GenesisTex: Adapting Image Denoising Diffusion to Texture Space

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Chenjian, Jiang, Boyan, Li, Xinghui, Zhang, Yingpeng, Yu, Qian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917622727049216
author Gao, Chenjian
Jiang, Boyan
Li, Xinghui
Zhang, Yingpeng
Yu, Qian
author_facet Gao, Chenjian
Jiang, Boyan
Li, Xinghui
Zhang, Yingpeng
Yu, Qian
contents We present GenesisTex, a novel method for synthesizing textures for 3D geometries from text descriptions. GenesisTex adapts the pretrained image diffusion model to texture space by texture space sampling. Specifically, we maintain a latent texture map for each viewpoint, which is updated with predicted noise on the rendering of the corresponding viewpoint. The sampled latent texture maps are then decoded into a final texture map. During the sampling process, we focus on both global and local consistency across multiple viewpoints: global consistency is achieved through the integration of style consistency mechanisms within the noise prediction network, and low-level consistency is achieved by dynamically aligning latent textures. Finally, we apply reference-based inpainting and img2img on denser views for texture refinement. Our approach overcomes the limitations of slow optimization in distillation-based methods and instability in inpainting-based methods. Experiments on meshes from various sources demonstrate that our method surpasses the baseline methods quantitatively and qualitatively.
format Preprint
id arxiv_https___arxiv_org_abs_2403_17782
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GenesisTex: Adapting Image Denoising Diffusion to Texture Space
Gao, Chenjian
Jiang, Boyan
Li, Xinghui
Zhang, Yingpeng
Yu, Qian
Computer Vision and Pattern Recognition
Graphics
We present GenesisTex, a novel method for synthesizing textures for 3D geometries from text descriptions. GenesisTex adapts the pretrained image diffusion model to texture space by texture space sampling. Specifically, we maintain a latent texture map for each viewpoint, which is updated with predicted noise on the rendering of the corresponding viewpoint. The sampled latent texture maps are then decoded into a final texture map. During the sampling process, we focus on both global and local consistency across multiple viewpoints: global consistency is achieved through the integration of style consistency mechanisms within the noise prediction network, and low-level consistency is achieved by dynamically aligning latent textures. Finally, we apply reference-based inpainting and img2img on denser views for texture refinement. Our approach overcomes the limitations of slow optimization in distillation-based methods and instability in inpainting-based methods. Experiments on meshes from various sources demonstrate that our method surpasses the baseline methods quantitatively and qualitatively.
title GenesisTex: Adapting Image Denoising Diffusion to Texture Space
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2403.17782