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.

SED-MVS		99.09 1	98.91 2	99.63 4	99.71 19	99.24 5	99.02 74	98.87 67	97.65 20	99.73 8	99.48 18	97.53 7	99.94 6	98.43 40	99.81 12	99.70 51

DVP-MVS++		99.08 2	98.89 3	99.64 3	99.17 92	99.23 7	99.69 1	98.88 60	97.32 40	99.53 21	99.47 20	97.81 3	99.94 6	98.47 36	99.72 49	99.74 35

DVP-MVS		99.03 3	98.83 7	99.63 4	99.72 12	99.25 2	98.97 84	98.58 147	97.62 22	99.45 23	99.46 24	97.42 9	99.94 6	98.47 36	99.81 12	99.69 54
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 4	98.84 6	99.55 9	99.57 33	98.96 16	99.39 12	98.93 48	97.38 37	99.41 26	99.54 8	96.66 17	99.84 65	98.86 19	99.85 5	99.87 5
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test_fmvsmconf_n		98.92 5	98.87 4	99.04 53	98.88 123	97.25 86	98.82 124	99.34 10	98.75 3	99.80 3	99.61 4	95.16 66	99.95 5	99.70 4	99.80 19	99.93 1

DPE-MVS		98.92 5	98.67 10	99.65 2	99.58 32	99.20 9	98.42 201	98.91 54	97.58 25	99.54 20	99.46 24	97.10 12	99.94 6	97.64 85	99.84 10	99.83 11
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SteuartSystems-ACMMP		98.90 7	98.75 8	99.36 21	99.22 87	98.43 33	99.10 58	98.87 67	97.38 37	99.35 30	99.40 29	97.78 5	99.87 56	97.77 75	99.85 5	99.78 19
Skip Steuart: Steuart Systems R&D Blog.
test_fmvsm_n_1920		98.87 8	99.01 1	98.45 91	99.42 54	96.43 124	98.96 89	99.36 9	98.63 5	99.86 2	99.51 13	95.91 37	99.97 1	99.72 3	99.75 40	98.94 172

TSAR-MVS + MP.		98.78 9	98.62 11	99.24 36	99.69 24	98.28 45	99.14 49	98.66 129	96.84 69	99.56 18	99.31 49	96.34 23	99.70 117	98.32 46	99.73 46	99.73 40
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 9	98.56 14	99.45 15	99.32 60	98.87 19	98.47 193	98.81 84	97.72 15	98.76 66	99.16 75	97.05 13	99.78 99	98.06 55	99.66 59	99.69 54

MSP-MVS		98.74 11	98.55 15	99.29 29	99.75 3	98.23 46	99.26 27	98.88 60	97.52 27	99.41 26	98.78 128	96.00 33	99.79 96	97.79 74	99.59 74	99.85 8
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 12	98.49 19	99.34 23	99.70 22	98.35 41	99.29 22	98.88 60	97.40 34	98.46 84	99.20 65	95.90 39	99.89 45	97.85 69	99.74 44	99.78 19

MCST-MVS		98.65 13	98.37 27	99.48 13	99.60 31	98.87 19	98.41 202	98.68 121	97.04 61	98.52 83	98.80 126	96.78 16	99.83 67	97.93 62	99.61 70	99.74 35

SD-MVS		98.64 14	98.68 9	98.53 83	99.33 57	98.36 40	98.90 99	98.85 76	97.28 43	99.72 10	99.39 30	96.63 19	97.60 341	98.17 50	99.85 5	99.64 69
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 15	98.40 24	99.32 28	99.72 12	98.29 44	99.23 31	98.96 43	96.10 102	98.94 51	99.17 72	96.06 30	99.92 29	97.62 86	99.78 28	99.75 33

ACMMP_NAP		98.61 16	98.30 39	99.55 9	99.62 30	98.95 17	98.82 124	98.81 84	95.80 116	99.16 42	99.47 20	95.37 54	99.92 29	97.89 66	99.75 40	99.79 17

region2R		98.61 16	98.38 26	99.29 29	99.74 7	98.16 51	99.23 31	98.93 48	96.15 99	98.94 51	99.17 72	95.91 37	99.94 6	97.55 93	99.79 24	99.78 19

NCCC		98.61 16	98.35 30	99.38 18	99.28 75	98.61 26	98.45 194	98.76 102	97.82 14	98.45 87	98.93 112	96.65 18	99.83 67	97.38 102	99.41 104	99.71 47

SF-MVS		98.59 19	98.32 38	99.41 17	99.54 35	98.71 22	99.04 68	98.81 84	95.12 151	99.32 31	99.39 30	96.22 24	99.84 65	97.72 78	99.73 46	99.67 63

ACMMPR		98.59 19	98.36 28	99.29 29	99.74 7	98.15 52	99.23 31	98.95 44	96.10 102	98.93 55	99.19 70	95.70 43	99.94 6	97.62 86	99.79 24	99.78 19

test_fmvsmconf0.1_n		98.58 21	98.44 22	98.99 55	97.73 223	97.15 91	98.84 120	98.97 40	98.75 3	99.43 25	99.54 8	93.29 100	99.93 23	99.64 7	99.79 24	99.89 4

SMA-MVS		98.58 21	98.25 42	99.56 8	99.51 39	99.04 15	98.95 90	98.80 91	93.67 222	99.37 29	99.52 11	96.52 21	99.89 45	98.06 55	99.81 12	99.76 32
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 21	98.29 40	99.46 14	99.76 2	98.64 25	98.90 99	98.74 106	97.27 47	98.02 109	99.39 30	94.81 75	99.96 4	97.91 64	99.79 24	99.77 25

HPM-MVS++		98.58 21	98.25 42	99.55 9	99.50 41	99.08 11	98.72 152	98.66 129	97.51 28	98.15 98	98.83 123	95.70 43	99.92 29	97.53 95	99.67 57	99.66 66

SR-MVS		98.57 25	98.35 30	99.24 36	99.53 36	98.18 49	99.09 59	98.82 79	96.58 81	99.10 44	99.32 47	95.39 52	99.82 74	97.70 82	99.63 67	99.72 43

CP-MVS		98.57 25	98.36 28	99.19 40	99.66 26	97.86 62	99.34 18	98.87 67	95.96 107	98.60 79	99.13 80	96.05 31	99.94 6	97.77 75	99.86 1	99.77 25

MSLP-MVS++		98.56 27	98.57 13	98.55 79	99.26 78	96.80 103	98.71 153	99.05 34	97.28 43	98.84 60	99.28 52	96.47 22	99.40 166	98.52 34	99.70 52	99.47 98

DeepC-MVS_fast	96.70 1	98.55 28	98.34 33	99.18 42	99.25 79	98.04 57	98.50 190	98.78 98	97.72 15	98.92 57	99.28 52	95.27 60	99.82 74	97.55 93	99.77 30	99.69 54
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 29	98.35 30	99.13 47	99.49 45	97.86 62	99.11 55	98.80 91	96.49 84	99.17 39	99.35 42	95.34 56	99.82 74	97.72 78	99.65 62	99.71 47

APD-MVS_3200maxsize		98.53 30	98.33 37	99.15 46	99.50 41	97.92 61	99.15 47	98.81 84	96.24 95	99.20 36	99.37 36	95.30 58	99.80 86	97.73 77	99.67 57	99.72 43

mPP-MVS		98.51 31	98.26 41	99.25 35	99.75 3	98.04 57	99.28 24	98.81 84	96.24 95	98.35 94	99.23 60	95.46 49	99.94 6	97.42 100	99.81 12	99.77 25

ZNCC-MVS		98.49 32	98.20 49	99.35 22	99.73 11	98.39 34	99.19 42	98.86 73	95.77 117	98.31 97	99.10 84	95.46 49	99.93 23	97.57 92	99.81 12	99.74 35

CS-MVS-test		98.49 32	98.50 18	98.46 90	99.20 90	97.05 93	99.64 4	98.50 167	97.45 33	98.88 58	99.14 79	95.25 62	99.15 189	98.83 20	99.56 84	99.20 137

PGM-MVS		98.49 32	98.23 45	99.27 34	99.72 12	98.08 56	98.99 81	99.49 5	95.43 133	99.03 45	99.32 47	95.56 46	99.94 6	96.80 131	99.77 30	99.78 19

MVS_0304		98.47 35	98.22 47	99.21 39	99.00 111	97.80 67	98.88 107	95.32 366	98.86 2	98.53 82	99.44 27	94.38 85	99.94 6	99.86 1	99.70 52	99.90 3

EI-MVSNet-Vis-set		98.47 35	98.39 25	98.69 70	99.46 49	96.49 121	98.30 213	98.69 118	97.21 50	98.84 60	99.36 40	95.41 51	99.78 99	98.62 24	99.65 62	99.80 16

MVS_111021_HR		98.47 35	98.34 33	98.88 64	99.22 87	97.32 79	97.91 256	99.58 3	97.20 51	98.33 95	99.00 101	95.99 34	99.64 129	98.05 57	99.76 36	99.69 54

test_fmvsmvis_n_1920		98.44 38	98.51 16	98.23 111	98.33 175	96.15 139	98.97 84	99.15 26	98.55 7	98.45 87	99.55 6	94.26 89	99.97 1	99.65 5	99.66 59	98.57 202

CS-MVS		98.44 38	98.49 19	98.31 103	99.08 104	96.73 107	99.67 3	98.47 173	97.17 53	98.94 51	99.10 84	95.73 42	99.13 192	98.71 22	99.49 94	99.09 155

GST-MVS		98.43 40	98.12 52	99.34 23	99.72 12	98.38 35	99.09 59	98.82 79	95.71 121	98.73 69	99.06 94	95.27 60	99.93 23	97.07 111	99.63 67	99.72 43

fmvsm_s_conf0.5_n		98.42 41	98.51 16	98.13 120	99.30 66	95.25 185	98.85 116	99.39 7	97.94 12	99.74 7	99.62 3	92.59 108	99.91 37	99.65 5	99.52 90	99.25 131

EI-MVSNet-UG-set		98.41 42	98.34 33	98.61 75	99.45 52	96.32 132	98.28 216	98.68 121	97.17 53	98.74 67	99.37 36	95.25 62	99.79 96	98.57 25	99.54 87	99.73 40

DELS-MVS		98.40 43	98.20 49	98.99 55	99.00 111	97.66 68	97.75 274	98.89 57	97.71 17	98.33 95	98.97 103	94.97 72	99.88 54	98.42 42	99.76 36	99.42 109
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 44	98.42 23	98.27 105	99.09 103	95.41 176	98.86 114	99.37 8	97.69 19	99.78 4	99.61 4	92.38 111	99.91 37	99.58 8	99.43 102	99.49 94

TSAR-MVS + GP.		98.38 44	98.24 44	98.81 66	99.22 87	97.25 86	98.11 238	98.29 209	97.19 52	98.99 50	99.02 96	96.22 24	99.67 124	98.52 34	98.56 147	99.51 87

HPM-MVS_fast		98.38 44	98.13 51	99.12 49	99.75 3	97.86 62	99.44 11	98.82 79	94.46 182	98.94 51	99.20 65	95.16 66	99.74 109	97.58 89	99.85 5	99.77 25

patch_mono-2		98.36 47	98.87 4	96.82 210	99.53 36	90.68 315	98.64 167	99.29 12	97.88 13	99.19 38	99.52 11	96.80 15	99.97 1	99.11 14	99.86 1	99.82 14

HPM-MVS		98.36 47	98.10 54	99.13 47	99.74 7	97.82 66	99.53 8	98.80 91	94.63 174	98.61 78	98.97 103	95.13 68	99.77 104	97.65 84	99.83 11	99.79 17
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
APD-MVS		98.35 49	98.00 59	99.42 16	99.51 39	98.72 21	98.80 133	98.82 79	94.52 179	99.23 35	99.25 59	95.54 48	99.80 86	96.52 139	99.77 30	99.74 35
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_LR		98.34 50	98.23 45	98.67 72	99.27 76	96.90 99	97.95 252	99.58 3	97.14 56	98.44 89	99.01 100	95.03 71	99.62 135	97.91 64	99.75 40	99.50 89

PHI-MVS		98.34 50	98.06 55	99.18 42	99.15 98	98.12 55	99.04 68	99.09 29	93.32 236	98.83 62	99.10 84	96.54 20	99.83 67	97.70 82	99.76 36	99.59 77

MP-MVS		98.33 52	98.01 58	99.28 32	99.75 3	98.18 49	99.22 35	98.79 96	96.13 100	97.92 120	99.23 60	94.54 78	99.94 6	96.74 134	99.78 28	99.73 40
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MP-MVS-pluss		98.31 53	97.92 61	99.49 12	99.72 12	98.88 18	98.43 199	98.78 98	94.10 190	97.69 133	99.42 28	95.25 62	99.92 29	98.09 54	99.80 19	99.67 63
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP		98.23 54	97.95 60	99.09 50	99.74 7	97.62 71	99.03 71	99.41 6	95.98 105	97.60 141	99.36 40	94.45 83	99.93 23	97.14 108	98.85 133	99.70 51
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 55	98.11 53	98.49 87	98.34 173	97.26 85	99.61 5	98.43 182	96.78 72	98.87 59	98.84 121	93.72 96	99.01 213	98.91 18	99.50 92	99.19 141

fmvsm_s_conf0.1_n		98.18 56	98.21 48	98.11 124	98.54 155	95.24 186	98.87 111	99.24 15	97.50 29	99.70 11	99.67 1	91.33 143	99.89 45	99.47 10	99.54 87	99.21 136

fmvsm_s_conf0.1_n_a		98.08 57	98.04 57	98.21 112	97.66 229	95.39 177	98.89 103	99.17 24	97.24 48	99.76 6	99.67 1	91.13 148	99.88 54	99.39 11	99.41 104	99.35 113

dcpmvs_2		98.08 57	98.59 12	96.56 234	99.57 33	90.34 322	99.15 47	98.38 191	96.82 71	99.29 32	99.49 17	95.78 41	99.57 140	98.94 17	99.86 1	99.77 25

CANet		98.05 59	97.76 64	98.90 63	98.73 135	97.27 81	98.35 204	98.78 98	97.37 39	97.72 131	98.96 108	91.53 139	99.92 29	98.79 21	99.65 62	99.51 87

train_agg		97.97 60	97.52 76	99.33 26	99.31 62	98.50 29	97.92 254	98.73 109	92.98 252	97.74 128	98.68 140	96.20 26	99.80 86	96.59 135	99.57 78	99.68 59

ETV-MVS		97.96 61	97.81 62	98.40 98	98.42 162	97.27 81	98.73 148	98.55 153	96.84 69	98.38 91	97.44 259	95.39 52	99.35 169	97.62 86	98.89 129	98.58 201

UA-Net		97.96 61	97.62 68	98.98 57	98.86 126	97.47 76	98.89 103	99.08 30	96.67 78	98.72 70	99.54 8	93.15 102	99.81 79	94.87 188	98.83 134	99.65 67

CDPH-MVS		97.94 63	97.49 77	99.28 32	99.47 47	98.44 31	97.91 256	98.67 126	92.57 267	98.77 65	98.85 120	95.93 36	99.72 111	95.56 171	99.69 54	99.68 59

DeepPCF-MVS	96.37 2	97.93 64	98.48 21	96.30 260	99.00 111	89.54 334	97.43 295	98.87 67	98.16 9	99.26 34	99.38 35	96.12 29	99.64 129	98.30 47	99.77 30	99.72 43

DeepC-MVS	95.98 3	97.88 65	97.58 70	98.77 67	99.25 79	96.93 97	98.83 122	98.75 104	96.96 65	96.89 165	99.50 15	90.46 162	99.87 56	97.84 71	99.76 36	99.52 84
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 66	97.54 75	98.83 65	95.48 346	96.83 102	98.95 90	98.60 139	98.58 6	98.93 55	99.55 6	88.57 204	99.91 37	99.54 9	99.61 70	99.77 25

DP-MVS Recon		97.86 66	97.46 80	99.06 52	99.53 36	98.35 41	98.33 206	98.89 57	92.62 264	98.05 104	98.94 111	95.34 56	99.65 127	96.04 154	99.42 103	99.19 141

CSCG		97.85 68	97.74 65	98.20 114	99.67 25	95.16 189	99.22 35	99.32 11	93.04 250	97.02 158	98.92 114	95.36 55	99.91 37	97.43 99	99.64 66	99.52 84

MG-MVS		97.81 69	97.60 69	98.44 93	99.12 100	95.97 149	97.75 274	98.78 98	96.89 68	98.46 84	99.22 62	93.90 95	99.68 123	94.81 192	99.52 90	99.67 63

VNet		97.79 70	97.40 84	98.96 59	98.88 123	97.55 73	98.63 170	98.93 48	96.74 75	99.02 46	98.84 121	90.33 165	99.83 67	98.53 28	96.66 204	99.50 89

EIA-MVS		97.75 71	97.58 70	98.27 105	98.38 165	96.44 123	99.01 76	98.60 139	95.88 113	97.26 147	97.53 253	94.97 72	99.33 171	97.38 102	99.20 116	99.05 161

PS-MVSNAJ		97.73 72	97.77 63	97.62 161	98.68 143	95.58 168	97.34 304	98.51 162	97.29 42	98.66 75	97.88 220	94.51 79	99.90 43	97.87 68	99.17 118	97.39 240

casdiffmvs_mvg		97.72 73	97.48 79	98.44 93	98.42 162	96.59 115	98.92 97	98.44 178	96.20 97	97.76 125	99.20 65	91.66 133	99.23 179	98.27 49	98.41 156	99.49 94
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 73	97.32 88	98.92 61	99.64 28	97.10 92	99.12 53	98.81 84	92.34 275	98.09 102	99.08 92	93.01 103	99.92 29	96.06 153	99.77 30	99.75 33

PVSNet_Blended_VisFu		97.70 75	97.46 80	98.44 93	99.27 76	95.91 157	98.63 170	99.16 25	94.48 181	97.67 134	98.88 117	92.80 105	99.91 37	97.11 109	99.12 119	99.50 89

mvsany_test1		97.69 76	97.70 66	97.66 159	98.24 181	94.18 238	97.53 290	97.53 295	95.52 129	99.66 13	99.51 13	94.30 87	99.56 143	98.38 43	98.62 143	99.23 133

canonicalmvs		97.67 77	97.23 91	98.98 57	98.70 140	98.38 35	99.34 18	98.39 188	96.76 74	97.67 134	97.40 262	92.26 115	99.49 156	98.28 48	96.28 220	99.08 159

xiu_mvs_v2_base		97.66 78	97.70 66	97.56 165	98.61 150	95.46 174	97.44 293	98.46 174	97.15 55	98.65 76	98.15 197	94.33 86	99.80 86	97.84 71	98.66 142	97.41 238

baseline		97.64 79	97.44 82	98.25 109	98.35 168	96.20 136	99.00 78	98.32 199	96.33 94	98.03 107	99.17 72	91.35 142	99.16 186	98.10 53	98.29 163	99.39 110

casdiffmvs		97.63 80	97.41 83	98.28 104	98.33 175	96.14 140	98.82 124	98.32 199	96.38 92	97.95 115	99.21 63	91.23 147	99.23 179	98.12 52	98.37 157	99.48 96
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
xiu_mvs_v1_base_debu		97.60 81	97.56 72	97.72 150	98.35 168	95.98 144	97.86 265	98.51 162	97.13 57	99.01 47	98.40 170	91.56 135	99.80 86	98.53 28	98.68 138	97.37 242

xiu_mvs_v1_base		97.60 81	97.56 72	97.72 150	98.35 168	95.98 144	97.86 265	98.51 162	97.13 57	99.01 47	98.40 170	91.56 135	99.80 86	98.53 28	98.68 138	97.37 242

xiu_mvs_v1_base_debi		97.60 81	97.56 72	97.72 150	98.35 168	95.98 144	97.86 265	98.51 162	97.13 57	99.01 47	98.40 170	91.56 135	99.80 86	98.53 28	98.68 138	97.37 242

diffmvs		97.58 84	97.40 84	98.13 120	98.32 178	95.81 162	98.06 242	98.37 192	96.20 97	98.74 67	98.89 116	91.31 145	99.25 176	98.16 51	98.52 148	99.34 114
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 85	97.49 77	97.84 138	98.07 199	95.76 163	99.47 9	98.40 186	94.98 159	98.79 63	98.83 123	92.34 112	98.41 287	96.91 117	99.59 74	99.34 114

alignmvs		97.56 86	97.07 98	99.01 54	98.66 145	98.37 39	98.83 122	98.06 255	96.74 75	98.00 113	97.65 242	90.80 156	99.48 160	98.37 44	96.56 208	99.19 141

DPM-MVS		97.55 87	96.99 101	99.23 38	99.04 106	98.55 27	97.17 319	98.35 195	94.85 166	97.93 119	98.58 151	95.07 70	99.71 116	92.60 259	99.34 111	99.43 107

OMC-MVS		97.55 87	97.34 87	98.20 114	99.33 57	95.92 156	98.28 216	98.59 142	95.52 129	97.97 114	99.10 84	93.28 101	99.49 156	95.09 185	98.88 130	99.19 141

PAPM_NR		97.46 89	97.11 95	98.50 85	99.50 41	96.41 127	98.63 170	98.60 139	95.18 148	97.06 156	98.06 203	94.26 89	99.57 140	93.80 227	98.87 132	99.52 84

EPP-MVSNet		97.46 89	97.28 89	97.99 131	98.64 147	95.38 178	99.33 21	98.31 201	93.61 226	97.19 149	99.07 93	94.05 92	99.23 179	96.89 121	98.43 155	99.37 112

3Dnovator	94.51 5	97.46 89	96.93 103	99.07 51	97.78 217	97.64 69	99.35 17	99.06 32	97.02 62	93.75 270	99.16 75	89.25 185	99.92 29	97.22 107	99.75 40	99.64 69

CNLPA		97.45 92	97.03 99	98.73 68	99.05 105	97.44 78	98.07 241	98.53 157	95.32 141	96.80 170	98.53 155	93.32 99	99.72 111	94.31 210	99.31 113	99.02 163

lupinMVS		97.44 93	97.22 92	98.12 123	98.07 199	95.76 163	97.68 279	97.76 276	94.50 180	98.79 63	98.61 146	92.34 112	99.30 173	97.58 89	99.59 74	99.31 120

3Dnovator+	94.38 6	97.43 94	96.78 111	99.38 18	97.83 215	98.52 28	99.37 14	98.71 114	97.09 60	92.99 297	99.13 80	89.36 181	99.89 45	96.97 114	99.57 78	99.71 47

Vis-MVSNet		97.42 95	97.11 95	98.34 101	98.66 145	96.23 135	99.22 35	99.00 37	96.63 80	98.04 106	99.21 63	88.05 219	99.35 169	96.01 156	99.21 115	99.45 104
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
API-MVS		97.41 96	97.25 90	97.91 135	98.70 140	96.80 103	98.82 124	98.69 118	94.53 177	98.11 100	98.28 185	94.50 82	99.57 140	94.12 216	99.49 94	97.37 242

sss		97.39 97	96.98 102	98.61 75	98.60 151	96.61 112	98.22 221	98.93 48	93.97 198	98.01 112	98.48 160	91.98 125	99.85 61	96.45 141	98.15 165	99.39 110

test_cas_vis1_n_1920		97.38 98	97.36 86	97.45 168	98.95 118	93.25 271	99.00 78	98.53 157	97.70 18	99.77 5	99.35 42	84.71 286	99.85 61	98.57 25	99.66 59	99.26 129

PVSNet_Blended		97.38 98	97.12 94	98.14 117	99.25 79	95.35 181	97.28 309	99.26 13	93.13 246	97.94 117	98.21 193	92.74 106	99.81 79	96.88 123	99.40 107	99.27 127

WTY-MVS		97.37 100	96.92 104	98.72 69	98.86 126	96.89 101	98.31 211	98.71 114	95.26 144	97.67 134	98.56 154	92.21 118	99.78 99	95.89 158	96.85 199	99.48 96

jason		97.32 101	97.08 97	98.06 128	97.45 248	95.59 167	97.87 264	97.91 270	94.79 167	98.55 81	98.83 123	91.12 149	99.23 179	97.58 89	99.60 72	99.34 114
jason: jason.
MVS_Test		97.28 102	97.00 100	98.13 120	98.33 175	95.97 149	98.74 144	98.07 250	94.27 186	98.44 89	98.07 202	92.48 109	99.26 175	96.43 142	98.19 164	99.16 147

EPNet		97.28 102	96.87 106	98.51 84	94.98 354	96.14 140	98.90 99	97.02 331	98.28 8	95.99 198	99.11 82	91.36 141	99.89 45	96.98 113	99.19 117	99.50 89
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_yl		97.22 104	96.78 111	98.54 81	98.73 135	96.60 113	98.45 194	98.31 201	94.70 168	98.02 109	98.42 168	90.80 156	99.70 117	96.81 129	96.79 201	99.34 114

DCV-MVSNet		97.22 104	96.78 111	98.54 81	98.73 135	96.60 113	98.45 194	98.31 201	94.70 168	98.02 109	98.42 168	90.80 156	99.70 117	96.81 129	96.79 201	99.34 114

IS-MVSNet		97.22 104	96.88 105	98.25 109	98.85 128	96.36 130	99.19 42	97.97 263	95.39 135	97.23 148	98.99 102	91.11 150	98.93 225	94.60 199	98.59 145	99.47 98

PLC	95.07 4	97.20 107	96.78 111	98.44 93	99.29 71	96.31 134	98.14 233	98.76 102	92.41 273	96.39 188	98.31 183	94.92 74	99.78 99	94.06 219	98.77 137	99.23 133
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		97.18 108	97.18 93	97.20 182	98.81 131	93.27 269	95.78 364	99.15 26	95.25 145	96.79 171	98.11 200	92.29 114	99.07 203	98.56 27	99.85 5	99.25 131

LS3D		97.16 109	96.66 119	98.68 71	98.53 156	97.19 89	98.93 95	98.90 55	92.83 259	95.99 198	99.37 36	92.12 121	99.87 56	93.67 231	99.57 78	98.97 168

AdaColmap		97.15 110	96.70 115	98.48 88	99.16 96	96.69 109	98.01 247	98.89 57	94.44 183	96.83 166	98.68 140	90.69 159	99.76 105	94.36 206	99.29 114	98.98 167

Effi-MVS+		97.12 111	96.69 116	98.39 99	98.19 189	96.72 108	97.37 300	98.43 182	93.71 215	97.65 137	98.02 206	92.20 119	99.25 176	96.87 126	97.79 177	99.19 141

CHOSEN 1792x2688		97.12 111	96.80 108	98.08 126	99.30 66	94.56 222	98.05 243	99.71 1	93.57 227	97.09 152	98.91 115	88.17 214	99.89 45	96.87 126	99.56 84	99.81 15

F-COLMAP		97.09 113	96.80 108	97.97 132	99.45 52	94.95 202	98.55 183	98.62 138	93.02 251	96.17 193	98.58 151	94.01 93	99.81 79	93.95 221	98.90 128	99.14 150

TAMVS		97.02 114	96.79 110	97.70 153	98.06 202	95.31 183	98.52 185	98.31 201	93.95 199	97.05 157	98.61 146	93.49 98	98.52 267	95.33 177	97.81 176	99.29 125

CDS-MVSNet		96.99 115	96.69 116	97.90 136	98.05 203	95.98 144	98.20 224	98.33 198	93.67 222	96.95 159	98.49 159	93.54 97	98.42 279	95.24 183	97.74 180	99.31 120
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CANet_DTU		96.96 116	96.55 122	98.21 112	98.17 193	96.07 142	97.98 250	98.21 218	97.24 48	97.13 151	98.93 112	86.88 243	99.91 37	95.00 187	99.37 110	98.66 193

114514_t		96.93 117	96.27 133	98.92 61	99.50 41	97.63 70	98.85 116	98.90 55	84.80 371	97.77 124	99.11 82	92.84 104	99.66 126	94.85 189	99.77 30	99.47 98

MAR-MVS		96.91 118	96.40 128	98.45 91	98.69 142	96.90 99	98.66 165	98.68 121	92.40 274	97.07 155	97.96 213	91.54 138	99.75 107	93.68 229	98.92 127	98.69 189
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		96.90 119	96.49 125	98.14 117	99.33 57	95.56 169	97.38 298	99.65 2	92.34 275	97.61 140	98.20 194	89.29 183	99.10 200	96.97 114	97.60 185	99.77 25

Vis-MVSNet (Re-imp)		96.87 120	96.55 122	97.83 139	98.73 135	95.46 174	99.20 40	98.30 207	94.96 161	96.60 177	98.87 118	90.05 168	98.59 259	93.67 231	98.60 144	99.46 102

SDMVSNet		96.85 121	96.42 126	98.14 117	99.30 66	96.38 128	99.21 38	99.23 18	95.92 108	95.96 200	98.76 134	85.88 260	99.44 165	97.93 62	95.59 230	98.60 197

PAPR		96.84 122	96.24 135	98.65 73	98.72 139	96.92 98	97.36 302	98.57 149	93.33 235	96.67 173	97.57 250	94.30 87	99.56 143	91.05 296	98.59 145	99.47 98

HY-MVS	93.96 8	96.82 123	96.23 136	98.57 77	98.46 160	97.00 94	98.14 233	98.21 218	93.95 199	96.72 172	97.99 210	91.58 134	99.76 105	94.51 203	96.54 209	98.95 171

UGNet		96.78 124	96.30 132	98.19 116	98.24 181	95.89 159	98.88 107	98.93 48	97.39 36	96.81 169	97.84 224	82.60 313	99.90 43	96.53 138	99.49 94	98.79 181
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		96.73 125	96.60 120	97.12 189	99.25 79	95.35 181	98.26 219	99.26 13	94.28 185	97.94 117	97.46 256	92.74 106	99.81 79	96.88 123	93.32 270	96.20 335

test_vis1_n_1920		96.71 126	96.84 107	96.31 259	99.11 101	89.74 329	99.05 65	98.58 147	98.08 10	99.87 1	99.37 36	78.48 339	99.93 23	99.29 12	99.69 54	99.27 127

mvs_anonymous		96.70 127	96.53 124	97.18 184	98.19 189	93.78 247	98.31 211	98.19 222	94.01 195	94.47 229	98.27 188	92.08 123	98.46 274	97.39 101	97.91 172	99.31 120

1112_ss		96.63 128	96.00 144	98.50 85	98.56 152	96.37 129	98.18 231	98.10 243	92.92 255	94.84 217	98.43 166	92.14 120	99.58 139	94.35 207	96.51 210	99.56 83

PMMVS		96.60 129	96.33 130	97.41 172	97.90 212	93.93 243	97.35 303	98.41 184	92.84 258	97.76 125	97.45 258	91.10 151	99.20 183	96.26 146	97.91 172	99.11 153

DP-MVS		96.59 130	95.93 147	98.57 77	99.34 55	96.19 138	98.70 157	98.39 188	89.45 343	94.52 227	99.35 42	91.85 128	99.85 61	92.89 255	98.88 130	99.68 59

PatchMatch-RL		96.59 130	96.03 143	98.27 105	99.31 62	96.51 120	97.91 256	99.06 32	93.72 214	96.92 163	98.06 203	88.50 209	99.65 127	91.77 283	99.00 125	98.66 193

GeoE		96.58 132	96.07 140	98.10 125	98.35 168	95.89 159	99.34 18	98.12 237	93.12 247	96.09 194	98.87 118	89.71 174	98.97 215	92.95 251	98.08 168	99.43 107

mvsmamba		96.57 133	96.32 131	97.32 178	96.60 301	96.43 124	99.54 7	97.98 261	96.49 84	95.20 210	98.64 144	90.82 154	98.55 263	97.97 59	93.65 260	96.98 253

XVG-OURS		96.55 134	96.41 127	96.99 196	98.75 134	93.76 248	97.50 292	98.52 160	95.67 123	96.83 166	99.30 50	88.95 198	99.53 151	95.88 159	96.26 221	97.69 231

FIs		96.51 135	96.12 138	97.67 156	97.13 272	97.54 74	99.36 15	99.22 21	95.89 111	94.03 256	98.35 176	91.98 125	98.44 277	96.40 143	92.76 279	97.01 251

XVG-OURS-SEG-HR		96.51 135	96.34 129	97.02 195	98.77 133	93.76 248	97.79 272	98.50 167	95.45 132	96.94 160	99.09 90	87.87 224	99.55 150	96.76 133	95.83 229	97.74 228

PS-MVSNAJss		96.43 137	96.26 134	96.92 205	95.84 336	95.08 194	99.16 46	98.50 167	95.87 114	93.84 266	98.34 180	94.51 79	98.61 256	96.88 123	93.45 267	97.06 248

test_fmvs1		96.42 138	96.67 118	95.66 285	98.82 130	88.53 351	98.80 133	98.20 220	96.39 91	99.64 15	99.20 65	80.35 329	99.67 124	99.04 15	99.57 78	98.78 184

iter_conf_final		96.42 138	96.12 138	97.34 177	98.46 160	96.55 119	99.08 61	98.06 255	96.03 104	95.63 204	98.46 164	87.72 226	98.59 259	97.84 71	93.80 255	96.87 269

FC-MVSNet-test		96.42 138	96.05 141	97.53 166	96.95 281	97.27 81	99.36 15	99.23 18	95.83 115	93.93 260	98.37 174	92.00 124	98.32 296	96.02 155	92.72 280	97.00 252

ab-mvs		96.42 138	95.71 159	98.55 79	98.63 148	96.75 106	97.88 263	98.74 106	93.84 205	96.54 182	98.18 196	85.34 272	99.75 107	95.93 157	96.35 214	99.15 148

FA-MVS(test-final)		96.41 142	95.94 146	97.82 141	98.21 185	95.20 188	97.80 270	97.58 286	93.21 241	97.36 145	97.70 236	89.47 178	99.56 143	94.12 216	97.99 169	98.71 188

PVSNet	91.96 18	96.35 143	96.15 137	96.96 200	99.17 92	92.05 289	96.08 357	98.68 121	93.69 218	97.75 127	97.80 230	88.86 199	99.69 122	94.26 212	99.01 124	99.15 148

Test_1112_low_res		96.34 144	95.66 164	98.36 100	98.56 152	95.94 152	97.71 277	98.07 250	92.10 284	94.79 221	97.29 267	91.75 130	99.56 143	94.17 214	96.50 211	99.58 81

Effi-MVS+-dtu		96.29 145	96.56 121	95.51 289	97.89 213	90.22 323	98.80 133	98.10 243	96.57 83	96.45 187	96.66 317	90.81 155	98.91 227	95.72 165	97.99 169	97.40 239

QAPM		96.29 145	95.40 168	98.96 59	97.85 214	97.60 72	99.23 31	98.93 48	89.76 337	93.11 294	99.02 96	89.11 190	99.93 23	91.99 278	99.62 69	99.34 114

Fast-Effi-MVS+		96.28 147	95.70 161	98.03 129	98.29 180	95.97 149	98.58 176	98.25 215	91.74 292	95.29 209	97.23 272	91.03 153	99.15 189	92.90 253	97.96 171	98.97 168

nrg030		96.28 147	95.72 156	97.96 134	96.90 286	98.15 52	99.39 12	98.31 201	95.47 131	94.42 235	98.35 176	92.09 122	98.69 249	97.50 97	89.05 325	97.04 249

1314		96.25 149	95.73 155	97.79 143	97.13 272	95.55 171	98.19 227	98.59 142	93.47 230	92.03 322	97.82 228	91.33 143	99.49 156	94.62 198	98.44 153	98.32 212

sd_testset		96.17 150	95.76 154	97.42 171	99.30 66	94.34 231	98.82 124	99.08 30	95.92 108	95.96 200	98.76 134	82.83 312	99.32 172	95.56 171	95.59 230	98.60 197

h-mvs33		96.17 150	95.62 165	97.81 142	99.03 107	94.45 224	98.64 167	98.75 104	97.48 30	98.67 71	98.72 137	89.76 172	99.86 60	97.95 60	81.59 368	99.11 153

HQP_MVS		96.14 152	95.90 148	96.85 208	97.42 250	94.60 220	98.80 133	98.56 151	97.28 43	95.34 207	98.28 185	87.09 238	99.03 208	96.07 150	94.27 238	96.92 258

iter_conf05		96.13 153	95.79 151	97.15 186	98.16 194	95.99 143	98.88 107	97.98 261	95.91 110	95.58 205	98.46 164	85.53 267	98.59 259	97.88 67	93.75 256	96.86 272

tttt0517		96.07 154	95.51 167	97.78 144	98.41 164	94.84 206	99.28 24	94.33 377	94.26 187	97.64 138	98.64 144	84.05 301	99.47 162	95.34 176	97.60 185	99.03 162

MVSTER		96.06 155	95.72 156	97.08 192	98.23 183	95.93 155	98.73 148	98.27 210	94.86 165	95.07 212	98.09 201	88.21 213	98.54 265	96.59 135	93.46 265	96.79 278

thisisatest0530		96.01 156	95.36 173	97.97 132	98.38 165	95.52 172	98.88 107	94.19 379	94.04 192	97.64 138	98.31 183	83.82 308	99.46 163	95.29 180	97.70 182	98.93 173

test_djsdf		96.00 157	95.69 162	96.93 202	95.72 338	95.49 173	99.47 9	98.40 186	94.98 159	94.58 225	97.86 221	89.16 188	98.41 287	96.91 117	94.12 246	96.88 267

RRT_MVS		95.98 158	95.78 152	96.56 234	96.48 309	94.22 237	99.57 6	97.92 268	95.89 111	93.95 259	98.70 138	89.27 184	98.42 279	97.23 106	93.02 274	97.04 249

EI-MVSNet		95.96 159	95.83 150	96.36 255	97.93 210	93.70 254	98.12 236	98.27 210	93.70 217	95.07 212	99.02 96	92.23 117	98.54 265	94.68 194	93.46 265	96.84 274

ECVR-MVS		95.95 160	95.71 159	96.65 220	99.02 108	90.86 310	99.03 71	91.80 388	96.96 65	98.10 101	99.26 55	81.31 319	99.51 155	96.90 120	99.04 121	99.59 77

BH-untuned		95.95 160	95.72 156	96.65 220	98.55 154	92.26 285	98.23 220	97.79 275	93.73 213	94.62 224	98.01 208	88.97 197	99.00 214	93.04 248	98.51 149	98.68 190

test1111		95.94 162	95.78 152	96.41 252	98.99 115	90.12 324	99.04 68	92.45 387	96.99 64	98.03 107	99.27 54	81.40 318	99.48 160	96.87 126	99.04 121	99.63 71

MSDG		95.93 163	95.30 180	97.83 139	98.90 121	95.36 179	96.83 344	98.37 192	91.32 307	94.43 234	98.73 136	90.27 166	99.60 137	90.05 310	98.82 135	98.52 203

BH-RMVSNet		95.92 164	95.32 177	97.69 154	98.32 178	94.64 214	98.19 227	97.45 305	94.56 175	96.03 196	98.61 146	85.02 277	99.12 194	90.68 301	99.06 120	99.30 123

test_fmvs1_n		95.90 165	95.99 145	95.63 286	98.67 144	88.32 355	99.26 27	98.22 217	96.40 90	99.67 12	99.26 55	73.91 366	99.70 117	99.02 16	99.50 92	98.87 176

Fast-Effi-MVS+-dtu		95.87 166	95.85 149	95.91 275	97.74 222	91.74 295	98.69 159	98.15 233	95.56 127	94.92 215	97.68 241	88.98 196	98.79 243	93.19 243	97.78 178	97.20 246

LFMVS		95.86 167	94.98 195	98.47 89	98.87 125	96.32 132	98.84 120	96.02 357	93.40 233	98.62 77	99.20 65	74.99 361	99.63 132	97.72 78	97.20 191	99.46 102

baseline1		95.84 168	95.12 188	98.01 130	98.49 159	95.98 144	98.73 148	97.03 329	95.37 138	96.22 191	98.19 195	89.96 170	99.16 186	94.60 199	87.48 341	98.90 175

OpenMVS	93.04 13	95.83 169	95.00 193	98.32 102	97.18 269	97.32 79	99.21 38	98.97 40	89.96 333	91.14 330	99.05 95	86.64 246	99.92 29	93.38 237	99.47 97	97.73 229

VDD-MVS		95.82 170	95.23 182	97.61 162	98.84 129	93.98 242	98.68 160	97.40 309	95.02 158	97.95 115	99.34 46	74.37 365	99.78 99	98.64 23	96.80 200	99.08 159

UniMVSNet (Re)		95.78 171	95.19 184	97.58 163	96.99 279	97.47 76	98.79 138	99.18 23	95.60 125	93.92 261	97.04 291	91.68 131	98.48 270	95.80 163	87.66 340	96.79 278

VPA-MVSNet		95.75 172	95.11 189	97.69 154	97.24 261	97.27 81	98.94 93	99.23 18	95.13 150	95.51 206	97.32 265	85.73 263	98.91 227	97.33 104	89.55 317	96.89 266

bld_raw_dy_0_64		95.74 173	95.31 179	97.03 194	96.35 315	95.76 163	99.12 53	97.37 312	95.97 106	94.70 223	98.48 160	85.80 262	98.49 269	96.55 137	93.48 264	96.84 274

HQP-MVS		95.72 174	95.40 168	96.69 218	97.20 265	94.25 235	98.05 243	98.46 174	96.43 87	94.45 230	97.73 233	86.75 244	98.96 219	95.30 178	94.18 242	96.86 272

hse-mvs2		95.71 175	95.30 180	96.93 202	98.50 157	93.53 259	98.36 203	98.10 243	97.48 30	98.67 71	97.99 210	89.76 172	99.02 211	97.95 60	80.91 372	98.22 215

UniMVSNet_NR-MVSNet		95.71 175	95.15 185	97.40 174	96.84 289	96.97 95	98.74 144	99.24 15	95.16 149	93.88 263	97.72 235	91.68 131	98.31 298	95.81 161	87.25 346	96.92 258

PatchmatchNet		95.71 175	95.52 166	96.29 261	97.58 234	90.72 314	96.84 343	97.52 296	94.06 191	97.08 153	96.96 301	89.24 186	98.90 230	92.03 277	98.37 157	99.26 129
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
OPM-MVS		95.69 178	95.33 176	96.76 213	96.16 324	94.63 215	98.43 199	98.39 188	96.64 79	95.02 214	98.78 128	85.15 276	99.05 204	95.21 184	94.20 241	96.60 301
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMM	93.85 9	95.69 178	95.38 172	96.61 227	97.61 232	93.84 246	98.91 98	98.44 178	95.25 145	94.28 242	98.47 162	86.04 259	99.12 194	95.50 174	93.95 251	96.87 269
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpmrst		95.63 180	95.69 162	95.44 293	97.54 239	88.54 350	96.97 329	97.56 288	93.50 229	97.52 143	96.93 305	89.49 176	99.16 186	95.25 182	96.42 213	98.64 195

FE-MVS		95.62 181	94.90 199	97.78 144	98.37 167	94.92 203	97.17 319	97.38 311	90.95 318	97.73 130	97.70 236	85.32 274	99.63 132	91.18 291	98.33 160	98.79 181

LPG-MVS_test		95.62 181	95.34 174	96.47 246	97.46 245	93.54 257	98.99 81	98.54 155	94.67 172	94.36 238	98.77 130	85.39 269	99.11 196	95.71 166	94.15 244	96.76 281

CLD-MVS		95.62 181	95.34 174	96.46 249	97.52 242	93.75 250	97.27 310	98.46 174	95.53 128	94.42 235	98.00 209	86.21 254	98.97 215	96.25 148	94.37 236	96.66 296
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		95.61 184	94.89 200	97.76 147	98.15 195	95.15 191	96.77 345	94.41 375	92.95 254	97.18 150	97.43 260	84.78 283	99.45 164	94.63 196	97.73 181	98.68 190

thres600view7		95.49 185	94.77 203	97.67 156	98.98 116	95.02 195	98.85 116	96.90 338	95.38 136	96.63 175	96.90 306	84.29 293	99.59 138	88.65 332	96.33 215	98.40 207

test_vis1_n		95.47 186	95.13 186	96.49 243	97.77 218	90.41 320	99.27 26	98.11 240	96.58 81	99.66 13	99.18 71	67.00 378	99.62 135	99.21 13	99.40 107	99.44 105

SCA		95.46 187	95.13 186	96.46 249	97.67 227	91.29 303	97.33 305	97.60 285	94.68 171	96.92 163	97.10 278	83.97 303	98.89 231	92.59 261	98.32 162	99.20 137

IterMVS-LS		95.46 187	95.21 183	96.22 263	98.12 196	93.72 253	98.32 210	98.13 236	93.71 215	94.26 243	97.31 266	92.24 116	98.10 314	94.63 196	90.12 308	96.84 274
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
jajsoiax		95.45 189	95.03 192	96.73 214	95.42 350	94.63 215	99.14 49	98.52 160	95.74 118	93.22 288	98.36 175	83.87 306	98.65 254	96.95 116	94.04 247	96.91 263

CVMVSNet		95.43 190	96.04 142	93.57 334	97.93 210	83.62 372	98.12 236	98.59 142	95.68 122	96.56 178	99.02 96	87.51 231	97.51 346	93.56 235	97.44 187	99.60 75

anonymousdsp		95.42 191	94.91 198	96.94 201	95.10 353	95.90 158	99.14 49	98.41 184	93.75 210	93.16 290	97.46 256	87.50 233	98.41 287	95.63 170	94.03 248	96.50 320

DU-MVS		95.42 191	94.76 204	97.40 174	96.53 305	96.97 95	98.66 165	98.99 39	95.43 133	93.88 263	97.69 238	88.57 204	98.31 298	95.81 161	87.25 346	96.92 258

mvs_tets		95.41 193	95.00 193	96.65 220	95.58 342	94.42 226	99.00 78	98.55 153	95.73 120	93.21 289	98.38 173	83.45 310	98.63 255	97.09 110	94.00 249	96.91 263

thres100view900		95.38 194	94.70 207	97.41 172	98.98 116	94.92 203	98.87 111	96.90 338	95.38 136	96.61 176	96.88 307	84.29 293	99.56 143	88.11 335	96.29 217	97.76 226

thres400		95.38 194	94.62 210	97.65 160	98.94 119	94.98 199	98.68 160	96.93 336	95.33 139	96.55 180	96.53 323	84.23 297	99.56 143	88.11 335	96.29 217	98.40 207

BH-w/o		95.38 194	95.08 190	96.26 262	98.34 173	91.79 292	97.70 278	97.43 307	92.87 257	94.24 245	97.22 273	88.66 202	98.84 237	91.55 287	97.70 182	98.16 218

VDDNet		95.36 197	94.53 214	97.86 137	98.10 198	95.13 192	98.85 116	97.75 277	90.46 324	98.36 92	99.39 30	73.27 368	99.64 129	97.98 58	96.58 207	98.81 180

TAPA-MVS	93.98 7	95.35 198	94.56 213	97.74 149	99.13 99	94.83 208	98.33 206	98.64 134	86.62 359	96.29 190	98.61 146	94.00 94	99.29 174	80.00 373	99.41 104	99.09 155
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ACMP	93.49 10	95.34 199	94.98 195	96.43 251	97.67 227	93.48 261	98.73 148	98.44 178	94.94 164	92.53 310	98.53 155	84.50 292	99.14 191	95.48 175	94.00 249	96.66 296
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
COLMAP_ROB	93.27 12	95.33 200	94.87 201	96.71 215	99.29 71	93.24 272	98.58 176	98.11 240	89.92 334	93.57 274	99.10 84	86.37 252	99.79 96	90.78 299	98.10 167	97.09 247
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
tfpn200view9		95.32 201	94.62 210	97.43 170	98.94 119	94.98 199	98.68 160	96.93 336	95.33 139	96.55 180	96.53 323	84.23 297	99.56 143	88.11 335	96.29 217	97.76 226

Anonymous202405211		95.28 202	94.49 216	97.67 156	99.00 111	93.75 250	98.70 157	97.04 328	90.66 320	96.49 184	98.80 126	78.13 343	99.83 67	96.21 149	95.36 234	99.44 105

thres200		95.25 203	94.57 212	97.28 179	98.81 131	94.92 203	98.20 224	97.11 323	95.24 147	96.54 182	96.22 334	84.58 290	99.53 151	87.93 339	96.50 211	97.39 240

AllTest		95.24 204	94.65 209	96.99 196	99.25 79	93.21 273	98.59 174	98.18 225	91.36 303	93.52 276	98.77 130	84.67 287	99.72 111	89.70 317	97.87 174	98.02 221

LCM-MVSNet-Re		95.22 205	95.32 177	94.91 308	98.18 191	87.85 361	98.75 141	95.66 363	95.11 152	88.96 348	96.85 310	90.26 167	97.65 339	95.65 169	98.44 153	99.22 135

EPNet_dtu		95.21 206	94.95 197	95.99 270	96.17 322	90.45 319	98.16 232	97.27 317	96.77 73	93.14 293	98.33 181	90.34 164	98.42 279	85.57 352	98.81 136	99.09 155
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
XXY-MVS		95.20 207	94.45 221	97.46 167	96.75 294	96.56 117	98.86 114	98.65 133	93.30 238	93.27 287	98.27 188	84.85 281	98.87 234	94.82 191	91.26 296	96.96 255

D2MVS		95.18 208	95.08 190	95.48 290	97.10 274	92.07 288	98.30 213	99.13 28	94.02 194	92.90 298	96.73 314	89.48 177	98.73 247	94.48 204	93.60 263	95.65 348

WR-MVS		95.15 209	94.46 219	97.22 181	96.67 299	96.45 122	98.21 222	98.81 84	94.15 188	93.16 290	97.69 238	87.51 231	98.30 300	95.29 180	88.62 331	96.90 265

TranMVSNet+NR-MVSNet		95.14 210	94.48 217	97.11 190	96.45 311	96.36 130	99.03 71	99.03 35	95.04 157	93.58 273	97.93 215	88.27 212	98.03 320	94.13 215	86.90 351	96.95 257

baseline2		95.11 211	94.52 215	96.87 207	96.65 300	93.56 256	98.27 218	94.10 381	93.45 231	92.02 323	97.43 260	87.45 235	99.19 184	93.88 224	97.41 189	97.87 224

miper_enhance_ethall		95.10 212	94.75 205	96.12 267	97.53 241	93.73 252	96.61 351	98.08 248	92.20 283	93.89 262	96.65 319	92.44 110	98.30 300	94.21 213	91.16 297	96.34 329

Anonymous20240529		95.10 212	94.22 229	97.75 148	99.01 110	94.26 234	98.87 111	98.83 78	85.79 367	96.64 174	98.97 103	78.73 337	99.85 61	96.27 145	94.89 235	99.12 152

test-LLR		95.10 212	94.87 201	95.80 280	96.77 291	89.70 330	96.91 334	95.21 367	95.11 152	94.83 219	95.72 346	87.71 227	98.97 215	93.06 246	98.50 150	98.72 186

WR-MVS_H		95.05 215	94.46 219	96.81 211	96.86 288	95.82 161	99.24 30	99.24 15	93.87 204	92.53 310	96.84 311	90.37 163	98.24 306	93.24 241	87.93 337	96.38 328

miper_ehance_all_eth		95.01 216	94.69 208	95.97 272	97.70 225	93.31 268	97.02 327	98.07 250	92.23 280	93.51 278	96.96 301	91.85 128	98.15 310	93.68 229	91.16 297	96.44 326

ADS-MVSNet		95.00 217	94.45 221	96.63 224	98.00 204	91.91 291	96.04 358	97.74 278	90.15 330	96.47 185	96.64 320	87.89 222	98.96 219	90.08 308	97.06 193	99.02 163

VPNet		94.99 218	94.19 231	97.40 174	97.16 270	96.57 116	98.71 153	98.97 40	95.67 123	94.84 217	98.24 192	80.36 328	98.67 253	96.46 140	87.32 345	96.96 255

EPMVS		94.99 218	94.48 217	96.52 241	97.22 263	91.75 294	97.23 311	91.66 389	94.11 189	97.28 146	96.81 312	85.70 264	98.84 237	93.04 248	97.28 190	98.97 168

NR-MVSNet		94.98 220	94.16 234	97.44 169	96.53 305	97.22 88	98.74 144	98.95 44	94.96 161	89.25 347	97.69 238	89.32 182	98.18 308	94.59 201	87.40 343	96.92 258

FMVSNet3		94.97 221	94.26 228	97.11 190	98.18 191	96.62 110	98.56 182	98.26 214	93.67 222	94.09 252	97.10 278	84.25 295	98.01 321	92.08 273	92.14 283	96.70 290

CostFormer		94.95 222	94.73 206	95.60 288	97.28 259	89.06 341	97.53 290	96.89 340	89.66 339	96.82 168	96.72 315	86.05 257	98.95 224	95.53 173	96.13 226	98.79 181

PAPM		94.95 222	94.00 244	97.78 144	97.04 276	95.65 166	96.03 360	98.25 215	91.23 312	94.19 248	97.80 230	91.27 146	98.86 236	82.61 367	97.61 184	98.84 179

CP-MVSNet		94.94 224	94.30 227	96.83 209	96.72 296	95.56 169	99.11 55	98.95 44	93.89 202	92.42 315	97.90 217	87.19 237	98.12 313	94.32 209	88.21 334	96.82 277

TR-MVS		94.94 224	94.20 230	97.17 185	97.75 219	94.14 239	97.59 287	97.02 331	92.28 279	95.75 203	97.64 244	83.88 305	98.96 219	89.77 314	96.15 225	98.40 207

RPSCF		94.87 226	95.40 168	93.26 340	98.89 122	82.06 378	98.33 206	98.06 255	90.30 329	96.56 178	99.26 55	87.09 238	99.49 156	93.82 226	96.32 216	98.24 213

GA-MVS		94.81 227	94.03 240	97.14 187	97.15 271	93.86 245	96.76 346	97.58 286	94.00 196	94.76 222	97.04 291	80.91 323	98.48 270	91.79 282	96.25 222	99.09 155

c3_l		94.79 228	94.43 223	95.89 277	97.75 219	93.12 276	97.16 321	98.03 258	92.23 280	93.46 281	97.05 290	91.39 140	98.01 321	93.58 234	89.21 323	96.53 312

V42		94.78 229	94.14 236	96.70 217	96.33 317	95.22 187	98.97 84	98.09 247	92.32 277	94.31 241	97.06 288	88.39 210	98.55 263	92.90 253	88.87 329	96.34 329

CR-MVSNet		94.76 230	94.15 235	96.59 230	97.00 277	93.43 262	94.96 370	97.56 288	92.46 268	96.93 161	96.24 330	88.15 215	97.88 333	87.38 341	96.65 205	98.46 205

v2v482		94.69 231	94.03 240	96.65 220	96.17 322	94.79 211	98.67 163	98.08 248	92.72 261	94.00 257	97.16 276	87.69 230	98.45 275	92.91 252	88.87 329	96.72 286

pmmvs4		94.69 231	93.99 246	96.81 211	95.74 337	95.94 152	97.40 296	97.67 280	90.42 326	93.37 284	97.59 248	89.08 191	98.20 307	92.97 250	91.67 290	96.30 332

cl22		94.68 233	94.19 231	96.13 266	98.11 197	93.60 255	96.94 331	98.31 201	92.43 272	93.32 286	96.87 309	86.51 247	98.28 304	94.10 218	91.16 297	96.51 318

eth_miper_zixun_eth		94.68 233	94.41 224	95.47 291	97.64 230	91.71 296	96.73 348	98.07 250	92.71 262	93.64 271	97.21 274	90.54 161	98.17 309	93.38 237	89.76 312	96.54 310

PCF-MVS	93.45 11	94.68 233	93.43 280	98.42 97	98.62 149	96.77 105	95.48 368	98.20 220	84.63 372	93.34 285	98.32 182	88.55 207	99.81 79	84.80 359	98.96 126	98.68 190
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS		94.67 236	93.54 276	98.08 126	96.88 287	96.56 117	98.19 227	98.50 167	78.05 381	92.69 305	98.02 206	91.07 152	99.63 132	90.09 307	98.36 159	98.04 220

PS-CasMVS		94.67 236	93.99 246	96.71 215	96.68 298	95.26 184	99.13 52	99.03 35	93.68 220	92.33 316	97.95 214	85.35 271	98.10 314	93.59 233	88.16 336	96.79 278

cascas		94.63 238	93.86 255	96.93 202	96.91 285	94.27 233	96.00 361	98.51 162	85.55 368	94.54 226	96.23 332	84.20 299	98.87 234	95.80 163	96.98 198	97.66 232

tpmvs		94.60 239	94.36 226	95.33 297	97.46 245	88.60 349	96.88 340	97.68 279	91.29 309	93.80 268	96.42 327	88.58 203	99.24 178	91.06 294	96.04 227	98.17 217

LTVRE_ROB	92.95 15	94.60 239	93.90 252	96.68 219	97.41 253	94.42 226	98.52 185	98.59 142	91.69 295	91.21 329	98.35 176	84.87 280	99.04 207	91.06 294	93.44 268	96.60 301
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		94.59 241	93.92 249	96.60 229	96.21 319	94.78 212	98.59 174	98.14 235	91.86 291	94.21 247	97.02 294	87.97 220	98.41 287	91.72 284	89.57 315	96.61 300

ADS-MVSNet2		94.58 242	94.40 225	95.11 303	98.00 204	88.74 347	96.04 358	97.30 314	90.15 330	96.47 185	96.64 320	87.89 222	97.56 344	90.08 308	97.06 193	99.02 163

ACMH	92.88 16	94.55 243	93.95 248	96.34 257	97.63 231	93.26 270	98.81 132	98.49 172	93.43 232	89.74 342	98.53 155	81.91 315	99.08 202	93.69 228	93.30 271	96.70 290
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		94.54 244	93.85 256	96.63 224	97.98 208	93.06 278	98.77 140	97.84 273	93.67 222	93.80 268	98.04 205	76.88 354	98.96 219	94.79 193	92.86 277	97.86 225

XVG-ACMP-BASELINE		94.54 244	94.14 236	95.75 283	96.55 304	91.65 297	98.11 238	98.44 178	94.96 161	94.22 246	97.90 217	79.18 336	99.11 196	94.05 220	93.85 253	96.48 323

AUN-MVS		94.53 246	93.73 266	96.92 205	98.50 157	93.52 260	98.34 205	98.10 243	93.83 207	95.94 202	97.98 212	85.59 266	99.03 208	94.35 207	80.94 371	98.22 215

DIV-MVS_self_test		94.52 247	94.03 240	95.99 270	97.57 238	93.38 266	97.05 325	97.94 266	91.74 292	92.81 300	97.10 278	89.12 189	98.07 318	92.60 259	90.30 305	96.53 312

cl____		94.51 248	94.01 243	96.02 269	97.58 234	93.40 265	97.05 325	97.96 265	91.73 294	92.76 302	97.08 284	89.06 192	98.13 312	92.61 258	90.29 306	96.52 315

GBi-Net		94.49 249	93.80 259	96.56 234	98.21 185	95.00 196	98.82 124	98.18 225	92.46 268	94.09 252	97.07 285	81.16 320	97.95 325	92.08 273	92.14 283	96.72 286

test1		94.49 249	93.80 259	96.56 234	98.21 185	95.00 196	98.82 124	98.18 225	92.46 268	94.09 252	97.07 285	81.16 320	97.95 325	92.08 273	92.14 283	96.72 286

dmvs_re		94.48 251	94.18 233	95.37 295	97.68 226	90.11 325	98.54 184	97.08 324	94.56 175	94.42 235	97.24 271	84.25 295	97.76 337	91.02 297	92.83 278	98.24 213

v8		94.47 252	93.77 262	96.57 233	96.36 314	94.83 208	99.05 65	98.19 222	91.92 288	93.16 290	96.97 299	88.82 201	98.48 270	91.69 285	87.79 338	96.39 327

FMVSNet2		94.47 252	93.61 272	97.04 193	98.21 185	96.43 124	98.79 138	98.27 210	92.46 268	93.50 279	97.09 282	81.16 320	98.00 323	91.09 292	91.93 286	96.70 290

test2506		94.44 254	93.91 251	96.04 268	99.02 108	88.99 344	99.06 63	79.47 401	96.96 65	98.36 92	99.26 55	77.21 351	99.52 154	96.78 132	99.04 121	99.59 77

Patchmatch-test		94.42 255	93.68 270	96.63 224	97.60 233	91.76 293	94.83 374	97.49 300	89.45 343	94.14 250	97.10 278	88.99 193	98.83 239	85.37 355	98.13 166	99.29 125

PEN-MVS		94.42 255	93.73 266	96.49 243	96.28 318	94.84 206	99.17 45	99.00 37	93.51 228	92.23 318	97.83 227	86.10 256	97.90 329	92.55 264	86.92 350	96.74 283

v144192		94.39 257	93.70 268	96.48 245	96.06 327	94.35 230	98.58 176	98.16 232	91.45 300	94.33 240	97.02 294	87.50 233	98.45 275	91.08 293	89.11 324	96.63 298

Baseline_NR-MVSNet		94.35 258	93.81 258	95.96 273	96.20 320	94.05 241	98.61 173	96.67 349	91.44 301	93.85 265	97.60 247	88.57 204	98.14 311	94.39 205	86.93 349	95.68 347

miper_lstm_enhance		94.33 259	94.07 239	95.11 303	97.75 219	90.97 307	97.22 312	98.03 258	91.67 296	92.76 302	96.97 299	90.03 169	97.78 336	92.51 266	89.64 314	96.56 307

v1192		94.32 260	93.58 273	96.53 240	96.10 325	94.45 224	98.50 190	98.17 230	91.54 298	94.19 248	97.06 288	86.95 242	98.43 278	90.14 306	89.57 315	96.70 290

ACMH+	92.99 14	94.30 261	93.77 262	95.88 278	97.81 216	92.04 290	98.71 153	98.37 192	93.99 197	90.60 336	98.47 162	80.86 325	99.05 204	92.75 257	92.40 282	96.55 309

v148		94.29 262	93.76 264	95.91 275	96.10 325	92.93 279	98.58 176	97.97 263	92.59 266	93.47 280	96.95 303	88.53 208	98.32 296	92.56 263	87.06 348	96.49 321

v10		94.29 262	93.55 275	96.51 242	96.39 313	94.80 210	98.99 81	98.19 222	91.35 305	93.02 296	96.99 297	88.09 217	98.41 287	90.50 303	88.41 333	96.33 331

MVP-Stereo		94.28 264	93.92 249	95.35 296	94.95 355	92.60 282	97.97 251	97.65 281	91.61 297	90.68 335	97.09 282	86.32 253	98.42 279	89.70 317	99.34 111	95.02 359
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UniMVSNet_ETH3D		94.24 265	93.33 282	96.97 199	97.19 268	93.38 266	98.74 144	98.57 149	91.21 314	93.81 267	98.58 151	72.85 369	98.77 245	95.05 186	93.93 252	98.77 185

OurMVSNet-221017-0		94.21 266	94.00 244	94.85 312	95.60 341	89.22 339	98.89 103	97.43 307	95.29 142	92.18 319	98.52 158	82.86 311	98.59 259	93.46 236	91.76 288	96.74 283

v1921920		94.20 267	93.47 279	96.40 254	95.98 330	94.08 240	98.52 185	98.15 233	91.33 306	94.25 244	97.20 275	86.41 251	98.42 279	90.04 311	89.39 321	96.69 295

v7n		94.19 268	93.43 280	96.47 246	95.90 333	94.38 229	99.26 27	98.34 197	91.99 286	92.76 302	97.13 277	88.31 211	98.52 267	89.48 322	87.70 339	96.52 315

tpm2		94.19 268	93.76 264	95.46 292	97.23 262	89.04 342	97.31 307	96.85 344	87.08 358	96.21 192	96.79 313	83.75 309	98.74 246	92.43 269	96.23 223	98.59 199

TESTMET0.1,1		94.18 270	93.69 269	95.63 286	96.92 283	89.12 340	96.91 334	94.78 372	93.17 243	94.88 216	96.45 326	78.52 338	98.92 226	93.09 245	98.50 150	98.85 177

dp		94.15 271	93.90 252	94.90 309	97.31 258	86.82 366	96.97 329	97.19 321	91.22 313	96.02 197	96.61 322	85.51 268	99.02 211	90.00 312	94.30 237	98.85 177

ET-MVSNet_ETH3D		94.13 272	92.98 288	97.58 163	98.22 184	96.20 136	97.31 307	95.37 365	94.53 177	79.56 380	97.63 246	86.51 247	97.53 345	96.91 117	90.74 301	99.02 163

tpm		94.13 272	93.80 259	95.12 302	96.50 307	87.91 360	97.44 293	95.89 362	92.62 264	96.37 189	96.30 329	84.13 300	98.30 300	93.24 241	91.66 291	99.14 150

IterMVS-SCA-FT		94.11 274	93.87 254	94.85 312	97.98 208	90.56 318	97.18 317	98.11 240	93.75 210	92.58 308	97.48 255	83.97 303	97.41 348	92.48 268	91.30 294	96.58 303

Anonymous20231211		94.10 275	93.26 285	96.61 227	99.11 101	94.28 232	99.01 76	98.88 60	86.43 361	92.81 300	97.57 250	81.66 317	98.68 252	94.83 190	89.02 327	96.88 267

IterMVS		94.09 276	93.85 256	94.80 315	97.99 206	90.35 321	97.18 317	98.12 237	93.68 220	92.46 314	97.34 263	84.05 301	97.41 348	92.51 266	91.33 293	96.62 299
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test-mter		94.08 277	93.51 277	95.80 280	96.77 291	89.70 330	96.91 334	95.21 367	92.89 256	94.83 219	95.72 346	77.69 346	98.97 215	93.06 246	98.50 150	98.72 186

test0.0.03 1		94.08 277	93.51 277	95.80 280	95.53 344	92.89 280	97.38 298	95.97 359	95.11 152	92.51 312	96.66 317	87.71 227	96.94 355	87.03 343	93.67 258	97.57 236

v1240		94.06 279	93.29 284	96.34 257	96.03 329	93.90 244	98.44 197	98.17 230	91.18 315	94.13 251	97.01 296	86.05 257	98.42 279	89.13 327	89.50 319	96.70 290

X-MVStestdata		94.06 279	92.30 302	99.34 23	99.70 22	98.35 41	99.29 22	98.88 60	97.40 34	98.46 84	43.50 394	95.90 39	99.89 45	97.85 69	99.74 44	99.78 19

DTE-MVSNet		93.98 281	93.26 285	96.14 265	96.06 327	94.39 228	99.20 40	98.86 73	93.06 249	91.78 324	97.81 229	85.87 261	97.58 343	90.53 302	86.17 355	96.46 325

pm-mvs1		93.94 282	93.06 287	96.59 230	96.49 308	95.16 189	98.95 90	98.03 258	92.32 277	91.08 331	97.84 224	84.54 291	98.41 287	92.16 271	86.13 357	96.19 336

MS-PatchMatch		93.84 283	93.63 271	94.46 326	96.18 321	89.45 335	97.76 273	98.27 210	92.23 280	92.13 320	97.49 254	79.50 333	98.69 249	89.75 315	99.38 109	95.25 352

tfpnnormal		93.66 284	92.70 294	96.55 239	96.94 282	95.94 152	98.97 84	99.19 22	91.04 316	91.38 328	97.34 263	84.94 279	98.61 256	85.45 354	89.02 327	95.11 356

EU-MVSNet		93.66 284	94.14 236	92.25 350	95.96 332	83.38 374	98.52 185	98.12 237	94.69 170	92.61 307	98.13 199	87.36 236	96.39 366	91.82 281	90.00 310	96.98 253

our_test_3		93.65 286	93.30 283	94.69 317	95.45 348	89.68 332	96.91 334	97.65 281	91.97 287	91.66 326	96.88 307	89.67 175	97.93 328	88.02 338	91.49 292	96.48 323

pmmvs5		93.65 286	92.97 289	95.68 284	95.49 345	92.37 283	98.20 224	97.28 316	89.66 339	92.58 308	97.26 268	82.14 314	98.09 316	93.18 244	90.95 300	96.58 303

test_fmvs2		93.43 288	93.58 273	92.95 344	96.97 280	83.91 371	99.19 42	97.24 319	95.74 118	95.20 210	98.27 188	69.65 371	98.72 248	96.26 146	93.73 257	96.24 333

tpm cat1		93.36 289	92.80 291	95.07 305	97.58 234	87.97 359	96.76 346	97.86 272	82.17 377	93.53 275	96.04 338	86.13 255	99.13 192	89.24 325	95.87 228	98.10 219

JIA-IIPM		93.35 290	92.49 298	95.92 274	96.48 309	90.65 316	95.01 369	96.96 334	85.93 365	96.08 195	87.33 384	87.70 229	98.78 244	91.35 289	95.58 232	98.34 210

SixPastTwentyTwo		93.34 291	92.86 290	94.75 316	95.67 339	89.41 337	98.75 141	96.67 349	93.89 202	90.15 340	98.25 191	80.87 324	98.27 305	90.90 298	90.64 302	96.57 305

USDC		93.33 292	92.71 293	95.21 299	96.83 290	90.83 312	96.91 334	97.50 298	93.84 205	90.72 334	98.14 198	77.69 346	98.82 240	89.51 321	93.21 273	95.97 341

IB-MVS	91.98 17	93.27 293	91.97 306	97.19 183	97.47 244	93.41 264	97.09 324	95.99 358	93.32 236	92.47 313	95.73 344	78.06 344	99.53 151	94.59 201	82.98 363	98.62 196
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		93.26 294	92.21 303	96.41 252	97.73 223	93.13 275	95.65 365	97.03 329	91.27 311	94.04 255	96.06 337	75.33 359	97.19 351	86.56 345	96.23 223	98.92 174

ppachtmachnet_test		93.22 295	92.63 295	94.97 307	95.45 348	90.84 311	96.88 340	97.88 271	90.60 321	92.08 321	97.26 268	88.08 218	97.86 334	85.12 356	90.33 304	96.22 334

Patchmtry		93.22 295	92.35 301	95.84 279	96.77 291	93.09 277	94.66 377	97.56 288	87.37 357	92.90 298	96.24 330	88.15 215	97.90 329	87.37 342	90.10 309	96.53 312

testing3		93.19 297	92.48 299	95.30 298	98.07 199	92.27 284	98.64 167	97.17 322	93.94 201	93.98 258	97.04 291	67.97 375	96.01 370	88.40 333	97.14 192	97.63 233

FMVSNet1		93.19 297	92.07 304	96.56 234	97.54 239	95.00 196	98.82 124	98.18 225	90.38 327	92.27 317	97.07 285	73.68 367	97.95 325	89.36 324	91.30 294	96.72 286

LF4IMVS		93.14 299	92.79 292	94.20 329	95.88 334	88.67 348	97.66 281	97.07 326	93.81 208	91.71 325	97.65 242	77.96 345	98.81 241	91.47 288	91.92 287	95.12 355

testgi		93.06 300	92.45 300	94.88 311	96.43 312	89.90 326	98.75 141	97.54 294	95.60 125	91.63 327	97.91 216	74.46 364	97.02 353	86.10 348	93.67 258	97.72 230

PatchT		93.06 300	91.97 306	96.35 256	96.69 297	92.67 281	94.48 378	97.08 324	86.62 359	97.08 153	92.23 378	87.94 221	97.90 329	78.89 377	96.69 203	98.49 204

RPMNet		92.81 302	91.34 311	97.24 180	97.00 277	93.43 262	94.96 370	98.80 91	82.27 376	96.93 161	92.12 379	86.98 241	99.82 74	76.32 382	96.65 205	98.46 205

myMVS_eth3d		92.73 303	92.01 305	94.89 310	97.39 254	90.94 308	97.91 256	97.46 301	93.16 244	93.42 282	95.37 351	68.09 374	96.12 368	88.34 334	96.99 195	97.60 234

TransMVSNet (Re)		92.67 304	91.51 310	96.15 264	96.58 303	94.65 213	98.90 99	96.73 345	90.86 319	89.46 346	97.86 221	85.62 265	98.09 316	86.45 346	81.12 369	95.71 346

Syy-MVS		92.55 305	92.61 296	92.38 347	97.39 254	83.41 373	97.91 256	97.46 301	93.16 244	93.42 282	95.37 351	84.75 284	96.12 368	77.00 381	96.99 195	97.60 234

K. test v3		92.55 305	91.91 308	94.48 324	95.64 340	89.24 338	99.07 62	94.88 371	94.04 192	86.78 361	97.59 248	77.64 349	97.64 340	92.08 273	89.43 320	96.57 305

DSMNet-mixed		92.52 307	92.58 297	92.33 348	94.15 363	82.65 376	98.30 213	94.26 378	89.08 348	92.65 306	95.73 344	85.01 278	95.76 372	86.24 347	97.76 179	98.59 199

TinyColmap		92.31 308	91.53 309	94.65 319	96.92 283	89.75 328	96.92 332	96.68 348	90.45 325	89.62 343	97.85 223	76.06 357	98.81 241	86.74 344	92.51 281	95.41 350

gg-mvs-nofinetune		92.21 309	90.58 317	97.13 188	96.75 294	95.09 193	95.85 362	89.40 394	85.43 369	94.50 228	81.98 387	80.80 326	98.40 293	92.16 271	98.33 160	97.88 223

FMVSNet5		91.81 310	90.92 313	94.49 323	97.21 264	92.09 287	98.00 249	97.55 293	89.31 346	90.86 333	95.61 349	74.48 363	95.32 376	85.57 352	89.70 313	96.07 339

pmmvs6		91.77 311	90.63 316	95.17 301	94.69 361	91.24 304	98.67 163	97.92 268	86.14 363	89.62 343	97.56 252	75.79 358	98.34 294	90.75 300	84.56 359	95.94 342

Anonymous20231206		91.66 312	91.10 312	93.33 338	94.02 367	87.35 363	98.58 176	97.26 318	90.48 323	90.16 339	96.31 328	83.83 307	96.53 364	79.36 375	89.90 311	96.12 337

Patchmatch-RL test		91.49 313	90.85 314	93.41 336	91.37 376	84.40 369	92.81 382	95.93 361	91.87 290	87.25 358	94.87 357	88.99 193	96.53 364	92.54 265	82.00 365	99.30 123

test_0402		91.32 314	90.27 320	94.48 324	96.60 301	91.12 305	98.50 190	97.22 320	86.10 364	88.30 354	96.98 298	77.65 348	97.99 324	78.13 379	92.94 276	94.34 363

test_vis1_rt		91.29 315	90.65 315	93.19 342	97.45 248	86.25 367	98.57 181	90.90 392	93.30 238	86.94 360	93.59 369	62.07 382	99.11 196	97.48 98	95.58 232	94.22 366

PVSNet_0	88.72 19	91.28 316	90.03 322	95.00 306	97.99 206	87.29 364	94.84 373	98.50 167	92.06 285	89.86 341	95.19 353	79.81 332	99.39 167	92.27 270	69.79 387	98.33 211

Anonymous20240521		91.18 317	90.44 318	93.42 335	93.70 368	88.47 352	98.94 93	97.56 288	88.46 352	89.56 345	95.08 356	77.15 353	96.97 354	83.92 362	89.55 317	94.82 361

EG-PatchMatch MVS		91.13 318	90.12 321	94.17 331	94.73 360	89.00 343	98.13 235	97.81 274	89.22 347	85.32 371	96.46 325	67.71 376	98.42 279	87.89 340	93.82 254	95.08 357

TDRefinement		91.06 319	89.68 324	95.21 299	85.35 391	91.49 300	98.51 189	97.07 326	91.47 299	88.83 352	97.84 224	77.31 350	99.09 201	92.79 256	77.98 380	95.04 358

UnsupCasMVSNet_eth		90.99 320	89.92 323	94.19 330	94.08 364	89.83 327	97.13 323	98.67 126	93.69 218	85.83 367	96.19 335	75.15 360	96.74 358	89.14 326	79.41 376	96.00 340

test20.03		90.89 321	90.38 319	92.43 346	93.48 369	88.14 358	98.33 206	97.56 288	93.40 233	87.96 355	96.71 316	80.69 327	94.13 381	79.15 376	86.17 355	95.01 360

MDA-MVSNet_test_wron		90.71 322	89.38 327	94.68 318	94.83 357	90.78 313	97.19 316	97.46 301	87.60 355	72.41 387	95.72 346	86.51 247	96.71 361	85.92 350	86.80 352	96.56 307

YYNet1		90.70 323	89.39 326	94.62 320	94.79 359	90.65 316	97.20 314	97.46 301	87.54 356	72.54 386	95.74 342	86.51 247	96.66 362	86.00 349	86.76 353	96.54 310

KD-MVS_self_test		90.38 324	89.38 327	93.40 337	92.85 372	88.94 345	97.95 252	97.94 266	90.35 328	90.25 338	93.96 366	79.82 331	95.94 371	84.62 361	76.69 382	95.33 351

pmmvs-eth3d		90.36 325	89.05 330	94.32 328	91.10 378	92.12 286	97.63 286	96.95 335	88.86 350	84.91 372	93.13 373	78.32 340	96.74 358	88.70 330	81.81 367	94.09 369

CL-MVSNet_self_test		90.11 326	89.14 329	93.02 343	91.86 375	88.23 357	96.51 354	98.07 250	90.49 322	90.49 337	94.41 361	84.75 284	95.34 375	80.79 371	74.95 384	95.50 349

new_pmnet		90.06 327	89.00 331	93.22 341	94.18 362	88.32 355	96.42 356	96.89 340	86.19 362	85.67 368	93.62 368	77.18 352	97.10 352	81.61 369	89.29 322	94.23 365

MDA-MVSNet-bldmvs		89.97 328	88.35 334	94.83 314	95.21 352	91.34 301	97.64 283	97.51 297	88.36 353	71.17 388	96.13 336	79.22 335	96.63 363	83.65 363	86.27 354	96.52 315

CMPMVS	66.06 21	89.70 329	89.67 325	89.78 355	93.19 370	76.56 381	97.00 328	98.35 195	80.97 378	81.57 377	97.75 232	74.75 362	98.61 256	89.85 313	93.63 261	94.17 367
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet1		89.67 330	88.28 335	93.82 332	92.81 373	91.08 306	98.01 247	97.45 305	87.95 354	87.90 356	95.87 341	67.63 377	94.56 380	78.73 378	88.18 335	95.83 344

KD-MVS_2432*1600		89.61 331	87.96 338	94.54 321	94.06 365	91.59 298	95.59 366	97.63 283	89.87 335	88.95 349	94.38 363	78.28 341	96.82 356	84.83 357	68.05 388	95.21 353

miper_refine_blended		89.61 331	87.96 338	94.54 321	94.06 365	91.59 298	95.59 366	97.63 283	89.87 335	88.95 349	94.38 363	78.28 341	96.82 356	84.83 357	68.05 388	95.21 353

MVS-HIRNet		89.46 333	88.40 333	92.64 345	97.58 234	82.15 377	94.16 381	93.05 386	75.73 383	90.90 332	82.52 386	79.42 334	98.33 295	83.53 364	98.68 138	97.43 237

OpenMVS_ROB	86.42 20	89.00 334	87.43 342	93.69 333	93.08 371	89.42 336	97.91 256	96.89 340	78.58 380	85.86 366	94.69 358	69.48 372	98.29 303	77.13 380	93.29 272	93.36 375

mvsany_test3		88.80 335	88.04 336	91.09 354	89.78 381	81.57 379	97.83 269	95.49 364	93.81 208	87.53 357	93.95 367	56.14 385	97.43 347	94.68 194	83.13 362	94.26 364

new-patchmatchnet		88.50 336	87.45 341	91.67 352	90.31 380	85.89 368	97.16 321	97.33 313	89.47 342	83.63 374	92.77 375	76.38 355	95.06 378	82.70 366	77.29 381	94.06 371

APD_test1		88.22 337	88.01 337	88.86 357	95.98 330	74.66 387	97.21 313	96.44 353	83.96 374	86.66 363	97.90 217	60.95 383	97.84 335	82.73 365	90.23 307	94.09 369

PM-MVS		87.77 338	86.55 344	91.40 353	91.03 379	83.36 375	96.92 332	95.18 369	91.28 310	86.48 365	93.42 370	53.27 386	96.74 358	89.43 323	81.97 366	94.11 368

dmvs_testset		87.64 339	88.93 332	83.79 365	95.25 351	63.36 396	97.20 314	91.17 390	93.07 248	85.64 369	95.98 340	85.30 275	91.52 388	69.42 387	87.33 344	96.49 321

test_fmvs3		87.17 340	87.06 343	87.50 359	91.21 377	75.66 383	99.05 65	96.61 351	92.79 260	88.85 351	92.78 374	43.72 389	93.49 382	93.95 221	84.56 359	93.34 376

UnsupCasMVSNet_bld		87.17 340	85.12 347	93.31 339	91.94 374	88.77 346	94.92 372	98.30 207	84.30 373	82.30 375	90.04 381	63.96 381	97.25 350	85.85 351	74.47 386	93.93 373

N_pmnet		87.12 342	87.77 340	85.17 363	95.46 347	61.92 397	97.37 300	70.66 402	85.83 366	88.73 353	96.04 338	85.33 273	97.76 337	80.02 372	90.48 303	95.84 343

pmmvs3		86.67 343	84.86 348	92.11 351	88.16 385	87.19 365	96.63 350	94.75 373	79.88 379	87.22 359	92.75 376	66.56 379	95.20 377	81.24 370	76.56 383	93.96 372

test_f		86.07 344	85.39 345	88.10 358	89.28 383	75.57 384	97.73 276	96.33 355	89.41 345	85.35 370	91.56 380	43.31 391	95.53 373	91.32 290	84.23 361	93.21 377

WB-MVS		84.86 345	85.33 346	83.46 366	89.48 382	69.56 391	98.19 227	96.42 354	89.55 341	81.79 376	94.67 359	84.80 282	90.12 389	52.44 392	80.64 373	90.69 380

SSC-MVS		84.27 346	84.71 349	82.96 370	89.19 384	68.83 392	98.08 240	96.30 356	89.04 349	81.37 378	94.47 360	84.60 289	89.89 390	49.80 394	79.52 375	90.15 381

test_vis3_rt		79.22 347	77.40 353	84.67 364	86.44 389	74.85 386	97.66 281	81.43 399	84.98 370	67.12 390	81.91 388	28.09 399	97.60 341	88.96 328	80.04 374	81.55 388

test_method		79.03 348	78.17 350	81.63 371	86.06 390	54.40 402	82.75 390	96.89 340	39.54 394	80.98 379	95.57 350	58.37 384	94.73 379	84.74 360	78.61 377	95.75 345

testf1		79.02 349	77.70 351	82.99 368	88.10 386	66.90 393	94.67 375	93.11 383	71.08 385	74.02 383	93.41 371	34.15 395	93.25 383	72.25 385	78.50 378	88.82 383

APD_test2		79.02 349	77.70 351	82.99 368	88.10 386	66.90 393	94.67 375	93.11 383	71.08 385	74.02 383	93.41 371	34.15 395	93.25 383	72.25 385	78.50 378	88.82 383

LCM-MVSNet		78.70 351	76.24 356	86.08 361	77.26 397	71.99 389	94.34 379	96.72 346	61.62 389	76.53 381	89.33 382	33.91 397	92.78 386	81.85 368	74.60 385	93.46 374

Gipuma		78.40 352	76.75 355	83.38 367	95.54 343	80.43 380	79.42 391	97.40 309	64.67 388	73.46 385	80.82 389	45.65 388	93.14 385	66.32 389	87.43 342	76.56 391
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		77.95 353	75.44 357	85.46 362	82.54 392	74.95 385	94.23 380	93.08 385	72.80 384	74.68 382	87.38 383	36.36 394	91.56 387	73.95 383	63.94 390	89.87 382

FPMVS		77.62 354	77.14 354	79.05 373	79.25 395	60.97 398	95.79 363	95.94 360	65.96 387	67.93 389	94.40 362	37.73 393	88.88 392	68.83 388	88.46 332	87.29 385

EGC-MVSNET		75.22 355	69.54 358	92.28 349	94.81 358	89.58 333	97.64 283	96.50 352	1.82 399	5.57 400	95.74 342	68.21 373	96.26 367	73.80 384	91.71 289	90.99 379

ANet_high		69.08 356	65.37 360	80.22 372	65.99 399	71.96 390	90.91 386	90.09 393	82.62 375	49.93 395	78.39 390	29.36 398	81.75 393	62.49 390	38.52 394	86.95 387

tmp_tt		68.90 357	66.97 359	74.68 375	50.78 401	59.95 399	87.13 387	83.47 398	38.80 395	62.21 391	96.23 332	64.70 380	76.91 397	88.91 329	30.49 395	87.19 386

PMVS	61.03 23	65.95 358	63.57 362	73.09 376	57.90 400	51.22 403	85.05 389	93.93 382	54.45 390	44.32 396	83.57 385	13.22 400	89.15 391	58.68 391	81.00 370	78.91 390
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		64.94 359	64.25 361	67.02 377	82.28 393	59.36 400	91.83 385	85.63 396	52.69 391	60.22 392	77.28 391	41.06 392	80.12 395	46.15 395	41.14 392	61.57 393

EMVS		64.07 360	63.26 363	66.53 378	81.73 394	58.81 401	91.85 384	84.75 397	51.93 393	59.09 393	75.13 392	43.32 390	79.09 396	42.03 396	39.47 393	61.69 392

MVE	62.14 22	63.28 361	59.38 364	74.99 374	74.33 398	65.47 395	85.55 388	80.50 400	52.02 392	51.10 394	75.00 393	10.91 403	80.50 394	51.60 393	53.40 391	78.99 389
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		30.17 362	30.18 366	30.16 379	78.61 396	43.29 404	66.79 392	14.21 403	17.31 396	14.82 399	11.93 399	11.55 402	41.43 398	37.08 397	19.30 396	5.76 396

cdsmvs_eth3d_5k		23.98 363	31.98 365	0.00 382	0.00 404	0.00 407	0.00 393	98.59 142	0.00 400	0.00 401	98.61 146	90.60 160	0.00 401	0.00 400	0.00 399	0.00 397

testmvs		21.48 364	24.95 367	11.09 381	14.89 402	6.47 406	96.56 352	9.87 404	7.55 397	17.93 397	39.02 395	9.43 404	5.90 400	16.56 399	12.72 397	20.91 395

test123		20.95 365	23.72 368	12.64 380	13.54 403	8.19 405	96.55 353	6.13 405	7.48 398	16.74 398	37.98 396	12.97 401	6.05 399	16.69 398	5.43 398	23.68 394

ab-mvs-re		8.20 366	10.94 369	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	98.43 166	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

pcd_1.5k_mvsjas		7.88 367	10.50 370	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	94.51 79	0.00 401	0.00 400	0.00 399	0.00 397

test_blank		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uanet_test		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

DCPMVS		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

sosnet-low-res		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

sosnet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uncertanet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

Regformer		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uanet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

MM				99.33 26		98.14 54	98.93 95	97.02 331	98.96 1	99.17 39	99.47 20	91.97 127	99.94 6	99.85 2	99.69 54	99.91 2

WAC-MVS						90.94 308								88.66 331

FOURS1					99.82 1	98.66 24	99.69 1	98.95 44	97.46 32	99.39 28

MSC_two_6792asdad				99.62 6	99.17 92	99.08 11		98.63 136					99.94 6	98.53 28	99.80 19	99.86 6

PC_three_1452									95.08 156	99.60 17	99.16 75	97.86 2	98.47 273	97.52 96	99.72 49	99.74 35

No_MVS				99.62 6	99.17 92	99.08 11		98.63 136					99.94 6	98.53 28	99.80 19	99.86 6

test_one_0601					99.66 26	99.25 2		98.86 73	97.55 26	99.20 36	99.47 20	97.57 6

eth-test2					0.00 404

eth-test					0.00 404

ZD-MVS					99.46 49	98.70 23		98.79 96	93.21 241	98.67 71	98.97 103	95.70 43	99.83 67	96.07 150	99.58 77

RE-MVS-def			98.34 33		99.49 45	97.86 62	99.11 55	98.80 91	96.49 84	99.17 39	99.35 42	95.29 59		97.72 78	99.65 62	99.71 47

IU-MVS					99.71 19	99.23 7		98.64 134	95.28 143	99.63 16				98.35 45	99.81 12	99.83 11

OPU-MVS				99.37 20	99.24 85	99.05 14	99.02 74				99.16 75	97.81 3	99.37 168	97.24 105	99.73 46	99.70 51

test_241102_TWO								98.87 67	97.65 20	99.53 21	99.48 18	97.34 11	99.94 6	98.43 40	99.80 19	99.83 11

test_241102_ONE					99.71 19	99.24 5		98.87 67	97.62 22	99.73 8	99.39 30	97.53 7	99.74 109

9.14			98.06 55		99.47 47		98.71 153	98.82 79	94.36 184	99.16 42	99.29 51	96.05 31	99.81 79	97.00 112	99.71 51

save fliter					99.46 49	98.38 35	98.21 222	98.71 114	97.95 11

test_0728_THIRD									97.32 40	99.45 23	99.46 24	97.88 1	99.94 6	98.47 36	99.86 1	99.85 8

test_0728_SECOND				99.71 1	99.72 12	99.35 1	98.97 84	98.88 60					99.94 6	98.47 36	99.81 12	99.84 10

test0726					99.72 12	99.25 2	99.06 63	98.88 60	97.62 22	99.56 18	99.50 15	97.42 9

GSMVS																99.20 137

test_part2					99.63 29	99.18 10				99.27 33

sam_mvs1												89.45 179				99.20 137

sam_mvs												88.99 193

ambc				89.49 356	86.66 388	75.78 382	92.66 383	96.72 346		86.55 364	92.50 377	46.01 387	97.90 329	90.32 304	82.09 364	94.80 362

MTGPA								98.74 106

test_post1							96.68 349				30.43 398	87.85 225	98.69 249	92.59 261

test_post											31.83 397	88.83 200	98.91 227

patchmatchnet-post											95.10 355	89.42 180	98.89 231

GG-mvs-BLEND				96.59 230	96.34 316	94.98 199	96.51 354	88.58 395		93.10 295	94.34 365	80.34 330	98.05 319	89.53 320	96.99 195	96.74 283

MTMP							98.89 103	94.14 380

gm-plane-assit					95.88 334	87.47 362			89.74 338		96.94 304		99.19 184	93.32 240

test9_res														96.39 144	99.57 78	99.69 54

TEST9					99.31 62	98.50 29	97.92 254	98.73 109	92.63 263	97.74 128	98.68 140	96.20 26	99.80 86

test_8					99.29 71	98.44 31	97.89 262	98.72 111	92.98 252	97.70 132	98.66 143	96.20 26	99.80 86

agg_prior2														95.87 160	99.57 78	99.68 59

agg_prior					99.30 66	98.38 35		98.72 111		97.57 142			99.81 79

TestCases				96.99 196	99.25 79	93.21 273		98.18 225	91.36 303	93.52 276	98.77 130	84.67 287	99.72 111	89.70 317	97.87 174	98.02 221

test_prior4						98.01 59	97.86 265

test_prior2							97.80 270		96.12 101	97.89 122	98.69 139	95.96 35		96.89 121	99.60 72

test_prior				99.19 40	99.31 62	98.22 47		98.84 77					99.70 117			99.65 67

旧先验2							97.57 289		91.30 308	98.67 71			99.80 86	95.70 168

新几何2							97.64 283

新几何1				99.16 45	99.34 55	98.01 59		98.69 118	90.06 332	98.13 99	98.95 110	94.60 77	99.89 45	91.97 279	99.47 97	99.59 77

旧先验1					99.29 71	97.48 75		98.70 117			99.09 90	95.56 46			99.47 97	99.61 73

无先验							97.58 288	98.72 111	91.38 302				99.87 56	93.36 239		99.60 75

原ACMM2							97.67 280

原ACMM1				98.65 73	99.32 60	96.62 110		98.67 126	93.27 240	97.81 123	98.97 103	95.18 65	99.83 67	93.84 225	99.46 100	99.50 89

test222					99.23 86	97.17 90	97.40 296	98.66 129	88.68 351	98.05 104	98.96 108	94.14 91			99.53 89	99.61 73

testdata2													99.89 45	91.65 286

segment_acmp												96.85 14

testdata				98.26 108	99.20 90	95.36 179		98.68 121	91.89 289	98.60 79	99.10 84	94.44 84	99.82 74	94.27 211	99.44 101	99.58 81

testdata1							97.32 306		96.34 93

test12				99.18 42	99.16 96	98.19 48		98.53 157		98.07 103		95.13 68	99.72 111		99.56 84	99.63 71

plane_prior7					97.42 250	94.63 215

plane_prior6					97.35 257	94.61 218						87.09 238

plane_prior5								98.56 151					99.03 208	96.07 150	94.27 238	96.92 258

plane_prior4											98.28 185

plane_prior3						94.61 218			97.02 62	95.34 207

plane_prior2							98.80 133		97.28 43

plane_prior1					97.37 256

plane_prior						94.60 220	98.44 197		96.74 75						94.22 240

n2								0.00 406

nn								0.00 406

door-mid								94.37 376

lessismore_v0				94.45 327	94.93 356	88.44 353		91.03 391		86.77 362	97.64 244	76.23 356	98.42 279	90.31 305	85.64 358	96.51 318

LGP-MVS_train				96.47 246	97.46 245	93.54 257		98.54 155	94.67 172	94.36 238	98.77 130	85.39 269	99.11 196	95.71 166	94.15 244	96.76 281

test11								98.66 129

door								94.64 374

HQP5-MVS						94.25 235

HQP-NCC					97.20 265		98.05 243		96.43 87	94.45 230

ACMP_Plane					97.20 265		98.05 243		96.43 87	94.45 230

BP-MVS														95.30 178

HQP4-MVS										94.45 230			98.96 219			96.87 269

HQP3-MVS								98.46 174							94.18 242

HQP2-MVS												86.75 244

NP-MVS					97.28 259	94.51 223					97.73 233

MDTV_nov1_ep13_2view						84.26 370	96.89 339		90.97 317	97.90 121		89.89 171		93.91 223		99.18 146

MDTV_nov1_ep13			95.40 168		97.48 243	88.34 354	96.85 342	97.29 315	93.74 212	97.48 144	97.26 268	89.18 187	99.05 204	91.92 280	97.43 188

ACMMP++_ref															92.97 275

ACMMP++															93.61 262

Test By Simon												94.64 76

ITE_SJBPF				95.44 293	97.42 250	91.32 302		97.50 298	95.09 155	93.59 272	98.35 176	81.70 316	98.88 233	89.71 316	93.39 269	96.12 337

DeepMVS_CX				86.78 360	97.09 275	72.30 388		95.17 370	75.92 382	84.34 373	95.19 353	70.58 370	95.35 374	79.98 374	89.04 326	92.68 378

High-resolution multi-view benchmark