Dynamic in Static: Hybrid Visual Correspondence for Self-Supervised Video Object Segmentation

arXiv:2404.13505v1 Announce Type: new
Abstract: Conventional video object segmentation (VOS) methods usually necessitate a substantial volume of pixel-level annotated video data for fully supervised learning. In this paper, we present HVC, a \textbf{h}ybrid static-dynamic \textbf{v}isual \textbf{c}orrespondence framework for self-supervised VOS. HVC extracts pseudo-dynamic signals from static images, enabling an efficient and scalable VOS model. Our approach utilizes a minimalist fully-convolutional architecture to capture static-dynamic visual correspondence in image-cropped views. To achieve this objective, we present a unified self-supervised approach to …

abstract arxiv cs.cv data dynamic enabling framework hybrid images object paper pixel segmentation supervised learning type video video data visual