Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimation

arXiv:2404.14908v1 Announce Type: new
Abstract: This paper focuses on self-supervised monocular depth estimation in dynamic scenes trained on monocular videos. Existing methods jointly estimate pixel-wise depth and motion, relying mainly on an image reconstruction loss. Dynamic regions1 remain a critical challenge for these methods due to the inherent ambiguity in depth and motion estimation, resulting in inaccurate depth estimation. This paper proposes a self-supervised training framework exploiting pseudo depth labels for dynamic regions from training data. The key contribution of …

abstract arxiv challenge cs.cv dynamic image loss mining paper pixel supervision type videos wise