Monocular Depth Estimation with Sharp Boundary

TL;DR

This paper introduces a novel approach for monocular depth estimation that significantly improves boundary sharpness by incorporating a scene understanding module, a scale transform, and a boundary-aware loss, leading to clearer depth map boundaries.

Contribution

The paper proposes a new scene understanding module, a scale transform mechanism, and a boundary-aware loss function to address boundary blur in depth estimation.

Findings

Improved boundary clarity in depth maps on NYU-depth v2 and SUN RGB-D datasets.

Competitive depth accuracy performance.

Effective mitigation of boundary blur problem.

Abstract

Monocular depth estimation is the base task in computer vision. It has a tremendous development in the decade with the development of deep learning. But the boundary blur of the depth map is still a serious problem. Research finds the boundary blur problem is mainly caused by two factors, first, the low-level features containing boundary and structure information may loss in deeper networks during the convolution process., second, the model ignores the errors introduced by the boundary area due to the few portions of the boundary in the whole areas during the backpropagation. In order to mitigate the boundary blur problem, we focus on the above two impact factors. Firstly, we design a scene understanding module to learn the global information with low- and high-level features, and then to transform the global information to different scales with our proposed scale transform module according to the different phases in the decoder. Secondly, we propose a boundary-aware depth loss function to pay attention to the effects of the boundary's depth value. The extensive experiments show that our method can predict the depth maps with clearer boundaries, and the performance of the depth accuracy base on NYU-depth v2 and SUN RGB-D is competitive.