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.

MSC_two_6792asdad				96.52 1	97.78 56	90.86 1		96.85 74					99.61 4	96.03 24	99.06 9	99.07 5

No_MVS				96.52 1	97.78 56	90.86 1		96.85 74					99.61 4	96.03 24	99.06 9	99.07 5

OPU-MVS				96.21 3	98.00 44	90.85 3	97.13 15				97.08 63	92.59 2	98.94 86	92.25 85	98.99 14	98.84 15

HPM-MVS++		95.14 10	94.91 21	95.83 4	98.25 31	89.65 4	95.92 81	96.96 62	91.75 12	94.02 64	96.83 75	88.12 24	99.55 16	93.41 59	98.94 16	98.28 57

MM		95.10 11	94.91 21	95.68 5	96.09 111	88.34 9	96.68 34	94.37 266	95.08 1	94.68 50	97.72 36	82.94 95	99.64 1	97.85 4	98.76 29	99.06 7

SMA-MVS		95.20 8	95.07 15	95.59 6	98.14 37	88.48 8	96.26 49	97.28 35	85.90 182	97.67 3	98.10 12	88.41 20	99.56 12	94.66 43	99.19 1	98.71 21
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
3Dnovator+	87.14 4	92.42 97	91.37 107	95.55 7	95.63 136	88.73 6	97.07 19	96.77 85	90.84 23	84.02 302	96.62 88	75.95 188	99.34 38	87.77 158	97.68 90	98.59 25

CNVR-MVS		95.40 7	95.37 9	95.50 8	98.11 38	88.51 7	95.29 122	96.96 62	92.09 9	95.32 42	97.08 63	89.49 15	99.33 41	95.10 38	98.85 20	98.66 22

MVS_0304		94.18 44	93.80 58	95.34 9	94.91 175	87.62 14	95.97 76	93.01 310	92.58 6	94.22 55	97.20 57	80.56 127	99.59 8	97.04 17	98.68 37	98.81 18

ACMMP_NAP		94.74 22	94.56 27	95.28 10	98.02 43	87.70 11	95.68 99	97.34 26	88.28 115	95.30 43	97.67 38	85.90 51	99.54 20	93.91 51	98.95 15	98.60 24

DPE-MVS		95.57 4	95.67 4	95.25 11	98.36 27	87.28 18	95.56 111	97.51 7	89.13 84	97.14 13	97.91 29	91.64 7	99.62 2	94.61 44	99.17 2	98.86 12
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SF-MVS		94.97 14	94.90 23	95.20 12	97.84 52	87.76 10	96.65 35	97.48 12	87.76 137	95.71 37	97.70 37	88.28 23	99.35 37	93.89 52	98.78 26	98.48 31

MCST-MVS		94.45 29	94.20 45	95.19 13	98.46 19	87.50 16	95.00 145	97.12 50	87.13 150	92.51 105	96.30 97	89.24 17	99.34 38	93.46 56	98.62 46	98.73 19

NCCC		94.81 19	94.69 26	95.17 14	97.83 53	87.46 17	95.66 102	96.93 66	92.34 7	93.94 65	96.58 90	87.74 27	99.44 29	92.83 68	98.40 54	98.62 23

DPM-MVS		92.58 93	91.74 103	95.08 15	96.19 102	89.31 5	92.66 286	96.56 105	83.44 251	91.68 129	95.04 160	86.60 43	98.99 76	85.60 190	97.92 79	96.93 158

ZNCC-MVS		94.47 28	94.28 39	95.03 16	98.52 15	86.96 20	96.85 29	97.32 30	88.24 116	93.15 80	97.04 66	86.17 48	99.62 2	92.40 79	98.81 23	98.52 27

test_0728_SECOND				95.01 17	98.79 2	86.43 39	97.09 17	97.49 8					99.61 4	95.62 31	99.08 7	98.99 9

MTAPA		94.42 33	94.22 42	95.00 18	98.42 21	86.95 21	94.36 195	96.97 59	91.07 19	93.14 81	97.56 40	84.30 76	99.56 12	93.43 57	98.75 30	98.47 34

MSP-MVS		95.42 6	95.56 6	94.98 19	98.49 17	86.52 36	96.91 26	97.47 13	91.73 13	96.10 30	96.69 80	89.90 12	99.30 44	94.70 42	98.04 74	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
region2R		94.43 31	94.27 41	94.92 20	98.65 8	86.67 30	96.92 25	97.23 38	88.60 106	93.58 72	97.27 51	85.22 59	99.54 20	92.21 86	98.74 31	98.56 26

APDe-MVS		95.46 5	95.64 5	94.91 21	98.26 30	86.29 46	97.46 7	97.40 22	89.03 89	96.20 29	98.10 12	89.39 16	99.34 38	95.88 26	99.03 11	99.10 4
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		94.43 31	94.28 39	94.91 21	98.63 9	86.69 28	96.94 21	97.32 30	88.63 103	93.53 75	97.26 53	85.04 63	99.54 20	92.35 82	98.78 26	98.50 28

GST-MVS		94.21 39	93.97 54	94.90 23	98.41 22	86.82 24	96.54 37	97.19 39	88.24 116	93.26 77	96.83 75	85.48 56	99.59 8	91.43 112	98.40 54	98.30 51

HFP-MVS		94.52 26	94.40 32	94.86 24	98.61 10	86.81 25	96.94 21	97.34 26	88.63 103	93.65 70	97.21 55	86.10 49	99.49 26	92.35 82	98.77 28	98.30 51

sasdasda		93.27 76	92.75 86	94.85 25	95.70 131	87.66 12	96.33 40	96.41 115	90.00 48	94.09 60	94.60 182	82.33 104	98.62 124	92.40 79	92.86 204	98.27 59

MP-MVS-pluss		94.21 39	94.00 53	94.85 25	98.17 35	86.65 31	94.82 158	97.17 44	86.26 174	92.83 90	97.87 31	85.57 55	99.56 12	94.37 47	98.92 17	98.34 44
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
canonicalmvs		93.27 76	92.75 86	94.85 25	95.70 131	87.66 12	96.33 40	96.41 115	90.00 48	94.09 60	94.60 182	82.33 104	98.62 124	92.40 79	92.86 204	98.27 59

XVS		94.45 29	94.32 35	94.85 25	98.54 13	86.60 34	96.93 23	97.19 39	90.66 31	92.85 88	97.16 61	85.02 64	99.49 26	91.99 97	98.56 50	98.47 34

X-MVStestdata		88.31 206	86.13 255	94.85 25	98.54 13	86.60 34	96.93 23	97.19 39	90.66 31	92.85 88	23.41 453	85.02 64	99.49 26	91.99 97	98.56 50	98.47 34

SteuartSystems-ACMMP		95.20 8	95.32 11	94.85 25	96.99 77	86.33 42	97.33 8	97.30 32	91.38 17	95.39 41	97.46 43	88.98 19	99.40 30	94.12 48	98.89 18	98.82 17
Skip Steuart: Steuart Systems R&D Blog.
DVP-MVS++		95.98 1	96.36 1	94.82 31	97.78 56	86.00 52	98.29 1	97.49 8	90.75 26	97.62 6	98.06 20	92.59 2	99.61 4	95.64 29	99.02 12	98.86 12

alignmvs		93.08 84	92.50 92	94.81 32	95.62 137	87.61 15	95.99 74	96.07 151	89.77 61	94.12 59	94.87 166	80.56 127	98.66 117	92.42 78	93.10 200	98.15 71

SED-MVS		95.91 2	96.28 2	94.80 33	98.77 5	85.99 54	97.13 15	97.44 17	90.31 38	97.71 1	98.07 18	92.31 4	99.58 10	95.66 27	99.13 3	98.84 15

DeepC-MVS_fast	89.43 2	94.04 47	93.79 59	94.80 33	97.48 66	86.78 26	95.65 104	96.89 71	89.40 72	92.81 91	96.97 68	85.37 58	99.24 47	90.87 121	98.69 35	98.38 43
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MP-MVS		94.25 36	94.07 50	94.77 35	98.47 18	86.31 44	96.71 32	96.98 58	89.04 87	91.98 116	97.19 58	85.43 57	99.56 12	92.06 95	98.79 24	98.44 38
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
APD-MVS		94.24 37	94.07 50	94.75 36	98.06 41	86.90 23	95.88 83	96.94 65	85.68 189	95.05 48	97.18 59	87.31 35	99.07 59	91.90 103	98.61 48	98.28 57
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CP-MVS		94.34 34	94.21 44	94.74 37	98.39 25	86.64 32	97.60 5	97.24 36	88.53 108	92.73 96	97.23 54	85.20 60	99.32 42	92.15 89	98.83 22	98.25 64

PGM-MVS		93.96 52	93.72 64	94.68 38	98.43 20	86.22 47	95.30 120	97.78 1	87.45 144	93.26 77	97.33 49	84.62 73	99.51 24	90.75 123	98.57 49	98.32 50

DVP-MVS		95.67 3	96.02 3	94.64 39	98.78 3	85.93 57	97.09 17	96.73 91	90.27 42	97.04 17	98.05 22	91.47 8	99.55 16	95.62 31	99.08 7	98.45 37
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
mPP-MVS		93.99 50	93.78 60	94.63 40	98.50 16	85.90 62	96.87 27	96.91 69	88.70 101	91.83 125	97.17 60	83.96 80	99.55 16	91.44 111	98.64 45	98.43 39

PHI-MVS		93.89 54	93.65 68	94.62 41	96.84 80	86.43 39	96.69 33	97.49 8	85.15 209	93.56 74	96.28 98	85.60 54	99.31 43	92.45 76	98.79 24	98.12 75

TSAR-MVS + MP.		94.85 16	94.94 19	94.58 42	98.25 31	86.33 42	96.11 62	96.62 100	88.14 121	96.10 30	96.96 69	89.09 18	98.94 86	94.48 45	98.68 37	98.48 31
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CANet		93.54 63	93.20 77	94.55 43	95.65 134	85.73 67	94.94 148	96.69 96	91.89 11	90.69 144	95.88 121	81.99 116	99.54 20	93.14 63	97.95 78	98.39 41

train_agg		93.44 69	93.08 79	94.52 44	97.53 63	86.49 37	94.07 214	96.78 83	81.86 292	92.77 93	96.20 101	87.63 29	99.12 57	92.14 90	98.69 35	97.94 87

CDPH-MVS		92.83 88	92.30 95	94.44 45	97.79 54	86.11 51	94.06 216	96.66 97	80.09 323	92.77 93	96.63 87	86.62 41	99.04 63	87.40 163	98.66 41	98.17 69

3Dnovator	86.66 5	91.73 108	90.82 121	94.44 45	94.59 196	86.37 41	97.18 13	97.02 56	89.20 81	84.31 297	96.66 83	73.74 226	99.17 51	86.74 173	97.96 77	97.79 100

SR-MVS		94.23 38	94.17 48	94.43 47	98.21 34	85.78 65	96.40 39	96.90 70	88.20 119	94.33 54	97.40 46	84.75 72	99.03 64	93.35 60	97.99 76	98.48 31

HPM-MVS		94.02 48	93.88 55	94.43 47	98.39 25	85.78 65	97.25 11	97.07 54	86.90 158	92.62 102	96.80 79	84.85 70	99.17 51	92.43 77	98.65 44	98.33 46
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
TSAR-MVS + GP.		93.66 61	93.41 72	94.41 49	96.59 87	86.78 26	94.40 187	93.93 284	89.77 61	94.21 56	95.59 135	87.35 34	98.61 126	92.72 71	96.15 128	97.83 98

reproduce-ours		94.82 17	94.97 17	94.38 50	97.91 49	85.46 70	95.86 84	97.15 46	89.82 54	95.23 45	98.10 12	87.09 37	99.37 33	95.30 35	98.25 62	98.30 51

our_new_method		94.82 17	94.97 17	94.38 50	97.91 49	85.46 70	95.86 84	97.15 46	89.82 54	95.23 45	98.10 12	87.09 37	99.37 33	95.30 35	98.25 62	98.30 51

NormalMVS		93.46 66	93.16 78	94.37 52	98.40 23	86.20 48	96.30 42	96.27 128	91.65 15	92.68 98	96.13 107	77.97 161	98.84 99	90.75 123	98.26 59	98.07 77

test12				94.34 53	97.13 75	86.15 50		96.29 124		91.04 140		85.08 62	99.01 69		98.13 69	97.86 95

SymmetryMVS		92.81 90	92.31 94	94.32 54	96.15 103	86.20 48	96.30 42	94.43 262	91.65 15	92.68 98	96.13 107	77.97 161	98.84 99	90.75 123	94.72 158	97.92 90

ACMMP		93.24 78	92.88 84	94.30 55	98.09 40	85.33 74	96.86 28	97.45 16	88.33 112	90.15 156	97.03 67	81.44 121	99.51 24	90.85 122	95.74 135	98.04 82
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
reproduce_model		94.76 21	94.92 20	94.29 56	97.92 45	85.18 76	95.95 79	97.19 39	89.67 64	95.27 44	98.16 5	86.53 44	99.36 36	95.42 34	98.15 67	98.33 46

DeepC-MVS	88.79 3	93.31 75	92.99 82	94.26 57	96.07 113	85.83 63	94.89 151	96.99 57	89.02 90	89.56 162	97.37 48	82.51 101	99.38 31	92.20 87	98.30 57	97.57 114
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MGCFI-Net		93.03 85	92.63 89	94.23 58	95.62 137	85.92 59	96.08 64	96.33 122	89.86 52	93.89 67	94.66 179	82.11 111	98.50 132	92.33 84	92.82 207	98.27 59

fmvsm_l_conf0.5_n_3		94.80 20	95.01 16	94.15 59	95.64 135	85.08 77	96.09 63	97.36 24	90.98 21	97.09 15	98.12 9	84.98 68	98.94 86	97.07 14	97.80 85	98.43 39

EPNet		91.79 105	91.02 116	94.10 60	90.10 379	85.25 75	96.03 71	92.05 337	92.83 5	87.39 208	95.78 127	79.39 143	99.01 69	88.13 153	97.48 93	98.05 81
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
lecture		95.10 11	95.46 8	94.01 61	98.40 23	84.36 102	97.70 3	97.78 1	91.19 18	96.22 28	98.08 17	86.64 40	99.37 33	94.91 40	98.26 59	98.29 56

test_fmvsmconf_n		94.60 24	94.81 24	93.98 62	94.62 194	84.96 80	96.15 57	97.35 25	89.37 73	96.03 33	98.11 10	86.36 45	99.01 69	97.45 9	97.83 83	97.96 86

DELS-MVS		93.43 73	93.25 75	93.97 63	95.42 145	85.04 78	93.06 272	97.13 49	90.74 28	91.84 123	95.09 159	86.32 46	99.21 49	91.22 113	98.45 52	97.65 109
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
DP-MVS Recon		91.95 102	91.28 110	93.96 64	98.33 29	85.92 59	94.66 170	96.66 97	82.69 271	90.03 158	95.82 125	82.30 106	99.03 64	84.57 207	96.48 121	96.91 160

HPM-MVS_fast		93.40 74	93.22 76	93.94 65	98.36 27	84.83 82	97.15 14	96.80 82	85.77 186	92.47 106	97.13 62	82.38 102	99.07 59	90.51 128	98.40 54	97.92 90

test_fmvsmconf0.1_n		94.20 41	94.31 37	93.88 66	92.46 295	84.80 83	96.18 54	96.82 79	89.29 78	95.68 38	98.11 10	85.10 61	98.99 76	97.38 10	97.75 89	97.86 95

SD-MVS		94.96 15	95.33 10	93.88 66	97.25 74	86.69 28	96.19 52	97.11 52	90.42 34	96.95 19	97.27 51	89.53 14	96.91 285	94.38 46	98.85 20	98.03 83
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
MVS_111021_HR		93.45 68	93.31 73	93.84 68	96.99 77	84.84 81	93.24 263	97.24 36	88.76 98	91.60 130	95.85 123	86.07 50	98.66 117	91.91 101	98.16 66	98.03 83

SR-MVS-dyc-post		93.82 56	93.82 57	93.82 69	97.92 45	84.57 89	96.28 46	96.76 86	87.46 142	93.75 68	97.43 44	84.24 77	99.01 69	92.73 69	97.80 85	97.88 93

test_prior				93.82 69	97.29 72	84.49 93		96.88 72					98.87 93			98.11 76

APD-MVS_3200maxsize		93.78 57	93.77 61	93.80 71	97.92 45	84.19 106	96.30 42	96.87 73	86.96 154	93.92 66	97.47 42	83.88 81	98.96 83	92.71 72	97.87 81	98.26 63

fmvsm_l_conf0.5_n		94.29 35	94.46 30	93.79 72	95.28 150	85.43 72	95.68 99	96.43 113	86.56 166	96.84 21	97.81 34	87.56 32	98.77 108	97.14 12	96.82 111	97.16 139

CSCG		93.23 79	93.05 80	93.76 73	98.04 42	84.07 108	96.22 51	97.37 23	84.15 232	90.05 157	95.66 132	87.77 26	99.15 55	89.91 133	98.27 58	98.07 77

GDP-MVS		92.04 100	91.46 106	93.75 74	94.55 202	84.69 86	95.60 110	96.56 105	87.83 134	93.07 84	95.89 120	73.44 230	98.65 119	90.22 131	96.03 130	97.91 92

BP-MVS1		92.48 95	92.07 98	93.72 75	94.50 205	84.39 101	95.90 82	94.30 269	90.39 35	92.67 100	95.94 117	74.46 209	98.65 119	93.14 63	97.35 97	98.13 72

test_fmvsmconf0.01_n		93.19 80	93.02 81	93.71 76	89.25 392	84.42 100	96.06 68	96.29 124	89.06 85	94.68 50	98.13 6	79.22 145	98.98 80	97.22 11	97.24 99	97.74 103

UA-Net		92.83 88	92.54 91	93.68 77	96.10 110	84.71 85	95.66 102	96.39 117	91.92 10	93.22 79	96.49 93	83.16 90	98.87 93	84.47 209	95.47 142	97.45 120

fmvsm_l_conf0.5_n_a		94.20 41	94.40 32	93.60 78	95.29 149	84.98 79	95.61 107	96.28 127	86.31 172	96.75 23	97.86 32	87.40 33	98.74 112	97.07 14	97.02 104	97.07 144

QAPM		89.51 168	88.15 192	93.59 79	94.92 173	84.58 88	96.82 30	96.70 95	78.43 350	83.41 318	96.19 104	73.18 235	99.30 44	77.11 318	96.54 118	96.89 161

test_fmvsm_n_1920		94.71 23	95.11 14	93.50 80	95.79 126	84.62 87	96.15 57	97.64 3	89.85 53	97.19 12	97.89 30	86.28 47	98.71 115	97.11 13	98.08 73	97.17 135

fmvsm_s_conf0.5_n_9		94.99 13	95.50 7	93.44 81	96.51 95	82.25 175	95.76 94	96.92 67	93.37 3	97.63 5	98.43 1	84.82 71	99.16 54	98.15 1	97.92 79	98.90 11

KinetiMVS		91.82 104	91.30 108	93.39 82	94.72 187	83.36 133	95.45 113	96.37 119	90.33 37	92.17 111	96.03 112	72.32 247	98.75 109	87.94 156	96.34 123	98.07 77

casdiffmvs_mvg		92.96 87	92.83 85	93.35 83	94.59 196	83.40 131	95.00 145	96.34 121	90.30 40	92.05 114	96.05 111	83.43 84	98.15 168	92.07 92	95.67 136	98.49 30
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
fmvsm_s_conf0.5_n_5		93.96 52	94.18 47	93.30 84	94.79 182	83.81 117	95.77 92	96.74 90	88.02 124	96.23 27	97.84 33	83.36 88	98.83 102	97.49 7	97.34 98	97.25 130

EI-MVSNet-Vis-set		93.01 86	92.92 83	93.29 85	95.01 164	83.51 128	94.48 179	95.77 176	90.87 22	92.52 104	96.67 82	84.50 74	99.00 74	91.99 97	94.44 170	97.36 122

Vis-MVSNet		91.75 107	91.23 111	93.29 85	95.32 148	83.78 118	96.14 59	95.98 158	89.89 50	90.45 148	96.58 90	75.09 200	98.31 159	84.75 202	96.90 107	97.78 101
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
balanced_conf03		93.98 51	94.22 42	93.26 87	96.13 105	83.29 135	96.27 48	96.52 108	89.82 54	95.56 40	95.51 137	84.50 74	98.79 106	94.83 41	98.86 19	97.72 105

SPE-MVS-test		94.02 48	94.29 38	93.24 88	96.69 83	83.24 136	97.49 6	96.92 67	92.14 8	92.90 86	95.77 128	85.02 64	98.33 156	93.03 65	98.62 46	98.13 72

VNet		92.24 99	91.91 100	93.24 88	96.59 87	83.43 129	94.84 157	96.44 112	89.19 82	94.08 63	95.90 119	77.85 167	98.17 166	88.90 144	93.38 192	98.13 72

VDD-MVS		90.74 127	89.92 141	93.20 90	96.27 100	83.02 150	95.73 96	93.86 288	88.42 111	92.53 103	96.84 74	62.09 353	98.64 121	90.95 119	92.62 213	97.93 89

Elysia		90.12 146	89.10 163	93.18 91	93.16 269	84.05 110	95.22 129	96.27 128	85.16 207	90.59 145	94.68 175	64.64 336	98.37 149	86.38 179	95.77 133	97.12 141

StellarMVS		90.12 146	89.10 163	93.18 91	93.16 269	84.05 110	95.22 129	96.27 128	85.16 207	90.59 145	94.68 175	64.64 336	98.37 149	86.38 179	95.77 133	97.12 141

CS-MVS		94.12 45	94.44 31	93.17 93	96.55 90	83.08 147	97.63 4	96.95 64	91.71 14	93.50 76	96.21 100	85.61 53	98.24 161	93.64 54	98.17 65	98.19 67

nrg030		91.08 121	90.39 125	93.17 93	93.07 275	86.91 22	96.41 38	96.26 132	88.30 114	88.37 185	94.85 169	82.19 110	97.64 215	91.09 114	82.95 335	94.96 244

MVSMamba_PlusPlus		93.44 69	93.54 70	93.14 95	96.58 89	83.05 148	96.06 68	96.50 110	84.42 229	94.09 60	95.56 136	85.01 67	98.69 116	94.96 39	98.66 41	97.67 108

EI-MVSNet-UG-set		92.74 91	92.62 90	93.12 96	94.86 178	83.20 138	94.40 187	95.74 179	90.71 30	92.05 114	96.60 89	84.00 79	98.99 76	91.55 109	93.63 183	97.17 135

test_fmvsmvis_n_1920		93.44 69	93.55 69	93.10 97	93.67 255	84.26 104	95.83 88	96.14 142	89.00 91	92.43 107	97.50 41	83.37 87	98.72 113	96.61 21	97.44 94	96.32 184

新几何1				93.10 97	97.30 71	84.35 103		95.56 193	71.09 416	91.26 137	96.24 99	82.87 97	98.86 95	79.19 297	98.10 70	96.07 200

OMC-MVS		91.23 116	90.62 124	93.08 99	96.27 100	84.07 108	93.52 245	95.93 162	86.95 155	89.51 163	96.13 107	78.50 155	98.35 153	85.84 188	92.90 203	96.83 166

OpenMVS	83.78 11	88.74 194	87.29 212	93.08 99	92.70 290	85.39 73	96.57 36	96.43 113	78.74 345	80.85 350	96.07 110	69.64 282	99.01 69	78.01 309	96.65 116	94.83 252

MAR-MVS		90.30 142	89.37 156	93.07 101	96.61 86	84.48 94	95.68 99	95.67 185	82.36 276	87.85 195	92.85 248	76.63 179	98.80 104	80.01 285	96.68 115	95.91 206
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
lupinMVS		90.92 122	90.21 129	93.03 102	93.86 241	83.88 115	92.81 283	93.86 288	79.84 326	91.76 126	94.29 195	77.92 164	98.04 184	90.48 129	97.11 100	97.17 135

Effi-MVS+		91.59 111	91.11 113	93.01 103	94.35 218	83.39 132	94.60 172	95.10 227	87.10 151	90.57 147	93.10 243	81.43 122	98.07 182	89.29 139	94.48 168	97.59 113

fmvsm_s_conf0.5_n_a		93.57 62	93.76 62	93.00 104	95.02 163	83.67 121	96.19 52	96.10 148	87.27 147	95.98 34	98.05 22	83.07 94	98.45 142	96.68 20	95.51 139	96.88 162

MVS_111021_LR		92.47 96	92.29 96	92.98 105	95.99 119	84.43 98	93.08 269	96.09 149	88.20 119	91.12 139	95.72 131	81.33 123	97.76 204	91.74 105	97.37 96	96.75 168

fmvsm_s_conf0.1_n_a		93.19 80	93.26 74	92.97 106	92.49 293	83.62 124	96.02 72	95.72 182	86.78 160	96.04 32	98.19 3	82.30 106	98.43 146	96.38 22	95.42 145	96.86 163

ETV-MVS		92.74 91	92.66 88	92.97 106	95.20 156	84.04 112	95.07 141	96.51 109	90.73 29	92.96 85	91.19 309	84.06 78	98.34 154	91.72 106	96.54 118	96.54 179

LFMVS		90.08 149	89.13 162	92.95 108	96.71 82	82.32 174	96.08 64	89.91 393	86.79 159	92.15 113	96.81 77	62.60 351	98.34 154	87.18 167	93.90 178	98.19 67

UGNet		89.95 155	88.95 168	92.95 108	94.51 204	83.31 134	95.70 98	95.23 220	89.37 73	87.58 202	93.94 211	64.00 341	98.78 107	83.92 216	96.31 124	96.74 169
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
jason		90.80 125	90.10 133	92.90 110	93.04 278	83.53 127	93.08 269	94.15 277	80.22 320	91.41 134	94.91 163	76.87 173	97.93 195	90.28 130	96.90 107	97.24 131
jason: jason.
DP-MVS		87.25 247	85.36 284	92.90 110	97.65 60	83.24 136	94.81 159	92.00 339	74.99 384	81.92 339	95.00 161	72.66 240	99.05 61	66.92 398	92.33 218	96.40 181

fmvsm_s_conf0.5_n_8		94.56 25	95.12 13	92.87 112	95.96 122	81.32 198	95.76 94	97.57 5	93.48 2	97.53 8	98.32 2	81.78 120	99.13 56	97.91 2	97.81 84	98.16 70

fmvsm_s_conf0.5_n		93.76 58	94.06 52	92.86 113	95.62 137	83.17 139	96.14 59	96.12 146	88.13 122	95.82 36	98.04 25	83.43 84	98.48 134	96.97 18	96.23 125	96.92 159

fmvsm_s_conf0.1_n		93.46 66	93.66 67	92.85 114	93.75 248	83.13 141	96.02 72	95.74 179	87.68 139	95.89 35	98.17 4	82.78 98	98.46 138	96.71 19	96.17 127	96.98 153

CANet_DTU		90.26 144	89.41 155	92.81 115	93.46 262	83.01 151	93.48 246	94.47 261	89.43 71	87.76 200	94.23 200	70.54 270	99.03 64	84.97 197	96.39 122	96.38 182

MVSFormer		91.68 110	91.30 108	92.80 116	93.86 241	83.88 115	95.96 77	95.90 166	84.66 225	91.76 126	94.91 163	77.92 164	97.30 252	89.64 135	97.11 100	97.24 131

PVSNet_Blended_VisFu		91.38 113	90.91 118	92.80 116	96.39 97	83.17 139	94.87 153	96.66 97	83.29 256	89.27 169	94.46 190	80.29 130	99.17 51	87.57 161	95.37 146	96.05 203

LuminaMVS		90.55 138	89.81 143	92.77 118	92.78 288	84.21 105	94.09 212	94.17 276	85.82 183	91.54 131	94.14 202	69.93 276	97.92 196	91.62 108	94.21 173	96.18 192

fmvsm_s_conf0.5_n_6		94.11 46	94.56 27	92.76 119	94.98 168	81.96 182	95.79 90	97.29 34	89.31 76	97.52 9	97.61 39	83.25 89	98.88 92	97.05 16	98.22 64	97.43 121

VDDNet		89.56 167	88.49 183	92.76 119	95.07 162	82.09 177	96.30 42	93.19 305	81.05 314	91.88 121	96.86 73	61.16 369	98.33 156	88.43 150	92.49 217	97.84 97

h-mvs33		90.80 125	90.15 132	92.75 121	96.01 115	82.66 164	95.43 114	95.53 197	89.80 57	93.08 82	95.64 133	75.77 189	99.00 74	92.07 92	78.05 392	96.60 174

casdiffmvs		92.51 94	92.43 93	92.74 122	94.41 213	81.98 180	94.54 176	96.23 136	89.57 67	91.96 118	96.17 105	82.58 100	98.01 186	90.95 119	95.45 144	98.23 65
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_yl		90.69 130	90.02 139	92.71 123	95.72 129	82.41 172	94.11 208	95.12 225	85.63 190	91.49 132	94.70 173	74.75 204	98.42 147	86.13 183	92.53 215	97.31 123

DCV-MVSNet		90.69 130	90.02 139	92.71 123	95.72 129	82.41 172	94.11 208	95.12 225	85.63 190	91.49 132	94.70 173	74.75 204	98.42 147	86.13 183	92.53 215	97.31 123

PCF-MVS	84.11 10	87.74 221	86.08 259	92.70 125	94.02 231	84.43 98	89.27 373	95.87 170	73.62 398	84.43 289	94.33 192	78.48 157	98.86 95	70.27 372	94.45 169	94.81 253
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
mamba_0404		90.73 128	90.08 134	92.69 126	95.00 167	83.13 141	94.32 196	95.00 234	85.41 199	89.84 159	95.35 143	76.13 182	97.98 190	85.46 193	94.18 174	96.95 155

baseline		92.39 98	92.29 96	92.69 126	94.46 208	81.77 185	94.14 205	96.27 128	89.22 80	91.88 121	96.00 113	82.35 103	97.99 188	91.05 115	95.27 150	98.30 51

MSLP-MVS++		93.72 60	94.08 49	92.65 128	97.31 70	83.43 129	95.79 90	97.33 28	90.03 47	93.58 72	96.96 69	84.87 69	97.76 204	92.19 88	98.66 41	96.76 167

EC-MVSNet		93.44 69	93.71 65	92.63 129	95.21 155	82.43 169	97.27 10	96.71 94	90.57 33	92.88 87	95.80 126	83.16 90	98.16 167	93.68 53	98.14 68	97.31 123

ab-mvs		89.41 173	88.35 185	92.60 130	95.15 160	82.65 166	92.20 303	95.60 192	83.97 236	88.55 181	93.70 225	74.16 217	98.21 165	82.46 238	89.37 262	96.94 157

LS3D		87.89 216	86.32 248	92.59 131	96.07 113	82.92 154	95.23 127	94.92 241	75.66 376	82.89 325	95.98 115	72.48 244	99.21 49	68.43 386	95.23 151	95.64 220

Anonymous20240529		88.09 212	86.59 237	92.58 132	96.53 92	81.92 183	95.99 74	95.84 172	74.11 393	89.06 173	95.21 153	61.44 361	98.81 103	83.67 221	87.47 293	97.01 151

fmvsm_s_conf0.5_n_3		94.49 27	95.13 12	92.56 133	95.49 143	81.10 208	95.93 80	97.16 45	92.96 4	97.39 10	98.13 6	83.63 83	98.80 104	97.89 3	97.61 92	97.78 101

CPTT-MVS		91.99 101	91.80 101	92.55 134	98.24 33	81.98 180	96.76 31	96.49 111	81.89 291	90.24 151	96.44 95	78.59 153	98.61 126	89.68 134	97.85 82	97.06 145

114514_t		89.51 168	88.50 181	92.54 135	98.11 38	81.99 179	95.16 137	96.36 120	70.19 420	85.81 242	95.25 149	76.70 177	98.63 123	82.07 248	96.86 110	97.00 152

PAPM_NR		91.22 117	90.78 122	92.52 136	97.60 61	81.46 194	94.37 193	96.24 135	86.39 171	87.41 205	94.80 171	82.06 114	98.48 134	82.80 233	95.37 146	97.61 111

DeepPCF-MVS	89.96 1	94.20 41	94.77 25	92.49 137	96.52 93	80.00 244	94.00 222	97.08 53	90.05 46	95.65 39	97.29 50	89.66 13	98.97 81	93.95 50	98.71 32	98.50 28

mamba_test_0407		90.47 140	89.80 144	92.46 138	94.76 183	82.66 164	93.98 224	95.00 234	85.41 199	88.96 175	95.35 143	76.13 182	97.88 199	85.46 193	93.15 199	96.85 164

IS-MVSNet		91.43 112	91.09 115	92.46 138	95.87 125	81.38 197	96.95 20	93.69 296	89.72 63	89.50 165	95.98 115	78.57 154	97.77 203	83.02 227	96.50 120	98.22 66

API-MVS		90.66 133	90.07 135	92.45 140	96.36 98	84.57 89	96.06 68	95.22 222	82.39 274	89.13 170	94.27 198	80.32 129	98.46 138	80.16 284	96.71 114	94.33 276

xiu_mvs_v1_base_debu		90.64 134	90.05 136	92.40 141	93.97 237	84.46 95	93.32 254	95.46 201	85.17 204	92.25 108	94.03 203	70.59 266	98.57 129	90.97 116	94.67 160	94.18 279

xiu_mvs_v1_base		90.64 134	90.05 136	92.40 141	93.97 237	84.46 95	93.32 254	95.46 201	85.17 204	92.25 108	94.03 203	70.59 266	98.57 129	90.97 116	94.67 160	94.18 279

xiu_mvs_v1_base_debi		90.64 134	90.05 136	92.40 141	93.97 237	84.46 95	93.32 254	95.46 201	85.17 204	92.25 108	94.03 203	70.59 266	98.57 129	90.97 116	94.67 160	94.18 279

fmvsm_s_conf0.5_n_2		93.47 65	93.83 56	92.39 144	95.36 146	81.19 204	95.20 134	96.56 105	90.37 36	97.13 14	98.03 26	77.47 169	98.96 83	97.79 5	96.58 117	97.03 148

fmvsm_s_conf0.1_n_2		93.16 82	93.42 71	92.37 145	94.62 194	81.13 206	95.23 127	95.89 168	90.30 40	96.74 24	98.02 27	76.14 181	98.95 85	97.64 6	96.21 126	97.03 148

AdaColmap		89.89 158	89.07 165	92.37 145	97.41 67	83.03 149	94.42 186	95.92 163	82.81 268	86.34 231	94.65 180	73.89 222	99.02 67	80.69 275	95.51 139	95.05 239

CNLPA		89.07 184	87.98 196	92.34 147	96.87 79	84.78 84	94.08 213	93.24 302	81.41 305	84.46 287	95.13 158	75.57 196	96.62 298	77.21 316	93.84 180	95.61 223

fmvsm_s_conf0.5_n_4		93.86 55	94.37 34	92.33 148	95.13 161	80.95 213	95.64 105	96.97 59	89.60 66	96.85 20	97.77 35	83.08 93	98.92 89	97.49 7	96.78 112	97.13 140

ET-MVSNet_ETH3D		87.51 235	85.91 267	92.32 149	93.70 254	83.93 113	92.33 298	90.94 371	84.16 231	72.09 419	92.52 261	69.90 277	95.85 345	89.20 140	88.36 280	97.17 135

Anonymous202405211		87.68 222	86.13 255	92.31 150	96.66 84	80.74 220	94.87 153	91.49 356	80.47 319	89.46 166	95.44 139	54.72 405	98.23 162	82.19 244	89.89 252	97.97 85

CHOSEN 1792x2688		88.84 190	87.69 202	92.30 151	96.14 104	81.42 196	90.01 360	95.86 171	74.52 389	87.41 205	93.94 211	75.46 197	98.36 151	80.36 280	95.53 138	97.12 141

HY-MVS	83.01 12	89.03 186	87.94 198	92.29 152	94.86 178	82.77 156	92.08 308	94.49 260	81.52 304	86.93 212	92.79 254	78.32 159	98.23 162	79.93 286	90.55 239	95.88 209

CDS-MVSNet		89.45 171	88.51 180	92.29 152	93.62 257	83.61 126	93.01 273	94.68 257	81.95 286	87.82 198	93.24 237	78.69 151	96.99 279	80.34 281	93.23 197	96.28 187
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PAPR		90.02 151	89.27 161	92.29 152	95.78 127	80.95 213	92.68 285	96.22 137	81.91 288	86.66 222	93.75 223	82.23 108	98.44 144	79.40 296	94.79 157	97.48 118

mvsmamba		90.33 141	89.69 146	92.25 155	95.17 157	81.64 187	95.27 125	93.36 301	84.88 216	89.51 163	94.27 198	69.29 291	97.42 238	89.34 138	96.12 129	97.68 107

PLC	84.53 7	89.06 185	88.03 194	92.15 156	97.27 73	82.69 163	94.29 197	95.44 206	79.71 328	84.01 303	94.18 201	76.68 178	98.75 109	77.28 315	93.41 191	95.02 240
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EPP-MVSNet		91.70 109	91.56 105	92.13 157	95.88 123	80.50 227	97.33 8	95.25 219	86.15 177	89.76 161	95.60 134	83.42 86	98.32 158	87.37 165	93.25 196	97.56 115

patch_mono-2		93.74 59	94.32 35	92.01 158	97.54 62	78.37 286	93.40 250	97.19 39	88.02 124	94.99 49	97.21 55	88.35 21	98.44 144	94.07 49	98.09 71	99.23 1

原ACMM1				92.01 158	97.34 69	81.05 209		96.81 81	78.89 339	90.45 148	95.92 118	82.65 99	98.84 99	80.68 276	98.26 59	96.14 194

UniMVSNet (Re)		89.80 161	89.07 165	92.01 158	93.60 258	84.52 92	94.78 161	97.47 13	89.26 79	86.44 228	92.32 267	82.10 112	97.39 249	84.81 201	80.84 369	94.12 283

MG-MVS		91.77 106	91.70 104	92.00 161	97.08 76	80.03 242	93.60 243	95.18 223	87.85 133	90.89 142	96.47 94	82.06 114	98.36 151	85.07 196	97.04 103	97.62 110

EIA-MVS		91.95 102	91.94 99	91.98 162	95.16 158	80.01 243	95.36 115	96.73 91	88.44 109	89.34 167	92.16 272	83.82 82	98.45 142	89.35 137	97.06 102	97.48 118

PVSNet_Blended		90.73 128	90.32 127	91.98 162	96.12 106	81.25 200	92.55 290	96.83 77	82.04 284	89.10 171	92.56 260	81.04 125	98.85 97	86.72 175	95.91 131	95.84 211

guyue		91.12 120	90.84 120	91.96 164	94.59 196	80.57 225	94.87 153	93.71 295	88.96 92	91.14 138	95.22 150	73.22 234	97.76 204	92.01 96	93.81 181	97.54 117

PS-MVSNAJ		91.18 118	90.92 117	91.96 164	95.26 153	82.60 168	92.09 307	95.70 183	86.27 173	91.84 123	92.46 262	79.70 138	98.99 76	89.08 141	95.86 132	94.29 277

TAMVS		89.21 179	88.29 189	91.96 164	93.71 252	82.62 167	93.30 258	94.19 274	82.22 279	87.78 199	93.94 211	78.83 148	96.95 282	77.70 311	92.98 202	96.32 184

SDMVSNet		90.19 145	89.61 149	91.93 167	96.00 116	83.09 146	92.89 280	95.98 158	88.73 99	86.85 218	95.20 154	72.09 249	97.08 271	88.90 144	89.85 254	95.63 221

FA-MVS(test-final)		89.66 163	88.91 170	91.93 167	94.57 200	80.27 231	91.36 324	94.74 254	84.87 217	89.82 160	92.61 259	74.72 207	98.47 137	83.97 215	93.53 186	97.04 147

MVS_Test		91.31 115	91.11 113	91.93 167	94.37 214	80.14 235	93.46 248	95.80 174	86.46 169	91.35 136	93.77 221	82.21 109	98.09 179	87.57 161	94.95 154	97.55 116

NR-MVSNet		88.58 200	87.47 208	91.93 167	93.04 278	84.16 107	94.77 162	96.25 134	89.05 86	80.04 364	93.29 235	79.02 147	97.05 276	81.71 259	80.05 379	94.59 260

HyFIR lowres test		88.09 212	86.81 225	91.93 167	96.00 116	80.63 222	90.01 360	95.79 175	73.42 400	87.68 201	92.10 278	73.86 223	97.96 191	80.75 274	91.70 222	97.19 134

GeoE		90.05 150	89.43 154	91.90 172	95.16 158	80.37 230	95.80 89	94.65 258	83.90 237	87.55 204	94.75 172	78.18 160	97.62 217	81.28 264	93.63 183	97.71 106

thisisatest0530		88.67 195	87.61 204	91.86 173	94.87 177	80.07 238	94.63 171	89.90 394	84.00 235	88.46 183	93.78 220	66.88 315	98.46 138	83.30 223	92.65 209	97.06 145

xiu_mvs_v2_base		91.13 119	90.89 119	91.86 173	94.97 169	82.42 170	92.24 301	95.64 190	86.11 181	91.74 128	93.14 241	79.67 141	98.89 91	89.06 142	95.46 143	94.28 278

DU-MVS		89.34 178	88.50 181	91.85 175	93.04 278	83.72 119	94.47 182	96.59 102	89.50 68	86.46 225	93.29 235	77.25 171	97.23 261	84.92 198	81.02 365	94.59 260

AstraMVS		90.69 130	90.30 128	91.84 176	93.81 244	79.85 249	94.76 163	92.39 325	88.96 92	91.01 141	95.87 122	70.69 264	97.94 194	92.49 75	92.70 208	97.73 104

OPM-MVS		90.12 146	89.56 150	91.82 177	93.14 271	83.90 114	94.16 204	95.74 179	88.96 92	87.86 194	95.43 141	72.48 244	97.91 197	88.10 155	90.18 246	93.65 314
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HQP_MVS		90.60 137	90.19 130	91.82 177	94.70 190	82.73 160	95.85 86	96.22 137	90.81 24	86.91 214	94.86 167	74.23 213	98.12 169	88.15 151	89.99 248	94.63 257

UniMVSNet_NR-MVSNet		89.92 157	89.29 159	91.81 179	93.39 264	83.72 119	94.43 185	97.12 50	89.80 57	86.46 225	93.32 232	83.16 90	97.23 261	84.92 198	81.02 365	94.49 270

diffmvs		91.37 114	91.23 111	91.77 180	93.09 274	80.27 231	92.36 295	95.52 198	87.03 153	91.40 135	94.93 162	80.08 132	97.44 236	92.13 91	94.56 165	97.61 111
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
1112_ss		88.42 201	87.33 211	91.72 181	94.92 173	80.98 211	92.97 277	94.54 259	78.16 356	83.82 306	93.88 216	78.78 150	97.91 197	79.45 292	89.41 261	96.26 188

Fast-Effi-MVS+		89.41 173	88.64 176	91.71 182	94.74 184	80.81 218	93.54 244	95.10 227	83.11 260	86.82 220	90.67 332	79.74 137	97.75 208	80.51 279	93.55 185	96.57 177

WTY-MVS		89.60 165	88.92 169	91.67 183	95.47 144	81.15 205	92.38 294	94.78 252	83.11 260	89.06 173	94.32 193	78.67 152	96.61 301	81.57 260	90.89 235	97.24 131

TAPA-MVS	84.62 6	88.16 210	87.01 220	91.62 184	96.64 85	80.65 221	94.39 189	96.21 140	76.38 369	86.19 235	95.44 139	79.75 136	98.08 181	62.75 416	95.29 148	96.13 195
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
VPA-MVSNet		89.62 164	88.96 167	91.60 185	93.86 241	82.89 155	95.46 112	97.33 28	87.91 128	88.43 184	93.31 233	74.17 216	97.40 246	87.32 166	82.86 340	94.52 265

FE-MVS		87.40 240	86.02 261	91.57 186	94.56 201	79.69 253	90.27 347	93.72 294	80.57 317	88.80 177	91.62 298	65.32 331	98.59 128	74.97 341	94.33 172	96.44 180

XVG-OURS		89.40 175	88.70 175	91.52 187	94.06 229	81.46 194	91.27 328	96.07 151	86.14 178	88.89 176	95.77 128	68.73 300	97.26 258	87.39 164	89.96 250	95.83 212

hse-mvs2		89.88 159	89.34 157	91.51 188	94.83 180	81.12 207	93.94 226	93.91 287	89.80 57	93.08 82	93.60 226	75.77 189	97.66 212	92.07 92	77.07 399	95.74 216

TranMVSNet+NR-MVSNet		88.84 190	87.95 197	91.49 189	92.68 291	83.01 151	94.92 150	96.31 123	89.88 51	85.53 251	93.85 218	76.63 179	96.96 281	81.91 252	79.87 382	94.50 268

AUN-MVS		87.78 220	86.54 240	91.48 190	94.82 181	81.05 209	93.91 230	93.93 284	83.00 263	86.93 212	93.53 227	69.50 285	97.67 210	86.14 181	77.12 398	95.73 218

XVG-OURS-SEG-HR		89.95 155	89.45 152	91.47 191	94.00 235	81.21 203	91.87 312	96.06 153	85.78 185	88.55 181	95.73 130	74.67 208	97.27 256	88.71 147	89.64 259	95.91 206

MVS		87.44 238	86.10 258	91.44 192	92.61 292	83.62 124	92.63 287	95.66 187	67.26 426	81.47 342	92.15 273	77.95 163	98.22 164	79.71 288	95.48 141	92.47 357

F-COLMAP		87.95 215	86.80 226	91.40 193	96.35 99	80.88 216	94.73 165	95.45 204	79.65 329	82.04 337	94.61 181	71.13 256	98.50 132	76.24 328	91.05 233	94.80 254

dcpmvs_2		93.49 64	94.19 46	91.38 194	97.69 59	76.78 323	94.25 199	96.29 124	88.33 112	94.46 52	96.88 72	88.07 25	98.64 121	93.62 55	98.09 71	98.73 19

thisisatest0515		87.33 243	85.99 262	91.37 195	93.49 260	79.55 254	90.63 342	89.56 402	80.17 321	87.56 203	90.86 322	67.07 312	98.28 160	81.50 261	93.02 201	96.29 186

HQP-MVS		89.80 161	89.28 160	91.34 196	94.17 224	81.56 188	94.39 189	96.04 154	88.81 95	85.43 260	93.97 210	73.83 224	97.96 191	87.11 170	89.77 257	94.50 268

fmvsm_s_conf0.5_n_7		93.15 83	93.76 62	91.31 197	94.42 212	79.48 256	94.52 177	97.14 48	89.33 75	94.17 58	98.09 16	81.83 118	97.49 228	96.33 23	98.02 75	96.95 155

RRT-MVS		90.85 124	90.70 123	91.30 198	94.25 220	76.83 322	94.85 156	96.13 145	89.04 87	90.23 152	94.88 165	70.15 275	98.72 113	91.86 104	94.88 155	98.34 44

FMVSNet3		87.40 240	86.11 257	91.30 198	93.79 247	83.64 123	94.20 203	94.81 250	83.89 238	84.37 290	91.87 289	68.45 303	96.56 306	78.23 306	85.36 310	93.70 313

FMVSNet2		87.19 253	85.82 270	91.30 198	94.01 232	83.67 121	94.79 160	94.94 236	83.57 246	83.88 305	92.05 282	66.59 320	96.51 310	77.56 313	85.01 313	93.73 311

RPMNet		83.95 330	81.53 341	91.21 201	90.58 369	79.34 262	85.24 419	96.76 86	71.44 414	85.55 249	82.97 426	70.87 261	98.91 90	61.01 420	89.36 263	95.40 227

IB-MVS	80.51 15	85.24 307	83.26 325	91.19 202	92.13 304	79.86 248	91.75 315	91.29 361	83.28 257	80.66 354	88.49 379	61.28 363	98.46 138	80.99 270	79.46 386	95.25 233
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
CLD-MVS		89.47 170	88.90 171	91.18 203	94.22 222	82.07 178	92.13 305	96.09 149	87.90 129	85.37 266	92.45 263	74.38 211	97.56 222	87.15 168	90.43 241	93.93 292
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
LPG-MVS_test		89.45 171	88.90 171	91.12 204	94.47 206	81.49 192	95.30 120	96.14 142	86.73 162	85.45 257	95.16 156	69.89 278	98.10 171	87.70 159	89.23 266	93.77 307

LGP-MVS_train				91.12 204	94.47 206	81.49 192		96.14 142	86.73 162	85.45 257	95.16 156	69.89 278	98.10 171	87.70 159	89.23 266	93.77 307

ACMM	84.12 9	89.14 180	88.48 184	91.12 204	94.65 193	81.22 202	95.31 118	96.12 146	85.31 203	85.92 240	94.34 191	70.19 274	98.06 183	85.65 189	88.86 271	94.08 287
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tttt0517		88.61 197	87.78 201	91.11 207	94.96 170	77.81 302	95.35 116	89.69 397	85.09 211	88.05 192	94.59 184	66.93 313	98.48 134	83.27 224	92.13 220	97.03 148

GBi-Net		87.26 245	85.98 263	91.08 208	94.01 232	83.10 143	95.14 138	94.94 236	83.57 246	84.37 290	91.64 294	66.59 320	96.34 323	78.23 306	85.36 310	93.79 302

test1		87.26 245	85.98 263	91.08 208	94.01 232	83.10 143	95.14 138	94.94 236	83.57 246	84.37 290	91.64 294	66.59 320	96.34 323	78.23 306	85.36 310	93.79 302

FMVSNet1		85.85 292	84.11 312	91.08 208	92.81 286	83.10 143	95.14 138	94.94 236	81.64 299	82.68 327	91.64 294	59.01 385	96.34 323	75.37 335	83.78 324	93.79 302

Test_1112_low_res		87.65 224	86.51 241	91.08 208	94.94 172	79.28 266	91.77 314	94.30 269	76.04 374	83.51 316	92.37 265	77.86 166	97.73 209	78.69 301	89.13 268	96.22 189

PS-MVSNAJss		89.97 153	89.62 148	91.02 212	91.90 313	80.85 217	95.26 126	95.98 158	86.26 174	86.21 234	94.29 195	79.70 138	97.65 213	88.87 146	88.10 282	94.57 262

BH-RMVSNet		88.37 204	87.48 207	91.02 212	95.28 150	79.45 258	92.89 280	93.07 308	85.45 198	86.91 214	94.84 170	70.35 271	97.76 204	73.97 349	94.59 164	95.85 210

UniMVSNet_ETH3D		87.53 234	86.37 245	91.00 214	92.44 296	78.96 271	94.74 164	95.61 191	84.07 234	85.36 267	94.52 186	59.78 377	97.34 251	82.93 228	87.88 287	96.71 170

FIs		90.51 139	90.35 126	90.99 215	93.99 236	80.98 211	95.73 96	97.54 6	89.15 83	86.72 221	94.68 175	81.83 118	97.24 260	85.18 195	88.31 281	94.76 255

ACMP	84.23 8	89.01 188	88.35 185	90.99 215	94.73 185	81.27 199	95.07 141	95.89 168	86.48 167	83.67 311	94.30 194	69.33 287	97.99 188	87.10 172	88.55 273	93.72 312
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Anonymous20231211		86.59 275	85.13 290	90.98 217	96.52 93	81.50 190	96.14 59	96.16 141	73.78 396	83.65 312	92.15 273	63.26 347	97.37 250	82.82 232	81.74 354	94.06 288

icg_test_0403		89.97 153	89.64 147	90.96 218	93.72 249	77.75 307	93.00 274	95.34 215	85.53 195	88.77 178	94.49 187	78.49 156	97.84 200	84.75 202	92.65 209	97.28 126

sss		88.93 189	88.26 191	90.94 219	94.05 230	80.78 219	91.71 316	95.38 210	81.55 303	88.63 180	93.91 215	75.04 201	95.47 364	82.47 237	91.61 223	96.57 177

icg_test_0407		89.85 160	89.51 151	90.88 220	93.72 249	77.75 307	93.07 271	95.34 215	85.53 195	88.34 186	94.49 187	77.69 168	97.60 218	84.75 202	92.65 209	97.28 126

sd_testset		88.59 199	87.85 200	90.83 221	96.00 116	80.42 229	92.35 296	94.71 255	88.73 99	86.85 218	95.20 154	67.31 307	96.43 317	79.64 290	89.85 254	95.63 221

PVSNet_BlendedMVS		89.98 152	89.70 145	90.82 222	96.12 106	81.25 200	93.92 228	96.83 77	83.49 250	89.10 171	92.26 270	81.04 125	98.85 97	86.72 175	87.86 288	92.35 363

cascas		86.43 283	84.98 293	90.80 223	92.10 306	80.92 215	90.24 351	95.91 165	73.10 403	83.57 315	88.39 380	65.15 333	97.46 232	84.90 200	91.43 225	94.03 290

ECVR-MVS		89.09 183	88.53 179	90.77 224	95.62 137	75.89 336	96.16 55	84.22 428	87.89 131	90.20 153	96.65 84	63.19 348	98.10 171	85.90 186	96.94 105	98.33 46

GA-MVS		86.61 273	85.27 287	90.66 225	91.33 336	78.71 275	90.40 346	93.81 291	85.34 202	85.12 270	89.57 361	61.25 364	97.11 270	80.99 270	89.59 260	96.15 193

thres600view7		87.65 224	86.67 232	90.59 226	96.08 112	78.72 273	94.88 152	91.58 352	87.06 152	88.08 190	92.30 268	68.91 297	98.10 171	70.05 379	91.10 228	94.96 244

thres400		87.62 229	86.64 233	90.57 227	95.99 119	78.64 276	94.58 173	91.98 341	86.94 156	88.09 188	91.77 290	69.18 293	98.10 171	70.13 376	91.10 228	94.96 244

baseline1		88.10 211	87.28 213	90.57 227	94.96 170	80.07 238	94.27 198	91.29 361	86.74 161	87.41 205	94.00 208	76.77 176	96.20 328	80.77 273	79.31 388	95.44 225

FC-MVSNet-test		90.27 143	90.18 131	90.53 229	93.71 252	79.85 249	95.77 92	97.59 4	89.31 76	86.27 232	94.67 178	81.93 117	97.01 278	84.26 211	88.09 284	94.71 256

PAPM		86.68 272	85.39 282	90.53 229	93.05 277	79.33 265	89.79 363	94.77 253	78.82 342	81.95 338	93.24 237	76.81 174	97.30 252	66.94 396	93.16 198	94.95 248

WR-MVS		88.38 203	87.67 203	90.52 231	93.30 266	80.18 233	93.26 261	95.96 161	88.57 107	85.47 256	92.81 252	76.12 184	96.91 285	81.24 265	82.29 345	94.47 273

MVSTER		88.84 190	88.29 189	90.51 232	92.95 283	80.44 228	93.73 237	95.01 231	84.66 225	87.15 209	93.12 242	72.79 239	97.21 263	87.86 157	87.36 296	93.87 297

testdata				90.49 233	96.40 96	77.89 299		95.37 212	72.51 408	93.63 71	96.69 80	82.08 113	97.65 213	83.08 225	97.39 95	95.94 205

test1111		89.10 181	88.64 176	90.48 234	95.53 142	74.97 346	96.08 64	84.89 426	88.13 122	90.16 155	96.65 84	63.29 346	98.10 171	86.14 181	96.90 107	98.39 41

tt0805		86.92 261	85.74 276	90.48 234	92.22 300	79.98 245	95.63 106	94.88 244	83.83 240	84.74 279	92.80 253	57.61 391	97.67 210	85.48 192	84.42 317	93.79 302

jajsoiax		88.24 208	87.50 206	90.48 234	90.89 357	80.14 235	95.31 118	95.65 189	84.97 214	84.24 298	94.02 206	65.31 332	97.42 238	88.56 148	88.52 275	93.89 293

PatchMatch-RL		86.77 269	85.54 278	90.47 237	95.88 123	82.71 162	90.54 344	92.31 329	79.82 327	84.32 295	91.57 302	68.77 299	96.39 319	73.16 355	93.48 190	92.32 364

tfpn200view9		87.58 232	86.64 233	90.41 238	95.99 119	78.64 276	94.58 173	91.98 341	86.94 156	88.09 188	91.77 290	69.18 293	98.10 171	70.13 376	91.10 228	94.48 271

VPNet		88.20 209	87.47 208	90.39 239	93.56 259	79.46 257	94.04 217	95.54 196	88.67 102	86.96 211	94.58 185	69.33 287	97.15 265	84.05 214	80.53 374	94.56 263

ACMH	80.38 17	85.36 302	83.68 319	90.39 239	94.45 209	80.63 222	94.73 165	94.85 246	82.09 281	77.24 389	92.65 257	60.01 375	97.58 220	72.25 360	84.87 314	92.96 342
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thres100view900		87.63 227	86.71 229	90.38 241	96.12 106	78.55 279	95.03 144	91.58 352	87.15 149	88.06 191	92.29 269	68.91 297	98.10 171	70.13 376	91.10 228	94.48 271

mvs_tets		88.06 214	87.28 213	90.38 241	90.94 353	79.88 247	95.22 129	95.66 187	85.10 210	84.21 299	93.94 211	63.53 344	97.40 246	88.50 149	88.40 279	93.87 297

1314		87.51 235	86.57 238	90.34 243	92.42 297	79.74 252	92.63 287	95.35 214	78.35 351	80.14 361	91.62 298	74.05 218	97.15 265	81.05 266	93.53 186	94.12 283

LTVRE_ROB	82.13 13	86.26 286	84.90 296	90.34 243	94.44 210	81.50 190	92.31 300	94.89 242	83.03 262	79.63 371	92.67 256	69.69 281	97.79 202	71.20 365	86.26 305	91.72 374
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
test_djsdf		89.03 186	88.64 176	90.21 245	90.74 364	79.28 266	95.96 77	95.90 166	84.66 225	85.33 268	92.94 247	74.02 219	97.30 252	89.64 135	88.53 274	94.05 289

v2v482		87.84 217	87.06 217	90.17 246	90.99 349	79.23 269	94.00 222	95.13 224	84.87 217	85.53 251	92.07 281	74.45 210	97.45 233	84.71 206	81.75 353	93.85 300

pmmvs4		85.43 300	83.86 317	90.16 247	90.02 382	82.97 153	90.27 347	92.67 320	75.93 375	80.73 352	91.74 292	71.05 257	95.73 353	78.85 300	83.46 331	91.78 373

V42		87.68 222	86.86 222	90.15 248	90.58 369	80.14 235	94.24 201	95.28 218	83.66 244	85.67 246	91.33 304	74.73 206	97.41 244	84.43 210	81.83 351	92.89 345

MSDG		84.86 315	83.09 328	90.14 249	93.80 245	80.05 240	89.18 376	93.09 307	78.89 339	78.19 381	91.91 287	65.86 330	97.27 256	68.47 385	88.45 277	93.11 337

sc_t1		81.53 354	78.67 375	90.12 250	90.78 361	78.64 276	93.91 230	90.20 384	68.42 423	80.82 351	89.88 354	46.48 428	96.76 290	76.03 331	71.47 413	94.96 244

anonymousdsp		87.84 217	87.09 216	90.12 250	89.13 393	80.54 226	94.67 169	95.55 194	82.05 282	83.82 306	92.12 275	71.47 254	97.15 265	87.15 168	87.80 291	92.67 351

thres200		87.21 251	86.24 252	90.12 250	95.36 146	78.53 280	93.26 261	92.10 335	86.42 170	88.00 193	91.11 315	69.24 292	98.00 187	69.58 380	91.04 234	93.83 301

CR-MVSNet		85.35 303	83.76 318	90.12 250	90.58 369	79.34 262	85.24 419	91.96 343	78.27 353	85.55 249	87.87 390	71.03 258	95.61 356	73.96 350	89.36 263	95.40 227

v1144		87.61 230	86.79 227	90.06 254	91.01 348	79.34 262	93.95 225	95.42 209	83.36 255	85.66 247	91.31 307	74.98 202	97.42 238	83.37 222	82.06 347	93.42 323

XXY-MVS		87.65 224	86.85 223	90.03 255	92.14 303	80.60 224	93.76 236	95.23 220	82.94 265	84.60 281	94.02 206	74.27 212	95.49 363	81.04 267	83.68 327	94.01 291

Vis-MVSNet (Re-imp)		89.59 166	89.44 153	90.03 255	95.74 128	75.85 337	95.61 107	90.80 375	87.66 141	87.83 197	95.40 142	76.79 175	96.46 315	78.37 302	96.73 113	97.80 99

test2506		87.21 251	86.28 250	90.02 257	95.62 137	73.64 362	96.25 50	71.38 451	87.89 131	90.45 148	96.65 84	55.29 402	98.09 179	86.03 185	96.94 105	98.33 46

BH-untuned		88.60 198	88.13 193	90.01 258	95.24 154	78.50 282	93.29 259	94.15 277	84.75 222	84.46 287	93.40 229	75.76 191	97.40 246	77.59 312	94.52 167	94.12 283

v1192		87.25 247	86.33 247	90.00 259	90.76 363	79.04 270	93.80 234	95.48 199	82.57 272	85.48 255	91.18 311	73.38 233	97.42 238	82.30 241	82.06 347	93.53 317

v7n		86.81 264	85.76 274	89.95 260	90.72 365	79.25 268	95.07 141	95.92 163	84.45 228	82.29 331	90.86 322	72.60 243	97.53 224	79.42 295	80.52 375	93.08 339

testing91		87.11 256	86.18 253	89.92 261	94.43 211	75.38 345	91.53 321	92.27 331	86.48 167	86.50 223	90.24 340	61.19 367	97.53 224	82.10 246	90.88 236	96.84 165

ICG_test_0404		87.60 231	86.84 224	89.89 262	93.72 249	77.75 307	88.56 385	95.34 215	85.53 195	79.98 365	94.49 187	66.54 323	94.64 377	84.75 202	92.65 209	97.28 126

v8		87.50 237	86.71 229	89.89 262	91.37 333	79.40 259	94.50 178	95.38 210	84.81 220	83.60 314	91.33 304	76.05 185	97.42 238	82.84 231	80.51 376	92.84 347

v10		87.25 247	86.38 244	89.85 264	91.19 339	79.50 255	94.48 179	95.45 204	83.79 242	83.62 313	91.19 309	75.13 199	97.42 238	81.94 251	80.60 371	92.63 353

baseline2		86.50 279	85.39 282	89.84 265	91.12 344	76.70 325	91.88 311	88.58 406	82.35 277	79.95 366	90.95 320	73.42 231	97.63 216	80.27 283	89.95 251	95.19 234

pm-mvs1		86.61 273	85.54 278	89.82 266	91.44 328	80.18 233	95.28 124	94.85 246	83.84 239	81.66 340	92.62 258	72.45 246	96.48 312	79.67 289	78.06 391	92.82 348

TR-MVS		86.78 266	85.76 274	89.82 266	94.37 214	78.41 284	92.47 291	92.83 314	81.11 313	86.36 229	92.40 264	68.73 300	97.48 229	73.75 353	89.85 254	93.57 316

ACMH+	81.04 14	85.05 310	83.46 322	89.82 266	94.66 192	79.37 260	94.44 184	94.12 280	82.19 280	78.04 383	92.82 251	58.23 388	97.54 223	73.77 352	82.90 339	92.54 354

EI-MVSNet		89.10 181	88.86 173	89.80 269	91.84 315	78.30 288	93.70 240	95.01 231	85.73 187	87.15 209	95.28 147	79.87 135	97.21 263	83.81 218	87.36 296	93.88 296

v144192		87.19 253	86.35 246	89.74 270	90.64 367	78.24 290	93.92 228	95.43 207	81.93 287	85.51 253	91.05 318	74.21 215	97.45 233	82.86 230	81.56 355	93.53 317

COLMAP_ROB	80.39 16	83.96 329	82.04 338	89.74 270	95.28 150	79.75 251	94.25 199	92.28 330	75.17 382	78.02 384	93.77 221	58.60 387	97.84 200	65.06 407	85.92 306	91.63 376
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
SCA		86.32 285	85.18 289	89.73 272	92.15 302	76.60 326	91.12 332	91.69 348	83.53 249	85.50 254	88.81 373	66.79 316	96.48 312	76.65 321	90.35 243	96.12 196

IterMVS-LS		88.36 205	87.91 199	89.70 273	93.80 245	78.29 289	93.73 237	95.08 229	85.73 187	84.75 278	91.90 288	79.88 134	96.92 284	83.83 217	82.51 341	93.89 293
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing11		86.44 282	85.35 285	89.69 274	94.29 219	75.40 344	91.30 326	90.53 379	84.76 221	85.06 272	90.13 346	58.95 386	97.45 233	82.08 247	91.09 232	96.21 191

testing99		86.72 270	85.73 277	89.69 274	94.23 221	74.91 348	91.35 325	90.97 369	86.14 178	86.36 229	90.22 341	59.41 380	97.48 229	82.24 243	90.66 238	96.69 172

v1921920		86.97 260	86.06 260	89.69 274	90.53 372	78.11 293	93.80 234	95.43 207	81.90 289	85.33 268	91.05 318	72.66 240	97.41 244	82.05 249	81.80 352	93.53 317

VortexMVS		88.42 201	88.01 195	89.63 277	93.89 240	78.82 272	93.82 233	95.47 200	86.67 164	84.53 285	91.99 284	72.62 242	96.65 296	89.02 143	84.09 321	93.41 324

Fast-Effi-MVS+-dtu		87.44 238	86.72 228	89.63 277	92.04 307	77.68 311	94.03 218	93.94 283	85.81 184	82.42 330	91.32 306	70.33 272	97.06 274	80.33 282	90.23 245	94.14 282

v1240		86.78 266	85.85 269	89.56 279	90.45 374	77.79 304	93.61 242	95.37 212	81.65 298	85.43 260	91.15 313	71.50 253	97.43 237	81.47 262	82.05 349	93.47 321

Effi-MVS+-dtu		88.65 196	88.35 185	89.54 280	93.33 265	76.39 330	94.47 182	94.36 267	87.70 138	85.43 260	89.56 362	73.45 229	97.26 258	85.57 191	91.28 227	94.97 241

AllTest		83.42 336	81.39 342	89.52 281	95.01 164	77.79 304	93.12 265	90.89 373	77.41 360	76.12 398	93.34 230	54.08 408	97.51 226	68.31 387	84.27 319	93.26 327

TestCases				89.52 281	95.01 164	77.79 304		90.89 373	77.41 360	76.12 398	93.34 230	54.08 408	97.51 226	68.31 387	84.27 319	93.26 327

mvs_anonymous		89.37 177	89.32 158	89.51 283	93.47 261	74.22 355	91.65 319	94.83 248	82.91 266	85.45 257	93.79 219	81.23 124	96.36 322	86.47 177	94.09 175	97.94 87

XVG-ACMP-BASELINE		86.00 288	84.84 298	89.45 284	91.20 338	78.00 295	91.70 317	95.55 194	85.05 212	82.97 324	92.25 271	54.49 406	97.48 229	82.93 228	87.45 295	92.89 345

testing222		84.84 316	83.32 323	89.43 285	94.15 227	75.94 335	91.09 333	89.41 404	84.90 215	85.78 243	89.44 363	52.70 413	96.28 326	70.80 371	91.57 224	96.07 200

MVP-Stereo		85.97 289	84.86 297	89.32 286	90.92 355	82.19 176	92.11 306	94.19 274	78.76 344	78.77 380	91.63 297	68.38 304	96.56 306	75.01 340	93.95 177	89.20 414
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PatchmatchNet		85.85 292	84.70 300	89.29 287	91.76 319	75.54 341	88.49 386	91.30 360	81.63 300	85.05 273	88.70 377	71.71 250	96.24 327	74.61 345	89.05 269	96.08 199
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v148		87.04 258	86.32 248	89.21 288	90.94 353	77.26 316	93.71 239	94.43 262	84.84 219	84.36 293	90.80 326	76.04 186	97.05 276	82.12 245	79.60 385	93.31 326

tfpnnormal		84.72 318	83.23 326	89.20 289	92.79 287	80.05 240	94.48 179	95.81 173	82.38 275	81.08 348	91.21 308	69.01 296	96.95 282	61.69 418	80.59 372	90.58 401

cl22		86.78 266	85.98 263	89.18 290	92.34 298	77.62 312	90.84 338	94.13 279	81.33 307	83.97 304	90.15 345	73.96 220	96.60 303	84.19 212	82.94 336	93.33 325

BH-w/o		87.57 233	87.05 218	89.12 291	94.90 176	77.90 298	92.41 292	93.51 298	82.89 267	83.70 310	91.34 303	75.75 192	97.07 273	75.49 333	93.49 188	92.39 361

WR-MVS_H		87.80 219	87.37 210	89.10 292	93.23 267	78.12 292	95.61 107	97.30 32	87.90 129	83.72 309	92.01 283	79.65 142	96.01 337	76.36 325	80.54 373	93.16 335

miper_enhance_ethall		86.90 262	86.18 253	89.06 293	91.66 324	77.58 313	90.22 353	94.82 249	79.16 335	84.48 286	89.10 367	79.19 146	96.66 295	84.06 213	82.94 336	92.94 343

c3_l		87.14 255	86.50 242	89.04 294	92.20 301	77.26 316	91.22 331	94.70 256	82.01 285	84.34 294	90.43 337	78.81 149	96.61 301	83.70 220	81.09 362	93.25 329

miper_ehance_all_eth		87.22 250	86.62 236	89.02 295	92.13 304	77.40 315	90.91 337	94.81 250	81.28 308	84.32 295	90.08 348	79.26 144	96.62 298	83.81 218	82.94 336	93.04 340

gg-mvs-nofinetune		81.77 348	79.37 363	88.99 296	90.85 359	77.73 310	86.29 411	79.63 439	74.88 387	83.19 323	69.05 442	60.34 372	96.11 332	75.46 334	94.64 163	93.11 337

ETVMVS		84.43 323	82.92 332	88.97 297	94.37 214	74.67 349	91.23 330	88.35 408	83.37 254	86.06 238	89.04 368	55.38 400	95.67 355	67.12 394	91.34 226	96.58 176

pmmvs6		83.42 336	81.60 340	88.87 298	88.01 408	77.87 300	94.96 147	94.24 273	74.67 388	78.80 379	91.09 316	60.17 374	96.49 311	77.06 320	75.40 405	92.23 366

test_cas_vis1_n_1920		88.83 193	88.85 174	88.78 299	91.15 343	76.72 324	93.85 232	94.93 240	83.23 259	92.81 91	96.00 113	61.17 368	94.45 378	91.67 107	94.84 156	95.17 235

MIMVSNet		82.59 342	80.53 347	88.76 300	91.51 326	78.32 287	86.57 410	90.13 387	79.32 331	80.70 353	88.69 378	52.98 412	93.07 403	66.03 402	88.86 271	94.90 249

cl____		86.52 278	85.78 271	88.75 301	92.03 308	76.46 328	90.74 339	94.30 269	81.83 294	83.34 320	90.78 327	75.74 194	96.57 304	81.74 257	81.54 356	93.22 331

DIV-MVS_self_test		86.53 277	85.78 271	88.75 301	92.02 309	76.45 329	90.74 339	94.30 269	81.83 294	83.34 320	90.82 325	75.75 192	96.57 304	81.73 258	81.52 357	93.24 330

CP-MVSNet		87.63 227	87.26 215	88.74 303	93.12 272	76.59 327	95.29 122	96.58 103	88.43 110	83.49 317	92.98 246	75.28 198	95.83 346	78.97 298	81.15 361	93.79 302

eth_miper_zixun_eth		86.50 279	85.77 273	88.68 304	91.94 310	75.81 338	90.47 345	94.89 242	82.05 282	84.05 301	90.46 336	75.96 187	96.77 289	82.76 234	79.36 387	93.46 322

CHOSEN 280x420		85.15 308	83.99 315	88.65 305	92.47 294	78.40 285	79.68 441	92.76 317	74.90 386	81.41 344	89.59 360	69.85 280	95.51 360	79.92 287	95.29 148	92.03 369

PS-CasMVS		87.32 244	86.88 221	88.63 306	92.99 281	76.33 332	95.33 117	96.61 101	88.22 118	83.30 322	93.07 244	73.03 237	95.79 350	78.36 303	81.00 367	93.75 309

TransMVSNet (Re)		84.43 323	83.06 330	88.54 307	91.72 320	78.44 283	95.18 135	92.82 316	82.73 270	79.67 370	92.12 275	73.49 228	95.96 339	71.10 369	68.73 423	91.21 388

tt0320-xc		79.63 377	76.66 386	88.52 308	91.03 347	78.72 273	93.00 274	89.53 403	66.37 427	76.11 400	87.11 401	46.36 430	95.32 368	72.78 357	67.67 424	91.51 380

EG-PatchMatch MVS		82.37 344	80.34 350	88.46 309	90.27 376	79.35 261	92.80 284	94.33 268	77.14 364	73.26 416	90.18 344	47.47 425	96.72 291	70.25 373	87.32 298	89.30 411

PEN-MVS		86.80 265	86.27 251	88.40 310	92.32 299	75.71 340	95.18 135	96.38 118	87.97 126	82.82 326	93.15 240	73.39 232	95.92 341	76.15 329	79.03 390	93.59 315

Baseline_NR-MVSNet		87.07 257	86.63 235	88.40 310	91.44 328	77.87 300	94.23 202	92.57 322	84.12 233	85.74 245	92.08 279	77.25 171	96.04 333	82.29 242	79.94 380	91.30 386

UBG		85.51 298	84.57 305	88.35 312	94.21 223	71.78 386	90.07 358	89.66 399	82.28 278	85.91 241	89.01 369	61.30 362	97.06 274	76.58 324	92.06 221	96.22 189

D2MVS		85.90 290	85.09 291	88.35 312	90.79 360	77.42 314	91.83 313	95.70 183	80.77 316	80.08 363	90.02 350	66.74 318	96.37 320	81.88 253	87.97 286	91.26 387

pmmvs5		84.21 325	82.84 335	88.34 314	88.95 395	76.94 320	92.41 292	91.91 345	75.63 377	80.28 358	91.18 311	64.59 338	95.57 357	77.09 319	83.47 330	92.53 355

mamv4		90.92 122	91.78 102	88.33 315	95.67 133	70.75 399	92.92 279	96.02 157	81.90 289	88.11 187	95.34 145	85.88 52	96.97 280	95.22 37	95.01 153	97.26 129

tt0320		80.13 370	77.41 379	88.29 316	90.50 373	78.02 294	93.10 268	90.71 377	66.06 430	76.75 393	86.97 402	49.56 420	95.40 365	71.65 361	71.41 414	91.46 383

LCM-MVSNet-Re		88.30 207	88.32 188	88.27 317	94.71 189	72.41 381	93.15 264	90.98 368	87.77 136	79.25 374	91.96 285	78.35 158	95.75 351	83.04 226	95.62 137	96.65 173

CostFormer		85.77 295	84.94 295	88.26 318	91.16 342	72.58 379	89.47 371	91.04 367	76.26 372	86.45 227	89.97 352	70.74 263	96.86 288	82.35 240	87.07 301	95.34 231

ITE_SJBPF				88.24 319	91.88 314	77.05 319		92.92 311	85.54 193	80.13 362	93.30 234	57.29 392	96.20 328	72.46 359	84.71 315	91.49 381

PVSNet	78.82 18	85.55 297	84.65 301	88.23 320	94.72 187	71.93 382	87.12 406	92.75 318	78.80 343	84.95 275	90.53 334	64.43 339	96.71 293	74.74 343	93.86 179	96.06 202

IterMVS-SCA-FT		85.45 299	84.53 306	88.18 321	91.71 321	76.87 321	90.19 355	92.65 321	85.40 201	81.44 343	90.54 333	66.79 316	95.00 374	81.04 267	81.05 363	92.66 352

EPNet_dtu		86.49 281	85.94 266	88.14 322	90.24 377	72.82 371	94.11 208	92.20 333	86.66 165	79.42 373	92.36 266	73.52 227	95.81 348	71.26 364	93.66 182	95.80 214
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Patchmtry		82.71 340	80.93 346	88.06 323	90.05 381	76.37 331	84.74 424	91.96 343	72.28 411	81.32 346	87.87 390	71.03 258	95.50 362	68.97 382	80.15 378	92.32 364

test_vis1_n_1920		89.39 176	89.84 142	88.04 324	92.97 282	72.64 376	94.71 167	96.03 156	86.18 176	91.94 120	96.56 92	61.63 357	95.74 352	93.42 58	95.11 152	95.74 216

DTE-MVSNet		86.11 287	85.48 280	87.98 325	91.65 325	74.92 347	94.93 149	95.75 178	87.36 146	82.26 332	93.04 245	72.85 238	95.82 347	74.04 348	77.46 396	93.20 333

PMMVS		85.71 296	84.96 294	87.95 326	88.90 396	77.09 318	88.68 383	90.06 389	72.32 410	86.47 224	90.76 328	72.15 248	94.40 380	81.78 256	93.49 188	92.36 362

GG-mvs-BLEND				87.94 327	89.73 388	77.91 297	87.80 395	78.23 444		80.58 355	83.86 419	59.88 376	95.33 367	71.20 365	92.22 219	90.60 400

MonoMVSNet		86.89 263	86.55 239	87.92 328	89.46 391	73.75 359	94.12 206	93.10 306	87.82 135	85.10 271	90.76 328	69.59 283	94.94 375	86.47 177	82.50 342	95.07 238

reproduce_monomvs		86.37 284	85.87 268	87.87 329	93.66 256	73.71 360	93.44 249	95.02 230	88.61 105	82.64 329	91.94 286	57.88 390	96.68 294	89.96 132	79.71 384	93.22 331

pmmvs-eth3d		80.97 363	78.72 374	87.74 330	84.99 426	79.97 246	90.11 357	91.65 350	75.36 379	73.51 414	86.03 409	59.45 379	93.96 390	75.17 337	72.21 410	89.29 413

MS-PatchMatch		85.05 310	84.16 310	87.73 331	91.42 331	78.51 281	91.25 329	93.53 297	77.50 359	80.15 360	91.58 300	61.99 354	95.51 360	75.69 332	94.35 171	89.16 415

mmtdpeth		85.04 312	84.15 311	87.72 332	93.11 273	75.74 339	94.37 193	92.83 314	84.98 213	89.31 168	86.41 406	61.61 359	97.14 268	92.63 74	62.11 434	90.29 402

test_0402		81.30 359	79.17 368	87.67 333	93.19 268	78.17 291	92.98 276	91.71 346	75.25 381	76.02 401	90.31 339	59.23 381	96.37 320	50.22 437	83.63 328	88.47 422

IterMVS		84.88 314	83.98 316	87.60 334	91.44 328	76.03 334	90.18 356	92.41 324	83.24 258	81.06 349	90.42 338	66.60 319	94.28 384	79.46 291	80.98 368	92.48 356
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Patchmatch-test		81.37 357	79.30 364	87.58 335	90.92 355	74.16 357	80.99 436	87.68 413	70.52 418	76.63 395	88.81 373	71.21 255	92.76 406	60.01 424	86.93 302	95.83 212

EPMVS		83.90 332	82.70 336	87.51 336	90.23 378	72.67 374	88.62 384	81.96 434	81.37 306	85.01 274	88.34 381	66.31 324	94.45 378	75.30 336	87.12 299	95.43 226

ADS-MVSNet2		81.66 351	79.71 360	87.50 337	91.35 334	74.19 356	83.33 429	88.48 407	72.90 405	82.24 333	85.77 412	64.98 334	93.20 401	64.57 409	83.74 325	95.12 236

OurMVSNet-221017-0		85.35 303	84.64 303	87.49 338	90.77 362	72.59 378	94.01 220	94.40 265	84.72 223	79.62 372	93.17 239	61.91 355	96.72 291	81.99 250	81.16 359	93.16 335

tpm2		84.08 327	82.94 331	87.48 339	91.39 332	71.27 391	89.23 375	90.37 381	71.95 412	84.64 280	89.33 364	67.30 308	96.55 308	75.17 337	87.09 300	94.63 257

RPSCF		85.07 309	84.27 307	87.48 339	92.91 285	70.62 401	91.69 318	92.46 323	76.20 373	82.67 328	95.22 150	63.94 342	97.29 255	77.51 314	85.80 307	94.53 264

myMVS_eth3d28		85.80 294	85.26 288	87.42 341	94.73 185	69.92 406	90.60 343	90.95 370	87.21 148	86.06 238	90.04 349	59.47 378	96.02 335	74.89 342	93.35 195	96.33 183

WBMVS		84.97 313	84.18 309	87.34 342	94.14 228	71.62 390	90.20 354	92.35 326	81.61 301	84.06 300	90.76 328	61.82 356	96.52 309	78.93 299	83.81 323	93.89 293

miper_lstm_enhance		85.27 306	84.59 304	87.31 343	91.28 337	74.63 350	87.69 400	94.09 281	81.20 312	81.36 345	89.85 356	74.97 203	94.30 383	81.03 269	79.84 383	93.01 341

FMVSNet5		81.52 355	79.60 361	87.27 344	91.17 340	77.95 296	91.49 322	92.26 332	76.87 365	76.16 397	87.91 389	51.67 414	92.34 409	67.74 391	81.16 359	91.52 379

USDC		82.76 339	81.26 344	87.26 345	91.17 340	74.55 351	89.27 373	93.39 300	78.26 354	75.30 405	92.08 279	54.43 407	96.63 297	71.64 362	85.79 308	90.61 398

test-LLR		85.87 291	85.41 281	87.25 346	90.95 351	71.67 388	89.55 367	89.88 395	83.41 252	84.54 283	87.95 387	67.25 309	95.11 371	81.82 254	93.37 193	94.97 241

test-mter		84.54 322	83.64 320	87.25 346	90.95 351	71.67 388	89.55 367	89.88 395	79.17 334	84.54 283	87.95 387	55.56 398	95.11 371	81.82 254	93.37 193	94.97 241

JIA-IIPM		81.04 360	78.98 372	87.25 346	88.64 397	73.48 364	81.75 435	89.61 401	73.19 402	82.05 336	73.71 438	66.07 329	95.87 344	71.18 367	84.60 316	92.41 360

TDRefinement		79.81 374	77.34 380	87.22 349	79.24 441	75.48 342	93.12 265	92.03 338	76.45 368	75.01 406	91.58 300	49.19 421	96.44 316	70.22 375	69.18 420	89.75 407

tpmvs		83.35 338	82.07 337	87.20 350	91.07 346	71.00 397	88.31 389	91.70 347	78.91 337	80.49 357	87.18 399	69.30 290	97.08 271	68.12 390	83.56 329	93.51 320

ppachtmachnet_test		81.84 347	80.07 355	87.15 351	88.46 401	74.43 354	89.04 379	92.16 334	75.33 380	77.75 386	88.99 370	66.20 326	95.37 366	65.12 406	77.60 394	91.65 375

dmvs_re		84.20 326	83.22 327	87.14 352	91.83 317	77.81 302	90.04 359	90.19 385	84.70 224	81.49 341	89.17 366	64.37 340	91.13 420	71.58 363	85.65 309	92.46 358

tpm cat1		81.96 345	80.27 351	87.01 353	91.09 345	71.02 396	87.38 404	91.53 355	66.25 428	80.17 359	86.35 408	68.22 305	96.15 331	69.16 381	82.29 345	93.86 299

test_fmvs1_n		87.03 259	87.04 219	86.97 354	89.74 387	71.86 383	94.55 175	94.43 262	78.47 348	91.95 119	95.50 138	51.16 416	93.81 391	93.02 66	94.56 165	95.26 232

OpenMVS_ROB	74.94 19	79.51 378	77.03 385	86.93 355	87.00 414	76.23 333	92.33 298	90.74 376	68.93 422	74.52 410	88.23 384	49.58 419	96.62 298	57.64 429	84.29 318	87.94 425

SixPastTwentyTwo		83.91 331	82.90 333	86.92 356	90.99 349	70.67 400	93.48 246	91.99 340	85.54 193	77.62 388	92.11 277	60.59 371	96.87 287	76.05 330	77.75 393	93.20 333

ADS-MVSNet		81.56 353	79.78 357	86.90 357	91.35 334	71.82 384	83.33 429	89.16 405	72.90 405	82.24 333	85.77 412	64.98 334	93.76 392	64.57 409	83.74 325	95.12 236

PatchT		82.68 341	81.27 343	86.89 358	90.09 380	70.94 398	84.06 426	90.15 386	74.91 385	85.63 248	83.57 421	69.37 286	94.87 376	65.19 404	88.50 276	94.84 251

tpm		84.73 317	84.02 314	86.87 359	90.33 375	68.90 409	89.06 378	89.94 392	80.85 315	85.75 244	89.86 355	68.54 302	95.97 338	77.76 310	84.05 322	95.75 215

Patchmatch-RL test		81.67 350	79.96 356	86.81 360	85.42 424	71.23 392	82.17 434	87.50 414	78.47 348	77.19 390	82.50 428	70.81 262	93.48 396	82.66 235	72.89 409	95.71 219

test_vis1_n		86.56 276	86.49 243	86.78 361	88.51 398	72.69 373	94.68 168	93.78 293	79.55 330	90.70 143	95.31 146	48.75 422	93.28 399	93.15 62	93.99 176	94.38 275

testing3-2		86.72 270	86.71 229	86.74 362	96.11 109	65.92 421	93.39 251	89.65 400	89.46 69	87.84 196	92.79 254	59.17 383	97.60 218	81.31 263	90.72 237	96.70 171

test_fmvs1		87.34 242	87.56 205	86.68 363	90.59 368	71.80 385	94.01 220	94.04 282	78.30 352	91.97 117	95.22 150	56.28 396	93.71 393	92.89 67	94.71 159	94.52 265

MDA-MVSNet-bldmvs		78.85 383	76.31 388	86.46 364	89.76 386	73.88 358	88.79 381	90.42 380	79.16 335	59.18 438	88.33 382	60.20 373	94.04 386	62.00 417	68.96 421	91.48 382

mvs5depth		80.98 362	79.15 369	86.45 365	84.57 427	73.29 366	87.79 396	91.67 349	80.52 318	82.20 335	89.72 358	55.14 403	95.93 340	73.93 351	66.83 426	90.12 404

tpmrst		85.35 303	84.99 292	86.43 366	90.88 358	67.88 414	88.71 382	91.43 358	80.13 322	86.08 237	88.80 375	73.05 236	96.02 335	82.48 236	83.40 333	95.40 227

TESTMET0.1,1		83.74 334	82.85 334	86.42 367	89.96 383	71.21 393	89.55 367	87.88 410	77.41 360	83.37 319	87.31 395	56.71 394	93.65 395	80.62 277	92.85 206	94.40 274

our_test_3		81.93 346	80.46 349	86.33 368	88.46 401	73.48 364	88.46 387	91.11 363	76.46 367	76.69 394	88.25 383	66.89 314	94.36 381	68.75 383	79.08 389	91.14 390

lessismore_v0				86.04 369	88.46 401	68.78 410		80.59 437		73.01 417	90.11 347	55.39 399	96.43 317	75.06 339	65.06 429	92.90 344

TinyColmap		79.76 375	77.69 378	85.97 370	91.71 321	73.12 367	89.55 367	90.36 382	75.03 383	72.03 420	90.19 343	46.22 431	96.19 330	63.11 413	81.03 364	88.59 421

KD-MVS_2432*1600		78.50 384	76.02 391	85.93 371	86.22 417	74.47 352	84.80 422	92.33 327	79.29 332	76.98 391	85.92 410	53.81 410	93.97 388	67.39 392	57.42 439	89.36 409

miper_refine_blended		78.50 384	76.02 391	85.93 371	86.22 417	74.47 352	84.80 422	92.33 327	79.29 332	76.98 391	85.92 410	53.81 410	93.97 388	67.39 392	57.42 439	89.36 409

K. test v3		81.59 352	80.15 354	85.91 373	89.89 385	69.42 408	92.57 289	87.71 412	85.56 192	73.44 415	89.71 359	55.58 397	95.52 359	77.17 317	69.76 417	92.78 349

SSC-MVS3.2		84.60 321	84.19 308	85.85 374	92.74 289	68.07 411	88.15 391	93.81 291	87.42 145	83.76 308	91.07 317	62.91 349	95.73 353	74.56 346	83.24 334	93.75 309

mvsany_test1		85.42 301	85.30 286	85.77 375	87.95 410	75.41 343	87.61 403	80.97 436	76.82 366	88.68 179	95.83 124	77.44 170	90.82 422	85.90 186	86.51 303	91.08 394

MIMVSNet1		79.38 379	77.28 381	85.69 376	86.35 416	73.67 361	91.61 320	92.75 318	78.11 357	72.64 418	88.12 385	48.16 423	91.97 414	60.32 421	77.49 395	91.43 384

UWE-MVS		83.69 335	83.09 328	85.48 377	93.06 276	65.27 426	90.92 336	86.14 418	79.90 325	86.26 233	90.72 331	57.17 393	95.81 348	71.03 370	92.62 213	95.35 230

UnsupCasMVSNet_eth		80.07 371	78.27 377	85.46 378	85.24 425	72.63 377	88.45 388	94.87 245	82.99 264	71.64 422	88.07 386	56.34 395	91.75 415	73.48 354	63.36 432	92.01 370

CL-MVSNet_self_test		81.74 349	80.53 347	85.36 379	85.96 419	72.45 380	90.25 349	93.07 308	81.24 310	79.85 369	87.29 396	70.93 260	92.52 407	66.95 395	69.23 419	91.11 392

MDA-MVSNet_test_wron		79.21 381	77.19 383	85.29 380	88.22 405	72.77 372	85.87 413	90.06 389	74.34 390	62.62 435	87.56 393	66.14 327	91.99 413	66.90 399	73.01 407	91.10 393

YYNet1		79.22 380	77.20 382	85.28 381	88.20 406	72.66 375	85.87 413	90.05 391	74.33 391	62.70 433	87.61 392	66.09 328	92.03 411	66.94 396	72.97 408	91.15 389

WB-MVSnew		83.77 333	83.28 324	85.26 382	91.48 327	71.03 395	91.89 310	87.98 409	78.91 337	84.78 277	90.22 341	69.11 295	94.02 387	64.70 408	90.44 240	90.71 396

dp		81.47 356	80.23 352	85.17 383	89.92 384	65.49 424	86.74 408	90.10 388	76.30 371	81.10 347	87.12 400	62.81 350	95.92 341	68.13 389	79.88 381	94.09 286

UnsupCasMVSNet_bld		76.23 393	73.27 397	85.09 384	83.79 429	72.92 369	85.65 416	93.47 299	71.52 413	68.84 428	79.08 433	49.77 418	93.21 400	66.81 400	60.52 436	89.13 417

SD_0403		84.71 319	84.65 301	84.92 385	92.95 283	65.95 420	92.07 309	93.23 303	83.82 241	79.03 375	93.73 224	73.90 221	92.91 405	63.02 415	90.05 247	95.89 208

Anonymous20231206		81.03 361	79.77 359	84.82 386	87.85 411	70.26 403	91.42 323	92.08 336	73.67 397	77.75 386	89.25 365	62.43 352	93.08 402	61.50 419	82.00 350	91.12 391

test0.0.03 1		82.41 343	81.69 339	84.59 387	88.23 404	72.89 370	90.24 351	87.83 411	83.41 252	79.86 368	89.78 357	67.25 309	88.99 432	65.18 405	83.42 332	91.90 372

CMPMVS	59.16 21	80.52 365	79.20 367	84.48 388	83.98 428	67.63 417	89.95 362	93.84 290	64.79 432	66.81 430	91.14 314	57.93 389	95.17 369	76.25 327	88.10 282	90.65 397
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CVMVSNet		84.69 320	84.79 299	84.37 389	91.84 315	64.92 427	93.70 240	91.47 357	66.19 429	86.16 236	95.28 147	67.18 311	93.33 398	80.89 272	90.42 242	94.88 250

PVSNet_0	73.20 20	77.22 389	74.83 395	84.37 389	90.70 366	71.10 394	83.09 431	89.67 398	72.81 407	73.93 413	83.13 423	60.79 370	93.70 394	68.54 384	50.84 444	88.30 423

LF4IMVS		80.37 368	79.07 371	84.27 391	86.64 415	69.87 407	89.39 372	91.05 366	76.38 369	74.97 407	90.00 351	47.85 424	94.25 385	74.55 347	80.82 370	88.69 420

Anonymous20240521		80.44 367	79.21 366	84.11 392	85.75 422	67.89 413	92.86 282	93.23 303	75.61 378	75.59 404	87.47 394	50.03 417	94.33 382	71.14 368	81.21 358	90.12 404

PM-MVS		78.11 386	76.12 390	84.09 393	83.54 430	70.08 404	88.97 380	85.27 425	79.93 324	74.73 409	86.43 405	34.70 442	93.48 396	79.43 294	72.06 411	88.72 419

test_fmvs2		83.98 328	84.03 313	83.83 394	87.16 413	67.53 418	93.93 227	92.89 312	77.62 358	86.89 217	93.53 227	47.18 426	92.02 412	90.54 126	86.51 303	91.93 371

testgi		80.94 364	80.20 353	83.18 395	87.96 409	66.29 419	91.28 327	90.70 378	83.70 243	78.12 382	92.84 249	51.37 415	90.82 422	63.34 412	82.46 343	92.43 359

KD-MVS_self_test		80.20 369	79.24 365	83.07 396	85.64 423	65.29 425	91.01 335	93.93 284	78.71 346	76.32 396	86.40 407	59.20 382	92.93 404	72.59 358	69.35 418	91.00 395

testing3		80.46 366	79.59 362	83.06 397	93.44 263	64.64 428	93.33 253	85.47 423	84.34 230	79.93 367	90.84 324	44.35 434	92.39 408	57.06 431	87.56 292	92.16 368

ambc				83.06 397	79.99 439	63.51 432	77.47 442	92.86 313		74.34 412	84.45 418	28.74 443	95.06 373	73.06 356	68.89 422	90.61 398

test20.03		79.95 373	79.08 370	82.55 399	85.79 421	67.74 416	91.09 333	91.08 364	81.23 311	74.48 411	89.96 353	61.63 357	90.15 424	60.08 422	76.38 401	89.76 406

MVStest1		72.91 397	69.70 402	82.54 400	78.14 442	73.05 368	88.21 390	86.21 417	60.69 436	64.70 431	90.53 334	46.44 429	85.70 439	58.78 427	53.62 441	88.87 418

test_vis1_rt		77.96 387	76.46 387	82.48 401	85.89 420	71.74 387	90.25 349	78.89 440	71.03 417	71.30 423	81.35 430	42.49 436	91.05 421	84.55 208	82.37 344	84.65 428

EU-MVSNet		81.32 358	80.95 345	82.42 402	88.50 400	63.67 431	93.32 254	91.33 359	64.02 433	80.57 356	92.83 250	61.21 366	92.27 410	76.34 326	80.38 377	91.32 385

myMVS_eth3d		79.67 376	78.79 373	82.32 403	91.92 311	64.08 429	89.75 365	87.40 415	81.72 296	78.82 377	87.20 397	45.33 432	91.29 418	59.09 426	87.84 289	91.60 377

ttmdpeth		76.55 391	74.64 396	82.29 404	82.25 435	67.81 415	89.76 364	85.69 421	70.35 419	75.76 402	91.69 293	46.88 427	89.77 426	66.16 401	63.23 433	89.30 411

pmmvs3		71.81 400	68.71 403	81.11 405	75.86 444	70.42 402	86.74 408	83.66 429	58.95 439	68.64 429	80.89 431	36.93 440	89.52 428	63.10 414	63.59 431	83.39 429

Syy-MVS		80.07 371	79.78 357	80.94 406	91.92 311	59.93 438	89.75 365	87.40 415	81.72 296	78.82 377	87.20 397	66.29 325	91.29 418	47.06 439	87.84 289	91.60 377

UWE-MVS-28		78.98 382	78.38 376	80.80 407	88.18 407	60.66 437	90.65 341	78.51 441	78.84 341	77.93 385	90.93 321	59.08 384	89.02 431	50.96 436	90.33 244	92.72 350

new-patchmatchnet		76.41 392	75.17 394	80.13 408	82.65 434	59.61 439	87.66 401	91.08 364	78.23 355	69.85 426	83.22 422	54.76 404	91.63 417	64.14 411	64.89 430	89.16 415

mvsany_test3		74.95 394	73.26 398	80.02 409	74.61 445	63.16 433	85.53 417	78.42 442	74.16 392	74.89 408	86.46 404	36.02 441	89.09 430	82.39 239	66.91 425	87.82 426

test_fmvs3		77.67 388	77.16 384	79.22 410	79.52 440	61.14 435	92.34 297	91.64 351	73.98 394	78.86 376	86.59 403	27.38 446	87.03 434	88.12 154	75.97 403	89.50 408

DSMNet-mixed		76.94 390	76.29 389	78.89 411	83.10 432	56.11 447	87.78 397	79.77 438	60.65 437	75.64 403	88.71 376	61.56 360	88.34 433	60.07 423	89.29 265	92.21 367

EGC-MVSNET		61.97 408	56.37 413	78.77 412	89.63 389	73.50 363	89.12 377	82.79 431	0.21 458	1.24 459	84.80 416	39.48 437	90.04 425	44.13 441	75.94 404	72.79 440

new_pmnet		72.15 398	70.13 401	78.20 413	82.95 433	65.68 422	83.91 427	82.40 433	62.94 435	64.47 432	79.82 432	42.85 435	86.26 438	57.41 430	74.44 406	82.65 433

MVS-HIRNet		73.70 396	72.20 399	78.18 414	91.81 318	56.42 446	82.94 432	82.58 432	55.24 440	68.88 427	66.48 443	55.32 401	95.13 370	58.12 428	88.42 278	83.01 431

LCM-MVSNet		66.00 405	62.16 410	77.51 415	64.51 455	58.29 441	83.87 428	90.90 372	48.17 444	54.69 441	73.31 439	16.83 455	86.75 435	65.47 403	61.67 435	87.48 427

APD_test1		69.04 401	66.26 407	77.36 416	80.51 438	62.79 434	85.46 418	83.51 430	54.11 442	59.14 439	84.79 417	23.40 449	89.61 427	55.22 432	70.24 416	79.68 437

test_f		71.95 399	70.87 400	75.21 417	74.21 447	59.37 440	85.07 421	85.82 420	65.25 431	70.42 425	83.13 423	23.62 447	82.93 445	78.32 304	71.94 412	83.33 430

ANet_high		58.88 412	54.22 417	72.86 418	56.50 458	56.67 443	80.75 437	86.00 419	73.09 404	37.39 450	64.63 446	22.17 450	79.49 448	43.51 442	23.96 452	82.43 434

test_vis3_rt		65.12 406	62.60 408	72.69 419	71.44 448	60.71 436	87.17 405	65.55 452	63.80 434	53.22 442	65.65 445	14.54 456	89.44 429	76.65 321	65.38 428	67.91 443

FPMVS		64.63 407	62.55 409	70.88 420	70.80 449	56.71 442	84.42 425	84.42 427	51.78 443	49.57 443	81.61 429	23.49 448	81.48 446	40.61 446	76.25 402	74.46 439

dmvs_testset		74.57 395	75.81 393	70.86 421	87.72 412	40.47 456	87.05 407	77.90 446	82.75 269	71.15 424	85.47 414	67.98 306	84.12 443	45.26 440	76.98 400	88.00 424

N_pmnet		68.89 402	68.44 404	70.23 422	89.07 394	28.79 461	88.06 392	19.50 461	69.47 421	71.86 421	84.93 415	61.24 365	91.75 415	54.70 433	77.15 397	90.15 403

testf1		59.54 410	56.11 414	69.85 423	69.28 450	56.61 444	80.37 438	76.55 449	42.58 447	45.68 446	75.61 434	11.26 457	84.18 441	43.20 443	60.44 437	68.75 441

APD_test2		59.54 410	56.11 414	69.85 423	69.28 450	56.61 444	80.37 438	76.55 449	42.58 447	45.68 446	75.61 434	11.26 457	84.18 441	43.20 443	60.44 437	68.75 441

WB-MVS		67.92 403	67.49 405	69.21 425	81.09 436	41.17 455	88.03 393	78.00 445	73.50 399	62.63 434	83.11 425	63.94 342	86.52 436	25.66 451	51.45 443	79.94 436

PMMVS2		59.60 409	56.40 412	69.21 425	68.83 452	46.58 451	73.02 446	77.48 447	55.07 441	49.21 444	72.95 440	17.43 454	80.04 447	49.32 438	44.33 447	80.99 435

SSC-MVS		67.06 404	66.56 406	68.56 427	80.54 437	40.06 457	87.77 398	77.37 448	72.38 409	61.75 436	82.66 427	63.37 345	86.45 437	24.48 452	48.69 446	79.16 438

Gipuma		57.99 414	54.91 416	67.24 428	88.51 398	65.59 423	52.21 449	90.33 383	43.58 446	42.84 449	51.18 450	20.29 452	85.07 440	34.77 447	70.45 415	51.05 449
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	47.18 22	52.22 416	48.46 420	63.48 429	45.72 460	46.20 452	73.41 445	78.31 443	41.03 449	30.06 452	65.68 444	6.05 459	83.43 444	30.04 449	65.86 427	60.80 444
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
dongtai		58.82 413	58.24 411	60.56 430	83.13 431	45.09 454	82.32 433	48.22 460	67.61 425	61.70 437	69.15 441	38.75 438	76.05 449	32.01 448	41.31 448	60.55 445

MVE	39.65 23	43.39 418	38.59 424	57.77 431	56.52 457	48.77 450	55.38 448	58.64 456	29.33 452	28.96 453	52.65 449	4.68 460	64.62 453	28.11 450	33.07 450	59.93 446
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		50.52 417	48.47 419	56.66 432	52.26 459	18.98 463	41.51 451	81.40 435	10.10 453	44.59 448	75.01 437	28.51 444	68.16 450	53.54 434	49.31 445	82.83 432

DeepMVS_CX				56.31 433	74.23 446	51.81 449		56.67 457	44.85 445	48.54 445	75.16 436	27.87 445	58.74 455	40.92 445	52.22 442	58.39 447

kuosan		53.51 415	53.30 418	54.13 434	76.06 443	45.36 453	80.11 440	48.36 459	59.63 438	54.84 440	63.43 447	37.41 439	62.07 454	20.73 454	39.10 449	54.96 448

E-PMN		43.23 419	42.29 421	46.03 435	65.58 454	37.41 458	73.51 444	64.62 453	33.99 450	28.47 454	47.87 451	19.90 453	67.91 451	22.23 453	24.45 451	32.77 450

EMVS		42.07 420	41.12 422	44.92 436	63.45 456	35.56 460	73.65 443	63.48 454	33.05 451	26.88 455	45.45 452	21.27 451	67.14 452	19.80 455	23.02 453	32.06 451

tmp_tt		35.64 421	39.24 423	24.84 437	14.87 461	23.90 462	62.71 447	51.51 458	6.58 455	36.66 451	62.08 448	44.37 433	30.34 457	52.40 435	22.00 454	20.27 452

wuyk23d		21.27 423	20.48 426	23.63 438	68.59 453	36.41 459	49.57 450	6.85 462	9.37 454	7.89 456	4.46 458	4.03 461	31.37 456	17.47 456	16.07 455	3.12 453

test123		8.76 425	11.22 428	1.39 439	0.85 463	0.97 464	85.76 415	0.35 464	0.54 457	2.45 458	8.14 457	0.60 462	0.48 458	2.16 458	0.17 457	2.71 454

testmvs		8.92 424	11.52 427	1.12 440	1.06 462	0.46 465	86.02 412	0.65 463	0.62 456	2.74 457	9.52 456	0.31 463	0.45 459	2.38 457	0.39 456	2.46 455

mmdepth		0.00 428	0.00 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

monomultidepth		0.00 428	0.00 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

test_blank		0.00 428	0.00 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

uanet_test		0.00 428	0.00 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

DCPMVS		0.00 428	0.00 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

cdsmvs_eth3d_5k		22.14 422	29.52 425	0.00 441	0.00 464	0.00 466	0.00 452	95.76 177	0.00 459	0.00 460	94.29 195	75.66 195	0.00 460	0.00 459	0.00 458	0.00 456

pcd_1.5k_mvsjas		6.64 427	8.86 430	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	79.70 138	0.00 460	0.00 459	0.00 458	0.00 456

sosnet-low-res		0.00 428	0.00 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

sosnet		0.00 428	0.00 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

uncertanet		0.00 428	0.00 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

Regformer		0.00 428	0.00 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

ab-mvs-re		7.82 426	10.43 429	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	93.88 216	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

uanet		0.00 428	0.00 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.00 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

WAC-MVS						64.08 429								59.14 425

FOURS1					98.86 1	85.54 69	98.29 1	97.49 8	89.79 60	96.29 26

PC_three_1452									82.47 273	97.09 15	97.07 65	92.72 1	98.04 184	92.70 73	99.02 12	98.86 12

test_one_0601					98.58 11	85.83 63		97.44 17	91.05 20	96.78 22	98.06 20	91.45 11

eth-test2					0.00 464

eth-test					0.00 464

ZD-MVS					98.15 36	86.62 33		97.07 54	83.63 245	94.19 57	96.91 71	87.57 31	99.26 46	91.99 97	98.44 53

RE-MVS-def			93.68 66		97.92 45	84.57 89	96.28 46	96.76 86	87.46 142	93.75 68	97.43 44	82.94 95		92.73 69	97.80 85	97.88 93

IU-MVS					98.77 5	86.00 52		96.84 76	81.26 309	97.26 11				95.50 33	99.13 3	99.03 8

test_241102_TWO								97.44 17	90.31 38	97.62 6	98.07 18	91.46 10	99.58 10	95.66 27	99.12 6	98.98 10

test_241102_ONE					98.77 5	85.99 54		97.44 17	90.26 44	97.71 1	97.96 28	92.31 4	99.38 31

9.14			94.47 29		97.79 54		96.08 64	97.44 17	86.13 180	95.10 47	97.40 46	88.34 22	99.22 48	93.25 61	98.70 34

save fliter					97.85 51	85.63 68	95.21 132	96.82 79	89.44 70

test_0728_THIRD									90.75 26	97.04 17	98.05 22	92.09 6	99.55 16	95.64 29	99.13 3	99.13 2

test0726					98.78 3	85.93 57	97.19 12	97.47 13	90.27 42	97.64 4	98.13 6	91.47 8

GSMVS																96.12 196

test_part2					98.55 12	87.22 19				96.40 25

sam_mvs1												71.70 251				96.12 196

sam_mvs												70.60 265

MTGPA								96.97 59

test_post1							88.00 394				9.81 455	69.31 289	95.53 358	76.65 321

test_post											10.29 454	70.57 269	95.91 343

patchmatchnet-post											83.76 420	71.53 252	96.48 312

MTMP							96.16 55	60.64 455

gm-plane-assit					89.60 390	68.00 412			77.28 363		88.99 370		97.57 221	79.44 293

test9_res														91.91 101	98.71 32	98.07 77

TEST9					97.53 63	86.49 37	94.07 214	96.78 83	81.61 301	92.77 93	96.20 101	87.71 28	99.12 57

test_8					97.49 65	86.30 45	94.02 219	96.76 86	81.86 292	92.70 97	96.20 101	87.63 29	99.02 67

agg_prior2														90.54 126	98.68 37	98.27 59

agg_prior					97.38 68	85.92 59		96.72 93		92.16 112			98.97 81

test_prior4						85.96 56	94.11 208

test_prior2							94.12 206		87.67 140	92.63 101	96.39 96	86.62 41		91.50 110	98.67 40

旧先验2							93.36 252		71.25 415	94.37 53			97.13 269	86.74 173

新几何2							93.11 267

旧先验1					96.79 81	81.81 184		95.67 185			96.81 77	86.69 39			97.66 91	96.97 154

无先验							93.28 260	96.26 132	73.95 395				99.05 61	80.56 278		96.59 175

原ACMM2							92.94 278

test222					96.55 90	81.70 186	92.22 302	95.01 231	68.36 424	90.20 153	96.14 106	80.26 131			97.80 85	96.05 203

testdata2													98.75 109	78.30 305

segment_acmp												87.16 36

testdata1							92.15 304		87.94 127

plane_prior7					94.70 190	82.74 159

plane_prior6					94.52 203	82.75 157						74.23 213

plane_prior5								96.22 137					98.12 169	88.15 151	89.99 248	94.63 257

plane_prior4											94.86 167

plane_prior3						82.75 157			90.26 44	86.91 214

plane_prior2							95.85 86		90.81 24

plane_prior1					94.59 196

plane_prior						82.73 160	95.21 132		89.66 65						89.88 253

n2								0.00 465

nn								0.00 465

door-mid								85.49 422

test11								96.57 104

door								85.33 424

HQP5-MVS						81.56 188

HQP-NCC					94.17 224		94.39 189		88.81 95	85.43 260

ACMP_Plane					94.17 224		94.39 189		88.81 95	85.43 260

BP-MVS														87.11 170

HQP4-MVS										85.43 260			97.96 191			94.51 267

HQP3-MVS								96.04 154							89.77 257

HQP2-MVS												73.83 224

NP-MVS					94.37 214	82.42 170					93.98 209

MDTV_nov1_ep13_2view						55.91 448	87.62 402		73.32 401	84.59 282		70.33 272		74.65 344		95.50 224

MDTV_nov1_ep13			83.56 321		91.69 323	69.93 405	87.75 399	91.54 354	78.60 347	84.86 276	88.90 372	69.54 284	96.03 334	70.25 373	88.93 270

ACMMP++_ref															87.47 293

ACMMP++															88.01 285

Test By Simon												80.02 133

High-resolution multi-view benchmark