	92.59 310	98.49 235

thres600view7		95.49 205	94.77 224	97.67 179	98.98 127	95.02 212	98.85 127	96.90 369	95.38 155	96.63 200	96.90 333	84.29 313	99.59 154	88.65 365	96.33 242	98.40 239

test_vis1_n		95.47 206	95.13 207	96.49 267	97.77 251	90.41 349	99.27 26	98.11 264	96.58 100	99.66 24	99.18 85	67.00 415	99.62 151	99.21 25	99.40 122	99.44 114

SCA		95.46 207	95.13 207	96.46 273	97.67 260	91.29 329	97.33 341	97.60 306	94.68 196	96.92 188	97.10 302	83.97 323	98.89 263	92.59 289	98.32 183	99.20 151

IterMVS-LS		95.46 207	95.21 204	96.22 287	98.12 220	93.72 272	98.32 233	98.13 260	93.71 248	94.26 275	97.31 289	92.24 129	98.10 346	94.63 223	90.12 340	96.84 306
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing3-2		95.45 209	95.34 195	95.77 308	98.69 158	88.75 381	98.87 119	97.21 347	96.13 119	97.22 173	97.68 258	77.95 373	99.65 141	97.58 110	96.77 229	98.91 194

jajsoiax		95.45 209	95.03 213	96.73 238	95.42 385	94.63 234	99.14 54	98.52 178	95.74 136	93.22 321	98.36 191	83.87 326	98.65 288	96.95 137	94.04 281	96.91 296

CVMVSNet		95.43 211	96.04 164	93.57 371	97.93 241	83.62 409	98.12 261	98.59 159	95.68 140	96.56 204	99.02 112	87.51 252	97.51 381	93.56 263	97.44 209	99.60 84

anonymousdsp		95.42 212	94.91 219	96.94 225	95.10 389	95.90 173	99.14 54	98.41 204	93.75 242	93.16 324	97.46 275	87.50 254	98.41 317	95.63 193	94.03 282	96.50 352

DU-MVS		95.42 212	94.76 225	97.40 197	96.53 340	96.97 113	98.66 183	98.99 49	95.43 151	93.88 294	97.69 255	88.57 225	98.31 330	95.81 183	87.25 379	96.92 291

mvs_tets		95.41 214	95.00 214	96.65 244	95.58 376	94.42 245	99.00 83	98.55 171	95.73 138	93.21 322	98.38 189	83.45 330	98.63 289	97.09 131	94.00 283	96.91 296

thres100view900		95.38 215	94.70 229	97.41 195	98.98 127	94.92 221	98.87 119	96.90 369	95.38 155	96.61 202	96.88 334	84.29 313	99.56 160	88.11 368	96.29 246	97.76 260

thres400		95.38 215	94.62 233	97.65 183	98.94 132	94.98 217	98.68 177	96.93 367	95.33 158	96.55 206	96.53 352	84.23 317	99.56 160	88.11 368	96.29 246	98.40 239

BH-w/o		95.38 215	95.08 211	96.26 286	98.34 193	91.79 318	97.70 313	97.43 330	92.87 291	94.24 277	97.22 296	88.66 223	98.84 269	91.55 317	97.70 203	98.16 251

VDDNet		95.36 218	94.53 238	97.86 158	98.10 222	95.13 208	98.85 127	97.75 297	90.46 360	98.36 110	99.39 43	73.27 404	99.64 144	97.98 80	96.58 234	98.81 201

TAPA-MVS	93.98 7	95.35 219	94.56 237	97.74 171	99.13 109	94.83 226	98.33 229	98.64 149	86.62 395	96.29 217	98.61 164	94.00 101	99.29 203	80.00 410	99.41 119	99.09 171
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ACMP	93.49 10	95.34 220	94.98 216	96.43 275	97.67 260	93.48 280	98.73 164	98.44 198	94.94 186	92.53 344	98.53 174	84.50 312	99.14 221	95.48 198	94.00 283	96.66 328
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
COLMAP_ROB	93.27 12	95.33 221	94.87 222	96.71 239	99.29 78	93.24 294	98.58 196	98.11 264	89.92 370	93.57 306	99.10 98	86.37 274	99.79 110	90.78 332	98.10 188	97.09 281
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
UBG		95.32 222	94.72 228	97.13 211	98.05 228	93.26 291	97.87 296	97.20 348	94.96 182	96.18 221	95.66 384	80.97 345	99.35 196	94.47 232	97.08 216	98.78 205

tfpn200view9		95.32 222	94.62 233	97.43 193	98.94 132	94.98 217	98.68 177	96.93 367	95.33 158	96.55 206	96.53 352	84.23 317	99.56 160	88.11 368	96.29 246	97.76 260

Anonymous202405211		95.28 224	94.49 240	97.67 179	99.00 123	93.75 269	98.70 173	97.04 359	90.66 356	96.49 210	98.80 144	78.13 369	99.83 81	96.21 171	95.36 268	99.44 114

thres200		95.25 225	94.57 236	97.28 201	98.81 146	94.92 221	98.20 248	97.11 352	95.24 166	96.54 208	96.22 363	84.58 310	99.53 170	87.93 373	96.50 238	97.39 274

AllTest		95.24 226	94.65 232	96.99 220	99.25 86	93.21 295	98.59 194	98.18 248	91.36 338	93.52 308	98.77 148	84.67 307	99.72 125	89.70 350	97.87 195	98.02 255

LCM-MVSNet-Re		95.22 227	95.32 199	94.91 338	98.18 214	87.85 396	98.75 156	95.66 398	95.11 171	88.96 384	96.85 337	90.26 184	97.65 374	95.65 192	98.44 174	99.22 148

EPNet_dtu		95.21 228	94.95 218	95.99 295	96.17 356	90.45 347	98.16 257	97.27 343	96.77 88	93.14 327	98.33 197	90.34 180	98.42 310	85.57 386	98.81 156	99.09 171
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
XXY-MVS		95.20 229	94.45 245	97.46 190	96.75 330	96.56 135	98.86 123	98.65 148	93.30 272	93.27 320	98.27 204	84.85 301	98.87 266	94.82 218	91.26 326	96.96 287

D2MVS		95.18 230	95.08 211	95.48 318	97.10 308	92.07 314	98.30 236	99.13 37	94.02 224	92.90 332	96.73 343	89.48 196	98.73 281	94.48 231	93.60 294	95.65 380

WR-MVS		95.15 231	94.46 243	97.22 203	96.67 335	96.45 139	98.21 246	98.81 98	94.15 218	93.16 324	97.69 255	87.51 252	98.30 332	95.29 204	88.62 364	96.90 298

TranMVSNet+NR-MVSNet		95.14 232	94.48 241	97.11 214	96.45 346	96.36 146	99.03 76	99.03 44	95.04 176	93.58 305	97.93 231	88.27 233	98.03 352	94.13 243	86.90 384	96.95 289

myMVS_eth3d28		95.12 233	94.62 233	96.64 248	98.17 217	92.17 310	98.02 274	97.32 337	95.41 153	96.22 218	96.05 369	78.01 371	99.13 222	95.22 208	97.16 214	98.60 226

baseline2		95.11 234	94.52 239	96.87 231	96.65 336	93.56 275	98.27 241	94.10 416	93.45 265	92.02 357	97.43 279	87.45 256	99.19 214	93.88 252	97.41 211	97.87 258

miper_enhance_ethall		95.10 235	94.75 226	96.12 291	97.53 275	93.73 271	96.61 387	98.08 272	92.20 318	93.89 293	96.65 348	92.44 120	98.30 332	94.21 241	91.16 327	96.34 361

Anonymous20240529		95.10 235	94.22 255	97.75 170	99.01 122	94.26 254	98.87 119	98.83 89	85.79 403	96.64 199	98.97 119	78.73 362	99.85 75	96.27 167	94.89 269	99.12 166

test-LLR		95.10 235	94.87 222	95.80 305	96.77 327	89.70 361	96.91 370	95.21 402	95.11 171	94.83 251	95.72 381	87.71 248	98.97 246	93.06 274	98.50 171	98.72 210

WR-MVS_H		95.05 238	94.46 243	96.81 235	96.86 322	95.82 176	99.24 30	99.24 18	93.87 236	92.53 344	96.84 338	90.37 179	98.24 338	93.24 269	87.93 370	96.38 360

miper_ehance_all_eth		95.01 239	94.69 230	95.97 297	97.70 258	93.31 289	97.02 363	98.07 274	92.23 315	93.51 310	96.96 327	91.85 143	98.15 342	93.68 257	91.16 327	96.44 358

testing11		95.00 240	94.28 252	97.16 209	97.96 238	93.36 288	98.09 266	97.06 358	94.94 186	95.33 241	96.15 365	76.89 386	99.40 191	95.77 187	96.30 245	98.72 210

ADS-MVSNet		95.00 240	94.45 245	96.63 249	98.00 232	91.91 317	96.04 394	97.74 298	90.15 366	96.47 211	96.64 349	87.89 244	98.96 250	90.08 341	97.06 217	99.02 182

VPNet		94.99 242	94.19 257	97.40 197	97.16 304	96.57 134	98.71 169	98.97 50	95.67 141	94.84 249	98.24 208	80.36 352	98.67 287	96.46 161	87.32 378	96.96 287

EPMVS		94.99 242	94.48 241	96.52 265	97.22 297	91.75 320	97.23 347	91.66 426	94.11 219	97.28 170	96.81 340	85.70 285	98.84 269	93.04 276	97.28 212	98.97 187

testing91		94.98 244	94.25 254	97.20 204	97.94 239	93.41 283	98.00 277	97.58 307	94.99 179	95.45 237	96.04 370	77.20 381	99.42 190	94.97 214	96.02 259	98.78 205

NR-MVSNet		94.98 244	94.16 260	97.44 192	96.53 340	97.22 104	98.74 160	98.95 54	94.96 182	89.25 383	97.69 255	89.32 203	98.18 340	94.59 228	87.40 376	96.92 291

FMVSNet3		94.97 246	94.26 253	97.11 214	98.18 214	96.62 128	98.56 204	98.26 237	93.67 255	94.09 284	97.10 302	84.25 315	98.01 353	92.08 301	92.14 313	96.70 322

CostFormer		94.95 247	94.73 227	95.60 315	97.28 293	89.06 374	97.53 325	96.89 371	89.66 375	96.82 193	96.72 344	86.05 279	98.95 255	95.53 196	96.13 257	98.79 202

PAPM		94.95 247	94.00 273	97.78 165	97.04 310	95.65 180	96.03 396	98.25 238	91.23 347	94.19 280	97.80 247	91.27 162	98.86 268	82.61 403	97.61 205	98.84 199

CP-MVSNet		94.94 249	94.30 251	96.83 233	96.72 332	95.56 183	99.11 60	98.95 54	93.89 234	92.42 349	97.90 234	87.19 258	98.12 345	94.32 237	88.21 367	96.82 309

TR-MVS		94.94 249	94.20 256	97.17 208	97.75 252	94.14 258	97.59 322	97.02 362	92.28 314	95.75 233	97.64 263	83.88 325	98.96 250	89.77 347	96.15 256	98.40 239

RPSCF		94.87 251	95.40 189	93.26 377	98.89 135	82.06 415	98.33 229	98.06 279	90.30 365	96.56 204	99.26 68	87.09 259	99.49 178	93.82 254	96.32 243	98.24 246

testing99		94.83 252	94.08 265	97.07 217	97.94 239	93.13 297	98.10 265	97.17 350	94.86 188	95.34 238	96.00 373	76.31 389	99.40 191	95.08 211	95.90 260	98.68 217

GA-MVS		94.81 253	94.03 269	97.14 210	97.15 305	93.86 264	96.76 382	97.58 307	94.00 228	94.76 255	97.04 317	80.91 346	98.48 301	91.79 311	96.25 252	99.09 171

c3_l		94.79 254	94.43 247	95.89 302	97.75 252	93.12 299	97.16 357	98.03 281	92.23 315	93.46 314	97.05 316	91.39 156	98.01 353	93.58 262	89.21 356	96.53 344

V42		94.78 255	94.14 262	96.70 241	96.33 351	95.22 203	98.97 89	98.09 271	92.32 312	94.31 273	97.06 313	88.39 231	98.55 296	92.90 281	88.87 362	96.34 361

reproduce_monomvs		94.77 256	94.67 231	95.08 333	98.40 184	89.48 367	98.80 144	98.64 149	97.57 39	93.21 322	97.65 260	80.57 351	98.83 272	97.72 97	89.47 352	96.93 290

CR-MVSNet		94.76 257	94.15 261	96.59 255	97.00 311	93.43 281	94.96 407	97.56 310	92.46 303	96.93 186	96.24 359	88.15 236	97.88 366	87.38 375	96.65 232	98.46 237

v2v482		94.69 258	94.03 269	96.65 244	96.17 356	94.79 229	98.67 181	98.08 272	92.72 295	94.00 289	97.16 299	87.69 251	98.45 306	92.91 280	88.87 362	96.72 318

pmmvs4		94.69 258	93.99 275	96.81 235	95.74 371	95.94 167	97.40 332	97.67 301	90.42 362	93.37 317	97.59 267	89.08 211	98.20 339	92.97 278	91.67 320	96.30 364

cl22		94.68 260	94.19 257	96.13 290	98.11 221	93.60 274	96.94 367	98.31 224	92.43 307	93.32 319	96.87 336	86.51 268	98.28 336	94.10 246	91.16 327	96.51 350

eth_miper_zixun_eth		94.68 260	94.41 248	95.47 319	97.64 263	91.71 322	96.73 384	98.07 274	92.71 296	93.64 303	97.21 297	90.54 177	98.17 341	93.38 265	89.76 344	96.54 342

PCF-MVS	93.45 11	94.68 260	93.43 311	98.42 115	98.62 168	96.77 123	95.48 404	98.20 243	84.63 408	93.34 318	98.32 198	88.55 228	99.81 93	84.80 395	98.96 145	98.68 217
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS		94.67 263	93.54 306	98.08 144	96.88 321	96.56 135	98.19 251	98.50 186	78.05 419	92.69 339	98.02 222	91.07 168	99.63 147	90.09 340	98.36 180	98.04 254

PS-CasMVS		94.67 263	93.99 275	96.71 239	96.68 334	95.26 200	99.13 57	99.03 44	93.68 253	92.33 350	97.95 230	85.35 291	98.10 346	93.59 261	88.16 369	96.79 310

cascas		94.63 265	93.86 285	96.93 226	96.91 319	94.27 253	96.00 397	98.51 181	85.55 404	94.54 258	96.23 361	84.20 319	98.87 266	95.80 185	96.98 222	97.66 266

tpmvs		94.60 266	94.36 250	95.33 325	97.46 279	88.60 384	96.88 376	97.68 299	91.29 344	93.80 299	96.42 356	88.58 224	99.24 208	91.06 327	96.04 258	98.17 250

LTVRE_ROB	92.95 15	94.60 266	93.90 281	96.68 243	97.41 287	94.42 245	98.52 207	98.59 159	91.69 330	91.21 364	98.35 192	84.87 300	99.04 238	91.06 327	93.44 298	96.60 333
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		94.59 268	93.92 278	96.60 254	96.21 353	94.78 230	98.59 194	98.14 259	91.86 326	94.21 279	97.02 320	87.97 242	98.41 317	91.72 313	89.57 347	96.61 332

ADS-MVSNet2		94.58 269	94.40 249	95.11 331	98.00 232	88.74 382	96.04 394	97.30 339	90.15 366	96.47 211	96.64 349	87.89 244	97.56 379	90.08 341	97.06 217	99.02 182

WBMVS		94.56 270	94.04 267	96.10 292	98.03 230	93.08 301	97.82 304	98.18 248	94.02 224	93.77 301	96.82 339	81.28 340	98.34 325	95.47 199	91.00 330	96.88 300

ACMH	92.88 16	94.55 271	93.95 277	96.34 281	97.63 264	93.26 291	98.81 143	98.49 191	93.43 266	89.74 378	98.53 174	81.91 335	99.08 233	93.69 256	93.30 301	96.70 322
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		94.54 272	93.85 286	96.63 249	97.98 236	93.06 302	98.77 155	97.84 293	93.67 255	93.80 299	98.04 221	76.88 387	98.96 250	94.79 220	92.86 306	97.86 259

XVG-ACMP-BASELINE		94.54 272	94.14 262	95.75 309	96.55 339	91.65 323	98.11 263	98.44 198	94.96 182	94.22 278	97.90 234	79.18 361	99.11 227	94.05 248	93.85 287	96.48 355

AUN-MVS		94.53 274	93.73 296	96.92 229	98.50 176	93.52 279	98.34 228	98.10 267	93.83 239	95.94 231	97.98 228	85.59 287	99.03 239	94.35 235	80.94 408	98.22 248

DIV-MVS_self_test		94.52 275	94.03 269	95.99 295	97.57 272	93.38 286	97.05 361	97.94 287	91.74 327	92.81 334	97.10 302	89.12 209	98.07 350	92.60 287	90.30 337	96.53 344

cl____		94.51 276	94.01 272	96.02 294	97.58 268	93.40 285	97.05 361	97.96 286	91.73 329	92.76 336	97.08 308	89.06 212	98.13 344	92.61 286	90.29 338	96.52 347

ETVMVS		94.50 277	93.44 310	97.68 178	98.18 214	95.35 196	98.19 251	97.11 352	93.73 245	96.40 214	95.39 387	74.53 398	98.84 269	91.10 323	96.31 244	98.84 199

GBi-Net		94.49 278	93.80 289	96.56 259	98.21 208	95.00 213	98.82 135	98.18 248	92.46 303	94.09 284	97.07 309	81.16 341	97.95 358	92.08 301	92.14 313	96.72 318

test1		94.49 278	93.80 289	96.56 259	98.21 208	95.00 213	98.82 135	98.18 248	92.46 303	94.09 284	97.07 309	81.16 341	97.95 358	92.08 301	92.14 313	96.72 318

dmvs_re		94.48 280	94.18 259	95.37 323	97.68 259	90.11 354	98.54 206	97.08 354	94.56 203	94.42 267	97.24 294	84.25 315	97.76 371	91.02 330	92.83 307	98.24 246

v8		94.47 281	93.77 292	96.57 258	96.36 349	94.83 226	99.05 69	98.19 245	91.92 323	93.16 324	96.97 325	88.82 222	98.48 301	91.69 314	87.79 371	96.39 359

FMVSNet2		94.47 281	93.61 302	97.04 218	98.21 208	96.43 141	98.79 152	98.27 233	92.46 303	93.50 311	97.09 306	81.16 341	98.00 355	91.09 324	91.93 316	96.70 322

test2506		94.44 283	93.91 280	96.04 293	99.02 120	88.99 377	99.06 67	79.47 438	96.96 80	98.36 110	99.26 68	77.21 380	99.52 173	96.78 154	99.04 139	99.59 86

Patchmatch-test		94.42 284	93.68 300	96.63 249	97.60 266	91.76 319	94.83 411	97.49 322	89.45 379	94.14 282	97.10 302	88.99 213	98.83 272	85.37 389	98.13 187	99.29 136

PEN-MVS		94.42 284	93.73 296	96.49 267	96.28 352	94.84 224	99.17 49	99.00 46	93.51 261	92.23 352	97.83 244	86.10 278	97.90 362	92.55 292	86.92 383	96.74 315

v144192		94.39 286	93.70 298	96.48 269	96.06 361	94.35 249	98.58 196	98.16 256	91.45 335	94.33 272	97.02 320	87.50 254	98.45 306	91.08 326	89.11 357	96.63 330

Baseline_NR-MVSNet		94.35 287	93.81 288	95.96 298	96.20 354	94.05 260	98.61 193	96.67 381	91.44 336	93.85 296	97.60 266	88.57 225	98.14 343	94.39 233	86.93 382	95.68 379

miper_lstm_enhance		94.33 288	94.07 266	95.11 331	97.75 252	90.97 333	97.22 348	98.03 281	91.67 331	92.76 336	96.97 325	90.03 186	97.78 370	92.51 294	89.64 346	96.56 339

v1192		94.32 289	93.58 303	96.53 264	96.10 359	94.45 243	98.50 213	98.17 254	91.54 333	94.19 280	97.06 313	86.95 263	98.43 309	90.14 339	89.57 347	96.70 322

UWE-MVS		94.30 290	93.89 283	95.53 316	97.83 247	88.95 378	97.52 327	93.25 418	94.44 211	96.63 200	97.07 309	78.70 363	99.28 204	91.99 306	97.56 208	98.36 242

ACMH+	92.99 14	94.30 290	93.77 292	95.88 303	97.81 249	92.04 316	98.71 169	98.37 214	93.99 229	90.60 371	98.47 180	80.86 348	99.05 235	92.75 285	92.40 312	96.55 341

v148		94.29 292	93.76 294	95.91 300	96.10 359	92.93 303	98.58 196	97.97 284	92.59 301	93.47 313	96.95 329	88.53 229	98.32 328	92.56 291	87.06 381	96.49 353

v10		94.29 292	93.55 305	96.51 266	96.39 348	94.80 228	98.99 86	98.19 245	91.35 340	93.02 330	96.99 323	88.09 238	98.41 317	90.50 336	88.41 366	96.33 363

MVP-Stereo		94.28 294	93.92 278	95.35 324	94.95 391	92.60 306	97.97 280	97.65 302	91.61 332	90.68 370	97.09 306	86.32 275	98.42 310	89.70 350	99.34 128	95.02 393
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UniMVSNet_ETH3D		94.24 295	93.33 313	96.97 223	97.19 302	93.38 286	98.74 160	98.57 166	91.21 349	93.81 298	98.58 169	72.85 405	98.77 279	95.05 212	93.93 286	98.77 208

OurMVSNet-221017-0		94.21 296	94.00 273	94.85 342	95.60 375	89.22 372	98.89 110	97.43 330	95.29 161	92.18 353	98.52 177	82.86 331	98.59 294	93.46 264	91.76 318	96.74 315

v1921920		94.20 297	93.47 309	96.40 278	95.98 364	94.08 259	98.52 207	98.15 257	91.33 341	94.25 276	97.20 298	86.41 273	98.42 310	90.04 344	89.39 354	96.69 327

WB-MVSnew		94.19 298	94.04 267	94.66 349	96.82 325	92.14 311	97.86 298	95.96 394	93.50 262	95.64 234	96.77 342	88.06 240	97.99 356	84.87 392	96.86 223	93.85 410

v7n		94.19 298	93.43 311	96.47 270	95.90 367	94.38 248	99.26 27	98.34 220	91.99 321	92.76 336	97.13 301	88.31 232	98.52 299	89.48 355	87.70 372	96.52 347

tpm2		94.19 298	93.76 294	95.46 320	97.23 296	89.04 375	97.31 343	96.85 375	87.08 394	96.21 220	96.79 341	83.75 329	98.74 280	92.43 297	96.23 254	98.59 229

TESTMET0.1,1		94.18 301	93.69 299	95.63 313	96.92 317	89.12 373	96.91 370	94.78 407	93.17 277	94.88 248	96.45 355	78.52 364	98.92 257	93.09 273	98.50 171	98.85 197

dp		94.15 302	93.90 281	94.90 339	97.31 292	86.82 401	96.97 365	97.19 349	91.22 348	96.02 226	96.61 351	85.51 288	99.02 242	90.00 345	94.30 271	98.85 197

ET-MVSNet_ETH3D		94.13 303	92.98 321	97.58 186	98.22 207	96.20 152	97.31 343	95.37 401	94.53 205	79.56 419	97.63 265	86.51 268	97.53 380	96.91 138	90.74 332	99.02 182

tpm		94.13 303	93.80 289	95.12 330	96.50 342	87.91 395	97.44 329	95.89 397	92.62 299	96.37 216	96.30 358	84.13 320	98.30 332	93.24 269	91.66 321	99.14 164

testing222		94.12 305	93.03 320	97.37 200	98.02 231	94.66 231	97.94 284	96.65 383	94.63 199	95.78 232	95.76 376	71.49 406	98.92 257	91.17 322	95.88 261	98.52 233

IterMVS-SCA-FT		94.11 306	93.87 284	94.85 342	97.98 236	90.56 346	97.18 353	98.11 264	93.75 242	92.58 342	97.48 274	83.97 323	97.41 383	92.48 296	91.30 324	96.58 335

Anonymous20231211		94.10 307	93.26 316	96.61 252	99.11 112	94.28 252	99.01 81	98.88 70	86.43 397	92.81 334	97.57 269	81.66 337	98.68 286	94.83 217	89.02 360	96.88 300

IterMVS		94.09 308	93.85 286	94.80 345	97.99 234	90.35 350	97.18 353	98.12 261	93.68 253	92.46 348	97.34 285	84.05 321	97.41 383	92.51 294	91.33 323	96.62 331
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test-mter		94.08 309	93.51 307	95.80 305	96.77 327	89.70 361	96.91 370	95.21 402	92.89 290	94.83 251	95.72 381	77.69 375	98.97 246	93.06 274	98.50 171	98.72 210

test0.0.03 1		94.08 309	93.51 307	95.80 305	95.53 379	92.89 304	97.38 334	95.97 393	95.11 171	92.51 346	96.66 346	87.71 248	96.94 390	87.03 377	93.67 290	97.57 270

v1240		94.06 311	93.29 315	96.34 281	96.03 363	93.90 263	98.44 220	98.17 254	91.18 350	94.13 283	97.01 322	86.05 279	98.42 310	89.13 360	89.50 351	96.70 322

X-MVStestdata		94.06 311	92.30 337	99.34 26	99.70 22	98.35 44	99.29 22	98.88 70	97.40 49	98.46 102	43.50 433	95.90 45	99.89 59	97.85 89	99.74 52	99.78 26

DTE-MVSNet		93.98 313	93.26 316	96.14 289	96.06 361	94.39 247	99.20 42	98.86 83	93.06 283	91.78 358	97.81 246	85.87 283	97.58 378	90.53 335	86.17 388	96.46 357

pm-mvs1		93.94 314	93.06 319	96.59 255	96.49 343	95.16 205	98.95 95	98.03 281	92.32 312	91.08 366	97.84 241	84.54 311	98.41 317	92.16 299	86.13 391	96.19 368

MS-PatchMatch		93.84 315	93.63 301	94.46 359	96.18 355	89.45 368	97.76 308	98.27 233	92.23 315	92.13 354	97.49 273	79.50 358	98.69 283	89.75 348	99.38 124	95.25 385

tfpnnormal		93.66 316	92.70 327	96.55 263	96.94 316	95.94 167	98.97 89	99.19 30	91.04 351	91.38 363	97.34 285	84.94 299	98.61 291	85.45 388	89.02 360	95.11 389

EU-MVSNet		93.66 316	94.14 262	92.25 387	95.96 366	83.38 411	98.52 207	98.12 261	94.69 195	92.61 341	98.13 215	87.36 257	96.39 403	91.82 310	90.00 342	96.98 286

our_test_3		93.65 318	93.30 314	94.69 347	95.45 383	89.68 363	96.91 370	97.65 302	91.97 322	91.66 361	96.88 334	89.67 193	97.93 361	88.02 371	91.49 322	96.48 355

pmmvs5		93.65 318	92.97 322	95.68 310	95.49 380	92.37 307	98.20 248	97.28 342	89.66 375	92.58 342	97.26 291	82.14 334	98.09 348	93.18 272	90.95 331	96.58 335

SSC-MVS3.2		93.59 320	93.13 318	94.97 336	96.81 326	89.71 360	97.95 281	98.49 191	94.59 202	93.50 311	96.91 332	77.74 374	98.37 324	91.69 314	90.47 335	96.83 308

test_fmvs2		93.43 321	93.58 303	92.95 381	96.97 314	83.91 407	99.19 44	97.24 345	95.74 136	95.20 243	98.27 204	69.65 408	98.72 282	96.26 168	93.73 289	96.24 365

tpm cat1		93.36 322	92.80 324	95.07 334	97.58 268	87.97 394	96.76 382	97.86 292	82.17 415	93.53 307	96.04 370	86.13 277	99.13 222	89.24 358	95.87 262	98.10 253

JIA-IIPM		93.35 323	92.49 333	95.92 299	96.48 344	90.65 343	95.01 406	96.96 365	85.93 401	96.08 224	87.33 423	87.70 250	98.78 278	91.35 319	95.58 266	98.34 243

SixPastTwentyTwo		93.34 324	92.86 323	94.75 346	95.67 373	89.41 370	98.75 156	96.67 381	93.89 234	90.15 376	98.25 207	80.87 347	98.27 337	90.90 331	90.64 333	96.57 337

USDC		93.33 325	92.71 326	95.21 327	96.83 324	90.83 339	96.91 370	97.50 320	93.84 237	90.72 369	98.14 214	77.69 375	98.82 274	89.51 354	93.21 303	95.97 373

IB-MVS	91.98 17	93.27 326	91.97 341	97.19 206	97.47 278	93.41 283	97.09 360	95.99 392	93.32 270	92.47 347	95.73 379	78.06 370	99.53 170	94.59 228	82.98 399	98.62 224
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		93.26 327	92.21 338	96.41 276	97.73 256	93.13 297	95.65 401	97.03 360	91.27 346	94.04 287	96.06 368	75.33 394	97.19 386	86.56 379	96.23 254	98.92 193

ppachtmachnet_test		93.22 328	92.63 328	94.97 336	95.45 383	90.84 338	96.88 376	97.88 291	90.60 357	92.08 355	97.26 291	88.08 239	97.86 367	85.12 391	90.33 336	96.22 366

Patchmtry		93.22 328	92.35 336	95.84 304	96.77 327	93.09 300	94.66 414	97.56 310	87.37 393	92.90 332	96.24 359	88.15 236	97.90 362	87.37 376	90.10 341	96.53 344

testing3		93.19 330	92.48 334	95.30 326	98.07 223	92.27 308	98.64 187	97.17 350	93.94 233	93.98 290	97.04 317	67.97 412	96.01 407	88.40 366	97.14 215	97.63 267

FMVSNet1		93.19 330	92.07 339	96.56 259	97.54 273	95.00 213	98.82 135	98.18 248	90.38 363	92.27 351	97.07 309	73.68 403	97.95 358	89.36 357	91.30 324	96.72 318

LF4IMVS		93.14 332	92.79 325	94.20 363	95.88 368	88.67 383	97.66 316	97.07 356	93.81 240	91.71 359	97.65 260	77.96 372	98.81 275	91.47 318	91.92 317	95.12 388

mmtdpeth		93.12 333	92.61 329	94.63 351	97.60 266	89.68 363	99.21 39	97.32 337	94.02 224	97.72 152	94.42 398	77.01 385	99.44 188	99.05 28	77.18 420	94.78 398

testgi		93.06 334	92.45 335	94.88 341	96.43 347	89.90 355	98.75 156	97.54 316	95.60 143	91.63 362	97.91 233	74.46 400	97.02 388	86.10 382	93.67 290	97.72 264

PatchT		93.06 334	91.97 341	96.35 280	96.69 333	92.67 305	94.48 417	97.08 354	86.62 395	97.08 178	92.23 417	87.94 243	97.90 362	78.89 414	96.69 230	98.49 235

RPMNet		92.81 336	91.34 347	97.24 202	97.00 311	93.43 281	94.96 407	98.80 105	82.27 414	96.93 186	92.12 418	86.98 262	99.82 88	76.32 419	96.65 232	98.46 237

UWE-MVS-28		92.79 337	92.51 332	93.62 370	96.46 345	86.28 402	97.93 285	92.71 423	94.17 217	94.78 254	97.16 299	81.05 344	96.43 402	81.45 406	96.86 223	98.14 252

myMVS_eth3d		92.73 338	92.01 340	94.89 340	97.39 288	90.94 334	97.91 288	97.46 324	93.16 278	93.42 315	95.37 388	68.09 411	96.12 405	88.34 367	96.99 219	97.60 268

TransMVSNet (Re)		92.67 339	91.51 346	96.15 288	96.58 338	94.65 232	98.90 106	96.73 377	90.86 354	89.46 382	97.86 238	85.62 286	98.09 348	86.45 380	81.12 406	95.71 378

ttmdpeth		92.61 340	91.96 343	94.55 353	94.10 401	90.60 345	98.52 207	97.29 340	92.67 297	90.18 374	97.92 232	79.75 357	97.79 369	91.09 324	86.15 390	95.26 384

Syy-MVS		92.55 341	92.61 329	92.38 384	97.39 288	83.41 410	97.91 288	97.46 324	93.16 278	93.42 315	95.37 388	84.75 304	96.12 405	77.00 418	96.99 219	97.60 268

K. test v3		92.55 341	91.91 344	94.48 357	95.64 374	89.24 371	99.07 66	94.88 406	94.04 222	86.78 398	97.59 267	77.64 378	97.64 375	92.08 301	89.43 353	96.57 337

DSMNet-mixed		92.52 343	92.58 331	92.33 385	94.15 400	82.65 413	98.30 236	94.26 413	89.08 384	92.65 340	95.73 379	85.01 298	95.76 409	86.24 381	97.76 200	98.59 229

TinyColmap		92.31 344	91.53 345	94.65 350	96.92 317	89.75 358	96.92 368	96.68 380	90.45 361	89.62 379	97.85 240	76.06 392	98.81 275	86.74 378	92.51 311	95.41 382

gg-mvs-nofinetune		92.21 345	90.58 353	97.13 211	96.75 330	95.09 209	95.85 398	89.40 431	85.43 405	94.50 260	81.98 426	80.80 349	98.40 323	92.16 299	98.33 181	97.88 257

FMVSNet5		91.81 346	90.92 349	94.49 356	97.21 298	92.09 313	98.00 277	97.55 315	89.31 382	90.86 368	95.61 385	74.48 399	95.32 413	85.57 386	89.70 345	96.07 371

pmmvs6		91.77 347	90.63 352	95.17 329	94.69 397	91.24 330	98.67 181	97.92 289	86.14 399	89.62 379	97.56 271	75.79 393	98.34 325	90.75 333	84.56 393	95.94 374

Anonymous20231206		91.66 348	91.10 348	93.33 375	94.02 405	87.35 398	98.58 196	97.26 344	90.48 359	90.16 375	96.31 357	83.83 327	96.53 400	79.36 412	89.90 343	96.12 369

Patchmatch-RL test		91.49 349	90.85 350	93.41 373	91.37 416	84.40 405	92.81 421	95.93 396	91.87 325	87.25 394	94.87 394	88.99 213	96.53 400	92.54 293	82.00 401	99.30 134

test_0402		91.32 350	90.27 356	94.48 357	96.60 337	91.12 331	98.50 213	97.22 346	86.10 400	88.30 390	96.98 324	77.65 377	97.99 356	78.13 416	92.94 305	94.34 399

test_vis1_rt		91.29 351	90.65 351	93.19 379	97.45 282	86.25 403	98.57 203	90.90 429	93.30 272	86.94 397	93.59 407	62.07 421	99.11 227	97.48 120	95.58 266	94.22 402

PVSNet_0	88.72 19	91.28 352	90.03 359	95.00 335	97.99 234	87.29 399	94.84 410	98.50 186	92.06 320	89.86 377	95.19 390	79.81 356	99.39 194	92.27 298	69.79 426	98.33 244

mvs5depth		91.23 353	90.17 357	94.41 361	92.09 413	89.79 357	95.26 405	96.50 385	90.73 355	91.69 360	97.06 313	76.12 391	98.62 290	88.02 371	84.11 396	94.82 395

Anonymous20240521		91.18 354	90.44 354	93.42 372	93.70 406	88.47 387	98.94 98	97.56 310	88.46 388	89.56 381	95.08 393	77.15 383	96.97 389	83.92 398	89.55 349	94.82 395

EG-PatchMatch MVS		91.13 355	90.12 358	94.17 365	94.73 396	89.00 376	98.13 260	97.81 294	89.22 383	85.32 408	96.46 354	67.71 413	98.42 310	87.89 374	93.82 288	95.08 390

TDRefinement		91.06 356	89.68 361	95.21 327	85.35 431	91.49 326	98.51 212	97.07 356	91.47 334	88.83 388	97.84 241	77.31 379	99.09 232	92.79 284	77.98 418	95.04 392

UnsupCasMVSNet_eth		90.99 357	89.92 360	94.19 364	94.08 402	89.83 356	97.13 359	98.67 141	93.69 251	85.83 404	96.19 364	75.15 395	96.74 394	89.14 359	79.41 413	96.00 372

test20.03		90.89 358	90.38 355	92.43 383	93.48 407	88.14 393	98.33 229	97.56 310	93.40 267	87.96 391	96.71 345	80.69 350	94.13 418	79.15 413	86.17 388	95.01 394

MDA-MVSNet_test_wron		90.71 359	89.38 364	94.68 348	94.83 393	90.78 340	97.19 352	97.46 324	87.60 391	72.41 426	95.72 381	86.51 268	96.71 397	85.92 384	86.80 385	96.56 339

YYNet1		90.70 360	89.39 363	94.62 352	94.79 395	90.65 343	97.20 350	97.46 324	87.54 392	72.54 425	95.74 377	86.51 268	96.66 398	86.00 383	86.76 386	96.54 342

KD-MVS_self_test		90.38 361	89.38 364	93.40 374	92.85 410	88.94 379	97.95 281	97.94 287	90.35 364	90.25 373	93.96 404	79.82 355	95.94 408	84.62 397	76.69 421	95.33 383

pmmvs-eth3d		90.36 362	89.05 367	94.32 362	91.10 418	92.12 312	97.63 321	96.95 366	88.86 386	84.91 409	93.13 412	78.32 366	96.74 394	88.70 363	81.81 403	94.09 405

CL-MVSNet_self_test		90.11 363	89.14 366	93.02 380	91.86 415	88.23 392	96.51 390	98.07 274	90.49 358	90.49 372	94.41 399	84.75 304	95.34 412	80.79 408	74.95 423	95.50 381

new_pmnet		90.06 364	89.00 368	93.22 378	94.18 399	88.32 390	96.42 392	96.89 371	86.19 398	85.67 405	93.62 406	77.18 382	97.10 387	81.61 405	89.29 355	94.23 401

MDA-MVSNet-bldmvs		89.97 365	88.35 371	94.83 344	95.21 387	91.34 327	97.64 318	97.51 319	88.36 389	71.17 427	96.13 366	79.22 360	96.63 399	83.65 399	86.27 387	96.52 347

CMPMVS	66.06 21	89.70 366	89.67 362	89.78 392	93.19 408	76.56 418	97.00 364	98.35 217	80.97 416	81.57 414	97.75 249	74.75 397	98.61 291	89.85 346	93.63 292	94.17 403
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet1		89.67 367	88.28 372	93.82 368	92.81 411	91.08 332	98.01 275	97.45 328	87.95 390	87.90 392	95.87 375	67.63 414	94.56 417	78.73 415	88.18 368	95.83 376

KD-MVS_2432*1600		89.61 368	87.96 376	94.54 354	94.06 403	91.59 324	95.59 402	97.63 304	89.87 371	88.95 385	94.38 401	78.28 367	96.82 392	84.83 393	68.05 427	95.21 386

miper_refine_blended		89.61 368	87.96 376	94.54 354	94.06 403	91.59 324	95.59 402	97.63 304	89.87 371	88.95 385	94.38 401	78.28 367	96.82 392	84.83 393	68.05 427	95.21 386

MVStest1		89.53 370	87.99 375	94.14 367	94.39 398	90.42 348	98.25 243	96.84 376	82.81 411	81.18 416	97.33 287	77.09 384	96.94 390	85.27 390	78.79 414	95.06 391

MVS-HIRNet		89.46 371	88.40 370	92.64 382	97.58 268	82.15 414	94.16 420	93.05 422	75.73 422	90.90 367	82.52 425	79.42 359	98.33 327	83.53 400	98.68 158	97.43 271

OpenMVS_ROB	86.42 20	89.00 372	87.43 380	93.69 369	93.08 409	89.42 369	97.91 288	96.89 371	78.58 418	85.86 403	94.69 395	69.48 409	98.29 335	77.13 417	93.29 302	93.36 412

mvsany_test3		88.80 373	88.04 373	91.09 391	89.78 421	81.57 416	97.83 303	95.49 400	93.81 240	87.53 393	93.95 405	56.14 424	97.43 382	94.68 221	83.13 398	94.26 400

new-patchmatchnet		88.50 374	87.45 379	91.67 389	90.31 420	85.89 404	97.16 357	97.33 336	89.47 378	83.63 411	92.77 414	76.38 388	95.06 415	82.70 402	77.29 419	94.06 407

APD_test1		88.22 375	88.01 374	88.86 394	95.98 364	74.66 426	97.21 349	96.44 387	83.96 410	86.66 400	97.90 234	60.95 422	97.84 368	82.73 401	90.23 339	94.09 405

PM-MVS		87.77 376	86.55 382	91.40 390	91.03 419	83.36 412	96.92 368	95.18 404	91.28 345	86.48 402	93.42 408	53.27 425	96.74 394	89.43 356	81.97 402	94.11 404

dmvs_testset		87.64 377	88.93 369	83.79 403	95.25 386	63.36 435	97.20 350	91.17 427	93.07 282	85.64 406	95.98 374	85.30 295	91.52 425	69.42 424	87.33 377	96.49 353

test_fmvs3		87.17 378	87.06 381	87.50 396	91.21 417	75.66 421	99.05 69	96.61 384	92.79 294	88.85 387	92.78 413	43.72 428	93.49 419	93.95 249	84.56 393	93.34 413

UnsupCasMVSNet_bld		87.17 378	85.12 385	93.31 376	91.94 414	88.77 380	94.92 409	98.30 230	84.30 409	82.30 412	90.04 420	63.96 419	97.25 385	85.85 385	74.47 425	93.93 409

N_pmnet		87.12 380	87.77 378	85.17 400	95.46 382	61.92 436	97.37 336	70.66 441	85.83 402	88.73 389	96.04 370	85.33 293	97.76 371	80.02 409	90.48 334	95.84 375

pmmvs3		86.67 381	84.86 386	92.11 388	88.16 425	87.19 400	96.63 386	94.75 408	79.88 417	87.22 395	92.75 415	66.56 416	95.20 414	81.24 407	76.56 422	93.96 408

test_f		86.07 382	85.39 383	88.10 395	89.28 423	75.57 422	97.73 311	96.33 389	89.41 381	85.35 407	91.56 419	43.31 430	95.53 410	91.32 320	84.23 395	93.21 414

WB-MVS		84.86 383	85.33 384	83.46 404	89.48 422	69.56 430	98.19 251	96.42 388	89.55 377	81.79 413	94.67 396	84.80 302	90.12 426	52.44 430	80.64 410	90.69 417

SSC-MVS		84.27 384	84.71 387	82.96 408	89.19 424	68.83 431	98.08 267	96.30 390	89.04 385	81.37 415	94.47 397	84.60 309	89.89 427	49.80 432	79.52 412	90.15 418

dongtai		82.47 385	81.88 388	84.22 402	95.19 388	76.03 419	94.59 416	74.14 440	82.63 412	87.19 396	96.09 367	64.10 418	87.85 430	58.91 428	84.11 396	88.78 422

test_vis3_rt		79.22 386	77.40 393	84.67 401	86.44 429	74.85 425	97.66 316	81.43 436	84.98 406	67.12 429	81.91 427	28.09 438	97.60 376	88.96 361	80.04 411	81.55 427

test_method		79.03 387	78.17 389	81.63 409	86.06 430	54.40 441	82.75 429	96.89 371	39.54 433	80.98 417	95.57 386	58.37 423	94.73 416	84.74 396	78.61 415	95.75 377

testf1		79.02 388	77.70 390	82.99 406	88.10 426	66.90 432	94.67 412	93.11 419	71.08 424	74.02 422	93.41 409	34.15 434	93.25 420	72.25 422	78.50 416	88.82 420

APD_test2		79.02 388	77.70 390	82.99 406	88.10 426	66.90 432	94.67 412	93.11 419	71.08 424	74.02 422	93.41 409	34.15 434	93.25 420	72.25 422	78.50 416	88.82 420

LCM-MVSNet		78.70 390	76.24 396	86.08 398	77.26 437	71.99 428	94.34 418	96.72 378	61.62 428	76.53 420	89.33 421	33.91 436	92.78 423	81.85 404	74.60 424	93.46 411

kuosan		78.45 391	77.69 392	80.72 410	92.73 412	75.32 423	94.63 415	74.51 439	75.96 420	80.87 418	93.19 411	63.23 420	79.99 434	42.56 434	81.56 405	86.85 426

Gipuma		78.40 392	76.75 395	83.38 405	95.54 377	80.43 417	79.42 430	97.40 332	64.67 427	73.46 424	80.82 428	45.65 427	93.14 422	66.32 426	87.43 375	76.56 430
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		77.95 393	75.44 397	85.46 399	82.54 432	74.95 424	94.23 419	93.08 421	72.80 423	74.68 421	87.38 422	36.36 433	91.56 424	73.95 420	63.94 429	89.87 419

FPMVS		77.62 394	77.14 394	79.05 412	79.25 435	60.97 437	95.79 399	95.94 395	65.96 426	67.93 428	94.40 400	37.73 432	88.88 429	68.83 425	88.46 365	87.29 423

EGC-MVSNET		75.22 395	69.54 398	92.28 386	94.81 394	89.58 365	97.64 318	96.50 385	1.82 438	5.57 439	95.74 377	68.21 410	96.26 404	73.80 421	91.71 319	90.99 416

ANet_high		69.08 396	65.37 400	80.22 411	65.99 439	71.96 429	90.91 425	90.09 430	82.62 413	49.93 434	78.39 429	29.36 437	81.75 431	62.49 427	38.52 433	86.95 425

tmp_tt		68.90 397	66.97 399	74.68 414	50.78 441	59.95 438	87.13 426	83.47 435	38.80 434	62.21 430	96.23 361	64.70 417	76.91 436	88.91 362	30.49 434	87.19 424

PMVS	61.03 23	65.95 398	63.57 402	73.09 415	57.90 440	51.22 442	85.05 428	93.93 417	54.45 429	44.32 435	83.57 424	13.22 439	89.15 428	58.68 429	81.00 407	78.91 429
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		64.94 399	64.25 401	67.02 416	82.28 433	59.36 439	91.83 424	85.63 433	52.69 430	60.22 431	77.28 430	41.06 431	80.12 433	46.15 433	41.14 431	61.57 432

EMVS		64.07 400	63.26 403	66.53 417	81.73 434	58.81 440	91.85 423	84.75 434	51.93 432	59.09 432	75.13 431	43.32 429	79.09 435	42.03 435	39.47 432	61.69 431

MVE	62.14 22	63.28 401	59.38 404	74.99 413	74.33 438	65.47 434	85.55 427	80.50 437	52.02 431	51.10 433	75.00 432	10.91 442	80.50 432	51.60 431	53.40 430	78.99 428
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		30.17 402	30.18 406	30.16 418	78.61 436	43.29 443	66.79 431	14.21 442	17.31 435	14.82 438	11.93 438	11.55 441	41.43 437	37.08 436	19.30 435	5.76 435

cdsmvs_eth3d_5k		23.98 403	31.98 405	0.00 421	0.00 444	0.00 446	0.00 432	98.59 159	0.00 439	0.00 440	98.61 164	90.60 176	0.00 440	0.00 439	0.00 438	0.00 436

testmvs		21.48 404	24.95 407	11.09 420	14.89 442	6.47 445	96.56 388	9.87 443	7.55 436	17.93 436	39.02 434	9.43 443	5.90 439	16.56 438	12.72 436	20.91 434

test123		20.95 405	23.72 408	12.64 419	13.54 443	8.19 444	96.55 389	6.13 444	7.48 437	16.74 437	37.98 435	12.97 440	6.05 438	16.69 437	5.43 437	23.68 433

ab-mvs-re		8.20 406	10.94 409	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	98.43 182	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

pcd_1.5k_mvsjas		7.88 407	10.50 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	94.51 87	0.00 440	0.00 439	0.00 438	0.00 436

mmdepth		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

monomultidepth		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

test_blank		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet_test		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

DCPMVS		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

sosnet-low-res		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

sosnet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uncertanet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

Regformer		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

WAC-MVS						90.94 334								88.66 364

FOURS1					99.82 1	98.66 24	99.69 1	98.95 54	97.46 47	99.39 39

MSC_two_6792asdad				99.62 6	99.17 101	99.08 11		98.63 152					99.94 12	98.53 47	99.80 24	99.86 9

PC_three_1452									95.08 175	99.60 28	99.16 89	97.86 2	98.47 304	97.52 118	99.72 60	99.74 42

No_MVS				99.62 6	99.17 101	99.08 11		98.63 152					99.94 12	98.53 47	99.80 24	99.86 9

test_one_0601					99.66 26	99.25 2		98.86 83	97.55 40	99.20 51	99.47 31	97.57 6

eth-test2					0.00 444

eth-test					0.00 444

ZD-MVS					99.46 52	98.70 23		98.79 110	93.21 275	98.67 89	98.97 119	95.70 49	99.83 81	96.07 172	99.58 91

RE-MVS-def			98.34 46		99.49 46	97.86 69	99.11 60	98.80 105	96.49 103	99.17 54	99.35 55	95.29 65		97.72 97	99.65 74	99.71 55

IU-MVS					99.71 19	99.23 7		98.64 149	95.28 162	99.63 27				98.35 64	99.81 15	99.83 14

OPU-MVS				99.37 22	99.24 93	99.05 14	99.02 79				99.16 89	97.81 3	99.37 195	97.24 127	99.73 55	99.70 59

test_241102_TWO								98.87 77	97.65 33	99.53 32	99.48 29	97.34 11	99.94 12	98.43 59	99.80 24	99.83 14

test_241102_ONE					99.71 19	99.24 5		98.87 77	97.62 35	99.73 18	99.39 43	97.53 7	99.74 123

9.14			98.06 71		99.47 50		98.71 169	98.82 92	94.36 213	99.16 57	99.29 64	96.05 37	99.81 93	97.00 133	99.71 62

save fliter					99.46 52	98.38 35	98.21 246	98.71 128	97.95 24

test_0728_THIRD									97.32 55	99.45 34	99.46 35	97.88 1	99.94 12	98.47 55	99.86 2	99.85 11

test_0728_SECOND				99.71 1	99.72 12	99.35 1	98.97 89	98.88 70					99.94 12	98.47 55	99.81 15	99.84 13

test0726					99.72 12	99.25 2	99.06 67	98.88 70	97.62 35	99.56 29	99.50 25	97.42 9

GSMVS																99.20 151

test_part2					99.63 29	99.18 10				99.27 48

sam_mvs1												89.45 199				99.20 151

sam_mvs												88.99 213

ambc				89.49 393	86.66 428	75.78 420	92.66 422	96.72 378		86.55 401	92.50 416	46.01 426	97.90 362	90.32 337	82.09 400	94.80 397

MTGPA								98.74 120

test_post1							96.68 385				30.43 437	87.85 247	98.69 283	92.59 289

test_post											31.83 436	88.83 220	98.91 259

patchmatchnet-post											95.10 392	89.42 200	98.89 263

GG-mvs-BLEND				96.59 255	96.34 350	94.98 217	96.51 390	88.58 432		93.10 329	94.34 403	80.34 354	98.05 351	89.53 353	96.99 219	96.74 315

MTMP							98.89 110	94.14 415

gm-plane-assit					95.88 368	87.47 397			89.74 374		96.94 330		99.19 214	93.32 268

test9_res														96.39 166	99.57 92	99.69 62

TEST9					99.31 69	98.50 29	97.92 286	98.73 123	92.63 298	97.74 149	98.68 159	96.20 32	99.80 100

test_8					99.29 78	98.44 31	97.89 294	98.72 125	92.98 286	97.70 154	98.66 162	96.20 32	99.80 100

agg_prior2														95.87 182	99.57 92	99.68 67

agg_prior					99.30 73	98.38 35		98.72 125		97.57 166			99.81 93

TestCases				96.99 220	99.25 86	93.21 295		98.18 248	91.36 338	93.52 308	98.77 148	84.67 307	99.72 125	89.70 350	97.87 195	98.02 255

test_prior4						98.01 65	97.86 298

test_prior2							97.80 305		96.12 121	97.89 142	98.69 158	95.96 41		96.89 142	99.60 86

test_prior				99.19 44	99.31 69	98.22 52		98.84 87					99.70 131			99.65 75

旧先验2							97.57 324		91.30 343	98.67 89			99.80 100	95.70 191

新几何2							97.64 318

新几何1				99.16 49	99.34 62	98.01 65		98.69 133	90.06 368	98.13 118	98.95 126	94.60 85	99.89 59	91.97 308	99.47 112	99.59 86

旧先验1					99.29 78	97.48 83		98.70 132			99.09 105	95.56 52			99.47 112	99.61 82

无先验							97.58 323	98.72 125	91.38 337				99.87 70	93.36 267		99.60 84

原ACMM2							97.67 315

原ACMM1				98.65 89	99.32 67	96.62 128		98.67 141	93.27 274	97.81 144	98.97 119	95.18 72	99.83 81	93.84 253	99.46 115	99.50 98

test222					99.23 94	97.17 106	97.40 332	98.66 144	88.68 387	98.05 124	98.96 124	94.14 98			99.53 103	99.61 82

testdata2													99.89 59	91.65 316

segment_acmp												96.85 14

testdata				98.26 126	99.20 99	95.36 194		98.68 136	91.89 324	98.60 97	99.10 98	94.44 92	99.82 88	94.27 239	99.44 116	99.58 90

testdata1							97.32 342		96.34 111

test12				99.18 46	99.16 105	98.19 54		98.53 175		98.07 122		95.13 75	99.72 125		99.56 98	99.63 80

plane_prior7					97.42 284	94.63 234

plane_prior6					97.35 291	94.61 237						87.09 259

plane_prior5								98.56 169					99.03 239	96.07 172	94.27 272	96.92 291

plane_prior4											98.28 201

plane_prior3						94.61 237			97.02 77	95.34 238

plane_prior2							98.80 144		97.28 58

plane_prior1					97.37 290

plane_prior						94.60 239	98.44 220		96.74 91						94.22 274

n2								0.00 445

nn								0.00 445

door-mid								94.37 411

lessismore_v0				94.45 360	94.93 392	88.44 388		91.03 428		86.77 399	97.64 263	76.23 390	98.42 310	90.31 338	85.64 392	96.51 350

LGP-MVS_train				96.47 270	97.46 279	93.54 276		98.54 173	94.67 197	94.36 270	98.77 148	85.39 289	99.11 227	95.71 189	94.15 278	96.76 313

test11								98.66 144

door								94.64 409

HQP5-MVS						94.25 255

HQP-NCC					97.20 299		98.05 270		96.43 105	94.45 262

ACMP_Plane					97.20 299		98.05 270		96.43 105	94.45 262

BP-MVS														95.30 202

HQP4-MVS										94.45 262			98.96 250			96.87 303

HQP3-MVS								98.46 194							94.18 276

HQP2-MVS												86.75 265

NP-MVS					97.28 293	94.51 242					97.73 250

MDTV_nov1_ep13_2view						84.26 406	96.89 375		90.97 352	97.90 141		89.89 188		93.91 251		99.18 160

MDTV_nov1_ep13			95.40 189		97.48 277	88.34 389	96.85 378	97.29 340	93.74 244	97.48 168	97.26 291	89.18 207	99.05 235	91.92 309	97.43 210

ACMMP++_ref															92.97 304

ACMMP++															93.61 293

Test By Simon												94.64 84

ITE_SJBPF				95.44 321	97.42 284	91.32 328		97.50 320	95.09 174	93.59 304	98.35 192	81.70 336	98.88 265	89.71 349	93.39 299	96.12 369

DeepMVS_CX				86.78 397	97.09 309	72.30 427		95.17 405	75.92 421	84.34 410	95.19 390	70.58 407	95.35 411	79.98 411	89.04 359	92.68 415

High-resolution multi-view benchmark