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 5	92.05 8	97.14 1	94.19 1	94.71 7	93.25 1	95.08 1	94.32 11	92.59 15	96.49 18	99.58 3

DPE-MVS		95.10 2	95.53 2	94.60 5	97.77 7	98.64 3	96.60 4	92.45 6	96.34 5	91.41 5	96.70 2	92.26 5	93.56 4	93.68 17	91.73 29	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 2	97.59 10	98.89 2	95.37 11	92.04 9	96.85 3	94.00 2	92.81 14	93.02 2	92.93 5	94.22 14	92.15 20	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
MSP-MVS		95.00 4	95.47 3	94.45 6	96.78 18	98.11 9	95.72 7	90.91 14	96.68 4	91.57 4	96.98 1	89.47 13	94.76 2	95.24 3	92.15 20	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 5	94.85 6	94.15 8	98.03 4	98.59 4	95.56 8	92.91 3	94.86 13	88.46 15	91.32 21	90.83 10	94.03 3	95.20 4	94.16 5	95.89 33	99.01 15

SF-MVS		94.40 6	94.15 11	94.70 2	98.25 2	98.24 6	96.86 2	93.46 1	94.87 11	90.26 9	95.96 3	88.42 16	92.76 8	92.29 30	90.84 40	96.62 13	98.44 26

APDe-MVS		94.31 7	94.30 9	94.33 7	97.57 11	98.06 11	95.79 6	91.98 10	95.50 8	92.19 3	95.25 5	87.97 19	92.93 5	93.01 23	91.02 38	95.52 39	99.29 8

MCST-MVS		94.10 8	94.77 7	93.31 10	98.31 1	98.34 5	95.43 9	92.54 5	94.41 17	83.05 31	91.38 19	90.97 9	92.24 13	95.05 6	94.02 6	98.31 1	99.20 10

HPM-MVS++		94.04 9	94.96 5	92.96 12	97.93 5	97.71 17	94.65 14	91.01 13	95.91 6	87.43 17	93.52 11	92.63 4	92.29 12	94.22 14	92.34 17	94.47 58	98.37 28

NCCC		93.59 10	94.00 13	93.10 11	97.90 6	97.93 13	95.40 10	92.39 7	94.47 16	84.94 22	91.21 22	89.32 14	92.53 10	93.90 16	92.98 12	95.44 41	98.22 31

SMA-MVS		93.47 11	94.29 10	92.52 14	97.72 8	97.77 16	94.46 17	90.19 17	94.96 10	87.15 18	90.15 25	90.99 8	91.49 16	94.31 12	93.33 10	94.10 63	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 11	93.44 16	93.50 9	97.06 14	97.09 27	95.27 12	91.47 11	95.71 7	89.57 12	93.66 9	86.28 25	92.81 7	92.06 34	90.70 42	94.83 55	98.60 21
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SD-MVS		93.36 13	94.33 8	92.22 16	94.68 44	97.89 15	94.56 15	90.89 15	94.80 14	90.04 11	93.53 10	90.14 11	89.78 23	92.74 25	92.17 18	93.35 102	99.07 13
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 14	93.53 15	92.53 13	94.23 47	97.54 21	94.75 13	89.87 18	95.26 9	89.20 14	93.16 12	88.19 18	92.15 14	91.79 38	89.65 56	94.99 51	99.16 11
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 15	93.19 18	92.47 15	95.78 35	97.40 22	97.39 1	92.56 4	92.88 26	81.84 39	81.31 40	92.95 3	91.21 17	96.54 1	97.33 1	96.01 30	93.94 108

SteuartSystems-ACMMP		92.31 16	93.31 17	91.15 23	96.88 16	97.36 23	93.95 21	89.44 20	92.62 27	83.20 28	94.34 8	85.55 27	88.95 30	93.07 22	91.90 25	94.51 57	98.30 29
Skip Steuart: Steuart Systems R&D Blog.
ACMMP_NAP		92.16 17	92.91 21	91.28 22	96.95 15	97.36 23	93.66 22	89.23 22	93.33 21	83.71 26	90.53 23	86.84 22	90.39 19	93.30 21	91.56 31	93.74 74	97.43 45

HFP-MVS		92.02 18	92.13 23	91.89 20	97.16 13	96.46 40	93.57 23	87.60 26	93.79 19	88.17 16	93.15 13	83.94 38	91.19 18	90.81 48	89.83 51	93.66 78	96.94 61

train_agg		91.99 19	93.71 14	89.98 28	96.42 27	97.03 29	94.31 19	89.05 23	93.33 21	77.75 46	95.06 6	88.27 17	88.38 36	92.02 35	91.41 33	94.00 66	98.84 18

xxxxxxxxxxxxxcwj		91.86 20	89.43 37	94.70 2	98.25 2	98.24 6	96.86 2	93.46 1	94.87 11	90.26 9	95.96 3	55.37 144	92.76 8	92.29 30	90.84 40	96.62 13	98.44 26

DeepC-MVS_fast	86.59 2	91.69 21	91.39 26	92.05 19	97.43 12	96.92 32	94.05 20	90.23 16	93.31 24	83.19 29	77.91 47	84.23 34	92.42 11	94.62 9	94.83 3	95.00 50	97.88 35
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
zzz-MVS		91.59 22	91.12 27	92.13 17	96.76 19	96.68 35	93.39 24	88.00 25	93.63 20	90.76 8	83.97 36	85.33 29	89.89 22	91.60 40	89.65 56	94.00 66	96.97 59

TSAR-MVS + GP.		91.29 23	93.11 20	89.18 34	87.81 85	96.21 46	92.51 33	83.83 46	94.24 18	83.77 25	91.87 18	89.62 12	90.07 20	90.40 52	90.31 46	97.09 6	99.10 12

ACMMPR		91.15 24	91.44 25	90.81 24	96.61 21	96.25 44	93.09 25	87.08 29	93.32 23	84.78 23	92.08 17	82.10 44	89.71 24	90.24 53	89.82 52	93.61 83	96.30 73

DeepPCF-MVS	86.71 1	91.00 25	94.05 12	87.43 45	95.58 38	98.17 8	86.22 74	88.59 24	97.01 2	76.77 52	85.11 34	88.90 15	87.29 42	95.02 7	94.69 4	90.15 173	99.48 6

TSAR-MVS + ACMM		90.98 26	93.18 19	88.42 39	95.69 36	96.73 34	94.52 16	86.97 32	92.99 25	76.32 53	92.31 16	86.64 23	84.40 68	92.97 24	92.02 22	92.62 125	98.59 22

MP-MVS		90.81 27	91.45 24	90.06 27	96.59 22	96.33 43	92.46 34	87.19 28	90.27 40	82.54 35	91.38 19	84.88 31	88.27 37	90.58 50	89.30 62	93.30 104	97.44 43
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CP-MVS		90.57 28	90.68 29	90.44 25	96.13 29	95.90 51	92.77 30	86.86 33	92.12 31	84.19 24	89.18 28	82.37 42	89.43 28	89.65 62	88.43 69	93.27 105	97.13 53

MSLP-MVS++		90.33 29	88.82 41	92.10 18	96.52 25	95.93 47	94.35 18	86.26 34	88.37 53	89.24 13	75.94 52	82.60 41	89.71 24	89.45 65	92.17 18	96.51 17	97.24 50

CANet		89.98 30	90.42 33	89.47 33	94.13 48	98.05 12	91.76 39	83.27 49	90.87 37	81.90 38	72.32 58	84.82 32	88.42 34	94.52 10	93.78 8	97.34 4	98.58 23

PGM-MVS		89.97 31	90.64 31	89.18 34	96.53 24	95.90 51	93.06 26	82.48 57	90.04 42	80.37 41	92.75 15	80.96 49	88.93 31	89.88 58	89.08 64	93.69 77	95.86 77

PHI-MVS		89.88 32	92.75 22	86.52 55	94.97 41	97.57 20	89.99 50	84.56 42	92.52 29	69.72 86	90.35 24	87.11 21	84.89 60	91.82 37	92.37 16	95.02 49	97.51 41

CSCG		89.81 33	89.69 34	89.96 29	96.55 23	97.90 14	92.89 28	87.06 30	88.74 51	86.17 19	78.24 46	86.53 24	84.75 63	87.82 85	90.59 43	92.32 130	98.01 34

X-MVS		89.73 34	90.65 30	88.66 37	96.44 26	95.93 47	92.26 36	86.98 31	90.73 38	76.32 53	89.56 27	82.05 45	86.51 49	89.98 56	89.60 58	93.43 97	96.72 68

EPNet		89.30 35	90.89 28	87.44 44	95.67 37	96.81 33	91.13 42	83.12 51	91.14 34	76.31 57	87.60 30	80.40 52	84.45 66	92.13 33	91.12 37	93.96 68	97.01 57
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepC-MVS	84.14 3	88.80 36	88.03 45	89.71 31	94.83 42	96.56 36	92.57 32	89.38 21	89.25 48	79.59 43	70.02 67	77.05 65	88.24 38	92.44 28	92.79 13	93.65 81	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 37	90.43 32	86.81 51	96.04 31	96.53 39	92.95 27	85.95 36	90.36 39	67.93 91	85.80 33	80.69 50	83.82 71	90.81 48	91.85 28	94.18 61	96.99 58

3Dnovator+	81.14 5	88.59 38	87.49 47	89.88 30	95.83 34	96.45 42	91.94 38	82.41 58	87.09 59	85.94 21	62.80 95	85.37 28	89.46 26	91.51 41	91.89 27	93.72 75	97.30 48

ACMMP		88.48 39	88.71 42	88.22 41	94.61 45	95.53 56	90.64 46	85.60 38	90.97 35	78.62 45	89.88 26	74.20 78	86.29 50	88.16 82	86.37 88	93.57 84	95.86 77
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 40	85.75 61	91.62 21	96.25 28	95.35 61	90.71 44	91.08 12	90.22 41	86.17 19	74.33 54	73.67 81	92.00 15	86.31 101	85.82 96	93.52 87	94.53 95

MVS_0304		88.43 41	89.46 36	87.21 46	91.85 60	97.60 18	92.62 31	81.10 64	87.16 58	73.80 63	72.19 60	83.36 40	87.03 44	94.64 8	93.67 9	96.88 9	97.64 40

3Dnovator	80.58 8	88.20 42	86.53 53	90.15 26	96.86 17	96.46 40	91.97 37	83.06 52	85.16 64	83.66 27	62.28 98	82.15 43	88.98 29	90.99 46	92.65 14	96.38 23	96.03 74

CPTT-MVS		88.17 43	87.84 46	88.55 38	93.33 50	93.75 76	92.33 35	84.75 41	89.87 44	81.72 40	83.93 37	81.12 48	88.45 33	85.42 110	84.07 115	90.72 165	96.72 68

MVS_111021_HR		87.82 44	88.84 40	86.62 53	94.42 46	97.36 23	88.21 59	83.26 50	83.42 67	72.52 73	82.63 38	76.93 66	84.95 59	91.93 36	91.15 36	96.39 22	98.49 25

DELS-MVS		87.75 45	86.92 51	88.71 36	94.69 43	97.34 26	92.78 29	84.50 43	77.87 90	81.94 37	67.17 75	75.49 73	82.84 77	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 46	89.12 38	86.01 57	88.11 83	90.05 113	89.28 53	77.05 84	91.37 32	79.97 42	76.70 50	85.25 30	84.89 60	93.53 18	91.41 33	96.73 11	95.55 84

MVS_111021_LR		87.58 47	88.67 43	86.31 56	92.58 54	95.89 53	86.20 75	82.49 56	89.08 50	77.47 49	86.20 32	74.22 77	85.49 55	90.03 55	88.52 67	93.66 78	96.74 67

QAPM		87.06 48	86.46 54	87.75 42	96.63 20	97.09 27	91.71 40	82.62 55	80.58 80	71.28 79	66.04 82	84.24 33	87.01 45	89.93 57	89.91 50	97.26 5	97.44 43

PVSNet_BlendedMVS		86.98 49	87.05 49	86.90 48	93.03 51	96.98 30	86.57 71	81.82 60	89.78 45	82.78 33	71.54 61	66.07 109	80.73 88	93.46 19	91.97 23	96.45 20	99.53 4

PVSNet_Blended		86.98 49	87.05 49	86.90 48	93.03 51	96.98 30	86.57 71	81.82 60	89.78 45	82.78 33	71.54 61	66.07 109	80.73 88	93.46 19	91.97 23	96.45 20	99.53 4

ETV-MVS		86.94 51	89.49 35	83.95 67	87.28 91	95.61 55	83.58 100	76.37 89	92.59 28	73.20 65	80.35 42	76.42 69	87.38 41	92.20 32	90.45 45	95.90 32	98.83 19

CS-MVS		86.48 52	89.02 39	83.52 71	87.37 90	95.52 57	84.21 94	75.09 97	87.63 55	71.30 78	80.94 41	78.24 55	87.23 43	92.72 26	90.05 48	95.95 31	98.03 33

OMC-MVS		86.38 53	86.21 58	86.57 54	92.30 56	94.35 70	87.60 63	83.51 48	92.32 30	77.37 50	72.27 59	77.83 58	86.59 48	87.62 87	85.95 93	92.08 134	93.11 121

HQP-MVS		86.17 54	87.35 48	84.80 63	91.41 63	92.37 93	91.05 43	84.35 45	88.52 52	64.21 97	87.05 31	68.91 99	84.80 62	89.12 68	88.16 73	92.96 116	97.31 47

canonicalmvs		85.93 55	86.26 57	85.54 58	88.94 74	95.44 58	89.56 51	76.01 91	87.83 54	77.70 47	76.43 51	68.66 101	87.80 40	87.02 90	91.51 32	93.25 106	96.95 60

MAR-MVS		85.65 56	86.30 56	84.88 62	95.51 40	95.89 53	86.50 73	76.71 85	89.23 49	68.59 88	70.93 65	74.49 75	88.55 32	89.40 66	90.30 47	93.42 98	93.88 112
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 57	84.41 66	86.81 51	91.51 62	96.23 45	90.27 47	89.81 19	77.87 90	70.67 82	69.20 69	77.86 56	85.55 54	85.92 106	86.38 87	93.03 113	97.43 45
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CLD-MVS		85.43 58	84.24 69	86.83 50	87.69 87	93.16 84	90.01 49	82.72 54	87.17 57	79.28 44	71.43 64	65.81 111	86.02 51	87.33 89	86.96 81	95.25 45	97.83 37
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 59	83.42 73	87.03 47	96.12 30	96.55 38	89.36 52	81.59 62	79.19 86	75.20 59	55.84 124	79.04 54	84.45 66	88.47 76	89.35 61	95.48 40	95.48 85

TSAR-MVS + COLMAP		84.93 60	85.79 60	83.92 68	90.90 65	93.57 80	89.25 54	82.00 59	91.29 33	61.66 105	88.25 29	59.46 132	86.71 47	89.79 59	87.09 79	93.01 114	91.09 140

TAPA-MVS	80.99 7	84.83 61	84.42 65	85.31 59	91.89 59	93.73 78	88.53 58	82.80 53	89.99 43	69.78 85	71.53 63	75.03 74	85.47 56	86.26 102	84.54 110	93.39 100	89.90 150
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PLC	81.02 6	84.81 62	81.81 90	88.31 40	93.77 49	90.35 108	88.80 56	84.47 44	86.76 60	82.17 36	66.56 78	71.01 92	88.41 35	85.48 108	84.28 113	92.26 132	88.21 163
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EIA-MVS		84.75 63	86.43 55	82.79 74	86.88 94	95.36 60	82.84 105	76.39 88	87.61 56	71.03 80	74.33 54	71.12 91	85.16 57	89.69 61	88.70 66	94.40 59	98.23 30

CNLPA		84.72 64	82.14 85	87.73 43	92.85 53	93.83 75	84.70 90	85.07 39	90.90 36	83.16 30	56.28 120	71.53 88	88.14 39	84.19 115	84.00 119	92.48 127	94.26 102

MVS_Test		84.60 65	85.13 64	83.99 66	88.17 81	95.27 62	88.21 59	73.15 112	84.31 66	70.55 83	68.67 73	68.78 100	86.99 46	91.71 39	91.90 25	96.84 10	95.27 89

casdiffmvs		83.84 66	82.65 81	85.22 60	87.25 92	94.62 68	86.01 78	79.62 67	79.48 83	77.59 48	61.92 101	64.34 115	85.57 53	90.55 51	90.51 44	95.26 43	97.14 52

baseline		83.83 67	84.38 67	83.18 73	86.65 96	94.59 69	85.79 81	73.78 109	85.83 62	72.94 66	69.28 68	70.80 94	83.45 74	86.80 93	87.59 75	96.47 19	95.77 81

diffmvs		83.69 68	83.17 77	84.31 64	85.45 109	93.92 71	86.89 66	78.62 70	82.71 73	75.95 58	66.78 77	63.90 118	83.84 70	87.90 84	89.16 63	95.10 48	97.82 38

CANet_DTU		83.33 69	86.59 52	79.53 94	88.88 75	94.87 65	86.63 70	68.85 144	85.45 63	50.54 150	77.86 48	69.94 97	85.62 52	92.63 27	90.88 39	96.63 12	94.46 96

DI_MVS_plusplus_trai		83.32 70	82.53 83	84.25 65	86.26 103	93.66 79	90.23 48	77.16 83	77.05 97	74.06 62	53.74 133	74.33 76	83.61 73	91.40 43	89.82 52	94.17 62	97.73 39

baseline1		82.63 71	82.02 86	83.34 72	88.30 80	91.89 97	88.03 62	80.86 65	75.05 104	65.96 93	64.27 89	72.20 86	80.01 92	91.32 44	89.56 59	96.90 8	89.85 151

PVSNet_Blended_VisFu		82.55 72	83.70 72	81.21 83	89.66 69	95.15 64	82.41 106	77.36 82	72.53 119	73.64 64	61.15 104	77.19 64	70.35 147	91.31 45	89.72 55	93.84 70	98.85 17

ET-MVSNet_ETH3D		82.37 73	85.68 62	78.51 104	62.90 206	94.66 66	87.06 65	73.57 110	83.13 69	61.52 107	78.37 45	76.01 71	89.99 21	84.14 116	89.03 65	96.03 29	94.42 97

PMMVS		82.26 74	85.48 63	78.51 104	85.92 106	91.92 96	78.30 136	70.77 129	86.30 61	61.11 109	82.46 39	70.88 93	84.70 64	88.05 83	84.78 106	90.24 172	93.98 106

ACMP	79.58 9	82.23 75	81.82 89	82.71 75	88.15 82	90.95 105	85.23 86	78.52 72	81.70 75	72.52 73	78.41 44	60.63 126	80.48 90	82.88 126	83.44 123	91.37 151	94.70 93
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
CHOSEN 280x420		82.15 76	85.87 59	77.80 109	86.54 99	93.42 82	81.74 108	59.96 185	78.99 88	63.99 98	74.50 53	83.95 37	80.99 83	89.53 64	85.01 101	93.56 86	95.71 83

LGP-MVS_train		82.12 77	82.57 82	81.59 80	89.26 73	90.23 111	88.76 57	78.05 73	81.26 77	61.64 106	79.52 43	62.11 121	79.59 94	85.20 111	84.68 108	92.27 131	95.02 91

FMVSNet3		81.93 78	81.98 87	81.88 79	79.49 146	87.02 128	88.15 61	72.57 115	83.02 70	72.63 70	56.55 116	73.48 82	82.34 80	91.49 42	91.20 35	96.07 25	91.13 139

thisisatest0530		81.67 79	84.27 68	78.63 100	85.53 107	93.88 74	81.77 107	73.84 106	81.35 76	63.85 100	68.79 71	77.64 60	73.02 128	88.73 74	85.73 97	93.76 73	93.80 116

tttt0517		81.51 80	84.12 71	78.47 106	85.33 111	93.74 77	81.42 111	73.84 106	81.21 78	63.59 101	68.73 72	77.46 63	73.02 128	88.47 76	85.73 97	93.63 82	93.49 120

OPM-MVS		81.34 81	78.18 106	85.02 61	91.27 64	91.78 98	90.66 45	83.62 47	62.39 148	65.91 94	63.35 93	64.33 116	85.03 58	87.77 86	85.88 95	93.66 78	91.75 136

baseline2		81.21 82	83.36 76	78.70 98	83.22 125	92.71 86	80.32 117	74.25 105	80.39 81	63.94 99	68.89 70	68.44 102	74.67 114	89.61 63	86.68 85	95.83 36	96.81 66

IS_MVSNet		80.92 83	84.14 70	77.16 112	87.43 88	93.90 73	80.44 113	74.64 99	75.05 104	61.10 110	65.59 84	76.89 67	67.39 155	90.88 47	90.05 48	91.95 138	96.62 71

ACMM	78.09 10	80.91 84	78.39 104	83.86 69	89.61 72	87.71 125	85.16 87	80.67 66	79.04 87	74.18 61	63.82 92	60.84 125	82.59 78	84.33 113	83.59 122	90.96 159	89.39 156
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EPP-MVSNet		80.82 85	82.79 79	78.52 102	86.31 102	92.37 93	79.83 120	74.51 100	73.79 113	64.46 96	67.01 76	80.63 51	74.33 117	85.63 107	84.35 112	91.68 144	95.79 80

CostFormer		80.72 86	81.81 90	79.44 96	86.50 100	91.65 99	84.31 92	59.84 186	80.86 79	72.69 68	62.46 97	73.74 79	79.93 93	82.58 130	84.50 111	93.37 101	96.90 64

GBi-Net		80.72 86	80.49 93	81.00 86	78.18 150	86.19 142	86.73 67	72.57 115	83.02 70	72.63 70	56.55 116	73.48 82	80.99 83	86.57 95	86.83 82	94.89 52	90.77 143

test1		80.72 86	80.49 93	81.00 86	78.18 150	86.19 142	86.73 67	72.57 115	83.02 70	72.63 70	56.55 116	73.48 82	80.99 83	86.57 95	86.83 82	94.89 52	90.77 143

UGNet		80.71 89	83.09 78	77.93 108	87.02 93	92.71 86	80.28 118	76.53 86	73.83 112	71.35 77	70.07 66	73.71 80	58.93 175	87.39 88	86.97 80	93.48 94	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 90	79.16 101	81.48 81	91.97 57	96.56 36	86.18 76	75.40 95	76.17 100	61.32 108	37.43 193	61.08 124	76.52 107	92.35 29	91.64 30	97.46 3	98.86 16

thres100view900		79.83 91	77.79 110	82.21 76	88.42 77	93.54 81	87.07 64	81.11 63	70.15 126	61.01 111	56.65 114	51.22 148	81.78 81	89.77 60	85.95 93	93.84 70	97.26 49

Effi-MVS+		79.80 92	80.04 95	79.52 95	85.53 107	93.31 83	85.28 84	70.68 131	74.15 108	58.79 120	62.03 100	60.51 127	83.37 75	88.41 78	86.09 92	93.49 93	95.80 79

DCV-MVSNet		79.76 93	79.17 100	80.44 91	84.65 115	84.51 166	84.20 95	72.36 120	75.17 103	70.81 81	66.21 81	66.56 106	80.99 83	82.89 125	84.56 109	89.65 178	94.30 101

FC-MVSNet-train		79.54 94	78.20 105	81.09 85	86.55 98	88.63 121	79.96 119	78.53 71	70.90 124	68.24 89	65.87 83	56.45 142	80.29 91	86.20 104	84.08 114	92.97 115	95.31 88

test-LLR		79.52 95	83.42 73	74.97 121	81.79 130	91.26 100	76.17 157	70.57 132	77.71 92	52.14 137	66.26 79	77.47 61	73.10 124	87.02 90	87.16 77	96.05 27	97.02 55

FMVSNet2		79.24 96	78.14 107	80.53 90	78.18 150	86.19 142	86.73 67	71.91 121	72.97 115	70.48 84	50.63 143	66.56 106	80.99 83	90.10 54	89.77 54	94.89 52	90.77 143

TESTMET0.1,1		79.15 97	83.42 73	74.18 127	79.81 144	91.26 100	76.17 157	67.83 157	77.71 92	52.14 137	66.26 79	77.47 61	73.10 124	87.02 90	87.16 77	96.05 27	97.02 55

tfpn200view9		79.05 98	77.21 113	81.18 84	88.42 77	92.55 91	85.12 88	77.94 75	70.15 126	61.01 111	56.65 114	51.22 148	81.11 82	88.23 79	84.80 105	93.50 92	96.90 64

PatchMatch-RL		78.75 99	76.47 120	81.41 82	88.53 76	91.10 102	78.09 137	77.51 81	77.33 94	71.98 75	64.38 88	48.10 160	82.55 79	84.06 117	82.35 132	89.78 175	87.97 165

LS3D		78.72 100	75.79 124	82.15 77	91.91 58	89.39 118	83.66 98	85.88 37	76.81 98	59.22 119	57.67 111	58.53 136	83.72 72	82.07 135	81.63 143	88.50 186	84.39 176

thres200		78.69 101	76.71 116	80.99 88	88.35 79	92.56 89	86.03 77	77.94 75	66.27 133	60.66 113	56.08 121	51.11 150	79.45 95	88.23 79	85.54 100	93.52 87	97.20 51

Anonymous20231211		78.61 102	75.57 127	82.15 77	84.43 119	90.26 109	84.08 96	77.68 78	71.09 122	72.90 67	39.24 186	66.21 108	84.23 69	82.15 133	84.04 116	89.61 179	96.03 74

IB-MVS	74.10 12	78.52 103	78.51 103	78.52 102	90.15 67	95.39 59	71.95 177	77.53 80	74.95 106	77.25 51	58.93 108	55.92 143	58.37 177	79.01 160	87.89 74	95.88 34	97.47 42
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		78.49 104	81.96 88	74.45 126	92.57 55	88.74 120	82.98 101	78.83 69	83.28 68	44.64 181	77.40 49	67.73 103	53.98 186	85.44 109	84.91 102	93.71 76	86.22 171
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
thres400		78.39 105	76.39 121	80.73 89	88.02 84	92.94 85	84.77 89	78.88 68	65.20 141	59.70 117	55.20 127	50.85 151	79.45 95	88.81 71	84.81 104	93.57 84	96.91 63

UA-Net		78.30 106	80.92 92	75.25 120	87.42 89	92.48 92	79.54 123	75.49 94	60.47 152	60.52 114	68.44 74	84.08 36	57.54 179	88.54 75	88.45 68	90.96 159	83.97 178

Vis-MVSNet (Re-imp)		78.28 107	82.68 80	73.16 138	86.64 97	92.68 88	78.07 138	74.48 101	74.05 109	53.47 130	64.22 90	76.52 68	54.28 182	88.96 70	88.29 71	92.03 136	94.00 105

MSDG		78.11 108	73.17 140	83.86 69	91.78 61	86.83 130	85.25 85	86.02 35	72.84 117	69.69 87	51.43 140	54.00 146	77.61 99	81.95 138	82.27 134	92.83 121	82.91 183

HyFIR lowres test		78.08 109	76.81 114	79.56 93	90.77 66	94.64 67	82.97 102	69.85 137	69.81 128	59.53 118	33.52 198	64.66 112	78.97 97	88.77 73	88.38 70	95.27 42	97.86 36

GeoE		78.04 110	77.52 112	78.65 99	84.51 117	90.84 106	80.94 112	69.24 142	72.86 116	66.06 92	53.45 134	60.46 128	77.37 100	84.20 114	84.85 103	93.78 72	96.00 76

test-mter		77.90 111	82.44 84	72.60 143	78.52 148	90.24 110	73.85 170	65.31 171	76.37 99	51.29 141	65.58 85	75.94 72	71.36 138	85.98 105	86.26 89	95.26 43	96.71 70

thres600view7		77.66 112	75.67 125	79.98 92	87.71 86	92.56 89	83.79 97	77.94 75	64.41 143	58.69 121	54.32 132	50.54 152	78.23 98	88.23 79	83.06 126	93.52 87	96.55 72

MS-PatchMatch		77.47 113	76.48 119	78.63 100	89.89 68	90.42 107	85.42 83	69.53 139	70.79 125	60.43 115	50.05 145	70.62 96	70.66 144	86.71 94	82.54 129	95.86 35	84.23 177

Fast-Effi-MVS+		77.37 114	76.68 117	78.17 107	82.84 127	89.94 114	81.47 110	68.01 153	72.99 114	60.26 116	55.07 128	53.20 147	82.99 76	86.47 100	86.12 91	93.46 95	92.98 124

Vis-MVSNet		77.24 115	79.99 98	74.02 128	84.62 116	93.92 71	80.33 116	72.55 118	62.58 147	55.25 128	64.45 87	69.49 98	57.00 180	88.78 72	88.21 72	94.36 60	92.54 127
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
MDTV_nov1_ep13		77.20 116	80.04 95	73.90 130	82.22 128	90.14 112	79.25 127	61.52 181	78.63 89	56.98 122	65.52 86	72.80 85	73.05 126	80.93 146	83.20 124	90.36 169	89.05 159

EPMVS		77.16 117	79.08 102	74.92 122	86.73 95	91.98 95	78.62 132	55.44 194	79.43 84	56.59 124	61.24 103	70.73 95	76.97 104	80.59 149	81.43 150	95.15 47	88.17 164

tpm cat1		76.93 118	76.19 123	77.79 110	85.08 114	88.58 122	82.96 103	59.33 187	75.72 102	72.64 69	51.25 141	64.41 114	75.74 111	77.90 169	80.10 166	90.97 158	95.35 86

PatchmatchNet		76.85 119	80.03 97	73.15 139	84.08 121	91.04 104	77.76 142	55.85 193	79.43 84	52.74 135	62.08 99	76.02 70	74.56 115	79.92 154	81.41 151	93.92 69	90.29 148
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
IterMVS-LS		76.80 120	76.33 122	77.35 111	84.07 122	84.11 168	81.54 109	68.52 146	66.17 134	61.74 104	57.84 110	64.31 117	74.88 113	83.48 122	86.21 90	93.34 103	92.16 131
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CDS-MVSNet		76.57 121	76.78 115	76.32 115	80.94 137	89.75 115	82.94 104	72.64 114	59.01 158	62.95 103	58.60 109	62.67 120	66.91 157	86.26 102	87.20 76	91.57 146	93.97 107
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SCA		76.41 122	79.90 99	72.35 147	84.26 120	85.24 157	75.57 164	54.56 196	79.95 82	52.72 136	64.22 90	77.84 57	73.73 121	80.48 150	81.37 152	93.25 106	90.20 149

tpmrst		76.27 123	77.65 111	74.66 124	86.13 105	89.53 117	79.31 126	54.91 195	77.19 96	56.27 125	55.87 123	64.58 113	77.25 101	80.85 147	80.21 163	94.07 64	95.32 87

dps		75.76 124	75.02 129	76.63 114	84.51 117	88.12 123	77.51 143	58.33 189	75.91 101	71.98 75	57.37 112	57.85 137	76.81 106	77.89 170	78.40 175	90.63 166	89.63 153

CR-MVSNet		74.84 125	77.91 108	71.26 160	81.77 132	85.52 153	78.32 134	54.14 198	74.05 109	51.09 144	50.00 146	71.38 90	70.77 142	86.48 98	84.03 117	91.46 150	93.92 109

Effi-MVS+-dtu		74.57 126	74.60 133	74.53 125	81.38 134	86.74 132	80.39 115	67.70 158	67.36 132	53.06 131	59.86 106	57.50 138	75.84 110	80.19 152	78.62 173	88.79 185	91.95 135

test_part1		74.38 127	70.16 153	79.31 97	83.30 124	84.45 167	84.31 92	71.43 126	55.24 171	74.88 60	38.77 188	59.61 131	75.29 112	78.96 161	81.53 145	86.63 194	92.55 126

RPSCF		74.27 128	73.24 139	75.48 119	81.01 136	80.18 190	76.24 156	72.37 119	74.84 107	68.24 89	72.47 57	67.39 104	73.89 118	71.05 194	69.38 201	81.14 206	77.37 195

FMVSNet1		74.26 129	71.95 145	76.95 113	74.28 182	83.94 170	83.61 99	69.99 135	57.08 164	65.08 95	42.39 175	57.41 139	76.98 103	86.57 95	86.83 82	91.77 143	89.42 154

GA-MVS		73.62 130	74.52 134	72.58 144	79.93 142	89.29 119	78.02 139	71.67 124	60.79 151	42.68 185	54.41 131	49.07 156	70.07 148	89.39 67	86.55 86	93.13 111	92.12 132

Fast-Effi-MVS+-dtu		73.56 131	75.32 128	71.50 156	80.35 139	86.83 130	79.72 121	58.07 190	67.64 131	44.83 178	60.28 105	54.07 145	73.59 123	81.90 140	82.30 133	92.46 128	94.18 103

tpm		73.50 132	74.85 130	71.93 150	83.19 126	86.84 129	78.61 133	55.91 192	65.64 136	48.90 157	56.30 119	61.09 123	72.31 130	79.10 159	80.61 162	92.68 123	94.35 100

RPMNet		73.46 133	77.85 109	68.34 170	81.71 133	85.52 153	73.83 171	50.54 205	74.05 109	46.10 172	53.03 137	71.91 87	66.31 159	83.55 120	82.18 136	91.55 148	94.71 92

USDC		73.43 134	72.31 143	74.73 123	80.86 138	86.21 140	80.42 114	71.83 123	71.69 121	46.94 165	59.60 107	42.58 181	76.47 108	82.66 129	81.22 155	91.88 140	82.24 189

pmmvs4		73.38 135	71.53 148	75.55 118	75.95 168	85.24 157	77.25 147	71.59 125	71.03 123	63.10 102	49.09 151	44.22 171	73.73 121	82.04 136	80.18 164	91.68 144	88.89 161

UniMVSNet_NR-MVSNet		73.11 136	72.59 141	73.71 133	76.90 159	86.58 136	77.01 148	75.82 92	65.59 137	48.82 158	50.97 142	48.42 158	71.61 134	79.19 158	83.03 127	92.11 133	94.37 98

FMVSNet5		72.83 137	73.89 137	71.59 154	67.42 200	76.28 198	75.88 161	63.74 175	77.27 95	54.59 129	53.32 135	71.48 89	73.85 119	81.95 138	81.69 141	94.06 65	75.20 199

PatchT		72.66 138	76.58 118	68.09 172	79.02 147	86.09 146	59.81 199	51.78 203	72.00 120	51.09 144	46.84 155	66.70 105	70.77 142	86.48 98	84.03 117	96.07 25	93.92 109

ACMH	71.22 14	72.65 139	70.13 154	75.59 117	86.19 104	86.14 145	75.76 162	77.63 79	54.79 173	46.16 171	53.28 136	47.28 162	77.24 102	78.91 162	81.18 156	90.57 167	89.33 157
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IterMVS		72.43 140	74.05 135	70.55 164	80.34 140	81.17 184	77.44 144	61.00 184	63.57 146	46.82 167	55.88 122	59.09 135	65.03 161	83.15 123	83.83 120	92.67 124	91.65 137
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMH+	72.14 13	72.38 141	69.34 161	75.93 116	85.21 112	84.89 161	76.96 151	76.04 90	59.76 153	51.63 140	50.37 144	48.69 157	76.90 105	76.06 178	78.69 171	88.85 184	86.90 169

DU-MVS		72.19 142	71.35 149	73.17 137	75.95 168	86.02 147	77.01 148	74.42 102	65.39 139	48.82 158	49.10 149	42.81 179	71.61 134	78.67 163	83.10 125	91.22 154	94.37 98

IterMVS-SCA-FT		72.18 143	73.96 136	70.11 166	80.15 141	81.11 185	77.42 145	61.09 183	63.67 145	46.73 168	55.77 125	59.15 134	63.95 164	82.83 127	83.70 121	91.31 152	91.49 138

UniMVSNet (Re)		72.12 144	72.28 144	71.93 150	76.77 160	87.38 127	75.73 163	73.51 111	65.76 135	50.24 152	48.65 152	46.49 163	63.85 165	80.10 153	82.47 130	91.49 149	95.13 90

ADS-MVSNet		72.11 145	73.72 138	70.24 165	81.24 135	86.59 135	74.75 167	50.56 204	72.58 118	49.17 155	55.40 126	61.46 122	73.80 120	76.01 179	78.14 176	91.93 139	85.86 172

gg-mvs-nofinetune		72.10 146	74.79 131	68.97 169	83.31 123	95.22 63	85.66 82	48.77 206	35.68 209	22.17 215	30.49 201	77.73 59	76.37 109	94.30 13	93.03 11	97.55 2	97.05 54

TAMVS		72.06 147	71.76 147	72.41 146	76.68 161	88.12 123	74.82 166	68.09 151	53.52 178	56.91 123	52.94 138	56.93 141	66.91 157	81.37 143	82.44 131	91.07 156	86.99 168

v2v482		71.73 148	69.80 156	73.99 129	75.88 172	86.66 134	79.58 122	71.90 122	57.58 162	50.41 151	45.35 159	43.24 177	73.05 126	79.69 155	82.18 136	93.08 112	93.87 113

test0.0.03 1		71.70 149	74.68 132	68.23 171	81.79 130	83.81 171	68.64 181	70.57 132	68.81 130	43.47 182	62.77 96	60.09 130	51.77 193	82.48 131	81.67 142	93.16 109	83.13 181

V42		71.58 150	70.11 155	73.30 136	75.66 175	86.68 133	79.17 129	69.92 136	59.29 157	52.80 134	44.36 163	45.66 165	68.83 149	79.48 157	81.49 147	93.44 96	93.82 115

NR-MVSNet		71.47 151	71.11 150	71.90 152	77.73 155	86.02 147	76.88 152	74.42 102	65.39 139	46.09 173	49.10 149	39.87 194	64.27 163	81.40 142	82.24 135	91.99 137	93.75 117

v8		71.42 152	69.69 157	73.43 135	76.45 164	85.12 160	79.53 124	67.47 161	59.34 156	52.90 133	44.60 161	45.82 164	71.05 140	79.56 156	81.45 149	93.17 108	91.96 134

TranMVSNet+NR-MVSNet		71.12 153	70.24 152	72.15 148	76.01 167	84.80 163	76.55 154	75.65 93	61.99 149	45.29 176	48.42 153	43.07 178	67.55 153	78.28 166	82.83 128	91.85 141	92.29 128

v10		70.97 154	69.44 158	72.75 140	75.90 171	84.58 165	79.43 125	66.45 166	58.07 160	49.93 153	43.87 169	43.68 172	71.91 132	82.04 136	81.70 140	92.89 119	92.11 133

v1144		70.93 155	69.42 160	72.70 141	75.48 176	86.26 138	79.22 128	69.39 141	55.61 169	48.05 163	43.47 170	42.55 182	71.51 136	82.11 134	81.74 139	92.56 126	94.17 104

thisisatest0515		70.62 156	71.94 146	69.07 168	76.48 163	85.59 152	68.03 182	68.02 152	59.70 154	52.94 132	52.19 139	50.36 153	58.10 178	83.15 123	81.63 143	90.87 162	90.99 141

Baseline_NR-MVSNet		70.61 157	68.87 164	72.65 142	75.95 168	80.49 188	75.92 160	74.75 98	65.10 142	48.78 160	41.28 181	44.28 170	68.45 150	78.67 163	79.64 167	92.04 135	92.62 125

v148		70.34 158	68.46 167	72.54 145	76.04 166	86.38 137	74.83 165	72.73 113	55.88 168	55.26 127	43.32 172	43.49 173	64.52 162	76.93 176	80.11 165	91.85 141	93.11 121

v1192		70.32 159	68.77 165	72.12 149	74.76 178	85.62 151	78.73 130	68.53 145	55.08 172	46.34 170	42.39 175	40.67 189	71.90 133	82.27 132	81.53 145	92.43 129	93.86 114

v144192		70.10 160	68.55 166	71.90 152	74.55 179	85.67 150	77.81 140	68.22 150	54.65 174	46.91 166	42.76 173	41.27 186	70.95 141	80.48 150	81.11 160	92.96 116	93.90 111

pmmvs5		70.01 161	69.31 162	70.82 163	75.80 174	86.26 138	72.94 172	67.91 154	53.84 177	47.22 164	47.31 154	41.47 185	67.61 152	83.93 119	81.93 138	93.42 98	90.42 147

COLMAP_ROB	66.31 15	69.91 162	66.61 172	73.76 131	86.44 101	82.76 175	76.59 153	76.46 87	63.82 144	50.92 148	45.60 158	49.13 155	65.87 160	74.96 184	74.45 191	86.30 196	75.57 198
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
v1921920		69.85 163	68.38 168	71.58 155	74.35 180	85.39 155	77.78 141	67.88 156	54.64 175	45.39 175	42.11 178	39.97 193	71.10 139	81.68 141	81.17 158	92.96 116	93.69 119

pm-mvs1		69.62 164	68.07 170	71.44 157	77.21 157	85.32 156	76.11 159	71.05 127	46.55 198	51.17 143	41.83 179	48.20 159	61.81 171	84.00 118	81.14 159	91.28 153	89.42 154

UniMVSNet_ETH3D		69.49 165	65.86 174	73.72 132	76.51 162	85.88 149	78.65 131	70.52 134	48.08 195	55.71 126	37.64 190	40.56 190	71.38 137	75.05 183	81.49 147	89.57 181	92.29 128

tfpnnormal		69.29 166	65.58 175	73.62 134	79.87 143	84.82 162	76.97 150	75.12 96	45.29 199	49.03 156	35.57 196	37.20 202	68.02 151	82.70 128	81.24 154	92.69 122	92.20 130

v1240		69.28 167	67.82 171	71.00 162	74.09 184	85.13 159	76.54 155	67.28 163	53.17 179	44.70 179	41.55 180	39.38 195	70.51 146	81.29 144	81.18 156	92.88 120	93.02 123

CVMVSNet		68.95 168	70.79 151	66.79 178	79.69 145	83.75 172	72.05 176	70.90 128	56.20 166	36.30 197	54.94 130	59.22 133	54.03 185	78.33 165	78.65 172	87.77 191	84.44 175

MIMVSNet		68.66 169	69.43 159	67.76 173	64.92 203	84.68 164	74.16 168	54.10 200	60.85 150	51.27 142	39.47 185	49.48 154	67.48 154	84.86 112	85.57 99	94.63 56	81.10 190

TDRefinement		67.82 170	64.91 181	71.22 161	82.08 129	81.45 180	77.42 145	73.79 108	59.62 155	48.35 162	42.35 177	42.40 183	60.87 173	74.69 185	74.64 190	84.83 200	79.20 193

anonymousdsp		67.61 171	68.94 163	66.04 179	71.44 196	83.97 169	66.45 186	63.53 177	50.54 188	42.42 186	49.39 147	45.63 166	62.84 168	77.99 168	81.34 153	89.59 180	93.75 117

TinyColmap		67.16 172	63.51 188	71.42 158	77.94 153	79.54 194	72.80 173	69.78 138	56.58 165	45.52 174	44.53 162	33.53 207	74.45 116	76.91 177	77.06 182	88.03 190	76.41 196

FC-MVSNet-test		67.04 173	72.47 142	60.70 196	76.92 158	81.41 181	61.52 196	69.45 140	65.58 138	26.74 211	61.79 102	60.40 129	41.17 202	77.60 172	77.78 178	88.41 187	82.70 185

TransMVSNet (Re)		66.87 174	64.30 183	69.88 167	78.32 149	81.35 183	73.88 169	74.34 104	43.19 203	45.20 177	40.12 183	42.37 184	55.97 181	80.85 147	79.15 168	91.56 147	83.06 182

CMPMVS	50.59 17	66.74 175	62.72 192	71.42 158	85.40 110	89.72 116	72.69 174	70.72 130	51.24 184	51.75 139	38.91 187	44.40 168	63.74 166	70.84 195	71.52 195	84.19 201	72.45 203
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
v7n		66.43 176	65.51 176	67.51 174	71.63 195	83.10 173	70.89 180	65.02 172	50.13 191	44.68 180	39.59 184	38.77 196	62.57 169	77.59 173	78.91 169	90.29 171	90.44 146

EG-PatchMatch MVS		66.23 177	65.20 178	67.43 175	77.74 154	86.20 141	72.51 175	63.68 176	43.95 201	43.44 183	36.22 195	45.43 167	54.04 184	81.00 145	80.95 161	93.15 110	82.67 186

WR-MVS		64.98 178	66.59 173	63.09 189	74.34 181	82.68 176	64.98 192	69.17 143	54.42 176	36.18 198	44.32 164	44.35 169	44.65 196	73.60 186	77.83 177	89.21 183	88.96 160

gm-plane-assit		64.86 179	68.15 169	61.02 195	76.44 165	68.29 207	41.60 212	53.37 201	34.68 211	26.19 213	33.22 199	57.09 140	71.97 131	95.12 5	93.97 7	96.54 16	94.66 94

CP-MVSNet		64.84 180	64.97 179	64.69 184	72.09 191	81.04 186	66.66 185	67.53 160	52.45 181	37.40 193	44.00 168	38.37 198	53.54 188	72.26 190	76.93 183	90.94 161	89.75 152

MDTV_nov1_ep13_2view		64.72 181	64.94 180	64.46 185	71.14 197	81.94 179	67.53 183	54.54 197	55.92 167	43.29 184	44.02 167	43.27 176	59.87 174	71.85 192	74.77 189	90.36 169	82.82 184

MVS-HIRNet		64.63 182	64.03 187	65.33 181	75.01 177	82.84 174	58.54 203	52.10 202	55.42 170	49.29 154	29.83 204	43.48 174	66.97 156	78.28 166	78.81 170	90.07 174	79.52 192

pmnet_mix02		64.58 183	64.11 186	65.12 182	74.16 183	80.17 191	63.24 194	67.91 154	57.87 161	41.69 187	45.86 157	40.99 188	53.97 187	69.92 198	71.67 194	89.77 176	82.29 188

LTVRE_ROB	63.07 16	64.49 184	63.16 191	66.04 179	77.47 156	82.64 177	70.98 179	65.02 172	34.01 212	29.61 207	49.12 148	35.58 206	70.57 145	75.10 182	78.45 174	82.60 204	87.24 167
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		64.35 185	64.29 184	64.42 186	72.67 187	79.83 192	66.97 184	68.24 149	51.21 185	35.29 200	44.09 165	38.51 197	52.36 191	71.06 193	77.65 179	90.99 157	87.68 166

pmmvs6		64.24 186	61.77 196	67.12 176	72.39 190	81.39 182	71.33 178	65.95 170	36.05 208	48.48 161	30.55 200	43.45 175	58.75 176	77.88 171	76.36 186	85.83 197	86.70 170

pmmvs-eth3d		64.24 186	61.96 194	66.90 177	66.35 201	76.04 200	66.09 188	66.31 167	52.59 180	50.94 147	37.61 191	32.79 209	62.43 170	75.78 180	75.48 188	89.27 182	83.39 180

PS-CasMVS		64.22 188	64.19 185	64.25 187	71.86 193	80.67 187	66.42 187	67.43 162	50.64 187	36.48 195	42.60 174	37.46 201	52.56 190	71.98 191	76.69 185	90.76 163	89.29 158

WR-MVS_H		64.14 189	65.36 177	62.71 191	72.47 189	82.33 178	65.13 189	66.99 164	51.81 183	36.47 196	43.33 171	42.77 180	43.99 198	72.41 189	75.99 187	91.20 155	88.86 162

SixPastTwentyTwo		63.75 190	63.42 189	64.13 188	72.91 186	80.34 189	61.29 197	63.90 174	49.58 192	40.42 189	54.99 129	37.13 203	60.90 172	68.46 199	70.80 196	85.37 199	82.65 187

PM-MVS		63.52 191	62.51 193	64.70 183	64.79 205	76.08 199	65.07 190	62.08 179	58.13 159	46.56 169	44.98 160	31.31 210	62.89 167	72.58 188	69.93 200	86.81 193	84.55 174

DTE-MVSNet		63.26 192	63.41 190	63.08 190	72.59 188	78.56 195	65.03 191	68.28 148	50.53 189	32.38 204	44.03 166	37.79 200	49.48 194	70.83 196	76.73 184	90.73 164	85.42 173

testgi		63.11 193	64.88 182	61.05 194	75.83 173	78.51 196	60.42 198	66.20 168	48.77 193	34.56 201	56.96 113	40.35 191	40.95 203	77.46 174	77.22 181	88.37 189	74.86 201

GG-mvs-BLEND		62.08 194	88.31 44	31.46 209	0.16 220	98.10 10	91.57 41	0.09 217	85.07 65	0.21 221	73.90 56	83.74 39	0.19 218	88.98 69	89.39 60	96.58 15	99.02 14

Anonymous20231206		62.05 195	61.83 195	62.30 193	72.09 191	77.84 197	63.10 195	67.62 159	50.20 190	36.68 194	29.59 205	37.05 204	43.90 199	77.33 175	77.31 180	90.41 168	83.49 179

N_pmnet		60.52 196	58.83 199	62.50 192	68.97 199	75.61 201	59.72 201	66.47 165	51.90 182	41.26 188	35.42 197	35.63 205	52.25 192	67.07 202	70.08 199	86.35 195	76.10 197

EU-MVSNet		58.73 197	60.92 197	56.17 199	66.17 202	72.39 204	58.85 202	61.24 182	48.47 194	27.91 209	46.70 156	40.06 192	39.07 204	68.27 200	70.34 198	83.77 202	80.23 191

test20.03		57.93 198	59.22 198	56.44 198	71.84 194	73.78 203	53.55 206	65.96 169	43.02 204	28.46 208	37.50 192	38.17 199	30.41 208	75.25 181	74.42 192	88.41 187	72.37 204

MDA-MVSNet-bldmvs		54.99 199	52.66 203	57.71 197	52.74 211	74.87 202	55.61 204	68.41 147	43.65 202	32.54 202	37.93 189	22.11 216	54.11 183	48.85 209	67.34 202	82.85 203	73.88 202

new-patchmatchnet		53.91 200	52.69 202	55.33 201	64.83 204	70.90 205	52.24 207	61.75 180	41.09 205	30.82 205	29.90 203	28.22 212	36.69 205	61.52 204	65.08 203	85.64 198	72.14 205

MIMVSNet1		52.76 201	53.95 201	51.38 203	41.96 214	70.79 206	53.56 205	63.03 178	39.36 206	27.83 210	22.73 210	33.07 208	34.47 207	70.49 197	72.69 193	87.41 192	68.51 206

pmmvs3		52.59 202	52.43 204	52.78 202	54.53 210	64.49 209	50.07 208	46.89 209	35.31 210	30.19 206	27.27 207	26.96 214	53.02 189	67.28 201	70.54 197	81.96 205	75.20 199

new_pmnet		50.32 203	51.36 205	49.11 204	49.19 212	64.89 208	48.66 210	47.99 208	47.55 196	26.27 212	29.51 206	28.66 211	44.89 195	61.12 205	62.74 205	77.66 207	65.03 207

FPMVS		50.25 204	45.67 207	55.58 200	70.48 198	60.12 210	59.78 200	59.33 187	46.66 197	37.94 191	30.22 202	27.51 213	35.94 206	50.98 208	47.90 208	70.02 209	56.31 208

test_method		47.92 205	55.39 200	39.21 207	19.90 218	49.24 212	39.29 213	34.65 214	57.37 163	32.54 202	25.11 208	41.02 187	44.31 197	66.58 203	57.57 207	64.59 212	90.82 142

PMVS	36.83 18	40.62 206	36.39 208	45.56 205	58.40 207	33.20 215	32.62 215	56.02 191	28.25 213	37.92 192	22.29 211	26.15 215	25.29 210	48.49 210	43.82 211	63.13 213	52.53 211
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		35.20 207	33.96 209	36.65 208	43.30 213	32.51 216	26.96 217	48.31 207	38.87 207	20.08 216	8.08 213	7.41 220	26.44 209	53.60 206	58.43 206	54.81 214	38.79 213
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		32.52 208	33.92 210	30.88 210	34.15 217	44.70 214	27.79 216	39.69 213	22.21 214	4.31 220	15.73 212	14.13 218	12.45 215	40.11 211	47.00 209	66.88 210	53.54 209

E-PMN		21.42 209	17.56 212	25.94 211	36.25 216	19.02 219	11.56 218	43.72 211	15.25 216	6.99 218	8.04 214	4.53 222	21.77 212	16.13 214	26.16 213	35.34 216	33.77 214

MVE	25.07 19	21.25 210	23.51 211	18.62 213	15.07 219	29.77 218	10.67 220	34.60 215	12.51 217	9.46 217	7.84 215	3.82 223	14.38 214	27.45 213	42.42 212	27.56 218	40.74 212
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		20.61 211	16.32 213	25.62 212	36.41 215	18.93 220	11.51 219	43.75 210	15.65 215	6.53 219	7.56 216	4.68 221	22.03 211	14.56 215	23.10 214	33.51 217	29.77 215

testmvs		0.76 212	1.23 214	0.21 214	0.05 221	0.21 221	0.38 222	0.09 217	0.94 218	0.05 222	2.13 218	0.08 224	0.60 217	0.82 216	0.77 215	0.11 219	3.62 217

test123		0.67 213	1.11 215	0.16 215	0.01 222	0.14 222	0.20 223	0.04 219	0.77 219	0.02 223	2.15 217	0.02 225	0.61 216	0.23 217	0.72 216	0.07 220	3.76 216

uanet_test		0.00 214	0.00 216	0.00 216	0.00 223	0.00 223	0.00 224	0.00 220	0.00 220	0.00 224	0.00 219	0.00 226	0.00 219	0.00 218	0.00 217	0.00 221	0.00 218

sosnet-low-res		0.00 214	0.00 216	0.00 216	0.00 223	0.00 223	0.00 224	0.00 220	0.00 220	0.00 224	0.00 219	0.00 226	0.00 219	0.00 218	0.00 217	0.00 221	0.00 218

sosnet		0.00 214	0.00 216	0.00 216	0.00 223	0.00 223	0.00 224	0.00 220	0.00 220	0.00 224	0.00 219	0.00 226	0.00 219	0.00 218	0.00 217	0.00 221	0.00 218

RE-MVS-def										39.41 190

9.14												91.16 7

SR-MVS					96.04 31			87.51 27				87.60 20

Anonymous202405211			75.59 126		85.13 113	91.06 103	84.62 91	77.96 74	69.47 129		40.79 182	63.84 119	84.57 65	83.55 120	84.69 107	89.69 177	95.75 82

our_test_3					73.80 185	79.57 193	64.47 193

ambc			50.35 206		55.61 209	59.93 211	48.73 209		44.08 200	35.81 199	24.01 209	10.64 219	41.57 201	72.83 187	63.35 204	74.99 208	77.61 194

MTAPA										91.14 6		85.84 26

MTMP										90.95 7		84.13 35

Patchmatch-RL test							8.17 221

tmp_tt				39.78 206	56.31 208	31.71 217	35.84 214	15.08 216	82.57 74	50.83 149	63.07 94	47.51 161	15.28 213	52.23 207	44.24 210	65.35 211

XVS					89.65 70	95.93 47	85.97 79			76.32 53		82.05 45				93.51 90

X-MVStestdata					89.65 70	95.93 47	85.97 79			76.32 53		82.05 45				93.51 90

abl_6				89.54 32	95.55 39	97.59 19	89.01 55	85.00 40	94.67 15	83.04 32	84.70 35	91.47 6	89.46 26			95.20 46	98.63 20

mPP-MVS					95.90 33							80.22 53

NP-MVS									89.55 47

Patchmtry						87.41 126	78.32 134	54.14 198		51.09 144

DeepMVS_CX						48.96 213	43.77 211	40.58 212	50.93 186	24.67 214	36.95 194	20.18 217	41.60 200	38.92 212		52.37 215	53.31 210

High-resolution multi-view benchmark