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	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

DVP-MVS		97.93 3	98.23 3	97.58 3	99.05 7	99.31 1	98.64 6	96.62 5	97.56 2	95.08 6	96.61 14	99.64 1	97.32 1	97.91 4	97.31 6	98.77 17	99.26 2
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
DVP-MVS++		98.07 1	98.46 1	97.62 1	99.08 4	99.29 2	98.84 3	96.63 4	97.89 1	95.35 3	97.83 4	99.48 3	96.98 9	97.99 2	97.14 11	98.82 12	99.60 1

SED-MVS		97.98 2	98.36 2	97.54 4	98.94 18	99.29 2	98.81 4	96.64 3	97.14 3	95.16 5	97.96 2	99.61 2	96.92 12	98.00 1	97.24 8	98.75 18	99.25 3

DPE-MVS		97.83 4	98.13 4	97.48 5	98.83 24	99.19 4	98.99 1	96.70 1	96.05 20	94.39 11	98.30 1	99.47 4	97.02 6	97.75 7	97.02 14	98.98 2	99.10 9
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSP-MVS		97.70 6	98.09 5	97.24 7	99.00 12	99.17 5	98.76 5	96.41 10	96.91 5	93.88 16	97.72 5	99.04 7	96.93 11	97.29 16	97.31 6	98.45 37	99.23 4
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
APDe-MVS		97.79 5	97.96 6	97.60 2	99.20 2	99.10 6	98.88 2	96.68 2	96.81 7	94.64 7	97.84 3	98.02 11	97.24 3	97.74 8	97.02 14	98.97 4	99.16 6

CSCG		95.68 31	95.46 36	95.93 29	98.71 26	99.07 7	97.13 37	93.55 39	95.48 26	93.35 21	90.61 46	93.82 47	95.16 39	94.60 82	95.57 54	97.70 106	99.08 10

SMA-MVS		97.53 7	97.93 7	97.07 12	99.21 1	99.02 8	98.08 20	96.25 12	96.36 12	93.57 17	96.56 15	99.27 5	96.78 17	97.91 4	97.43 3	98.51 27	98.94 12
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
ACMMP_NAP		96.93 17	97.27 15	96.53 25	99.06 6	98.95 9	98.24 14	96.06 16	95.66 23	90.96 35	95.63 25	97.71 16	96.53 21	97.66 10	96.68 21	98.30 55	98.61 21

SteuartSystems-ACMMP		97.10 15	97.49 10	96.65 20	98.97 14	98.95 9	98.43 9	95.96 19	95.12 30	91.46 30	96.85 10	97.60 18	96.37 25	97.76 6	97.16 10	98.68 19	98.97 11
Skip Steuart: Steuart Systems R&D Blog.
ACMMPR		96.92 18	96.96 19	96.87 17	98.99 13	98.78 11	98.38 11	95.52 26	96.57 10	92.81 26	96.06 21	95.90 37	97.07 5	96.60 39	96.34 34	98.46 34	98.42 36

HFP-MVS		97.11 14	97.19 16	97.00 14	98.97 14	98.73 12	98.37 12	95.69 23	96.60 9	93.28 22	96.87 9	96.64 29	97.27 2	96.64 37	96.33 35	98.44 38	98.56 23

zzz-MVS		96.98 16	96.68 24	97.33 6	99.09 3	98.71 13	98.43 9	96.01 17	96.11 19	95.19 4	92.89 34	97.32 23	96.84 13	97.20 20	96.09 46	98.44 38	98.46 35

XVS					95.68 64	98.66 14	94.96 63			88.03 54		96.06 33				98.46 34

X-MVStestdata					95.68 64	98.66 14	94.96 63			88.03 54		96.06 33				98.46 34

X-MVS		96.07 27	96.33 29	95.77 31	98.94 18	98.66 14	97.94 24	95.41 32	95.12 30	88.03 54	93.00 33	96.06 33	95.85 32	96.65 36	96.35 31	98.47 32	98.48 32

SD-MVS		97.35 8	97.73 8	96.90 16	97.35 46	98.66 14	97.85 26	96.25 12	96.86 6	94.54 10	96.75 12	99.13 6	96.99 7	96.94 27	96.58 24	98.39 45	99.20 5
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
PHI-MVS		95.86 29	96.93 22	94.61 43	97.60 43	98.65 18	96.49 42	93.13 42	94.07 44	87.91 57	97.12 8	97.17 25	93.90 56	96.46 42	96.93 17	98.64 21	98.10 51

PGM-MVS		96.16 25	96.33 29	95.95 28	99.04 8	98.63 19	98.32 13	92.76 44	93.42 49	90.49 40	96.30 17	95.31 42	96.71 19	96.46 42	96.02 48	98.38 46	98.19 44

APD-MVS		97.12 13	97.05 18	97.19 8	99.04 8	98.63 19	98.45 8	96.54 6	94.81 38	93.50 18	96.10 20	97.40 22	96.81 14	97.05 24	96.82 19	98.80 13	98.56 23
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CNVR-MVS		97.30 10	97.41 11	97.18 9	99.02 11	98.60 21	98.15 17	96.24 14	96.12 18	94.10 13	95.54 26	97.99 12	96.99 7	97.97 3	97.17 9	98.57 25	98.50 31

CP-MVS		96.68 21	96.59 27	96.77 19	98.85 23	98.58 22	98.18 16	95.51 28	95.34 27	92.94 25	95.21 29	96.25 32	96.79 16	96.44 44	95.77 51	98.35 47	98.56 23

TSAR-MVS + MP.		97.31 9	97.64 9	96.92 15	97.28 48	98.56 23	98.61 7	95.48 30	96.72 8	94.03 15	96.73 13	98.29 9	97.15 4	97.61 12	96.42 27	98.96 5	99.13 7
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
HPM-MVS++		97.22 11	97.40 12	97.01 13	99.08 4	98.55 24	98.19 15	96.48 7	96.02 21	93.28 22	96.26 18	98.71 8	96.76 18	97.30 15	96.25 37	98.30 55	98.68 15

DeepC-MVS	92.10 3	95.22 36	94.77 42	95.75 32	97.77 39	98.54 25	97.63 29	95.96 19	95.07 33	88.85 48	85.35 76	91.85 55	95.82 33	96.88 29	97.10 12	98.44 38	98.63 18
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMMP		95.54 33	95.49 35	95.61 34	98.27 32	98.53 26	97.16 36	94.86 34	94.88 36	89.34 43	95.36 28	91.74 57	95.50 37	95.51 61	94.16 75	98.50 29	98.22 42
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
CANet		94.85 40	94.92 39	94.78 39	97.25 49	98.52 27	97.20 34	91.81 50	93.25 50	91.06 34	86.29 68	94.46 45	92.99 67	97.02 25	96.68 21	98.34 49	98.20 43

xxxxxxxxxxxxxcwj		95.62 32	94.35 49	97.10 10	98.95 16	98.51 28	97.51 30	96.48 7	96.17 16	94.64 7	97.32 6	76.98 139	96.23 27	96.78 30	96.15 40	98.79 15	98.55 28

SF-MVS		97.20 12	97.29 14	97.10 10	98.95 16	98.51 28	97.51 30	96.48 7	96.17 16	94.64 7	97.32 6	97.57 19	96.23 27	96.78 30	96.15 40	98.79 15	98.55 28

MVS_0304		94.30 47	94.68 43	93.86 51	96.33 60	98.48 30	97.41 32	91.20 56	92.75 55	86.96 65	86.03 71	93.81 48	92.64 71	96.89 28	96.54 26	98.61 23	98.24 41

MP-MVS		96.56 22	96.72 23	96.37 26	98.93 20	98.48 30	98.04 21	95.55 25	94.32 42	90.95 37	95.88 23	97.02 26	96.29 26	96.77 32	96.01 49	98.47 32	98.56 23
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MCST-MVS		96.83 19	97.06 17	96.57 21	98.88 22	98.47 32	98.02 22	96.16 15	95.58 25	90.96 35	95.78 24	97.84 14	96.46 23	97.00 26	96.17 39	98.94 7	98.55 28

MVS_111021_HR		94.84 41	95.91 31	93.60 53	97.35 46	98.46 33	95.08 62	91.19 57	94.18 43	85.97 73	95.38 27	92.56 53	93.61 60	96.61 38	96.25 37	98.40 43	97.92 58

NCCC		96.75 20	96.67 25	96.85 18	99.03 10	98.44 34	98.15 17	96.28 11	96.32 13	92.39 27	92.16 36	97.55 20	96.68 20	97.32 13	96.65 23	98.55 26	98.26 40

TSAR-MVS + ACMM		96.19 24	97.39 13	94.78 39	97.70 41	98.41 35	97.72 28	95.49 29	96.47 11	86.66 68	96.35 16	97.85 13	93.99 53	97.19 22	96.37 30	97.12 131	99.13 7

DELS-MVS		93.71 53	93.47 54	94.00 46	96.82 55	98.39 36	96.80 40	91.07 59	89.51 99	89.94 42	83.80 86	89.29 73	90.95 88	97.32 13	97.65 2	98.42 41	98.32 39
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
QAPM		94.13 49	94.33 51	93.90 49	97.82 38	98.37 37	96.47 43	90.89 61	92.73 57	85.63 81	85.35 76	93.87 46	94.17 51	95.71 59	95.90 50	98.40 43	98.42 36

DeepC-MVS_fast	93.32 1	96.48 23	96.42 28	96.56 22	98.70 27	98.31 38	97.97 23	95.76 22	96.31 14	92.01 29	91.43 41	95.42 41	96.46 23	97.65 11	97.69 1	98.49 31	98.12 49
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test2506		90.93 85	89.20 103	92.95 64	94.97 75	98.30 39	94.53 67	90.25 67	89.91 92	88.39 53	83.23 90	64.17 192	90.69 91	96.75 34	96.10 44	98.87 8	95.97 124

test1111		90.47 93	89.10 105	92.07 77	94.92 77	98.30 39	94.17 80	90.30 66	89.56 98	83.92 95	73.25 151	73.66 148	90.26 97	96.77 32	96.14 42	98.87 8	96.04 122

ECVR-MVS		90.77 88	89.27 101	92.52 70	94.97 75	98.30 39	94.53 67	90.25 67	89.91 92	85.80 78	73.64 144	74.31 147	90.69 91	96.75 34	96.10 44	98.87 8	95.91 127

DeepPCF-MVS	92.65 2	95.50 35	96.96 19	93.79 52	96.44 58	98.21 42	93.51 98	94.08 38	96.94 4	89.29 44	93.08 32	96.77 28	93.82 57	97.68 9	97.40 4	95.59 177	98.65 17

3Dnovator	90.28 7	94.70 44	94.34 50	95.11 37	98.06 34	98.21 42	96.89 39	91.03 60	94.72 39	91.45 31	82.87 94	93.10 51	94.61 43	96.24 50	97.08 13	98.63 22	98.16 45

MSLP-MVS++		96.05 28	95.63 32	96.55 23	98.33 31	98.17 44	96.94 38	94.61 36	94.70 40	94.37 12	89.20 54	95.96 36	96.81 14	95.57 60	97.33 5	98.24 63	98.47 33

3Dnovator+	90.56 5	95.06 38	94.56 45	95.65 33	98.11 33	98.15 45	97.19 35	91.59 54	95.11 32	93.23 24	81.99 103	94.71 44	95.43 38	96.48 41	96.88 18	98.35 47	98.63 18

TSAR-MVS + GP.		95.86 29	96.95 21	94.60 44	94.07 86	98.11 46	96.30 45	91.76 52	95.67 22	91.07 33	96.82 11	97.69 17	95.71 35	95.96 54	95.75 52	98.68 19	98.63 18

CDPH-MVS		94.80 43	95.50 34	93.98 48	98.34 30	98.06 47	97.41 32	93.23 41	92.81 54	82.98 99	92.51 35	94.82 43	93.53 61	96.08 52	96.30 36	98.42 41	97.94 56

train_agg		96.15 26	96.64 26	95.58 35	98.44 29	98.03 48	98.14 19	95.40 33	93.90 46	87.72 58	96.26 18	98.10 10	95.75 34	96.25 49	95.45 56	98.01 85	98.47 33

OpenMVS	88.18 11	92.51 63	91.61 80	93.55 54	97.74 40	98.02 49	95.66 55	90.46 64	89.14 102	86.50 69	75.80 135	90.38 71	92.69 70	94.99 67	95.30 58	98.27 59	97.63 67

abl_6				94.78 39	97.46 44	97.99 50	95.76 53	91.80 51	93.72 47	91.25 32	91.33 42	96.47 30	94.28 50			98.14 72	97.39 78

CPTT-MVS		95.54 33	95.07 37	96.10 27	97.88 37	97.98 51	97.92 25	94.86 34	94.56 41	92.16 28	91.01 43	95.71 38	96.97 10	94.56 83	93.50 91	96.81 154	98.14 47

PCF-MVS	90.19 8	92.98 58	92.07 73	94.04 45	96.39 59	97.87 52	96.03 49	95.47 31	87.16 117	85.09 92	84.81 80	93.21 50	93.46 63	91.98 132	91.98 129	97.78 98	97.51 74
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
canonicalmvs		93.08 57	93.09 57	93.07 63	94.24 82	97.86 53	95.45 58	87.86 102	94.00 45	87.47 60	88.32 58	82.37 105	95.13 40	93.96 98	96.41 29	98.27 59	98.73 13

PVSNet_Blended_VisFu		91.92 70	92.39 69	91.36 90	95.45 72	97.85 54	92.25 115	89.54 78	88.53 109	87.47 60	79.82 113	90.53 68	85.47 150	96.31 48	95.16 62	97.99 87	98.56 23

PVSNet_BlendedMVS		92.80 59	92.44 67	93.23 56	96.02 62	97.83 55	93.74 91	90.58 62	91.86 64	90.69 38	85.87 74	82.04 107	90.01 98	96.39 45	95.26 59	98.34 49	97.81 63

PVSNet_Blended		92.80 59	92.44 67	93.23 56	96.02 62	97.83 55	93.74 91	90.58 62	91.86 64	90.69 38	85.87 74	82.04 107	90.01 98	96.39 45	95.26 59	98.34 49	97.81 63

EIA-MVS		92.72 61	92.96 60	92.44 72	93.86 95	97.76 57	93.13 104	88.65 88	89.78 95	86.68 67	86.69 65	87.57 74	93.74 58	96.07 53	95.32 57	98.58 24	97.53 73

AdaColmap		95.02 39	93.71 52	96.54 24	98.51 28	97.76 57	96.69 41	95.94 21	93.72 47	93.50 18	89.01 55	90.53 68	96.49 22	94.51 85	93.76 84	98.07 79	96.69 99

CS-MVS		93.79 52	94.84 40	92.57 69	93.72 99	97.75 59	93.53 97	87.65 107	93.06 51	85.40 89	88.62 56	91.82 56	96.14 29	97.23 19	96.69 20	98.95 6	98.68 15

IS_MVSNet		91.87 71	93.35 56	90.14 103	94.09 85	97.73 60	93.09 105	88.12 94	88.71 106	79.98 116	84.49 81	90.63 67	87.49 129	97.07 23	96.96 16	98.07 79	97.88 62

OMC-MVS		94.49 45	94.36 48	94.64 42	97.17 50	97.73 60	95.49 57	92.25 46	96.18 15	90.34 41	88.51 57	92.88 52	94.90 42	94.92 70	94.17 74	97.69 107	96.15 118

MVS_111021_LR		94.84 41	95.57 33	94.00 46	97.11 51	97.72 62	94.88 65	91.16 58	95.24 29	88.74 49	96.03 22	91.52 60	94.33 49	95.96 54	95.01 63	97.79 97	97.49 75

DROMVSNet		94.19 48	95.05 38	93.18 59	93.56 102	97.65 63	95.34 59	86.37 116	92.05 62	88.71 50	89.91 49	93.32 49	96.14 29	97.29 16	96.42 27	98.98 2	98.70 14

TAPA-MVS	90.35 6	93.69 55	93.52 53	93.90 49	96.89 54	97.62 64	96.15 46	91.67 53	94.94 34	85.97 73	87.72 60	91.96 54	94.40 46	93.76 99	93.06 106	98.30 55	95.58 134
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Vis-MVSNet		89.36 108	91.49 82	86.88 135	92.10 124	97.60 65	92.16 119	85.89 120	84.21 145	75.20 132	82.58 98	87.13 75	77.40 190	95.90 56	95.63 53	98.51 27	97.36 79
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ETV-MVS		93.80 51	94.57 44	92.91 66	93.98 88	97.50 66	93.62 94	88.70 86	91.95 63	87.57 59	90.21 48	90.79 64	94.56 44	97.20 20	96.35 31	99.02 1	97.98 53

DPM-MVS		95.07 37	94.84 40	95.34 36	97.44 45	97.49 67	97.76 27	95.52 26	94.88 36	88.92 47	87.25 61	96.44 31	94.41 45	95.78 57	96.11 43	97.99 87	95.95 125

UA-Net		90.81 86	92.58 64	88.74 115	94.87 79	97.44 68	92.61 109	88.22 92	82.35 159	78.93 120	85.20 78	95.61 39	79.56 185	96.52 40	96.57 25	98.23 64	94.37 153

CNLPA		93.69 55	92.50 65	95.06 38	97.11 51	97.36 69	93.88 87	93.30 40	95.64 24	93.44 20	80.32 111	90.73 66	94.99 41	93.58 101	93.33 95	97.67 109	96.57 104

EPP-MVSNet		92.13 67	93.06 58	91.05 92	93.66 101	97.30 70	92.18 116	87.90 98	90.24 83	83.63 96	86.14 70	90.52 70	90.76 90	94.82 75	94.38 71	98.18 69	97.98 53

tfpn200view9		89.55 105	87.86 120	91.53 84	93.90 93	97.26 71	94.31 75	89.74 73	85.87 129	81.15 107	76.46 130	70.38 159	91.76 80	94.92 70	93.51 88	98.28 58	96.61 101

thres600view7		89.28 111	87.47 130	91.39 87	94.12 84	97.25 72	93.94 85	89.74 73	85.62 134	80.63 113	75.24 139	69.33 164	91.66 82	94.92 70	93.23 98	98.27 59	96.72 98

thres200		89.49 106	87.72 122	91.55 83	93.95 90	97.25 72	94.34 73	89.74 73	85.66 132	81.18 106	76.12 134	70.19 162	91.80 78	94.92 70	93.51 88	98.27 59	96.40 108

thres400		89.40 107	87.58 127	91.53 84	94.06 87	97.21 74	94.19 79	89.83 72	85.69 131	81.08 109	75.50 137	69.76 163	91.80 78	94.79 77	93.51 88	98.20 67	96.60 102

casdiffmvs		91.72 75	91.16 85	92.38 74	93.16 107	97.15 75	93.95 83	89.49 79	91.58 69	86.03 72	80.75 110	80.95 113	93.16 65	95.25 63	95.22 61	98.50 29	97.23 84

UGNet		91.52 77	93.41 55	89.32 109	94.13 83	97.15 75	91.83 125	89.01 82	90.62 76	85.86 77	86.83 62	91.73 58	77.40 190	94.68 79	94.43 70	97.71 104	98.40 38
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
MAR-MVS		92.71 62	92.63 63	92.79 67	97.70 41	97.15 75	93.75 90	87.98 96	90.71 73	85.76 79	86.28 69	86.38 79	94.35 48	94.95 68	95.49 55	97.22 124	97.44 76
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
LS3D		91.97 69	90.98 87	93.12 61	97.03 53	97.09 78	95.33 61	95.59 24	92.47 59	79.26 119	81.60 106	82.77 100	94.39 47	94.28 87	94.23 73	97.14 130	94.45 152

tttt0517		91.01 84	91.71 78	90.19 101	92.98 109	97.07 79	91.96 124	87.63 108	90.61 77	81.42 104	86.76 64	82.26 106	89.23 110	94.86 74	93.03 108	97.90 92	97.36 79

thisisatest0530		91.04 83	91.74 77	90.21 99	92.93 113	97.00 80	92.06 121	87.63 108	90.74 72	81.51 103	86.81 63	82.48 102	89.23 110	94.81 76	93.03 108	97.90 92	97.33 81

HyFIR lowres test		87.87 119	86.42 136	89.57 106	95.56 67	96.99 81	92.37 112	84.15 140	86.64 122	77.17 126	57.65 205	83.97 91	91.08 87	92.09 130	92.44 116	97.09 133	95.16 143

MVS_Test		91.81 73	92.19 71	91.37 89	93.24 104	96.95 82	94.43 69	86.25 118	91.45 70	83.45 97	86.31 67	85.15 87	92.93 68	93.99 94	94.71 68	97.92 91	96.77 97

Vis-MVSNet (Re-imp)		90.54 92	92.76 62	87.94 124	93.73 98	96.94 83	92.17 118	87.91 97	88.77 105	76.12 130	83.68 87	90.80 63	79.49 186	96.34 47	96.35 31	98.21 66	96.46 106

CHOSEN 1792x2688		88.57 114	87.82 121	89.44 108	95.46 70	96.89 84	93.74 91	85.87 121	89.63 96	77.42 125	61.38 199	83.31 95	88.80 120	93.44 107	93.16 102	95.37 182	96.95 93

thres100view900		89.36 108	87.61 125	91.39 87	93.90 93	96.86 85	94.35 72	89.66 77	85.87 129	81.15 107	76.46 130	70.38 159	91.17 85	94.09 92	93.43 94	98.13 73	96.16 117

IB-MVS	85.10 14	87.98 118	87.97 119	87.99 123	94.55 80	96.86 85	84.52 194	88.21 93	86.48 127	88.54 52	74.41 142	77.74 134	74.10 201	89.65 171	92.85 110	98.06 81	97.80 65
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
CANet_DTU		90.74 90	92.93 61	88.19 120	94.36 81	96.61 87	94.34 73	84.66 133	90.66 74	68.75 169	90.41 47	86.89 77	89.78 100	95.46 62	94.87 65	97.25 123	95.62 132

DI_MVS_plusplus_trai		91.05 82	90.15 94	92.11 76	92.67 119	96.61 87	96.03 49	88.44 90	90.25 82	85.92 75	73.73 143	84.89 89	91.92 77	94.17 91	94.07 79	97.68 108	97.31 82

CS-MVS-test		93.70 54	94.53 46	92.72 68	93.18 105	96.58 89	95.34 59	86.37 116	92.52 58	86.45 70	89.44 51	91.29 62	96.14 29	97.29 16	96.03 47	98.85 11	98.58 22

EPNet		93.92 50	94.40 47	93.36 55	97.89 36	96.55 90	96.08 48	92.14 47	91.65 67	89.16 45	94.07 31	90.17 72	87.78 125	95.24 64	94.97 64	97.09 133	98.15 46
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
gg-mvs-nofinetune		81.83 189	83.58 162	79.80 197	91.57 130	96.54 91	93.79 89	68.80 213	62.71 217	43.01 222	55.28 208	85.06 88	83.65 164	96.13 51	94.86 66	97.98 90	94.46 151

PLC	90.69 4	94.32 46	92.99 59	95.87 30	97.91 35	96.49 92	95.95 52	94.12 37	94.94 34	94.09 14	85.90 72	90.77 65	95.58 36	94.52 84	93.32 97	97.55 114	95.00 146
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
diffmvs		91.37 78	91.09 86	91.70 81	92.71 118	96.47 93	94.03 81	88.78 84	92.74 56	85.43 88	83.63 88	80.37 115	91.76 80	93.39 108	93.78 83	97.50 116	97.23 84

TSAR-MVS + COLMAP		92.39 65	92.31 70	92.47 71	95.35 74	96.46 94	96.13 47	92.04 49	95.33 28	80.11 115	94.95 30	77.35 137	94.05 52	94.49 86	93.08 104	97.15 128	94.53 150

Effi-MVS+		89.79 102	89.83 98	89.74 105	92.98 109	96.45 95	93.48 99	84.24 138	87.62 115	76.45 128	81.76 104	77.56 136	93.48 62	94.61 81	93.59 87	97.82 96	97.22 86

ACMP	89.13 9	92.03 68	91.70 79	92.41 73	94.92 77	96.44 96	93.95 83	89.96 70	91.81 66	85.48 86	90.97 44	79.12 121	92.42 73	93.28 112	92.55 115	97.76 100	97.74 66
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Anonymous202405211			88.00 117		93.16 107	96.38 97	93.58 95	89.34 80	87.92 113		65.04 188	83.03 97	92.07 76	92.67 117	93.33 95	96.96 141	97.63 67

CLD-MVS		92.50 64	91.96 75	93.13 60	93.93 92	96.24 98	95.69 54	88.77 85	92.92 52	89.01 46	88.19 59	81.74 110	93.13 66	93.63 100	93.08 104	98.23 64	97.91 60
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
ET-MVSNet_ETH3D		89.93 99	90.84 88	88.87 113	79.60 212	96.19 99	94.43 69	86.56 114	90.63 75	80.75 112	90.71 45	77.78 133	93.73 59	91.36 140	93.45 93	98.15 70	95.77 129

LGP-MVS_train		91.83 72	92.04 74	91.58 82	95.46 70	96.18 100	95.97 51	89.85 71	90.45 79	77.76 122	91.92 39	80.07 118	92.34 75	94.27 88	93.47 92	98.11 76	97.90 61

OPM-MVS		91.08 81	89.34 100	93.11 62	96.18 61	96.13 101	96.39 44	92.39 45	82.97 156	81.74 102	82.55 100	80.20 117	93.97 55	94.62 80	93.23 98	98.00 86	95.73 130
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Anonymous20231211		89.82 101	88.18 115	91.74 80	92.52 120	96.09 102	93.38 100	89.30 81	88.95 104	85.90 76	64.55 192	84.39 90	92.41 74	92.24 127	93.06 106	96.93 146	97.95 55

GeoE		89.29 110	88.68 109	89.99 104	92.75 117	96.03 103	93.07 107	83.79 145	86.98 119	81.34 105	74.72 140	78.92 122	91.22 84	93.31 110	93.21 100	97.78 98	97.60 72

HQP-MVS		92.39 65	92.49 66	92.29 75	95.65 66	95.94 104	95.64 56	92.12 48	92.46 60	79.65 117	91.97 38	82.68 101	92.92 69	93.47 106	92.77 111	97.74 102	98.12 49

baseline1		90.81 86	90.29 91	91.42 86	93.67 100	95.86 105	93.94 85	89.69 76	89.29 101	82.85 100	82.91 93	80.30 116	89.60 101	95.05 66	94.79 67	98.80 13	93.82 161

PatchMatch-RL		90.30 95	88.93 107	91.89 78	95.41 73	95.68 106	90.94 128	88.67 87	89.80 94	86.95 66	85.90 72	72.51 150	92.46 72	93.56 103	92.18 121	96.93 146	92.89 171

baseline2		88.97 112	89.50 99	88.36 117	91.14 136	95.30 107	90.13 142	85.17 130	87.24 116	80.80 111	84.46 82	78.44 127	85.60 147	93.54 104	91.87 130	97.31 121	95.66 131

Fast-Effi-MVS+		88.56 115	87.99 118	89.22 110	91.56 131	95.21 108	92.29 114	82.69 156	86.82 120	77.73 123	76.24 133	73.39 149	93.36 64	94.22 90	93.64 85	97.65 110	96.43 107

FC-MVSNet-train		90.55 91	90.19 93	90.97 93	93.78 97	95.16 109	92.11 120	88.85 83	87.64 114	83.38 98	84.36 83	78.41 128	89.53 102	94.69 78	93.15 103	98.15 70	97.92 58

ACMM	88.76 10	91.70 76	90.43 90	93.19 58	95.56 67	95.14 110	93.35 101	91.48 55	92.26 61	87.12 63	84.02 84	79.34 120	93.99 53	94.07 93	92.68 112	97.62 113	95.50 135
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline		91.19 80	91.89 76	90.38 95	92.76 115	95.04 111	93.55 96	84.54 136	92.92 52	85.71 80	86.68 66	86.96 76	89.28 108	92.00 131	92.62 114	96.46 159	96.99 91

Effi-MVS+-dtu		87.51 123	88.13 116	86.77 137	91.10 137	94.90 112	90.91 129	82.67 157	83.47 152	71.55 148	81.11 109	77.04 138	89.41 104	92.65 119	91.68 136	95.00 189	96.09 120

MVSTER		91.73 74	91.61 80	91.86 79	93.18 105	94.56 113	94.37 71	87.90 98	90.16 87	88.69 51	89.23 53	81.28 112	88.92 118	95.75 58	93.95 81	98.12 74	96.37 109

CDS-MVSNet		88.34 116	88.71 108	87.90 125	90.70 144	94.54 114	92.38 111	86.02 119	80.37 168	79.42 118	79.30 114	83.43 94	82.04 173	93.39 108	94.01 80	96.86 152	95.93 126
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
ACMH	85.51 13	87.31 125	86.59 134	88.14 121	93.96 89	94.51 115	89.00 164	87.99 95	81.58 162	70.15 159	78.41 119	71.78 155	90.60 94	91.30 141	91.99 128	97.17 127	96.58 103
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
COLMAP_ROB	84.39 15	87.61 121	86.03 140	89.46 107	95.54 69	94.48 116	91.77 126	90.14 69	87.16 117	75.50 131	73.41 149	76.86 141	87.33 131	90.05 165	89.76 175	96.48 158	90.46 187
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
GG-mvs-BLEND		62.84 210	90.21 92	30.91 219	0.57 227	94.45 117	86.99 181	0.34 225	88.71 106	0.98 227	81.55 108	91.58 59	0.86 224	92.66 118	91.43 139	95.73 171	91.11 182

UniMVSNet (Re)		86.22 134	85.46 150	87.11 132	88.34 164	94.42 118	89.65 154	87.10 112	84.39 142	74.61 133	70.41 163	68.10 169	85.10 153	91.17 144	91.79 132	97.84 95	97.94 56

ACMH+	85.75 12	87.19 126	86.02 141	88.56 116	93.42 103	94.41 119	89.91 148	87.66 106	83.45 153	72.25 146	76.42 132	71.99 154	90.78 89	89.86 166	90.94 143	97.32 120	95.11 145

MSDG		90.42 94	88.25 114	92.94 65	96.67 57	94.41 119	93.96 82	92.91 43	89.59 97	86.26 71	76.74 128	80.92 114	90.43 96	92.60 120	92.08 126	97.44 119	91.41 178

UniMVSNet_ETH3D		84.57 155	81.40 189	88.28 119	89.34 154	94.38 121	90.33 134	86.50 115	74.74 201	77.52 124	59.90 203	62.04 200	88.78 121	88.82 181	92.65 113	97.22 124	97.24 83

GA-MVS		85.08 150	85.65 147	84.42 162	89.77 149	94.25 122	89.26 158	84.62 134	81.19 165	62.25 199	75.72 136	68.44 168	84.14 161	93.57 102	91.68 136	96.49 157	94.71 149

TDRefinement		84.97 152	83.39 167	86.81 136	92.97 111	94.12 123	92.18 116	87.77 103	82.78 157	71.31 151	68.43 169	68.07 170	81.10 181	89.70 170	89.03 182	95.55 179	91.62 176

MS-PatchMatch		87.63 120	87.61 125	87.65 128	93.95 90	94.09 124	92.60 110	81.52 172	86.64 122	76.41 129	73.46 148	85.94 83	85.01 154	92.23 128	90.00 169	96.43 161	90.93 184

UniMVSNet_NR-MVSNet		86.80 128	85.86 145	87.89 126	88.17 166	94.07 125	90.15 140	88.51 89	84.20 146	73.45 139	72.38 155	70.30 161	88.95 116	90.25 159	92.21 120	98.12 74	97.62 69

USDC		86.73 130	85.96 143	87.63 129	91.64 128	93.97 126	92.76 108	84.58 135	88.19 110	70.67 156	80.10 112	67.86 171	89.43 103	91.81 133	89.77 174	96.69 156	90.05 191

SCA		86.25 132	87.52 128	84.77 156	91.59 129	93.90 127	89.11 161	73.25 206	90.38 81	72.84 142	83.26 89	83.79 93	88.49 122	86.07 195	85.56 193	93.33 192	89.67 193

FMVSNet3		90.19 98	90.06 97	90.34 96	88.69 159	93.85 128	94.58 66	85.78 123	90.03 88	85.56 83	77.38 121	86.13 80	89.22 112	93.29 111	94.36 72	98.20 67	95.40 140

EG-PatchMatch MVS		81.70 191	81.31 190	82.15 190	88.75 157	93.81 129	87.14 180	78.89 185	71.57 206	64.12 196	61.20 201	68.46 167	76.73 194	91.48 137	90.77 147	97.28 122	91.90 175

DU-MVS		86.12 136	84.81 154	87.66 127	87.77 173	93.78 130	90.15 140	87.87 100	84.40 140	73.45 139	70.59 160	64.82 189	88.95 116	90.14 160	92.33 117	97.76 100	97.62 69

NR-MVSNet		85.46 146	84.54 156	86.52 140	88.33 165	93.78 130	90.45 133	87.87 100	84.40 140	71.61 147	70.59 160	62.09 199	82.79 169	91.75 134	91.75 133	98.10 77	97.44 76

EPMVS		85.77 140	86.24 138	85.23 152	92.76 115	93.78 130	89.91 148	73.60 202	90.19 85	74.22 134	82.18 102	78.06 130	87.55 128	85.61 197	85.38 195	93.32 193	88.48 200

Fast-Effi-MVS+-dtu		86.25 132	87.70 123	84.56 160	90.37 147	93.70 133	90.54 132	78.14 187	83.50 151	65.37 191	81.59 107	75.83 145	86.09 146	91.70 135	91.70 134	96.88 150	95.84 128

MDTV_nov1_ep13		86.64 131	87.50 129	85.65 146	90.73 142	93.69 134	89.96 146	78.03 189	89.48 100	76.85 127	84.92 79	82.42 104	86.14 144	86.85 192	86.15 189	92.17 201	88.97 196

thisisatest0515		85.70 141	87.00 131	84.19 165	88.16 167	93.67 135	84.20 196	84.14 141	83.39 154	72.91 141	76.79 127	74.75 146	78.82 188	92.57 121	91.26 141	96.94 143	96.56 105

GBi-Net		90.21 96	90.11 95	90.32 97	88.66 160	93.65 136	94.25 76	85.78 123	90.03 88	85.56 83	77.38 121	86.13 80	89.38 105	93.97 95	94.16 75	98.31 52	95.47 136

test1		90.21 96	90.11 95	90.32 97	88.66 160	93.65 136	94.25 76	85.78 123	90.03 88	85.56 83	77.38 121	86.13 80	89.38 105	93.97 95	94.16 75	98.31 52	95.47 136

FMVSNet2		89.61 104	89.14 104	90.16 102	88.66 160	93.65 136	94.25 76	85.44 127	88.57 108	84.96 93	73.53 146	83.82 92	89.38 105	94.23 89	94.68 69	98.31 52	95.47 136

anonymousdsp		84.51 157	85.85 146	82.95 182	86.30 197	93.51 139	85.77 191	80.38 179	78.25 183	63.42 197	73.51 147	72.20 152	84.64 156	93.21 113	92.16 123	97.19 126	98.14 47

DCV-MVSNet		91.24 79	91.26 83	91.22 91	92.84 114	93.44 140	93.82 88	86.75 113	91.33 71	85.61 82	84.00 85	85.46 86	91.27 83	92.91 114	93.62 86	97.02 137	98.05 52

PatchmatchNet		85.70 141	86.65 133	84.60 159	91.79 126	93.40 141	89.27 157	73.62 201	90.19 85	72.63 144	82.74 97	81.93 109	87.64 126	84.99 198	84.29 200	92.64 198	89.00 195
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
pm-mvs1		84.55 156	83.46 163	85.82 143	88.16 167	93.39 142	89.05 163	85.36 129	74.03 202	72.43 145	65.08 187	71.11 156	82.30 172	93.48 105	91.70 134	97.64 111	95.43 139

TranMVSNet+NR-MVSNet		85.57 144	84.41 157	86.92 134	87.67 176	93.34 143	90.31 136	88.43 91	83.07 155	70.11 160	69.99 166	65.28 184	86.96 134	89.73 168	92.27 118	98.06 81	97.17 88

WR-MVS_H		82.86 182	82.66 176	83.10 179	87.44 179	93.33 144	85.71 192	83.20 154	77.36 187	68.20 174	66.37 178	65.23 185	76.05 196	89.35 172	90.13 162	97.99 87	96.89 95

test_part1		87.53 122	84.97 151	90.52 94	92.11 123	93.31 145	93.32 102	85.79 122	79.56 176	87.38 62	62.89 196	78.60 125	89.25 109	90.65 154	92.17 122	95.24 184	97.62 69

WR-MVS		83.14 177	83.38 168	82.87 183	87.55 177	93.29 146	86.36 187	84.21 139	80.05 172	66.41 184	66.91 175	66.92 176	75.66 197	88.96 179	90.56 153	97.05 135	96.96 92

v2v482		84.51 157	83.05 173	86.20 142	87.25 182	93.28 147	90.22 138	85.40 128	79.94 174	69.78 162	67.74 171	65.15 186	87.57 127	89.12 177	90.55 154	96.97 139	95.60 133

V42		84.48 159	83.36 169	85.79 145	87.14 185	93.28 147	90.03 143	83.98 143	80.30 169	71.20 152	66.90 176	67.17 173	85.55 148	89.35 172	90.27 159	96.82 153	96.27 115

tfpnnormal		83.80 169	81.26 191	86.77 137	89.60 151	93.26 149	89.72 153	87.60 110	72.78 203	70.44 157	60.53 202	61.15 204	85.55 148	92.72 116	91.44 138	97.71 104	96.92 94

CostFormer		86.78 129	86.05 139	87.62 130	92.15 122	93.20 150	91.55 127	75.83 194	88.11 112	85.29 90	81.76 104	76.22 143	87.80 124	84.45 200	85.21 196	93.12 194	93.42 166

pmmvs5		83.37 174	82.68 175	84.18 166	87.13 186	93.18 151	86.74 183	82.08 166	76.48 192	67.28 180	71.26 157	62.70 196	84.71 155	90.77 149	90.12 165	97.15 128	94.24 154

FC-MVSNet-test		86.15 135	89.10 105	82.71 185	89.83 148	93.18 151	87.88 174	84.69 132	86.54 124	62.18 200	82.39 101	83.31 95	74.18 200	92.52 122	91.86 131	97.50 116	93.88 160

TAMVS		84.94 153	84.95 152	84.93 155	88.82 156	93.18 151	88.44 170	81.28 174	77.16 188	73.76 138	75.43 138	76.57 142	82.04 173	90.59 155	90.79 145	95.22 185	90.94 183

v1144		84.03 166	82.88 174	85.37 148	87.17 184	93.15 154	90.18 139	83.31 152	78.83 179	67.85 175	65.99 181	64.99 187	86.79 136	90.75 150	90.33 158	96.90 148	96.15 118

SixPastTwentyTwo		83.12 178	83.44 165	82.74 184	87.71 175	93.11 155	82.30 201	82.33 162	79.24 177	64.33 194	78.77 117	62.75 195	84.11 162	88.11 183	87.89 185	95.70 173	94.21 156

LTVRE_ROB	81.71 16	82.44 186	81.84 184	83.13 177	89.01 155	92.99 156	88.90 165	82.32 163	66.26 214	54.02 214	74.68 141	59.62 211	88.87 119	90.71 152	92.02 127	95.68 174	96.62 100
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
v8		84.45 161	83.30 170	85.80 144	87.53 178	92.95 157	90.31 136	82.46 161	80.46 167	71.43 149	66.99 174	67.16 174	86.14 144	89.26 175	90.22 161	96.94 143	96.06 121

v148		83.61 171	82.10 180	85.37 148	87.34 180	92.94 158	87.48 176	85.72 126	78.92 178	73.87 137	65.71 184	64.69 190	81.78 177	87.82 184	89.35 179	96.01 166	95.26 142

RPSCF		89.68 103	89.24 102	90.20 100	92.97 111	92.93 159	92.30 113	87.69 104	90.44 80	85.12 91	91.68 40	85.84 85	90.69 91	87.34 188	86.07 190	92.46 200	90.37 188

v144192		83.48 173	82.23 178	84.94 154	86.65 192	92.84 160	89.63 155	82.48 160	77.87 184	67.36 179	65.33 186	63.50 193	86.51 138	89.72 169	89.99 170	97.03 136	96.35 110

v1192		83.56 172	82.35 177	84.98 153	86.84 191	92.84 160	90.01 145	82.70 155	78.54 180	66.48 183	64.88 189	62.91 194	86.91 135	90.72 151	90.25 160	96.94 143	96.32 112

FMVSNet1		87.33 124	86.00 142	88.89 112	87.13 186	92.83 162	93.08 106	84.46 137	81.35 164	82.20 101	66.33 179	77.96 131	88.96 115	93.97 95	94.16 75	97.54 115	95.38 141

CHOSEN 280x420		90.77 88	92.14 72	89.17 111	93.86 95	92.81 163	93.16 103	80.22 180	90.21 84	84.67 94	89.89 50	91.38 61	90.57 95	94.94 69	92.11 124	92.52 199	93.65 163

CP-MVSNet		83.11 179	82.15 179	84.23 164	87.20 183	92.70 164	86.42 186	83.53 150	77.83 185	67.67 177	66.89 177	60.53 207	82.47 170	89.23 176	90.65 152	98.08 78	97.20 87

v10		84.18 162	83.17 172	85.37 148	87.34 180	92.68 165	90.32 135	81.33 173	79.93 175	69.23 167	66.33 179	65.74 182	87.03 133	90.84 148	90.38 156	96.97 139	96.29 114

v1921920		83.30 175	82.09 181	84.70 157	86.59 195	92.67 166	89.82 151	82.23 164	78.32 181	65.76 188	64.64 191	62.35 197	86.78 137	90.34 158	90.02 168	97.02 137	96.31 113

test-mter		86.09 138	88.38 111	83.43 175	87.89 170	92.61 167	86.89 182	77.11 192	84.30 143	68.62 171	82.57 99	82.45 103	84.34 157	92.40 123	90.11 166	95.74 170	94.21 156

v7n		82.25 187	81.54 187	83.07 180	85.55 201	92.58 168	86.68 185	81.10 177	76.54 191	65.97 187	62.91 195	60.56 206	82.36 171	91.07 146	90.35 157	96.77 155	96.80 96

dps		85.00 151	83.21 171	87.08 133	90.73 142	92.55 169	89.34 156	75.29 196	84.94 135	87.01 64	79.27 115	67.69 172	87.27 132	84.22 201	83.56 201	92.83 197	90.25 189

test0.0.03 1		85.58 143	87.69 124	83.11 178	91.22 134	92.54 170	85.60 193	83.62 147	85.66 132	67.84 176	82.79 96	79.70 119	73.51 203	91.15 145	90.79 145	96.88 150	91.23 181

PS-CasMVS		82.53 184	81.54 187	83.68 171	87.08 188	92.54 170	86.20 188	83.46 151	76.46 193	65.73 189	65.71 184	59.41 212	81.61 178	89.06 178	90.55 154	98.03 83	97.07 90

v1240		82.88 181	81.66 185	84.29 163	86.46 196	92.52 172	89.06 162	81.82 169	77.16 188	65.09 192	64.17 193	61.50 202	86.36 139	90.12 162	90.13 162	96.95 142	96.04 122

IterMVS-LS		88.60 113	88.45 110	88.78 114	92.02 125	92.44 173	92.00 123	83.57 149	86.52 125	78.90 121	78.61 118	81.34 111	89.12 113	90.68 153	93.18 101	97.10 132	96.35 110
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Patchmtry						92.39 174	89.18 159	73.30 204		71.08 153

EPNet_dtu		88.32 117	90.61 89	85.64 147	96.79 56	92.27 175	92.03 122	90.31 65	89.05 103	65.44 190	89.43 52	85.90 84	74.22 199	92.76 115	92.09 125	95.02 188	92.76 172
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MIMVSNet		82.97 180	84.00 160	81.77 193	82.23 208	92.25 176	87.40 179	72.73 207	81.48 163	69.55 163	68.79 168	72.42 151	81.82 176	92.23 128	92.25 119	96.89 149	88.61 198

CR-MVSNet		85.48 145	86.29 137	84.53 161	91.08 139	92.10 177	89.18 159	73.30 204	84.75 136	71.08 153	73.12 153	77.91 132	86.27 142	91.48 137	90.75 148	96.27 163	93.94 158

RPMNet		84.82 154	85.90 144	83.56 173	91.10 137	92.10 177	88.73 168	71.11 209	84.75 136	68.79 168	73.56 145	77.62 135	85.33 151	90.08 164	89.43 178	96.32 162	93.77 162

test-LLR		86.88 127	88.28 112	85.24 151	91.22 134	92.07 179	87.41 177	83.62 147	84.58 138	69.33 165	83.00 91	82.79 98	84.24 158	92.26 125	89.81 172	95.64 175	93.44 164

TESTMET0.1,1		86.11 137	88.28 112	83.59 172	87.80 171	92.07 179	87.41 177	77.12 191	84.58 138	69.33 165	83.00 91	82.79 98	84.24 158	92.26 125	89.81 172	95.64 175	93.44 164

PEN-MVS		82.49 185	81.58 186	83.56 173	86.93 189	92.05 181	86.71 184	83.84 144	76.94 190	64.68 193	67.24 172	60.11 208	81.17 180	87.78 185	90.70 151	98.02 84	96.21 116

pmmvs4		86.00 139	84.28 158	88.00 122	87.80 171	92.01 182	89.94 147	84.91 131	86.79 121	80.98 110	73.41 149	66.34 180	88.12 123	89.31 174	88.90 183	96.24 164	93.20 169

PMMVS		89.88 100	91.19 84	88.35 118	89.73 150	91.97 183	90.62 131	81.92 167	90.57 78	80.58 114	92.16 36	86.85 78	91.17 85	92.31 124	91.35 140	96.11 165	93.11 170

TinyColmap		84.04 165	82.01 182	86.42 141	90.87 140	91.84 184	88.89 166	84.07 142	82.11 161	69.89 161	71.08 158	60.81 205	89.04 114	90.52 156	89.19 180	95.76 169	88.50 199

CMPMVS	61.19 17	79.86 196	77.46 204	82.66 186	91.54 132	91.82 185	83.25 197	81.57 171	70.51 210	68.64 170	59.89 204	66.77 177	79.63 184	84.00 203	84.30 199	91.34 205	84.89 208
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ADS-MVSNet		84.08 164	84.95 152	83.05 181	91.53 133	91.75 186	88.16 171	70.70 210	89.96 91	69.51 164	78.83 116	76.97 140	86.29 141	84.08 202	84.60 198	92.13 203	88.48 200

tpmrst		83.72 170	83.45 164	84.03 168	92.21 121	91.66 187	88.74 167	73.58 203	88.14 111	72.67 143	77.37 124	72.11 153	86.34 140	82.94 205	82.05 204	90.63 209	89.86 192

pmmvs6		80.90 192	78.77 198	83.38 176	85.84 198	91.61 188	86.01 189	82.54 159	64.17 215	70.43 158	54.14 212	67.06 175	80.73 182	90.50 157	89.17 181	94.74 190	94.75 148

PatchT		83.86 167	85.51 149	81.94 191	88.41 163	91.56 189	78.79 208	71.57 208	84.08 148	71.08 153	70.62 159	76.13 144	86.27 142	91.48 137	90.75 148	95.52 180	93.94 158

TransMVSNet (Re)		82.67 183	80.93 194	84.69 158	88.71 158	91.50 190	87.90 173	87.15 111	71.54 208	68.24 173	63.69 194	64.67 191	78.51 189	91.65 136	90.73 150	97.64 111	92.73 174

tpm cat1		84.13 163	81.99 183	86.63 139	91.74 127	91.50 190	90.68 130	75.69 195	86.12 128	85.44 87	72.39 154	70.72 157	85.16 152	80.89 209	81.56 205	91.07 207	90.71 185

DTE-MVSNet		81.76 190	81.04 192	82.60 187	86.63 193	91.48 192	85.97 190	83.70 146	76.45 194	62.44 198	67.16 173	59.98 209	78.98 187	87.15 189	89.93 171	97.88 94	95.12 144

tpm		83.16 176	83.64 161	82.60 187	90.75 141	91.05 193	88.49 169	73.99 199	82.36 158	67.08 182	78.10 120	68.79 165	84.17 160	85.95 196	85.96 191	91.09 206	93.23 168

CVMVSNet		83.83 168	85.53 148	81.85 192	89.60 151	90.92 194	87.81 175	83.21 153	80.11 171	60.16 204	76.47 129	78.57 126	76.79 192	89.76 167	90.13 162	93.51 191	92.75 173

MDTV_nov1_ep13_2view		80.43 193	80.94 193	79.84 196	84.82 204	90.87 195	84.23 195	73.80 200	80.28 170	64.33 194	70.05 165	68.77 166	79.67 183	84.83 199	83.50 202	92.17 201	88.25 202

IterMVS-SCA-FT		85.44 147	86.71 132	83.97 169	90.59 145	90.84 196	89.73 152	78.34 186	84.07 149	66.40 185	77.27 126	78.66 124	83.06 166	91.20 142	90.10 167	95.72 172	94.78 147

testgi		81.94 188	84.09 159	79.43 198	89.53 153	90.83 197	82.49 200	81.75 170	80.59 166	59.46 206	82.82 95	65.75 181	67.97 205	90.10 163	89.52 177	95.39 181	89.03 194

Baseline_NR-MVSNet		85.28 148	83.42 166	87.46 131	87.77 173	90.80 198	89.90 150	87.69 104	83.93 150	74.16 135	64.72 190	66.43 179	87.48 130	90.14 160	90.83 144	97.73 103	97.11 89

IterMVS		85.25 149	86.49 135	83.80 170	90.42 146	90.77 199	90.02 144	78.04 188	84.10 147	66.27 186	77.28 125	78.41 128	83.01 167	90.88 147	89.72 176	95.04 187	94.24 154
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
our_test_3					86.93 189	89.77 200	81.61 202

pmnet_mix02		80.14 195	80.21 196	80.06 195	86.61 194	89.66 201	80.40 205	82.20 165	82.29 160	61.35 201	71.52 156	66.67 178	76.75 193	82.55 206	80.18 209	93.05 195	88.62 197

Anonymous20231206		78.09 200	78.11 201	78.07 201	85.19 203	89.17 202	80.99 203	81.24 176	75.46 199	58.25 208	54.78 211	59.90 210	66.73 208	88.94 180	88.26 184	96.01 166	90.25 189

MDA-MVSNet-bldmvs		73.81 204	72.56 208	75.28 204	72.52 217	88.87 203	74.95 212	82.67 157	71.57 206	55.02 211	65.96 182	42.84 223	76.11 195	70.61 215	81.47 206	90.38 211	86.59 203

FMVSNet5		84.47 160	84.72 155	84.18 166	83.30 207	88.43 204	88.09 172	79.42 183	84.25 144	74.14 136	73.15 152	78.74 123	83.65 164	91.19 143	91.19 142	96.46 159	86.07 205

PM-MVS		80.29 194	79.30 197	81.45 194	81.91 209	88.23 205	82.61 199	79.01 184	79.99 173	67.15 181	69.07 167	51.39 217	82.92 168	87.55 187	85.59 192	95.08 186	93.28 167

MVS-HIRNet		78.16 199	77.57 203	78.83 199	85.83 199	87.76 206	76.67 209	70.22 211	75.82 198	67.39 178	55.61 207	70.52 158	81.96 175	86.67 193	85.06 197	90.93 208	81.58 211

test20.03		76.41 203	78.49 200	73.98 205	85.64 200	87.50 207	75.89 210	80.71 178	70.84 209	51.07 218	68.06 170	61.40 203	54.99 214	88.28 182	87.20 187	95.58 178	86.15 204

pmmvs-eth3d		79.78 197	77.58 202	82.34 189	81.57 210	87.46 208	82.92 198	81.28 174	75.33 200	71.34 150	61.88 197	52.41 216	81.59 179	87.56 186	86.90 188	95.36 183	91.48 177

N_pmnet		77.55 202	76.68 205	78.56 200	85.43 202	87.30 209	78.84 207	81.88 168	78.30 182	60.61 202	61.46 198	62.15 198	74.03 202	82.04 207	80.69 208	90.59 210	84.81 209

EU-MVSNet		78.43 198	80.25 195	76.30 203	83.81 206	87.27 210	80.99 203	79.52 182	76.01 195	54.12 213	70.44 162	64.87 188	67.40 207	86.23 194	85.54 194	91.95 204	91.41 178

MIMVSNet1		73.19 205	73.70 206	72.60 208	65.42 220	86.69 211	75.56 211	79.65 181	67.87 213	55.30 210	45.24 216	56.41 214	63.79 210	86.98 190	87.66 186	95.85 168	85.04 207

gm-plane-assit		77.65 201	78.50 199	76.66 202	87.96 169	85.43 212	64.70 218	74.50 197	64.15 216	51.26 217	61.32 200	58.17 213	84.11 162	95.16 65	93.83 82	97.45 118	91.41 178

new-patchmatchnet		72.32 206	71.09 209	73.74 206	81.17 211	84.86 213	72.21 215	77.48 190	68.32 212	54.89 212	55.10 209	49.31 220	63.68 211	79.30 211	76.46 212	93.03 196	84.32 210

new_pmnet		72.29 207	73.25 207	71.16 210	75.35 214	81.38 214	73.72 214	69.27 212	75.97 196	49.84 219	56.27 206	56.12 215	69.08 204	81.73 208	80.86 207	89.72 213	80.44 213

pmmvs3		71.13 208	71.06 210	71.21 209	73.54 216	80.19 215	71.69 216	64.86 215	62.04 218	52.10 215	54.92 210	48.00 221	75.03 198	83.75 204	83.24 203	90.04 212	85.27 206

ambc			67.96 211		73.69 215	79.79 216	73.82 213		71.61 205	59.80 205	46.00 215	20.79 225	66.15 209	86.92 191	80.11 210	89.13 214	90.50 186

FPMVS		69.87 209	67.10 212	73.10 207	84.09 205	78.35 217	79.40 206	76.41 193	71.92 204	57.71 209	54.06 213	50.04 218	56.72 212	71.19 214	68.70 214	84.25 215	75.43 215

DeepMVS_CX						71.82 218	68.37 217	48.05 220	77.38 186	46.88 220	65.77 183	47.03 222	67.48 206	64.27 218		76.89 220	76.72 214

PMMVS2		53.68 214	55.72 216	51.30 213	58.84 221	67.02 219	54.23 220	60.97 218	47.50 220	19.42 224	34.81 218	31.97 224	30.88 220	65.84 217	69.99 213	83.47 216	72.92 217

Gipuma		58.52 212	56.17 215	61.27 212	67.14 219	58.06 220	52.16 222	68.40 214	69.00 211	45.02 221	22.79 219	20.57 226	55.11 213	76.27 212	79.33 211	79.80 218	67.16 218
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	56.77 18	61.27 211	58.64 214	64.35 211	75.66 213	54.60 221	53.62 221	74.23 198	53.69 219	58.37 207	44.27 217	49.38 219	44.16 218	69.51 216	65.35 216	80.07 217	73.66 216
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	39.81 19	39.52 216	41.58 217	37.11 218	33.93 224	49.06 222	26.45 226	54.22 219	29.46 223	24.15 223	20.77 221	10.60 229	34.42 219	51.12 219	65.27 217	49.49 224	64.81 219
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				50.24 215	68.55 218	46.86 223	48.90 223	18.28 222	86.51 126	68.32 172	70.19 164	65.33 183	26.69 221	74.37 213	66.80 215	70.72 221

test_method		58.10 213	64.61 213	50.51 214	28.26 225	41.71 224	61.28 219	32.07 221	75.92 197	52.04 216	47.94 214	61.83 201	51.80 215	79.83 210	63.95 218	77.60 219	81.05 212

EMVS		39.04 217	34.32 219	44.54 217	58.25 222	39.35 225	27.61 225	62.55 217	35.99 221	16.40 226	20.04 222	14.77 227	44.80 216	33.12 221	44.10 220	57.61 223	52.89 221

E-PMN		40.00 215	35.74 218	44.98 216	57.69 223	39.15 226	28.05 224	62.70 216	35.52 222	17.78 225	20.90 220	14.36 228	44.47 217	35.89 220	47.86 219	59.15 222	56.47 220

testmvs		4.35 218	6.54 220	1.79 220	0.60 226	1.82 227	3.06 228	0.95 223	7.22 224	0.88 228	12.38 223	1.25 230	3.87 223	6.09 222	5.58 221	1.40 225	11.42 223

test123		3.48 219	5.31 221	1.34 221	0.20 228	1.52 228	2.17 229	0.58 224	6.13 225	0.31 229	9.85 224	0.31 231	3.90 222	2.65 223	5.28 222	0.87 226	11.46 222

uanet_test		0.00 220	0.00 222	0.00 222	0.00 229	0.00 229	0.00 230	0.00 226	0.00 226	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

sosnet-low-res		0.00 220	0.00 222	0.00 222	0.00 229	0.00 229	0.00 230	0.00 226	0.00 226	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

sosnet		0.00 220	0.00 222	0.00 222	0.00 229	0.00 229	0.00 230	0.00 226	0.00 226	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

RE-MVS-def										60.19 203

9.14												97.28 24

SR-MVS					98.93 20			96.00 18				97.75 15

MTAPA										95.36 2		97.46 21

MTMP										95.70 1		96.90 27

Patchmatch-RL test							18.47 227

mPP-MVS					98.76 25							95.49 40

NP-MVS									91.63 68

High-resolution multi-view benchmark