paper-with-me

홈 › Papers

OptiWorld: Optimal Control for Video World Generation under Physical Constraints

2026-05-30 · Yu Yuan, Jianhao Yuan, Xijun Wang, Daiqing Li, Liu He, Lu Ling, Stanley H. Chan arxiv

Video generation models are becoming a scalable form of world models, but they mainly generate plausible motion rather than proactively control or optimize the underlying dynamics. As a result, an object in the generated video may follow trajectories that are unsafe, not smooth, inefficient, or physically inconsistent. In this work, we propose \textbf{OptiWorld}, a framework that brings classical optimal control into video generation at inference time. OptiWorld first extracts a compact, task-relevant world state, then plans an optimal trajectory under physical constraints, and finally renders the video conditioned on this trajectory. We formulate planning as a geometric problem on a continuous manifold, which converts 3D geometry and task-dependent physical constraints into a unified planning geometry. By adding this optimal-control layer, OptiWorld generates videos with preferable dynamics, demonstrating strong potential in multiple tasks including goal-conditioned image-to-video generation, video dynamics editing, and counterfactual generation.

📄 PDF Abstract BibTeX arXiv:2606.00499

Code (0)

등록된 구현이 없습니다.

Tasks

Video Generation

Similar Papers 제목 키워드 기반

Video-P2P: Video Editing with Cross-attention Control

2023-03-08 · CVPR 2024 1 · Shaoteng Liu, Yuechen Zhang, Wenbo Li, Zhe Lin 외

This paper presents Video-P2P, a novel framework for real-world video editing with cross-attention control. While attention control has proven effective for image editing with pre-trained image generation models, there a…

Image GenerationVideo EditingVideo Generation

Video-P2P: Video Editing with Cross-attention Control

2023-03-08 · arXiv 2023 3 · Shaoteng Liu;Yuechen Zhang;Wenbo Li;Zhe Lin;Jiaya Jia

This paper presents Video-P2P, a novel framework for real-world video editing with cross-attention control. While attention control has proven effective for image editing with pre-trained image generation models, there a…

Image GenerationVideo EditingVideo Generation

CamWorldQA: Perceptual Quality Assessment of Camera-Controlled World Video Generation

2026-08-19 · Yunhe Li, Likun Wu, Sijing Wu, Xinyu Tian 외 arxiv

Recent advances in generative video models have enabled camera-controlled world video generation, allowing models to synthesize videos under user-defined camera trajectories. However, existing video quality assessment (V…

Video Quality AssessmentVideo Generation

GameGen-X: Interactive Open-world Game Video Generation

2024-11-01 · Haoxuan Che, Xuanhua He, Quande Liu, Cheng Jin 외

We introduce GameGen-X, the first diffusion transformer model specifically designed for both generating and interactively controlling open-world game videos. This model facilitates high-quality, open-domain generation by…

Text-to-Video GenerationVideo Generation

Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control

2026-06-26 · Haoyuan Wang, Yabo Chen, Haibin Huang, Chi Zhang 외 arxiv

Building interactive world models requires generating realistic videos while maintaining controllable dynamics over long horizons. Autoregressive video generation offers a scalable foundation, but suffers from error accu…

Video Generation