FusionDepth: Complement Self-Supervised Monocular Depth Estimation with Cost Volume
This work addresses depth estimation for autonomous driving and robotics by combining monocular and multi-view techniques to handle moving objects and low-textured surfaces, representing an incremental advancement.
The paper tackles the problem of improving self-supervised monocular depth estimation by integrating it with multi-view stereo cost volumes, resulting in a method that surpasses state-of-the-art unsupervised approaches on the KITTI benchmark.
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.