Skip to content
arXiv cs.CV · Papers

Keyframe-Anchored Identity Preservation for Sequential-Action Video Generation

arXiv:2607.17985v1 Announce Type: new Abstract: Identity-preserving text-to-video generation aims to synthesize a video that accurately follows a textual description while maintaining the recognizability of a user-specified subject throughout. The IPVG26 challenge extends this framework from a single holistic prompt to