基于条件扩散模型的时尚度增强穿搭图像编辑
Fashionability-Enhancing Outfit Image Editing with Conditional Diffusion Models
AI总结：
本文提出一种基于条件扩散模型的方法，通过时尚度增强、身体特征保留和自动时尚优化，在无需外部提示下生成更时尚的穿搭图像，实验证明其优于基线Fashion++。
摘要：
时尚领域的图像生成主要集中在保留身体特征或遵循输入提示上，但很少关注提升输出图像的内在时尚度。本文提出了一种基于扩散模型的新方法，在保持对关键属性控制的同时，生成具有更高时尚度的时尚图像。该方法的核心组件包括：1）时尚度增强，确保生成的图像比输入图像更时尚；2）身体特征保留，促使生成图像维持输入的原始形状和比例；3）自动时尚优化，不依赖手动输入或外部提示。我们还采用了两种方法来收集训练数据，以在生成和评估图像时提供指导。具体而言，我们使用时尚度分数对穿搭图像进行评分，这些分数由多位时尚专家通过基于OpenSkill和五个关键方面的成对比较进行标注。这些方法为评估和提升生成图像的时尚度提供了互补的视角。实验结果表明，我们的方法在生成具有卓越时尚度的图像方面优于基线模型Fashion++，证明了其在生成更时尚、更具吸引力的时尚图像方面的有效性。
英文摘要：
Image generation in the fashion domain has predominantly focused on preserving body characteristics or following input prompts, but little attention has been paid to improving the inherent fashionability of the output images. This paper presents a novel diffusion model-based approach that generates fashion images with improved fashionability while maintaining control over key attributes. Key components of our method include: 1) fashionability enhancement, which ensures that the generated images are more fashionable than the input; 2) preservation of body characteristics, encouraging the generated images to maintain the original shape and proportions of the input; and 3) automatic fashion optimization, which does not rely on manual input or external prompts. We also employ two methods to collect training data for guidance while generating and evaluating the images. In particular, we rate outfit images using fashionability scores annotated by multiple fashion experts through OpenSkill-based and five critical aspect-based pairwise comparisons. These methods provide complementary perspectives for assessing and improving the fashionability of the generated images. The experimental results show that our approach outperforms the baseline Fashion++ in generating images with superior fashionability, demonstrating its effectiveness in producing more stylish and appealing fashion images.
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。
