Research map / 3D vision / 3D generation
PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image
Ziang Cao, Fangzhou Hong, Zhaoxi Chen, Liang Pan, Ziwei Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add merged-run index tokenization (higher compression) vs raw voxel (ablation) | PhysX-Anything · PhysX-Mobility | PSNR: 16.96 -> 20.35 | Improved |
| add merged-run index tokenization vs raw voxel (ablation) | PhysX-Anything · PhysX-Mobility | F-score: 63.10 -> 77.50 | Improved |
| merge consecutive index ranges beyond plain index serialization (ablation) | PhysX-Anything · PhysX-Mobility | kinematic parameters (VLM): 0.76 -> 0.94 | Improved |
| merge consecutive index ranges beyond plain index serialization (ablation) | PhysX-Anything · PhysX-Mobility | absolute scale error: 0.30 -> 0.30 | No clear effect |
| use VLM-based generation instead of PhysXGen diffusion | PhysXGen · PhysX-Mobility | absolute scale error: 43.44 -> 0.30 | Improved |
| use VLM-based generation instead of PhysXGen diffusion | PhysXGen · PhysX-Mobility | PSNR: 20.33 -> 20.35 | No clear effect |
| use VLM-based generation instead of retrieval (Articulate-Anything) | Articulate-Anything · In-the-wild images | geometry (VLM): 0.61 -> 0.94 | Improved |
| use VLM-based generation instead of PhysXGen | PhysXGen · In-the-wild images | geometry (human rating): 0.61 -> 0.98 | Improved |
Later papers that compared with this method
3 later accepted papers report PhysX-Anything as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- URDF-Anything+: End-to-End Generation for Simulation-Ready Articulated Assets (NeurIPS 2026 · better on 6 of 6 shared results)
- PRISM: Programming Interactive Scenes from Monocular Images for Embodied Simulation (NeurIPS 2026 · better on 1 of 1 shared result)
- AutoPhyX: Automatic Text-Condition Physics Property Generation (ECCV 2026 · better on 1 of 1 shared result)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- PhysX-3D: Physical-Grounded 3D Asset Generation (NeurIPS 2025 · similarity 0.93)
- PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI (CVPR 2024 · similarity 0.88)
- PhysGen3D: Crafting a Miniature Interactive World from a Single Image (CVPR 2025 · similarity 0.87)
- Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model (ICLR 2025 · similarity 0.87)
- URDF-Anything+: End-to-End Generation for Simulation-Ready Articulated Assets (NeurIPS 2026 · similarity 0.87)
- PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation (NeurIPS 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
