RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation

07/25/2022
by   Mu He, et al.
0

Existing self-supervised monocular depth estimation methods can get rid of expensive annotations and achieve promising results. However, these methods suffer from severe performance degradation when directly adopting a model trained on a fixed resolution to evaluate at other different resolutions. In this paper, we propose a resolution adaptive self-supervised monocular depth estimation method (RA-Depth) by learning the scale invariance of the scene depth. Specifically, we propose a simple yet efficient data augmentation method to generate images with arbitrary scales for the same scene. Then, we develop a dual high-resolution network that uses the multi-path encoder and decoder with dense interactions to aggregate multi-scale features for accurate depth inference. Finally, to explicitly learn the scale invariance of the scene depth, we formulate a cross-scale depth consistency loss on depth predictions with different scales. Extensive experiments on the KITTI, Make3D and NYU-V2 datasets demonstrate that RA-Depth not only achieves state-of-the-art performance, but also exhibits a good ability of resolution adaptation.

READ FULL TEXT

page 2

page 5

page 11

research
10/08/2022

Detaching and Boosting: Dual Engine for Scale-Invariant Self-Supervised Monocular Depth Estimation

Monocular depth estimation (MDE) in the self-supervised scenario has eme...
research
03/24/2021

SaccadeCam: Adaptive Visual Attention for Monocular Depth Sensing

Most monocular depth sensing methods use conventionally captured images ...
research
03/03/2021

Multimodal Scale Consistency and Awareness for Monocular Self-Supervised Depth Estimation

Dense depth estimation is essential to scene-understanding for autonomou...
research
12/24/2021

Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimation

Self-supervised learning has shown very promising results for monocular ...
research
06/08/2018

Deep multi-scale architectures for monocular depth estimation

This paper aims at understanding the role of multi-scale information in ...
research
11/30/2021

360MonoDepth: High-Resolution 360° Monocular Depth Estimation

360 cameras can capture complete environments in a single shot, which ma...
research
10/20/2019

Unsupervised High-Resolution Depth Learning From Videos With Dual Networks

Unsupervised depth learning takes the appearance difference between a ta...

Please sign up or login with your details

Forgot password? Click here to reset