ExplorerComputer VisionComputer Vision
Research PaperResearchia:202607.03005

WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory

Hanlin Wang

Abstract

We present WorldDirector, a highly controllable video world model framework designed for persistent dynamic object memory and unrestricted viewpoint exploration. Unlike existing world models that entangle physical dynamics with pixel rendering and rely on continuous visual observation to sustain motion, our framework explicitly decouples semantic motion orchestration from visual generation. By leveraging an LLM to coordinate 3D trajectories with camera movements and subsequently employing these ...

Submitted: July 3, 2026Subjects: Computer Vision; Computer Vision

Description / Details

We present WorldDirector, a highly controllable video world model framework designed for persistent dynamic object memory and unrestricted viewpoint exploration. Unlike existing world models that entangle physical dynamics with pixel rendering and rely on continuous visual observation to sustain motion, our framework explicitly decouples semantic motion orchestration from visual generation. By leveraging an LLM to coordinate 3D trajectories with camera movements and subsequently employing these orchestrated trajectories as control signals for video generation, our approach ensures strict physical logic and appearance stability, successfully preserving the exact visual identities of dynamic entities even when they re-enter the scene after prolonged periods out of view. Experimental results demonstrate that our method supports the synthesis of complex and extended events with unprecedented controllability and persistent dynamic object memory. Project Page: https://worlddirector.github.io/


Source: arXiv:2607.02517v1 - http://arxiv.org/abs/2607.02517v1 PDF: https://arxiv.org/pdf/2607.02517v1 Original Link: http://arxiv.org/abs/2607.02517v1

Please sign in to join the discussion.

No comments yet. Be the first to share your thoughts!

Access Paper
View Source PDF
Submission Info
Date:
Jul 3, 2026
Topic:
Computer Vision
Area:
Computer Vision
Comments:
0
Bookmark