Moving Object Segmentation: All You Need Is SAM (and Flow)

arXiv:2404.12389v1 Announce Type: new
Abstract: The objective of this paper is motion segmentation -- discovering and segmenting the moving objects in a video. This is a much studied area with numerous careful,and sometimes complex, approaches and training schemes including: self-supervised learning, learning from synthetic datasets, object-centric representations, amodal representations, and many more. Our interest in this paper is to determine if the Segment Anything model (SAM) can contribute to this task. We investigate two models for combining SAM with optical …

abstract arxiv cs.cv datasets flow moving object objects paper sam segmentation self-supervised learning supervised learning synthetic training type video