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 12	99.85 5	99.43 33	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 71	97.65 28	99.73 13	99.48 24	97.53 7	99.94 9	98.43 53	99.81 15	99.70 56

DVP-MVS++		99.08 3	98.89 5	99.64 3	99.17 99	99.23 7	99.69 1	98.88 64	97.32 49	99.53 26	99.47 26	97.81 3	99.94 9	98.47 49	99.72 58	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 11	99.86 3	99.42 34	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	98.58 158	97.62 30	99.45 28	99.46 30	97.42 9	99.94 9	98.47 49	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 52	97.38 46	99.41 31	99.54 14	96.66 18	99.84 73	98.86 28	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 81	98.06 16	99.35 35	99.61 4	96.39 27	99.94 9	98.77 31	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 83	98.06 16	99.29 39	99.58 10	96.40 25	99.94 9	98.68 33	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 83	98.06 16	99.29 39	99.58 10	96.40 25	99.94 9	98.68 33	99.81 15	99.81 17

test_fmvsmconf_n		98.92 10	98.87 6	99.04 58	98.88 132	97.25 98	98.82 133	99.34 10	98.75 5	99.80 6	99.61 4	95.16 73	99.95 7	99.70 8	99.80 24	99.93 1

DPE-MVS		98.92 10	98.67 15	99.65 2	99.58 32	99.20 9	98.42 217	98.91 58	97.58 33	99.54 25	99.46 30	97.10 12	99.94 9	97.64 100	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 94	98.43 33	99.10 63	98.87 71	97.38 46	99.35 35	99.40 36	97.78 5	99.87 64	97.77 88	99.85 6	99.78 23
Skip Steuart: Steuart Systems R&D Blog.
test_fmvsm_n_1920		98.87 13	99.01 3	98.45 105	99.42 58	96.43 137	98.96 94	99.36 9	98.63 7	99.86 3	99.51 19	95.91 43	99.97 1	99.72 6	99.75 47	98.94 187

TSAR-MVS + MP.		98.78 14	98.62 16	99.24 39	99.69 24	98.28 48	99.14 54	98.66 138	96.84 78	99.56 23	99.31 56	96.34 28	99.70 125	98.32 59	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	98.47 209	98.81 92	97.72 23	98.76 78	99.16 83	97.05 13	99.78 107	98.06 70	99.66 68	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 64	97.52 36	99.41 31	98.78 140	96.00 39	99.79 104	97.79 87	99.59 83	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 64	97.40 43	98.46 96	99.20 73	95.90 45	99.89 53	97.85 83	99.74 51	99.78 23

MCST-MVS		98.65 18	98.37 33	99.48 13	99.60 31	98.87 19	98.41 218	98.68 130	97.04 70	98.52 94	98.80 138	96.78 16	99.83 75	97.93 77	99.61 79	99.74 39

SD-MVS		98.64 19	98.68 14	98.53 96	99.33 62	98.36 43	98.90 106	98.85 80	97.28 52	99.72 15	99.39 37	96.63 20	97.60 367	98.17 65	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 30	99.32 31	99.72 12	98.29 47	99.23 32	98.96 47	96.10 115	98.94 61	99.17 80	96.06 36	99.92 35	97.62 101	99.78 34	99.75 37

ACMMP_NAP		98.61 21	98.30 46	99.55 9	99.62 30	98.95 17	98.82 133	98.81 92	95.80 126	99.16 51	99.47 26	95.37 60	99.92 35	97.89 81	99.75 47	99.79 21

region2R		98.61 21	98.38 32	99.29 32	99.74 7	98.16 56	99.23 32	98.93 52	96.15 112	98.94 61	99.17 80	95.91 43	99.94 9	97.55 108	99.79 30	99.78 23

NCCC		98.61 21	98.35 36	99.38 18	99.28 80	98.61 26	98.45 210	98.76 110	97.82 22	98.45 99	98.93 122	96.65 19	99.83 75	97.38 117	99.41 113	99.71 52

SF-MVS		98.59 24	98.32 45	99.41 17	99.54 35	98.71 22	99.04 73	98.81 92	95.12 162	99.32 38	99.39 37	96.22 30	99.84 73	97.72 91	99.73 54	99.67 68

ACMMPR		98.59 24	98.36 34	99.29 32	99.74 7	98.15 57	99.23 32	98.95 48	96.10 115	98.93 65	99.19 78	95.70 49	99.94 9	97.62 101	99.79 30	99.78 23

test_fmvsmconf0.1_n		98.58 26	98.44 28	98.99 60	97.73 248	97.15 103	98.84 129	98.97 44	98.75 5	99.43 30	99.54 14	93.29 107	99.93 28	99.64 11	99.79 30	99.89 4

SMA-MVS		98.58 26	98.25 49	99.56 8	99.51 40	99.04 15	98.95 95	98.80 99	93.67 245	99.37 34	99.52 17	96.52 22	99.89 53	98.06 70	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 47	99.46 14	99.76 2	98.64 25	98.90 106	98.74 114	97.27 56	98.02 123	99.39 37	94.81 83	99.96 4	97.91 79	99.79 30	99.77 29

HPM-MVS++		98.58 26	98.25 49	99.55 9	99.50 42	99.08 11	98.72 163	98.66 138	97.51 37	98.15 110	98.83 135	95.70 49	99.92 35	97.53 110	99.67 65	99.66 71

SR-MVS		98.57 30	98.35 36	99.24 39	99.53 36	98.18 54	99.09 64	98.82 86	96.58 94	99.10 53	99.32 54	95.39 58	99.82 82	97.70 96	99.63 76	99.72 48

CP-MVS		98.57 30	98.36 34	99.19 43	99.66 26	97.86 68	99.34 16	98.87 71	95.96 118	98.60 91	99.13 88	96.05 37	99.94 9	97.77 88	99.86 2	99.77 29

MSLP-MVS++		98.56 32	98.57 18	98.55 92	99.26 83	96.80 117	98.71 164	99.05 38	97.28 52	98.84 71	99.28 59	96.47 23	99.40 184	98.52 47	99.70 61	99.47 103

DeepC-MVS_fast	96.70 1	98.55 33	98.34 40	99.18 45	99.25 84	98.04 62	98.50 206	98.78 106	97.72 23	98.92 67	99.28 59	95.27 66	99.82 82	97.55 108	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 36	99.13 51	99.49 46	97.86 68	99.11 60	98.80 99	96.49 97	99.17 48	99.35 49	95.34 62	99.82 82	97.72 91	99.65 71	99.71 52

fmvsm_s_conf0.5_n_3		98.53 35	98.45 27	98.79 74	99.23 92	97.32 90	98.80 142	99.26 15	98.82 2	99.87 1	99.60 8	90.95 164	99.93 28	99.76 5	99.73 54	99.12 162

APD-MVS_3200maxsize		98.53 35	98.33 44	99.15 49	99.50 42	97.92 67	99.15 51	98.81 92	96.24 108	99.20 45	99.37 43	95.30 64	99.80 94	97.73 90	99.67 65	99.72 48

MM		98.51 37	98.24 51	99.33 29	99.12 107	98.14 59	98.93 101	97.02 353	98.96 1	99.17 48	99.47 26	91.97 137	99.94 9	99.85 3	99.69 62	99.91 2

mPP-MVS		98.51 37	98.26 48	99.25 38	99.75 3	98.04 62	99.28 24	98.81 92	96.24 108	98.35 106	99.23 68	95.46 55	99.94 9	97.42 115	99.81 15	99.77 29

ZNCC-MVS		98.49 39	98.20 57	99.35 24	99.73 11	98.39 34	99.19 44	98.86 77	95.77 128	98.31 109	99.10 92	95.46 55	99.93 28	97.57 107	99.81 15	99.74 39

SPE-MVS-test		98.49 39	98.50 23	98.46 104	99.20 97	97.05 107	99.64 4	98.50 180	97.45 42	98.88 68	99.14 87	95.25 68	99.15 212	98.83 29	99.56 93	99.20 147

PGM-MVS		98.49 39	98.23 53	99.27 37	99.72 12	98.08 61	98.99 86	99.49 5	95.43 144	99.03 54	99.32 54	95.56 52	99.94 9	96.80 146	99.77 36	99.78 23

EI-MVSNet-Vis-set		98.47 42	98.39 31	98.69 81	99.46 52	96.49 134	98.30 229	98.69 127	97.21 59	98.84 71	99.36 47	95.41 57	99.78 107	98.62 36	99.65 71	99.80 20

MVS_111021_HR		98.47 42	98.34 40	98.88 71	99.22 94	97.32 90	97.91 278	99.58 3	97.20 60	98.33 107	99.00 111	95.99 40	99.64 137	98.05 72	99.76 42	99.69 59

balanced_conf03		98.45 44	98.35 36	98.74 77	98.65 159	97.55 78	99.19 44	98.60 149	96.72 88	99.35 35	98.77 142	95.06 78	99.55 160	98.95 25	99.87 1	99.12 162

test_fmvsmvis_n_1920		98.44 45	98.51 21	98.23 125	98.33 189	96.15 151	98.97 89	99.15 30	98.55 10	98.45 99	99.55 12	94.26 96	99.97 1	99.65 9	99.66 68	98.57 224

CS-MVS		98.44 45	98.49 24	98.31 117	99.08 112	96.73 121	99.67 3	98.47 186	97.17 62	98.94 61	99.10 92	95.73 48	99.13 215	98.71 32	99.49 103	99.09 167

GST-MVS		98.43 47	98.12 61	99.34 25	99.72 12	98.38 35	99.09 64	98.82 86	95.71 132	98.73 81	99.06 103	95.27 66	99.93 28	97.07 125	99.63 76	99.72 48

fmvsm_s_conf0.5_n		98.42 48	98.51 21	98.13 134	99.30 71	95.25 197	98.85 125	99.39 7	97.94 20	99.74 12	99.62 3	92.59 116	99.91 44	99.65 9	99.52 99	99.25 140

EI-MVSNet-UG-set		98.41 49	98.34 40	98.61 87	99.45 55	96.32 144	98.28 232	98.68 130	97.17 62	98.74 79	99.37 43	95.25 68	99.79 104	98.57 38	99.54 96	99.73 44

DELS-MVS		98.40 50	98.20 57	98.99 60	99.00 119	97.66 73	97.75 299	98.89 61	97.71 25	98.33 107	98.97 113	94.97 80	99.88 62	98.42 55	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 51	98.42 29	98.27 119	99.09 111	95.41 187	98.86 121	99.37 8	97.69 27	99.78 8	99.61 4	92.38 119	99.91 44	99.58 13	99.43 111	99.49 99

TSAR-MVS + GP.		98.38 51	98.24 51	98.81 73	99.22 94	97.25 98	98.11 256	98.29 225	97.19 61	98.99 59	99.02 106	96.22 30	99.67 132	98.52 47	98.56 161	99.51 92

HPM-MVS_fast		98.38 51	98.13 60	99.12 53	99.75 3	97.86 68	99.44 9	98.82 86	94.46 201	98.94 61	99.20 73	95.16 73	99.74 117	97.58 104	99.85 6	99.77 29

patch_mono-2		98.36 54	98.87 6	96.82 228	99.53 36	90.68 335	98.64 181	99.29 14	97.88 21	99.19 47	99.52 17	96.80 15	99.97 1	99.11 21	99.86 2	99.82 16

HPM-MVS		98.36 54	98.10 64	99.13 51	99.74 7	97.82 72	99.53 6	98.80 99	94.63 191	98.61 90	98.97 113	95.13 75	99.77 112	97.65 99	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 56	98.00 70	99.42 16	99.51 40	98.72 21	98.80 142	98.82 86	94.52 198	99.23 44	99.25 67	95.54 54	99.80 94	96.52 153	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 57	98.23 53	98.67 83	99.27 81	96.90 113	97.95 273	99.58 3	97.14 65	98.44 101	99.01 110	95.03 79	99.62 144	97.91 79	99.75 47	99.50 94

PHI-MVS		98.34 57	98.06 65	99.18 45	99.15 105	98.12 60	99.04 73	99.09 33	93.32 260	98.83 73	99.10 92	96.54 21	99.83 75	97.70 96	99.76 42	99.59 82

MP-MVS		98.33 59	98.01 69	99.28 35	99.75 3	98.18 54	99.22 36	98.79 104	96.13 113	97.92 134	99.23 68	94.54 86	99.94 9	96.74 149	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 60	98.19 59	98.67 83	98.96 126	97.36 88	99.24 30	98.57 160	94.81 183	98.99 59	98.90 126	95.22 71	99.59 147	99.15 20	99.84 11	99.07 175

MP-MVS-pluss		98.31 60	97.92 72	99.49 12	99.72 12	98.88 18	98.43 215	98.78 106	94.10 210	97.69 149	99.42 34	95.25 68	99.92 35	98.09 69	99.80 24	99.67 68
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.5_n_2		98.30 62	98.21 55	98.57 89	99.25 84	97.11 104	98.66 177	99.20 25	98.82 2	99.79 7	99.60 8	89.38 195	99.92 35	99.80 4	99.38 118	98.69 208

MVS_0304		98.23 63	97.91 73	99.21 42	98.06 218	97.96 66	98.58 190	95.51 390	98.58 8	98.87 69	99.26 62	92.99 111	99.95 7	99.62 12	99.67 65	99.73 44

ACMMP		98.23 63	97.95 71	99.09 55	99.74 7	97.62 76	99.03 76	99.41 6	95.98 117	97.60 158	99.36 47	94.45 91	99.93 28	97.14 122	98.85 147	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 65	98.11 62	98.49 101	98.34 186	97.26 97	99.61 5	98.43 195	96.78 81	98.87 69	98.84 133	93.72 103	99.01 236	98.91 27	99.50 101	99.19 151

fmvsm_s_conf0.1_n		98.18 66	98.21 55	98.11 138	98.54 168	95.24 198	98.87 118	99.24 18	97.50 38	99.70 16	99.67 1	91.33 153	99.89 53	99.47 15	99.54 96	99.21 146

fmvsm_s_conf0.1_n_2		98.14 67	98.02 68	98.53 96	98.88 132	97.07 106	98.69 170	98.82 86	98.78 4	99.77 9	99.61 4	88.83 214	99.91 44	99.71 7	99.07 131	98.61 218

fmvsm_s_conf0.1_n_a		98.08 68	98.04 67	98.21 126	97.66 254	95.39 188	98.89 110	99.17 28	97.24 57	99.76 11	99.67 1	91.13 158	99.88 62	99.39 16	99.41 113	99.35 119

dcpmvs_2		98.08 68	98.59 17	96.56 252	99.57 33	90.34 344	99.15 51	98.38 205	96.82 80	99.29 39	99.49 23	95.78 47	99.57 150	98.94 26	99.86 2	99.77 29

CANet		98.05 70	97.76 76	98.90 70	98.73 145	97.27 93	98.35 220	98.78 106	97.37 48	97.72 146	98.96 118	91.53 149	99.92 35	98.79 30	99.65 71	99.51 92

train_agg		97.97 71	97.52 88	99.33 29	99.31 67	98.50 29	97.92 276	98.73 117	92.98 276	97.74 143	98.68 153	96.20 32	99.80 94	96.59 150	99.57 87	99.68 64

ETV-MVS		97.96 72	97.81 74	98.40 112	98.42 174	97.27 93	98.73 159	98.55 165	96.84 78	98.38 103	97.44 271	95.39 58	99.35 189	97.62 101	98.89 142	98.58 223

UA-Net		97.96 72	97.62 80	98.98 62	98.86 136	97.47 84	98.89 110	99.08 34	96.67 91	98.72 82	99.54 14	93.15 109	99.81 87	94.87 207	98.83 148	99.65 72

CDPH-MVS		97.94 74	97.49 90	99.28 35	99.47 50	98.44 31	97.91 278	98.67 135	92.57 292	98.77 77	98.85 132	95.93 42	99.72 119	95.56 187	99.69 62	99.68 64

DeepPCF-MVS	96.37 2	97.93 75	98.48 26	96.30 277	99.00 119	89.54 358	97.43 321	98.87 71	98.16 14	99.26 43	99.38 42	96.12 35	99.64 137	98.30 60	99.77 36	99.72 48

DeepC-MVS	95.98 3	97.88 76	97.58 82	98.77 75	99.25 84	96.93 111	98.83 131	98.75 112	96.96 74	96.89 183	99.50 21	90.46 172	99.87 64	97.84 85	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 77	97.54 87	98.83 72	95.48 371	96.83 116	98.95 95	98.60 149	98.58 8	98.93 65	99.55 12	88.57 219	99.91 44	99.54 14	99.61 79	99.77 29

DP-MVS Recon		97.86 77	97.46 93	99.06 57	99.53 36	98.35 44	98.33 222	98.89 61	92.62 289	98.05 118	98.94 121	95.34 62	99.65 135	96.04 169	99.42 112	99.19 151

CSCG		97.85 79	97.74 77	98.20 128	99.67 25	95.16 201	99.22 36	99.32 11	93.04 274	97.02 176	98.92 124	95.36 61	99.91 44	97.43 114	99.64 75	99.52 89

BP-MVS1		97.82 80	97.51 89	98.76 76	98.25 196	97.39 87	99.15 51	97.68 292	96.69 89	98.47 95	99.10 92	90.29 176	99.51 167	98.60 37	99.35 121	99.37 117

MG-MVS		97.81 81	97.60 81	98.44 107	99.12 107	95.97 160	97.75 299	98.78 106	96.89 77	98.46 96	99.22 70	93.90 102	99.68 131	94.81 211	99.52 99	99.67 68

VNet		97.79 82	97.40 97	98.96 65	98.88 132	97.55 78	98.63 184	98.93 52	96.74 85	99.02 55	98.84 133	90.33 175	99.83 75	98.53 41	96.66 222	99.50 94

EIA-MVS		97.75 83	97.58 82	98.27 119	98.38 178	96.44 136	99.01 81	98.60 149	95.88 122	97.26 165	97.53 265	94.97 80	99.33 192	97.38 117	99.20 127	99.05 176

PS-MVSNAJ		97.73 84	97.77 75	97.62 178	98.68 154	95.58 178	97.34 330	98.51 175	97.29 51	98.66 87	97.88 231	94.51 87	99.90 51	97.87 82	99.17 129	97.39 265

casdiffmvs_mvg		97.72 85	97.48 92	98.44 107	98.42 174	96.59 129	98.92 103	98.44 191	96.20 110	97.76 140	99.20 73	91.66 143	99.23 202	98.27 64	98.41 171	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 85	97.32 101	98.92 67	99.64 28	97.10 105	99.12 58	98.81 92	92.34 300	98.09 115	99.08 101	93.01 110	99.92 35	96.06 168	99.77 36	99.75 37

PVSNet_Blended_VisFu		97.70 87	97.46 93	98.44 107	99.27 81	95.91 168	98.63 184	99.16 29	94.48 200	97.67 150	98.88 129	92.80 113	99.91 44	97.11 123	99.12 130	99.50 94

mvsany_test1		97.69 88	97.70 78	97.66 176	98.24 197	94.18 251	97.53 315	97.53 310	95.52 140	99.66 18	99.51 19	94.30 94	99.56 153	98.38 56	98.62 157	99.23 142

sasdasda		97.67 89	97.23 105	98.98 62	98.70 150	98.38 35	99.34 16	98.39 201	96.76 83	97.67 150	97.40 275	92.26 123	99.49 171	98.28 61	96.28 240	99.08 171

canonicalmvs		97.67 89	97.23 105	98.98 62	98.70 150	98.38 35	99.34 16	98.39 201	96.76 83	97.67 150	97.40 275	92.26 123	99.49 171	98.28 61	96.28 240	99.08 171

xiu_mvs_v2_base		97.66 91	97.70 78	97.56 182	98.61 163	95.46 185	97.44 319	98.46 187	97.15 64	98.65 88	98.15 207	94.33 93	99.80 94	97.84 85	98.66 156	97.41 263

GDP-MVS		97.64 92	97.28 102	98.71 80	98.30 194	97.33 89	99.05 69	98.52 172	96.34 105	98.80 74	99.05 104	89.74 185	99.51 167	96.86 143	98.86 146	99.28 134

baseline		97.64 92	97.44 95	98.25 123	98.35 181	96.20 148	99.00 83	98.32 215	96.33 107	98.03 121	99.17 80	91.35 152	99.16 209	98.10 68	98.29 178	99.39 115

casdiffmvs		97.63 94	97.41 96	98.28 118	98.33 189	96.14 152	98.82 133	98.32 215	96.38 104	97.95 129	99.21 71	91.23 157	99.23 202	98.12 67	98.37 172	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 95	97.19 108	98.92 67	98.66 156	98.20 52	99.32 21	98.38 205	96.69 89	97.58 159	97.42 274	92.10 131	99.50 170	98.28 61	96.25 243	99.08 171

xiu_mvs_v1_base_debu		97.60 96	97.56 84	97.72 166	98.35 181	95.98 155	97.86 288	98.51 175	97.13 66	99.01 56	98.40 180	91.56 145	99.80 94	98.53 41	98.68 152	97.37 267

xiu_mvs_v1_base		97.60 96	97.56 84	97.72 166	98.35 181	95.98 155	97.86 288	98.51 175	97.13 66	99.01 56	98.40 180	91.56 145	99.80 94	98.53 41	98.68 152	97.37 267

xiu_mvs_v1_base_debi		97.60 96	97.56 84	97.72 166	98.35 181	95.98 155	97.86 288	98.51 175	97.13 66	99.01 56	98.40 180	91.56 145	99.80 94	98.53 41	98.68 152	97.37 267

diffmvs		97.58 99	97.40 97	98.13 134	98.32 192	95.81 173	98.06 262	98.37 207	96.20 110	98.74 79	98.89 128	91.31 155	99.25 199	98.16 66	98.52 163	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		97.57 100	97.49 90	97.84 153	98.07 215	95.76 174	99.47 7	98.40 199	94.98 172	98.79 75	98.83 135	92.34 120	98.41 309	96.91 131	99.59 83	99.34 121

alignmvs		97.56 101	97.07 114	99.01 59	98.66 156	98.37 42	98.83 131	98.06 272	96.74 85	98.00 127	97.65 253	90.80 166	99.48 176	98.37 57	96.56 226	99.19 151

DPM-MVS		97.55 102	96.99 117	99.23 41	99.04 114	98.55 27	97.17 345	98.35 210	94.85 182	97.93 133	98.58 163	95.07 77	99.71 124	92.60 279	99.34 122	99.43 112

OMC-MVS		97.55 102	97.34 100	98.20 128	99.33 62	95.92 167	98.28 232	98.59 153	95.52 140	97.97 128	99.10 92	93.28 108	99.49 171	95.09 202	98.88 143	99.19 151

PAPM_NR		97.46 104	97.11 111	98.50 99	99.50 42	96.41 139	98.63 184	98.60 149	95.18 159	97.06 174	98.06 213	94.26 96	99.57 150	93.80 247	98.87 145	99.52 89

EPP-MVSNet		97.46 104	97.28 102	97.99 146	98.64 160	95.38 189	99.33 20	98.31 217	93.61 249	97.19 167	99.07 102	94.05 99	99.23 202	96.89 135	98.43 170	99.37 117

3Dnovator	94.51 5	97.46 104	96.93 120	99.07 56	97.78 242	97.64 74	99.35 15	99.06 36	97.02 71	93.75 293	99.16 83	89.25 199	99.92 35	97.22 121	99.75 47	99.64 74

CNLPA		97.45 107	97.03 115	98.73 78	99.05 113	97.44 86	98.07 261	98.53 169	95.32 152	96.80 188	98.53 168	93.32 106	99.72 119	94.31 230	99.31 124	99.02 178

lupinMVS		97.44 108	97.22 107	98.12 137	98.07 215	95.76 174	97.68 304	97.76 289	94.50 199	98.79 75	98.61 158	92.34 120	99.30 195	97.58 104	99.59 83	99.31 127

3Dnovator+	94.38 6	97.43 109	96.78 128	99.38 18	97.83 239	98.52 28	99.37 12	98.71 122	97.09 69	92.99 321	99.13 88	89.36 196	99.89 53	96.97 128	99.57 87	99.71 52

Vis-MVSNet		97.42 110	97.11 111	98.34 115	98.66 156	96.23 147	99.22 36	99.00 41	96.63 93	98.04 120	99.21 71	88.05 235	99.35 189	96.01 171	99.21 126	99.45 109
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
API-MVS		97.41 111	97.25 104	97.91 150	98.70 150	96.80 117	98.82 133	98.69 127	94.53 196	98.11 113	98.28 195	94.50 90	99.57 150	94.12 236	99.49 103	97.37 267

sss		97.39 112	96.98 119	98.61 87	98.60 164	96.61 126	98.22 238	98.93 52	93.97 220	98.01 126	98.48 173	91.98 135	99.85 69	96.45 155	98.15 180	99.39 115

test_cas_vis1_n_1920		97.38 113	97.36 99	97.45 185	98.95 127	93.25 287	99.00 83	98.53 169	97.70 26	99.77 9	99.35 49	84.71 300	99.85 69	98.57 38	99.66 68	99.26 138

PVSNet_Blended		97.38 113	97.12 110	98.14 131	99.25 84	95.35 192	97.28 335	99.26 15	93.13 270	97.94 131	98.21 203	92.74 114	99.81 87	96.88 137	99.40 116	99.27 135

WTY-MVS		97.37 115	96.92 121	98.72 79	98.86 136	96.89 115	98.31 227	98.71 122	95.26 155	97.67 150	98.56 167	92.21 127	99.78 107	95.89 173	96.85 217	99.48 101

jason		97.32 116	97.08 113	98.06 142	97.45 274	95.59 177	97.87 286	97.91 283	94.79 184	98.55 93	98.83 135	91.12 159	99.23 202	97.58 104	99.60 81	99.34 121
jason: jason.
MVS_Test		97.28 117	97.00 116	98.13 134	98.33 189	95.97 160	98.74 155	98.07 267	94.27 206	98.44 101	98.07 212	92.48 117	99.26 198	96.43 156	98.19 179	99.16 157

EPNet		97.28 117	96.87 123	98.51 98	94.98 380	96.14 152	98.90 106	97.02 353	98.28 13	95.99 219	99.11 90	91.36 151	99.89 53	96.98 127	99.19 128	99.50 94
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvsmamba		97.25 119	96.99 117	98.02 144	98.34 186	95.54 182	99.18 48	97.47 316	95.04 168	98.15 110	98.57 166	89.46 192	99.31 194	97.68 98	99.01 136	99.22 144

test_yl		97.22 120	96.78 128	98.54 94	98.73 145	96.60 127	98.45 210	98.31 217	94.70 185	98.02 123	98.42 178	90.80 166	99.70 125	96.81 144	96.79 219	99.34 121

DCV-MVSNet		97.22 120	96.78 128	98.54 94	98.73 145	96.60 127	98.45 210	98.31 217	94.70 185	98.02 123	98.42 178	90.80 166	99.70 125	96.81 144	96.79 219	99.34 121

IS-MVSNet		97.22 120	96.88 122	98.25 123	98.85 138	96.36 142	99.19 44	97.97 277	95.39 146	97.23 166	98.99 112	91.11 160	98.93 248	94.60 218	98.59 159	99.47 103

PLC	95.07 4	97.20 123	96.78 128	98.44 107	99.29 76	96.31 146	98.14 251	98.76 110	92.41 298	96.39 208	98.31 193	94.92 82	99.78 107	94.06 239	98.77 151	99.23 142
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		97.18 124	97.18 109	97.20 198	98.81 141	93.27 284	95.78 390	99.15 30	95.25 156	96.79 189	98.11 210	92.29 122	99.07 226	98.56 40	99.85 6	99.25 140

LS3D		97.16 125	96.66 137	98.68 82	98.53 169	97.19 101	98.93 101	98.90 59	92.83 283	95.99 219	99.37 43	92.12 130	99.87 64	93.67 251	99.57 87	98.97 183

AdaColmap		97.15 126	96.70 133	98.48 102	99.16 103	96.69 123	98.01 267	98.89 61	94.44 202	96.83 184	98.68 153	90.69 169	99.76 113	94.36 226	99.29 125	98.98 182

mamv4		97.13 127	98.11 62	94.17 356	98.97 125	83.70 398	98.66 177	98.71 122	94.63 191	97.83 137	98.90 126	96.25 29	99.55 160	99.27 18	99.76 42	99.27 135

Effi-MVS+		97.12 128	96.69 134	98.39 113	98.19 205	96.72 122	97.37 326	98.43 195	93.71 238	97.65 154	98.02 216	92.20 128	99.25 199	96.87 140	97.79 192	99.19 151

CHOSEN 1792x2688		97.12 128	96.80 125	98.08 140	99.30 71	94.56 235	98.05 263	99.71 1	93.57 250	97.09 170	98.91 125	88.17 229	99.89 53	96.87 140	99.56 93	99.81 17

F-COLMAP		97.09 130	96.80 125	97.97 147	99.45 55	94.95 214	98.55 198	98.62 148	93.02 275	96.17 214	98.58 163	94.01 100	99.81 87	93.95 241	98.90 141	99.14 160

RRT-MVS		97.03 131	96.78 128	97.77 162	97.90 235	94.34 244	99.12 58	98.35 210	95.87 123	98.06 117	98.70 151	86.45 266	99.63 140	98.04 73	98.54 162	99.35 119

TAMVS		97.02 132	96.79 127	97.70 169	98.06 218	95.31 195	98.52 200	98.31 217	93.95 221	97.05 175	98.61 158	93.49 105	98.52 291	95.33 194	97.81 191	99.29 132

CDS-MVSNet		96.99 133	96.69 134	97.90 151	98.05 220	95.98 155	98.20 241	98.33 214	93.67 245	96.95 177	98.49 172	93.54 104	98.42 302	95.24 200	97.74 195	99.31 127
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CANet_DTU		96.96 134	96.55 140	98.21 126	98.17 210	96.07 154	97.98 271	98.21 234	97.24 57	97.13 169	98.93 122	86.88 258	99.91 44	95.00 205	99.37 120	98.66 214

114514_t		96.93 135	96.27 150	98.92 67	99.50 42	97.63 75	98.85 125	98.90 59	84.80 397	97.77 139	99.11 90	92.84 112	99.66 134	94.85 208	99.77 36	99.47 103

MAR-MVS		96.91 136	96.40 146	98.45 105	98.69 153	96.90 113	98.66 177	98.68 130	92.40 299	97.07 173	97.96 223	91.54 148	99.75 115	93.68 249	98.92 140	98.69 208
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		96.90 137	96.49 143	98.14 131	99.33 62	95.56 179	97.38 324	99.65 2	92.34 300	97.61 157	98.20 204	89.29 198	99.10 223	96.97 128	97.60 200	99.77 29

Vis-MVSNet (Re-imp)		96.87 138	96.55 140	97.83 154	98.73 145	95.46 185	99.20 42	98.30 223	94.96 174	96.60 196	98.87 130	90.05 179	98.59 286	93.67 251	98.60 158	99.46 107

SDMVSNet		96.85 139	96.42 144	98.14 131	99.30 71	96.38 140	99.21 39	99.23 21	95.92 119	95.96 221	98.76 147	85.88 276	99.44 181	97.93 77	95.59 255	98.60 219

PAPR		96.84 140	96.24 152	98.65 85	98.72 149	96.92 112	97.36 328	98.57 160	93.33 259	96.67 191	97.57 262	94.30 94	99.56 153	91.05 320	98.59 159	99.47 103

HY-MVS	93.96 8	96.82 141	96.23 153	98.57 89	98.46 173	97.00 108	98.14 251	98.21 234	93.95 221	96.72 190	97.99 220	91.58 144	99.76 113	94.51 222	96.54 227	98.95 186

UGNet		96.78 142	96.30 149	98.19 130	98.24 197	95.89 170	98.88 115	98.93 52	97.39 45	96.81 187	97.84 235	82.60 327	99.90 51	96.53 152	99.49 103	98.79 197
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		96.73 143	96.60 138	97.12 207	99.25 84	95.35 192	98.26 235	99.26 15	94.28 205	97.94 131	97.46 268	92.74 114	99.81 87	96.88 137	93.32 291	96.20 357

test_vis1_n_1920		96.71 144	96.84 124	96.31 276	99.11 109	89.74 352	99.05 69	98.58 158	98.08 15	99.87 1	99.37 43	78.48 358	99.93 28	99.29 17	99.69 62	99.27 135

mvs_anonymous		96.70 145	96.53 142	97.18 201	98.19 205	93.78 260	98.31 227	98.19 238	94.01 217	94.47 252	98.27 198	92.08 133	98.46 297	97.39 116	97.91 187	99.31 127

1112_ss		96.63 146	96.00 160	98.50 99	98.56 165	96.37 141	98.18 249	98.10 260	92.92 279	94.84 241	98.43 176	92.14 129	99.58 149	94.35 227	96.51 228	99.56 88

PMMVS		96.60 147	96.33 148	97.41 189	97.90 235	93.93 256	97.35 329	98.41 197	92.84 282	97.76 140	97.45 270	91.10 161	99.20 206	96.26 161	97.91 187	99.11 165

DP-MVS		96.59 148	95.93 163	98.57 89	99.34 60	96.19 150	98.70 168	98.39 201	89.45 369	94.52 250	99.35 49	91.85 138	99.85 69	92.89 275	98.88 143	99.68 64

PatchMatch-RL		96.59 148	96.03 159	98.27 119	99.31 67	96.51 133	97.91 278	99.06 36	93.72 237	96.92 181	98.06 213	88.50 224	99.65 135	91.77 304	99.00 138	98.66 214

GeoE		96.58 150	96.07 156	98.10 139	98.35 181	95.89 170	99.34 16	98.12 254	93.12 271	96.09 215	98.87 130	89.71 186	98.97 238	92.95 271	98.08 183	99.43 112

XVG-OURS		96.55 151	96.41 145	96.99 214	98.75 144	93.76 261	97.50 318	98.52 172	95.67 134	96.83 184	99.30 57	88.95 212	99.53 163	95.88 174	96.26 242	97.69 256

FIs		96.51 152	96.12 155	97.67 173	97.13 298	97.54 80	99.36 13	99.22 24	95.89 121	94.03 279	98.35 186	91.98 135	98.44 300	96.40 157	92.76 299	97.01 275

XVG-OURS-SEG-HR		96.51 152	96.34 147	97.02 213	98.77 143	93.76 261	97.79 297	98.50 180	95.45 143	96.94 178	99.09 99	87.87 240	99.55 160	96.76 148	95.83 254	97.74 253

PS-MVSNAJss		96.43 154	96.26 151	96.92 223	95.84 360	95.08 206	99.16 50	98.50 180	95.87 123	93.84 288	98.34 190	94.51 87	98.61 283	96.88 137	93.45 288	97.06 273

test_fmvs1		96.42 155	96.67 136	95.66 304	98.82 140	88.53 377	98.80 142	98.20 236	96.39 103	99.64 20	99.20 73	80.35 346	99.67 132	99.04 23	99.57 87	98.78 200

FC-MVSNet-test		96.42 155	96.05 157	97.53 183	96.95 307	97.27 93	99.36 13	99.23 21	95.83 125	93.93 282	98.37 184	92.00 134	98.32 319	96.02 170	92.72 300	97.00 276

ab-mvs		96.42 155	95.71 173	98.55 92	98.63 161	96.75 120	97.88 285	98.74 114	93.84 227	96.54 201	98.18 206	85.34 286	99.75 115	95.93 172	96.35 232	99.15 158

FA-MVS(test-final)		96.41 158	95.94 162	97.82 156	98.21 201	95.20 200	97.80 295	97.58 300	93.21 265	97.36 163	97.70 247	89.47 191	99.56 153	94.12 236	97.99 184	98.71 207

PVSNet	91.96 18	96.35 159	96.15 154	96.96 218	99.17 99	92.05 308	96.08 383	98.68 130	93.69 241	97.75 142	97.80 241	88.86 213	99.69 130	94.26 232	99.01 136	99.15 158

Test_1112_low_res		96.34 160	95.66 178	98.36 114	98.56 165	95.94 163	97.71 302	98.07 267	92.10 309	94.79 245	97.29 283	91.75 140	99.56 153	94.17 234	96.50 229	99.58 86

Effi-MVS+-dtu		96.29 161	96.56 139	95.51 309	97.89 237	90.22 345	98.80 142	98.10 260	96.57 96	96.45 206	96.66 337	90.81 165	98.91 251	95.72 181	97.99 184	97.40 264

QAPM		96.29 161	95.40 183	98.96 65	97.85 238	97.60 77	99.23 32	98.93 52	89.76 363	93.11 318	99.02 106	89.11 204	99.93 28	91.99 298	99.62 78	99.34 121

Fast-Effi-MVS+		96.28 163	95.70 175	98.03 143	98.29 195	95.97 160	98.58 190	98.25 231	91.74 317	95.29 234	97.23 288	91.03 163	99.15 212	92.90 273	97.96 186	98.97 183

nrg030		96.28 163	95.72 170	97.96 149	96.90 312	98.15 57	99.39 10	98.31 217	95.47 142	94.42 258	98.35 186	92.09 132	98.69 275	97.50 112	89.05 348	97.04 274

1314		96.25 165	95.73 169	97.79 158	97.13 298	95.55 181	98.19 244	98.59 153	93.47 254	92.03 346	97.82 239	91.33 153	99.49 171	94.62 217	98.44 168	98.32 237

sd_testset		96.17 166	95.76 168	97.42 188	99.30 71	94.34 244	98.82 133	99.08 34	95.92 119	95.96 221	98.76 147	82.83 326	99.32 193	95.56 187	95.59 255	98.60 219

h-mvs33		96.17 166	95.62 179	97.81 157	99.03 115	94.45 237	98.64 181	98.75 112	97.48 39	98.67 83	98.72 150	89.76 183	99.86 68	97.95 75	81.59 394	99.11 165

HQP_MVS		96.14 168	95.90 164	96.85 226	97.42 276	94.60 233	98.80 142	98.56 163	97.28 52	95.34 230	98.28 195	87.09 253	99.03 231	96.07 165	94.27 263	96.92 282

tttt0517		96.07 169	95.51 181	97.78 159	98.41 176	94.84 218	99.28 24	94.33 403	94.26 207	97.64 155	98.64 157	84.05 315	99.47 178	95.34 193	97.60 200	99.03 177

MVSTER		96.06 170	95.72 170	97.08 210	98.23 199	95.93 166	98.73 159	98.27 226	94.86 180	95.07 236	98.09 211	88.21 228	98.54 289	96.59 150	93.46 286	96.79 300

thisisatest0530		96.01 171	95.36 188	97.97 147	98.38 178	95.52 183	98.88 115	94.19 405	94.04 212	97.64 155	98.31 193	83.82 322	99.46 179	95.29 197	97.70 197	98.93 188

test_djsdf		96.00 172	95.69 176	96.93 220	95.72 362	95.49 184	99.47 7	98.40 199	94.98 172	94.58 248	97.86 232	89.16 202	98.41 309	96.91 131	94.12 271	96.88 291

EI-MVSNet		95.96 173	95.83 166	96.36 272	97.93 233	93.70 267	98.12 254	98.27 226	93.70 240	95.07 236	99.02 106	92.23 126	98.54 289	94.68 213	93.46 286	96.84 297

ECVR-MVS		95.95 174	95.71 173	96.65 238	99.02 116	90.86 330	99.03 76	91.80 415	96.96 74	98.10 114	99.26 62	81.31 333	99.51 167	96.90 134	99.04 133	99.59 82

BH-untuned		95.95 174	95.72 170	96.65 238	98.55 167	92.26 303	98.23 237	97.79 288	93.73 235	94.62 247	98.01 218	88.97 211	99.00 237	93.04 268	98.51 164	98.68 210

test1111		95.94 176	95.78 167	96.41 269	98.99 122	90.12 346	99.04 73	92.45 414	96.99 73	98.03 121	99.27 61	81.40 332	99.48 176	96.87 140	99.04 133	99.63 76

MSDG		95.93 177	95.30 194	97.83 154	98.90 130	95.36 190	96.83 370	98.37 207	91.32 332	94.43 257	98.73 149	90.27 177	99.60 146	90.05 334	98.82 149	98.52 225

BH-RMVSNet		95.92 178	95.32 192	97.69 170	98.32 192	94.64 227	98.19 244	97.45 321	94.56 194	96.03 217	98.61 158	85.02 291	99.12 217	90.68 325	99.06 132	99.30 130

test_fmvs1_n		95.90 179	95.99 161	95.63 305	98.67 155	88.32 381	99.26 27	98.22 233	96.40 102	99.67 17	99.26 62	73.91 392	99.70 125	99.02 24	99.50 101	98.87 191

Fast-Effi-MVS+-dtu		95.87 180	95.85 165	95.91 293	97.74 247	91.74 314	98.69 170	98.15 250	95.56 138	94.92 239	97.68 252	88.98 210	98.79 269	93.19 263	97.78 193	97.20 271

LFMVS		95.86 181	94.98 209	98.47 103	98.87 135	96.32 144	98.84 129	96.02 382	93.40 257	98.62 89	99.20 73	74.99 386	99.63 140	97.72 91	97.20 207	99.46 107

baseline1		95.84 182	95.12 202	98.01 145	98.49 172	95.98 155	98.73 159	97.03 351	95.37 149	96.22 211	98.19 205	89.96 181	99.16 209	94.60 218	87.48 364	98.90 190

OpenMVS	93.04 13	95.83 183	95.00 207	98.32 116	97.18 295	97.32 90	99.21 39	98.97 44	89.96 359	91.14 355	99.05 104	86.64 261	99.92 35	93.38 257	99.47 106	97.73 254

VDD-MVS		95.82 184	95.23 196	97.61 179	98.84 139	93.98 255	98.68 172	97.40 325	95.02 170	97.95 129	99.34 53	74.37 391	99.78 107	98.64 35	96.80 218	99.08 171

UniMVSNet (Re)		95.78 185	95.19 198	97.58 180	96.99 305	97.47 84	98.79 149	99.18 27	95.60 136	93.92 283	97.04 309	91.68 141	98.48 293	95.80 178	87.66 363	96.79 300

VPA-MVSNet		95.75 186	95.11 203	97.69 170	97.24 287	97.27 93	98.94 98	99.23 21	95.13 161	95.51 228	97.32 281	85.73 278	98.91 251	97.33 119	89.55 339	96.89 290

HQP-MVS		95.72 187	95.40 183	96.69 236	97.20 291	94.25 249	98.05 263	98.46 187	96.43 99	94.45 253	97.73 244	86.75 259	98.96 242	95.30 195	94.18 267	96.86 296

hse-mvs2		95.71 188	95.30 194	96.93 220	98.50 170	93.53 272	98.36 219	98.10 260	97.48 39	98.67 83	97.99 220	89.76 183	99.02 234	97.95 75	80.91 399	98.22 240

UniMVSNet_NR-MVSNet		95.71 188	95.15 199	97.40 191	96.84 315	96.97 109	98.74 155	99.24 18	95.16 160	93.88 285	97.72 246	91.68 141	98.31 321	95.81 176	87.25 369	96.92 282

PatchmatchNet		95.71 188	95.52 180	96.29 278	97.58 260	90.72 334	96.84 369	97.52 311	94.06 211	97.08 171	96.96 319	89.24 200	98.90 254	92.03 297	98.37 172	99.26 138
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
OPM-MVS		95.69 191	95.33 191	96.76 231	96.16 348	94.63 228	98.43 215	98.39 201	96.64 92	95.02 238	98.78 140	85.15 290	99.05 227	95.21 201	94.20 266	96.60 323
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMM	93.85 9	95.69 191	95.38 187	96.61 245	97.61 257	93.84 259	98.91 105	98.44 191	95.25 156	94.28 265	98.47 174	86.04 275	99.12 217	95.50 190	93.95 276	96.87 294
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpmrst		95.63 193	95.69 176	95.44 313	97.54 265	88.54 376	96.97 355	97.56 303	93.50 252	97.52 161	96.93 323	89.49 189	99.16 209	95.25 199	96.42 231	98.64 216

FE-MVS		95.62 194	94.90 213	97.78 159	98.37 180	94.92 215	97.17 345	97.38 327	90.95 343	97.73 145	97.70 247	85.32 288	99.63 140	91.18 312	98.33 175	98.79 197

LPG-MVS_test		95.62 194	95.34 189	96.47 263	97.46 271	93.54 270	98.99 86	98.54 167	94.67 189	94.36 261	98.77 142	85.39 283	99.11 219	95.71 182	94.15 269	96.76 303

CLD-MVS		95.62 194	95.34 189	96.46 266	97.52 268	93.75 263	97.27 336	98.46 187	95.53 139	94.42 258	98.00 219	86.21 270	98.97 238	96.25 163	94.37 261	96.66 318
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		95.61 197	94.89 214	97.76 163	98.15 211	95.15 203	96.77 371	94.41 401	92.95 278	97.18 168	97.43 272	84.78 297	99.45 180	94.63 215	97.73 196	98.68 210

MonoMVSNet		95.51 198	95.45 182	95.68 302	95.54 367	90.87 329	98.92 103	97.37 328	95.79 127	95.53 227	97.38 277	89.58 188	97.68 364	96.40 157	92.59 301	98.49 227

thres600view7		95.49 199	94.77 217	97.67 173	98.98 123	95.02 207	98.85 125	96.90 360	95.38 147	96.63 193	96.90 324	84.29 307	99.59 147	88.65 356	96.33 233	98.40 231

test_vis1_n		95.47 200	95.13 200	96.49 260	97.77 243	90.41 342	99.27 26	98.11 257	96.58 94	99.66 18	99.18 79	67.00 405	99.62 144	99.21 19	99.40 116	99.44 110

SCA		95.46 201	95.13 200	96.46 266	97.67 252	91.29 322	97.33 331	97.60 299	94.68 188	96.92 181	97.10 294	83.97 317	98.89 255	92.59 281	98.32 177	99.20 147

IterMVS-LS		95.46 201	95.21 197	96.22 280	98.12 212	93.72 266	98.32 226	98.13 253	93.71 238	94.26 266	97.31 282	92.24 125	98.10 337	94.63 215	90.12 330	96.84 297
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
jajsoiax		95.45 203	95.03 206	96.73 232	95.42 375	94.63 228	99.14 54	98.52 172	95.74 129	93.22 311	98.36 185	83.87 320	98.65 280	96.95 130	94.04 272	96.91 287

CVMVSNet		95.43 204	96.04 158	93.57 361	97.93 233	83.62 399	98.12 254	98.59 153	95.68 133	96.56 197	99.02 106	87.51 246	97.51 372	93.56 255	97.44 203	99.60 80

anonymousdsp		95.42 205	94.91 212	96.94 219	95.10 379	95.90 169	99.14 54	98.41 197	93.75 232	93.16 314	97.46 268	87.50 248	98.41 309	95.63 186	94.03 273	96.50 342

DU-MVS		95.42 205	94.76 218	97.40 191	96.53 331	96.97 109	98.66 177	98.99 43	95.43 144	93.88 285	97.69 249	88.57 219	98.31 321	95.81 176	87.25 369	96.92 282

mvs_tets		95.41 207	95.00 207	96.65 238	95.58 366	94.42 239	99.00 83	98.55 165	95.73 131	93.21 312	98.38 183	83.45 324	98.63 281	97.09 124	94.00 274	96.91 287

thres100view900		95.38 208	94.70 222	97.41 189	98.98 123	94.92 215	98.87 118	96.90 360	95.38 147	96.61 195	96.88 325	84.29 307	99.56 153	88.11 359	96.29 237	97.76 251

thres400		95.38 208	94.62 226	97.65 177	98.94 128	94.98 211	98.68 172	96.93 358	95.33 150	96.55 199	96.53 343	84.23 311	99.56 153	88.11 359	96.29 237	98.40 231

BH-w/o		95.38 208	95.08 204	96.26 279	98.34 186	91.79 311	97.70 303	97.43 323	92.87 281	94.24 268	97.22 289	88.66 217	98.84 261	91.55 308	97.70 197	98.16 243

VDDNet		95.36 211	94.53 230	97.86 152	98.10 214	95.13 204	98.85 125	97.75 290	90.46 350	98.36 104	99.39 37	73.27 394	99.64 137	97.98 74	96.58 225	98.81 196

TAPA-MVS	93.98 7	95.35 212	94.56 229	97.74 165	99.13 106	94.83 220	98.33 222	98.64 143	86.62 385	96.29 210	98.61 158	94.00 101	99.29 196	80.00 400	99.41 113	99.09 167
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ACMP	93.49 10	95.34 213	94.98 209	96.43 268	97.67 252	93.48 274	98.73 159	98.44 191	94.94 178	92.53 334	98.53 168	84.50 306	99.14 214	95.48 191	94.00 274	96.66 318
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
COLMAP_ROB	93.27 12	95.33 214	94.87 215	96.71 233	99.29 76	93.24 288	98.58 190	98.11 257	89.92 360	93.57 297	99.10 92	86.37 268	99.79 104	90.78 323	98.10 182	97.09 272
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
UBG		95.32 215	94.72 221	97.13 205	98.05 220	93.26 285	97.87 286	97.20 339	94.96 174	96.18 213	95.66 374	80.97 338	99.35 189	94.47 224	97.08 209	98.78 200

tfpn200view9		95.32 215	94.62 226	97.43 187	98.94 128	94.98 211	98.68 172	96.93 358	95.33 150	96.55 199	96.53 343	84.23 311	99.56 153	88.11 359	96.29 237	97.76 251

Anonymous202405211		95.28 217	94.49 232	97.67 173	99.00 119	93.75 263	98.70 168	97.04 350	90.66 346	96.49 203	98.80 138	78.13 362	99.83 75	96.21 164	95.36 259	99.44 110

thres200		95.25 218	94.57 228	97.28 195	98.81 141	94.92 215	98.20 241	97.11 343	95.24 158	96.54 201	96.22 354	84.58 304	99.53 163	87.93 364	96.50 229	97.39 265

AllTest		95.24 219	94.65 225	96.99 214	99.25 84	93.21 289	98.59 188	98.18 241	91.36 328	93.52 299	98.77 142	84.67 301	99.72 119	89.70 341	97.87 189	98.02 246

LCM-MVSNet-Re		95.22 220	95.32 192	94.91 329	98.18 207	87.85 387	98.75 152	95.66 389	95.11 163	88.96 374	96.85 328	90.26 178	97.65 365	95.65 185	98.44 168	99.22 144

EPNet_dtu		95.21 221	94.95 211	95.99 288	96.17 346	90.45 340	98.16 250	97.27 335	96.77 82	93.14 317	98.33 191	90.34 174	98.42 302	85.57 377	98.81 150	99.09 167
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
XXY-MVS		95.20 222	94.45 237	97.46 184	96.75 321	96.56 131	98.86 121	98.65 142	93.30 262	93.27 310	98.27 198	84.85 295	98.87 258	94.82 210	91.26 317	96.96 278

D2MVS		95.18 223	95.08 204	95.48 310	97.10 300	92.07 307	98.30 229	99.13 32	94.02 214	92.90 322	96.73 334	89.48 190	98.73 273	94.48 223	93.60 285	95.65 370

WR-MVS		95.15 224	94.46 235	97.22 197	96.67 326	96.45 135	98.21 239	98.81 92	94.15 208	93.16 314	97.69 249	87.51 246	98.30 323	95.29 197	88.62 354	96.90 289

TranMVSNet+NR-MVSNet		95.14 225	94.48 233	97.11 208	96.45 336	96.36 142	99.03 76	99.03 39	95.04 168	93.58 296	97.93 225	88.27 227	98.03 343	94.13 235	86.90 374	96.95 280

baseline2		95.11 226	94.52 231	96.87 225	96.65 327	93.56 269	98.27 234	94.10 407	93.45 255	92.02 347	97.43 272	87.45 250	99.19 207	93.88 244	97.41 205	97.87 249

miper_enhance_ethall		95.10 227	94.75 219	96.12 284	97.53 267	93.73 265	96.61 377	98.08 265	92.20 308	93.89 284	96.65 339	92.44 118	98.30 323	94.21 233	91.16 318	96.34 351

Anonymous20240529		95.10 227	94.22 247	97.75 164	99.01 118	94.26 248	98.87 118	98.83 83	85.79 393	96.64 192	98.97 113	78.73 355	99.85 69	96.27 160	94.89 260	99.12 162

test-LLR		95.10 227	94.87 215	95.80 298	96.77 318	89.70 353	96.91 360	95.21 393	95.11 163	94.83 243	95.72 371	87.71 242	98.97 238	93.06 266	98.50 165	98.72 204

WR-MVS_H		95.05 230	94.46 235	96.81 229	96.86 314	95.82 172	99.24 30	99.24 18	93.87 226	92.53 334	96.84 329	90.37 173	98.24 329	93.24 261	87.93 360	96.38 350

miper_ehance_all_eth		95.01 231	94.69 223	95.97 290	97.70 250	93.31 283	97.02 353	98.07 267	92.23 305	93.51 301	96.96 319	91.85 138	98.15 333	93.68 249	91.16 318	96.44 348

testing11		95.00 232	94.28 244	97.16 203	97.96 230	93.36 282	98.09 259	97.06 349	94.94 178	95.33 233	96.15 356	76.89 376	99.40 184	95.77 180	96.30 236	98.72 204

ADS-MVSNet		95.00 232	94.45 237	96.63 242	98.00 224	91.91 310	96.04 384	97.74 291	90.15 356	96.47 204	96.64 340	87.89 238	98.96 242	90.08 332	97.06 210	99.02 178

VPNet		94.99 234	94.19 249	97.40 191	97.16 296	96.57 130	98.71 164	98.97 44	95.67 134	94.84 241	98.24 202	80.36 345	98.67 279	96.46 154	87.32 368	96.96 278

EPMVS		94.99 234	94.48 233	96.52 258	97.22 289	91.75 313	97.23 337	91.66 416	94.11 209	97.28 164	96.81 331	85.70 279	98.84 261	93.04 268	97.28 206	98.97 183

testing91		94.98 236	94.25 246	97.20 198	97.94 231	93.41 277	98.00 269	97.58 300	94.99 171	95.45 229	96.04 360	77.20 371	99.42 183	94.97 206	96.02 250	98.78 200

NR-MVSNet		94.98 236	94.16 252	97.44 186	96.53 331	97.22 100	98.74 155	98.95 48	94.96 174	89.25 373	97.69 249	89.32 197	98.18 331	94.59 220	87.40 366	96.92 282

FMVSNet3		94.97 238	94.26 245	97.11 208	98.18 207	96.62 124	98.56 197	98.26 230	93.67 245	94.09 275	97.10 294	84.25 309	98.01 344	92.08 293	92.14 304	96.70 312

CostFormer		94.95 239	94.73 220	95.60 307	97.28 285	89.06 366	97.53 315	96.89 362	89.66 365	96.82 186	96.72 335	86.05 273	98.95 247	95.53 189	96.13 248	98.79 197

PAPM		94.95 239	94.00 265	97.78 159	97.04 302	95.65 176	96.03 386	98.25 231	91.23 337	94.19 271	97.80 241	91.27 156	98.86 260	82.61 394	97.61 199	98.84 194

CP-MVSNet		94.94 241	94.30 243	96.83 227	96.72 323	95.56 179	99.11 60	98.95 48	93.89 224	92.42 339	97.90 228	87.19 252	98.12 336	94.32 229	88.21 357	96.82 299

TR-MVS		94.94 241	94.20 248	97.17 202	97.75 244	94.14 252	97.59 312	97.02 353	92.28 304	95.75 225	97.64 256	83.88 319	98.96 242	89.77 338	96.15 247	98.40 231

RPSCF		94.87 243	95.40 183	93.26 367	98.89 131	82.06 405	98.33 222	98.06 272	90.30 355	96.56 197	99.26 62	87.09 253	99.49 171	93.82 246	96.32 234	98.24 238

testing99		94.83 244	94.08 257	97.07 211	97.94 231	93.13 291	98.10 258	97.17 341	94.86 180	95.34 230	96.00 363	76.31 379	99.40 184	95.08 203	95.90 251	98.68 210

GA-MVS		94.81 245	94.03 261	97.14 204	97.15 297	93.86 258	96.76 372	97.58 300	94.00 218	94.76 246	97.04 309	80.91 339	98.48 293	91.79 303	96.25 243	99.09 167

c3_l		94.79 246	94.43 239	95.89 295	97.75 244	93.12 293	97.16 347	98.03 274	92.23 305	93.46 304	97.05 308	91.39 150	98.01 344	93.58 254	89.21 346	96.53 334

V42		94.78 247	94.14 254	96.70 235	96.33 341	95.22 199	98.97 89	98.09 264	92.32 302	94.31 264	97.06 305	88.39 225	98.55 288	92.90 273	88.87 352	96.34 351

reproduce_monomvs		94.77 248	94.67 224	95.08 325	98.40 177	89.48 359	98.80 142	98.64 143	97.57 34	93.21 312	97.65 253	80.57 344	98.83 264	97.72 91	89.47 342	96.93 281

CR-MVSNet		94.76 249	94.15 253	96.59 248	97.00 303	93.43 275	94.96 397	97.56 303	92.46 293	96.93 179	96.24 350	88.15 230	97.88 357	87.38 366	96.65 223	98.46 229

v2v482		94.69 250	94.03 261	96.65 238	96.17 346	94.79 223	98.67 175	98.08 265	92.72 285	94.00 280	97.16 292	87.69 245	98.45 298	92.91 272	88.87 352	96.72 308

pmmvs4		94.69 250	93.99 267	96.81 229	95.74 361	95.94 163	97.40 322	97.67 294	90.42 352	93.37 307	97.59 260	89.08 205	98.20 330	92.97 270	91.67 311	96.30 354

cl22		94.68 252	94.19 249	96.13 283	98.11 213	93.60 268	96.94 357	98.31 217	92.43 297	93.32 309	96.87 327	86.51 262	98.28 327	94.10 238	91.16 318	96.51 340

eth_miper_zixun_eth		94.68 252	94.41 240	95.47 311	97.64 255	91.71 315	96.73 374	98.07 267	92.71 286	93.64 294	97.21 290	90.54 171	98.17 332	93.38 257	89.76 334	96.54 332

PCF-MVS	93.45 11	94.68 252	93.43 303	98.42 111	98.62 162	96.77 119	95.48 394	98.20 236	84.63 398	93.34 308	98.32 192	88.55 222	99.81 87	84.80 386	98.96 139	98.68 210
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS		94.67 255	93.54 298	98.08 140	96.88 313	96.56 131	98.19 244	98.50 180	78.05 409	92.69 329	98.02 216	91.07 162	99.63 140	90.09 331	98.36 174	98.04 245

PS-CasMVS		94.67 255	93.99 267	96.71 233	96.68 325	95.26 196	99.13 57	99.03 39	93.68 243	92.33 340	97.95 224	85.35 285	98.10 337	93.59 253	88.16 359	96.79 300

cascas		94.63 257	93.86 277	96.93 220	96.91 311	94.27 247	96.00 387	98.51 175	85.55 394	94.54 249	96.23 352	84.20 313	98.87 258	95.80 178	96.98 215	97.66 257

tpmvs		94.60 258	94.36 242	95.33 317	97.46 271	88.60 375	96.88 366	97.68 292	91.29 334	93.80 290	96.42 347	88.58 218	99.24 201	91.06 318	96.04 249	98.17 242

LTVRE_ROB	92.95 15	94.60 258	93.90 273	96.68 237	97.41 279	94.42 239	98.52 200	98.59 153	91.69 320	91.21 354	98.35 186	84.87 294	99.04 230	91.06 318	93.44 289	96.60 323
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		94.59 260	93.92 270	96.60 247	96.21 343	94.78 224	98.59 188	98.14 252	91.86 316	94.21 270	97.02 312	87.97 236	98.41 309	91.72 305	89.57 337	96.61 322

ADS-MVSNet2		94.58 261	94.40 241	95.11 323	98.00 224	88.74 373	96.04 384	97.30 331	90.15 356	96.47 204	96.64 340	87.89 238	97.56 370	90.08 332	97.06 210	99.02 178

WBMVS		94.56 262	94.04 259	96.10 285	98.03 222	93.08 295	97.82 294	98.18 241	94.02 214	93.77 292	96.82 330	81.28 334	98.34 316	95.47 192	91.00 321	96.88 291

ACMH	92.88 16	94.55 263	93.95 269	96.34 274	97.63 256	93.26 285	98.81 141	98.49 185	93.43 256	89.74 368	98.53 168	81.91 329	99.08 225	93.69 248	93.30 292	96.70 312
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		94.54 264	93.85 278	96.63 242	97.98 228	93.06 296	98.77 151	97.84 286	93.67 245	93.80 290	98.04 215	76.88 377	98.96 242	94.79 212	92.86 297	97.86 250

XVG-ACMP-BASELINE		94.54 264	94.14 254	95.75 301	96.55 330	91.65 316	98.11 256	98.44 191	94.96 174	94.22 269	97.90 228	79.18 354	99.11 219	94.05 240	93.85 278	96.48 345

AUN-MVS		94.53 266	93.73 288	96.92 223	98.50 170	93.52 273	98.34 221	98.10 260	93.83 229	95.94 223	97.98 222	85.59 281	99.03 231	94.35 227	80.94 398	98.22 240

DIV-MVS_self_test		94.52 267	94.03 261	95.99 288	97.57 264	93.38 280	97.05 351	97.94 280	91.74 317	92.81 324	97.10 294	89.12 203	98.07 341	92.60 279	90.30 327	96.53 334

cl____		94.51 268	94.01 264	96.02 287	97.58 260	93.40 279	97.05 351	97.96 279	91.73 319	92.76 326	97.08 300	89.06 206	98.13 335	92.61 278	90.29 328	96.52 337

ETVMVS		94.50 269	93.44 302	97.68 172	98.18 207	95.35 192	98.19 244	97.11 343	93.73 235	96.40 207	95.39 377	74.53 388	98.84 261	91.10 314	96.31 235	98.84 194

GBi-Net		94.49 270	93.80 281	96.56 252	98.21 201	95.00 208	98.82 133	98.18 241	92.46 293	94.09 275	97.07 301	81.16 335	97.95 349	92.08 293	92.14 304	96.72 308

test1		94.49 270	93.80 281	96.56 252	98.21 201	95.00 208	98.82 133	98.18 241	92.46 293	94.09 275	97.07 301	81.16 335	97.95 349	92.08 293	92.14 304	96.72 308

dmvs_re		94.48 272	94.18 251	95.37 315	97.68 251	90.11 347	98.54 199	97.08 345	94.56 194	94.42 258	97.24 287	84.25 309	97.76 362	91.02 321	92.83 298	98.24 238

v8		94.47 273	93.77 284	96.57 251	96.36 339	94.83 220	99.05 69	98.19 238	91.92 313	93.16 314	96.97 317	88.82 216	98.48 293	91.69 306	87.79 361	96.39 349

FMVSNet2		94.47 273	93.61 294	97.04 212	98.21 201	96.43 137	98.79 149	98.27 226	92.46 293	93.50 302	97.09 298	81.16 335	98.00 346	91.09 315	91.93 307	96.70 312

test2506		94.44 275	93.91 272	96.04 286	99.02 116	88.99 369	99.06 67	79.47 428	96.96 74	98.36 104	99.26 62	77.21 370	99.52 166	96.78 147	99.04 133	99.59 82

Patchmatch-test		94.42 276	93.68 292	96.63 242	97.60 258	91.76 312	94.83 401	97.49 315	89.45 369	94.14 273	97.10 294	88.99 207	98.83 264	85.37 380	98.13 181	99.29 132

PEN-MVS		94.42 276	93.73 288	96.49 260	96.28 342	94.84 218	99.17 49	99.00 41	93.51 251	92.23 342	97.83 238	86.10 272	97.90 353	92.55 284	86.92 373	96.74 305

v144192		94.39 278	93.70 290	96.48 262	96.06 351	94.35 243	98.58 190	98.16 249	91.45 325	94.33 263	97.02 312	87.50 248	98.45 298	91.08 317	89.11 347	96.63 320

Baseline_NR-MVSNet		94.35 279	93.81 280	95.96 291	96.20 344	94.05 254	98.61 187	96.67 372	91.44 326	93.85 287	97.60 259	88.57 219	98.14 334	94.39 225	86.93 372	95.68 369

miper_lstm_enhance		94.33 280	94.07 258	95.11 323	97.75 244	90.97 326	97.22 338	98.03 274	91.67 321	92.76 326	96.97 317	90.03 180	97.78 361	92.51 286	89.64 336	96.56 329

v1192		94.32 281	93.58 295	96.53 257	96.10 349	94.45 237	98.50 206	98.17 247	91.54 323	94.19 271	97.06 305	86.95 257	98.43 301	90.14 330	89.57 337	96.70 312

UWE-MVS		94.30 282	93.89 275	95.53 308	97.83 239	88.95 370	97.52 317	93.25 409	94.44 202	96.63 193	97.07 301	78.70 356	99.28 197	91.99 298	97.56 202	98.36 234

ACMH+	92.99 14	94.30 282	93.77 284	95.88 296	97.81 241	92.04 309	98.71 164	98.37 207	93.99 219	90.60 361	98.47 174	80.86 341	99.05 227	92.75 277	92.40 303	96.55 331

v148		94.29 284	93.76 286	95.91 293	96.10 349	92.93 297	98.58 190	97.97 277	92.59 291	93.47 303	96.95 321	88.53 223	98.32 319	92.56 283	87.06 371	96.49 343

v10		94.29 284	93.55 297	96.51 259	96.39 338	94.80 222	98.99 86	98.19 238	91.35 330	93.02 320	96.99 315	88.09 232	98.41 309	90.50 327	88.41 356	96.33 353

MVP-Stereo		94.28 286	93.92 270	95.35 316	94.95 381	92.60 300	97.97 272	97.65 295	91.61 322	90.68 360	97.09 298	86.32 269	98.42 302	89.70 341	99.34 122	95.02 383
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UniMVSNet_ETH3D		94.24 287	93.33 305	96.97 217	97.19 294	93.38 280	98.74 155	98.57 160	91.21 339	93.81 289	98.58 163	72.85 395	98.77 271	95.05 204	93.93 277	98.77 203

OurMVSNet-221017-0		94.21 288	94.00 265	94.85 333	95.60 365	89.22 364	98.89 110	97.43 323	95.29 153	92.18 343	98.52 171	82.86 325	98.59 286	93.46 256	91.76 309	96.74 305

v1921920		94.20 289	93.47 301	96.40 271	95.98 354	94.08 253	98.52 200	98.15 250	91.33 331	94.25 267	97.20 291	86.41 267	98.42 302	90.04 335	89.39 344	96.69 317

WB-MVSnew		94.19 290	94.04 259	94.66 340	96.82 317	92.14 304	97.86 288	95.96 385	93.50 252	95.64 226	96.77 333	88.06 234	97.99 347	84.87 383	96.86 216	93.85 400

v7n		94.19 290	93.43 303	96.47 263	95.90 357	94.38 242	99.26 27	98.34 213	91.99 311	92.76 326	97.13 293	88.31 226	98.52 291	89.48 346	87.70 362	96.52 337

tpm2		94.19 290	93.76 286	95.46 312	97.23 288	89.04 367	97.31 333	96.85 366	87.08 384	96.21 212	96.79 332	83.75 323	98.74 272	92.43 289	96.23 245	98.59 221

TESTMET0.1,1		94.18 293	93.69 291	95.63 305	96.92 309	89.12 365	96.91 360	94.78 398	93.17 267	94.88 240	96.45 346	78.52 357	98.92 249	93.09 265	98.50 165	98.85 192

dp		94.15 294	93.90 273	94.90 330	97.31 284	86.82 392	96.97 355	97.19 340	91.22 338	96.02 218	96.61 342	85.51 282	99.02 234	90.00 336	94.30 262	98.85 192

ET-MVSNet_ETH3D		94.13 295	92.98 312	97.58 180	98.22 200	96.20 148	97.31 333	95.37 392	94.53 196	79.56 409	97.63 258	86.51 262	97.53 371	96.91 131	90.74 323	99.02 178

tpm		94.13 295	93.80 281	95.12 322	96.50 333	87.91 386	97.44 319	95.89 388	92.62 289	96.37 209	96.30 349	84.13 314	98.30 323	93.24 261	91.66 312	99.14 160

testing222		94.12 297	93.03 311	97.37 194	98.02 223	94.66 225	97.94 275	96.65 374	94.63 191	95.78 224	95.76 366	71.49 396	98.92 249	91.17 313	95.88 252	98.52 225

IterMVS-SCA-FT		94.11 298	93.87 276	94.85 333	97.98 228	90.56 339	97.18 343	98.11 257	93.75 232	92.58 332	97.48 267	83.97 317	97.41 374	92.48 288	91.30 315	96.58 325

Anonymous20231211		94.10 299	93.26 308	96.61 245	99.11 109	94.28 246	99.01 81	98.88 64	86.43 387	92.81 324	97.57 262	81.66 331	98.68 278	94.83 209	89.02 350	96.88 291

IterMVS		94.09 300	93.85 278	94.80 336	97.99 226	90.35 343	97.18 343	98.12 254	93.68 243	92.46 338	97.34 278	84.05 315	97.41 374	92.51 286	91.33 314	96.62 321
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test-mter		94.08 301	93.51 299	95.80 298	96.77 318	89.70 353	96.91 360	95.21 393	92.89 280	94.83 243	95.72 371	77.69 365	98.97 238	93.06 266	98.50 165	98.72 204

test0.0.03 1		94.08 301	93.51 299	95.80 298	95.53 369	92.89 298	97.38 324	95.97 384	95.11 163	92.51 336	96.66 337	87.71 242	96.94 381	87.03 368	93.67 281	97.57 261

v1240		94.06 303	93.29 307	96.34 274	96.03 353	93.90 257	98.44 213	98.17 247	91.18 340	94.13 274	97.01 314	86.05 273	98.42 302	89.13 351	89.50 341	96.70 312

X-MVStestdata		94.06 303	92.30 327	99.34 25	99.70 22	98.35 44	99.29 22	98.88 64	97.40 43	98.46 96	43.50 423	95.90 45	99.89 53	97.85 83	99.74 51	99.78 23

DTE-MVSNet		93.98 305	93.26 308	96.14 282	96.06 351	94.39 241	99.20 42	98.86 77	93.06 273	91.78 348	97.81 240	85.87 277	97.58 369	90.53 326	86.17 378	96.46 347

pm-mvs1		93.94 306	93.06 310	96.59 248	96.49 334	95.16 201	98.95 95	98.03 274	92.32 302	91.08 356	97.84 235	84.54 305	98.41 309	92.16 291	86.13 381	96.19 358

MS-PatchMatch		93.84 307	93.63 293	94.46 350	96.18 345	89.45 360	97.76 298	98.27 226	92.23 305	92.13 344	97.49 266	79.50 351	98.69 275	89.75 339	99.38 118	95.25 375

tfpnnormal		93.66 308	92.70 318	96.55 256	96.94 308	95.94 163	98.97 89	99.19 26	91.04 341	91.38 353	97.34 278	84.94 293	98.61 283	85.45 379	89.02 350	95.11 379

EU-MVSNet		93.66 308	94.14 254	92.25 377	95.96 356	83.38 401	98.52 200	98.12 254	94.69 187	92.61 331	98.13 209	87.36 251	96.39 393	91.82 302	90.00 332	96.98 277

our_test_3		93.65 310	93.30 306	94.69 338	95.45 373	89.68 355	96.91 360	97.65 295	91.97 312	91.66 351	96.88 325	89.67 187	97.93 352	88.02 362	91.49 313	96.48 345

pmmvs5		93.65 310	92.97 313	95.68 302	95.49 370	92.37 301	98.20 241	97.28 334	89.66 365	92.58 332	97.26 284	82.14 328	98.09 339	93.18 264	90.95 322	96.58 325

test_fmvs2		93.43 312	93.58 295	92.95 371	96.97 306	83.91 397	99.19 44	97.24 337	95.74 129	95.20 235	98.27 198	69.65 398	98.72 274	96.26 161	93.73 280	96.24 355

tpm cat1		93.36 313	92.80 315	95.07 326	97.58 260	87.97 385	96.76 372	97.86 285	82.17 405	93.53 298	96.04 360	86.13 271	99.13 215	89.24 349	95.87 253	98.10 244

JIA-IIPM		93.35 314	92.49 323	95.92 292	96.48 335	90.65 336	95.01 396	96.96 356	85.93 391	96.08 216	87.33 413	87.70 244	98.78 270	91.35 310	95.58 257	98.34 235

SixPastTwentyTwo		93.34 315	92.86 314	94.75 337	95.67 363	89.41 362	98.75 152	96.67 372	93.89 224	90.15 366	98.25 201	80.87 340	98.27 328	90.90 322	90.64 324	96.57 327

USDC		93.33 316	92.71 317	95.21 319	96.83 316	90.83 332	96.91 360	97.50 313	93.84 227	90.72 359	98.14 208	77.69 365	98.82 266	89.51 345	93.21 294	95.97 363

IB-MVS	91.98 17	93.27 317	91.97 331	97.19 200	97.47 270	93.41 277	97.09 350	95.99 383	93.32 260	92.47 337	95.73 369	78.06 363	99.53 163	94.59 220	82.98 389	98.62 217
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		93.26 318	92.21 328	96.41 269	97.73 248	93.13 291	95.65 391	97.03 351	91.27 336	94.04 278	96.06 359	75.33 384	97.19 377	86.56 370	96.23 245	98.92 189

ppachtmachnet_test		93.22 319	92.63 319	94.97 328	95.45 373	90.84 331	96.88 366	97.88 284	90.60 347	92.08 345	97.26 284	88.08 233	97.86 358	85.12 382	90.33 326	96.22 356

Patchmtry		93.22 319	92.35 326	95.84 297	96.77 318	93.09 294	94.66 404	97.56 303	87.37 383	92.90 322	96.24 350	88.15 230	97.90 353	87.37 367	90.10 331	96.53 334

testing3		93.19 321	92.48 324	95.30 318	98.07 215	92.27 302	98.64 181	97.17 341	93.94 223	93.98 281	97.04 309	67.97 402	96.01 397	88.40 357	97.14 208	97.63 258

FMVSNet1		93.19 321	92.07 329	96.56 252	97.54 265	95.00 208	98.82 133	98.18 241	90.38 353	92.27 341	97.07 301	73.68 393	97.95 349	89.36 348	91.30 315	96.72 308

LF4IMVS		93.14 323	92.79 316	94.20 354	95.88 358	88.67 374	97.66 306	97.07 347	93.81 230	91.71 349	97.65 253	77.96 364	98.81 267	91.47 309	91.92 308	95.12 378

mmtdpeth		93.12 324	92.61 320	94.63 342	97.60 258	89.68 355	99.21 39	97.32 330	94.02 214	97.72 146	94.42 388	77.01 375	99.44 181	99.05 22	77.18 410	94.78 388

testgi		93.06 325	92.45 325	94.88 332	96.43 337	89.90 348	98.75 152	97.54 309	95.60 136	91.63 352	97.91 227	74.46 390	97.02 379	86.10 373	93.67 281	97.72 255

PatchT		93.06 325	91.97 331	96.35 273	96.69 324	92.67 299	94.48 407	97.08 345	86.62 385	97.08 171	92.23 407	87.94 237	97.90 353	78.89 404	96.69 221	98.49 227

RPMNet		92.81 327	91.34 337	97.24 196	97.00 303	93.43 275	94.96 397	98.80 99	82.27 404	96.93 179	92.12 408	86.98 256	99.82 82	76.32 409	96.65 223	98.46 229

myMVS_eth3d		92.73 328	92.01 330	94.89 331	97.39 280	90.94 327	97.91 278	97.46 317	93.16 268	93.42 305	95.37 378	68.09 401	96.12 395	88.34 358	96.99 212	97.60 259

TransMVSNet (Re)		92.67 329	91.51 336	96.15 281	96.58 329	94.65 226	98.90 106	96.73 368	90.86 344	89.46 372	97.86 232	85.62 280	98.09 339	86.45 371	81.12 396	95.71 368

ttmdpeth		92.61 330	91.96 333	94.55 344	94.10 391	90.60 338	98.52 200	97.29 332	92.67 287	90.18 364	97.92 226	79.75 350	97.79 360	91.09 315	86.15 380	95.26 374

Syy-MVS		92.55 331	92.61 320	92.38 374	97.39 280	83.41 400	97.91 278	97.46 317	93.16 268	93.42 305	95.37 378	84.75 298	96.12 395	77.00 408	96.99 212	97.60 259

K. test v3		92.55 331	91.91 334	94.48 348	95.64 364	89.24 363	99.07 66	94.88 397	94.04 212	86.78 388	97.59 260	77.64 368	97.64 366	92.08 293	89.43 343	96.57 327

DSMNet-mixed		92.52 333	92.58 322	92.33 375	94.15 390	82.65 403	98.30 229	94.26 404	89.08 374	92.65 330	95.73 369	85.01 292	95.76 399	86.24 372	97.76 194	98.59 221

TinyColmap		92.31 334	91.53 335	94.65 341	96.92 309	89.75 351	96.92 358	96.68 371	90.45 351	89.62 369	97.85 234	76.06 382	98.81 267	86.74 369	92.51 302	95.41 372

gg-mvs-nofinetune		92.21 335	90.58 343	97.13 205	96.75 321	95.09 205	95.85 388	89.40 421	85.43 395	94.50 251	81.98 416	80.80 342	98.40 315	92.16 291	98.33 175	97.88 248

FMVSNet5		91.81 336	90.92 339	94.49 347	97.21 290	92.09 306	98.00 269	97.55 308	89.31 372	90.86 358	95.61 375	74.48 389	95.32 403	85.57 377	89.70 335	96.07 361

pmmvs6		91.77 337	90.63 342	95.17 321	94.69 387	91.24 323	98.67 175	97.92 282	86.14 389	89.62 369	97.56 264	75.79 383	98.34 316	90.75 324	84.56 383	95.94 364

Anonymous20231206		91.66 338	91.10 338	93.33 365	94.02 395	87.35 389	98.58 190	97.26 336	90.48 349	90.16 365	96.31 348	83.83 321	96.53 391	79.36 402	89.90 333	96.12 359

Patchmatch-RL test		91.49 339	90.85 340	93.41 363	91.37 406	84.40 395	92.81 411	95.93 387	91.87 315	87.25 384	94.87 384	88.99 207	96.53 391	92.54 285	82.00 391	99.30 130

test_0402		91.32 340	90.27 346	94.48 348	96.60 328	91.12 324	98.50 206	97.22 338	86.10 390	88.30 380	96.98 316	77.65 367	97.99 347	78.13 406	92.94 296	94.34 389

test_vis1_rt		91.29 341	90.65 341	93.19 369	97.45 274	86.25 393	98.57 196	90.90 419	93.30 262	86.94 387	93.59 397	62.07 411	99.11 219	97.48 113	95.58 257	94.22 392

PVSNet_0	88.72 19	91.28 342	90.03 349	95.00 327	97.99 226	87.29 390	94.84 400	98.50 180	92.06 310	89.86 367	95.19 380	79.81 349	99.39 187	92.27 290	69.79 416	98.33 236

mvs5depth		91.23 343	90.17 347	94.41 352	92.09 403	89.79 350	95.26 395	96.50 376	90.73 345	91.69 350	97.06 305	76.12 381	98.62 282	88.02 362	84.11 386	94.82 385

Anonymous20240521		91.18 344	90.44 344	93.42 362	93.70 396	88.47 378	98.94 98	97.56 303	88.46 378	89.56 371	95.08 383	77.15 373	96.97 380	83.92 389	89.55 339	94.82 385

EG-PatchMatch MVS		91.13 345	90.12 348	94.17 356	94.73 386	89.00 368	98.13 253	97.81 287	89.22 373	85.32 398	96.46 345	67.71 403	98.42 302	87.89 365	93.82 279	95.08 380

TDRefinement		91.06 346	89.68 351	95.21 319	85.35 421	91.49 319	98.51 205	97.07 347	91.47 324	88.83 378	97.84 235	77.31 369	99.09 224	92.79 276	77.98 408	95.04 382

UnsupCasMVSNet_eth		90.99 347	89.92 350	94.19 355	94.08 392	89.83 349	97.13 349	98.67 135	93.69 241	85.83 394	96.19 355	75.15 385	96.74 385	89.14 350	79.41 403	96.00 362

test20.03		90.89 348	90.38 345	92.43 373	93.48 397	88.14 384	98.33 222	97.56 303	93.40 257	87.96 381	96.71 336	80.69 343	94.13 408	79.15 403	86.17 378	95.01 384

MDA-MVSNet_test_wron		90.71 349	89.38 354	94.68 339	94.83 383	90.78 333	97.19 342	97.46 317	87.60 381	72.41 416	95.72 371	86.51 262	96.71 388	85.92 375	86.80 375	96.56 329

YYNet1		90.70 350	89.39 353	94.62 343	94.79 385	90.65 336	97.20 340	97.46 317	87.54 382	72.54 415	95.74 367	86.51 262	96.66 389	86.00 374	86.76 376	96.54 332

KD-MVS_self_test		90.38 351	89.38 354	93.40 364	92.85 400	88.94 371	97.95 273	97.94 280	90.35 354	90.25 363	93.96 394	79.82 348	95.94 398	84.62 388	76.69 411	95.33 373

pmmvs-eth3d		90.36 352	89.05 357	94.32 353	91.10 408	92.12 305	97.63 311	96.95 357	88.86 376	84.91 399	93.13 402	78.32 359	96.74 385	88.70 354	81.81 393	94.09 395

CL-MVSNet_self_test		90.11 353	89.14 356	93.02 370	91.86 405	88.23 383	96.51 380	98.07 267	90.49 348	90.49 362	94.41 389	84.75 298	95.34 402	80.79 398	74.95 413	95.50 371

new_pmnet		90.06 354	89.00 358	93.22 368	94.18 389	88.32 381	96.42 382	96.89 362	86.19 388	85.67 395	93.62 396	77.18 372	97.10 378	81.61 396	89.29 345	94.23 391

MDA-MVSNet-bldmvs		89.97 355	88.35 361	94.83 335	95.21 377	91.34 320	97.64 308	97.51 312	88.36 379	71.17 417	96.13 357	79.22 353	96.63 390	83.65 390	86.27 377	96.52 337

CMPMVS	66.06 21	89.70 356	89.67 352	89.78 382	93.19 398	76.56 408	97.00 354	98.35 210	80.97 406	81.57 404	97.75 243	74.75 387	98.61 283	89.85 337	93.63 283	94.17 393
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet1		89.67 357	88.28 362	93.82 359	92.81 401	91.08 325	98.01 267	97.45 321	87.95 380	87.90 382	95.87 365	67.63 404	94.56 407	78.73 405	88.18 358	95.83 366

KD-MVS_2432*1600		89.61 358	87.96 366	94.54 345	94.06 393	91.59 317	95.59 392	97.63 297	89.87 361	88.95 375	94.38 391	78.28 360	96.82 383	84.83 384	68.05 417	95.21 376

miper_refine_blended		89.61 358	87.96 366	94.54 345	94.06 393	91.59 317	95.59 392	97.63 297	89.87 361	88.95 375	94.38 391	78.28 360	96.82 383	84.83 384	68.05 417	95.21 376

MVStest1		89.53 360	87.99 365	94.14 358	94.39 388	90.42 341	98.25 236	96.84 367	82.81 401	81.18 406	97.33 280	77.09 374	96.94 381	85.27 381	78.79 404	95.06 381

MVS-HIRNet		89.46 361	88.40 360	92.64 372	97.58 260	82.15 404	94.16 410	93.05 413	75.73 412	90.90 357	82.52 415	79.42 352	98.33 318	83.53 391	98.68 152	97.43 262

OpenMVS_ROB	86.42 20	89.00 362	87.43 370	93.69 360	93.08 399	89.42 361	97.91 278	96.89 362	78.58 408	85.86 393	94.69 385	69.48 399	98.29 326	77.13 407	93.29 293	93.36 402

mvsany_test3		88.80 363	88.04 363	91.09 381	89.78 411	81.57 406	97.83 293	95.49 391	93.81 230	87.53 383	93.95 395	56.14 414	97.43 373	94.68 213	83.13 388	94.26 390

new-patchmatchnet		88.50 364	87.45 369	91.67 379	90.31 410	85.89 394	97.16 347	97.33 329	89.47 368	83.63 401	92.77 404	76.38 378	95.06 405	82.70 393	77.29 409	94.06 397

APD_test1		88.22 365	88.01 364	88.86 384	95.98 354	74.66 416	97.21 339	96.44 378	83.96 400	86.66 390	97.90 228	60.95 412	97.84 359	82.73 392	90.23 329	94.09 395

PM-MVS		87.77 366	86.55 372	91.40 380	91.03 409	83.36 402	96.92 358	95.18 395	91.28 335	86.48 392	93.42 398	53.27 415	96.74 385	89.43 347	81.97 392	94.11 394

dmvs_testset		87.64 367	88.93 359	83.79 393	95.25 376	63.36 425	97.20 340	91.17 417	93.07 272	85.64 396	95.98 364	85.30 289	91.52 415	69.42 414	87.33 367	96.49 343

test_fmvs3		87.17 368	87.06 371	87.50 386	91.21 407	75.66 411	99.05 69	96.61 375	92.79 284	88.85 377	92.78 403	43.72 418	93.49 409	93.95 241	84.56 383	93.34 403

UnsupCasMVSNet_bld		87.17 368	85.12 375	93.31 366	91.94 404	88.77 372	94.92 399	98.30 223	84.30 399	82.30 402	90.04 410	63.96 409	97.25 376	85.85 376	74.47 415	93.93 399

N_pmnet		87.12 370	87.77 368	85.17 390	95.46 372	61.92 426	97.37 326	70.66 431	85.83 392	88.73 379	96.04 360	85.33 287	97.76 362	80.02 399	90.48 325	95.84 365

pmmvs3		86.67 371	84.86 376	92.11 378	88.16 415	87.19 391	96.63 376	94.75 399	79.88 407	87.22 385	92.75 405	66.56 406	95.20 404	81.24 397	76.56 412	93.96 398

test_f		86.07 372	85.39 373	88.10 385	89.28 413	75.57 412	97.73 301	96.33 380	89.41 371	85.35 397	91.56 409	43.31 420	95.53 400	91.32 311	84.23 385	93.21 404

WB-MVS		84.86 373	85.33 374	83.46 394	89.48 412	69.56 420	98.19 244	96.42 379	89.55 367	81.79 403	94.67 386	84.80 296	90.12 416	52.44 420	80.64 400	90.69 407

SSC-MVS		84.27 374	84.71 377	82.96 398	89.19 414	68.83 421	98.08 260	96.30 381	89.04 375	81.37 405	94.47 387	84.60 303	89.89 417	49.80 422	79.52 402	90.15 408

dongtai		82.47 375	81.88 378	84.22 392	95.19 378	76.03 409	94.59 406	74.14 430	82.63 402	87.19 386	96.09 358	64.10 408	87.85 420	58.91 418	84.11 386	88.78 412

test_vis3_rt		79.22 376	77.40 383	84.67 391	86.44 419	74.85 415	97.66 306	81.43 426	84.98 396	67.12 419	81.91 417	28.09 428	97.60 367	88.96 352	80.04 401	81.55 417

test_method		79.03 377	78.17 379	81.63 399	86.06 420	54.40 431	82.75 419	96.89 362	39.54 423	80.98 407	95.57 376	58.37 413	94.73 406	84.74 387	78.61 405	95.75 367

testf1		79.02 378	77.70 380	82.99 396	88.10 416	66.90 422	94.67 402	93.11 410	71.08 414	74.02 412	93.41 399	34.15 424	93.25 410	72.25 412	78.50 406	88.82 410

APD_test2		79.02 378	77.70 380	82.99 396	88.10 416	66.90 422	94.67 402	93.11 410	71.08 414	74.02 412	93.41 399	34.15 424	93.25 410	72.25 412	78.50 406	88.82 410

LCM-MVSNet		78.70 380	76.24 386	86.08 388	77.26 427	71.99 418	94.34 408	96.72 369	61.62 418	76.53 410	89.33 411	33.91 426	92.78 413	81.85 395	74.60 414	93.46 401

kuosan		78.45 381	77.69 382	80.72 400	92.73 402	75.32 413	94.63 405	74.51 429	75.96 410	80.87 408	93.19 401	63.23 410	79.99 424	42.56 424	81.56 395	86.85 416

Gipuma		78.40 382	76.75 385	83.38 395	95.54 367	80.43 407	79.42 420	97.40 325	64.67 417	73.46 414	80.82 418	45.65 417	93.14 412	66.32 416	87.43 365	76.56 420
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		77.95 383	75.44 387	85.46 389	82.54 422	74.95 414	94.23 409	93.08 412	72.80 413	74.68 411	87.38 412	36.36 423	91.56 414	73.95 410	63.94 419	89.87 409

FPMVS		77.62 384	77.14 384	79.05 402	79.25 425	60.97 427	95.79 389	95.94 386	65.96 416	67.93 418	94.40 390	37.73 422	88.88 419	68.83 415	88.46 355	87.29 413

EGC-MVSNET		75.22 385	69.54 388	92.28 376	94.81 384	89.58 357	97.64 308	96.50 376	1.82 428	5.57 429	95.74 367	68.21 400	96.26 394	73.80 411	91.71 310	90.99 406

ANet_high		69.08 386	65.37 390	80.22 401	65.99 429	71.96 419	90.91 415	90.09 420	82.62 403	49.93 424	78.39 419	29.36 427	81.75 421	62.49 417	38.52 423	86.95 415

tmp_tt		68.90 387	66.97 389	74.68 404	50.78 431	59.95 428	87.13 416	83.47 425	38.80 424	62.21 420	96.23 352	64.70 407	76.91 426	88.91 353	30.49 424	87.19 414

PMVS	61.03 23	65.95 388	63.57 392	73.09 405	57.90 430	51.22 432	85.05 418	93.93 408	54.45 419	44.32 425	83.57 414	13.22 429	89.15 418	58.68 419	81.00 397	78.91 419
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		64.94 389	64.25 391	67.02 406	82.28 423	59.36 429	91.83 414	85.63 423	52.69 420	60.22 421	77.28 420	41.06 421	80.12 423	46.15 423	41.14 421	61.57 422

EMVS		64.07 390	63.26 393	66.53 407	81.73 424	58.81 430	91.85 413	84.75 424	51.93 422	59.09 422	75.13 421	43.32 419	79.09 425	42.03 425	39.47 422	61.69 421

MVE	62.14 22	63.28 391	59.38 394	74.99 403	74.33 428	65.47 424	85.55 417	80.50 427	52.02 421	51.10 423	75.00 422	10.91 432	80.50 422	51.60 421	53.40 420	78.99 418
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		30.17 392	30.18 396	30.16 408	78.61 426	43.29 433	66.79 421	14.21 432	17.31 425	14.82 428	11.93 428	11.55 431	41.43 427	37.08 426	19.30 425	5.76 425

cdsmvs_eth3d_5k		23.98 393	31.98 395	0.00 411	0.00 434	0.00 436	0.00 422	98.59 153	0.00 429	0.00 430	98.61 158	90.60 170	0.00 430	0.00 429	0.00 428	0.00 426

testmvs		21.48 394	24.95 397	11.09 410	14.89 432	6.47 435	96.56 378	9.87 433	7.55 426	17.93 426	39.02 424	9.43 433	5.90 429	16.56 428	12.72 426	20.91 424

test123		20.95 395	23.72 398	12.64 409	13.54 433	8.19 434	96.55 379	6.13 434	7.48 427	16.74 427	37.98 425	12.97 430	6.05 428	16.69 427	5.43 427	23.68 423

ab-mvs-re		8.20 396	10.94 399	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	98.43 176	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

pcd_1.5k_mvsjas		7.88 397	10.50 400	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	94.51 87	0.00 430	0.00 429	0.00 428	0.00 426

mmdepth		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

monomultidepth		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

test_blank		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

uanet_test		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

DCPMVS		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

sosnet-low-res		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

sosnet		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

uncertanet		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

Regformer		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

uanet		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

WAC-MVS						90.94 327								88.66 355

FOURS1					99.82 1	98.66 24	99.69 1	98.95 48	97.46 41	99.39 33

MSC_two_6792asdad				99.62 6	99.17 99	99.08 11		98.63 146					99.94 9	98.53 41	99.80 24	99.86 7

PC_three_1452									95.08 167	99.60 22	99.16 83	97.86 2	98.47 296	97.52 111	99.72 58	99.74 39

No_MVS				99.62 6	99.17 99	99.08 11		98.63 146					99.94 9	98.53 41	99.80 24	99.86 7

test_one_0601					99.66 26	99.25 2		98.86 77	97.55 35	99.20 45	99.47 26	97.57 6

eth-test2					0.00 434

eth-test					0.00 434

ZD-MVS					99.46 52	98.70 23		98.79 104	93.21 265	98.67 83	98.97 113	95.70 49	99.83 75	96.07 165	99.58 86

RE-MVS-def			98.34 40		99.49 46	97.86 68	99.11 60	98.80 99	96.49 97	99.17 48	99.35 49	95.29 65		97.72 91	99.65 71	99.71 52

IU-MVS					99.71 19	99.23 7		98.64 143	95.28 154	99.63 21				98.35 58	99.81 15	99.83 12

OPU-MVS				99.37 22	99.24 91	99.05 14	99.02 79				99.16 83	97.81 3	99.37 188	97.24 120	99.73 54	99.70 56

test_241102_TWO								98.87 71	97.65 28	99.53 26	99.48 24	97.34 11	99.94 9	98.43 53	99.80 24	99.83 12

test_241102_ONE					99.71 19	99.24 5		98.87 71	97.62 30	99.73 13	99.39 37	97.53 7	99.74 117

9.14			98.06 65		99.47 50		98.71 164	98.82 86	94.36 204	99.16 51	99.29 58	96.05 37	99.81 87	97.00 126	99.71 60

save fliter					99.46 52	98.38 35	98.21 239	98.71 122	97.95 19

test_0728_THIRD									97.32 49	99.45 28	99.46 30	97.88 1	99.94 9	98.47 49	99.86 2	99.85 9

test_0728_SECOND				99.71 1	99.72 12	99.35 1	98.97 89	98.88 64					99.94 9	98.47 49	99.81 15	99.84 11

test0726					99.72 12	99.25 2	99.06 67	98.88 64	97.62 30	99.56 23	99.50 21	97.42 9

GSMVS																99.20 147

test_part2					99.63 29	99.18 10				99.27 42

sam_mvs1												89.45 193				99.20 147

sam_mvs												88.99 207

ambc				89.49 383	86.66 418	75.78 410	92.66 412	96.72 369		86.55 391	92.50 406	46.01 416	97.90 353	90.32 328	82.09 390	94.80 387

MTGPA								98.74 114

test_post1							96.68 375				30.43 427	87.85 241	98.69 275	92.59 281

test_post											31.83 426	88.83 214	98.91 251

patchmatchnet-post											95.10 382	89.42 194	98.89 255

GG-mvs-BLEND				96.59 248	96.34 340	94.98 211	96.51 380	88.58 422		93.10 319	94.34 393	80.34 347	98.05 342	89.53 344	96.99 212	96.74 305

MTMP							98.89 110	94.14 406

gm-plane-assit					95.88 358	87.47 388			89.74 364		96.94 322		99.19 207	93.32 260

test9_res														96.39 159	99.57 87	99.69 59

TEST9					99.31 67	98.50 29	97.92 276	98.73 117	92.63 288	97.74 143	98.68 153	96.20 32	99.80 94

test_8					99.29 76	98.44 31	97.89 284	98.72 119	92.98 276	97.70 148	98.66 156	96.20 32	99.80 94

agg_prior2														95.87 175	99.57 87	99.68 64

agg_prior					99.30 71	98.38 35		98.72 119		97.57 160			99.81 87

TestCases				96.99 214	99.25 84	93.21 289		98.18 241	91.36 328	93.52 299	98.77 142	84.67 301	99.72 119	89.70 341	97.87 189	98.02 246

test_prior4						98.01 64	97.86 288

test_prior2							97.80 295		96.12 114	97.89 136	98.69 152	95.96 41		96.89 135	99.60 81

test_prior				99.19 43	99.31 67	98.22 51		98.84 81					99.70 125			99.65 72

旧先验2							97.57 314		91.30 333	98.67 83			99.80 94	95.70 184

新几何2							97.64 308

新几何1				99.16 48	99.34 60	98.01 64		98.69 127	90.06 358	98.13 112	98.95 120	94.60 85	99.89 53	91.97 300	99.47 106	99.59 82

旧先验1					99.29 76	97.48 82		98.70 126			99.09 99	95.56 52			99.47 106	99.61 78

无先验							97.58 313	98.72 119	91.38 327				99.87 64	93.36 259		99.60 80

原ACMM2							97.67 305

原ACMM1				98.65 85	99.32 65	96.62 124		98.67 135	93.27 264	97.81 138	98.97 113	95.18 72	99.83 75	93.84 245	99.46 109	99.50 94

test222					99.23 92	97.17 102	97.40 322	98.66 138	88.68 377	98.05 118	98.96 118	94.14 98			99.53 98	99.61 78

testdata2													99.89 53	91.65 307

segment_acmp												96.85 14

testdata				98.26 122	99.20 97	95.36 190		98.68 130	91.89 314	98.60 91	99.10 92	94.44 92	99.82 82	94.27 231	99.44 110	99.58 86

testdata1							97.32 332		96.34 105

test12				99.18 45	99.16 103	98.19 53		98.53 169		98.07 116		95.13 75	99.72 119		99.56 93	99.63 76

plane_prior7					97.42 276	94.63 228

plane_prior6					97.35 283	94.61 231						87.09 253

plane_prior5								98.56 163					99.03 231	96.07 165	94.27 263	96.92 282

plane_prior4											98.28 195

plane_prior3						94.61 231			97.02 71	95.34 230

plane_prior2							98.80 142		97.28 52

plane_prior1					97.37 282

plane_prior						94.60 233	98.44 213		96.74 85						94.22 265

n2								0.00 435

nn								0.00 435

door-mid								94.37 402

lessismore_v0				94.45 351	94.93 382	88.44 379		91.03 418		86.77 389	97.64 256	76.23 380	98.42 302	90.31 329	85.64 382	96.51 340

LGP-MVS_train				96.47 263	97.46 271	93.54 270		98.54 167	94.67 189	94.36 261	98.77 142	85.39 283	99.11 219	95.71 182	94.15 269	96.76 303

test11								98.66 138

door								94.64 400

HQP5-MVS						94.25 249

HQP-NCC					97.20 291		98.05 263		96.43 99	94.45 253

ACMP_Plane					97.20 291		98.05 263		96.43 99	94.45 253

BP-MVS														95.30 195

HQP4-MVS										94.45 253			98.96 242			96.87 294

HQP3-MVS								98.46 187							94.18 267

HQP2-MVS												86.75 259

NP-MVS					97.28 285	94.51 236					97.73 244

MDTV_nov1_ep13_2view						84.26 396	96.89 365		90.97 342	97.90 135		89.89 182		93.91 243		99.18 156

MDTV_nov1_ep13			95.40 183		97.48 269	88.34 380	96.85 368	97.29 332	93.74 234	97.48 162	97.26 284	89.18 201	99.05 227	91.92 301	97.43 204

ACMMP++_ref															92.97 295

ACMMP++															93.61 284

Test By Simon												94.64 84

ITE_SJBPF				95.44 313	97.42 276	91.32 321		97.50 313	95.09 166	93.59 295	98.35 186	81.70 330	98.88 257	89.71 340	93.39 290	96.12 359

DeepMVS_CX				86.78 387	97.09 301	72.30 417		95.17 396	75.92 411	84.34 400	95.19 380	70.58 397	95.35 401	79.98 401	89.04 349	92.68 405

High-resolution multi-view benchmark