# Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation

**Authors:** Rui Chen, Yongwei Chen, Ningxin Jiao, Kui Jia  
**arXiv:** [2303.13873](https://arxiv.org/abs/2303.13873)  
**Date:** 2023-03-24  
**Summary page:** https://www.summarizepaper.com/en/paper/2303.13873v3/

## Key points

- Fantasia3D is a cutting-edge method for high-quality text-to-3D content creation
- Existing methods in automatic 3D content generation often fall short in capturing finer geometries and achieving photorealistic rendering
- Fantasia3D addresses this issue by disentangling the modeling and learning of geometry and appearance
- The method relies on a hybrid scene representation for geometry learning and incorporates spatially varying BRDF for appearance modeling
- This disentangled framework enhances compatibility with popular graphics engines, enabling functionalities such as relighting, editing, and physical simulation
- Fantasia3D has demonstrated superiority over existing methods across various text-to-3D task settings
- Accepted at ICCV 2023, this innovative approach opens up new possibilities in high-quality 3D content creation

## Summary

Fantasia3D is a cutting-edge method for high-quality text-to-3D content creation. Proposed by authors Rui Chen, Yongwei Chen, Ningxin Jiao, and Kui Jia, this innovative approach sets itself apart from existing methods in the realm of automatic 3D content generation. Recent advancements in this field have been fueled by the availability of pre-trained large language models and image diffusion models. This has led to the emergence of text-to-3D content creation as a prominent research topic. However, existing methods often utilize implicit scene representations that link geometry and appearance through volume rendering. While effective to some extent, these approaches fall short in capturing finer geometries and achieving photorealistic rendering. This limits their ability to generate top-notch 3D assets. Fantasia3D addresses this issue by introducing a novel approach that focuses on disentangling the modeling and learning of geometry and appearance. For geometry learning, the method relies on a hybrid scene representation and introduces the encoding of surface normals extracted from this representation as input for the image diffusion model. On the other hand, for appearance modeling, Fantasia3D incorporates spatially varying bidirectional reflectance distribution function (BRDF) into the text-to-3D task. By learning surface materials for photorealistic rendering of generated surfaces, this disentangled framework enhances compatibility with popular graphics engines while enabling functionalities such as relighting, editing, and physical simulation of the resulting 3D assets. The efficacy of Fantasia3D is demonstrated through comprehensive experiments showcasing its superiority over existing methods across various text-to-3D task settings. Accepted at ICCV 2023, this innovative approach opens up new possibilities in high-quality 3D content creation by bridging the gap between geometry and appearance modeling. For more information about Fantasia3D and access to source codes, interested individuals can visit the project page at https://fantasia3d.github.io/.