PhysGen3D: Crafting a Miniature Interactive World from a Single Image
Boyuan Chen, Hanxiao Jiang, Shaowei Liu, Saurabh Gupta, Yunzhu Li, Hao Zhao, Shenlong Wang
Abstract
Figure 1. PhysGen3D generates realistic, physically plausible motion from a single image and a text prompt by reasoning about geometry, semantics, and material properties. (a) An apple rolls under the influence of its initial velocity, friction, and shape, producing a natural progression over time. (b) Three animal figures interact dynamically, colliding after being propelled upwards and forwards. (c) A toy potato bounces back with soft-body dynamics in response to an initial downward force, capturing material-specific behaviors. PhysGen3D lets users quickly explore physics-driven object interactions and behaviors in a compact virtual scene generated from a single input image.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext f739edc6-adfd-45fb-b1a8-03a2ea899071Cited by top-tier papers18
- PointWorld: Scaling 3D World Models for In-The-Wild Robotic ManipulationWenlong Huang, Yu-Wei Chao, Arsalan Mousavian, Ming-Yu Liu et al.CVPR 2026 · 87 citations
- Force Prompting: Video Generation Models Can Learn And Generalize Physics-based Control SignalsNate Gillman, Charles Herrmann, Michael Freeman, Daksh Aggarwal et al.NeurIPS 2025 · 61 citations
- PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video GenerationChen Wang, Chuhao Chen, Yiming Huang, Zhiyang Dou et al.NeurIPS 2025 · 50 citations
- NewtonGen: Physics-consistent and Controllable Text-to-Video Generation via Neural Newtonian DynamicsYu Yuan, Xijun Wang, Tharindu Wickremasinghe, Zeeshan Nadir et al.ICLR 2026 · 46 citations
- PhysX-Anything: Simulation-Ready Physical 3D Assets from Single ImageZiang Cao, Fangzhou Hong, Zhaoxi Chen, Liang Pan et al.CVPR 2026 · 36 citations
Builds on37
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Scalable Diffusion Models with TransformersWilliam Peebles, Saining XieICCV 2023 · 5,568 citations
- AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific TuningYuwei Guo, Ceyuan Yang, Anyi Rao, Zhengyang Liang et al.ICLR 2024 · 1,493 citations
- Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video GeneratorsLevon Khachatryan, Andranik Movsisyan, Vahram Tadevosyan, Roberto Henschel et al.ICCV 2023 · 800 citations
Related papers
- Wonderplay: Dynamic 3D Scene Generation From a Single Image and ActionsZizhang Li, Hong-Xing Yu, Wei Liu, Yin Yang et al.ICCV 2025 · 10 citations
- OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics GenerationYuchen Lin, Chenguo Lin, Jianjin Xu, Yadong MuICLR 2025
- PAT3D: Physics-Augmented Text-to-3D Scene GenerationGuying Lin, Kemeng Huang, Michael Liu, Ruihan Gao et al.ICLR 2026 · 14 citations
- PhysSplat: Efficient Physics Simulation for 3D Scenes via MLLM-Guided Gaussian SplattingHaoyu Zhao, Hao Wang, Xingyue Zhao, Hao Fei et al.ICCV 2025 · 5 citations
- Phys4DGen: Physics-Compliant 4D Generation with Multi-Material Composition PerceptionJiajing Lin, Zhenzhong Wang, Dejun Xu, Shu Jiang et al.ACM MM 2025 · 2 citations
