Preprint
Oct 2026
Kepler4D: Controllable Future Video Generation via 4D Scene State Evolution
Video world models aim to preserve scene structure and predict how dynamic objects evolve beyond visual observations. We present Kepler4D, a framework for future video generation through explicit 4D scene state evolution. Given a monocular video, Kepler4D constructs a shared 3D representation of background geometry, ob...
Fei-Ran Wang, Bin Duan, Jun-Yi Wu et al.
· 0 citations