FlowDepth: Decoupling Optical Flow for Self-Supervised Monocular Depth Estimation

arXiv:2403.19294v1 Announce Type: cross
Abstract: Self-supervised multi-frame methods have currently achieved promising results in depth estimation. However, these methods often suffer from mismatch problems due to the moving objects, which break the static assumption. Additionally, unfairness can occur when calculating photometric errors in high-freq or low-texture regions of the images. To address these issues, existing approaches use additional semantic priori black-box networks to separate moving objects and improve the model only at the loss level. Therefore, we propose FlowDepth, where …

abstract arxiv cs.cv cs.lg errors flow however images low moving objects optical optical flow results texture type