WorldCrafter: consistent video world model with implicit 3D-aware memory

yshan2u · x · 2026-09-22

WorldCrafter is a new paper proposing a consistent video world model built on implicit 3D-aware memory. By encoding 3D spatial information implicitly into a memory module, the model aims to maintain consistent world state across frames and viewpoints during long video generation. Paper link in the original post.

Related event: TencentARC Releases WorldCrafter: Video World Model with Implicit 3D Memory for Long-Horizon Consistent Exploration(5 posts)→

Original post →

More from Research

Research channel →