ChronoWorld: Camera-Controlled Consistent 4D World Generation via Spatiotemporal Cues and Geometric Reflections

Paper recorded by Signals 4 on 2026-10-05 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-05 on arXiv · recorded by Signals 4 on 2026-10-06

Category: cs.CV · 计算机视觉 · first seen 2026-10-06

Abstract

While existing camera-controllable video generation models can produce visually compelling sequences, preserving intrinsic 4D spatiotemporal coherence remains challenging. To address this limitation, we propose ChronoWorld, an "Observation--State--Reflection" framework that leverages spatiotemporal causal cues and reconstruction priors to generate globally consistent, free-view 4D scenes. Given a

Read on arXiv →