TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models
Preprint
Abstract
We present TexFusion (Texture Diffusion), a new method to synthesize textures for given 3D geometries, using large-scale text-guided image diffusion models. In contrast to recent works that leverage 2D text-to-image diffusion models to distill 3D objects using a slow and fragile optimization process, TexFusion introduces a new 3D-consistent generation technique specifically designed for texture synthesis that employs regular diffusion model sampling on different 2D rendered views. Specifically, we leverage latent diffusion models, apply the diffusion model's denoiser on a set of 2D renders of the 3D object, and aggregate the different denoising predictions on a shared latent texture map. Final output RGB textures are produced by optimizing an intermediate neural color field on the decodings of 2D renders of the latent texture. We thoroughly validate TexFusion and show that we can efficiently generate diverse, high quality and globally coherent textures. We achieve state-of-the-art text-guided texture synthesis performance using only image diffusion models, while avoiding the pitfalls of previous distillation-based methods. The text-conditioning offers detailed control and we also do not rely on any ground truth 3D textures for training. This makes our method versatile and applicable to a broad range of geometry and texture types. We hope that TexFusion will advance AI-based texturing of 3D assets for applications in virtual reality, game design, simulation, and more.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- TetraDiffusion: Tetrahedral Diffusion Models for 3D Shape Generation2024
- Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation2023
- Magic3D: High-Resolution Text-to-3D Content Creation2023
- RODIN: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion2023
- 3D Neural Field Generation Using Triplane Diffusion2023
- RePaint: Inpainting using Denoising Diffusion Probabilistic Models2022
- Zero-Shot Text-Guided Object Generation with Dream Fields2022
- CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation2022
- SRDiff: Single image super-resolution with diffusion probabilistic modelsNeurocomputing, 2022
- Discrete Point Flow Networks for Efficient Point Cloud Generation2020