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.

PC_three_1452									82.47 237	97.09 10	97.07 51	92.72 1	98.04 163	92.70 55	99.02 12	98.86 11

DVP-MVS++		95.98 1	96.36 1	94.82 31	97.78 51	86.00 50	98.29 1	97.49 6	90.75 19	97.62 5	98.06 11	92.59 2	99.61 4	95.64 19	99.02 12	98.86 11

OPU-MVS				96.21 3	98.00 42	90.85 3	97.13 14				97.08 49	92.59 2	98.94 78	92.25 65	98.99 14	98.84 14

SED-MVS		95.91 2	96.28 2	94.80 33	98.77 5	85.99 52	97.13 14	97.44 15	90.31 28	97.71 1	98.07 9	92.31 4	99.58 10	95.66 17	99.13 3	98.84 14

test_241102_ONE					98.77 5	85.99 52		97.44 15	90.26 33	97.71 1	97.96 17	92.31 4	99.38 31

test_0728_THIRD									90.75 19	97.04 11	98.05 13	92.09 6	99.55 16	95.64 19	99.13 3	99.13 2

DPE-MVS		95.57 4	95.67 4	95.25 10	98.36 25	87.28 18	95.56 96	97.51 5	89.13 65	97.14 9	97.91 18	91.64 7	99.62 2	94.61 27	99.17 2	98.86 11
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		95.67 3	96.02 3	94.64 39	98.78 3	85.93 55	97.09 16	96.73 79	90.27 31	97.04 11	98.05 13	91.47 8	99.55 16	95.62 21	99.08 7	98.45 36
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
test0726					98.78 3	85.93 55	97.19 11	97.47 11	90.27 31	97.64 4	98.13 3	91.47 8

test_241102_TWO								97.44 15	90.31 28	97.62 5	98.07 9	91.46 10	99.58 10	95.66 17	99.12 6	98.98 10

test_one_0601					98.58 11	85.83 61		97.44 15	91.05 14	96.78 15	98.06 11	91.45 11

MSP-MVS		95.42 6	95.56 6	94.98 19	98.49 17	86.52 36	96.91 25	97.47 11	91.73 10	96.10 20	96.69 66	89.90 12	99.30 40	94.70 25	98.04 67	99.13 2
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
DeepPCF-MVS	89.96 1	94.20 34	94.77 17	92.49 116	96.52 87	80.00 221	94.00 195	97.08 44	90.05 35	95.65 29	97.29 37	89.66 13	98.97 75	93.95 33	98.71 33	98.50 27

SD-MVS		94.96 13	95.33 8	93.88 59	97.25 69	86.69 28	96.19 51	97.11 43	90.42 27	96.95 13	97.27 38	89.53 14	96.91 254	94.38 29	98.85 19	98.03 72
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
CNVR-MVS		95.40 7	95.37 7	95.50 8	98.11 36	88.51 7	95.29 107	96.96 52	92.09 6	95.32 31	97.08 49	89.49 15	99.33 37	95.10 24	98.85 19	98.66 20

APDe-MVS		95.46 5	95.64 5	94.91 21	98.26 28	86.29 46	97.46 6	97.40 20	89.03 69	96.20 19	98.10 7	89.39 16	99.34 34	95.88 16	99.03 11	99.10 4
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MCST-MVS		94.45 22	94.20 35	95.19 13	98.46 19	87.50 15	95.00 126	97.12 41	87.13 124	92.51 85	96.30 83	89.24 17	99.34 34	93.46 39	98.62 45	98.73 17

TSAR-MVS + MP.		94.85 14	94.94 12	94.58 42	98.25 29	86.33 42	96.11 61	96.62 88	88.14 100	96.10 20	96.96 55	89.09 18	98.94 78	94.48 28	98.68 38	98.48 30
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SteuartSystems-ACMMP		95.20 8	95.32 9	94.85 25	96.99 72	86.33 42	97.33 7	97.30 29	91.38 12	95.39 30	97.46 30	88.98 19	99.40 30	94.12 31	98.89 18	98.82 16
Skip Steuart: Steuart Systems R&D Blog.
SMA-MVS		95.20 8	95.07 11	95.59 6	98.14 35	88.48 8	96.26 48	97.28 31	85.90 157	97.67 3	98.10 7	88.41 20	99.56 12	94.66 26	99.19 1	98.71 19
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
patch_mono-2		93.74 47	94.32 26	92.01 134	97.54 57	78.37 259	93.40 219	97.19 35	88.02 103	94.99 35	97.21 42	88.35 21	98.44 124	94.07 32	98.09 64	99.23 1

9.14			94.47 20		97.79 49		96.08 62	97.44 15	86.13 155	95.10 33	97.40 33	88.34 22	99.22 44	93.25 44	98.70 35

SF-MVS		94.97 12	94.90 15	95.20 12	97.84 47	87.76 10	96.65 35	97.48 10	87.76 113	95.71 27	97.70 25	88.28 23	99.35 33	93.89 35	98.78 25	98.48 30

HPM-MVS++		95.14 10	94.91 13	95.83 4	98.25 29	89.65 4	95.92 75	96.96 52	91.75 9	94.02 47	96.83 61	88.12 24	99.55 16	93.41 42	98.94 16	98.28 50

dcpmvs_2		93.49 52	94.19 36	91.38 168	97.69 54	76.78 291	94.25 174	96.29 107	88.33 90	94.46 38	96.88 58	88.07 25	98.64 100	93.62 38	98.09 64	98.73 17

CSCG		93.23 64	93.05 63	93.76 66	98.04 40	84.07 98	96.22 50	97.37 21	84.15 197	90.05 131	95.66 112	87.77 26	99.15 50	89.91 110	98.27 57	98.07 68

NCCC		94.81 15	94.69 18	95.17 14	97.83 48	87.46 17	95.66 89	96.93 56	92.34 4	93.94 48	96.58 76	87.74 27	99.44 29	92.83 50	98.40 53	98.62 21

TEST9					97.53 58	86.49 37	94.07 187	96.78 72	81.61 263	92.77 76	96.20 87	87.71 28	99.12 51

train_agg		93.44 55	93.08 62	94.52 44	97.53 58	86.49 37	94.07 187	96.78 72	81.86 254	92.77 76	96.20 87	87.63 29	99.12 51	92.14 70	98.69 36	97.94 76

test_8					97.49 60	86.30 45	94.02 192	96.76 75	81.86 254	92.70 80	96.20 87	87.63 29	99.02 61

ZD-MVS					98.15 34	86.62 33		97.07 45	83.63 209	94.19 42	96.91 57	87.57 31	99.26 42	91.99 76	98.44 52

fmvsm_l_conf0.5_n		94.29 28	94.46 21	93.79 65	95.28 136	85.43 68	95.68 86	96.43 97	86.56 139	96.84 14	97.81 23	87.56 32	98.77 92	97.14 6	96.82 97	97.16 114

fmvsm_l_conf0.5_n_a		94.20 34	94.40 23	93.60 69	95.29 135	84.98 73	95.61 93	96.28 110	86.31 145	96.75 16	97.86 21	87.40 33	98.74 95	97.07 8	97.02 90	97.07 116

TSAR-MVS + GP.		93.66 49	93.41 56	94.41 49	96.59 82	86.78 26	94.40 164	93.93 252	89.77 47	94.21 41	95.59 115	87.35 34	98.61 105	92.72 53	96.15 110	97.83 85

APD-MVS		94.24 30	94.07 39	94.75 36	98.06 39	86.90 23	95.88 76	96.94 55	85.68 163	95.05 34	97.18 45	87.31 35	99.07 53	91.90 82	98.61 47	98.28 50
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
segment_acmp												87.16 36

旧先验1					96.79 76	81.81 165		95.67 162			96.81 63	86.69 37			97.66 80	96.97 126

test_prior2							94.12 181		87.67 116	92.63 81	96.39 82	86.62 38		91.50 87	98.67 40

CDPH-MVS		92.83 71	92.30 77	94.44 45	97.79 49	86.11 49	94.06 189	96.66 85	80.09 283	92.77 76	96.63 73	86.62 38	99.04 57	87.40 138	98.66 41	98.17 62

DPM-MVS		92.58 75	91.74 83	95.08 15	96.19 95	89.31 5	92.66 250	96.56 93	83.44 215	91.68 109	95.04 134	86.60 40	98.99 70	85.60 162	97.92 71	96.93 128

test_fmvsmconf_n		94.60 18	94.81 16	93.98 55	94.62 173	84.96 74	96.15 56	97.35 22	89.37 56	96.03 23	98.11 5	86.36 41	99.01 63	97.45 3	97.83 74	97.96 75

DELS-MVS		93.43 58	93.25 59	93.97 56	95.42 131	85.04 72	93.06 238	97.13 40	90.74 21	91.84 103	95.09 133	86.32 42	99.21 45	91.22 90	98.45 51	97.65 91
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
test_fmvsm_n_1920		94.71 17	95.11 10	93.50 71	95.79 115	84.62 80	96.15 56	97.64 2	89.85 42	97.19 8	97.89 19	86.28 43	98.71 97	97.11 7	98.08 66	97.17 110

ZNCC-MVS		94.47 21	94.28 30	95.03 16	98.52 15	86.96 20	96.85 28	97.32 27	88.24 94	93.15 63	97.04 52	86.17 44	99.62 2	92.40 59	98.81 22	98.52 26

HFP-MVS		94.52 20	94.40 23	94.86 24	98.61 10	86.81 25	96.94 20	97.34 23	88.63 82	93.65 53	97.21 42	86.10 45	99.49 26	92.35 62	98.77 27	98.30 47

MVS_111021_HR		93.45 54	93.31 57	93.84 61	96.99 72	84.84 75	93.24 231	97.24 32	88.76 77	91.60 110	95.85 103	86.07 46	98.66 98	91.91 80	98.16 60	98.03 72

ACMMP_NAP		94.74 16	94.56 19	95.28 9	98.02 41	87.70 11	95.68 86	97.34 23	88.28 93	95.30 32	97.67 26	85.90 47	99.54 20	93.91 34	98.95 15	98.60 23

CS-MVS		94.12 37	94.44 22	93.17 78	96.55 84	83.08 131	97.63 3	96.95 54	91.71 11	93.50 59	96.21 86	85.61 48	98.24 140	93.64 37	98.17 59	98.19 60

PHI-MVS		93.89 43	93.65 54	94.62 41	96.84 75	86.43 39	96.69 32	97.49 6	85.15 177	93.56 57	96.28 84	85.60 49	99.31 39	92.45 56	98.79 23	98.12 66

MP-MVS-pluss		94.21 32	94.00 42	94.85 25	98.17 33	86.65 31	94.82 137	97.17 39	86.26 147	92.83 73	97.87 20	85.57 50	99.56 12	94.37 30	98.92 17	98.34 42
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
GST-MVS		94.21 32	93.97 43	94.90 23	98.41 22	86.82 24	96.54 37	97.19 35	88.24 94	93.26 60	96.83 61	85.48 51	99.59 8	91.43 89	98.40 53	98.30 47

MP-MVS		94.25 29	94.07 39	94.77 35	98.47 18	86.31 44	96.71 31	96.98 49	89.04 68	91.98 96	97.19 44	85.43 52	99.56 12	92.06 75	98.79 23	98.44 37
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DeepC-MVS_fast	89.43 2	94.04 38	93.79 46	94.80 33	97.48 61	86.78 26	95.65 91	96.89 60	89.40 55	92.81 74	96.97 54	85.37 53	99.24 43	90.87 99	98.69 36	98.38 41
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
region2R		94.43 24	94.27 32	94.92 20	98.65 8	86.67 30	96.92 24	97.23 34	88.60 84	93.58 55	97.27 38	85.22 54	99.54 20	92.21 66	98.74 31	98.56 25

CP-MVS		94.34 27	94.21 34	94.74 37	98.39 23	86.64 32	97.60 4	97.24 32	88.53 86	92.73 79	97.23 41	85.20 55	99.32 38	92.15 69	98.83 21	98.25 57

test_fmvsmconf0.1_n		94.20 34	94.31 28	93.88 59	92.46 257	84.80 77	96.18 53	96.82 68	89.29 59	95.68 28	98.11 5	85.10 56	98.99 70	97.38 4	97.75 78	97.86 82

test12				94.34 50	97.13 70	86.15 48		96.29 107		91.04 118		85.08 57	99.01 63		98.13 62	97.86 82

ACMMPR		94.43 24	94.28 30	94.91 21	98.63 9	86.69 28	96.94 20	97.32 27	88.63 82	93.53 58	97.26 40	85.04 58	99.54 20	92.35 62	98.78 25	98.50 27

CS-MVS-test		94.02 39	94.29 29	93.24 75	96.69 78	83.24 121	97.49 5	96.92 57	92.14 5	92.90 69	95.77 108	85.02 59	98.33 135	93.03 47	98.62 45	98.13 64

XVS		94.45 22	94.32 26	94.85 25	98.54 13	86.60 34	96.93 22	97.19 35	90.66 24	92.85 71	97.16 47	85.02 59	99.49 26	91.99 76	98.56 49	98.47 33

X-MVStestdata		88.31 177	86.13 223	94.85 25	98.54 13	86.60 34	96.93 22	97.19 35	90.66 24	92.85 71	23.41 405	85.02 59	99.49 26	91.99 76	98.56 49	98.47 33

MSLP-MVS++		93.72 48	94.08 38	92.65 108	97.31 65	83.43 116	95.79 81	97.33 25	90.03 36	93.58 55	96.96 55	84.87 62	97.76 178	92.19 68	98.66 41	96.76 136

HPM-MVS		94.02 39	93.88 44	94.43 47	98.39 23	85.78 63	97.25 10	97.07 45	86.90 132	92.62 82	96.80 65	84.85 63	99.17 47	92.43 57	98.65 43	98.33 43
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
SR-MVS		94.23 31	94.17 37	94.43 47	98.21 32	85.78 63	96.40 41	96.90 59	88.20 98	94.33 40	97.40 33	84.75 64	99.03 58	93.35 43	97.99 68	98.48 30

PGM-MVS		93.96 42	93.72 50	94.68 38	98.43 20	86.22 47	95.30 105	97.78 1	87.45 120	93.26 60	97.33 36	84.62 65	99.51 24	90.75 101	98.57 48	98.32 46

EI-MVSNet-Vis-set		93.01 69	92.92 66	93.29 73	95.01 150	83.51 115	94.48 156	95.77 153	90.87 15	92.52 84	96.67 68	84.50 66	99.00 68	91.99 76	94.44 145	97.36 102

MTAPA		94.42 26	94.22 33	95.00 18	98.42 21	86.95 21	94.36 171	96.97 50	91.07 13	93.14 64	97.56 27	84.30 67	99.56 12	93.43 40	98.75 30	98.47 33

SR-MVS-dyc-post		93.82 44	93.82 45	93.82 62	97.92 43	84.57 82	96.28 46	96.76 75	87.46 118	93.75 51	97.43 31	84.24 68	99.01 63	92.73 51	97.80 75	97.88 80

ETV-MVS		92.74 73	92.66 71	92.97 90	95.20 142	84.04 100	95.07 122	96.51 94	90.73 22	92.96 68	91.19 275	84.06 69	98.34 133	91.72 84	96.54 102	96.54 147

EI-MVSNet-UG-set		92.74 73	92.62 73	93.12 80	94.86 161	83.20 123	94.40 164	95.74 156	90.71 23	92.05 94	96.60 75	84.00 70	98.99 70	91.55 86	93.63 155	97.17 110

mPP-MVS		93.99 41	93.78 47	94.63 40	98.50 16	85.90 60	96.87 26	96.91 58	88.70 80	91.83 105	97.17 46	83.96 71	99.55 16	91.44 88	98.64 44	98.43 38

APD-MVS_3200maxsize		93.78 45	93.77 48	93.80 64	97.92 43	84.19 96	96.30 44	96.87 62	86.96 128	93.92 49	97.47 29	83.88 72	98.96 77	92.71 54	97.87 72	98.26 56

EIA-MVS		91.95 82	91.94 80	91.98 138	95.16 143	80.01 220	95.36 100	96.73 79	88.44 87	89.34 139	92.16 241	83.82 73	98.45 122	89.35 114	97.06 88	97.48 99

MVS_0304		94.60 18	94.38 25	95.23 11	95.41 132	87.49 16	96.53 38	92.75 279	93.82 2	93.07 67	97.84 22	83.66 74	99.59 8	97.61 2	98.76 28	98.61 22

fmvsm_s_conf0.5_n		93.76 46	94.06 41	92.86 96	95.62 124	83.17 124	96.14 58	96.12 125	88.13 101	95.82 26	98.04 16	83.43 75	98.48 114	96.97 9	96.23 108	96.92 129

casdiffmvs_mvg		92.96 70	92.83 68	93.35 72	94.59 174	83.40 118	95.00 126	96.34 104	90.30 30	92.05 94	96.05 95	83.43 75	98.15 147	92.07 72	95.67 114	98.49 29
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EPP-MVSNet		91.70 88	91.56 85	92.13 133	95.88 112	80.50 204	97.33 7	95.25 192	86.15 152	89.76 134	95.60 114	83.42 77	98.32 137	87.37 140	93.25 167	97.56 97

test_fmvsmvis_n_1920		93.44 55	93.55 55	93.10 81	93.67 222	84.26 95	95.83 79	96.14 122	89.00 72	92.43 88	97.50 28	83.37 78	98.72 96	96.61 12	97.44 82	96.32 151

UA-Net		92.83 71	92.54 74	93.68 68	96.10 100	84.71 79	95.66 89	96.39 101	91.92 7	93.22 62	96.49 79	83.16 79	98.87 82	84.47 176	95.47 120	97.45 101

UniMVSNet_NR-MVSNet		89.92 126	89.29 129	91.81 153	93.39 230	83.72 106	94.43 162	97.12 41	89.80 43	86.46 194	93.32 202	83.16 79	97.23 233	84.92 168	81.02 327	94.49 234

EC-MVSNet		93.44 55	93.71 51	92.63 109	95.21 141	82.43 151	97.27 9	96.71 82	90.57 26	92.88 70	95.80 106	83.16 79	98.16 146	93.68 36	98.14 61	97.31 103

fmvsm_s_conf0.5_n_a		93.57 50	93.76 49	93.00 88	95.02 149	83.67 108	96.19 51	96.10 127	87.27 122	95.98 24	98.05 13	83.07 82	98.45 122	96.68 11	95.51 117	96.88 132

MM		95.10 11	94.91 13	95.68 5	96.09 101	88.34 9	96.68 33	94.37 236	95.08 1	94.68 36	97.72 24	82.94 83	99.64 1	97.85 1	98.76 28	99.06 7

RE-MVS-def			93.68 52		97.92 43	84.57 82	96.28 46	96.76 75	87.46 118	93.75 51	97.43 31	82.94 83		92.73 51	97.80 75	97.88 80

新几何1				93.10 81	97.30 66	84.35 94		95.56 170	71.09 375	91.26 116	96.24 85	82.87 85	98.86 84	79.19 263	98.10 63	96.07 165

fmvsm_s_conf0.1_n		93.46 53	93.66 53	92.85 97	93.75 218	83.13 126	96.02 69	95.74 156	87.68 115	95.89 25	98.17 2	82.78 86	98.46 118	96.71 10	96.17 109	96.98 125

原ACMM1				92.01 134	97.34 64	81.05 188		96.81 70	78.89 299	90.45 123	95.92 100	82.65 87	98.84 88	80.68 242	98.26 58	96.14 159

casdiffmvs		92.51 76	92.43 76	92.74 103	94.41 187	81.98 161	94.54 154	96.23 116	89.57 51	91.96 98	96.17 91	82.58 88	98.01 165	90.95 97	95.45 122	98.23 58
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DeepC-MVS	88.79 3	93.31 60	92.99 65	94.26 52	96.07 103	85.83 61	94.89 132	96.99 48	89.02 71	89.56 135	97.37 35	82.51 89	99.38 31	92.20 67	98.30 56	97.57 96
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HPM-MVS_fast		93.40 59	93.22 60	93.94 58	98.36 25	84.83 76	97.15 13	96.80 71	85.77 160	92.47 87	97.13 48	82.38 90	99.07 53	90.51 105	98.40 53	97.92 79

baseline		92.39 79	92.29 78	92.69 107	94.46 183	81.77 166	94.14 180	96.27 111	89.22 61	91.88 101	96.00 96	82.35 91	97.99 167	91.05 92	95.27 128	98.30 47

sasdasda		93.27 61	92.75 69	94.85 25	95.70 120	87.66 12	96.33 42	96.41 99	90.00 37	94.09 44	94.60 155	82.33 92	98.62 103	92.40 59	92.86 174	98.27 52

canonicalmvs		93.27 61	92.75 69	94.85 25	95.70 120	87.66 12	96.33 42	96.41 99	90.00 37	94.09 44	94.60 155	82.33 92	98.62 103	92.40 59	92.86 174	98.27 52

fmvsm_s_conf0.1_n_a		93.19 65	93.26 58	92.97 90	92.49 255	83.62 111	96.02 69	95.72 159	86.78 134	96.04 22	98.19 1	82.30 94	98.43 127	96.38 13	95.42 123	96.86 133

DP-MVS Recon		91.95 82	91.28 88	93.96 57	98.33 27	85.92 57	94.66 148	96.66 85	82.69 235	90.03 132	95.82 105	82.30 94	99.03 58	84.57 174	96.48 105	96.91 130

PAPR		90.02 120	89.27 131	92.29 128	95.78 116	80.95 192	92.68 249	96.22 117	81.91 251	86.66 191	93.75 194	82.23 96	98.44 124	79.40 262	94.79 133	97.48 99

MVS_Test		91.31 94	91.11 91	91.93 142	94.37 188	80.14 212	93.46 218	95.80 151	86.46 142	91.35 115	93.77 192	82.21 97	98.09 158	87.57 136	94.95 131	97.55 98

nrg030		91.08 99	90.39 101	93.17 78	93.07 238	86.91 22	96.41 39	96.26 112	88.30 92	88.37 155	94.85 142	82.19 98	97.64 189	91.09 91	82.95 298	94.96 207

MGCFI-Net		93.03 68	92.63 72	94.23 53	95.62 124	85.92 57	96.08 62	96.33 105	89.86 41	93.89 50	94.66 152	82.11 99	98.50 112	92.33 64	92.82 177	98.27 52

UniMVSNet (Re)		89.80 130	89.07 133	92.01 134	93.60 224	84.52 85	94.78 140	97.47 11	89.26 60	86.44 197	92.32 236	82.10 100	97.39 220	84.81 171	80.84 331	94.12 248

testdata				90.49 205	96.40 89	77.89 271		95.37 188	72.51 367	93.63 54	96.69 66	82.08 101	97.65 186	83.08 192	97.39 83	95.94 170

PAPM_NR		91.22 96	90.78 99	92.52 115	97.60 56	81.46 176	94.37 170	96.24 115	86.39 144	87.41 172	94.80 145	82.06 102	98.48 114	82.80 200	95.37 124	97.61 93

MG-MVS		91.77 85	91.70 84	92.00 137	97.08 71	80.03 219	93.60 213	95.18 196	87.85 111	90.89 119	96.47 80	82.06 102	98.36 130	85.07 166	97.04 89	97.62 92

CANet		93.54 51	93.20 61	94.55 43	95.65 122	85.73 65	94.94 129	96.69 84	91.89 8	90.69 121	95.88 102	81.99 104	99.54 20	93.14 46	97.95 70	98.39 39

FC-MVSNet-test		90.27 114	90.18 106	90.53 201	93.71 219	79.85 226	95.77 82	97.59 3	89.31 58	86.27 201	94.67 151	81.93 105	97.01 248	84.26 178	88.09 249	94.71 218

FIs		90.51 112	90.35 102	90.99 189	93.99 208	80.98 190	95.73 83	97.54 4	89.15 64	86.72 190	94.68 150	81.83 106	97.24 232	85.18 165	88.31 246	94.76 217

ACMMP		93.24 63	92.88 67	94.30 51	98.09 38	85.33 70	96.86 27	97.45 14	88.33 90	90.15 130	97.03 53	81.44 107	99.51 24	90.85 100	95.74 113	98.04 71
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
Effi-MVS+		91.59 90	91.11 91	93.01 87	94.35 192	83.39 119	94.60 150	95.10 200	87.10 125	90.57 122	93.10 213	81.43 108	98.07 161	89.29 116	94.48 143	97.59 95

MVS_111021_LR		92.47 77	92.29 78	92.98 89	95.99 109	84.43 91	93.08 236	96.09 128	88.20 98	91.12 117	95.72 111	81.33 109	97.76 178	91.74 83	97.37 84	96.75 137

mvs_anonymous		89.37 146	89.32 128	89.51 253	93.47 227	74.22 322	91.65 282	94.83 218	82.91 230	85.45 225	93.79 190	81.23 110	96.36 287	86.47 152	94.09 148	97.94 76

PVSNet_BlendedMVS		89.98 121	89.70 117	90.82 194	96.12 97	81.25 181	93.92 200	96.83 66	83.49 214	89.10 142	92.26 239	81.04 111	98.85 86	86.72 150	87.86 253	92.35 323

PVSNet_Blended		90.73 104	90.32 103	91.98 138	96.12 97	81.25 181	92.55 254	96.83 66	82.04 247	89.10 142	92.56 229	81.04 111	98.85 86	86.72 150	95.91 111	95.84 175

alignmvs		93.08 67	92.50 75	94.81 32	95.62 124	87.61 14	95.99 71	96.07 130	89.77 47	94.12 43	94.87 139	80.56 113	98.66 98	92.42 58	93.10 170	98.15 63

API-MVS		90.66 107	90.07 109	92.45 118	96.36 91	84.57 82	96.06 66	95.22 195	82.39 238	89.13 141	94.27 169	80.32 114	98.46 118	80.16 250	96.71 99	94.33 240

PVSNet_Blended_VisFu		91.38 92	90.91 96	92.80 99	96.39 90	83.17 124	94.87 134	96.66 85	83.29 220	89.27 140	94.46 160	80.29 115	99.17 47	87.57 136	95.37 124	96.05 168

test222					96.55 84	81.70 167	92.22 266	95.01 203	68.36 381	90.20 127	96.14 92	80.26 116			97.80 75	96.05 168

diffmvs		91.37 93	91.23 89	91.77 154	93.09 237	80.27 208	92.36 259	95.52 175	87.03 127	91.40 114	94.93 136	80.08 117	97.44 208	92.13 71	94.56 140	97.61 93
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Test By Simon												80.02 118

IterMVS-LS		88.36 176	87.91 169	89.70 244	93.80 215	78.29 262	93.73 207	95.08 202	85.73 161	84.75 245	91.90 255	79.88 119	96.92 253	83.83 184	82.51 304	93.89 258
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		89.10 150	88.86 142	89.80 240	91.84 277	78.30 261	93.70 210	95.01 203	85.73 161	87.15 177	95.28 122	79.87 120	97.21 235	83.81 185	87.36 261	93.88 260

TAPA-MVS	84.62 6	88.16 181	87.01 191	91.62 158	96.64 80	80.65 199	94.39 166	96.21 120	76.38 328	86.19 204	95.44 117	79.75 121	98.08 160	62.75 372	95.29 126	96.13 160
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Fast-Effi-MVS+		89.41 142	88.64 145	91.71 156	94.74 165	80.81 196	93.54 214	95.10 200	83.11 224	86.82 189	90.67 294	79.74 122	97.75 181	80.51 245	93.55 157	96.57 145

pcd_1.5k_mvsjas		6.64 379	8.86 382	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	79.70 123	0.00 412	0.00 411	0.00 410	0.00 408

PS-MVSNAJss		89.97 122	89.62 118	91.02 186	91.90 275	80.85 195	95.26 110	95.98 136	86.26 147	86.21 203	94.29 166	79.70 123	97.65 186	88.87 122	88.10 247	94.57 224

PS-MVSNAJ		91.18 97	90.92 95	91.96 140	95.26 139	82.60 150	92.09 271	95.70 160	86.27 146	91.84 103	92.46 231	79.70 123	98.99 70	89.08 118	95.86 112	94.29 242

xiu_mvs_v2_base		91.13 98	90.89 97	91.86 148	94.97 153	82.42 152	92.24 265	95.64 167	86.11 156	91.74 108	93.14 211	79.67 126	98.89 81	89.06 119	95.46 121	94.28 243

WR-MVS_H		87.80 190	87.37 181	89.10 262	93.23 233	78.12 265	95.61 93	97.30 29	87.90 107	83.72 273	92.01 252	79.65 127	96.01 301	76.36 289	80.54 335	93.16 296

EPNet		91.79 84	91.02 94	94.10 54	90.10 338	85.25 71	96.03 68	92.05 300	92.83 3	87.39 175	95.78 107	79.39 128	99.01 63	88.13 129	97.48 81	98.05 70
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_ehance_all_eth		87.22 220	86.62 205	89.02 265	92.13 266	77.40 284	90.91 300	94.81 220	81.28 269	84.32 261	90.08 309	79.26 129	96.62 264	83.81 185	82.94 299	93.04 301

test_fmvsmconf0.01_n		93.19 65	93.02 64	93.71 67	89.25 350	84.42 93	96.06 66	96.29 107	89.06 66	94.68 36	98.13 3	79.22 130	98.98 74	97.22 5	97.24 85	97.74 89

miper_enhance_ethall		86.90 232	86.18 221	89.06 263	91.66 286	77.58 282	90.22 314	94.82 219	79.16 295	84.48 252	89.10 325	79.19 131	96.66 262	84.06 180	82.94 299	92.94 304

NR-MVSNet		88.58 172	87.47 179	91.93 142	93.04 241	84.16 97	94.77 141	96.25 114	89.05 67	80.04 325	93.29 205	79.02 132	97.05 246	81.71 226	80.05 341	94.59 222

TAMVS		89.21 148	88.29 159	91.96 140	93.71 219	82.62 149	93.30 226	94.19 243	82.22 242	87.78 166	93.94 182	78.83 133	96.95 251	77.70 276	92.98 172	96.32 151

c3_l		87.14 225	86.50 210	89.04 264	92.20 263	77.26 285	91.22 294	94.70 226	82.01 248	84.34 260	90.43 298	78.81 134	96.61 267	83.70 187	81.09 324	93.25 291

1112_ss		88.42 173	87.33 182	91.72 155	94.92 157	80.98 190	92.97 241	94.54 229	78.16 315	83.82 271	93.88 187	78.78 135	97.91 173	79.45 258	89.41 224	96.26 155

CDS-MVSNet		89.45 140	88.51 150	92.29 128	93.62 223	83.61 113	93.01 239	94.68 227	81.95 249	87.82 165	93.24 207	78.69 136	96.99 249	80.34 247	93.23 168	96.28 154
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
WTY-MVS		89.60 134	88.92 138	91.67 157	95.47 130	81.15 186	92.38 258	94.78 222	83.11 224	89.06 145	94.32 164	78.67 137	96.61 267	81.57 227	90.89 200	97.24 106

CPTT-MVS		91.99 81	91.80 82	92.55 113	98.24 31	81.98 161	96.76 30	96.49 95	81.89 253	90.24 126	96.44 81	78.59 138	98.61 105	89.68 111	97.85 73	97.06 117

IS-MVSNet		91.43 91	91.09 93	92.46 117	95.87 114	81.38 179	96.95 19	93.69 262	89.72 49	89.50 137	95.98 98	78.57 139	97.77 177	83.02 194	96.50 104	98.22 59

OMC-MVS		91.23 95	90.62 100	93.08 83	96.27 93	84.07 98	93.52 215	95.93 140	86.95 129	89.51 136	96.13 93	78.50 140	98.35 132	85.84 160	92.90 173	96.83 135

PCF-MVS	84.11 10	87.74 192	86.08 227	92.70 106	94.02 203	84.43 91	89.27 331	95.87 147	73.62 357	84.43 255	94.33 163	78.48 141	98.86 84	70.27 330	94.45 144	94.81 215
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
LCM-MVSNet-Re		88.30 178	88.32 158	88.27 283	94.71 168	72.41 344	93.15 232	90.98 331	87.77 112	79.25 334	91.96 253	78.35 142	95.75 314	83.04 193	95.62 115	96.65 141

HY-MVS	83.01 12	89.03 156	87.94 168	92.29 128	94.86 161	82.77 139	92.08 272	94.49 230	81.52 265	86.93 181	92.79 224	78.32 143	98.23 141	79.93 252	90.55 203	95.88 173

GeoE		90.05 119	89.43 124	91.90 147	95.16 143	80.37 207	95.80 80	94.65 228	83.90 202	87.55 171	94.75 147	78.18 144	97.62 191	81.28 230	93.63 155	97.71 90

MVS		87.44 208	86.10 226	91.44 166	92.61 254	83.62 111	92.63 251	95.66 164	67.26 382	81.47 304	92.15 242	77.95 145	98.22 143	79.71 254	95.48 119	92.47 317

MVSFormer		91.68 89	91.30 87	92.80 99	93.86 212	83.88 103	95.96 73	95.90 144	84.66 191	91.76 106	94.91 137	77.92 146	97.30 224	89.64 112	97.11 86	97.24 106

lupinMVS		90.92 100	90.21 104	93.03 86	93.86 212	83.88 103	92.81 247	93.86 256	79.84 286	91.76 106	94.29 166	77.92 146	98.04 163	90.48 108	97.11 86	97.17 110

Test_1112_low_res		87.65 195	86.51 209	91.08 182	94.94 156	79.28 242	91.77 277	94.30 239	76.04 333	83.51 280	92.37 234	77.86 148	97.73 182	78.69 266	89.13 231	96.22 156

VNet		92.24 80	91.91 81	93.24 75	96.59 82	83.43 116	94.84 136	96.44 96	89.19 63	94.08 46	95.90 101	77.85 149	98.17 145	88.90 120	93.38 164	98.13 64

mvsany_test1		85.42 266	85.30 253	85.77 333	87.95 367	75.41 310	87.61 357	80.97 391	76.82 325	88.68 149	95.83 104	77.44 150	90.82 379	85.90 158	86.51 269	91.08 352

DU-MVS		89.34 147	88.50 151	91.85 150	93.04 241	83.72 106	94.47 159	96.59 90	89.50 52	86.46 194	93.29 205	77.25 151	97.23 233	84.92 168	81.02 327	94.59 222

Baseline_NR-MVSNet		87.07 227	86.63 204	88.40 279	91.44 290	77.87 272	94.23 177	92.57 284	84.12 198	85.74 212	92.08 248	77.25 151	96.04 298	82.29 209	79.94 342	91.30 344

jason		90.80 101	90.10 108	92.90 94	93.04 241	83.53 114	93.08 236	94.15 245	80.22 280	91.41 113	94.91 137	76.87 153	97.93 172	90.28 109	96.90 93	97.24 106
jason: jason.
PAPM		86.68 240	85.39 249	90.53 201	93.05 240	79.33 241	89.79 322	94.77 223	78.82 301	81.95 300	93.24 207	76.81 154	97.30 224	66.94 354	93.16 169	94.95 210

Vis-MVSNet (Re-imp)		89.59 135	89.44 123	90.03 227	95.74 117	75.85 305	95.61 93	90.80 337	87.66 117	87.83 164	95.40 120	76.79 155	96.46 280	78.37 267	96.73 98	97.80 86

baseline1		88.10 182	87.28 184	90.57 199	94.96 154	80.07 215	94.27 173	91.29 323	86.74 135	87.41 172	94.00 178	76.77 156	96.20 293	80.77 239	79.31 349	95.44 189

114514_t		89.51 137	88.50 151	92.54 114	98.11 36	81.99 160	95.16 118	96.36 103	70.19 378	85.81 209	95.25 124	76.70 157	98.63 102	82.07 215	96.86 96	97.00 122

PLC	84.53 7	89.06 155	88.03 165	92.15 132	97.27 68	82.69 146	94.29 172	95.44 182	79.71 288	84.01 268	94.18 171	76.68 158	98.75 93	77.28 280	93.41 163	95.02 203
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TranMVSNet+NR-MVSNet		88.84 162	87.95 167	91.49 163	92.68 253	83.01 134	94.92 131	96.31 106	89.88 40	85.53 218	93.85 189	76.63 159	96.96 250	81.91 219	79.87 344	94.50 232

MAR-MVS		90.30 113	89.37 126	93.07 85	96.61 81	84.48 87	95.68 86	95.67 162	82.36 240	87.85 163	92.85 218	76.63 159	98.80 90	80.01 251	96.68 100	95.91 171
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
WR-MVS		88.38 174	87.67 174	90.52 203	93.30 232	80.18 210	93.26 229	95.96 139	88.57 85	85.47 224	92.81 222	76.12 161	96.91 254	81.24 231	82.29 307	94.47 237

v8		87.50 207	86.71 199	89.89 234	91.37 295	79.40 235	94.50 155	95.38 186	84.81 186	83.60 278	91.33 270	76.05 162	97.42 210	82.84 198	80.51 338	92.84 308

v148		87.04 228	86.32 216	89.21 258	90.94 314	77.26 285	93.71 209	94.43 232	84.84 185	84.36 259	90.80 290	76.04 163	97.05 246	82.12 212	79.60 346	93.31 288

eth_miper_zixun_eth		86.50 247	85.77 240	88.68 274	91.94 272	75.81 306	90.47 306	94.89 212	82.05 245	84.05 266	90.46 297	75.96 164	96.77 258	82.76 201	79.36 348	93.46 285

3Dnovator+	87.14 4	92.42 78	91.37 86	95.55 7	95.63 123	88.73 6	97.07 18	96.77 74	90.84 16	84.02 267	96.62 74	75.95 165	99.34 34	87.77 133	97.68 79	98.59 24

h-mvs33		90.80 101	90.15 107	92.75 102	96.01 105	82.66 147	95.43 99	95.53 174	89.80 43	93.08 65	95.64 113	75.77 166	99.00 68	92.07 72	78.05 353	96.60 142

hse-mvs2		89.88 128	89.34 127	91.51 162	94.83 163	81.12 187	93.94 198	93.91 255	89.80 43	93.08 65	93.60 196	75.77 166	97.66 185	92.07 72	77.07 360	95.74 180

BH-untuned		88.60 170	88.13 163	90.01 230	95.24 140	78.50 255	93.29 227	94.15 245	84.75 188	84.46 253	93.40 199	75.76 168	97.40 217	77.59 277	94.52 142	94.12 248

DIV-MVS_self_test		86.53 245	85.78 238	88.75 271	92.02 271	76.45 297	90.74 302	94.30 239	81.83 256	83.34 284	90.82 289	75.75 169	96.57 270	81.73 225	81.52 319	93.24 292

BH-w/o		87.57 203	87.05 189	89.12 261	94.90 159	77.90 270	92.41 256	93.51 264	82.89 231	83.70 274	91.34 269	75.75 169	97.07 244	75.49 296	93.49 160	92.39 321

cl____		86.52 246	85.78 238	88.75 271	92.03 270	76.46 296	90.74 302	94.30 239	81.83 256	83.34 284	90.78 291	75.74 171	96.57 270	81.74 224	81.54 318	93.22 293

cdsmvs_eth3d_5k		22.14 374	29.52 377	0.00 393	0.00 416	0.00 418	0.00 404	95.76 154	0.00 411	0.00 412	94.29 166	75.66 172	0.00 412	0.00 411	0.00 410	0.00 408

CNLPA		89.07 154	87.98 166	92.34 124	96.87 74	84.78 78	94.08 186	93.24 267	81.41 266	84.46 253	95.13 132	75.57 173	96.62 264	77.21 281	93.84 153	95.61 187

CHOSEN 1792x2688		88.84 162	87.69 173	92.30 127	96.14 96	81.42 178	90.01 319	95.86 148	74.52 348	87.41 172	93.94 182	75.46 174	98.36 130	80.36 246	95.53 116	97.12 115

CP-MVSNet		87.63 198	87.26 186	88.74 273	93.12 236	76.59 295	95.29 107	96.58 91	88.43 88	83.49 281	92.98 216	75.28 175	95.83 309	78.97 264	81.15 323	93.79 266

v10		87.25 217	86.38 212	89.85 235	91.19 301	79.50 232	94.48 156	95.45 180	83.79 206	83.62 277	91.19 275	75.13 176	97.42 210	81.94 218	80.60 333	92.63 313

Vis-MVSNet		91.75 86	91.23 89	93.29 73	95.32 134	83.78 105	96.14 58	95.98 136	89.89 39	90.45 123	96.58 76	75.09 177	98.31 138	84.75 172	96.90 93	97.78 88
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
sss		88.93 159	88.26 161	90.94 192	94.05 202	80.78 197	91.71 279	95.38 186	81.55 264	88.63 150	93.91 186	75.04 178	95.47 326	82.47 204	91.61 188	96.57 145

v1144		87.61 201	86.79 197	90.06 226	91.01 309	79.34 238	93.95 197	95.42 185	83.36 219	85.66 214	91.31 273	74.98 179	97.42 210	83.37 189	82.06 309	93.42 286

miper_lstm_enhance		85.27 271	84.59 269	87.31 304	91.28 299	74.63 317	87.69 354	94.09 249	81.20 273	81.36 307	89.85 315	74.97 180	94.30 341	81.03 235	79.84 345	93.01 302

test_yl		90.69 105	90.02 113	92.71 104	95.72 118	82.41 154	94.11 182	95.12 198	85.63 164	91.49 111	94.70 148	74.75 181	98.42 128	86.13 155	92.53 181	97.31 103

DCV-MVSNet		90.69 105	90.02 113	92.71 104	95.72 118	82.41 154	94.11 182	95.12 198	85.63 164	91.49 111	94.70 148	74.75 181	98.42 128	86.13 155	92.53 181	97.31 103

V42		87.68 193	86.86 193	90.15 221	90.58 329	80.14 212	94.24 176	95.28 191	83.66 208	85.67 213	91.33 270	74.73 183	97.41 215	84.43 177	81.83 313	92.89 306

FA-MVS(test-final)		89.66 132	88.91 139	91.93 142	94.57 177	80.27 208	91.36 287	94.74 224	84.87 183	89.82 133	92.61 228	74.72 184	98.47 117	83.97 182	93.53 158	97.04 119

XVG-OURS-SEG-HR		89.95 124	89.45 122	91.47 165	94.00 207	81.21 184	91.87 275	96.06 132	85.78 159	88.55 151	95.73 110	74.67 185	97.27 228	88.71 123	89.64 221	95.91 171

v2v482		87.84 188	87.06 188	90.17 219	90.99 310	79.23 245	94.00 195	95.13 197	84.87 183	85.53 218	92.07 250	74.45 186	97.45 205	84.71 173	81.75 315	93.85 264

CLD-MVS		89.47 139	88.90 140	91.18 176	94.22 196	82.07 159	92.13 269	96.09 128	87.90 107	85.37 234	92.45 232	74.38 187	97.56 194	87.15 143	90.43 205	93.93 257
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XXY-MVS		87.65 195	86.85 194	90.03 227	92.14 265	80.60 202	93.76 206	95.23 193	82.94 229	84.60 248	94.02 176	74.27 188	95.49 325	81.04 233	83.68 291	94.01 256

HQP_MVS		90.60 111	90.19 105	91.82 151	94.70 169	82.73 143	95.85 77	96.22 117	90.81 17	86.91 183	94.86 140	74.23 189	98.12 148	88.15 127	89.99 210	94.63 219

plane_prior6					94.52 179	82.75 140						74.23 189

v144192		87.19 223	86.35 214	89.74 241	90.64 327	78.24 263	93.92 200	95.43 183	81.93 250	85.51 220	91.05 283	74.21 191	97.45 205	82.86 197	81.56 317	93.53 280

VPA-MVSNet		89.62 133	88.96 136	91.60 159	93.86 212	82.89 138	95.46 98	97.33 25	87.91 106	88.43 154	93.31 203	74.17 192	97.40 217	87.32 141	82.86 303	94.52 227

ab-mvs		89.41 142	88.35 155	92.60 110	95.15 145	82.65 148	92.20 267	95.60 169	83.97 201	88.55 151	93.70 195	74.16 193	98.21 144	82.46 205	89.37 225	96.94 127

1314		87.51 205	86.57 207	90.34 216	92.42 259	79.74 228	92.63 251	95.35 190	78.35 310	80.14 322	91.62 264	74.05 194	97.15 237	81.05 232	93.53 158	94.12 248

test_djsdf		89.03 156	88.64 145	90.21 218	90.74 324	79.28 242	95.96 73	95.90 144	84.66 191	85.33 236	92.94 217	74.02 195	97.30 224	89.64 112	88.53 239	94.05 254

cl22		86.78 235	85.98 231	89.18 260	92.34 260	77.62 281	90.84 301	94.13 247	81.33 268	83.97 269	90.15 306	73.96 196	96.60 269	84.19 179	82.94 299	93.33 287

AdaColmap		89.89 127	89.07 133	92.37 123	97.41 62	83.03 132	94.42 163	95.92 141	82.81 232	86.34 200	94.65 153	73.89 197	99.02 61	80.69 241	95.51 117	95.05 202

HyFIR lowres test		88.09 183	86.81 195	91.93 142	96.00 106	80.63 200	90.01 319	95.79 152	73.42 359	87.68 168	92.10 247	73.86 198	97.96 169	80.75 240	91.70 187	97.19 109

HQP2-MVS												73.83 199

HQP-MVS		89.80 130	89.28 130	91.34 170	94.17 197	81.56 170	94.39 166	96.04 133	88.81 74	85.43 228	93.97 180	73.83 199	97.96 169	87.11 145	89.77 219	94.50 232

3Dnovator	86.66 5	91.73 87	90.82 98	94.44 45	94.59 174	86.37 41	97.18 12	97.02 47	89.20 62	84.31 263	96.66 69	73.74 201	99.17 47	86.74 148	97.96 69	97.79 87

EPNet_dtu		86.49 249	85.94 234	88.14 288	90.24 336	72.82 334	94.11 182	92.20 295	86.66 138	79.42 333	92.36 235	73.52 202	95.81 311	71.26 322	93.66 154	95.80 178
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TransMVSNet (Re)		84.43 284	83.06 291	88.54 277	91.72 282	78.44 256	95.18 115	92.82 277	82.73 234	79.67 330	92.12 244	73.49 203	95.96 303	71.10 327	68.73 382	91.21 346

Effi-MVS+-dtu		88.65 168	88.35 155	89.54 250	93.33 231	76.39 298	94.47 159	94.36 237	87.70 114	85.43 228	89.56 320	73.45 204	97.26 230	85.57 163	91.28 192	94.97 204

baseline2		86.50 247	85.39 249	89.84 236	91.12 306	76.70 293	91.88 274	88.58 363	82.35 241	79.95 326	90.95 285	73.42 205	97.63 190	80.27 249	89.95 213	95.19 198

PEN-MVS		86.80 234	86.27 219	88.40 279	92.32 261	75.71 307	95.18 115	96.38 102	87.97 104	82.82 290	93.15 210	73.39 206	95.92 304	76.15 293	79.03 351	93.59 278

v1192		87.25 217	86.33 215	90.00 231	90.76 323	79.04 246	93.80 204	95.48 176	82.57 236	85.48 223	91.18 277	73.38 207	97.42 210	82.30 208	82.06 309	93.53 280

QAPM		89.51 137	88.15 162	93.59 70	94.92 157	84.58 81	96.82 29	96.70 83	78.43 309	83.41 282	96.19 90	73.18 208	99.30 40	77.11 283	96.54 102	96.89 131

mvsmamba		89.96 123	89.50 121	91.33 171	92.90 248	81.82 164	96.68 33	92.37 288	89.03 69	87.00 179	94.85 142	73.05 209	97.65 186	91.03 93	88.63 237	94.51 229

tpmrst		85.35 268	84.99 258	86.43 325	90.88 319	67.88 372	88.71 340	91.43 320	80.13 282	86.08 206	88.80 332	73.05 209	96.02 300	82.48 203	83.40 297	95.40 191

PS-CasMVS		87.32 214	86.88 192	88.63 276	92.99 244	76.33 300	95.33 102	96.61 89	88.22 96	83.30 286	93.07 214	73.03 211	95.79 313	78.36 268	81.00 329	93.75 273

DTE-MVSNet		86.11 254	85.48 247	87.98 291	91.65 287	74.92 314	94.93 130	95.75 155	87.36 121	82.26 295	93.04 215	72.85 212	95.82 310	74.04 309	77.46 357	93.20 294

MVSTER		88.84 162	88.29 159	90.51 204	92.95 246	80.44 205	93.73 207	95.01 203	84.66 191	87.15 177	93.12 212	72.79 213	97.21 235	87.86 132	87.36 261	93.87 261

v1921920		86.97 230	86.06 228	89.69 245	90.53 332	78.11 266	93.80 204	95.43 183	81.90 252	85.33 236	91.05 283	72.66 214	97.41 215	82.05 216	81.80 314	93.53 280

DP-MVS		87.25 217	85.36 251	92.90 94	97.65 55	83.24 121	94.81 138	92.00 302	74.99 343	81.92 301	95.00 135	72.66 214	99.05 55	66.92 356	92.33 184	96.40 149

v7n		86.81 233	85.76 241	89.95 232	90.72 325	79.25 244	95.07 122	95.92 141	84.45 194	82.29 294	90.86 286	72.60 216	97.53 197	79.42 261	80.52 337	93.08 300

OPM-MVS		90.12 117	89.56 120	91.82 151	93.14 235	83.90 102	94.16 179	95.74 156	88.96 73	87.86 162	95.43 119	72.48 217	97.91 173	88.10 131	90.18 209	93.65 277
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
LS3D		87.89 187	86.32 216	92.59 111	96.07 103	82.92 137	95.23 111	94.92 211	75.66 335	82.89 289	95.98 98	72.48 217	99.21 45	68.43 344	95.23 129	95.64 184

pm-mvs1		86.61 241	85.54 245	89.82 237	91.44 290	80.18 210	95.28 109	94.85 216	83.84 204	81.66 302	92.62 227	72.45 219	96.48 277	79.67 255	78.06 352	92.82 309

PMMVS		85.71 262	84.96 260	87.95 292	88.90 354	77.09 287	88.68 341	90.06 349	72.32 369	86.47 193	90.76 292	72.15 220	94.40 338	81.78 223	93.49 160	92.36 322

SDMVSNet		90.19 116	89.61 119	91.93 142	96.00 106	83.09 130	92.89 243	95.98 136	88.73 78	86.85 187	95.20 128	72.09 221	97.08 242	88.90 120	89.85 216	95.63 185

PatchmatchNet		85.85 259	84.70 266	89.29 257	91.76 281	75.54 308	88.49 343	91.30 322	81.63 262	85.05 240	88.70 334	71.71 222	96.24 292	74.61 307	89.05 232	96.08 164
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												71.70 223				96.12 161

patchmatchnet-post											83.76 374	71.53 224	96.48 277

v1240		86.78 235	85.85 236	89.56 249	90.45 333	77.79 276	93.61 212	95.37 188	81.65 260	85.43 228	91.15 279	71.50 225	97.43 209	81.47 229	82.05 311	93.47 284

anonymousdsp		87.84 188	87.09 187	90.12 223	89.13 351	80.54 203	94.67 147	95.55 171	82.05 245	83.82 271	92.12 244	71.47 226	97.15 237	87.15 143	87.80 256	92.67 311

Patchmatch-test		81.37 317	79.30 325	87.58 298	90.92 316	74.16 324	80.99 389	87.68 370	70.52 377	76.63 352	88.81 330	71.21 227	92.76 363	60.01 380	86.93 267	95.83 176

F-COLMAP		87.95 186	86.80 196	91.40 167	96.35 92	80.88 194	94.73 143	95.45 180	79.65 289	82.04 299	94.61 154	71.13 228	98.50 112	76.24 292	91.05 198	94.80 216

pmmvs4		85.43 265	83.86 278	90.16 220	90.02 341	82.97 136	90.27 308	92.67 282	75.93 334	80.73 313	91.74 259	71.05 229	95.73 316	78.85 265	83.46 295	91.78 333

CR-MVSNet		85.35 268	83.76 279	90.12 223	90.58 329	79.34 238	85.24 373	91.96 306	78.27 312	85.55 216	87.87 347	71.03 230	95.61 318	73.96 311	89.36 226	95.40 191

Patchmtry		82.71 301	80.93 307	88.06 289	90.05 340	76.37 299	84.74 378	91.96 306	72.28 370	81.32 308	87.87 347	71.03 230	95.50 324	68.97 340	80.15 340	92.32 324

CL-MVSNet_self_test		81.74 310	80.53 308	85.36 337	85.96 376	72.45 343	90.25 310	93.07 271	81.24 271	79.85 329	87.29 353	70.93 232	92.52 364	66.95 353	69.23 378	91.11 350

RPMNet		83.95 291	81.53 302	91.21 174	90.58 329	79.34 238	85.24 373	96.76 75	71.44 373	85.55 216	82.97 380	70.87 233	98.91 80	61.01 376	89.36 226	95.40 191

Patchmatch-RL test		81.67 311	79.96 317	86.81 321	85.42 381	71.23 353	82.17 387	87.50 371	78.47 307	77.19 348	82.50 382	70.81 234	93.48 354	82.66 202	72.89 370	95.71 183

CostFormer		85.77 261	84.94 261	88.26 284	91.16 304	72.58 342	89.47 329	91.04 330	76.26 331	86.45 196	89.97 312	70.74 235	96.86 257	82.35 207	87.07 266	95.34 195

sam_mvs												70.60 236

xiu_mvs_v1_base_debu		90.64 108	90.05 110	92.40 120	93.97 209	84.46 88	93.32 222	95.46 177	85.17 174	92.25 89	94.03 173	70.59 237	98.57 109	90.97 94	94.67 135	94.18 244

xiu_mvs_v1_base		90.64 108	90.05 110	92.40 120	93.97 209	84.46 88	93.32 222	95.46 177	85.17 174	92.25 89	94.03 173	70.59 237	98.57 109	90.97 94	94.67 135	94.18 244

xiu_mvs_v1_base_debi		90.64 108	90.05 110	92.40 120	93.97 209	84.46 88	93.32 222	95.46 177	85.17 174	92.25 89	94.03 173	70.59 237	98.57 109	90.97 94	94.67 135	94.18 244

test_post											10.29 406	70.57 240	95.91 306

CANet_DTU		90.26 115	89.41 125	92.81 98	93.46 228	83.01 134	93.48 216	94.47 231	89.43 54	87.76 167	94.23 170	70.54 241	99.03 58	84.97 167	96.39 106	96.38 150

BH-RMVSNet		88.37 175	87.48 178	91.02 186	95.28 136	79.45 234	92.89 243	93.07 271	85.45 169	86.91 183	94.84 144	70.35 242	97.76 178	73.97 310	94.59 139	95.85 174

Fast-Effi-MVS+-dtu		87.44 208	86.72 198	89.63 248	92.04 269	77.68 280	94.03 191	93.94 251	85.81 158	82.42 293	91.32 272	70.33 243	97.06 245	80.33 248	90.23 208	94.14 247

MDTV_nov1_ep13_2view						55.91 402	87.62 356		73.32 360	84.59 249		70.33 243		74.65 306		95.50 188

ACMM	84.12 9	89.14 149	88.48 154	91.12 178	94.65 172	81.22 183	95.31 103	96.12 125	85.31 172	85.92 208	94.34 162	70.19 245	98.06 162	85.65 161	88.86 235	94.08 252
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ET-MVSNet_ETH3D		87.51 205	85.91 235	92.32 125	93.70 221	83.93 101	92.33 262	90.94 333	84.16 196	72.09 374	92.52 230	69.90 246	95.85 308	89.20 117	88.36 245	97.17 110

LPG-MVS_test		89.45 140	88.90 140	91.12 178	94.47 181	81.49 174	95.30 105	96.14 122	86.73 136	85.45 225	95.16 130	69.89 247	98.10 150	87.70 134	89.23 229	93.77 271

LGP-MVS_train				91.12 178	94.47 181	81.49 174		96.14 122	86.73 136	85.45 225	95.16 130	69.89 247	98.10 150	87.70 134	89.23 229	93.77 271

CHOSEN 280x420		85.15 273	83.99 276	88.65 275	92.47 256	78.40 258	79.68 393	92.76 278	74.90 345	81.41 306	89.59 318	69.85 249	95.51 322	79.92 253	95.29 126	92.03 329

LTVRE_ROB	82.13 13	86.26 253	84.90 262	90.34 216	94.44 185	81.50 172	92.31 264	94.89 212	83.03 226	79.63 331	92.67 225	69.69 250	97.79 176	71.20 323	86.26 271	91.72 334
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
OpenMVS	83.78 11	88.74 166	87.29 183	93.08 83	92.70 252	85.39 69	96.57 36	96.43 97	78.74 304	80.85 312	96.07 94	69.64 251	99.01 63	78.01 274	96.65 101	94.83 214

MDTV_nov1_ep13			83.56 282		91.69 285	69.93 365	87.75 353	91.54 316	78.60 306	84.86 243	88.90 329	69.54 252	96.03 299	70.25 331	88.93 234

AUN-MVS		87.78 191	86.54 208	91.48 164	94.82 164	81.05 188	93.91 202	93.93 252	83.00 227	86.93 181	93.53 197	69.50 253	97.67 183	86.14 153	77.12 359	95.73 182

PatchT		82.68 302	81.27 304	86.89 319	90.09 339	70.94 359	84.06 380	90.15 346	74.91 344	85.63 215	83.57 375	69.37 254	94.87 335	65.19 361	88.50 241	94.84 213

RRT_MVS		89.09 152	88.62 148	90.49 205	92.85 249	79.65 230	96.41 39	94.41 234	88.22 96	85.50 221	94.77 146	69.36 255	97.31 223	89.33 115	86.73 268	94.51 229

VPNet		88.20 180	87.47 179	90.39 212	93.56 225	79.46 233	94.04 190	95.54 173	88.67 81	86.96 180	94.58 158	69.33 256	97.15 237	84.05 181	80.53 336	94.56 225

ACMP	84.23 8	89.01 158	88.35 155	90.99 189	94.73 166	81.27 180	95.07 122	95.89 146	86.48 140	83.67 275	94.30 165	69.33 256	97.99 167	87.10 147	88.55 238	93.72 275
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_post1							88.00 349				9.81 407	69.31 258	95.53 320	76.65 286

tpmvs		83.35 299	82.07 298	87.20 311	91.07 308	71.00 358	88.31 346	91.70 310	78.91 297	80.49 318	87.18 356	69.30 259	97.08 242	68.12 348	83.56 293	93.51 283

thres200		87.21 221	86.24 220	90.12 223	95.36 133	78.53 253	93.26 229	92.10 298	86.42 143	88.00 161	91.11 281	69.24 260	98.00 166	69.58 338	91.04 199	93.83 265

tfpn200view9		87.58 202	86.64 202	90.41 211	95.99 109	78.64 250	94.58 151	91.98 304	86.94 130	88.09 156	91.77 257	69.18 261	98.10 150	70.13 334	91.10 193	94.48 235

thres400		87.62 200	86.64 202	90.57 199	95.99 109	78.64 250	94.58 151	91.98 304	86.94 130	88.09 156	91.77 257	69.18 261	98.10 150	70.13 334	91.10 193	94.96 207

WB-MVSnew		83.77 294	83.28 285	85.26 340	91.48 289	71.03 356	91.89 273	87.98 366	78.91 297	84.78 244	90.22 302	69.11 263	94.02 345	64.70 365	90.44 204	90.71 354

tfpnnormal		84.72 281	83.23 287	89.20 259	92.79 251	80.05 217	94.48 156	95.81 150	82.38 239	81.08 310	91.21 274	69.01 264	96.95 251	61.69 374	80.59 334	90.58 359

thres100view900		87.63 198	86.71 199	90.38 214	96.12 97	78.55 252	95.03 125	91.58 314	87.15 123	88.06 159	92.29 238	68.91 265	98.10 150	70.13 334	91.10 193	94.48 235

thres600view7		87.65 195	86.67 201	90.59 198	96.08 102	78.72 248	94.88 133	91.58 314	87.06 126	88.08 158	92.30 237	68.91 265	98.10 150	70.05 337	91.10 193	94.96 207

PatchMatch-RL		86.77 238	85.54 245	90.47 210	95.88 112	82.71 145	90.54 305	92.31 291	79.82 287	84.32 261	91.57 268	68.77 267	96.39 284	73.16 315	93.48 162	92.32 324

XVG-OURS		89.40 144	88.70 144	91.52 161	94.06 201	81.46 176	91.27 291	96.07 130	86.14 153	88.89 147	95.77 108	68.73 268	97.26 230	87.39 139	89.96 212	95.83 176

TR-MVS		86.78 235	85.76 241	89.82 237	94.37 188	78.41 257	92.47 255	92.83 276	81.11 274	86.36 198	92.40 233	68.73 268	97.48 201	73.75 313	89.85 216	93.57 279

tpm		84.73 280	84.02 275	86.87 320	90.33 334	68.90 368	89.06 336	89.94 352	80.85 276	85.75 211	89.86 314	68.54 270	95.97 302	77.76 275	84.05 287	95.75 179

FMVSNet3		87.40 210	86.11 225	91.30 172	93.79 217	83.64 110	94.20 178	94.81 220	83.89 203	84.37 256	91.87 256	68.45 271	96.56 272	78.23 271	85.36 276	93.70 276

MVP-Stereo		85.97 256	84.86 263	89.32 256	90.92 316	82.19 157	92.11 270	94.19 243	78.76 303	78.77 339	91.63 263	68.38 272	96.56 272	75.01 303	93.95 150	89.20 369
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
tpm cat1		81.96 306	80.27 312	87.01 314	91.09 307	71.02 357	87.38 358	91.53 317	66.25 383	80.17 320	86.35 362	68.22 273	96.15 296	69.16 339	82.29 307	93.86 263

dmvs_testset		74.57 350	75.81 349	70.86 375	87.72 369	40.47 408	87.05 361	77.90 400	82.75 233	71.15 379	85.47 368	67.98 274	84.12 397	45.26 394	76.98 361	88.00 378

sd_testset		88.59 171	87.85 170	90.83 193	96.00 106	80.42 206	92.35 260	94.71 225	88.73 78	86.85 187	95.20 128	67.31 275	96.43 282	79.64 256	89.85 216	95.63 185

tpm2		84.08 288	82.94 292	87.48 302	91.39 294	71.27 352	89.23 333	90.37 342	71.95 371	84.64 247	89.33 322	67.30 276	96.55 274	75.17 300	87.09 265	94.63 219

test-LLR		85.87 258	85.41 248	87.25 307	90.95 312	71.67 350	89.55 325	89.88 355	83.41 216	84.54 250	87.95 344	67.25 277	95.11 331	81.82 221	93.37 165	94.97 204

test0.0.03 1		82.41 304	81.69 300	84.59 344	88.23 362	72.89 333	90.24 312	87.83 368	83.41 216	79.86 328	89.78 316	67.25 277	88.99 387	65.18 362	83.42 296	91.90 332

CVMVSNet		84.69 282	84.79 265	84.37 346	91.84 277	64.92 382	93.70 210	91.47 319	66.19 384	86.16 205	95.28 122	67.18 279	93.33 356	80.89 238	90.42 206	94.88 212

thisisatest0515		87.33 213	85.99 230	91.37 169	93.49 226	79.55 231	90.63 304	89.56 360	80.17 281	87.56 170	90.86 286	67.07 280	98.28 139	81.50 228	93.02 171	96.29 153

tttt0517		88.61 169	87.78 171	91.11 181	94.96 154	77.81 274	95.35 101	89.69 357	85.09 179	88.05 160	94.59 157	66.93 281	98.48 114	83.27 191	92.13 186	97.03 120

our_test_3		81.93 307	80.46 310	86.33 327	88.46 359	73.48 329	88.46 344	91.11 326	76.46 326	76.69 351	88.25 340	66.89 282	94.36 339	68.75 341	79.08 350	91.14 348

thisisatest0530		88.67 167	87.61 175	91.86 148	94.87 160	80.07 215	94.63 149	89.90 354	84.00 200	88.46 153	93.78 191	66.88 283	98.46 118	83.30 190	92.65 178	97.06 117

IterMVS-SCA-FT		85.45 264	84.53 270	88.18 287	91.71 283	76.87 290	90.19 315	92.65 283	85.40 170	81.44 305	90.54 295	66.79 284	95.00 334	81.04 233	81.05 325	92.66 312

SCA		86.32 252	85.18 255	89.73 243	92.15 264	76.60 294	91.12 295	91.69 311	83.53 213	85.50 221	88.81 330	66.79 284	96.48 277	76.65 286	90.35 207	96.12 161

D2MVS		85.90 257	85.09 257	88.35 281	90.79 321	77.42 283	91.83 276	95.70 160	80.77 277	80.08 324	90.02 310	66.74 286	96.37 285	81.88 220	87.97 251	91.26 345

IterMVS		84.88 277	83.98 277	87.60 297	91.44 290	76.03 302	90.18 316	92.41 287	83.24 222	81.06 311	90.42 299	66.60 287	94.28 342	79.46 257	80.98 330	92.48 316
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		87.26 215	85.98 231	91.08 182	94.01 204	83.10 127	95.14 119	94.94 206	83.57 210	84.37 256	91.64 260	66.59 288	96.34 288	78.23 271	85.36 276	93.79 266

test1		87.26 215	85.98 231	91.08 182	94.01 204	83.10 127	95.14 119	94.94 206	83.57 210	84.37 256	91.64 260	66.59 288	96.34 288	78.23 271	85.36 276	93.79 266

FMVSNet2		87.19 223	85.82 237	91.30 172	94.01 204	83.67 108	94.79 139	94.94 206	83.57 210	83.88 270	92.05 251	66.59 288	96.51 275	77.56 278	85.01 279	93.73 274

EPMVS		83.90 293	82.70 297	87.51 299	90.23 337	72.67 337	88.62 342	81.96 389	81.37 267	85.01 241	88.34 338	66.31 291	94.45 336	75.30 299	87.12 264	95.43 190

Syy-MVS		80.07 329	79.78 318	80.94 361	91.92 273	59.93 392	89.75 323	87.40 372	81.72 258	78.82 336	87.20 354	66.29 292	91.29 375	47.06 393	87.84 254	91.60 337

ppachtmachnet_test		81.84 308	80.07 316	87.15 312	88.46 359	74.43 321	89.04 337	92.16 296	75.33 339	77.75 344	88.99 327	66.20 293	95.37 327	65.12 363	77.60 355	91.65 335

MDA-MVSNet_test_wron		79.21 338	77.19 340	85.29 338	88.22 363	72.77 335	85.87 367	90.06 349	74.34 349	62.62 389	87.56 350	66.14 294	91.99 370	66.90 357	73.01 368	91.10 351

YYNet1		79.22 337	77.20 339	85.28 339	88.20 364	72.66 338	85.87 367	90.05 351	74.33 350	62.70 387	87.61 349	66.09 295	92.03 368	66.94 354	72.97 369	91.15 347

JIA-IIPM		81.04 320	78.98 332	87.25 307	88.64 355	73.48 329	81.75 388	89.61 359	73.19 361	82.05 298	73.71 392	66.07 296	95.87 307	71.18 325	84.60 282	92.41 320

MSDG		84.86 278	83.09 289	90.14 222	93.80 215	80.05 217	89.18 334	93.09 270	78.89 299	78.19 340	91.91 254	65.86 297	97.27 228	68.47 343	88.45 242	93.11 298

FE-MVS		87.40 210	86.02 229	91.57 160	94.56 178	79.69 229	90.27 308	93.72 261	80.57 278	88.80 148	91.62 264	65.32 298	98.59 108	74.97 304	94.33 147	96.44 148

jajsoiax		88.24 179	87.50 177	90.48 207	90.89 318	80.14 212	95.31 103	95.65 166	84.97 181	84.24 264	94.02 176	65.31 299	97.42 210	88.56 124	88.52 240	93.89 258

cascas		86.43 251	84.98 259	90.80 195	92.10 268	80.92 193	90.24 312	95.91 143	73.10 362	83.57 279	88.39 337	65.15 300	97.46 204	84.90 170	91.43 190	94.03 255

ADS-MVSNet2		81.66 312	79.71 321	87.50 300	91.35 296	74.19 323	83.33 383	88.48 364	72.90 364	82.24 296	85.77 366	64.98 301	93.20 359	64.57 366	83.74 289	95.12 200

ADS-MVSNet		81.56 314	79.78 318	86.90 318	91.35 296	71.82 347	83.33 383	89.16 362	72.90 364	82.24 296	85.77 366	64.98 301	93.76 350	64.57 366	83.74 289	95.12 200

pmmvs5		84.21 286	82.84 296	88.34 282	88.95 353	76.94 289	92.41 256	91.91 308	75.63 336	80.28 319	91.18 277	64.59 303	95.57 319	77.09 284	83.47 294	92.53 315

PVSNet	78.82 18	85.55 263	84.65 267	88.23 286	94.72 167	71.93 345	87.12 360	92.75 279	78.80 302	84.95 242	90.53 296	64.43 304	96.71 261	74.74 305	93.86 152	96.06 167

dmvs_re		84.20 287	83.22 288	87.14 313	91.83 279	77.81 274	90.04 318	90.19 345	84.70 190	81.49 303	89.17 324	64.37 305	91.13 377	71.58 321	85.65 275	92.46 318

UGNet		89.95 124	88.95 137	92.95 92	94.51 180	83.31 120	95.70 85	95.23 193	89.37 56	87.58 169	93.94 182	64.00 306	98.78 91	83.92 183	96.31 107	96.74 138
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
WB-MVS		67.92 357	67.49 359	69.21 379	81.09 390	41.17 407	88.03 348	78.00 399	73.50 358	62.63 388	83.11 379	63.94 307	86.52 391	25.66 404	51.45 397	79.94 390

RPSCF		85.07 274	84.27 271	87.48 302	92.91 247	70.62 361	91.69 281	92.46 285	76.20 332	82.67 292	95.22 125	63.94 307	97.29 227	77.51 279	85.80 273	94.53 226

iter_conf05		88.85 161	88.08 164	91.17 177	94.27 194	81.64 168	95.18 115	92.15 297	86.23 149	87.28 176	94.07 172	63.89 309	97.55 195	90.63 102	89.00 233	94.32 241

mvs_tets		88.06 185	87.28 184	90.38 214	90.94 314	79.88 224	95.22 112	95.66 164	85.10 178	84.21 265	93.94 182	63.53 310	97.40 217	88.50 125	88.40 244	93.87 261

SSC-MVS		67.06 358	66.56 360	68.56 381	80.54 391	40.06 409	87.77 352	77.37 402	72.38 368	61.75 390	82.66 381	63.37 311	86.45 392	24.48 405	48.69 400	79.16 392

test1111		89.10 150	88.64 145	90.48 207	95.53 129	74.97 313	96.08 62	84.89 381	88.13 101	90.16 129	96.65 70	63.29 312	98.10 150	86.14 153	96.90 93	98.39 39

Anonymous20231211		86.59 243	85.13 256	90.98 191	96.52 87	81.50 172	96.14 58	96.16 121	73.78 355	83.65 276	92.15 242	63.26 313	97.37 221	82.82 199	81.74 316	94.06 253

ECVR-MVS		89.09 152	88.53 149	90.77 196	95.62 124	75.89 304	96.16 54	84.22 383	87.89 109	90.20 127	96.65 70	63.19 314	98.10 150	85.90 158	96.94 91	98.33 43

dp		81.47 316	80.23 313	85.17 341	89.92 343	65.49 379	86.74 362	90.10 348	76.30 330	81.10 309	87.12 357	62.81 315	95.92 304	68.13 347	79.88 343	94.09 251

LFMVS		90.08 118	89.13 132	92.95 92	96.71 77	82.32 156	96.08 62	89.91 353	86.79 133	92.15 93	96.81 63	62.60 316	98.34 133	87.18 142	93.90 151	98.19 60

Anonymous20231206		81.03 321	79.77 320	84.82 343	87.85 368	70.26 363	91.42 286	92.08 299	73.67 356	77.75 344	89.25 323	62.43 317	93.08 360	61.50 375	82.00 312	91.12 349

VDD-MVS		90.74 103	89.92 115	93.20 77	96.27 93	83.02 133	95.73 83	93.86 256	88.42 89	92.53 83	96.84 60	62.09 318	98.64 100	90.95 97	92.62 179	97.93 78

MS-PatchMatch		85.05 275	84.16 272	87.73 295	91.42 293	78.51 254	91.25 292	93.53 263	77.50 318	80.15 321	91.58 266	61.99 319	95.51 322	75.69 295	94.35 146	89.16 370

OurMVSNet-221017-0		85.35 268	84.64 268	87.49 301	90.77 322	72.59 341	94.01 193	94.40 235	84.72 189	79.62 332	93.17 209	61.91 320	96.72 259	81.99 217	81.16 321	93.16 296

test_vis1_n_1920		89.39 145	89.84 116	88.04 290	92.97 245	72.64 339	94.71 145	96.03 135	86.18 151	91.94 100	96.56 78	61.63 321	95.74 315	93.42 41	95.11 130	95.74 180

test20.03		79.95 331	79.08 330	82.55 356	85.79 378	67.74 373	91.09 296	91.08 327	81.23 272	74.48 366	89.96 313	61.63 321	90.15 381	60.08 378	76.38 362	89.76 362

DSMNet-mixed		76.94 346	76.29 345	78.89 365	83.10 387	56.11 401	87.78 351	79.77 393	60.65 390	75.64 358	88.71 333	61.56 323	88.34 388	60.07 379	89.29 228	92.21 327

Anonymous20240529		88.09 183	86.59 206	92.58 112	96.53 86	81.92 163	95.99 71	95.84 149	74.11 352	89.06 145	95.21 127	61.44 324	98.81 89	83.67 188	87.47 258	97.01 121

IB-MVS	80.51 15	85.24 272	83.26 286	91.19 175	92.13 266	79.86 225	91.75 278	91.29 323	83.28 221	80.66 315	88.49 336	61.28 325	98.46 118	80.99 236	79.46 347	95.25 197
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
GA-MVS		86.61 241	85.27 254	90.66 197	91.33 298	78.71 249	90.40 307	93.81 259	85.34 171	85.12 238	89.57 319	61.25 326	97.11 241	80.99 236	89.59 222	96.15 158

N_pmnet		68.89 356	68.44 358	70.23 376	89.07 352	28.79 413	88.06 347	19.50 413	69.47 379	71.86 376	84.93 369	61.24 327	91.75 372	54.70 388	77.15 358	90.15 360

EU-MVSNet		81.32 318	80.95 306	82.42 358	88.50 358	63.67 386	93.32 222	91.33 321	64.02 387	80.57 317	92.83 220	61.21 328	92.27 367	76.34 290	80.38 339	91.32 343

testing91		87.11 226	86.18 221	89.92 233	94.43 186	75.38 312	91.53 284	92.27 293	86.48 140	86.50 192	90.24 301	61.19 329	97.53 197	82.10 213	90.88 201	96.84 134

test_cas_vis1_n_1920		88.83 165	88.85 143	88.78 269	91.15 305	76.72 292	93.85 203	94.93 210	83.23 223	92.81 74	96.00 96	61.17 330	94.45 336	91.67 85	94.84 132	95.17 199

VDDNet		89.56 136	88.49 153	92.76 101	95.07 148	82.09 158	96.30 44	93.19 269	81.05 275	91.88 101	96.86 59	61.16 331	98.33 135	88.43 126	92.49 183	97.84 84

PVSNet_0	73.20 20	77.22 345	74.83 351	84.37 346	90.70 326	71.10 355	83.09 385	89.67 358	72.81 366	73.93 368	83.13 377	60.79 332	93.70 352	68.54 342	50.84 398	88.30 377

SixPastTwentyTwo		83.91 292	82.90 294	86.92 317	90.99 310	70.67 360	93.48 216	91.99 303	85.54 167	77.62 346	92.11 246	60.59 333	96.87 256	76.05 294	77.75 354	93.20 294

gg-mvs-nofinetune		81.77 309	79.37 324	88.99 266	90.85 320	77.73 279	86.29 365	79.63 394	74.88 346	83.19 287	69.05 395	60.34 334	96.11 297	75.46 297	94.64 138	93.11 298

MDA-MVSNet-bldmvs		78.85 339	76.31 344	86.46 324	89.76 345	73.88 325	88.79 339	90.42 341	79.16 295	59.18 391	88.33 339	60.20 335	94.04 344	62.00 373	68.96 380	91.48 341

pmmvs6		83.42 297	81.60 301	88.87 268	88.01 365	77.87 272	94.96 128	94.24 242	74.67 347	78.80 338	91.09 282	60.17 336	96.49 276	77.06 285	75.40 366	92.23 326

ACMH	80.38 17	85.36 267	83.68 280	90.39 212	94.45 184	80.63 200	94.73 143	94.85 216	82.09 244	77.24 347	92.65 226	60.01 337	97.58 192	72.25 319	84.87 280	92.96 303
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GG-mvs-BLEND				87.94 293	89.73 347	77.91 269	87.80 350	78.23 398		80.58 316	83.86 373	59.88 338	95.33 328	71.20 323	92.22 185	90.60 358

UniMVSNet_ETH3D		87.53 204	86.37 213	91.00 188	92.44 258	78.96 247	94.74 142	95.61 168	84.07 199	85.36 235	94.52 159	59.78 339	97.34 222	82.93 195	87.88 252	96.71 139

pmmvs-eth3d		80.97 322	78.72 334	87.74 294	84.99 383	79.97 223	90.11 317	91.65 312	75.36 338	73.51 369	86.03 363	59.45 340	93.96 348	75.17 300	72.21 371	89.29 368

testing99		86.72 239	85.73 244	89.69 245	94.23 195	74.91 315	91.35 288	90.97 332	86.14 153	86.36 198	90.22 302	59.41 341	97.48 201	82.24 210	90.66 202	96.69 140

test_0402		81.30 319	79.17 329	87.67 296	93.19 234	78.17 264	92.98 240	91.71 309	75.25 340	76.02 357	90.31 300	59.23 342	96.37 285	50.22 391	83.63 292	88.47 376

KD-MVS_self_test		80.20 328	79.24 326	83.07 353	85.64 380	65.29 380	91.01 298	93.93 252	78.71 305	76.32 353	86.40 361	59.20 343	92.93 362	72.59 317	69.35 377	91.00 353

iter_conf05_11		89.88 128	89.04 135	92.41 119	95.12 146	81.63 169	92.87 245	92.45 286	86.21 150	92.48 86	93.95 181	59.05 344	98.60 107	90.50 106	98.72 32	96.99 123

bld_raw_dy_0_64		88.86 160	87.75 172	92.21 131	95.12 146	81.19 185	95.56 96	91.29 323	85.30 173	89.10 142	94.38 161	59.04 345	98.44 124	90.50 106	89.43 223	96.99 123

FMVSNet1		85.85 259	84.11 273	91.08 182	92.81 250	83.10 127	95.14 119	94.94 206	81.64 261	82.68 291	91.64 260	59.01 346	96.34 288	75.37 298	83.78 288	93.79 266

testing11		86.44 250	85.35 252	89.69 245	94.29 193	75.40 311	91.30 289	90.53 340	84.76 187	85.06 239	90.13 307	58.95 347	97.45 205	82.08 214	91.09 197	96.21 157

COLMAP_ROB	80.39 16	83.96 290	82.04 299	89.74 241	95.28 136	79.75 227	94.25 174	92.28 292	75.17 341	78.02 343	93.77 192	58.60 348	97.84 175	65.06 364	85.92 272	91.63 336
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMH+	81.04 14	85.05 275	83.46 283	89.82 237	94.66 171	79.37 236	94.44 161	94.12 248	82.19 243	78.04 342	92.82 221	58.23 349	97.54 196	73.77 312	82.90 302	92.54 314

CMPMVS	59.16 21	80.52 324	79.20 328	84.48 345	83.98 384	67.63 374	89.95 321	93.84 258	64.79 386	66.81 385	91.14 280	57.93 350	95.17 329	76.25 291	88.10 247	90.65 355
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
tt0805		86.92 231	85.74 243	90.48 207	92.22 262	79.98 222	95.63 92	94.88 214	83.83 205	84.74 246	92.80 223	57.61 351	97.67 183	85.48 164	84.42 283	93.79 266

ITE_SJBPF				88.24 285	91.88 276	77.05 288		92.92 273	85.54 167	80.13 323	93.30 204	57.29 352	96.20 293	72.46 318	84.71 281	91.49 340

UWE-MVS		83.69 296	83.09 289	85.48 335	93.06 239	65.27 381	90.92 299	86.14 374	79.90 285	86.26 202	90.72 293	57.17 353	95.81 311	71.03 328	92.62 179	95.35 194

TESTMET0.1,1		83.74 295	82.85 295	86.42 326	89.96 342	71.21 354	89.55 325	87.88 367	77.41 319	83.37 283	87.31 352	56.71 354	93.65 353	80.62 243	92.85 176	94.40 238

UnsupCasMVSNet_eth		80.07 329	78.27 335	85.46 336	85.24 382	72.63 340	88.45 345	94.87 215	82.99 228	71.64 377	88.07 343	56.34 355	91.75 372	73.48 314	63.36 389	92.01 330

test_fmvs1		87.34 212	87.56 176	86.68 323	90.59 328	71.80 348	94.01 193	94.04 250	78.30 311	91.97 97	95.22 125	56.28 356	93.71 351	92.89 49	94.71 134	94.52 227

K. test v3		81.59 313	80.15 315	85.91 332	89.89 344	69.42 367	92.57 253	87.71 369	85.56 166	73.44 370	89.71 317	55.58 357	95.52 321	77.17 282	69.76 376	92.78 310

test-mter		84.54 283	83.64 281	87.25 307	90.95 312	71.67 350	89.55 325	89.88 355	79.17 294	84.54 250	87.95 344	55.56 358	95.11 331	81.82 221	93.37 165	94.97 204

lessismore_v0				86.04 328	88.46 359	68.78 369		80.59 392		73.01 372	90.11 308	55.39 359	96.43 282	75.06 302	65.06 386	92.90 305

ETVMVS		84.43 284	82.92 293	88.97 267	94.37 188	74.67 316	91.23 293	88.35 365	83.37 218	86.06 207	89.04 326	55.38 360	95.67 317	67.12 352	91.34 191	96.58 144

MVS-HIRNet		73.70 351	72.20 354	78.18 368	91.81 280	56.42 400	82.94 386	82.58 387	55.24 392	68.88 382	66.48 396	55.32 361	95.13 330	58.12 383	88.42 243	83.01 385

test2506		87.21 221	86.28 218	90.02 229	95.62 124	73.64 327	96.25 49	71.38 405	87.89 109	90.45 123	96.65 70	55.29 362	98.09 158	86.03 157	96.94 91	98.33 43

new-patchmatchnet		76.41 347	75.17 350	80.13 362	82.65 389	59.61 393	87.66 355	91.08 327	78.23 314	69.85 381	83.22 376	54.76 363	91.63 374	64.14 368	64.89 387	89.16 370

Anonymous202405211		87.68 193	86.13 223	92.31 126	96.66 79	80.74 198	94.87 134	91.49 318	80.47 279	89.46 138	95.44 117	54.72 364	98.23 141	82.19 211	89.89 214	97.97 74

XVG-ACMP-BASELINE		86.00 255	84.84 264	89.45 254	91.20 300	78.00 267	91.70 280	95.55 171	85.05 180	82.97 288	92.25 240	54.49 365	97.48 201	82.93 195	87.45 260	92.89 306

USDC		82.76 300	81.26 305	87.26 306	91.17 302	74.55 318	89.27 331	93.39 266	78.26 313	75.30 360	92.08 248	54.43 366	96.63 263	71.64 320	85.79 274	90.61 356

AllTest		83.42 297	81.39 303	89.52 251	95.01 150	77.79 276	93.12 233	90.89 335	77.41 319	76.12 355	93.34 200	54.08 367	97.51 199	68.31 345	84.27 285	93.26 289

TestCases				89.52 251	95.01 150	77.79 276		90.89 335	77.41 319	76.12 355	93.34 200	54.08 367	97.51 199	68.31 345	84.27 285	93.26 289

KD-MVS_2432*1600		78.50 340	76.02 347	85.93 330	86.22 374	74.47 319	84.80 376	92.33 289	79.29 292	76.98 349	85.92 364	53.81 369	93.97 346	67.39 350	57.42 394	89.36 365

miper_refine_blended		78.50 340	76.02 347	85.93 330	86.22 374	74.47 319	84.80 376	92.33 289	79.29 292	76.98 349	85.92 364	53.81 369	93.97 346	67.39 350	57.42 394	89.36 365

MIMVSNet		82.59 303	80.53 308	88.76 270	91.51 288	78.32 260	86.57 364	90.13 347	79.32 291	80.70 314	88.69 335	52.98 371	93.07 361	66.03 359	88.86 235	94.90 211

testing222		84.84 279	83.32 284	89.43 255	94.15 200	75.94 303	91.09 296	89.41 361	84.90 182	85.78 210	89.44 321	52.70 372	96.28 291	70.80 329	91.57 189	96.07 165

FMVSNet5		81.52 315	79.60 322	87.27 305	91.17 302	77.95 268	91.49 285	92.26 294	76.87 324	76.16 354	87.91 346	51.67 373	92.34 366	67.74 349	81.16 321	91.52 339

testgi		80.94 323	80.20 314	83.18 352	87.96 366	66.29 376	91.28 290	90.70 339	83.70 207	78.12 341	92.84 219	51.37 374	90.82 379	63.34 369	82.46 305	92.43 319

test_fmvs1_n		87.03 229	87.04 190	86.97 315	89.74 346	71.86 346	94.55 153	94.43 232	78.47 307	91.95 99	95.50 116	51.16 375	93.81 349	93.02 48	94.56 140	95.26 196

Anonymous20240521		80.44 326	79.21 327	84.11 349	85.75 379	67.89 371	92.86 246	93.23 268	75.61 337	75.59 359	87.47 351	50.03 376	94.33 340	71.14 326	81.21 320	90.12 361

UnsupCasMVSNet_bld		76.23 348	73.27 352	85.09 342	83.79 385	72.92 332	85.65 370	93.47 265	71.52 372	68.84 383	79.08 387	49.77 377	93.21 358	66.81 358	60.52 391	89.13 372

OpenMVS_ROB	74.94 19	79.51 335	77.03 342	86.93 316	87.00 371	76.23 301	92.33 262	90.74 338	68.93 380	74.52 365	88.23 341	49.58 378	96.62 264	57.64 384	84.29 284	87.94 379

TDRefinement		79.81 332	77.34 337	87.22 310	79.24 395	75.48 309	93.12 233	92.03 301	76.45 327	75.01 361	91.58 266	49.19 379	96.44 281	70.22 333	69.18 379	89.75 363

test_vis1_n		86.56 244	86.49 211	86.78 322	88.51 356	72.69 336	94.68 146	93.78 260	79.55 290	90.70 120	95.31 121	48.75 380	93.28 357	93.15 45	93.99 149	94.38 239

MIMVSNet1		79.38 336	77.28 338	85.69 334	86.35 373	73.67 326	91.61 283	92.75 279	78.11 316	72.64 373	88.12 342	48.16 381	91.97 371	60.32 377	77.49 356	91.43 342

LF4IMVS		80.37 327	79.07 331	84.27 348	86.64 372	69.87 366	89.39 330	91.05 329	76.38 328	74.97 362	90.00 311	47.85 382	94.25 343	74.55 308	80.82 332	88.69 374

EG-PatchMatch MVS		82.37 305	80.34 311	88.46 278	90.27 335	79.35 237	92.80 248	94.33 238	77.14 323	73.26 371	90.18 305	47.47 383	96.72 259	70.25 331	87.32 263	89.30 367

test_fmvs2		83.98 289	84.03 274	83.83 351	87.16 370	67.53 375	93.93 199	92.89 274	77.62 317	86.89 186	93.53 197	47.18 384	92.02 369	90.54 103	86.51 269	91.93 331

TinyColmap		79.76 333	77.69 336	85.97 329	91.71 283	73.12 331	89.55 325	90.36 343	75.03 342	72.03 375	90.19 304	46.22 385	96.19 295	63.11 370	81.03 326	88.59 375

myMVS_eth3d		79.67 334	78.79 333	82.32 359	91.92 273	64.08 384	89.75 323	87.40 372	81.72 258	78.82 336	87.20 354	45.33 386	91.29 375	59.09 382	87.84 254	91.60 337

tmp_tt		35.64 373	39.24 375	24.84 389	14.87 413	23.90 414	62.71 399	51.51 412	6.58 407	36.66 403	62.08 400	44.37 387	30.34 409	52.40 390	22.00 406	20.27 404

testing3		80.46 325	79.59 323	83.06 354	93.44 229	64.64 383	93.33 221	85.47 378	84.34 195	79.93 327	90.84 288	44.35 388	92.39 365	57.06 386	87.56 257	92.16 328

new_pmnet		72.15 352	70.13 356	78.20 367	82.95 388	65.68 377	83.91 381	82.40 388	62.94 389	64.47 386	79.82 386	42.85 389	86.26 393	57.41 385	74.44 367	82.65 387

test_vis1_rt		77.96 343	76.46 343	82.48 357	85.89 377	71.74 349	90.25 310	78.89 395	71.03 376	71.30 378	81.35 384	42.49 390	91.05 378	84.55 175	82.37 306	84.65 382

EGC-MVSNET		61.97 362	56.37 366	78.77 366	89.63 348	73.50 328	89.12 335	82.79 386	0.21 410	1.24 411	84.80 370	39.48 391	90.04 382	44.13 395	75.94 365	72.79 394

pmmvs3		71.81 354	68.71 357	81.11 360	75.86 396	70.42 362	86.74 362	83.66 384	58.95 391	68.64 384	80.89 385	36.93 392	89.52 384	63.10 371	63.59 388	83.39 383

mvsany_test3		74.95 349	73.26 353	80.02 363	74.61 397	63.16 388	85.53 371	78.42 396	74.16 351	74.89 363	86.46 359	36.02 393	89.09 386	82.39 206	66.91 383	87.82 380

PM-MVS		78.11 342	76.12 346	84.09 350	83.54 386	70.08 364	88.97 338	85.27 380	79.93 284	74.73 364	86.43 360	34.70 394	93.48 354	79.43 260	72.06 372	88.72 373

ambc				83.06 354	79.99 393	63.51 387	77.47 394	92.86 275		74.34 367	84.45 372	28.74 395	95.06 333	73.06 316	68.89 381	90.61 356

test_method		50.52 369	48.47 371	56.66 385	52.26 411	18.98 415	41.51 403	81.40 390	10.10 405	44.59 400	75.01 391	28.51 396	68.16 403	53.54 389	49.31 399	82.83 386

DeepMVS_CX				56.31 386	74.23 398	51.81 403		56.67 411	44.85 397	48.54 397	75.16 390	27.87 397	58.74 407	40.92 399	52.22 396	58.39 400

test_fmvs3		77.67 344	77.16 341	79.22 364	79.52 394	61.14 390	92.34 261	91.64 313	73.98 353	78.86 335	86.59 358	27.38 398	87.03 389	88.12 130	75.97 364	89.50 364

test_f		71.95 353	70.87 355	75.21 371	74.21 399	59.37 394	85.07 375	85.82 376	65.25 385	70.42 380	83.13 377	23.62 399	82.93 399	78.32 269	71.94 373	83.33 384

FPMVS		64.63 361	62.55 363	70.88 374	70.80 401	56.71 396	84.42 379	84.42 382	51.78 395	49.57 395	81.61 383	23.49 400	81.48 400	40.61 400	76.25 363	74.46 393

APD_test1		69.04 355	66.26 361	77.36 370	80.51 392	62.79 389	85.46 372	83.51 385	54.11 394	59.14 392	84.79 371	23.40 401	89.61 383	55.22 387	70.24 375	79.68 391

ANet_high		58.88 366	54.22 370	72.86 372	56.50 410	56.67 397	80.75 390	86.00 375	73.09 363	37.39 402	64.63 399	22.17 402	79.49 402	43.51 396	23.96 404	82.43 388

EMVS		42.07 372	41.12 374	44.92 388	63.45 408	35.56 412	73.65 395	63.48 408	33.05 403	26.88 407	45.45 404	21.27 403	67.14 405	19.80 407	23.02 405	32.06 403

Gipuma		57.99 367	54.91 369	67.24 382	88.51 356	65.59 378	52.21 401	90.33 344	43.58 398	42.84 401	51.18 402	20.29 404	85.07 394	34.77 401	70.45 374	51.05 401
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		43.23 371	42.29 373	46.03 387	65.58 406	37.41 410	73.51 396	64.62 407	33.99 402	28.47 406	47.87 403	19.90 405	67.91 404	22.23 406	24.45 403	32.77 402

PMMVS2		59.60 363	56.40 365	69.21 379	68.83 404	46.58 405	73.02 398	77.48 401	55.07 393	49.21 396	72.95 394	17.43 406	80.04 401	49.32 392	44.33 401	80.99 389

LCM-MVSNet		66.00 359	62.16 364	77.51 369	64.51 407	58.29 395	83.87 382	90.90 334	48.17 396	54.69 393	73.31 393	16.83 407	86.75 390	65.47 360	61.67 390	87.48 381

test_vis3_rt		65.12 360	62.60 362	72.69 373	71.44 400	60.71 391	87.17 359	65.55 406	63.80 388	53.22 394	65.65 398	14.54 408	89.44 385	76.65 286	65.38 385	67.91 397

testf1		59.54 364	56.11 367	69.85 377	69.28 402	56.61 398	80.37 391	76.55 403	42.58 399	45.68 398	75.61 388	11.26 409	84.18 395	43.20 397	60.44 392	68.75 395

APD_test2		59.54 364	56.11 367	69.85 377	69.28 402	56.61 398	80.37 391	76.55 403	42.58 399	45.68 398	75.61 388	11.26 409	84.18 395	43.20 397	60.44 392	68.75 395

PMVS	47.18 22	52.22 368	48.46 372	63.48 383	45.72 412	46.20 406	73.41 397	78.31 397	41.03 401	30.06 404	65.68 397	6.05 411	83.43 398	30.04 402	65.86 384	60.80 398
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	39.65 23	43.39 370	38.59 376	57.77 384	56.52 409	48.77 404	55.38 400	58.64 410	29.33 404	28.96 405	52.65 401	4.68 412	64.62 406	28.11 403	33.07 402	59.93 399
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		21.27 375	20.48 378	23.63 390	68.59 405	36.41 411	49.57 402	6.85 414	9.37 406	7.89 408	4.46 410	4.03 413	31.37 408	17.47 408	16.07 407	3.12 405

test123		8.76 377	11.22 380	1.39 391	0.85 415	0.97 416	85.76 369	0.35 416	0.54 409	2.45 410	8.14 409	0.60 414	0.48 410	2.16 410	0.17 409	2.71 406

testmvs		8.92 376	11.52 379	1.12 392	1.06 414	0.46 417	86.02 366	0.65 415	0.62 408	2.74 409	9.52 408	0.31 415	0.45 411	2.38 409	0.39 408	2.46 407

test_blank		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet_test		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

DCPMVS		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

sosnet-low-res		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

sosnet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uncertanet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

Regformer		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

ab-mvs-re		7.82 378	10.43 381	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	93.88 187	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

WAC-MVS						64.08 384								59.14 381

FOURS1					98.86 1	85.54 67	98.29 1	97.49 6	89.79 46	96.29 18

MSC_two_6792asdad				96.52 1	97.78 51	90.86 1		96.85 63					99.61 4	96.03 14	99.06 9	99.07 5

No_MVS				96.52 1	97.78 51	90.86 1		96.85 63					99.61 4	96.03 14	99.06 9	99.07 5

eth-test2					0.00 416

eth-test					0.00 416

IU-MVS					98.77 5	86.00 50		96.84 65	81.26 270	97.26 7				95.50 23	99.13 3	99.03 8

save fliter					97.85 46	85.63 66	95.21 113	96.82 68	89.44 53

test_0728_SECOND				95.01 17	98.79 2	86.43 39	97.09 16	97.49 6					99.61 4	95.62 21	99.08 7	98.99 9

GSMVS																96.12 161

test_part2					98.55 12	87.22 19				96.40 17

MTGPA								96.97 50

MTMP							96.16 54	60.64 409

gm-plane-assit					89.60 349	68.00 370			77.28 322		88.99 327		97.57 193	79.44 259

test9_res														91.91 80	98.71 33	98.07 68

agg_prior2														90.54 103	98.68 38	98.27 52

agg_prior					97.38 63	85.92 57		96.72 81		92.16 92			98.97 75

test_prior4						85.96 54	94.11 182

test_prior				93.82 62	97.29 67	84.49 86		96.88 61					98.87 82			98.11 67

旧先验2							93.36 220		71.25 374	94.37 39			97.13 240	86.74 148

新几何2							93.11 235

无先验							93.28 228	96.26 112	73.95 354				99.05 55	80.56 244		96.59 143

原ACMM2							92.94 242

testdata2													98.75 93	78.30 270

testdata1							92.15 268		87.94 105

plane_prior7					94.70 169	82.74 142

plane_prior5								96.22 117					98.12 148	88.15 127	89.99 210	94.63 219

plane_prior4											94.86 140

plane_prior3						82.75 140			90.26 33	86.91 183

plane_prior2							95.85 77		90.81 17

plane_prior1					94.59 174

plane_prior						82.73 143	95.21 113		89.66 50						89.88 215

n2								0.00 417

nn								0.00 417

door-mid								85.49 377

test11								96.57 92

door								85.33 379

HQP5-MVS						81.56 170

HQP-NCC					94.17 197		94.39 166		88.81 74	85.43 228

ACMP_Plane					94.17 197		94.39 166		88.81 74	85.43 228

BP-MVS														87.11 145

HQP4-MVS										85.43 228			97.96 169			94.51 229

HQP3-MVS								96.04 133							89.77 219

NP-MVS					94.37 188	82.42 152					93.98 179

ACMMP++_ref															87.47 258

ACMMP++															88.01 250

High-resolution multi-view benchmark