Open AccessMulti-Scale Context Enhanced Network for Monocular Depth Estimation
Author(s) -
Wenju Wang,
Yue Ning
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1848/1/012023
Subject(s) - monocular , computer science , context (archaeology) , dimension (graph theory) , scale (ratio) , artificial intelligence , residual , convolution (computer science) , ranging , block (permutation group theory) , field (mathematics) , computer vision , pattern recognition (psychology) , algorithm , artificial neural network , mathematics , geography , geometry , telecommunications , cartography , archaeology , pure mathematics
Monocular depth estimation is a classical computer vision task. At present, most CNN methods cannot effectively combine high-level and low-level features, leading to the loss of details and blurring of boundaries. To solve the problem, we propose a Multi-Scale Context Enhanced Network (MCEN) to learn more abundant context and expand its receptive field for high-accuracy estimation. Our method employs CRE-HRNet (Context and Receptive Enhanced High-Resolution Network) with four branches ranging from low-dimension to high-dimension features to obtain richer contextual information and extract multi-scale features. It then uses RM (Refinement Module) adopting the residual dilated convolution to retains detailed information and improve the receptive field. Finally, non-local block enables our network to capture the longdistance context through its special non-local operation. Experiments with the NYU Depth V2 dataset show its outstanding performance.