PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World
Yunhan Yang, Chunshi Wang, Junliang Ye, YANG LI, Zanxin Chen, Zehuan Huang, Yao Mu, Zhuo Chen
Abstract
Synthesizing physics-grounded 3D assets is a critical bottleneck for interactive virtual worlds and embodied AI. Existing methods predominantly focus on static geometry, overlooking the functional properties essential for interaction. We propose that interactive asset generation must be rooted in functional logic and hierarchical physics. To bridge this gap, we introduce PhysForge, a decoupled two-stage framework supported by PhysDB, a large-scale dataset of 150,000 assets with four-tier physical annotations. First, a VLM acts as a physical architect to plan a Hierarchical Physical Blueprint defining material, functional, and kinematic constraints. Second, a physics-grounded diffusion model realizes this blueprint by synthesizing high-fidelity geometry alongside precise kinematic parameters via a novel KineVoxel Injection (KVI) mechanism. Experiments demonstrate that PhysForge produces functionally plausible, simulation-ready assets, providing a robust data engine for interactive 3D content and embodied agents.
BibTeX
@inproceedings{
yang2026physforge,
title={PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World},
author={Yunhan Yang and Chunshi Wang and Junliang Ye and YANG LI and Zanxin Chen and Zehuan Huang and Yao Mu and Zhuo Chen and Chunchao Guo and Xihui Liu},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=BBIcqAryty}
}