BEVScope: Enhancing Self-Supervised Depth Estimation Leveraging Bird's-Eye-View in Dynamic Scenarios
This addresses depth estimation challenges in dynamic scenarios for autonomous driving and robotics, but appears incremental as it builds on existing self-supervised methods.
The paper tackles limitations in self-supervised depth estimation for autonomous driving by introducing BEVScope, which uses Bird's-Eye-View features and an adaptive loss for dynamic objects, achieving competitive performance on the Nuscenes dataset.
Depth estimation is a cornerstone of perception in autonomous driving and robotic systems. The considerable cost and relatively sparse data acquisition of LiDAR systems have led to the exploration of cost-effective alternatives, notably, self-supervised depth estimation. Nevertheless, current self-supervised depth estimation methods grapple with several limitations: (1) the failure to adequately leverage informative multi-camera views. (2) the limited capacity to handle dynamic objects effectively. To address these challenges, we present BEVScope, an innovative approach to self-supervised depth estimation that harnesses Bird's-Eye-View (BEV) features. Concurrently, we propose an adaptive loss function, specifically designed to mitigate the complexities associated with moving objects. Empirical evaluations conducted on the Nuscenes dataset validate our approach, demonstrating competitive performance. Code will be released at https://github.com/myc634/BEVScope.