AudioScenic: Audio-Driven Video Scene Editing

arXiv:2404.16581v1 Announce Type: new
Abstract: Audio-driven visual scene editing endeavors to manipulate the visual background while leaving the foreground content unchanged, according to the given audio signals. Unlike current efforts focusing primarily on image editing, audio-driven video scene editing has not been extensively addressed. In this paper, we introduce AudioScenic, an audio-driven framework designed for video scene editing. AudioScenic integrates audio semantics into the visual scene through a temporal-aware audio semantic injection process. As our focus is on background editing, …

abstract arxiv audio cs.cv current editing framework image paper type video visual while