ER-Depth: Enhancing the Robustness of Self-Supervised Monocular Depth Estimation in Challenging Scenes
Open Access
- 21 November 2025
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (12) , 1-23
Abstract
Self-supervised monocular depth estimation holds significant importance in the fields of autonomous driving and robotics. However, existing methods are typically trained and evaluated on clear, sunny datasets, overlooking the impact of various adverse conditions commonly encountered in real-world applications, such as rainy weather, low visibility, and motion blur. As a result, they often struggle in challenging scenarios and produce artifacts. To address this issue, we propose ER-Depth, a novel two-stage self-supervised framework designed for robust depth estimation. In the first stage, we propose perturbation-invariant depth consistency regularization to propagate reliable supervision from standard to challenging scenes. In the second stage, we adopt the Mean Teacher paradigm for self-distillation and present a novel consistency-based pseudo-label filtering strategy to improve the quality of pseudo-labels. Extensive experiments demonstrate that our method exhibits exceptional robustness in challenging scenarios while maintaining high performance in standard scenes, significantly outperforming existing state-of-the-art methods on challenging KITTI-C, DrivingStereo, and NuScenes-Night benchmarks. Project page: https://ruijiezhu94.github.io/ERDepth_page .Keywords
All Related Versions
Funding Information
- National Key Research and Development Program of China (2024YFB3909902)
- National Nature Science Foundation of China (62306294)
This publication has 81 references indexed in Scilit:
- Hierarchical Object Relationship Constrained Monocular Depth Estimation.Pattern Recognition, 2021
- The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth2021
- Rain Rendering for Evaluating and Improving Robustness to Bad WeatherInternational Journal of Computer Vision, 2020
- 3D Packing for Self-Supervised Monocular Depth Estimation2020
- nuScenes: A Multimodal Dataset for Autonomous Driving2020
- Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement2020
- Pseudo-LiDAR From Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving2019
- Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue2016
- Deep Residual Learning for Image Recognition2016
- The Jensen-Shannon divergenceJournal of the Franklin Institute, 1997