PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Chen, Chen, Chuhao, Huang, Yiming, Dou, Zhiyang, Liu, Yuan, Gu, Jiatao, Liu, Lingjie
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918191530246144
author Wang, Chen
Chen, Chuhao
Huang, Yiming
Dou, Zhiyang
Liu, Yuan
Gu, Jiatao
Liu, Lingjie
author_facet Wang, Chen
Chen, Chuhao
Huang, Yiming
Dou, Zhiyang
Liu, Yuan
Gu, Jiatao
Liu, Lingjie
contents Existing video generation models excel at producing photo-realistic videos from text or images, but often lack physical plausibility and 3D controllability. To overcome these limitations, we introduce PhysCtrl, a novel framework for physics-grounded image-to-video generation with physical parameters and force control. At its core is a generative physics network that learns the distribution of physical dynamics across four materials (elastic, sand, plasticine, and rigid) via a diffusion model conditioned on physics parameters and applied forces. We represent physical dynamics as 3D point trajectories and train on a large-scale synthetic dataset of 550K animations generated by physics simulators. We enhance the diffusion model with a novel spatiotemporal attention block that emulates particle interactions and incorporates physics-based constraints during training to enforce physical plausibility. Experiments show that PhysCtrl generates realistic, physics-grounded motion trajectories which, when used to drive image-to-video models, yield high-fidelity, controllable videos that outperform existing methods in both visual quality and physical plausibility. Project Page: https://cwchenwang.github.io/physctrl
format Preprint
id arxiv_https___arxiv_org_abs_2509_20358
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation
Wang, Chen
Chen, Chuhao
Huang, Yiming
Dou, Zhiyang
Liu, Yuan
Gu, Jiatao
Liu, Lingjie
Computer Vision and Pattern Recognition
Existing video generation models excel at producing photo-realistic videos from text or images, but often lack physical plausibility and 3D controllability. To overcome these limitations, we introduce PhysCtrl, a novel framework for physics-grounded image-to-video generation with physical parameters and force control. At its core is a generative physics network that learns the distribution of physical dynamics across four materials (elastic, sand, plasticine, and rigid) via a diffusion model conditioned on physics parameters and applied forces. We represent physical dynamics as 3D point trajectories and train on a large-scale synthetic dataset of 550K animations generated by physics simulators. We enhance the diffusion model with a novel spatiotemporal attention block that emulates particle interactions and incorporates physics-based constraints during training to enforce physical plausibility. Experiments show that PhysCtrl generates realistic, physics-grounded motion trajectories which, when used to drive image-to-video models, yield high-fidelity, controllable videos that outperform existing methods in both visual quality and physical plausibility. Project Page: https://cwchenwang.github.io/physctrl
title PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.20358