DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic Environments. (arXiv:2209.08430v2 [cs.CV] UPDATED)

Learning-based visual odometry (VO) algorithms achieve remarkable performance
on common static scenes, benefiting from high-capacity models and massive
annotated data, but tend to fail in dynamic, populated environments. Semantic
segmentation is largely used to discard dynamic associations before estimating
camera motions but at the cost of discarding static features and is hard to
scale up to unseen categories. In this paper, we leverage the mutual dependence
between camera ego-motion and motion segmentation and show that both can be
jointly refined …

arxiv environments segmentation