Multilateral Temporal-view Pyramid Transformer for Video Inpainting Detection

arXiv:2404.11054v1 Announce Type: new
Abstract: The task of video inpainting detection is to expose the pixel-level inpainted regions within a video sequence. Existing methods usually focus on leveraging spatial and temporal inconsistencies. However, these methods typically employ fixed operations to combine spatial and temporal clues, limiting their applicability in different scenarios. In this paper, we introduce a novel Multilateral Temporal-view Pyramid Transformer ({\em MumPy}) that collaborates spatial-temporal clues flexibly. Our method utilizes a newly designed multilateral temporal-view encoder to extract …

abstract arxiv cs.cv detection focus however inpainting operations pixel pyramid spatial temporal transformer type video view