Open AccessAccurate Monocular Depth Estimation via Interaction of Hierarchical Features
Author(s) -
Jiahao Zhang,
Dan Chen,
Yandan Lin,
You Wu
Publication year - 2020
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 - 10.1088/1742-6596/1651/1/012180
Subject(s) - monocular , inference , ordinal regression , computer science , artificial intelligence , benchmark (surveying) , discretization , task (project management) , pattern recognition (psychology) , boundary (topology) , confusion , feature (linguistics) , regression , object (grammar) , machine learning , computer vision , mathematics , statistics , geography , psychology , mathematical analysis , linguistics , philosophy , management , geodesy , psychoanalysis , economics
Monocular depth estimation is a challenging task, which assists in understanding 3D scene geometry from the same 2D scene. The ordinal-regression-method demonstrates superior performance in this issue but naive ordinal inference strategy for inferring the final depth values and naive operations to up-sample to the desired space scale introduce significant discretization errors and object boundary confusion. Firstly, we come up with a novel inference strategy to reduce the discretization errors. And then a specifically designed decoder that completes the fusion of different hierarchical features under guidance and the fusion feature reconstruction. We evaluate on a public monocular depth-estimation benchmark dataset (NYU Depth V2). The experimental results show that the method proposed outperforms other ordinal regression methods.