FashionMAC: 无变形的时尚图像生成与细粒度模型外观定制
FashionMAC: Deformation-Free Fashion Image Generation with Fine-Grained Model Appearance Customization
AI总结：
FashionMAC通过无变形的扩散框架实现高质量可控的时尚图像生成，采用RADA机制和链式掩码注入策略提升细粒度外观可控性。
摘要：
以服装为中心的时尚图像生成旨在合成真实且可控的人体模型穿着给定服装，由于其在电子商务中的实际应用，这一任务引起了越来越多的关注。该任务的关键挑战在于两个方面：（1）忠实保留服装细节，（2）对模型外观获得细粒度可控性。现有方法通常需要在生成过程中进行服装变形，这往往导致服装纹理扭曲。此外，它们无法控制生成模型的细粒度属性，因为缺乏专门设计的机制。为了解决这些问题，我们提出了FashionMAC，一种新颖的基于扩散的无变形框架，实现了高质量且可控的时尚展示图像生成。我们的框架核心思想是消除在生成过程中进行服装变形的需要，并直接对外画出从穿着者中分割出的服装，这使能够忠实保留复杂的服装细节。此外，我们提出了一种新的区域自适应解耦注意力（RADA）机制以及一个链式掩码注入策略，以实现对合成人体模型的细粒度外观可控性。具体而言，RADA会自适应地为每个细粒度文本属性预测生成区域，并通过链式掩码注入策略强制文本属性聚焦在预测的区域上，显著提高了视觉保真度和可控性。广泛的实验验证了我们的框架相比现有最先进方法的优越性能。
英文摘要：
Garment-centric fashion image generation aims to synthesize realistic and controllable human models dressing a given garment, which has attracted growing interest due to its practical applications in e-commerce. The key challenges of the task lie in two aspects: (1) faithfully preserving the garment details, and (2) gaining fine-grained controllability over the model's appearance. Existing methods typically require performing garment deformation in the generation process, which often leads to garment texture distortions. Also, they fail to control the fine-grained attributes of the generated models, due to the lack of specifically designed mechanisms. To address these issues, we propose FashionMAC, a novel diffusion-based deformation-free framework that achieves high-quality and controllable fashion showcase image generation. The core idea of our framework is to eliminate the need for performing garment deformation and directly outpaint the garment segmented from a dressed person, which enables faithful preservation of the intricate garment details. Moreover, we propose a novel region-adaptive decoupled attention (RADA) mechanism along with a chained mask injection strategy to achieve fine-grained appearance controllability over the synthesized human models. Specifically, RADA adaptively predicts the generated regions for each fine-grained text attribute and enforces the text attribute to focus on the predicted regions by a chained mask injection strategy, significantly enhancing the visual fidelity and the controllability. Extensive experiments validate the superior performance of our framework compared to existing state-of-the-art methods.
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。
