{"ID":2836652,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.21978","arxiv_id":"2511.21978","title":"PAT3D: Physics-Augmented Text-to-3D Scene Generation","abstract":"We introduce PAT3D, the first physics-augmented text-to-3D scene generation framework that integrates vision-language models with physics-based simulation to produce physically plausible, simulation-ready, and intersection-free 3D scenes. Given a text prompt, PAT3D generates 3D objects, infers their spatial relations, and organizes them into a hierarchical scene tree, which is then converted into initial conditions for simulation. A differentiable rigid-body simulator ensures realistic object interactions under gravity, driving the scene toward static equilibrium without interpenetrations. To further enhance scene quality, we introduce a simulation-in-the-loop optimization procedure that guarantees physical stability and non-intersection, while improving semantic consistency with the input prompt. Experiments demonstrate that PAT3D substantially outperforms prior approaches in physical plausibility, semantic consistency, and visual quality. Beyond high-quality generation, PAT3D uniquely enables simulation-ready 3D scenes for downstream tasks such as scene editing and robotic manipulation. Code and data are available at: https://github.com/Simulation-Intelligence/PAT3D.","short_abstract":"We introduce PAT3D, the first physics-augmented text-to-3D scene generation framework that integrates vision-language models with physics-based simulation to produce physically plausible, simulation-ready, and intersection-free 3D scenes. Given a text prompt, PAT3D generates 3D objects, infers their spatial relations,...","url_abs":"https://arxiv.org/abs/2511.21978","url_pdf":"https://arxiv.org/pdf/2511.21978v2","authors":"[\"Guying Lin\",\"Kemeng Huang\",\"Michael Liu\",\"Ruihan Gao\",\"Hanke Chen\",\"Lyuhao Chen\",\"Beijia Lu\",\"Taku Komura\",\"Yuan Liu\",\"Jun-Yan Zhu\",\"Minchen Li\"]","published":"2025-11-26T23:23:58Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\",\"Generative Adversarial Network\"]","has_code":false,"code_links":[{"ID":606619,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2836652,"paper_url":"https://arxiv.org/abs/2511.21978","paper_title":"PAT3D: Physics-Augmented Text-to-3D Scene Generation","repo_url":"https://github.com/Simulation-Intelligence/PAT3D","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}