AnyDressing：基于潜在扩散模型的可定制多服装虚拟换装
AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models
AI总结：
本文提出 AnyDressing，通过 GarmentsNet、DressingNet 及服装特征提取、定位与纹理学习机制，实现任意服装组合和文本条件下的高一致性多服装虚拟换装。
摘要：
近来，基于扩散模型、由文本和图像提示生成以服装为中心的图像取得了令人瞩目的进展。然而，现有方法缺乏对多种服饰组合的支持，并且在保持服装细节的同时难以维持对文本提示的忠实性，从而限制了其在多样场景中的性能。本文聚焦于一项新任务，即多服装虚拟换装，并提出一种新颖的 AnyDressing 方法，用于在任意服装组合和任意个性化文本提示的条件下定制人物。AnyDressing 包含两个主要网络，分别名为 GarmentsNet 和 DressingNet，它们分别致力于提取细致的服装特征并生成定制图像。具体而言，我们在 GarmentsNet 中提出了一个高效且可扩展的模块，称为 Garment-Specific Feature Extractor（服装专属特征提取器），用于并行地单独编码服装纹理。该设计避免了服装混淆，同时保证了网络效率。同时，我们在 DressingNet 中设计了自适应的 Dressing-Attention（换装注意力）机制和新颖的 Instance-Level Garment Localization Learning（实例级服装定位学习）策略，以将多服装特征准确注入其对应区域。该方法有效地将多服装纹理线索整合到生成图像中，并进一步增强了文本-图像一致性。此外，我们引入 Garment-Enhanced Texture Learning（服装增强纹理学习）策略，以改善服装的细粒度纹理细节。得益于精心设计，AnyDressing 可作为插件模块，轻松与扩散模型的任意社区控制扩展集成，提升合成图像的多样性和可控性。大量实验表明，AnyDressing 取得了最先进的结果。
英文摘要：
Recent advances in garment-centric image generation from text and image prompts based on diffusion models are impressive. However, existing methods lack support for various combinations of attire, and struggle to preserve the garment details while maintaining faithfulness to the text prompts, limiting their performance across diverse scenarios. In this paper, we focus on a new task, i.e., Multi-Garment Virtual Dressing, and we propose a novel AnyDressing method for customizing characters conditioned on any combination of garments and any personalized text prompts. AnyDressing comprises two primary networks named GarmentsNet and DressingNet, which are respectively dedicated to extracting detailed clothing features and generating customized images. Specifically, we propose an efficient and scalable module called Garment-Specific Feature Extractor in GarmentsNet to individually encode garment textures in parallel. This design prevents garment confusion while ensuring network efficiency. Meanwhile, we design an adaptive Dressing-Attention mechanism and a novel Instance-Level Garment Localization Learning strategy in DressingNet to accurately inject multi-garment features into their corresponding regions. This approach efficiently integrates multi-garment texture cues into generated images and further enhances text-image consistency. Additionally, we introduce a Garment-Enhanced Texture Learning strategy to improve the fine-grained texture details of garments. Thanks to our well-craft design, AnyDressing can serve as a plug-in module to easily integrate with any community control extensions for diffusion models, improving the diversity and controllability of synthesized images. Extensive experiments show that AnyDressing achieves state-of-the-art results.
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。
