arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.03757cs.CV
收藏

DiffRetouch:站在专家肩膀上使用扩散模型进行图像润饰

DiffRetouch: Using Diffusion to Retouch on the Shoulder of Experts

Nankai University(南开大学);SenseTime Research(商汤科技研究院);Tsinghua University(清华大学);PBVR

Zheng-Peng Duan, Jiawei zhang, Zheng Lin, Xin Jin, Dongqing Zou, Chunle Guo, Chongyi Li

AI总结:

本文提出基于扩散模型的图像润饰方法DiffRetouch,通过建模专家润饰的复杂分布实现多样风格生成,并引入可调属性、仿射双边网格和对比学习,兼顾用户定制与纹理保真。

摘要:

图像润饰旨在提升照片的视觉质量。考虑到用户不同的审美偏好,润饰的目标具有主观性。然而,当前的润饰方法大多采用确定性模型,这不仅忽视了专家润饰结果中的风格多样性,并且倾向于在训练过程中学习一种平均风格,而且在推理阶段也缺乏样本多样性。本文提出了一种基于扩散模型的方法,命名为DiffRetouch。得益于扩散模型出色的分布建模能力,我们的方法能够捕捉训练数据中覆盖多种视觉愉悦风格的复杂精细润饰分布。此外,四个图像属性被设计为可调节,以提供用户友好的编辑机制。通过在指定范围内调整这些属性,用户可以在学习到的精细润饰分布内定制偏好的风格。另外,引入仿射双边网格和对比学习方案分别处理纹理失真和控制不敏感的问题。大量实验证明了我们的方法在视觉吸引力和样本多样性方面的优越性能。代码将向社区公开。

英文摘要:

Image retouching aims to enhance the visual quality of photos. Considering the different aesthetic preferences of users, the target of retouching is subjective. However, current retouching methods mostly adopt deterministic models, which not only neglects the style diversity in the expert-retouched results and tends to learn an average style during training, but also lacks sample diversity during inference. In this paper, we propose a diffusion-based method, named DiffRetouch. Thanks to the excellent distribution modeling ability of diffusion, our method can capture the complex fine-retouched distribution covering various visual-pleasing styles in the training data. Moreover, four image attributes are made adjustable to provide a user-friendly editing mechanism. By adjusting these attributes in specified ranges, users are allowed to customize preferred styles within the learned fine-retouched distribution. Additionally, the affine bilateral grid and contrastive learning scheme are introduced to handle the problem of texture distortion and control insensitivity respectively. Extensive experiments have demonstrated the superior performance of our method on visually appealing and sample diversity. The code will be made available to the community.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑