Text-to-3D Gaussian Splatting with Physics-Grounded Motion Generation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Wenqing, Fu, Yun
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912147790888960
author Wang, Wenqing
Fu, Yun
author_facet Wang, Wenqing
Fu, Yun
contents Text-to-3D generation is a valuable technology in virtual reality and digital content creation. While recent works have pushed the boundaries of text-to-3D generation, producing high-fidelity 3D objects with inefficient prompts and simulating their physics-grounded motion accurately still remain unsolved challenges. To address these challenges, we present an innovative framework that utilizes the Large Language Model (LLM)-refined prompts and diffusion priors-guided Gaussian Splatting (GS) for generating 3D models with accurate appearances and geometric structures. We also incorporate a continuum mechanics-based deformation map and color regularization to synthesize vivid physics-grounded motion for the generated 3D Gaussians, adhering to the conservation of mass and momentum. By integrating text-to-3D generation with physics-grounded motion synthesis, our framework renders photo-realistic 3D objects that exhibit physics-aware motion, accurately reflecting the behaviors of the objects under various forces and constraints across different materials. Extensive experiments demonstrate that our approach achieves high-quality 3D generations with realistic physics-grounded motion.
format Preprint
id arxiv_https___arxiv_org_abs_2412_05560
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Text-to-3D Gaussian Splatting with Physics-Grounded Motion Generation
Wang, Wenqing
Fu, Yun
Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Machine Learning
Image and Video Processing
Text-to-3D generation is a valuable technology in virtual reality and digital content creation. While recent works have pushed the boundaries of text-to-3D generation, producing high-fidelity 3D objects with inefficient prompts and simulating their physics-grounded motion accurately still remain unsolved challenges. To address these challenges, we present an innovative framework that utilizes the Large Language Model (LLM)-refined prompts and diffusion priors-guided Gaussian Splatting (GS) for generating 3D models with accurate appearances and geometric structures. We also incorporate a continuum mechanics-based deformation map and color regularization to synthesize vivid physics-grounded motion for the generated 3D Gaussians, adhering to the conservation of mass and momentum. By integrating text-to-3D generation with physics-grounded motion synthesis, our framework renders photo-realistic 3D objects that exhibit physics-aware motion, accurately reflecting the behaviors of the objects under various forces and constraints across different materials. Extensive experiments demonstrate that our approach achieves high-quality 3D generations with realistic physics-grounded motion.
title Text-to-3D Gaussian Splatting with Physics-Grounded Motion Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2412.05560