EC-Depth: Exploring the consistency of self-supervised monocular depth estimation in challenging scenes

TL;DR

EC-Depth introduces a two-stage self-supervised framework that enhances monocular depth estimation robustness in challenging scenes like rainy conditions, outperforming existing methods across multiple benchmarks.

Contribution

The paper proposes a novel depth consistency regularization and a pseudo-label filtering strategy within a two-stage framework to improve depth estimation in adverse scenarios.

Findings

Achieves superior accuracy on KITTI, KITTI-C, DrivingStereo, and NuScenes-Night datasets.

Demonstrates improved robustness in rainy and night conditions.

Outperforms state-of-the-art methods in challenging environments.

Abstract

Self-supervised monocular depth estimation holds significant importance in the fields of autonomous driving and robotics. However, existing methods are typically trained and tested on standard datasets, overlooking the impact of various adverse conditions prevalent in real-world applications, such as rainy days. As a result, it is commonly observed that these methods struggle to handle these challenging scenarios. To address this issue, we present EC-Depth, a novel self-supervised two-stage framework to achieve a robust depth estimation. In the first stage, we propose depth consistency regularization to propagate reliable supervision from standard to challenging scenes. In the second stage, we adopt the Mean Teacher paradigm and propose a novel consistency-based pseudo-label filtering strategy to improve the quality of pseudo-labels, further improving both the accuracy and robustness of our model. Extensive experiments demonstrate that our method achieves accurate and consistent depth predictions in both standard and challenging scenarios, surpassing existing state-of-the-art methods on KITTI, KITTI-C, DrivingStereo, and NuScenes-Night benchmarks.