AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homes

arXiv:2312.06644v2 Announce Type: replace
Abstract: Inspired by cognitive theories, we introduce AnyHome, a framework that translates any text into well-structured and textured indoor scenes at a house-scale. By prompting Large Language Models (LLMs) with designed templates, our approach converts provided textual narratives into amodal structured representations. These representations guarantee consistent and realistic spatial layouts by directing the synthesis of a geometry mesh within defined constraints. A Score Distillation Sampling process is then employed to refine the geometry, followed by an …

abstract arxiv cognitive consistent cs.ai cs.cv cs.gr framework homes language language models large language large language models llms prompting scale text textual type