Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xu, Qingshan, Liu, Jiao, Wong, Melvin, Chen, Caishun, Ong, Yew-Soon
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2403.12438
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914719715033088
author Xu, Qingshan
Liu, Jiao
Wong, Melvin
Chen, Caishun
Ong, Yew-Soon
author_facet Xu, Qingshan
Liu, Jiao
Wong, Melvin
Chen, Caishun
Ong, Yew-Soon
contents Text-to-3D generation has shown great promise in generating novel 3D content based on given text prompts. However, existing generative methods mostly focus on geometric or visual plausibility while ignoring precise physics perception for the generated 3D shapes. This greatly hinders the practicality of generated 3D shapes in real-world applications. In this work, we propose Phy3DGen, a precise-physics-driven text-to-3D generation method. By analyzing the solid mechanics of generated 3D shapes, we reveal that the 3D shapes generated by existing text-to-3D generation methods are impractical for real-world applications as the generated 3D shapes do not conform to the laws of physics. To this end, we leverage 3D diffusion models to provide 3D shape priors and design a data-driven differentiable physics layer to optimize 3D shape priors with solid mechanics. This allows us to optimize geometry efficiently and learn precise physics information about 3D shapes at the same time. Experimental results demonstrate that our method can consider both geometric plausibility and precise physics perception, further bridging 3D virtual modeling and precise physical worlds.
format Preprint
id arxiv_https___arxiv_org_abs_2403_12438
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Precise-Physics Driven Text-to-3D Generation
Xu, Qingshan
Liu, Jiao
Wong, Melvin
Chen, Caishun
Ong, Yew-Soon
Computer Vision and Pattern Recognition
Text-to-3D generation has shown great promise in generating novel 3D content based on given text prompts. However, existing generative methods mostly focus on geometric or visual plausibility while ignoring precise physics perception for the generated 3D shapes. This greatly hinders the practicality of generated 3D shapes in real-world applications. In this work, we propose Phy3DGen, a precise-physics-driven text-to-3D generation method. By analyzing the solid mechanics of generated 3D shapes, we reveal that the 3D shapes generated by existing text-to-3D generation methods are impractical for real-world applications as the generated 3D shapes do not conform to the laws of physics. To this end, we leverage 3D diffusion models to provide 3D shape priors and design a data-driven differentiable physics layer to optimize 3D shape priors with solid mechanics. This allows us to optimize geometry efficiently and learn precise physics information about 3D shapes at the same time. Experimental results demonstrate that our method can consider both geometric plausibility and precise physics perception, further bridging 3D virtual modeling and precise physical worlds.
title Precise-Physics Driven Text-to-3D Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.12438