Enregistré dans:
Détails bibliographiques
Auteurs principaux: Huo, Dong, Guo, Zixin, Zuo, Xinxin, Shi, Zhihao, Lu, Juwei, Dai, Peng, Xu, Songcen, Cheng, Li, Yang, Yee-Hong
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2408.01291
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929447004798976
author Huo, Dong
Guo, Zixin
Zuo, Xinxin
Shi, Zhihao
Lu, Juwei
Dai, Peng
Xu, Songcen
Cheng, Li
Yang, Yee-Hong
author_facet Huo, Dong
Guo, Zixin
Zuo, Xinxin
Shi, Zhihao
Lu, Juwei
Dai, Peng
Xu, Songcen
Cheng, Li
Yang, Yee-Hong
contents Given a 3D mesh, we aim to synthesize 3D textures that correspond to arbitrary textual descriptions. Current methods for generating and assembling textures from sampled views often result in prominent seams or excessive smoothing. To tackle these issues, we present TexGen, a novel multi-view sampling and resampling framework for texture generation leveraging a pre-trained text-to-image diffusion model. For view consistent sampling, first of all we maintain a texture map in RGB space that is parameterized by the denoising step and updated after each sampling step of the diffusion model to progressively reduce the view discrepancy. An attention-guided multi-view sampling strategy is exploited to broadcast the appearance information across views. To preserve texture details, we develop a noise resampling technique that aids in the estimation of noise, generating inputs for subsequent denoising steps, as directed by the text prompt and current texture map. Through an extensive amount of qualitative and quantitative evaluations, we demonstrate that our proposed method produces significantly better texture quality for diverse 3D objects with a high degree of view consistency and rich appearance details, outperforming current state-of-the-art methods. Furthermore, our proposed texture generation technique can also be applied to texture editing while preserving the original identity. More experimental results are available at https://dong-huo.github.io/TexGen/
format Preprint
id arxiv_https___arxiv_org_abs_2408_01291
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TexGen: Text-Guided 3D Texture Generation with Multi-view Sampling and Resampling
Huo, Dong
Guo, Zixin
Zuo, Xinxin
Shi, Zhihao
Lu, Juwei
Dai, Peng
Xu, Songcen
Cheng, Li
Yang, Yee-Hong
Computer Vision and Pattern Recognition
Given a 3D mesh, we aim to synthesize 3D textures that correspond to arbitrary textual descriptions. Current methods for generating and assembling textures from sampled views often result in prominent seams or excessive smoothing. To tackle these issues, we present TexGen, a novel multi-view sampling and resampling framework for texture generation leveraging a pre-trained text-to-image diffusion model. For view consistent sampling, first of all we maintain a texture map in RGB space that is parameterized by the denoising step and updated after each sampling step of the diffusion model to progressively reduce the view discrepancy. An attention-guided multi-view sampling strategy is exploited to broadcast the appearance information across views. To preserve texture details, we develop a noise resampling technique that aids in the estimation of noise, generating inputs for subsequent denoising steps, as directed by the text prompt and current texture map. Through an extensive amount of qualitative and quantitative evaluations, we demonstrate that our proposed method produces significantly better texture quality for diverse 3D objects with a high degree of view consistency and rich appearance details, outperforming current state-of-the-art methods. Furthermore, our proposed texture generation technique can also be applied to texture editing while preserving the original identity. More experimental results are available at https://dong-huo.github.io/TexGen/
title TexGen: Text-Guided 3D Texture Generation with Multi-view Sampling and Resampling
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.01291