DeVOS: Flow-Guided Deformable Transformer for Video Object Segmentation

arXiv:2405.08715v1 Announce Type: new
Abstract: The recent works on Video Object Segmentation achieved remarkable results by matching dense semantic and instance-level features between the current and previous frames for long-time propagation. Nevertheless, global feature matching ignores scene motion context, failing to satisfy temporal consistency. Even though some methods introduce local matching branch to achieve smooth propagation, they fail to model complex appearance changes due to the constraints of the local window. In this paper, we present DeVOS (Deformable VOS), an …

abstract arxiv context cs.cv current feature features flow global instance object propagation results segmentation semantic temporal transformer type video