VALSE 论文速览 第209期：将图像去噪扩散模型应用于纹理空间

论文题目：

GenesisTex: Adapting Image Denoising Diffusion to Texture Space

作者列表：

高宸健 (北京航空航天大学)，姜柏言 (腾讯)，李星辉 (腾讯)，张颖鹏 (腾讯)，于茜 (北京航空航天大学)

B站观看网址：

https://www.bilibili.com/video/BV1FrKweLEvH/

复制链接到浏览器打开或点击阅读原文即可跳转至观看页面。

论文摘要：

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.

参考文献：

[1] Gao, Chenjian, et al. "GenesisTex: Adapting Image Denoising Diffusion to Texture Space." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024.

论文链接：

[https://openaccess.thecvf.com/content/CVPR2024/papers/Gao_GenesisTex_Adapting_Image_Denoising_Diffusion_to_Texture_Space_CVPR_2024_paper.pdf]

视频讲者简介：

Chenjian Gao received his B.S. degree from the School of Software, Beihang University, Beijing, China in 2021. He is currently pursuing a Master's degree at Beihang University. His current research interests include 3D reconstruction and generative models.

个人主页：

https://cjeen.github.io

特别鸣谢本次论文速览主要组织者：

月度轮值AC：高广谓 (南京邮电大学)