Paper 2605.21572
PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects
- Published
- May 2026
- Research lab
- Independent
- Citations
- 1
- GitHub
- 307 stars
01 In brief
Summary
PhysX-Omni is a unified framework for generating simulation-ready physical 3D assets covering rigid, deformable, and articulated objects.
It introduces a novel template-based run-length encoding (RLE) geometry representation for Vision-Language Models, which directly encodes high-resolution 3D structures without special tokens or segmentation modules, improving generation quality and robustness.
The authors construct PhysXVerse, the first general simulation-ready 3D dataset with over 8.7K assets across 2.9K categories, and PhysX-Bench, a benchmark evaluating six attributes: geometry, absolute scale, material, affordance, kinematics, and description.
Experiments show PhysX-Omni outperforms prior methods on conventional metrics (e.g., on PhysXVerse, PSNR 21.52, CD 2.95, F-score 91.28, kinematic score 0.9185) and on PhysX-Bench, with strong human alignment (Spearman ρ=1.0 for most attributes).
Applications include robotic policy learning and sim-ready scene generation.
The framework is trained on 64 A100 GPUs for 14 days using Qwen2.5-VL-7B-Instruct and TRELLIS decoder.
02 From the paper
Abstract
Simulation-ready physical 3D assets have emerged as a promising direction owing to their broad applicability in downstream tasks. However, most existing 3D generation methods either neglect physical properties or are limited to a single asset category, e.g., rigid, deformable, or articulated objects. To address these limitations, we introduce PhysX-Omni, a unified framework for simulation-ready physical 3D generation across diverse asset types. Specifically, we develop a novel and efficient geometry representation tailored for Vision-Language Models, which directly encodes high-resolution 3D structures without compression, significantly improving generation performance. In addition, we construct the first general simulation-ready 3D dataset, PhysXVerse, covering diverse indoor and outdoor categories. Furthermore, to comprehensively and flexibly evaluate both generative and understanding capabilities in the wild, we propose PhysX-Bench, which encompasses six key attributes: geometry, absolute scale, material, affordance, kinematics, and function description. Extensive experiments with conventional metrics and PhysX-Bench show that PhysX-Omni performs strongly in both generation and understanding. Moreover, additional studies further validate the potential of PhysX-Omni for applications in simulation-ready scene generation and robotic policy learning. We believe PhysX-Omni can significantly advance a wide range of downstream applications, particularly in embodied AI and physics-based simulation.