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									82.47 236	97.09 10	97.07 51	92.72 1	98.04 165	92.70 57	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 68	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 29	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 27	98.04 69	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	92.49 119	96.52 88	80.00 222	94.00 195	97.08 44	90.05 35	95.65 29	97.29 37	89.66 13	98.97 75	93.95 35	98.71 32	98.50 27

SD-MVS		94.96 13	95.33 8	93.88 59	97.25 69	86.69 28	96.19 50	97.11 43	90.42 27	96.95 13	97.27 38	89.53 14	96.91 255	94.38 31	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	95.29 106	96.96 52	92.09 6	95.32 31	97.08 49	89.49 15	99.33 37	95.10 25	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	95.00 124	97.12 41	87.13 123	92.51 87	96.30 83	89.24 17	99.34 34	93.46 41	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 60	96.62 88	88.14 99	96.10 20	96.96 55	89.09 18	98.94 78	94.48 30	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 33	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 47	97.28 31	85.90 156	97.67 3	98.10 7	88.41 20	99.56 12	94.66 28	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	92.01 135	97.54 57	78.37 259	93.40 219	97.19 35	88.02 102	94.99 35	97.21 42	88.35 21	98.44 127	94.07 34	98.09 66	99.23 1

9.14			94.47 20		97.79 49		96.08 61	97.44 15	86.13 154	95.10 33	97.40 33	88.34 22	99.22 44	93.25 46	98.70 34

SF-MVS		94.97 12	94.90 15	95.20 12	97.84 47	87.76 10	96.65 35	97.48 10	87.76 112	95.71 27	97.70 25	88.28 23	99.35 33	93.89 37	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 48	96.83 61	88.12 24	99.55 16	93.41 44	98.94 16	98.28 50

dcpmvs_2		93.49 52	94.19 36	91.38 170	97.69 54	76.78 291	94.25 173	96.29 109	88.33 90	94.46 38	96.88 58	88.07 25	98.64 102	93.62 40	98.09 66	98.73 17

CSCG		93.23 64	93.05 63	93.76 66	98.04 40	84.07 98	96.22 49	97.37 21	84.15 196	90.05 133	95.66 112	87.77 26	99.15 50	89.91 112	98.27 59	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 49	96.58 76	87.74 27	99.44 29	92.83 52	98.40 55	98.62 21

TEST9					97.53 58	86.49 37	94.07 187	96.78 72	81.61 263	92.77 78	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 78	96.20 87	87.63 29	99.12 51	92.14 73	98.69 36	97.94 77

test_8					97.49 60	86.30 45	94.02 192	96.76 75	81.86 254	92.70 82	96.20 87	87.63 29	99.02 61

ZD-MVS					98.15 34	86.62 33		97.07 45	83.63 208	94.19 42	96.91 57	87.57 31	99.26 42	91.99 79	98.44 54

fmvsm_l_conf0.5_n		94.29 28	94.46 21	93.79 65	95.28 140	85.43 68	95.68 86	96.43 98	86.56 139	96.84 14	97.81 23	87.56 32	98.77 92	97.14 6	96.82 99	97.16 117

fmvsm_l_conf0.5_n_a		94.20 34	94.40 23	93.60 69	95.29 139	84.98 73	95.61 93	96.28 112	86.31 146	96.75 16	97.86 21	87.40 33	98.74 95	97.07 8	97.02 92	97.07 119

TSAR-MVS + GP.		93.66 49	93.41 56	94.41 49	96.59 82	86.78 26	94.40 163	93.93 256	89.77 47	94.21 41	95.59 115	87.35 34	98.61 107	92.72 55	96.15 113	97.83 86

APD-MVS		94.24 30	94.07 39	94.75 36	98.06 39	86.90 23	95.88 76	96.94 55	85.68 162	95.05 34	97.18 45	87.31 35	99.07 53	91.90 85	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	81.81 169		95.67 167			96.81 63	86.69 37			97.66 82	96.97 128

test_prior2							94.12 181		87.67 115	92.63 83	96.39 82	86.62 38		91.50 91	98.67 40

CDPH-MVS		92.83 73	92.30 80	94.44 45	97.79 49	86.11 49	94.06 189	96.66 85	80.09 283	92.77 78	96.63 73	86.62 38	99.04 57	87.40 139	98.66 41	98.17 62

DPM-MVS		92.58 78	91.74 87	95.08 15	96.19 96	89.31 5	92.66 250	96.56 93	83.44 214	91.68 110	95.04 137	86.60 40	98.99 70	85.60 163	97.92 73	96.93 130

test_fmvsmconf_n		94.60 18	94.81 16	93.98 55	94.62 176	84.96 74	96.15 55	97.35 22	89.37 56	96.03 23	98.11 5	86.36 41	99.01 63	97.45 3	97.83 76	97.96 75

DELS-MVS		93.43 58	93.25 59	93.97 56	95.42 135	85.04 72	93.06 238	97.13 40	90.74 21	91.84 104	95.09 136	86.32 42	99.21 45	91.22 94	98.45 53	97.65 93
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	95.79 117	84.62 80	96.15 55	97.64 2	89.85 42	97.19 8	97.89 19	86.28 43	98.71 97	97.11 7	98.08 68	97.17 113

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 65	97.04 52	86.17 44	99.62 2	92.40 61	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 54	97.21 42	86.10 45	99.49 26	92.35 64	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	91.60 111	95.85 103	86.07 46	98.66 100	91.91 83	98.16 62	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 36	98.95 15	98.60 23

mamv4		90.92 103	91.78 86	88.33 283	95.67 124	70.75 360	92.92 243	96.02 139	81.90 251	88.11 157	95.34 122	85.88 48	96.97 250	95.22 24	95.01 134	97.26 108

CS-MVS		94.12 37	94.44 22	93.17 78	96.55 85	83.08 131	97.63 3	96.95 54	91.71 11	93.50 60	96.21 86	85.61 49	98.24 142	93.64 39	98.17 61	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	85.15 175	93.56 58	96.28 84	85.60 50	99.31 39	92.45 58	98.79 23	98.12 66

MP-MVS-pluss		94.21 32	94.00 42	94.85 25	98.17 33	86.65 31	94.82 135	97.17 39	86.26 148	92.83 75	97.87 20	85.57 51	99.56 12	94.37 32	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 62	96.83 61	85.48 52	99.59 8	91.43 93	98.40 55	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 97	97.19 44	85.43 53	99.56 12	92.06 78	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 76	96.97 54	85.37 54	99.24 43	90.87 103	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 56	97.27 38	85.22 55	99.54 20	92.21 69	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 81	97.23 41	85.20 56	99.32 38	92.15 72	98.83 21	98.25 57

test_fmvsmconf0.1_n		94.20 34	94.31 28	93.88 59	92.46 258	84.80 77	96.18 52	96.82 68	89.29 59	95.68 28	98.11 5	85.10 57	98.99 70	97.38 4	97.75 80	97.86 83

test12				94.34 50	97.13 70	86.15 48		96.29 109		91.04 119		85.08 58	99.01 63		98.13 64	97.86 83

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 59	97.26 40	85.04 59	99.54 20	92.35 64	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 71	95.77 108	85.02 60	98.33 137	93.03 49	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 73	97.16 47	85.02 60	99.49 26	91.99 79	98.56 49	98.47 33

X-MVStestdata		88.31 178	86.13 224	94.85 25	98.54 13	86.60 34	96.93 22	97.19 35	90.66 24	92.85 73	23.41 408	85.02 60	99.49 26	91.99 79	98.56 49	98.47 33

iter_conf05		92.85 72	92.89 68	92.73 106	96.58 84	82.47 153	94.20 177	96.16 123	84.42 193	90.65 123	95.56 116	85.01 63	98.69 98	94.96 26	98.47 52	97.03 123

MSLP-MVS++		93.72 48	94.08 38	92.65 111	97.31 65	83.43 116	95.79 81	97.33 25	90.03 36	93.58 56	96.96 55	84.87 64	97.76 180	92.19 71	98.66 41	96.76 138

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 84	96.80 65	84.85 65	99.17 47	92.43 59	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 40	96.90 59	88.20 97	94.33 40	97.40 33	84.75 66	99.03 58	93.35 45	97.99 70	98.48 30

PGM-MVS		93.96 42	93.72 50	94.68 38	98.43 20	86.22 47	95.30 104	97.78 1	87.45 119	93.26 62	97.33 36	84.62 67	99.51 24	90.75 105	98.57 48	98.32 46

EI-MVSNet-Vis-set		93.01 69	92.92 67	93.29 73	95.01 153	83.51 115	94.48 155	95.77 158	90.87 15	92.52 86	96.67 68	84.50 68	99.00 68	91.99 79	94.44 149	97.36 104

MTAPA		94.42 26	94.22 33	95.00 18	98.42 21	86.95 21	94.36 170	96.97 50	91.07 13	93.14 66	97.56 27	84.30 69	99.56 12	93.43 42	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 45	96.76 75	87.46 117	93.75 52	97.43 31	84.24 70	99.01 63	92.73 53	97.80 77	97.88 81

ETV-MVS		92.74 76	92.66 73	92.97 92	95.20 146	84.04 100	95.07 120	96.51 94	90.73 22	92.96 70	91.19 276	84.06 71	98.34 135	91.72 87	96.54 105	96.54 149

EI-MVSNet-UG-set		92.74 76	92.62 76	93.12 80	94.86 164	83.20 123	94.40 163	95.74 161	90.71 23	92.05 95	96.60 75	84.00 72	98.99 70	91.55 90	93.63 159	97.17 113

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	91.83 106	97.17 46	83.96 73	99.55 16	91.44 92	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 43	96.87 62	86.96 127	93.92 50	97.47 29	83.88 74	98.96 77	92.71 56	97.87 74	98.26 56

EIA-MVS		91.95 85	91.94 83	91.98 139	95.16 147	80.01 221	95.36 99	96.73 79	88.44 87	89.34 141	92.16 242	83.82 75	98.45 125	89.35 116	97.06 90	97.48 101

MVS_0304		94.60 18	94.38 25	95.23 11	95.41 136	87.49 16	96.53 38	92.75 283	93.82 2	93.07 69	97.84 22	83.66 76	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 98	95.62 128	83.17 124	96.14 57	96.12 128	88.13 100	95.82 26	98.04 16	83.43 77	98.48 116	96.97 9	96.23 111	96.92 131

casdiffmvs_mvg		92.96 71	92.83 70	93.35 72	94.59 177	83.40 118	95.00 124	96.34 106	90.30 30	92.05 95	96.05 95	83.43 77	98.15 149	92.07 75	95.67 117	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 91	91.56 89	92.13 134	95.88 114	80.50 205	97.33 7	95.25 197	86.15 151	89.76 136	95.60 114	83.42 79	98.32 139	87.37 141	93.25 171	97.56 99

test_fmvsmvis_n_1920		93.44 55	93.55 55	93.10 81	93.67 224	84.26 95	95.83 79	96.14 125	89.00 72	92.43 89	97.50 28	83.37 80	98.72 96	96.61 12	97.44 84	96.32 153

UA-Net		92.83 73	92.54 77	93.68 68	96.10 101	84.71 79	95.66 89	96.39 102	91.92 7	93.22 64	96.49 79	83.16 81	98.87 82	84.47 177	95.47 123	97.45 103

UniMVSNet_NR-MVSNet		89.92 131	89.29 134	91.81 154	93.39 232	83.72 106	94.43 161	97.12 41	89.80 43	86.46 195	93.32 203	83.16 81	97.23 233	84.92 169	81.02 328	94.49 236

EC-MVSNet		93.44 55	93.71 51	92.63 112	95.21 145	82.43 154	97.27 9	96.71 82	90.57 26	92.88 72	95.80 106	83.16 81	98.16 148	93.68 38	98.14 63	97.31 105

fmvsm_s_conf0.5_n_a		93.57 50	93.76 49	93.00 90	95.02 152	83.67 108	96.19 50	96.10 130	87.27 121	95.98 24	98.05 13	83.07 84	98.45 125	96.68 11	95.51 120	96.88 134

MM		95.10 11	94.91 13	95.68 5	96.09 102	88.34 9	96.68 33	94.37 240	95.08 1	94.68 36	97.72 24	82.94 85	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 45	96.76 75	87.46 117	93.75 52	97.43 31	82.94 85		92.73 53	97.80 77	97.88 81

新几何1				93.10 81	97.30 66	84.35 94		95.56 175	71.09 376	91.26 117	96.24 85	82.87 87	98.86 84	79.19 264	98.10 65	96.07 167

fmvsm_s_conf0.1_n		93.46 53	93.66 53	92.85 99	93.75 220	83.13 126	96.02 69	95.74 161	87.68 114	95.89 25	98.17 2	82.78 88	98.46 121	96.71 10	96.17 112	96.98 127

原ACMM1				92.01 135	97.34 64	81.05 189		96.81 70	78.89 299	90.45 125	95.92 100	82.65 89	98.84 88	80.68 243	98.26 60	96.14 161

bld_raw_dy_0_64		90.17 121	89.64 122	91.79 155	95.65 125	82.00 163	90.56 305	95.93 144	75.32 340	85.34 236	94.26 172	82.58 90	98.48 116	90.30 110	96.78 100	94.88 214

casdiffmvs		92.51 79	92.43 79	92.74 105	94.41 190	81.98 165	94.54 153	96.23 118	89.57 51	91.96 99	96.17 91	82.58 90	98.01 167	90.95 101	95.45 125	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	96.07 104	85.83 61	94.89 130	96.99 48	89.02 71	89.56 137	97.37 35	82.51 92	99.38 31	92.20 70	98.30 58	97.57 98
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	85.77 159	92.47 88	97.13 48	82.38 93	99.07 53	90.51 108	98.40 55	97.92 80

baseline		92.39 82	92.29 81	92.69 110	94.46 186	81.77 170	94.14 180	96.27 113	89.22 61	91.88 102	96.00 96	82.35 94	97.99 169	91.05 96	95.27 131	98.30 47

sasdasda		93.27 61	92.75 71	94.85 25	95.70 122	87.66 12	96.33 41	96.41 100	90.00 37	94.09 44	94.60 158	82.33 95	98.62 105	92.40 61	92.86 178	98.27 52

canonicalmvs		93.27 61	92.75 71	94.85 25	95.70 122	87.66 12	96.33 41	96.41 100	90.00 37	94.09 44	94.60 158	82.33 95	98.62 105	92.40 61	92.86 178	98.27 52

fmvsm_s_conf0.1_n_a		93.19 65	93.26 58	92.97 92	92.49 256	83.62 111	96.02 69	95.72 164	86.78 134	96.04 22	98.19 1	82.30 97	98.43 129	96.38 13	95.42 126	96.86 135

DP-MVS Recon		91.95 85	91.28 92	93.96 57	98.33 27	85.92 57	94.66 147	96.66 85	82.69 234	90.03 134	95.82 105	82.30 97	99.03 58	84.57 175	96.48 108	96.91 132

PAPR		90.02 125	89.27 136	92.29 130	95.78 118	80.95 193	92.68 249	96.22 119	81.91 250	86.66 192	93.75 195	82.23 99	98.44 127	79.40 263	94.79 137	97.48 101

MVS_Test		91.31 97	91.11 95	91.93 143	94.37 191	80.14 213	93.46 218	95.80 156	86.46 142	91.35 116	93.77 193	82.21 100	98.09 160	87.57 137	94.95 135	97.55 100

nrg030		91.08 102	90.39 105	93.17 78	93.07 240	86.91 22	96.41 39	96.26 114	88.30 92	88.37 156	94.85 146	82.19 101	97.64 191	91.09 95	82.95 299	94.96 209

MGCFI-Net		93.03 68	92.63 75	94.23 53	95.62 128	85.92 57	96.08 61	96.33 107	89.86 41	93.89 51	94.66 155	82.11 102	98.50 114	92.33 67	92.82 181	98.27 52

UniMVSNet (Re)		89.80 134	89.07 138	92.01 135	93.60 226	84.52 85	94.78 138	97.47 11	89.26 60	86.44 198	92.32 237	82.10 103	97.39 221	84.81 172	80.84 332	94.12 249

testdata				90.49 206	96.40 90	77.89 271		95.37 193	72.51 368	93.63 55	96.69 66	82.08 104	97.65 188	83.08 193	97.39 85	95.94 172

PAPM_NR		91.22 99	90.78 103	92.52 118	97.60 56	81.46 178	94.37 169	96.24 117	86.39 144	87.41 174	94.80 149	82.06 105	98.48 116	82.80 201	95.37 127	97.61 95

MG-MVS		91.77 88	91.70 88	92.00 138	97.08 71	80.03 220	93.60 213	95.18 201	87.85 110	90.89 120	96.47 80	82.06 105	98.36 132	85.07 167	97.04 91	97.62 94

CANet		93.54 51	93.20 61	94.55 43	95.65 125	85.73 65	94.94 127	96.69 84	91.89 8	90.69 122	95.88 102	81.99 107	99.54 20	93.14 48	97.95 72	98.39 39

MVSMamba_pp		92.75 75	92.66 73	93.02 88	95.09 150	82.85 139	94.72 143	96.46 96	86.35 145	93.33 61	94.96 139	81.98 108	98.55 113	92.35 64	98.70 34	97.67 92

iter_conf05_11		92.98 70	92.96 66	93.03 86	95.91 113	82.49 152	96.06 65	96.37 104	86.94 129	94.09 44	95.16 132	81.94 109	98.67 99	91.65 89	98.56 49	97.95 76

FC-MVSNet-test		90.27 118	90.18 110	90.53 202	93.71 221	79.85 227	95.77 82	97.59 3	89.31 58	86.27 202	94.67 154	81.93 110	97.01 248	84.26 179	88.09 251	94.71 221

FIs		90.51 116	90.35 106	90.99 190	93.99 210	80.98 191	95.73 83	97.54 4	89.15 64	86.72 191	94.68 153	81.83 111	97.24 232	85.18 166	88.31 248	94.76 220

ACMMP		93.24 63	92.88 69	94.30 51	98.09 38	85.33 70	96.86 27	97.45 14	88.33 90	90.15 132	97.03 53	81.44 112	99.51 24	90.85 104	95.74 116	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 93	91.11 95	93.01 89	94.35 195	83.39 119	94.60 149	95.10 205	87.10 124	90.57 124	93.10 214	81.43 113	98.07 163	89.29 117	94.48 147	97.59 97

MVS_111021_LR		92.47 80	92.29 81	92.98 91	95.99 110	84.43 91	93.08 236	96.09 131	88.20 97	91.12 118	95.72 111	81.33 114	97.76 180	91.74 86	97.37 86	96.75 139

mvs_anonymous		89.37 150	89.32 133	89.51 253	93.47 229	74.22 322	91.65 282	94.83 223	82.91 229	85.45 225	93.79 191	81.23 115	96.36 288	86.47 153	94.09 152	97.94 77

PVSNet_BlendedMVS		89.98 126	89.70 121	90.82 195	96.12 98	81.25 183	93.92 200	96.83 66	83.49 213	89.10 144	92.26 240	81.04 116	98.85 86	86.72 151	87.86 255	92.35 324

PVSNet_Blended		90.73 108	90.32 107	91.98 139	96.12 98	81.25 183	92.55 254	96.83 66	82.04 246	89.10 144	92.56 230	81.04 116	98.85 86	86.72 151	95.91 114	95.84 177

alignmvs		93.08 67	92.50 78	94.81 32	95.62 128	87.61 14	95.99 71	96.07 133	89.77 47	94.12 43	94.87 143	80.56 118	98.66 100	92.42 60	93.10 174	98.15 63

API-MVS		90.66 111	90.07 113	92.45 121	96.36 92	84.57 82	96.06 65	95.22 200	82.39 237	89.13 143	94.27 171	80.32 119	98.46 121	80.16 251	96.71 102	94.33 242

PVSNet_Blended_VisFu		91.38 95	90.91 100	92.80 101	96.39 91	83.17 124	94.87 132	96.66 85	83.29 219	89.27 142	94.46 163	80.29 120	99.17 47	87.57 137	95.37 127	96.05 170

test222					96.55 85	81.70 171	92.22 266	95.01 208	68.36 382	90.20 129	96.14 92	80.26 121			97.80 77	96.05 170

diffmvs		91.37 96	91.23 93	91.77 156	93.09 239	80.27 209	92.36 259	95.52 180	87.03 126	91.40 115	94.93 140	80.08 122	97.44 209	92.13 74	94.56 144	97.61 95
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												80.02 123

IterMVS-LS		88.36 177	87.91 171	89.70 244	93.80 217	78.29 262	93.73 207	95.08 207	85.73 160	84.75 246	91.90 256	79.88 124	96.92 254	83.83 185	82.51 305	93.89 259
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		89.10 154	88.86 146	89.80 240	91.84 278	78.30 261	93.70 210	95.01 208	85.73 160	87.15 178	95.28 124	79.87 125	97.21 235	83.81 186	87.36 263	93.88 261

TAPA-MVS	84.62 6	88.16 182	87.01 192	91.62 160	96.64 80	80.65 200	94.39 165	96.21 122	76.38 328	86.19 205	95.44 118	79.75 126	98.08 162	62.75 373	95.29 129	96.13 162
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Fast-Effi-MVS+		89.41 146	88.64 149	91.71 158	94.74 168	80.81 197	93.54 214	95.10 205	83.11 223	86.82 190	90.67 295	79.74 127	97.75 183	80.51 246	93.55 161	96.57 147

pcd_1.5k_mvsjas		6.64 382	8.86 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	79.70 128	0.00 415	0.00 414	0.00 413	0.00 411

PS-MVSNAJss		89.97 127	89.62 123	91.02 187	91.90 276	80.85 196	95.26 109	95.98 140	86.26 148	86.21 204	94.29 168	79.70 128	97.65 188	88.87 123	88.10 249	94.57 227

PS-MVSNAJ		91.18 100	90.92 99	91.96 141	95.26 143	82.60 151	92.09 271	95.70 165	86.27 147	91.84 104	92.46 232	79.70 128	98.99 70	89.08 119	95.86 115	94.29 243

xiu_mvs_v2_base		91.13 101	90.89 101	91.86 149	94.97 156	82.42 155	92.24 265	95.64 172	86.11 155	91.74 109	93.14 212	79.67 131	98.89 81	89.06 120	95.46 124	94.28 244

WR-MVS_H		87.80 191	87.37 182	89.10 262	93.23 235	78.12 265	95.61 93	97.30 29	87.90 106	83.72 274	92.01 253	79.65 132	96.01 302	76.36 290	80.54 336	93.16 297

EPNet		91.79 87	91.02 98	94.10 54	90.10 339	85.25 71	96.03 68	92.05 302	92.83 3	87.39 177	95.78 107	79.39 133	99.01 63	88.13 130	97.48 83	98.05 70
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_ehance_all_eth		87.22 221	86.62 206	89.02 265	92.13 267	77.40 284	90.91 300	94.81 225	81.28 269	84.32 262	90.08 310	79.26 134	96.62 265	83.81 186	82.94 300	93.04 302

test_fmvsmconf0.01_n		93.19 65	93.02 64	93.71 67	89.25 351	84.42 93	96.06 65	96.29 109	89.06 66	94.68 36	98.13 3	79.22 135	98.98 74	97.22 5	97.24 87	97.74 90

miper_enhance_ethall		86.90 233	86.18 222	89.06 263	91.66 287	77.58 282	90.22 315	94.82 224	79.16 295	84.48 253	89.10 326	79.19 136	96.66 263	84.06 181	82.94 300	92.94 305

NR-MVSNet		88.58 173	87.47 180	91.93 143	93.04 243	84.16 97	94.77 139	96.25 116	89.05 67	80.04 326	93.29 206	79.02 137	97.05 246	81.71 227	80.05 342	94.59 225

TAMVS		89.21 152	88.29 162	91.96 141	93.71 221	82.62 150	93.30 226	94.19 247	82.22 241	87.78 168	93.94 183	78.83 138	96.95 252	77.70 277	92.98 176	96.32 153

c3_l		87.14 226	86.50 211	89.04 264	92.20 264	77.26 285	91.22 294	94.70 231	82.01 247	84.34 261	90.43 299	78.81 139	96.61 268	83.70 188	81.09 325	93.25 292

1112_ss		88.42 174	87.33 183	91.72 157	94.92 160	80.98 191	92.97 241	94.54 234	78.16 315	83.82 272	93.88 188	78.78 140	97.91 175	79.45 259	89.41 227	96.26 157

CDS-MVSNet		89.45 144	88.51 153	92.29 130	93.62 225	83.61 113	93.01 239	94.68 232	81.95 248	87.82 167	93.24 208	78.69 141	96.99 249	80.34 248	93.23 172	96.28 156
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
WTY-MVS		89.60 138	88.92 142	91.67 159	95.47 134	81.15 187	92.38 258	94.78 227	83.11 223	89.06 146	94.32 166	78.67 142	96.61 268	81.57 228	90.89 204	97.24 109

CPTT-MVS		91.99 84	91.80 85	92.55 116	98.24 31	81.98 165	96.76 30	96.49 95	81.89 253	90.24 128	96.44 81	78.59 143	98.61 107	89.68 113	97.85 75	97.06 120

IS-MVSNet		91.43 94	91.09 97	92.46 120	95.87 116	81.38 181	96.95 19	93.69 266	89.72 49	89.50 139	95.98 98	78.57 144	97.77 179	83.02 195	96.50 107	98.22 59

OMC-MVS		91.23 98	90.62 104	93.08 83	96.27 94	84.07 98	93.52 215	95.93 144	86.95 128	89.51 138	96.13 93	78.50 145	98.35 134	85.84 161	92.90 177	96.83 137

PCF-MVS	84.11 10	87.74 193	86.08 228	92.70 109	94.02 205	84.43 91	89.27 332	95.87 152	73.62 358	84.43 256	94.33 165	78.48 146	98.86 84	70.27 331	94.45 148	94.81 218
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
LCM-MVSNet-Re		88.30 179	88.32 161	88.27 284	94.71 171	72.41 344	93.15 232	90.98 332	87.77 111	79.25 335	91.96 254	78.35 147	95.75 315	83.04 194	95.62 118	96.65 143

HY-MVS	83.01 12	89.03 159	87.94 170	92.29 130	94.86 164	82.77 140	92.08 272	94.49 235	81.52 265	86.93 182	92.79 225	78.32 148	98.23 143	79.93 253	90.55 207	95.88 175

GeoE		90.05 124	89.43 129	91.90 148	95.16 147	80.37 208	95.80 80	94.65 233	83.90 201	87.55 173	94.75 150	78.18 149	97.62 193	81.28 231	93.63 159	97.71 91

MVS		87.44 209	86.10 227	91.44 168	92.61 255	83.62 111	92.63 251	95.66 169	67.26 384	81.47 305	92.15 243	77.95 150	98.22 145	79.71 255	95.48 122	92.47 318

MVSFormer		91.68 92	91.30 91	92.80 101	93.86 214	83.88 103	95.96 73	95.90 149	84.66 189	91.76 107	94.91 141	77.92 151	97.30 224	89.64 114	97.11 88	97.24 109

lupinMVS		90.92 103	90.21 108	93.03 86	93.86 214	83.88 103	92.81 247	93.86 260	79.84 286	91.76 107	94.29 168	77.92 151	98.04 165	90.48 109	97.11 88	97.17 113

Test_1112_low_res		87.65 196	86.51 210	91.08 183	94.94 159	79.28 242	91.77 277	94.30 243	76.04 333	83.51 281	92.37 235	77.86 153	97.73 184	78.69 267	89.13 234	96.22 158

VNet		92.24 83	91.91 84	93.24 75	96.59 82	83.43 116	94.84 134	96.44 97	89.19 63	94.08 47	95.90 101	77.85 154	98.17 147	88.90 121	93.38 168	98.13 64

mvsany_test1		85.42 267	85.30 254	85.77 334	87.95 368	75.41 310	87.61 358	80.97 392	76.82 325	88.68 150	95.83 104	77.44 155	90.82 380	85.90 159	86.51 270	91.08 353

DU-MVS		89.34 151	88.50 154	91.85 151	93.04 243	83.72 106	94.47 158	96.59 90	89.50 52	86.46 195	93.29 206	77.25 156	97.23 233	84.92 169	81.02 328	94.59 225

Baseline_NR-MVSNet		87.07 228	86.63 205	88.40 279	91.44 291	77.87 272	94.23 176	92.57 288	84.12 197	85.74 213	92.08 249	77.25 156	96.04 299	82.29 210	79.94 343	91.30 345

jason		90.80 105	90.10 112	92.90 96	93.04 243	83.53 114	93.08 236	94.15 249	80.22 280	91.41 114	94.91 141	76.87 158	97.93 174	90.28 111	96.90 95	97.24 109
jason: jason.
PAPM		86.68 241	85.39 250	90.53 202	93.05 242	79.33 241	89.79 323	94.77 228	78.82 301	81.95 301	93.24 208	76.81 159	97.30 224	66.94 355	93.16 173	94.95 212

Vis-MVSNet (Re-imp)		89.59 139	89.44 128	90.03 227	95.74 119	75.85 305	95.61 93	90.80 338	87.66 116	87.83 166	95.40 121	76.79 160	96.46 281	78.37 268	96.73 101	97.80 87

baseline1		88.10 183	87.28 185	90.57 200	94.96 157	80.07 216	94.27 172	91.29 325	86.74 135	87.41 174	94.00 180	76.77 161	96.20 294	80.77 240	79.31 350	95.44 191

114514_t		89.51 141	88.50 154	92.54 117	98.11 36	81.99 164	95.16 116	96.36 105	70.19 379	85.81 210	95.25 126	76.70 162	98.63 104	82.07 216	96.86 98	97.00 126

PLC	84.53 7	89.06 158	88.03 167	92.15 133	97.27 68	82.69 147	94.29 171	95.44 187	79.71 288	84.01 269	94.18 174	76.68 163	98.75 93	77.28 281	93.41 167	95.02 205
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TranMVSNet+NR-MVSNet		88.84 163	87.95 169	91.49 165	92.68 254	83.01 134	94.92 129	96.31 108	89.88 40	85.53 219	93.85 190	76.63 164	96.96 251	81.91 220	79.87 345	94.50 234

MAR-MVS		90.30 117	89.37 131	93.07 85	96.61 81	84.48 87	95.68 86	95.67 167	82.36 239	87.85 165	92.85 219	76.63 164	98.80 90	80.01 252	96.68 103	95.91 173
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		88.38 175	87.67 175	90.52 204	93.30 234	80.18 211	93.26 229	95.96 143	88.57 85	85.47 224	92.81 223	76.12 166	96.91 255	81.24 232	82.29 308	94.47 239

v8		87.50 208	86.71 200	89.89 234	91.37 296	79.40 235	94.50 154	95.38 191	84.81 184	83.60 279	91.33 271	76.05 167	97.42 211	82.84 199	80.51 339	92.84 309

v148		87.04 229	86.32 217	89.21 258	90.94 315	77.26 285	93.71 209	94.43 237	84.84 183	84.36 260	90.80 291	76.04 168	97.05 246	82.12 213	79.60 347	93.31 289

eth_miper_zixun_eth		86.50 248	85.77 241	88.68 274	91.94 273	75.81 306	90.47 307	94.89 217	82.05 244	84.05 267	90.46 298	75.96 169	96.77 259	82.76 202	79.36 349	93.46 286

3Dnovator+	87.14 4	92.42 81	91.37 90	95.55 7	95.63 127	88.73 6	97.07 18	96.77 74	90.84 16	84.02 268	96.62 74	75.95 170	99.34 34	87.77 134	97.68 81	98.59 24

h-mvs33		90.80 105	90.15 111	92.75 104	96.01 106	82.66 148	95.43 98	95.53 179	89.80 43	93.08 67	95.64 113	75.77 171	99.00 68	92.07 75	78.05 354	96.60 144

hse-mvs2		89.88 133	89.34 132	91.51 164	94.83 166	81.12 188	93.94 198	93.91 259	89.80 43	93.08 67	93.60 197	75.77 171	97.66 187	92.07 75	77.07 361	95.74 182

BH-untuned		88.60 171	88.13 166	90.01 230	95.24 144	78.50 255	93.29 227	94.15 249	84.75 186	84.46 254	93.40 200	75.76 173	97.40 218	77.59 278	94.52 146	94.12 249

DIV-MVS_self_test		86.53 246	85.78 239	88.75 271	92.02 272	76.45 297	90.74 302	94.30 243	81.83 256	83.34 285	90.82 290	75.75 174	96.57 271	81.73 226	81.52 320	93.24 293

BH-w/o		87.57 204	87.05 190	89.12 261	94.90 162	77.90 270	92.41 256	93.51 268	82.89 230	83.70 275	91.34 270	75.75 174	97.07 244	75.49 297	93.49 164	92.39 322

cl____		86.52 247	85.78 239	88.75 271	92.03 271	76.46 296	90.74 302	94.30 243	81.83 256	83.34 285	90.78 292	75.74 176	96.57 271	81.74 225	81.54 319	93.22 294

cdsmvs_eth3d_5k		22.14 377	29.52 380	0.00 396	0.00 419	0.00 421	0.00 407	95.76 159	0.00 414	0.00 415	94.29 168	75.66 177	0.00 415	0.00 414	0.00 413	0.00 411

CNLPA		89.07 157	87.98 168	92.34 126	96.87 74	84.78 78	94.08 186	93.24 271	81.41 266	84.46 254	95.13 135	75.57 178	96.62 265	77.21 282	93.84 157	95.61 189

CHOSEN 1792x2688		88.84 163	87.69 174	92.30 129	96.14 97	81.42 180	90.01 320	95.86 153	74.52 349	87.41 174	93.94 183	75.46 179	98.36 132	80.36 247	95.53 119	97.12 118

CP-MVSNet		87.63 199	87.26 187	88.74 273	93.12 238	76.59 295	95.29 106	96.58 91	88.43 88	83.49 282	92.98 217	75.28 180	95.83 310	78.97 265	81.15 324	93.79 267

v10		87.25 218	86.38 213	89.85 235	91.19 302	79.50 232	94.48 155	95.45 185	83.79 205	83.62 278	91.19 276	75.13 181	97.42 211	81.94 219	80.60 334	92.63 314

Vis-MVSNet		91.75 89	91.23 93	93.29 73	95.32 138	83.78 105	96.14 57	95.98 140	89.89 39	90.45 125	96.58 76	75.09 182	98.31 140	84.75 173	96.90 95	97.78 89
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
sss		88.93 162	88.26 164	90.94 193	94.05 204	80.78 198	91.71 279	95.38 191	81.55 264	88.63 151	93.91 187	75.04 183	95.47 327	82.47 205	91.61 192	96.57 147

v1144		87.61 202	86.79 198	90.06 226	91.01 310	79.34 238	93.95 197	95.42 190	83.36 218	85.66 215	91.31 274	74.98 184	97.42 211	83.37 190	82.06 310	93.42 287

miper_lstm_enhance		85.27 272	84.59 270	87.31 305	91.28 300	74.63 317	87.69 355	94.09 253	81.20 273	81.36 308	89.85 316	74.97 185	94.30 342	81.03 236	79.84 346	93.01 303

test_yl		90.69 109	90.02 117	92.71 107	95.72 120	82.41 157	94.11 182	95.12 203	85.63 163	91.49 112	94.70 151	74.75 186	98.42 130	86.13 156	92.53 185	97.31 105

DCV-MVSNet		90.69 109	90.02 117	92.71 107	95.72 120	82.41 157	94.11 182	95.12 203	85.63 163	91.49 112	94.70 151	74.75 186	98.42 130	86.13 156	92.53 185	97.31 105

V42		87.68 194	86.86 194	90.15 221	90.58 330	80.14 213	94.24 175	95.28 196	83.66 207	85.67 214	91.33 271	74.73 188	97.41 216	84.43 178	81.83 314	92.89 307

FA-MVS(test-final)		89.66 136	88.91 143	91.93 143	94.57 180	80.27 209	91.36 287	94.74 229	84.87 181	89.82 135	92.61 229	74.72 189	98.47 120	83.97 183	93.53 162	97.04 122

XVG-OURS-SEG-HR		89.95 129	89.45 127	91.47 167	94.00 209	81.21 186	91.87 275	96.06 135	85.78 158	88.55 152	95.73 110	74.67 190	97.27 228	88.71 124	89.64 225	95.91 173

v2v482		87.84 189	87.06 189	90.17 219	90.99 311	79.23 245	94.00 195	95.13 202	84.87 181	85.53 219	92.07 251	74.45 191	97.45 206	84.71 174	81.75 316	93.85 265

CLD-MVS		89.47 143	88.90 144	91.18 178	94.22 198	82.07 162	92.13 269	96.09 131	87.90 106	85.37 234	92.45 233	74.38 192	97.56 196	87.15 144	90.43 209	93.93 258
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XXY-MVS		87.65 196	86.85 195	90.03 227	92.14 266	80.60 203	93.76 206	95.23 198	82.94 228	84.60 249	94.02 178	74.27 193	95.49 326	81.04 234	83.68 292	94.01 257

HQP_MVS		90.60 115	90.19 109	91.82 152	94.70 172	82.73 144	95.85 77	96.22 119	90.81 17	86.91 184	94.86 144	74.23 194	98.12 150	88.15 128	89.99 214	94.63 222

plane_prior6					94.52 182	82.75 141						74.23 194

v144192		87.19 224	86.35 215	89.74 241	90.64 328	78.24 263	93.92 200	95.43 188	81.93 249	85.51 221	91.05 284	74.21 196	97.45 206	82.86 198	81.56 318	93.53 281

VPA-MVSNet		89.62 137	88.96 140	91.60 161	93.86 214	82.89 138	95.46 97	97.33 25	87.91 105	88.43 155	93.31 204	74.17 197	97.40 218	87.32 142	82.86 304	94.52 230

ab-mvs		89.41 146	88.35 158	92.60 113	95.15 149	82.65 149	92.20 267	95.60 174	83.97 200	88.55 152	93.70 196	74.16 198	98.21 146	82.46 206	89.37 228	96.94 129

1314		87.51 206	86.57 208	90.34 216	92.42 260	79.74 229	92.63 251	95.35 195	78.35 310	80.14 323	91.62 265	74.05 199	97.15 237	81.05 233	93.53 162	94.12 249

test_djsdf		89.03 159	88.64 149	90.21 218	90.74 325	79.28 242	95.96 73	95.90 149	84.66 189	85.33 237	92.94 218	74.02 200	97.30 224	89.64 114	88.53 241	94.05 255

cl22		86.78 236	85.98 232	89.18 260	92.34 261	77.62 281	90.84 301	94.13 251	81.33 268	83.97 270	90.15 307	73.96 201	96.60 270	84.19 180	82.94 300	93.33 288

AdaColmap		89.89 132	89.07 138	92.37 125	97.41 62	83.03 132	94.42 162	95.92 146	82.81 231	86.34 201	94.65 156	73.89 202	99.02 61	80.69 242	95.51 120	95.05 204

HyFIR lowres test		88.09 184	86.81 196	91.93 143	96.00 107	80.63 201	90.01 320	95.79 157	73.42 360	87.68 170	92.10 248	73.86 203	97.96 171	80.75 241	91.70 191	97.19 112

HQP2-MVS												73.83 204

HQP-MVS		89.80 134	89.28 135	91.34 172	94.17 199	81.56 172	94.39 165	96.04 136	88.81 74	85.43 228	93.97 182	73.83 204	97.96 171	87.11 146	89.77 223	94.50 234

3Dnovator	86.66 5	91.73 90	90.82 102	94.44 45	94.59 177	86.37 41	97.18 12	97.02 47	89.20 62	84.31 264	96.66 69	73.74 206	99.17 47	86.74 149	97.96 71	97.79 88

EPNet_dtu		86.49 250	85.94 235	88.14 289	90.24 337	72.82 334	94.11 182	92.20 298	86.66 138	79.42 334	92.36 236	73.52 207	95.81 312	71.26 323	93.66 158	95.80 180
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TransMVSNet (Re)		84.43 285	83.06 292	88.54 277	91.72 283	78.44 256	95.18 114	92.82 281	82.73 233	79.67 331	92.12 245	73.49 208	95.96 304	71.10 328	68.73 383	91.21 347

Effi-MVS+-dtu		88.65 169	88.35 158	89.54 250	93.33 233	76.39 298	94.47 158	94.36 241	87.70 113	85.43 228	89.56 321	73.45 209	97.26 230	85.57 164	91.28 196	94.97 206

baseline2		86.50 248	85.39 250	89.84 236	91.12 307	76.70 293	91.88 274	88.58 364	82.35 240	79.95 327	90.95 286	73.42 210	97.63 192	80.27 250	89.95 217	95.19 200

PEN-MVS		86.80 235	86.27 220	88.40 279	92.32 262	75.71 307	95.18 114	96.38 103	87.97 103	82.82 291	93.15 211	73.39 211	95.92 305	76.15 294	79.03 352	93.59 279

v1192		87.25 218	86.33 216	90.00 231	90.76 324	79.04 246	93.80 204	95.48 181	82.57 235	85.48 223	91.18 278	73.38 212	97.42 211	82.30 209	82.06 310	93.53 281

QAPM		89.51 141	88.15 165	93.59 70	94.92 160	84.58 81	96.82 29	96.70 83	78.43 309	83.41 283	96.19 90	73.18 213	99.30 40	77.11 284	96.54 105	96.89 133

mvsmamba		89.96 128	89.50 126	91.33 173	92.90 250	81.82 168	96.68 33	92.37 291	89.03 69	87.00 180	94.85 146	73.05 214	97.65 188	91.03 97	88.63 239	94.51 232

tpmrst		85.35 269	84.99 259	86.43 326	90.88 320	67.88 373	88.71 341	91.43 322	80.13 282	86.08 207	88.80 333	73.05 214	96.02 301	82.48 204	83.40 298	95.40 193

PS-CasMVS		87.32 215	86.88 193	88.63 276	92.99 246	76.33 300	95.33 101	96.61 89	88.22 96	83.30 287	93.07 215	73.03 216	95.79 314	78.36 269	81.00 330	93.75 274

DTE-MVSNet		86.11 255	85.48 248	87.98 292	91.65 288	74.92 314	94.93 128	95.75 160	87.36 120	82.26 296	93.04 216	72.85 217	95.82 311	74.04 310	77.46 358	93.20 295

MVSTER		88.84 163	88.29 162	90.51 205	92.95 248	80.44 206	93.73 207	95.01 208	84.66 189	87.15 178	93.12 213	72.79 218	97.21 235	87.86 133	87.36 263	93.87 262

v1921920		86.97 231	86.06 229	89.69 245	90.53 333	78.11 266	93.80 204	95.43 188	81.90 251	85.33 237	91.05 284	72.66 219	97.41 216	82.05 217	81.80 315	93.53 281

DP-MVS		87.25 218	85.36 252	92.90 96	97.65 55	83.24 121	94.81 136	92.00 304	74.99 344	81.92 302	95.00 138	72.66 219	99.05 55	66.92 357	92.33 188	96.40 151

v7n		86.81 234	85.76 242	89.95 232	90.72 326	79.25 244	95.07 120	95.92 146	84.45 192	82.29 295	90.86 287	72.60 221	97.53 198	79.42 262	80.52 338	93.08 301

OPM-MVS		90.12 122	89.56 125	91.82 152	93.14 237	83.90 102	94.16 179	95.74 161	88.96 73	87.86 164	95.43 120	72.48 222	97.91 175	88.10 132	90.18 213	93.65 278
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
LS3D		87.89 188	86.32 217	92.59 114	96.07 104	82.92 137	95.23 110	94.92 216	75.66 335	82.89 290	95.98 98	72.48 222	99.21 45	68.43 345	95.23 132	95.64 186

pm-mvs1		86.61 242	85.54 246	89.82 237	91.44 291	80.18 211	95.28 108	94.85 221	83.84 203	81.66 303	92.62 228	72.45 224	96.48 278	79.67 256	78.06 353	92.82 310

PMMVS		85.71 263	84.96 261	87.95 293	88.90 355	77.09 287	88.68 342	90.06 350	72.32 370	86.47 194	90.76 293	72.15 225	94.40 339	81.78 224	93.49 164	92.36 323

SDMVSNet		90.19 120	89.61 124	91.93 143	96.00 107	83.09 130	92.89 244	95.98 140	88.73 78	86.85 188	95.20 130	72.09 226	97.08 242	88.90 121	89.85 220	95.63 187

PatchmatchNet		85.85 260	84.70 267	89.29 257	91.76 282	75.54 308	88.49 344	91.30 324	81.63 262	85.05 241	88.70 335	71.71 227	96.24 293	74.61 308	89.05 235	96.08 166
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												71.70 228				96.12 163

patchmatchnet-post											83.76 375	71.53 229	96.48 278

v1240		86.78 236	85.85 237	89.56 249	90.45 334	77.79 276	93.61 212	95.37 193	81.65 260	85.43 228	91.15 280	71.50 230	97.43 210	81.47 230	82.05 312	93.47 285

anonymousdsp		87.84 189	87.09 188	90.12 223	89.13 352	80.54 204	94.67 146	95.55 176	82.05 244	83.82 272	92.12 245	71.47 231	97.15 237	87.15 144	87.80 258	92.67 312

Patchmatch-test		81.37 318	79.30 326	87.58 299	90.92 317	74.16 324	80.99 391	87.68 371	70.52 378	76.63 353	88.81 331	71.21 232	92.76 364	60.01 381	86.93 269	95.83 178

F-COLMAP		87.95 187	86.80 197	91.40 169	96.35 93	80.88 195	94.73 141	95.45 185	79.65 289	82.04 300	94.61 157	71.13 233	98.50 114	76.24 293	91.05 202	94.80 219

pmmvs4		85.43 266	83.86 279	90.16 220	90.02 342	82.97 136	90.27 309	92.67 286	75.93 334	80.73 314	91.74 260	71.05 234	95.73 317	78.85 266	83.46 296	91.78 334

CR-MVSNet		85.35 269	83.76 280	90.12 223	90.58 330	79.34 238	85.24 374	91.96 308	78.27 312	85.55 217	87.87 348	71.03 235	95.61 319	73.96 312	89.36 229	95.40 193

Patchmtry		82.71 302	80.93 308	88.06 290	90.05 341	76.37 299	84.74 379	91.96 308	72.28 371	81.32 309	87.87 348	71.03 235	95.50 325	68.97 341	80.15 341	92.32 325

CL-MVSNet_self_test		81.74 311	80.53 309	85.36 338	85.96 377	72.45 343	90.25 311	93.07 275	81.24 271	79.85 330	87.29 354	70.93 237	92.52 365	66.95 354	69.23 379	91.11 351

RPMNet		83.95 292	81.53 303	91.21 176	90.58 330	79.34 238	85.24 374	96.76 75	71.44 374	85.55 217	82.97 381	70.87 238	98.91 80	61.01 377	89.36 229	95.40 193

Patchmatch-RL test		81.67 312	79.96 318	86.81 322	85.42 382	71.23 353	82.17 389	87.50 372	78.47 307	77.19 349	82.50 383	70.81 239	93.48 355	82.66 203	72.89 371	95.71 185

CostFormer		85.77 262	84.94 262	88.26 285	91.16 305	72.58 342	89.47 330	91.04 331	76.26 331	86.45 197	89.97 313	70.74 240	96.86 258	82.35 208	87.07 268	95.34 197

sam_mvs												70.60 241

xiu_mvs_v1_base_debu		90.64 112	90.05 114	92.40 122	93.97 211	84.46 88	93.32 222	95.46 182	85.17 172	92.25 90	94.03 175	70.59 242	98.57 110	90.97 98	94.67 139	94.18 245

xiu_mvs_v1_base		90.64 112	90.05 114	92.40 122	93.97 211	84.46 88	93.32 222	95.46 182	85.17 172	92.25 90	94.03 175	70.59 242	98.57 110	90.97 98	94.67 139	94.18 245

xiu_mvs_v1_base_debi		90.64 112	90.05 114	92.40 122	93.97 211	84.46 88	93.32 222	95.46 182	85.17 172	92.25 90	94.03 175	70.59 242	98.57 110	90.97 98	94.67 139	94.18 245

test_post											10.29 409	70.57 245	95.91 307

CANet_DTU		90.26 119	89.41 130	92.81 100	93.46 230	83.01 134	93.48 216	94.47 236	89.43 54	87.76 169	94.23 173	70.54 246	99.03 58	84.97 168	96.39 109	96.38 152

BH-RMVSNet		88.37 176	87.48 179	91.02 187	95.28 140	79.45 234	92.89 244	93.07 275	85.45 168	86.91 184	94.84 148	70.35 247	97.76 180	73.97 311	94.59 143	95.85 176

Fast-Effi-MVS+-dtu		87.44 209	86.72 199	89.63 248	92.04 270	77.68 280	94.03 191	93.94 255	85.81 157	82.42 294	91.32 273	70.33 248	97.06 245	80.33 249	90.23 212	94.14 248

MDTV_nov1_ep13_2view						55.91 403	87.62 357		73.32 361	84.59 250		70.33 248		74.65 307		95.50 190

ACMM	84.12 9	89.14 153	88.48 157	91.12 179	94.65 175	81.22 185	95.31 102	96.12 128	85.31 171	85.92 209	94.34 164	70.19 250	98.06 164	85.65 162	88.86 237	94.08 253
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ET-MVSNet_ETH3D		87.51 206	85.91 236	92.32 127	93.70 223	83.93 101	92.33 262	90.94 334	84.16 195	72.09 375	92.52 231	69.90 251	95.85 309	89.20 118	88.36 247	97.17 113

LPG-MVS_test		89.45 144	88.90 144	91.12 179	94.47 184	81.49 176	95.30 104	96.14 125	86.73 136	85.45 225	95.16 132	69.89 252	98.10 152	87.70 135	89.23 232	93.77 272

LGP-MVS_train				91.12 179	94.47 184	81.49 176		96.14 125	86.73 136	85.45 225	95.16 132	69.89 252	98.10 152	87.70 135	89.23 232	93.77 272

CHOSEN 280x420		85.15 274	83.99 277	88.65 275	92.47 257	78.40 258	79.68 396	92.76 282	74.90 346	81.41 307	89.59 319	69.85 254	95.51 323	79.92 254	95.29 129	92.03 330

LTVRE_ROB	82.13 13	86.26 254	84.90 263	90.34 216	94.44 188	81.50 174	92.31 264	94.89 217	83.03 225	79.63 332	92.67 226	69.69 255	97.79 178	71.20 324	86.26 272	91.72 335
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	88.74 167	87.29 184	93.08 83	92.70 253	85.39 69	96.57 36	96.43 98	78.74 304	80.85 313	96.07 94	69.64 256	99.01 63	78.01 275	96.65 104	94.83 217

MDTV_nov1_ep13			83.56 283		91.69 286	69.93 366	87.75 354	91.54 318	78.60 306	84.86 244	88.90 330	69.54 257	96.03 300	70.25 332	88.93 236

AUN-MVS		87.78 192	86.54 209	91.48 166	94.82 167	81.05 189	93.91 202	93.93 256	83.00 226	86.93 182	93.53 198	69.50 258	97.67 185	86.14 154	77.12 360	95.73 184

PatchT		82.68 303	81.27 305	86.89 320	90.09 340	70.94 359	84.06 381	90.15 347	74.91 345	85.63 216	83.57 376	69.37 259	94.87 336	65.19 362	88.50 243	94.84 216

VPNet		88.20 181	87.47 180	90.39 212	93.56 227	79.46 233	94.04 190	95.54 178	88.67 81	86.96 181	94.58 161	69.33 260	97.15 237	84.05 182	80.53 337	94.56 228

ACMP	84.23 8	89.01 161	88.35 158	90.99 190	94.73 169	81.27 182	95.07 120	95.89 151	86.48 140	83.67 276	94.30 167	69.33 260	97.99 169	87.10 148	88.55 240	93.72 276
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_post1							88.00 350				9.81 410	69.31 262	95.53 321	76.65 287

tpmvs		83.35 300	82.07 299	87.20 312	91.07 309	71.00 358	88.31 347	91.70 312	78.91 297	80.49 319	87.18 357	69.30 263	97.08 242	68.12 349	83.56 294	93.51 284

thres200		87.21 222	86.24 221	90.12 223	95.36 137	78.53 253	93.26 229	92.10 300	86.42 143	88.00 163	91.11 282	69.24 264	98.00 168	69.58 339	91.04 203	93.83 266

tfpn200view9		87.58 203	86.64 203	90.41 211	95.99 110	78.64 250	94.58 150	91.98 306	86.94 129	88.09 158	91.77 258	69.18 265	98.10 152	70.13 335	91.10 197	94.48 237

thres400		87.62 201	86.64 203	90.57 200	95.99 110	78.64 250	94.58 150	91.98 306	86.94 129	88.09 158	91.77 258	69.18 265	98.10 152	70.13 335	91.10 197	94.96 209

WB-MVSnew		83.77 295	83.28 286	85.26 341	91.48 290	71.03 356	91.89 273	87.98 367	78.91 297	84.78 245	90.22 303	69.11 267	94.02 346	64.70 366	90.44 208	90.71 355

tfpnnormal		84.72 282	83.23 288	89.20 259	92.79 252	80.05 218	94.48 155	95.81 155	82.38 238	81.08 311	91.21 275	69.01 268	96.95 252	61.69 375	80.59 335	90.58 360

thres100view900		87.63 199	86.71 200	90.38 214	96.12 98	78.55 252	95.03 123	91.58 316	87.15 122	88.06 161	92.29 239	68.91 269	98.10 152	70.13 335	91.10 197	94.48 237

thres600view7		87.65 196	86.67 202	90.59 199	96.08 103	78.72 248	94.88 131	91.58 316	87.06 125	88.08 160	92.30 238	68.91 269	98.10 152	70.05 338	91.10 197	94.96 209

PatchMatch-RL		86.77 239	85.54 246	90.47 210	95.88 114	82.71 146	90.54 306	92.31 294	79.82 287	84.32 262	91.57 269	68.77 271	96.39 285	73.16 316	93.48 166	92.32 325

XVG-OURS		89.40 148	88.70 148	91.52 163	94.06 203	81.46 178	91.27 291	96.07 133	86.14 152	88.89 148	95.77 108	68.73 272	97.26 230	87.39 140	89.96 216	95.83 178

TR-MVS		86.78 236	85.76 242	89.82 237	94.37 191	78.41 257	92.47 255	92.83 280	81.11 274	86.36 199	92.40 234	68.73 272	97.48 202	73.75 314	89.85 220	93.57 280

tpm		84.73 281	84.02 276	86.87 321	90.33 335	68.90 369	89.06 337	89.94 353	80.85 276	85.75 212	89.86 315	68.54 274	95.97 303	77.76 276	84.05 288	95.75 181

FMVSNet3		87.40 211	86.11 226	91.30 174	93.79 219	83.64 110	94.20 177	94.81 225	83.89 202	84.37 257	91.87 257	68.45 275	96.56 273	78.23 272	85.36 277	93.70 277

MVP-Stereo		85.97 257	84.86 264	89.32 256	90.92 317	82.19 160	92.11 270	94.19 247	78.76 303	78.77 340	91.63 264	68.38 276	96.56 273	75.01 304	93.95 154	89.20 370
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
tpm cat1		81.96 307	80.27 313	87.01 315	91.09 308	71.02 357	87.38 359	91.53 319	66.25 385	80.17 321	86.35 363	68.22 277	96.15 297	69.16 340	82.29 308	93.86 264

dmvs_testset		74.57 351	75.81 350	70.86 376	87.72 370	40.47 411	87.05 362	77.90 401	82.75 232	71.15 380	85.47 369	67.98 278	84.12 398	45.26 395	76.98 362	88.00 379

sd_testset		88.59 172	87.85 172	90.83 194	96.00 107	80.42 207	92.35 260	94.71 230	88.73 78	86.85 188	95.20 130	67.31 279	96.43 283	79.64 257	89.85 220	95.63 187

tpm2		84.08 289	82.94 293	87.48 303	91.39 295	71.27 352	89.23 334	90.37 343	71.95 372	84.64 248	89.33 323	67.30 280	96.55 275	75.17 301	87.09 267	94.63 222

test-LLR		85.87 259	85.41 249	87.25 308	90.95 313	71.67 350	89.55 326	89.88 356	83.41 215	84.54 251	87.95 345	67.25 281	95.11 332	81.82 222	93.37 169	94.97 206

test0.0.03 1		82.41 305	81.69 301	84.59 345	88.23 363	72.89 333	90.24 313	87.83 369	83.41 215	79.86 329	89.78 317	67.25 281	88.99 388	65.18 363	83.42 297	91.90 333

CVMVSNet		84.69 283	84.79 266	84.37 347	91.84 278	64.92 383	93.70 210	91.47 321	66.19 386	86.16 206	95.28 124	67.18 283	93.33 357	80.89 239	90.42 210	94.88 214

thisisatest0515		87.33 214	85.99 231	91.37 171	93.49 228	79.55 231	90.63 304	89.56 361	80.17 281	87.56 172	90.86 287	67.07 284	98.28 141	81.50 229	93.02 175	96.29 155

tttt0517		88.61 170	87.78 173	91.11 182	94.96 157	77.81 274	95.35 100	89.69 358	85.09 177	88.05 162	94.59 160	66.93 285	98.48 116	83.27 192	92.13 190	97.03 123

our_test_3		81.93 308	80.46 311	86.33 328	88.46 360	73.48 329	88.46 345	91.11 327	76.46 326	76.69 352	88.25 341	66.89 286	94.36 340	68.75 342	79.08 351	91.14 349

thisisatest0530		88.67 168	87.61 176	91.86 149	94.87 163	80.07 216	94.63 148	89.90 355	84.00 199	88.46 154	93.78 192	66.88 287	98.46 121	83.30 191	92.65 182	97.06 120

IterMVS-SCA-FT		85.45 265	84.53 271	88.18 288	91.71 284	76.87 290	90.19 316	92.65 287	85.40 169	81.44 306	90.54 296	66.79 288	95.00 335	81.04 234	81.05 326	92.66 313

SCA		86.32 253	85.18 256	89.73 243	92.15 265	76.60 294	91.12 295	91.69 313	83.53 212	85.50 222	88.81 331	66.79 288	96.48 278	76.65 287	90.35 211	96.12 163

D2MVS		85.90 258	85.09 258	88.35 281	90.79 322	77.42 283	91.83 276	95.70 165	80.77 277	80.08 325	90.02 311	66.74 290	96.37 286	81.88 221	87.97 253	91.26 346

IterMVS		84.88 278	83.98 278	87.60 298	91.44 291	76.03 302	90.18 317	92.41 290	83.24 221	81.06 312	90.42 300	66.60 291	94.28 343	79.46 258	80.98 331	92.48 317
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		87.26 216	85.98 232	91.08 183	94.01 206	83.10 127	95.14 117	94.94 211	83.57 209	84.37 257	91.64 261	66.59 292	96.34 289	78.23 272	85.36 277	93.79 267

test1		87.26 216	85.98 232	91.08 183	94.01 206	83.10 127	95.14 117	94.94 211	83.57 209	84.37 257	91.64 261	66.59 292	96.34 289	78.23 272	85.36 277	93.79 267

FMVSNet2		87.19 224	85.82 238	91.30 174	94.01 206	83.67 108	94.79 137	94.94 211	83.57 209	83.88 271	92.05 252	66.59 292	96.51 276	77.56 279	85.01 280	93.73 275

EPMVS		83.90 294	82.70 298	87.51 300	90.23 338	72.67 337	88.62 343	81.96 390	81.37 267	85.01 242	88.34 339	66.31 295	94.45 337	75.30 300	87.12 266	95.43 192

Syy-MVS		80.07 330	79.78 319	80.94 362	91.92 274	59.93 393	89.75 324	87.40 373	81.72 258	78.82 337	87.20 355	66.29 296	91.29 376	47.06 394	87.84 256	91.60 338

ppachtmachnet_test		81.84 309	80.07 317	87.15 313	88.46 360	74.43 321	89.04 338	92.16 299	75.33 339	77.75 345	88.99 328	66.20 297	95.37 328	65.12 364	77.60 356	91.65 336

MDA-MVSNet_test_wron		79.21 339	77.19 341	85.29 339	88.22 364	72.77 335	85.87 368	90.06 350	74.34 350	62.62 390	87.56 351	66.14 298	91.99 371	66.90 358	73.01 369	91.10 352

YYNet1		79.22 338	77.20 340	85.28 340	88.20 365	72.66 338	85.87 368	90.05 352	74.33 351	62.70 388	87.61 350	66.09 299	92.03 369	66.94 355	72.97 370	91.15 348

JIA-IIPM		81.04 321	78.98 333	87.25 308	88.64 356	73.48 329	81.75 390	89.61 360	73.19 362	82.05 299	73.71 393	66.07 300	95.87 308	71.18 326	84.60 283	92.41 321

MSDG		84.86 279	83.09 290	90.14 222	93.80 217	80.05 218	89.18 335	93.09 274	78.89 299	78.19 341	91.91 255	65.86 301	97.27 228	68.47 344	88.45 244	93.11 299

FE-MVS		87.40 211	86.02 230	91.57 162	94.56 181	79.69 230	90.27 309	93.72 265	80.57 278	88.80 149	91.62 265	65.32 302	98.59 109	74.97 305	94.33 151	96.44 150

jajsoiax		88.24 180	87.50 178	90.48 207	90.89 319	80.14 213	95.31 102	95.65 171	84.97 179	84.24 265	94.02 178	65.31 303	97.42 211	88.56 125	88.52 242	93.89 259

cascas		86.43 252	84.98 260	90.80 196	92.10 269	80.92 194	90.24 313	95.91 148	73.10 363	83.57 280	88.39 338	65.15 304	97.46 205	84.90 171	91.43 194	94.03 256

ADS-MVSNet2		81.66 313	79.71 322	87.50 301	91.35 297	74.19 323	83.33 384	88.48 365	72.90 365	82.24 297	85.77 367	64.98 305	93.20 360	64.57 367	83.74 290	95.12 202

ADS-MVSNet		81.56 315	79.78 319	86.90 319	91.35 297	71.82 347	83.33 384	89.16 363	72.90 365	82.24 297	85.77 367	64.98 305	93.76 351	64.57 367	83.74 290	95.12 202

pmmvs5		84.21 287	82.84 297	88.34 282	88.95 354	76.94 289	92.41 256	91.91 310	75.63 336	80.28 320	91.18 278	64.59 307	95.57 320	77.09 285	83.47 295	92.53 316

PVSNet	78.82 18	85.55 264	84.65 268	88.23 287	94.72 170	71.93 345	87.12 361	92.75 283	78.80 302	84.95 243	90.53 297	64.43 308	96.71 262	74.74 306	93.86 156	96.06 169

dmvs_re		84.20 288	83.22 289	87.14 314	91.83 280	77.81 274	90.04 319	90.19 346	84.70 188	81.49 304	89.17 325	64.37 309	91.13 378	71.58 322	85.65 276	92.46 319

UGNet		89.95 129	88.95 141	92.95 94	94.51 183	83.31 120	95.70 85	95.23 198	89.37 56	87.58 171	93.94 183	64.00 310	98.78 91	83.92 184	96.31 110	96.74 140
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		67.92 358	67.49 360	69.21 380	81.09 392	41.17 410	88.03 349	78.00 400	73.50 359	62.63 389	83.11 380	63.94 311	86.52 392	25.66 406	51.45 398	79.94 391

RPSCF		85.07 275	84.27 272	87.48 303	92.91 249	70.62 362	91.69 281	92.46 289	76.20 332	82.67 293	95.22 127	63.94 311	97.29 227	77.51 280	85.80 274	94.53 229

mvs_tets		88.06 186	87.28 185	90.38 214	90.94 315	79.88 225	95.22 111	95.66 169	85.10 176	84.21 266	93.94 183	63.53 313	97.40 218	88.50 126	88.40 246	93.87 262

SSC-MVS		67.06 359	66.56 361	68.56 382	80.54 393	40.06 412	87.77 353	77.37 403	72.38 369	61.75 391	82.66 382	63.37 314	86.45 393	24.48 407	48.69 401	79.16 393

test1111		89.10 154	88.64 149	90.48 207	95.53 133	74.97 313	96.08 61	84.89 382	88.13 100	90.16 131	96.65 70	63.29 315	98.10 152	86.14 154	96.90 95	98.39 39

Anonymous20231211		86.59 244	85.13 257	90.98 192	96.52 88	81.50 174	96.14 57	96.16 123	73.78 356	83.65 277	92.15 243	63.26 316	97.37 222	82.82 200	81.74 317	94.06 254

ECVR-MVS		89.09 156	88.53 152	90.77 197	95.62 128	75.89 304	96.16 53	84.22 384	87.89 108	90.20 129	96.65 70	63.19 317	98.10 152	85.90 159	96.94 93	98.33 43

dp		81.47 317	80.23 314	85.17 342	89.92 344	65.49 380	86.74 363	90.10 349	76.30 330	81.10 310	87.12 358	62.81 318	95.92 305	68.13 348	79.88 344	94.09 252

LFMVS		90.08 123	89.13 137	92.95 94	96.71 77	82.32 159	96.08 61	89.91 354	86.79 133	92.15 94	96.81 63	62.60 319	98.34 135	87.18 143	93.90 155	98.19 60

Anonymous20231206		81.03 322	79.77 321	84.82 344	87.85 369	70.26 364	91.42 286	92.08 301	73.67 357	77.75 345	89.25 324	62.43 320	93.08 361	61.50 376	82.00 313	91.12 350

VDD-MVS		90.74 107	89.92 119	93.20 77	96.27 94	83.02 133	95.73 83	93.86 260	88.42 89	92.53 85	96.84 60	62.09 321	98.64 102	90.95 101	92.62 183	97.93 79

MS-PatchMatch		85.05 276	84.16 273	87.73 296	91.42 294	78.51 254	91.25 292	93.53 267	77.50 318	80.15 322	91.58 267	61.99 322	95.51 323	75.69 296	94.35 150	89.16 371

OurMVSNet-221017-0		85.35 269	84.64 269	87.49 302	90.77 323	72.59 341	94.01 193	94.40 239	84.72 187	79.62 333	93.17 210	61.91 323	96.72 260	81.99 218	81.16 322	93.16 297

test_vis1_n_1920		89.39 149	89.84 120	88.04 291	92.97 247	72.64 339	94.71 144	96.03 138	86.18 150	91.94 101	96.56 78	61.63 324	95.74 316	93.42 43	95.11 133	95.74 182

test20.03		79.95 332	79.08 331	82.55 357	85.79 379	67.74 374	91.09 296	91.08 328	81.23 272	74.48 367	89.96 314	61.63 324	90.15 382	60.08 379	76.38 363	89.76 363

DSMNet-mixed		76.94 347	76.29 346	78.89 366	83.10 389	56.11 402	87.78 352	79.77 394	60.65 392	75.64 359	88.71 334	61.56 326	88.34 389	60.07 380	89.29 231	92.21 328

Anonymous20240529		88.09 184	86.59 207	92.58 115	96.53 87	81.92 167	95.99 71	95.84 154	74.11 353	89.06 146	95.21 129	61.44 327	98.81 89	83.67 189	87.47 260	97.01 125

IB-MVS	80.51 15	85.24 273	83.26 287	91.19 177	92.13 267	79.86 226	91.75 278	91.29 325	83.28 220	80.66 316	88.49 337	61.28 328	98.46 121	80.99 237	79.46 348	95.25 199
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		86.61 242	85.27 255	90.66 198	91.33 299	78.71 249	90.40 308	93.81 263	85.34 170	85.12 239	89.57 320	61.25 329	97.11 241	80.99 237	89.59 226	96.15 160

N_pmnet		68.89 357	68.44 359	70.23 377	89.07 353	28.79 416	88.06 348	19.50 416	69.47 380	71.86 377	84.93 370	61.24 330	91.75 373	54.70 389	77.15 359	90.15 361

EU-MVSNet		81.32 319	80.95 307	82.42 359	88.50 359	63.67 387	93.32 222	91.33 323	64.02 389	80.57 318	92.83 221	61.21 331	92.27 368	76.34 291	80.38 340	91.32 344

testing91		87.11 227	86.18 222	89.92 233	94.43 189	75.38 312	91.53 284	92.27 296	86.48 140	86.50 193	90.24 302	61.19 332	97.53 198	82.10 214	90.88 205	96.84 136

test_cas_vis1_n_1920		88.83 166	88.85 147	88.78 269	91.15 306	76.72 292	93.85 203	94.93 215	83.23 222	92.81 76	96.00 96	61.17 333	94.45 337	91.67 88	94.84 136	95.17 201

VDDNet		89.56 140	88.49 156	92.76 103	95.07 151	82.09 161	96.30 43	93.19 273	81.05 275	91.88 102	96.86 59	61.16 334	98.33 137	88.43 127	92.49 187	97.84 85

PVSNet_0	73.20 20	77.22 346	74.83 352	84.37 347	90.70 327	71.10 355	83.09 386	89.67 359	72.81 367	73.93 369	83.13 378	60.79 335	93.70 353	68.54 343	50.84 399	88.30 378

SixPastTwentyTwo		83.91 293	82.90 295	86.92 318	90.99 311	70.67 361	93.48 216	91.99 305	85.54 166	77.62 347	92.11 247	60.59 336	96.87 257	76.05 295	77.75 355	93.20 295

gg-mvs-nofinetune		81.77 310	79.37 325	88.99 266	90.85 321	77.73 279	86.29 366	79.63 395	74.88 347	83.19 288	69.05 397	60.34 337	96.11 298	75.46 298	94.64 142	93.11 299

MDA-MVSNet-bldmvs		78.85 340	76.31 345	86.46 325	89.76 346	73.88 325	88.79 340	90.42 342	79.16 295	59.18 393	88.33 340	60.20 338	94.04 345	62.00 374	68.96 381	91.48 342

pmmvs6		83.42 298	81.60 302	88.87 268	88.01 366	77.87 272	94.96 126	94.24 246	74.67 348	78.80 339	91.09 283	60.17 339	96.49 277	77.06 286	75.40 367	92.23 327

ACMH	80.38 17	85.36 268	83.68 281	90.39 212	94.45 187	80.63 201	94.73 141	94.85 221	82.09 243	77.24 348	92.65 227	60.01 340	97.58 194	72.25 320	84.87 281	92.96 304
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GG-mvs-BLEND				87.94 294	89.73 348	77.91 269	87.80 351	78.23 399		80.58 317	83.86 374	59.88 341	95.33 329	71.20 324	92.22 189	90.60 359

UniMVSNet_ETH3D		87.53 205	86.37 214	91.00 189	92.44 259	78.96 247	94.74 140	95.61 173	84.07 198	85.36 235	94.52 162	59.78 342	97.34 223	82.93 196	87.88 254	96.71 141

pmmvs-eth3d		80.97 323	78.72 335	87.74 295	84.99 384	79.97 224	90.11 318	91.65 314	75.36 338	73.51 370	86.03 364	59.45 343	93.96 349	75.17 301	72.21 372	89.29 369

testing99		86.72 240	85.73 245	89.69 245	94.23 197	74.91 315	91.35 288	90.97 333	86.14 152	86.36 199	90.22 303	59.41 344	97.48 202	82.24 211	90.66 206	96.69 142

test_0402		81.30 320	79.17 330	87.67 297	93.19 236	78.17 264	92.98 240	91.71 311	75.25 341	76.02 358	90.31 301	59.23 345	96.37 286	50.22 392	83.63 293	88.47 377

KD-MVS_self_test		80.20 329	79.24 327	83.07 354	85.64 381	65.29 381	91.01 298	93.93 256	78.71 305	76.32 354	86.40 362	59.20 346	92.93 363	72.59 318	69.35 378	91.00 354

FMVSNet1		85.85 260	84.11 274	91.08 183	92.81 251	83.10 127	95.14 117	94.94 211	81.64 261	82.68 292	91.64 261	59.01 347	96.34 289	75.37 299	83.78 289	93.79 267

testing11		86.44 251	85.35 253	89.69 245	94.29 196	75.40 311	91.30 289	90.53 341	84.76 185	85.06 240	90.13 308	58.95 348	97.45 206	82.08 215	91.09 201	96.21 159

COLMAP_ROB	80.39 16	83.96 291	82.04 300	89.74 241	95.28 140	79.75 228	94.25 173	92.28 295	75.17 342	78.02 344	93.77 193	58.60 349	97.84 177	65.06 365	85.92 273	91.63 337
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	85.05 276	83.46 284	89.82 237	94.66 174	79.37 236	94.44 160	94.12 252	82.19 242	78.04 343	92.82 222	58.23 350	97.54 197	73.77 313	82.90 303	92.54 315

CMPMVS	59.16 21	80.52 325	79.20 329	84.48 346	83.98 385	67.63 375	89.95 322	93.84 262	64.79 388	66.81 386	91.14 281	57.93 351	95.17 330	76.25 292	88.10 249	90.65 356
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
tt0805		86.92 232	85.74 244	90.48 207	92.22 263	79.98 223	95.63 92	94.88 219	83.83 204	84.74 247	92.80 224	57.61 352	97.67 185	85.48 165	84.42 284	93.79 267

ITE_SJBPF				88.24 286	91.88 277	77.05 288		92.92 277	85.54 166	80.13 324	93.30 205	57.29 353	96.20 294	72.46 319	84.71 282	91.49 341

UWE-MVS		83.69 297	83.09 290	85.48 336	93.06 241	65.27 382	90.92 299	86.14 375	79.90 285	86.26 203	90.72 294	57.17 354	95.81 312	71.03 329	92.62 183	95.35 196

TESTMET0.1,1		83.74 296	82.85 296	86.42 327	89.96 343	71.21 354	89.55 326	87.88 368	77.41 319	83.37 284	87.31 353	56.71 355	93.65 354	80.62 244	92.85 180	94.40 240

UnsupCasMVSNet_eth		80.07 330	78.27 336	85.46 337	85.24 383	72.63 340	88.45 346	94.87 220	82.99 227	71.64 378	88.07 344	56.34 356	91.75 373	73.48 315	63.36 390	92.01 331

test_fmvs1		87.34 213	87.56 177	86.68 324	90.59 329	71.80 348	94.01 193	94.04 254	78.30 311	91.97 98	95.22 127	56.28 357	93.71 352	92.89 51	94.71 138	94.52 230

K. test v3		81.59 314	80.15 316	85.91 333	89.89 345	69.42 368	92.57 253	87.71 370	85.56 165	73.44 371	89.71 318	55.58 358	95.52 322	77.17 283	69.76 377	92.78 311

test-mter		84.54 284	83.64 282	87.25 308	90.95 313	71.67 350	89.55 326	89.88 356	79.17 294	84.54 251	87.95 345	55.56 359	95.11 332	81.82 222	93.37 169	94.97 206

lessismore_v0				86.04 329	88.46 360	68.78 370		80.59 393		73.01 373	90.11 309	55.39 360	96.43 283	75.06 303	65.06 387	92.90 306

ETVMVS		84.43 285	82.92 294	88.97 267	94.37 191	74.67 316	91.23 293	88.35 366	83.37 217	86.06 208	89.04 327	55.38 361	95.67 318	67.12 353	91.34 195	96.58 146

MVS-HIRNet		73.70 352	72.20 355	78.18 369	91.81 281	56.42 401	82.94 387	82.58 388	55.24 395	68.88 383	66.48 398	55.32 362	95.13 331	58.12 384	88.42 245	83.01 386

test2506		87.21 222	86.28 219	90.02 229	95.62 128	73.64 327	96.25 48	71.38 406	87.89 108	90.45 125	96.65 70	55.29 363	98.09 160	86.03 158	96.94 93	98.33 43

new-patchmatchnet		76.41 348	75.17 351	80.13 363	82.65 391	59.61 394	87.66 356	91.08 328	78.23 314	69.85 382	83.22 377	54.76 364	91.63 375	64.14 369	64.89 388	89.16 371

Anonymous202405211		87.68 194	86.13 224	92.31 128	96.66 79	80.74 199	94.87 132	91.49 320	80.47 279	89.46 140	95.44 118	54.72 365	98.23 143	82.19 212	89.89 218	97.97 74

XVG-ACMP-BASELINE		86.00 256	84.84 265	89.45 254	91.20 301	78.00 267	91.70 280	95.55 176	85.05 178	82.97 289	92.25 241	54.49 366	97.48 202	82.93 196	87.45 262	92.89 307

USDC		82.76 301	81.26 306	87.26 307	91.17 303	74.55 318	89.27 332	93.39 270	78.26 313	75.30 361	92.08 249	54.43 367	96.63 264	71.64 321	85.79 275	90.61 357

AllTest		83.42 298	81.39 304	89.52 251	95.01 153	77.79 276	93.12 233	90.89 336	77.41 319	76.12 356	93.34 201	54.08 368	97.51 200	68.31 346	84.27 286	93.26 290

TestCases				89.52 251	95.01 153	77.79 276		90.89 336	77.41 319	76.12 356	93.34 201	54.08 368	97.51 200	68.31 346	84.27 286	93.26 290

KD-MVS_2432*1600		78.50 341	76.02 348	85.93 331	86.22 375	74.47 319	84.80 377	92.33 292	79.29 292	76.98 350	85.92 365	53.81 370	93.97 347	67.39 351	57.42 395	89.36 366

miper_refine_blended		78.50 341	76.02 348	85.93 331	86.22 375	74.47 319	84.80 377	92.33 292	79.29 292	76.98 350	85.92 365	53.81 370	93.97 347	67.39 351	57.42 395	89.36 366

MIMVSNet		82.59 304	80.53 309	88.76 270	91.51 289	78.32 260	86.57 365	90.13 348	79.32 291	80.70 315	88.69 336	52.98 372	93.07 362	66.03 360	88.86 237	94.90 213

testing222		84.84 280	83.32 285	89.43 255	94.15 202	75.94 303	91.09 296	89.41 362	84.90 180	85.78 211	89.44 322	52.70 373	96.28 292	70.80 330	91.57 193	96.07 167

FMVSNet5		81.52 316	79.60 323	87.27 306	91.17 303	77.95 268	91.49 285	92.26 297	76.87 324	76.16 355	87.91 347	51.67 374	92.34 367	67.74 350	81.16 322	91.52 340

testgi		80.94 324	80.20 315	83.18 353	87.96 367	66.29 377	91.28 290	90.70 340	83.70 206	78.12 342	92.84 220	51.37 375	90.82 380	63.34 370	82.46 306	92.43 320

test_fmvs1_n		87.03 230	87.04 191	86.97 316	89.74 347	71.86 346	94.55 152	94.43 237	78.47 307	91.95 100	95.50 117	51.16 376	93.81 350	93.02 50	94.56 144	95.26 198

Anonymous20240521		80.44 327	79.21 328	84.11 350	85.75 380	67.89 372	92.86 246	93.23 272	75.61 337	75.59 360	87.47 352	50.03 377	94.33 341	71.14 327	81.21 321	90.12 362

UnsupCasMVSNet_bld		76.23 349	73.27 353	85.09 343	83.79 386	72.92 332	85.65 371	93.47 269	71.52 373	68.84 384	79.08 388	49.77 378	93.21 359	66.81 359	60.52 392	89.13 373

OpenMVS_ROB	74.94 19	79.51 336	77.03 343	86.93 317	87.00 372	76.23 301	92.33 262	90.74 339	68.93 381	74.52 366	88.23 342	49.58 379	96.62 265	57.64 385	84.29 285	87.94 380

TDRefinement		79.81 333	77.34 338	87.22 311	79.24 397	75.48 309	93.12 233	92.03 303	76.45 327	75.01 362	91.58 267	49.19 380	96.44 282	70.22 334	69.18 380	89.75 364

test_vis1_n		86.56 245	86.49 212	86.78 323	88.51 357	72.69 336	94.68 145	93.78 264	79.55 290	90.70 121	95.31 123	48.75 381	93.28 358	93.15 47	93.99 153	94.38 241

MIMVSNet1		79.38 337	77.28 339	85.69 335	86.35 374	73.67 326	91.61 283	92.75 283	78.11 316	72.64 374	88.12 343	48.16 382	91.97 372	60.32 378	77.49 357	91.43 343

LF4IMVS		80.37 328	79.07 332	84.27 349	86.64 373	69.87 367	89.39 331	91.05 330	76.38 328	74.97 363	90.00 312	47.85 383	94.25 344	74.55 309	80.82 333	88.69 375

EG-PatchMatch MVS		82.37 306	80.34 312	88.46 278	90.27 336	79.35 237	92.80 248	94.33 242	77.14 323	73.26 372	90.18 306	47.47 384	96.72 260	70.25 332	87.32 265	89.30 368

test_fmvs2		83.98 290	84.03 275	83.83 352	87.16 371	67.53 376	93.93 199	92.89 278	77.62 317	86.89 187	93.53 198	47.18 385	92.02 370	90.54 106	86.51 270	91.93 332

TinyColmap		79.76 334	77.69 337	85.97 330	91.71 284	73.12 331	89.55 326	90.36 344	75.03 343	72.03 376	90.19 305	46.22 386	96.19 296	63.11 371	81.03 327	88.59 376

myMVS_eth3d		79.67 335	78.79 334	82.32 360	91.92 274	64.08 385	89.75 324	87.40 373	81.72 258	78.82 337	87.20 355	45.33 387	91.29 376	59.09 383	87.84 256	91.60 338

tmp_tt		35.64 376	39.24 378	24.84 392	14.87 416	23.90 417	62.71 402	51.51 413	6.58 410	36.66 406	62.08 403	44.37 388	30.34 412	52.40 391	22.00 409	20.27 407

testing3		80.46 326	79.59 324	83.06 355	93.44 231	64.64 384	93.33 221	85.47 379	84.34 194	79.93 328	90.84 289	44.35 389	92.39 366	57.06 387	87.56 259	92.16 329

new_pmnet		72.15 353	70.13 357	78.20 368	82.95 390	65.68 378	83.91 382	82.40 389	62.94 391	64.47 387	79.82 387	42.85 390	86.26 394	57.41 386	74.44 368	82.65 388

test_vis1_rt		77.96 344	76.46 344	82.48 358	85.89 378	71.74 349	90.25 311	78.89 396	71.03 377	71.30 379	81.35 385	42.49 391	91.05 379	84.55 176	82.37 307	84.65 383

EGC-MVSNET		61.97 363	56.37 368	78.77 367	89.63 349	73.50 328	89.12 336	82.79 387	0.21 413	1.24 414	84.80 371	39.48 392	90.04 383	44.13 396	75.94 366	72.79 395

dongtai		58.82 368	58.24 366	60.56 385	83.13 388	45.09 409	82.32 388	48.22 415	67.61 383	61.70 392	69.15 396	38.75 393	76.05 404	32.01 403	41.31 403	60.55 400

kuosan		53.51 370	53.30 373	54.13 389	76.06 398	45.36 408	80.11 395	48.36 414	59.63 393	54.84 395	63.43 402	37.41 394	62.07 409	20.73 409	39.10 404	54.96 403

pmmvs3		71.81 355	68.71 358	81.11 361	75.86 399	70.42 363	86.74 363	83.66 385	58.95 394	68.64 385	80.89 386	36.93 395	89.52 385	63.10 372	63.59 389	83.39 384

mvsany_test3		74.95 350	73.26 354	80.02 364	74.61 400	63.16 389	85.53 372	78.42 397	74.16 352	74.89 364	86.46 360	36.02 396	89.09 387	82.39 207	66.91 384	87.82 381

PM-MVS		78.11 343	76.12 347	84.09 351	83.54 387	70.08 365	88.97 339	85.27 381	79.93 284	74.73 365	86.43 361	34.70 397	93.48 355	79.43 261	72.06 373	88.72 374

ambc				83.06 355	79.99 395	63.51 388	77.47 397	92.86 279		74.34 368	84.45 373	28.74 398	95.06 334	73.06 317	68.89 382	90.61 357

test_method		50.52 372	48.47 374	56.66 387	52.26 414	18.98 418	41.51 406	81.40 391	10.10 408	44.59 403	75.01 392	28.51 399	68.16 405	53.54 390	49.31 400	82.83 387

DeepMVS_CX				56.31 388	74.23 401	51.81 404		56.67 412	44.85 400	48.54 400	75.16 391	27.87 400	58.74 410	40.92 400	52.22 397	58.39 402

test_fmvs3		77.67 345	77.16 342	79.22 365	79.52 396	61.14 391	92.34 261	91.64 315	73.98 354	78.86 336	86.59 359	27.38 401	87.03 390	88.12 131	75.97 365	89.50 365

test_f		71.95 354	70.87 356	75.21 372	74.21 402	59.37 395	85.07 376	85.82 377	65.25 387	70.42 381	83.13 378	23.62 402	82.93 400	78.32 270	71.94 374	83.33 385

FPMVS		64.63 362	62.55 364	70.88 375	70.80 404	56.71 397	84.42 380	84.42 383	51.78 398	49.57 398	81.61 384	23.49 403	81.48 401	40.61 401	76.25 364	74.46 394

APD_test1		69.04 356	66.26 362	77.36 371	80.51 394	62.79 390	85.46 373	83.51 386	54.11 397	59.14 394	84.79 372	23.40 404	89.61 384	55.22 388	70.24 376	79.68 392

ANet_high		58.88 367	54.22 372	72.86 373	56.50 413	56.67 398	80.75 392	86.00 376	73.09 364	37.39 405	64.63 401	22.17 405	79.49 403	43.51 397	23.96 407	82.43 389

EMVS		42.07 375	41.12 377	44.92 391	63.45 411	35.56 415	73.65 398	63.48 409	33.05 406	26.88 410	45.45 407	21.27 406	67.14 407	19.80 410	23.02 408	32.06 406

Gipuma		57.99 369	54.91 371	67.24 383	88.51 357	65.59 379	52.21 404	90.33 345	43.58 401	42.84 404	51.18 405	20.29 407	85.07 395	34.77 402	70.45 375	51.05 404
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		43.23 374	42.29 376	46.03 390	65.58 409	37.41 413	73.51 399	64.62 408	33.99 405	28.47 409	47.87 406	19.90 408	67.91 406	22.23 408	24.45 406	32.77 405

PMMVS2		59.60 364	56.40 367	69.21 380	68.83 407	46.58 406	73.02 401	77.48 402	55.07 396	49.21 399	72.95 395	17.43 409	80.04 402	49.32 393	44.33 402	80.99 390

LCM-MVSNet		66.00 360	62.16 365	77.51 370	64.51 410	58.29 396	83.87 383	90.90 335	48.17 399	54.69 396	73.31 394	16.83 410	86.75 391	65.47 361	61.67 391	87.48 382

test_vis3_rt		65.12 361	62.60 363	72.69 374	71.44 403	60.71 392	87.17 360	65.55 407	63.80 390	53.22 397	65.65 400	14.54 411	89.44 386	76.65 287	65.38 386	67.91 398

testf1		59.54 365	56.11 369	69.85 378	69.28 405	56.61 399	80.37 393	76.55 404	42.58 402	45.68 401	75.61 389	11.26 412	84.18 396	43.20 398	60.44 393	68.75 396

APD_test2		59.54 365	56.11 369	69.85 378	69.28 405	56.61 399	80.37 393	76.55 404	42.58 402	45.68 401	75.61 389	11.26 412	84.18 396	43.20 398	60.44 393	68.75 396

PMVS	47.18 22	52.22 371	48.46 375	63.48 384	45.72 415	46.20 407	73.41 400	78.31 398	41.03 404	30.06 407	65.68 399	6.05 414	83.43 399	30.04 404	65.86 385	60.80 399
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	39.65 23	43.39 373	38.59 379	57.77 386	56.52 412	48.77 405	55.38 403	58.64 411	29.33 407	28.96 408	52.65 404	4.68 415	64.62 408	28.11 405	33.07 405	59.93 401
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		21.27 378	20.48 381	23.63 393	68.59 408	36.41 414	49.57 405	6.85 417	9.37 409	7.89 411	4.46 413	4.03 416	31.37 411	17.47 411	16.07 410	3.12 408

test123		8.76 380	11.22 383	1.39 394	0.85 418	0.97 419	85.76 370	0.35 419	0.54 412	2.45 413	8.14 412	0.60 417	0.48 413	2.16 413	0.17 412	2.71 409

testmvs		8.92 379	11.52 382	1.12 395	1.06 417	0.46 420	86.02 367	0.65 418	0.62 411	2.74 412	9.52 411	0.31 418	0.45 414	2.38 412	0.39 411	2.46 410

test_blank		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet_test		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

DCPMVS		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

sosnet-low-res		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

sosnet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uncertanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

Regformer		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

ab-mvs-re		7.82 381	10.43 384	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	93.88 188	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

WAC-MVS						64.08 385								59.14 382

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					0.00 419

eth-test					0.00 419

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	95.21 112	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																96.12 163

test_part2					98.55 12	87.22 19				96.40 17

MTGPA								96.97 50

MTMP							96.16 53	60.64 410

gm-plane-assit					89.60 350	68.00 371			77.28 322		88.99 328		97.57 195	79.44 260

test9_res														91.91 83	98.71 32	98.07 68

agg_prior2														90.54 106	98.68 38	98.27 52

agg_prior					97.38 63	85.92 57		96.72 81		92.16 93			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		71.25 375	94.37 39			97.13 240	86.74 149

新几何2							93.11 235

无先验							93.28 228	96.26 114	73.95 355				99.05 55	80.56 245		96.59 145

原ACMM2							92.94 242

testdata2													98.75 93	78.30 271

testdata1							92.15 268		87.94 104

plane_prior7					94.70 172	82.74 143

plane_prior5								96.22 119					98.12 150	88.15 128	89.99 214	94.63 222

plane_prior4											94.86 144

plane_prior3						82.75 141			90.26 33	86.91 184

plane_prior2							95.85 77		90.81 17

plane_prior1					94.59 177

plane_prior						82.73 144	95.21 112		89.66 50						89.88 219

n2								0.00 420

nn								0.00 420

door-mid								85.49 378

test11								96.57 92

door								85.33 380

HQP5-MVS						81.56 172

HQP-NCC					94.17 199		94.39 165		88.81 74	85.43 228

ACMP_Plane					94.17 199		94.39 165		88.81 74	85.43 228

BP-MVS														87.11 146

HQP4-MVS										85.43 228			97.96 171			94.51 232

HQP3-MVS								96.04 136							89.77 223

NP-MVS					94.37 191	82.42 155					93.98 181

ACMMP++_ref															87.47 260

ACMMP++															88.01 252

High-resolution multi-view benchmark