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.

SED-MVS		95.53 1	95.79 1	95.23 1	97.60 9	98.92 1	95.99 4	92.05 7	97.14 1	94.19 1	94.71 6	93.25 1	95.08 1	94.32 11	92.59 15	96.49 17	99.58 3

DPE-MVS		95.10 2	95.53 2	94.60 5	97.77 7	98.64 4	96.60 3	92.45 5	96.34 6	91.41 6	96.70 2	92.26 5	93.56 5	93.68 18	91.73 30	95.79 37	99.37 7
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		95.06 3	95.37 4	94.70 3	97.59 10	98.89 2	95.37 11	92.04 8	96.85 3	94.00 2	92.81 14	93.02 2	92.93 6	94.22 14	92.15 21	96.30 24	99.61 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++		95.03 4	95.03 5	95.03 2	97.91 5	98.84 3	95.80 5	91.88 10	96.65 5	93.15 3	93.79 8	90.11 11	95.03 2	94.20 16	92.39 16	96.44 21	99.22 10

MSP-MVS		95.00 5	95.47 3	94.45 6	96.78 18	98.11 9	95.72 7	90.91 14	96.68 4	91.57 5	96.98 1	89.47 13	94.76 3	95.24 3	92.15 21	96.98 7	99.64 1
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
CNVR-MVS		94.53 6	94.85 7	94.15 8	98.03 3	98.59 5	95.56 8	92.91 2	94.86 13	88.46 14	91.32 21	90.83 9	94.03 4	95.20 4	94.16 5	95.89 32	99.01 16

SF-MVS		94.40 7	94.15 12	94.70 3	98.25 2	98.24 7	96.86 2	93.46 1	94.87 12	90.26 9	95.96 3	88.42 16	92.76 9	92.29 31	90.84 41	96.62 13	98.44 26

APDe-MVS		94.31 8	94.30 10	94.33 7	97.57 11	98.06 11	95.79 6	91.98 9	95.50 9	92.19 4	95.25 4	87.97 19	92.93 6	93.01 24	91.02 39	95.52 39	99.29 8

MCST-MVS		94.10 9	94.77 8	93.31 10	98.31 1	98.34 6	95.43 9	92.54 4	94.41 16	83.05 30	91.38 19	90.97 8	92.24 13	95.05 6	94.02 6	98.31 1	99.20 11

HPM-MVS++		94.04 10	94.96 6	92.96 12	97.93 4	97.71 17	94.65 14	91.01 13	95.91 7	87.43 16	93.52 11	92.63 4	92.29 12	94.22 14	92.34 18	94.47 61	98.37 27

NCCC		93.59 11	94.00 14	93.10 11	97.90 6	97.93 13	95.40 10	92.39 6	94.47 15	84.94 21	91.21 22	89.32 14	92.53 10	93.90 17	92.98 12	95.44 41	98.22 30

SMA-MVS		93.47 12	94.29 11	92.52 14	97.72 8	97.77 16	94.46 17	90.19 17	94.96 11	87.15 17	90.15 25	90.99 7	91.49 16	94.31 12	93.33 10	94.10 67	98.53 24
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
APD-MVS		93.47 12	93.44 17	93.50 9	97.06 14	97.09 26	95.27 12	91.47 11	95.71 8	89.57 11	93.66 9	86.28 25	92.81 8	92.06 34	90.70 42	94.83 58	98.60 21
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SD-MVS		93.36 14	94.33 9	92.22 16	94.68 42	97.89 15	94.56 15	90.89 15	94.80 14	90.04 10	93.53 10	90.14 10	89.78 22	92.74 27	92.17 19	93.35 107	99.07 14
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
TSAR-MVS + MP.		93.07 15	93.53 16	92.53 13	94.23 45	97.54 20	94.75 13	89.87 18	95.26 10	89.20 13	93.16 12	88.19 18	92.15 14	91.79 39	89.65 58	94.99 54	99.16 12
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
DPM-MVS		92.86 16	93.19 19	92.47 15	95.78 34	97.40 21	97.39 1	92.56 3	92.88 24	81.84 37	81.31 38	92.95 3	91.21 17	96.54 1	97.33 1	96.01 30	93.94 110

SteuartSystems-ACMMP		92.31 17	93.31 18	91.15 22	96.88 16	97.36 22	93.95 21	89.44 20	92.62 25	83.20 27	94.34 7	85.55 27	88.95 29	93.07 23	91.90 26	94.51 60	98.30 28
Skip Steuart: Steuart Systems R&D Blog.
ACMMP_NAP		92.16 18	92.91 22	91.28 21	96.95 15	97.36 22	93.66 22	89.23 22	93.33 19	83.71 25	90.53 23	86.84 22	90.39 19	93.30 22	91.56 32	93.74 79	97.43 46

HFP-MVS		92.02 19	92.13 24	91.89 19	97.16 13	96.46 38	93.57 23	87.60 25	93.79 18	88.17 15	93.15 13	83.94 37	91.19 18	90.81 49	89.83 53	93.66 83	96.94 61

train_agg		91.99 20	93.71 15	89.98 27	96.42 26	97.03 28	94.31 19	89.05 23	93.33 19	77.75 45	95.06 5	88.27 17	88.38 36	92.02 36	91.41 34	94.00 71	98.84 19

DeepC-MVS_fast	86.59 2	91.69 21	91.39 27	92.05 18	97.43 12	96.92 31	94.05 20	90.23 16	93.31 22	83.19 28	77.91 44	84.23 33	92.42 11	94.62 9	94.83 3	95.00 53	97.88 36
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TSAR-MVS + GP.		91.29 22	93.11 21	89.18 32	87.81 88	96.21 44	92.51 32	83.83 44	94.24 17	83.77 24	91.87 18	89.62 12	90.07 20	90.40 54	90.31 46	97.09 6	99.10 13

ACMMPR		91.15 23	91.44 26	90.81 23	96.61 20	96.25 42	93.09 24	87.08 28	93.32 21	84.78 22	92.08 17	82.10 43	89.71 23	90.24 55	89.82 54	93.61 88	96.30 74

DeepPCF-MVS	86.71 1	91.00 24	94.05 13	87.43 43	95.58 37	98.17 8	86.22 73	88.59 24	97.01 2	76.77 53	85.11 34	88.90 15	87.29 43	95.02 7	94.69 4	90.15 178	99.48 6

TSAR-MVS + ACMM		90.98 25	93.18 20	88.42 37	95.69 35	96.73 33	94.52 16	86.97 31	92.99 23	76.32 54	92.31 16	86.64 23	84.40 69	92.97 25	92.02 23	92.62 130	98.59 22

MP-MVS		90.81 26	91.45 25	90.06 26	96.59 21	96.33 41	92.46 33	87.19 27	90.27 39	82.54 33	91.38 19	84.88 30	88.27 37	90.58 52	89.30 63	93.30 109	97.44 44
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CP-MVS		90.57 27	90.68 29	90.44 24	96.13 28	95.90 50	92.77 29	86.86 32	92.12 29	84.19 23	89.18 28	82.37 41	89.43 26	89.65 67	88.43 74	93.27 110	97.13 54

MSLP-MVS++		90.33 28	88.82 39	92.10 17	96.52 24	95.93 46	94.35 18	86.26 33	88.37 54	89.24 12	75.94 50	82.60 40	89.71 23	89.45 70	92.17 19	96.51 16	97.24 51

CANet		89.98 29	90.42 33	89.47 31	94.13 46	98.05 12	91.76 38	83.27 47	90.87 36	81.90 36	72.32 58	84.82 31	88.42 34	94.52 10	93.78 8	97.34 4	98.58 23

PGM-MVS		89.97 30	90.64 31	89.18 32	96.53 23	95.90 50	93.06 25	82.48 55	90.04 41	80.37 39	92.75 15	80.96 48	88.93 30	89.88 63	89.08 67	93.69 82	95.86 78

PHI-MVS		89.88 31	92.75 23	86.52 53	94.97 39	97.57 19	89.99 49	84.56 40	92.52 27	69.72 87	90.35 24	87.11 21	84.89 61	91.82 38	92.37 17	95.02 52	97.51 42

CSCG		89.81 32	89.69 34	89.96 28	96.55 22	97.90 14	92.89 27	87.06 29	88.74 51	86.17 18	78.24 43	86.53 24	84.75 64	87.82 91	90.59 43	92.32 135	98.01 33

X-MVS		89.73 33	90.65 30	88.66 35	96.44 25	95.93 46	92.26 35	86.98 30	90.73 37	76.32 54	89.56 27	82.05 44	86.51 49	89.98 61	89.60 59	93.43 102	96.72 69

EPNet		89.30 34	90.89 28	87.44 42	95.67 36	96.81 32	91.13 41	83.12 49	91.14 33	76.31 58	87.60 30	80.40 52	84.45 67	92.13 33	91.12 38	93.96 72	97.01 58
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepC-MVS	84.14 3	88.80 35	88.03 45	89.71 30	94.83 40	96.56 34	92.57 31	89.38 21	89.25 47	79.59 41	70.02 67	77.05 64	88.24 38	92.44 29	92.79 13	93.65 86	98.10 32
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CDPH-MVS		88.76 36	90.43 32	86.81 49	96.04 30	96.53 37	92.95 26	85.95 35	90.36 38	67.93 93	85.80 33	80.69 49	83.82 72	90.81 49	91.85 29	94.18 65	96.99 59

3Dnovator+	81.14 5	88.59 37	87.49 48	89.88 29	95.83 33	96.45 40	91.94 37	82.41 56	87.09 59	85.94 20	62.80 97	85.37 28	89.46 25	91.51 41	91.89 28	93.72 80	97.30 49

ACMMP		88.48 38	88.71 40	88.22 39	94.61 43	95.53 56	90.64 45	85.60 37	90.97 34	78.62 43	89.88 26	74.20 78	86.29 50	88.16 88	86.37 94	93.57 89	95.86 78
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
AdaColmap		88.46 39	85.75 62	91.62 20	96.25 27	95.35 60	90.71 43	91.08 12	90.22 40	86.17 18	74.33 54	73.67 81	92.00 15	86.31 107	85.82 102	93.52 92	94.53 97

MVS_0304		88.43 40	89.46 36	87.21 44	91.85 58	97.60 18	92.62 30	81.10 62	87.16 58	73.80 65	72.19 60	83.36 39	87.03 44	94.64 8	93.67 9	96.88 9	97.64 41

3Dnovator	80.58 8	88.20 41	86.53 54	90.15 25	96.86 17	96.46 38	91.97 36	83.06 50	85.16 64	83.66 26	62.28 100	82.15 42	88.98 28	90.99 46	92.65 14	96.38 23	96.03 75

CPTT-MVS		88.17 42	87.84 46	88.55 36	93.33 48	93.75 81	92.33 34	84.75 39	89.87 43	81.72 38	83.93 35	81.12 47	88.45 33	85.42 116	84.07 121	90.72 170	96.72 69

MVS_111021_HR		87.82 43	88.84 38	86.62 51	94.42 44	97.36 22	88.21 58	83.26 48	83.42 67	72.52 75	82.63 36	76.93 65	84.95 60	91.93 37	91.15 37	96.39 22	98.49 25

DELS-MVS		87.75 44	86.92 52	88.71 34	94.69 41	97.34 25	92.78 28	84.50 41	77.87 91	81.94 35	67.17 75	75.49 73	82.84 78	95.38 2	95.93 2	95.55 38	99.27 9
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
MVSTER		87.68 45	89.12 37	86.01 55	88.11 86	90.05 118	89.28 52	77.05 86	91.37 30	79.97 40	76.70 48	85.25 29	84.89 61	93.53 19	91.41 34	96.73 11	95.55 85

MVS_111021_LR		87.58 46	88.67 41	86.31 54	92.58 52	95.89 52	86.20 74	82.49 54	89.08 49	77.47 49	86.20 32	74.22 77	85.49 55	90.03 60	88.52 72	93.66 83	96.74 67

QAPM		87.06 47	86.46 55	87.75 40	96.63 19	97.09 26	91.71 39	82.62 53	80.58 80	71.28 80	66.04 82	84.24 32	87.01 45	89.93 62	89.91 52	97.26 5	97.44 44

PVSNet_BlendedMVS		86.98 48	87.05 50	86.90 46	93.03 49	96.98 29	86.57 70	81.82 58	89.78 44	82.78 31	71.54 61	66.07 112	80.73 90	93.46 20	91.97 24	96.45 19	99.53 4

PVSNet_Blended		86.98 48	87.05 50	86.90 46	93.03 49	96.98 29	86.57 70	81.82 58	89.78 44	82.78 31	71.54 61	66.07 112	80.73 90	93.46 20	91.97 24	96.45 19	99.53 4

ETV-MVS		86.94 50	89.49 35	83.95 69	87.28 95	95.61 55	83.58 101	76.37 93	92.59 26	73.20 67	80.35 39	76.42 68	87.38 42	92.20 32	90.45 45	95.90 31	98.83 20

CS-MVS-test		86.72 51	88.35 42	84.83 63	91.78 59	96.03 45	81.71 112	76.71 87	91.19 32	77.12 52	77.64 46	75.63 72	87.59 41	90.82 48	89.11 65	94.06 69	97.99 35

CS-MVS		86.70 52	87.61 47	85.65 56	91.33 63	95.64 54	84.73 90	76.64 89	88.68 52	77.78 44	74.87 51	72.86 85	89.09 27	92.89 26	90.18 49	94.31 64	98.16 31

DROMVSNet		86.42 53	88.31 43	84.20 67	86.61 102	94.08 75	86.20 74	72.18 124	89.06 50	76.02 59	74.48 53	80.47 51	88.90 31	92.03 35	90.07 50	95.30 42	98.00 34

OMC-MVS		86.38 54	86.21 59	86.57 52	92.30 54	94.35 74	87.60 62	83.51 46	92.32 28	77.37 50	72.27 59	77.83 57	86.59 48	87.62 93	85.95 99	92.08 139	93.11 123

HQP-MVS		86.17 55	87.35 49	84.80 64	91.41 62	92.37 98	91.05 42	84.35 43	88.52 53	64.21 100	87.05 31	68.91 101	84.80 63	89.12 73	88.16 78	92.96 121	97.31 48

canonicalmvs		85.93 56	86.26 58	85.54 57	88.94 76	95.44 57	89.56 50	76.01 95	87.83 55	77.70 46	76.43 49	68.66 103	87.80 40	87.02 96	91.51 33	93.25 111	96.95 60

MAR-MVS		85.65 57	86.30 57	84.88 62	95.51 38	95.89 52	86.50 72	76.71 87	89.23 48	68.59 90	70.93 65	74.49 75	88.55 32	89.40 71	90.30 47	93.42 103	93.88 114
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
PCF-MVS	82.38 4	85.52 58	84.41 67	86.81 49	91.51 61	96.23 43	90.27 46	89.81 19	77.87 91	70.67 83	69.20 69	77.86 55	85.55 54	85.92 112	86.38 93	93.03 118	97.43 46
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CLD-MVS		85.43 59	84.24 70	86.83 48	87.69 91	93.16 89	90.01 48	82.72 52	87.17 57	79.28 42	71.43 64	65.81 115	86.02 51	87.33 95	86.96 87	95.25 48	97.83 38
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
OpenMVS	77.91 11	85.09 60	83.42 74	87.03 45	96.12 29	96.55 36	89.36 51	81.59 60	79.19 87	75.20 61	55.84 127	79.04 54	84.45 67	88.47 82	89.35 62	95.48 40	95.48 86

TSAR-MVS + COLMAP		84.93 61	85.79 61	83.92 70	90.90 65	93.57 85	89.25 53	82.00 57	91.29 31	61.66 109	88.25 29	59.46 135	86.71 47	89.79 64	87.09 84	93.01 119	91.09 144

TAPA-MVS	80.99 7	84.83 62	84.42 66	85.31 59	91.89 57	93.73 83	88.53 57	82.80 51	89.99 42	69.78 86	71.53 63	75.03 74	85.47 56	86.26 108	84.54 116	93.39 105	89.90 154
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PLC	81.02 6	84.81 63	81.81 93	88.31 38	93.77 47	90.35 113	88.80 55	84.47 42	86.76 60	82.17 34	66.56 78	71.01 93	88.41 35	85.48 114	84.28 119	92.26 137	88.21 167
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EIA-MVS		84.75 64	86.43 56	82.79 75	86.88 98	95.36 59	82.84 108	76.39 92	87.61 56	71.03 81	74.33 54	71.12 92	85.16 57	89.69 66	88.70 71	94.40 62	98.23 29

CNLPA		84.72 65	82.14 87	87.73 41	92.85 51	93.83 80	84.70 91	85.07 38	90.90 35	83.16 29	56.28 123	71.53 89	88.14 39	84.19 121	84.00 125	92.48 132	94.26 104

MVS_Test		84.60 66	85.13 65	83.99 68	88.17 84	95.27 64	88.21 58	73.15 115	84.31 66	70.55 84	68.67 73	68.78 102	86.99 46	91.71 40	91.90 26	96.84 10	95.27 91

casdiffmvs_mvg		83.97 67	82.62 83	85.54 57	87.71 89	94.38 73	88.93 54	80.11 65	77.34 95	77.57 48	63.01 96	65.95 114	84.96 59	90.69 51	90.23 48	93.95 73	96.74 67
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
casdiffmvs		83.84 68	82.65 82	85.22 60	87.25 96	94.62 70	86.01 78	79.62 66	79.48 84	77.59 47	61.92 103	64.34 119	85.57 53	90.55 53	90.51 44	95.26 46	97.14 53
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		83.83 69	84.38 68	83.18 74	86.65 100	94.59 71	85.79 81	73.78 112	85.83 62	72.94 68	69.28 68	70.80 95	83.45 75	86.80 99	87.59 80	96.47 18	95.77 82

diffmvs		83.69 70	83.17 78	84.31 65	85.45 114	93.92 76	86.89 65	78.62 69	82.71 73	75.95 60	66.78 77	63.90 122	83.84 71	87.90 90	89.16 64	95.10 51	97.82 39
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CANet_DTU		83.33 71	86.59 53	79.53 99	88.88 77	94.87 67	86.63 69	68.85 147	85.45 63	50.54 154	77.86 45	69.94 98	85.62 52	92.63 28	90.88 40	96.63 12	94.46 98

DI_MVS_plusplus_trai		83.32 72	82.53 85	84.25 66	86.26 108	93.66 84	90.23 47	77.16 85	77.05 99	74.06 64	53.74 136	74.33 76	83.61 74	91.40 43	89.82 54	94.17 66	97.73 40

baseline1		82.63 73	82.02 88	83.34 73	88.30 83	91.89 102	88.03 61	80.86 63	75.05 106	65.96 95	64.27 89	72.20 87	80.01 94	91.32 44	89.56 60	96.90 8	89.85 155

PVSNet_Blended_VisFu		82.55 74	83.70 73	81.21 86	89.66 69	95.15 66	82.41 109	77.36 84	72.53 124	73.64 66	61.15 106	77.19 63	70.35 151	91.31 45	89.72 57	93.84 75	98.85 18

ET-MVSNet_ETH3D		82.37 75	85.68 63	78.51 108	62.90 210	94.66 68	87.06 64	73.57 113	83.13 69	61.52 111	78.37 42	76.01 70	89.99 21	84.14 122	89.03 68	96.03 29	94.42 99

PMMVS		82.26 76	85.48 64	78.51 108	85.92 111	91.92 101	78.30 140	70.77 132	86.30 61	61.11 113	82.46 37	70.88 94	84.70 65	88.05 89	84.78 112	90.24 177	93.98 108

ACMP	79.58 9	82.23 77	81.82 92	82.71 76	88.15 85	90.95 110	85.23 86	78.52 71	81.70 75	72.52 75	78.41 41	60.63 130	80.48 92	82.88 132	83.44 129	91.37 156	94.70 95
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
CHOSEN 280x420		82.15 78	85.87 60	77.80 113	86.54 104	93.42 87	81.74 111	59.96 189	78.99 89	63.99 101	74.50 52	83.95 36	80.99 85	89.53 69	85.01 107	93.56 91	95.71 84

LGP-MVS_train		82.12 79	82.57 84	81.59 82	89.26 73	90.23 116	88.76 56	78.05 72	81.26 77	61.64 110	79.52 40	62.11 125	79.59 96	85.20 117	84.68 114	92.27 136	95.02 93

FMVSNet3		81.93 80	81.98 89	81.88 81	79.49 150	87.02 133	88.15 60	72.57 118	83.02 70	72.63 72	56.55 119	73.48 82	82.34 81	91.49 42	91.20 36	96.07 25	91.13 143

test2506		81.91 81	81.78 95	82.06 80	89.09 74	95.32 61	84.61 93	77.54 80	74.61 110	68.77 89	63.80 93	67.53 106	77.09 105	90.19 57	89.01 69	95.27 43	92.00 136

thisisatest0530		81.67 82	84.27 69	78.63 104	85.53 112	93.88 79	81.77 110	73.84 109	81.35 76	63.85 103	68.79 71	77.64 59	73.02 132	88.73 80	85.73 103	93.76 78	93.80 118

tttt0517		81.51 83	84.12 72	78.47 110	85.33 116	93.74 82	81.42 115	73.84 109	81.21 78	63.59 104	68.73 72	77.46 62	73.02 132	88.47 82	85.73 103	93.63 87	93.49 122

FA-MVS(training)		81.41 84	81.98 89	80.76 92	87.58 92	94.59 71	83.09 103	61.18 186	79.80 83	74.74 62	58.46 112	69.76 99	82.12 82	88.90 76	87.00 85	95.83 35	95.33 88

OPM-MVS		81.34 85	78.18 111	85.02 61	91.27 64	91.78 103	90.66 44	83.62 45	62.39 153	65.91 96	63.35 94	64.33 120	85.03 58	87.77 92	85.88 101	93.66 83	91.75 140
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
baseline2		81.21 86	83.36 77	78.70 102	83.22 129	92.71 91	80.32 121	74.25 108	80.39 81	63.94 102	68.89 70	68.44 104	74.67 118	89.61 68	86.68 91	95.83 35	96.81 66

IS_MVSNet		80.92 87	84.14 71	77.16 116	87.43 93	93.90 78	80.44 117	74.64 102	75.05 106	61.10 114	65.59 84	76.89 66	67.39 159	90.88 47	90.05 51	91.95 143	96.62 72

ACMM	78.09 10	80.91 88	78.39 108	83.86 71	89.61 72	87.71 130	85.16 87	80.67 64	79.04 88	74.18 63	63.82 92	60.84 129	82.59 79	84.33 119	83.59 128	90.96 164	89.39 160
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EPP-MVSNet		80.82 89	82.79 80	78.52 106	86.31 107	92.37 98	79.83 124	74.51 103	73.79 117	64.46 99	67.01 76	80.63 50	74.33 121	85.63 113	84.35 118	91.68 149	95.79 81

CostFormer		80.72 90	81.81 93	79.44 101	86.50 105	91.65 104	84.31 95	59.84 190	80.86 79	72.69 70	62.46 99	73.74 79	79.93 95	82.58 136	84.50 117	93.37 106	96.90 64

GBi-Net		80.72 90	80.49 97	81.00 89	78.18 154	86.19 147	86.73 66	72.57 118	83.02 70	72.63 72	56.55 119	73.48 82	80.99 85	86.57 101	86.83 88	94.89 55	90.77 147

test1		80.72 90	80.49 97	81.00 89	78.18 154	86.19 147	86.73 66	72.57 118	83.02 70	72.63 72	56.55 119	73.48 82	80.99 85	86.57 101	86.83 88	94.89 55	90.77 147

UGNet		80.71 93	83.09 79	77.93 112	87.02 97	92.71 91	80.28 122	76.53 90	73.83 116	71.35 79	70.07 66	73.71 80	58.93 179	87.39 94	86.97 86	93.48 99	96.94 61
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
CHOSEN 1792x2688		80.23 94	79.16 105	81.48 84	91.97 55	96.56 34	86.18 76	75.40 99	76.17 102	61.32 112	37.43 197	61.08 128	76.52 111	92.35 30	91.64 31	97.46 3	98.86 17

thres100view900		79.83 95	77.79 115	82.21 77	88.42 80	93.54 86	87.07 63	81.11 61	70.15 131	61.01 115	56.65 117	51.22 152	81.78 83	89.77 65	85.95 99	93.84 75	97.26 50

Effi-MVS+		79.80 96	80.04 99	79.52 100	85.53 112	93.31 88	85.28 84	70.68 134	74.15 112	58.79 124	62.03 102	60.51 131	83.37 76	88.41 84	86.09 98	93.49 98	95.80 80

ECVR-MVS		79.76 97	78.27 109	81.50 83	89.09 74	95.32 61	84.61 93	77.54 80	74.61 110	65.38 97	50.22 148	56.31 146	77.09 105	90.19 57	89.01 69	95.27 43	92.25 131

DCV-MVSNet		79.76 97	79.17 104	80.44 95	84.65 120	84.51 171	84.20 96	72.36 123	75.17 105	70.81 82	66.21 81	66.56 109	80.99 85	82.89 131	84.56 115	89.65 183	94.30 103

FC-MVSNet-train		79.54 99	78.20 110	81.09 88	86.55 103	88.63 126	79.96 123	78.53 70	70.90 129	68.24 91	65.87 83	56.45 145	80.29 93	86.20 110	84.08 120	92.97 120	95.31 90

test-LLR		79.52 100	83.42 74	74.97 125	81.79 134	91.26 105	76.17 161	70.57 135	77.71 93	52.14 141	66.26 79	77.47 60	73.10 128	87.02 96	87.16 82	96.05 27	97.02 56

FMVSNet2		79.24 101	78.14 112	80.53 94	78.18 154	86.19 147	86.73 66	71.91 125	72.97 119	70.48 85	50.63 146	66.56 109	80.99 85	90.10 59	89.77 56	94.89 55	90.77 147

TESTMET0.1,1		79.15 102	83.42 74	74.18 131	79.81 148	91.26 105	76.17 161	67.83 160	77.71 93	52.14 141	66.26 79	77.47 60	73.10 128	87.02 96	87.16 82	96.05 27	97.02 56

tfpn200view9		79.05 103	77.21 119	81.18 87	88.42 80	92.55 96	85.12 88	77.94 74	70.15 131	61.01 115	56.65 117	51.22 152	81.11 84	88.23 85	84.80 111	93.50 97	96.90 64

test1111		78.99 104	77.77 116	80.42 96	88.64 78	95.31 63	83.39 102	77.67 78	72.76 122	61.91 107	49.58 151	55.59 148	75.67 116	90.23 56	89.09 66	95.23 49	91.83 139

PatchMatch-RL		78.75 105	76.47 126	81.41 85	88.53 79	91.10 107	78.09 141	77.51 83	77.33 96	71.98 77	64.38 88	48.10 164	82.55 80	84.06 123	82.35 138	89.78 180	87.97 169

LS3D		78.72 106	75.79 130	82.15 78	91.91 56	89.39 123	83.66 99	85.88 36	76.81 100	59.22 123	57.67 114	58.53 139	83.72 73	82.07 141	81.63 149	88.50 191	84.39 180

thres200		78.69 107	76.71 122	80.99 91	88.35 82	92.56 94	86.03 77	77.94 74	66.27 138	60.66 117	56.08 124	51.11 154	79.45 97	88.23 85	85.54 106	93.52 92	97.20 52

Anonymous20231211		78.61 108	75.57 133	82.15 78	84.43 124	90.26 114	84.08 97	77.68 77	71.09 127	72.90 69	39.24 191	66.21 111	84.23 70	82.15 139	84.04 122	89.61 184	96.03 75

IB-MVS	74.10 12	78.52 109	78.51 107	78.52 106	90.15 67	95.39 58	71.95 181	77.53 82	74.95 108	77.25 51	58.93 110	55.92 147	58.37 181	79.01 166	87.89 79	95.88 33	97.47 43
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
EPNet_dtu		78.49 110	81.96 91	74.45 130	92.57 53	88.74 125	82.98 104	78.83 68	83.28 68	44.64 185	77.40 47	67.73 105	53.98 190	85.44 115	84.91 108	93.71 81	86.22 175
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
thres400		78.39 111	76.39 127	80.73 93	88.02 87	92.94 90	84.77 89	78.88 67	65.20 146	59.70 121	55.20 130	50.85 155	79.45 97	88.81 77	84.81 110	93.57 89	96.91 63

UA-Net		78.30 112	80.92 96	75.25 124	87.42 94	92.48 97	79.54 127	75.49 98	60.47 157	60.52 118	68.44 74	84.08 35	57.54 183	88.54 81	88.45 73	90.96 164	83.97 182

Vis-MVSNet (Re-imp)		78.28 113	82.68 81	73.16 142	86.64 101	92.68 93	78.07 142	74.48 104	74.05 113	53.47 134	64.22 90	76.52 67	54.28 186	88.96 75	88.29 76	92.03 141	94.00 107

MSDG		78.11 114	73.17 146	83.86 71	91.78 59	86.83 135	85.25 85	86.02 34	72.84 121	69.69 88	51.43 143	54.00 150	77.61 101	81.95 144	82.27 140	92.83 126	82.91 187

HyFIR lowres test		78.08 115	76.81 120	79.56 98	90.77 66	94.64 69	82.97 105	69.85 140	69.81 133	59.53 122	33.52 202	64.66 116	78.97 99	88.77 79	88.38 75	95.27 43	97.86 37

GeoE		78.04 116	77.52 118	78.65 103	84.51 122	90.84 111	80.94 116	69.24 145	72.86 120	66.06 94	53.45 137	60.46 132	77.37 102	84.20 120	84.85 109	93.78 77	96.00 77

test-mter		77.90 117	82.44 86	72.60 147	78.52 152	90.24 115	73.85 174	65.31 174	76.37 101	51.29 145	65.58 85	75.94 71	71.36 142	85.98 111	86.26 95	95.26 46	96.71 71

thres600view7		77.66 118	75.67 131	79.98 97	87.71 89	92.56 94	83.79 98	77.94 74	64.41 148	58.69 125	54.32 135	50.54 156	78.23 100	88.23 85	83.06 132	93.52 92	96.55 73

MS-PatchMatch		77.47 119	76.48 125	78.63 104	89.89 68	90.42 112	85.42 83	69.53 142	70.79 130	60.43 119	50.05 149	70.62 97	70.66 148	86.71 100	82.54 135	95.86 34	84.23 181

Fast-Effi-MVS+		77.37 120	76.68 123	78.17 111	82.84 131	89.94 119	81.47 114	68.01 156	72.99 118	60.26 120	55.07 131	53.20 151	82.99 77	86.47 106	86.12 97	93.46 100	92.98 126

Vis-MVSNet		77.24 121	79.99 102	74.02 132	84.62 121	93.92 76	80.33 120	72.55 121	62.58 152	55.25 132	64.45 87	69.49 100	57.00 184	88.78 78	88.21 77	94.36 63	92.54 128
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
MDTV_nov1_ep13		77.20 122	80.04 99	73.90 134	82.22 132	90.14 117	79.25 131	61.52 184	78.63 90	56.98 126	65.52 86	72.80 86	73.05 130	80.93 152	83.20 130	90.36 174	89.05 163

EPMVS		77.16 123	79.08 106	74.92 126	86.73 99	91.98 100	78.62 136	55.44 198	79.43 85	56.59 128	61.24 105	70.73 96	76.97 108	80.59 155	81.43 155	95.15 50	88.17 168

tpm cat1		76.93 124	76.19 129	77.79 114	85.08 119	88.58 127	82.96 106	59.33 191	75.72 104	72.64 71	51.25 144	64.41 118	75.74 115	77.90 174	80.10 171	90.97 163	95.35 87

PatchmatchNet		76.85 125	80.03 101	73.15 143	84.08 126	91.04 109	77.76 146	55.85 197	79.43 85	52.74 139	62.08 101	76.02 69	74.56 119	79.92 160	81.41 156	93.92 74	90.29 152
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
IterMVS-LS		76.80 126	76.33 128	77.35 115	84.07 127	84.11 172	81.54 113	68.52 149	66.17 139	61.74 108	57.84 113	64.31 121	74.88 117	83.48 128	86.21 96	93.34 108	92.16 133
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CDS-MVSNet		76.57 127	76.78 121	76.32 119	80.94 141	89.75 120	82.94 107	72.64 117	59.01 163	62.95 106	58.60 111	62.67 124	66.91 161	86.26 108	87.20 81	91.57 151	93.97 109
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SCA		76.41 128	79.90 103	72.35 151	84.26 125	85.24 162	75.57 168	54.56 200	79.95 82	52.72 140	64.22 90	77.84 56	73.73 125	80.48 156	81.37 157	93.25 111	90.20 153

tpmrst		76.27 129	77.65 117	74.66 128	86.13 110	89.53 122	79.31 130	54.91 199	77.19 98	56.27 129	55.87 126	64.58 117	77.25 103	80.85 153	80.21 168	94.07 68	95.32 89

dps		75.76 130	75.02 135	76.63 118	84.51 122	88.12 128	77.51 147	58.33 193	75.91 103	71.98 77	57.37 115	57.85 140	76.81 110	77.89 175	78.40 180	90.63 171	89.63 157

CR-MVSNet		74.84 131	77.91 113	71.26 164	81.77 136	85.52 158	78.32 138	54.14 202	74.05 113	51.09 148	50.00 150	71.38 91	70.77 146	86.48 104	84.03 123	91.46 155	93.92 111

Effi-MVS+-dtu		74.57 132	74.60 139	74.53 129	81.38 138	86.74 137	80.39 119	67.70 161	67.36 137	53.06 135	59.86 108	57.50 141	75.84 114	80.19 158	78.62 178	88.79 190	91.95 138

RPSCF		74.27 133	73.24 145	75.48 123	81.01 140	80.18 194	76.24 160	72.37 122	74.84 109	68.24 91	72.47 57	67.39 107	73.89 122	71.05 199	69.38 206	81.14 210	77.37 199

FMVSNet1		74.26 134	71.95 151	76.95 117	74.28 186	83.94 174	83.61 100	69.99 138	57.08 169	65.08 98	42.39 180	57.41 142	76.98 107	86.57 101	86.83 88	91.77 148	89.42 158

GA-MVS		73.62 135	74.52 140	72.58 148	79.93 146	89.29 124	78.02 143	71.67 128	60.79 156	42.68 189	54.41 134	49.07 160	70.07 152	89.39 72	86.55 92	93.13 116	92.12 134

Fast-Effi-MVS+-dtu		73.56 136	75.32 134	71.50 160	80.35 143	86.83 135	79.72 125	58.07 194	67.64 136	44.83 182	60.28 107	54.07 149	73.59 127	81.90 146	82.30 139	92.46 133	94.18 105

tpm		73.50 137	74.85 136	71.93 154	83.19 130	86.84 134	78.61 137	55.91 196	65.64 141	48.90 161	56.30 122	61.09 127	72.31 134	79.10 165	80.61 167	92.68 128	94.35 102

RPMNet		73.46 138	77.85 114	68.34 174	81.71 137	85.52 158	73.83 175	50.54 209	74.05 113	46.10 176	53.03 140	71.91 88	66.31 163	83.55 126	82.18 142	91.55 153	94.71 94

USDC		73.43 139	72.31 149	74.73 127	80.86 142	86.21 145	80.42 118	71.83 127	71.69 126	46.94 169	59.60 109	42.58 185	76.47 112	82.66 135	81.22 160	91.88 145	82.24 193

pmmvs4		73.38 140	71.53 154	75.55 122	75.95 172	85.24 162	77.25 151	71.59 129	71.03 128	63.10 105	49.09 156	44.22 175	73.73 125	82.04 142	80.18 169	91.68 149	88.89 165

UniMVSNet_NR-MVSNet		73.11 141	72.59 147	73.71 137	76.90 163	86.58 141	77.01 152	75.82 96	65.59 142	48.82 162	50.97 145	48.42 162	71.61 138	79.19 164	83.03 133	92.11 138	94.37 100

FMVSNet5		72.83 142	73.89 143	71.59 158	67.42 204	76.28 202	75.88 165	63.74 178	77.27 97	54.59 133	53.32 138	71.48 90	73.85 123	81.95 144	81.69 147	94.06 69	75.20 203

PatchT		72.66 143	76.58 124	68.09 176	79.02 151	86.09 151	59.81 203	51.78 207	72.00 125	51.09 148	46.84 160	66.70 108	70.77 146	86.48 104	84.03 123	96.07 25	93.92 111

ACMH	71.22 14	72.65 144	70.13 159	75.59 121	86.19 109	86.14 150	75.76 166	77.63 79	54.79 177	46.16 175	53.28 139	47.28 166	77.24 104	78.91 167	81.18 161	90.57 172	89.33 161
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IterMVS		72.43 145	74.05 141	70.55 168	80.34 144	81.17 188	77.44 148	61.00 188	63.57 151	46.82 171	55.88 125	59.09 138	65.03 165	83.15 129	83.83 126	92.67 129	91.65 141
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMH+	72.14 13	72.38 146	69.34 166	75.93 120	85.21 117	84.89 166	76.96 155	76.04 94	59.76 158	51.63 144	50.37 147	48.69 161	76.90 109	76.06 183	78.69 176	88.85 189	86.90 173

DU-MVS		72.19 147	71.35 155	73.17 141	75.95 172	86.02 152	77.01 152	74.42 105	65.39 144	48.82 162	49.10 154	42.81 183	71.61 138	78.67 168	83.10 131	91.22 159	94.37 100

IterMVS-SCA-FT		72.18 148	73.96 142	70.11 170	80.15 145	81.11 189	77.42 149	61.09 187	63.67 150	46.73 172	55.77 128	59.15 137	63.95 168	82.83 133	83.70 127	91.31 157	91.49 142

UniMVSNet (Re)		72.12 149	72.28 150	71.93 154	76.77 164	87.38 132	75.73 167	73.51 114	65.76 140	50.24 156	48.65 157	46.49 167	63.85 169	80.10 159	82.47 136	91.49 154	95.13 92

ADS-MVSNet		72.11 150	73.72 144	70.24 169	81.24 139	86.59 140	74.75 171	50.56 208	72.58 123	49.17 159	55.40 129	61.46 126	73.80 124	76.01 184	78.14 181	91.93 144	85.86 176

gg-mvs-nofinetune		72.10 151	74.79 137	68.97 173	83.31 128	95.22 65	85.66 82	48.77 210	35.68 213	22.17 219	30.49 205	77.73 58	76.37 113	94.30 13	93.03 11	97.55 2	97.05 55

TAMVS		72.06 152	71.76 153	72.41 150	76.68 165	88.12 128	74.82 170	68.09 154	53.52 182	56.91 127	52.94 141	56.93 144	66.91 161	81.37 149	82.44 137	91.07 161	86.99 172

v2v482		71.73 153	69.80 161	73.99 133	75.88 176	86.66 139	79.58 126	71.90 126	57.58 167	50.41 155	45.35 164	43.24 181	73.05 130	79.69 161	82.18 142	93.08 117	93.87 115

test0.0.03 1		71.70 154	74.68 138	68.23 175	81.79 134	83.81 175	68.64 185	70.57 135	68.81 135	43.47 186	62.77 98	60.09 134	51.77 197	82.48 137	81.67 148	93.16 114	83.13 185

V42		71.58 155	70.11 160	73.30 140	75.66 179	86.68 138	79.17 133	69.92 139	59.29 162	52.80 138	44.36 168	45.66 169	68.83 153	79.48 163	81.49 152	93.44 101	93.82 117

NR-MVSNet		71.47 156	71.11 156	71.90 156	77.73 159	86.02 152	76.88 156	74.42 105	65.39 144	46.09 177	49.10 154	39.87 198	64.27 167	81.40 148	82.24 141	91.99 142	93.75 119

v8		71.42 157	69.69 162	73.43 139	76.45 168	85.12 165	79.53 128	67.47 164	59.34 161	52.90 137	44.60 166	45.82 168	71.05 144	79.56 162	81.45 154	93.17 113	91.96 137

TranMVSNet+NR-MVSNet		71.12 158	70.24 158	72.15 152	76.01 171	84.80 168	76.55 158	75.65 97	61.99 154	45.29 180	48.42 158	43.07 182	67.55 157	78.28 171	82.83 134	91.85 146	92.29 129

v10		70.97 159	69.44 163	72.75 144	75.90 175	84.58 170	79.43 129	66.45 169	58.07 165	49.93 157	43.87 174	43.68 176	71.91 136	82.04 142	81.70 146	92.89 124	92.11 135

v1144		70.93 160	69.42 165	72.70 145	75.48 180	86.26 143	79.22 132	69.39 144	55.61 174	48.05 167	43.47 175	42.55 186	71.51 140	82.11 140	81.74 145	92.56 131	94.17 106

thisisatest0515		70.62 161	71.94 152	69.07 172	76.48 167	85.59 157	68.03 186	68.02 155	59.70 159	52.94 136	52.19 142	50.36 157	58.10 182	83.15 129	81.63 149	90.87 167	90.99 145

Baseline_NR-MVSNet		70.61 162	68.87 169	72.65 146	75.95 172	80.49 192	75.92 164	74.75 101	65.10 147	48.78 164	41.28 186	44.28 174	68.45 154	78.67 168	79.64 172	92.04 140	92.62 127

v148		70.34 163	68.46 172	72.54 149	76.04 170	86.38 142	74.83 169	72.73 116	55.88 173	55.26 131	43.32 177	43.49 177	64.52 166	76.93 181	80.11 170	91.85 146	93.11 123

v1192		70.32 164	68.77 170	72.12 153	74.76 182	85.62 156	78.73 134	68.53 148	55.08 176	46.34 174	42.39 180	40.67 193	71.90 137	82.27 138	81.53 151	92.43 134	93.86 116

v144192		70.10 165	68.55 171	71.90 156	74.55 183	85.67 155	77.81 144	68.22 153	54.65 178	46.91 170	42.76 178	41.27 190	70.95 145	80.48 156	81.11 165	92.96 121	93.90 113

pmmvs5		70.01 166	69.31 167	70.82 167	75.80 178	86.26 143	72.94 176	67.91 157	53.84 181	47.22 168	47.31 159	41.47 189	67.61 156	83.93 125	81.93 144	93.42 103	90.42 151

COLMAP_ROB	66.31 15	69.91 167	66.61 177	73.76 135	86.44 106	82.76 179	76.59 157	76.46 91	63.82 149	50.92 152	45.60 163	49.13 159	65.87 164	74.96 189	74.45 196	86.30 200	75.57 202
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
v1921920		69.85 168	68.38 173	71.58 159	74.35 184	85.39 160	77.78 145	67.88 159	54.64 179	45.39 179	42.11 183	39.97 197	71.10 143	81.68 147	81.17 163	92.96 121	93.69 121

pm-mvs1		69.62 169	68.07 175	71.44 161	77.21 161	85.32 161	76.11 163	71.05 130	46.55 202	51.17 147	41.83 184	48.20 163	61.81 175	84.00 124	81.14 164	91.28 158	89.42 158

UniMVSNet_ETH3D		69.49 170	65.86 179	73.72 136	76.51 166	85.88 154	78.65 135	70.52 137	48.08 199	55.71 130	37.64 194	40.56 194	71.38 141	75.05 188	81.49 152	89.57 186	92.29 129

tfpnnormal		69.29 171	65.58 180	73.62 138	79.87 147	84.82 167	76.97 154	75.12 100	45.29 203	49.03 160	35.57 200	37.20 206	68.02 155	82.70 134	81.24 159	92.69 127	92.20 132

v1240		69.28 172	67.82 176	71.00 166	74.09 188	85.13 164	76.54 159	67.28 166	53.17 183	44.70 183	41.55 185	39.38 199	70.51 150	81.29 150	81.18 161	92.88 125	93.02 125

CVMVSNet		68.95 173	70.79 157	66.79 182	79.69 149	83.75 176	72.05 180	70.90 131	56.20 171	36.30 201	54.94 133	59.22 136	54.03 189	78.33 170	78.65 177	87.77 196	84.44 179

MIMVSNet		68.66 174	69.43 164	67.76 177	64.92 207	84.68 169	74.16 172	54.10 204	60.85 155	51.27 146	39.47 190	49.48 158	67.48 158	84.86 118	85.57 105	94.63 59	81.10 194

TDRefinement		67.82 175	64.91 186	71.22 165	82.08 133	81.45 184	77.42 149	73.79 111	59.62 160	48.35 166	42.35 182	42.40 187	60.87 177	74.69 190	74.64 195	84.83 204	79.20 197

anonymousdsp		67.61 176	68.94 168	66.04 183	71.44 200	83.97 173	66.45 190	63.53 180	50.54 192	42.42 190	49.39 152	45.63 170	62.84 172	77.99 173	81.34 158	89.59 185	93.75 119

TinyColmap		67.16 177	63.51 193	71.42 162	77.94 157	79.54 198	72.80 177	69.78 141	56.58 170	45.52 178	44.53 167	33.53 211	74.45 120	76.91 182	77.06 187	88.03 195	76.41 200

FC-MVSNet-test		67.04 178	72.47 148	60.70 200	76.92 162	81.41 185	61.52 200	69.45 143	65.58 143	26.74 215	61.79 104	60.40 133	41.17 206	77.60 177	77.78 183	88.41 192	82.70 189

TransMVSNet (Re)		66.87 179	64.30 188	69.88 171	78.32 153	81.35 187	73.88 173	74.34 107	43.19 207	45.20 181	40.12 188	42.37 188	55.97 185	80.85 153	79.15 173	91.56 152	83.06 186

CMPMVS	50.59 17	66.74 180	62.72 197	71.42 162	85.40 115	89.72 121	72.69 178	70.72 133	51.24 188	51.75 143	38.91 192	44.40 172	63.74 170	70.84 200	71.52 200	84.19 205	72.45 207
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
v7n		66.43 181	65.51 181	67.51 178	71.63 199	83.10 177	70.89 184	65.02 175	50.13 195	44.68 184	39.59 189	38.77 200	62.57 173	77.59 178	78.91 174	90.29 176	90.44 150

EG-PatchMatch MVS		66.23 182	65.20 183	67.43 179	77.74 158	86.20 146	72.51 179	63.68 179	43.95 205	43.44 187	36.22 199	45.43 171	54.04 188	81.00 151	80.95 166	93.15 115	82.67 190

WR-MVS		64.98 183	66.59 178	63.09 193	74.34 185	82.68 180	64.98 196	69.17 146	54.42 180	36.18 202	44.32 169	44.35 173	44.65 200	73.60 191	77.83 182	89.21 188	88.96 164

gm-plane-assit		64.86 184	68.15 174	61.02 199	76.44 169	68.29 211	41.60 216	53.37 205	34.68 215	26.19 217	33.22 203	57.09 143	71.97 135	95.12 5	93.97 7	96.54 15	94.66 96

CP-MVSNet		64.84 185	64.97 184	64.69 188	72.09 195	81.04 190	66.66 189	67.53 163	52.45 185	37.40 197	44.00 173	38.37 202	53.54 192	72.26 195	76.93 188	90.94 166	89.75 156

MDTV_nov1_ep13_2view		64.72 186	64.94 185	64.46 189	71.14 201	81.94 183	67.53 187	54.54 201	55.92 172	43.29 188	44.02 172	43.27 180	59.87 178	71.85 197	74.77 194	90.36 174	82.82 188

MVS-HIRNet		64.63 187	64.03 192	65.33 185	75.01 181	82.84 178	58.54 207	52.10 206	55.42 175	49.29 158	29.83 208	43.48 178	66.97 160	78.28 171	78.81 175	90.07 179	79.52 196

pmnet_mix02		64.58 188	64.11 191	65.12 186	74.16 187	80.17 195	63.24 198	67.91 157	57.87 166	41.69 191	45.86 162	40.99 192	53.97 191	69.92 203	71.67 199	89.77 181	82.29 192

LTVRE_ROB	63.07 16	64.49 189	63.16 196	66.04 183	77.47 160	82.64 181	70.98 183	65.02 175	34.01 216	29.61 211	49.12 153	35.58 210	70.57 149	75.10 187	78.45 179	82.60 208	87.24 171
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
PEN-MVS		64.35 190	64.29 189	64.42 190	72.67 191	79.83 196	66.97 188	68.24 152	51.21 189	35.29 204	44.09 170	38.51 201	52.36 195	71.06 198	77.65 184	90.99 162	87.68 170

pmmvs6		64.24 191	61.77 201	67.12 180	72.39 194	81.39 186	71.33 182	65.95 173	36.05 212	48.48 165	30.55 204	43.45 179	58.75 180	77.88 176	76.36 191	85.83 201	86.70 174

pmmvs-eth3d		64.24 191	61.96 199	66.90 181	66.35 205	76.04 204	66.09 192	66.31 170	52.59 184	50.94 151	37.61 195	32.79 213	62.43 174	75.78 185	75.48 193	89.27 187	83.39 184

PS-CasMVS		64.22 193	64.19 190	64.25 191	71.86 197	80.67 191	66.42 191	67.43 165	50.64 191	36.48 199	42.60 179	37.46 205	52.56 194	71.98 196	76.69 190	90.76 168	89.29 162

WR-MVS_H		64.14 194	65.36 182	62.71 195	72.47 193	82.33 182	65.13 193	66.99 167	51.81 187	36.47 200	43.33 176	42.77 184	43.99 202	72.41 194	75.99 192	91.20 160	88.86 166

SixPastTwentyTwo		63.75 195	63.42 194	64.13 192	72.91 190	80.34 193	61.29 201	63.90 177	49.58 196	40.42 193	54.99 132	37.13 207	60.90 176	68.46 204	70.80 201	85.37 203	82.65 191

PM-MVS		63.52 196	62.51 198	64.70 187	64.79 209	76.08 203	65.07 194	62.08 182	58.13 164	46.56 173	44.98 165	31.31 214	62.89 171	72.58 193	69.93 205	86.81 198	84.55 178

DTE-MVSNet		63.26 197	63.41 195	63.08 194	72.59 192	78.56 199	65.03 195	68.28 151	50.53 193	32.38 208	44.03 171	37.79 204	49.48 198	70.83 201	76.73 189	90.73 169	85.42 177

testgi		63.11 198	64.88 187	61.05 198	75.83 177	78.51 200	60.42 202	66.20 171	48.77 197	34.56 205	56.96 116	40.35 195	40.95 207	77.46 179	77.22 186	88.37 194	74.86 205

GG-mvs-BLEND		62.08 199	88.31 43	31.46 213	0.16 224	98.10 10	91.57 40	0.09 221	85.07 65	0.21 225	73.90 56	83.74 38	0.19 222	88.98 74	89.39 61	96.58 14	99.02 15

Anonymous20231206		62.05 200	61.83 200	62.30 197	72.09 195	77.84 201	63.10 199	67.62 162	50.20 194	36.68 198	29.59 209	37.05 208	43.90 203	77.33 180	77.31 185	90.41 173	83.49 183

N_pmnet		60.52 201	58.83 204	62.50 196	68.97 203	75.61 205	59.72 205	66.47 168	51.90 186	41.26 192	35.42 201	35.63 209	52.25 196	67.07 207	70.08 204	86.35 199	76.10 201

EU-MVSNet		58.73 202	60.92 202	56.17 203	66.17 206	72.39 208	58.85 206	61.24 185	48.47 198	27.91 213	46.70 161	40.06 196	39.07 208	68.27 205	70.34 203	83.77 206	80.23 195

test20.03		57.93 203	59.22 203	56.44 202	71.84 198	73.78 207	53.55 210	65.96 172	43.02 208	28.46 212	37.50 196	38.17 203	30.41 212	75.25 186	74.42 197	88.41 192	72.37 208

MDA-MVSNet-bldmvs		54.99 204	52.66 208	57.71 201	52.74 215	74.87 206	55.61 208	68.41 150	43.65 206	32.54 206	37.93 193	22.11 220	54.11 187	48.85 214	67.34 207	82.85 207	73.88 206

new-patchmatchnet		53.91 205	52.69 207	55.33 205	64.83 208	70.90 209	52.24 211	61.75 183	41.09 209	30.82 209	29.90 207	28.22 216	36.69 209	61.52 209	65.08 208	85.64 202	72.14 209

MIMVSNet1		52.76 206	53.95 206	51.38 207	41.96 218	70.79 210	53.56 209	63.03 181	39.36 210	27.83 214	22.73 214	33.07 212	34.47 211	70.49 202	72.69 198	87.41 197	68.51 210

pmmvs3		52.59 207	52.43 209	52.78 206	54.53 214	64.49 213	50.07 212	46.89 213	35.31 214	30.19 210	27.27 211	26.96 218	53.02 193	67.28 206	70.54 202	81.96 209	75.20 203

new_pmnet		50.32 208	51.36 210	49.11 208	49.19 216	64.89 212	48.66 214	47.99 212	47.55 200	26.27 216	29.51 210	28.66 215	44.89 199	61.12 210	62.74 210	77.66 211	65.03 211

FPMVS		50.25 209	45.67 212	55.58 204	70.48 202	60.12 214	59.78 204	59.33 191	46.66 201	37.94 195	30.22 206	27.51 217	35.94 210	50.98 213	47.90 213	70.02 213	56.31 212

test_method		47.92 210	55.39 205	39.21 211	19.90 222	49.24 216	39.29 217	34.65 218	57.37 168	32.54 206	25.11 212	41.02 191	44.31 201	66.58 208	57.57 212	64.59 216	90.82 146

PMVS	36.83 18	40.62 211	36.39 213	45.56 209	58.40 211	33.20 219	32.62 219	56.02 195	28.25 217	37.92 196	22.29 215	26.15 219	25.29 214	48.49 215	43.82 216	63.13 217	52.53 215
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		35.20 212	33.96 214	36.65 212	43.30 217	32.51 220	26.96 221	48.31 211	38.87 211	20.08 220	8.08 217	7.41 224	26.44 213	53.60 211	58.43 211	54.81 218	38.79 217
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		32.52 213	33.92 215	30.88 214	34.15 221	44.70 218	27.79 220	39.69 217	22.21 218	4.31 224	15.73 216	14.13 222	12.45 219	40.11 216	47.00 214	66.88 214	53.54 213

E-PMN		21.42 214	17.56 217	25.94 215	36.25 220	19.02 223	11.56 222	43.72 215	15.25 220	6.99 222	8.04 218	4.53 226	21.77 216	16.13 219	26.16 218	35.34 220	33.77 218

MVE	25.07 19	21.25 215	23.51 216	18.62 217	15.07 223	29.77 222	10.67 224	34.60 219	12.51 221	9.46 221	7.84 219	3.82 227	14.38 218	27.45 218	42.42 217	27.56 222	40.74 216
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		20.61 216	16.32 218	25.62 216	36.41 219	18.93 224	11.51 223	43.75 214	15.65 219	6.53 223	7.56 220	4.68 225	22.03 215	14.56 220	23.10 219	33.51 221	29.77 219

testmvs		0.76 217	1.23 219	0.21 218	0.05 225	0.21 225	0.38 226	0.09 221	0.94 222	0.05 226	2.13 222	0.08 228	0.60 221	0.82 221	0.77 220	0.11 223	3.62 221

test123		0.67 218	1.11 220	0.16 219	0.01 226	0.14 226	0.20 227	0.04 223	0.77 223	0.02 227	2.15 221	0.02 229	0.61 220	0.23 222	0.72 221	0.07 224	3.76 220

uanet_test		0.00 219	0.00 221	0.00 220	0.00 227	0.00 227	0.00 228	0.00 224	0.00 224	0.00 228	0.00 223	0.00 230	0.00 223	0.00 223	0.00 222	0.00 225	0.00 222

sosnet-low-res		0.00 219	0.00 221	0.00 220	0.00 227	0.00 227	0.00 228	0.00 224	0.00 224	0.00 228	0.00 223	0.00 230	0.00 223	0.00 223	0.00 222	0.00 225	0.00 222

sosnet		0.00 219	0.00 221	0.00 220	0.00 227	0.00 227	0.00 228	0.00 224	0.00 224	0.00 228	0.00 223	0.00 230	0.00 223	0.00 223	0.00 222	0.00 225	0.00 222

RE-MVS-def										39.41 194

9.14												91.16 6

SR-MVS					96.04 30			87.51 26				87.60 20

Anonymous202405211			75.59 132		85.13 118	91.06 108	84.62 92	77.96 73	69.47 134		40.79 187	63.84 123	84.57 66	83.55 126	84.69 113	89.69 182	95.75 83

our_test_3					73.80 189	79.57 197	64.47 197

ambc			50.35 211		55.61 213	59.93 215	48.73 213		44.08 204	35.81 203	24.01 213	10.64 223	41.57 205	72.83 192	63.35 209	74.99 212	77.61 198

MTAPA										91.14 7		85.84 26

MTMP										90.95 8		84.13 34

Patchmatch-RL test							8.17 225

tmp_tt				39.78 210	56.31 212	31.71 221	35.84 218	15.08 220	82.57 74	50.83 153	63.07 95	47.51 165	15.28 217	52.23 212	44.24 215	65.35 215

XVS					89.65 70	95.93 46	85.97 79			76.32 54		82.05 44				93.51 95

X-MVStestdata					89.65 70	95.93 46	85.97 79			76.32 54		82.05 44				93.51 95

mPP-MVS					95.90 32							80.22 53

NP-MVS									89.55 46

Patchmtry						87.41 131	78.32 138	54.14 202		51.09 148

DeepMVS_CX						48.96 217	43.77 215	40.58 216	50.93 190	24.67 218	36.95 198	20.18 221	41.60 204	38.92 217		52.37 219	53.31 214

High-resolution multi-view benchmark