PhysiOpt: Physics-Driven Shape Optimization for 3D Generative Models
Name
3757377.3763884.pdf
Size
142.42 MB
Format
Adobe PDF
Checksum (MD5)
cbc2a0efa71a26d3ceeceba5a2b9ae94
Author(s)
Zhan, Xiao
Jambon, Cl?ment
Thompson, Evan
Ng, Kenney
Konakovi? Lukovi?, Mina
Date Issued
December 14, 2025
Publisher
ACM|SIGGRAPH Asia 2025 Conference Papers
Citation
Xiao Zhan, Clément Jambon, Evan Thompson, Kenney Ng, and Mina Konaković Luković. 2025. PhysiOpt: Physics-Driven Shape Optimization for 3D Generative Models. In Proceedings of the SIGGRAPH Asia 2025 Conference Papers (SA Conference Papers '25). Association for Computing Machinery, New York, NY, USA, Article 109, 1–11.
Version
Final published version
Abstract
Generative models have recently demonstrated impressive capabilities in producing high-quality 3D shapes from a variety of user inputs (e.g., text or images). However, generated objects often lack physical integrity. We introduce PhysiOpt, a differentiable physics optimizer designed to improve the physical behavior of 3D generative outputs, enabling them to transition from virtual designs to physically plausible, real-world objects. While most generative models represent geometry as continuous implicit fields, physics-based approaches often rely on the finite element method (FEM), requiring ad hoc mesh extraction to perform shape optimization. In addition, these methods are typically slow, limiting their integration in fast, iterative generative design workflows. Instead, we bridge the representation gap and propose a fast and effective differentiable simulation pipeline that optimizes shapes directly in the latent space of generative models using an intuitive and easy-to-implement differentiable mapping. This approach enables fast optimization while preserving semantic structure, unlike traditional methods relying on local mesh-based adjustments. We demonstrate the versatility of our optimizer across a range of shape priors, from global and part-based latent models to a state-of-the-art large-scale 3D generator, and compare it to a traditional mesh-based shape optimizer. Our method preserves the native representation and capabilities of the underlying generative model while supporting user-specified materials, loads, and boundary conditions. The resulting designs exhibit improved physical behavior, remain faithful to the learned priors, and are suitable for fabrication. We demonstrate the effectiveness of our approach on both virtual and fabricated objects.
Description
SA Conference Papers ’25, Hong Kong, Hong Kong
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
MIT-IBM Watson AI Lab
MIT-IBM Watson AI Lab
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3757377.3763884
