UCSD's LIFT Lets You Control Future Video Layouts via On-Policy Self-Distillation

UCSanDiego · hf · 2026-09-30

LIFT from UC San Diego is a unified image-to-video framework adding Layout-In-FuTure control: users specify what should appear in future views and where, addressing large viewpoint changes where the camera reveals unseen regions. On-policy self-distillation (OPSD) transfers dense-layout teacher control to a last-frame-layout student, supported by the LIFT-Vista dataset of large-viewpoint videos with consistent layout annotations. LIFT improves video quality, future-layout, and camera controllability over prior methods.

Original post →

More from Multimodal

Multimodal channel →