$\mathrm{F^2Depth}$: Self-supervised Indoor Monocular Depth Estimation via Optical Flow Consistency and Feature Map Synthesis

arXiv:2403.18443v1 Announce Type: new
Abstract: Self-supervised monocular depth estimation methods have been increasingly given much attention due to the benefit of not requiring large, labelled datasets. Such self-supervised methods require high-quality salient features and consequently suffer from severe performance drop for indoor scenes, where low-textured regions dominant in the scenes are almost indiscriminative. To address the issue, we propose a self-supervised indoor monocular depth estimation framework called $\mathrm{F^2Depth}$. A self-supervised optical flow estimation network is introduced to supervise depth learning. …

abstract arxiv attention benefit cs.cv datasets feature features flow low map optical optical flow performance quality synthesis type via