RealWonder: Real-Time Physical Action-Conditioned Video Generation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Wei, Chen, Ziyu, Li, Zizhang, Wang, Yue, Yu, Hong-Xing, Wu, Jiajun
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908868580212736
author Liu, Wei
Chen, Ziyu
Li, Zizhang
Wang, Yue
Yu, Hong-Xing
Wu, Jiajun
author_facet Liu, Wei
Chen, Ziyu
Li, Zizhang
Wang, Yue
Yu, Hong-Xing
Wu, Jiajun
contents Current video generation models cannot simulate physical consequences of 3D actions like forces and robotic manipulations, as they lack structural understanding of how actions affect 3D scenes. We present RealWonder, the first real-time system for action-conditioned video generation from a single image. Our key insight is using physics simulation as an intermediate bridge: instead of directly encoding continuous actions, we translate them through physics simulation into visual representations (optical flow and RGB) that video models can process. RealWonder integrates three components: 3D reconstruction from single images, physics simulation, and a distilled video generator requiring only 4 diffusion steps. Our system achieves 13.2 FPS at 480x832 resolution, enabling interactive exploration of forces, robot actions, and camera controls on rigid objects, deformable bodies, fluids, and granular materials. We envision RealWonder opens new opportunities to apply video models in immersive experiences, AR/VR, and robot learning. Our code and model weights are publicly available in our project website: https://liuwei283.github.io/RealWonder/
format Preprint
id arxiv_https___arxiv_org_abs_2603_05449
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RealWonder: Real-Time Physical Action-Conditioned Video Generation
Liu, Wei
Chen, Ziyu
Li, Zizhang
Wang, Yue
Yu, Hong-Xing
Wu, Jiajun
Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Current video generation models cannot simulate physical consequences of 3D actions like forces and robotic manipulations, as they lack structural understanding of how actions affect 3D scenes. We present RealWonder, the first real-time system for action-conditioned video generation from a single image. Our key insight is using physics simulation as an intermediate bridge: instead of directly encoding continuous actions, we translate them through physics simulation into visual representations (optical flow and RGB) that video models can process. RealWonder integrates three components: 3D reconstruction from single images, physics simulation, and a distilled video generator requiring only 4 diffusion steps. Our system achieves 13.2 FPS at 480x832 resolution, enabling interactive exploration of forces, robot actions, and camera controls on rigid objects, deformable bodies, fluids, and granular materials. We envision RealWonder opens new opportunities to apply video models in immersive experiences, AR/VR, and robot learning. Our code and model weights are publicly available in our project website: https://liuwei283.github.io/RealWonder/
title RealWonder: Real-Time Physical Action-Conditioned Video Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
url https://arxiv.org/abs/2603.05449