PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Yunhan, Wang, Chunshi, Ye, Junliang, Li, Yang, Chen, Zanxin, Huang, Zehuan, Mu, Yao, Chen, Zhuo, Guo, Chunchao, Liu, Xihui
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911653099995136
author Yang, Yunhan
Wang, Chunshi
Ye, Junliang
Li, Yang
Chen, Zanxin
Huang, Zehuan
Mu, Yao
Chen, Zhuo
Guo, Chunchao
Liu, Xihui
author_facet Yang, Yunhan
Wang, Chunshi
Ye, Junliang
Li, Yang
Chen, Zanxin
Huang, Zehuan
Mu, Yao
Chen, Zhuo
Guo, Chunchao
Liu, Xihui
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_05163
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World
Yang, Yunhan
Wang, Chunshi
Ye, Junliang
Li, Yang
Chen, Zanxin
Huang, Zehuan
Mu, Yao
Chen, Zhuo
Guo, Chunchao
Liu, Xihui
Computer Vision and Pattern Recognition
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.
title PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.05163