Paper ID: 2305.06036

FusionDepth: Complement Self-Supervised Monocular Depth Estimation with Cost Volume

Zhuofei Huang, Jianlin Liu, Shang Xu, Ying Chen, Yong Liu

Multi-view stereo depth estimation based on cost volume usually works better than self-supervised monocular depth estimation except for moving objects and low-textured surfaces. So in this paper, we propose a multi-frame depth estimation framework which monocular depth can be refined continuously by multi-frame sequential constraints, leveraging a Bayesian fusion layer within several iterations. Both monocular and multi-view networks can be trained with no depth supervision. Our method also enhances the interpretability when combining monocular estimation with multi-view cost volume. Detailed experiments show that our method surpasses state-of-the-art unsupervised methods utilizing single or multiple frames at test time on KITTI benchmark.

Submitted: May 10, 2023