Accurate Monocular Depth Estimation via Interaction of Hierarchical Features. (November 2020)

• Record Type: Journal Article
• Authors: Zhang, Jiahao; Chen, Dan; Lin, Ye; Wu, You
• Is Part Of: Journal of physics. Volume 1651(2020)
• Publication Date: 2020-11
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1651/1/012180
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: 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.