IMAGDressing-v1：可定制虚拟换装
IMAGDressing-v1: Customizable Virtual Dressing
AI总结：
本文提出可定制虚拟换装框架IMAGDressing-v1，通过服装UNet与混合注意力融合语义、纹理及文本控制，并发布IGPair数据集和CAMI指标，实现多条件可控的SOTA人物图像合成。
摘要：
最新进展通过使用潜在扩散模型进行局部服装修复，实现了逼真的虚拟试穿（VTON），显著提升了消费者的在线购物体验。然而，现有VTON技术忽视了商家全面展示服装的需求，包括对服装以及可选面部、姿势和场景的灵活控制。为解决这一问题，我们定义了一项虚拟换装（VD）任务，重点是在固定服装和可选条件下生成可自由编辑的人物图像。同时，我们设计了综合亲和度指标指数（CAMI），用于评估生成图像与参考服装之间的一致性。随后，我们提出IMAGDressing-v1，该模型包含一个服装UNet，用于捕获来自CLIP的语义特征和来自VAE的纹理特征。我们提出一种混合注意力模块，包括冻结的自注意力和可训练的交叉注意力，以将来自服装UNet的服装特征整合到冻结的去噪UNet中，确保用户能够通过文本控制不同场景。IMAGDressing-v1可与ControlNet和IP-Adapter等其他扩展插件结合，以增强生成图像的多样性和可控性。此外，为解决数据匮乏问题，我们发布了交互式服装配对（IGPair）数据集，其中包含超过300,000对服装与着装图像，并建立了标准的数据组装流程。大量实验表明，我们的IMAGDressing-v1在各种受控条件下取得了最先进的人物图像合成性能。代码和模型将在https://github.com/muzishen/IMAGDressing提供。
英文摘要：
Latest advances have achieved realistic virtual try-on (VTON) through localized garment inpainting using latent diffusion models, significantly enhancing consumers' online shopping experience. However, existing VTON technologies neglect the need for merchants to showcase garments comprehensively, including flexible control over garments, optional faces, poses, and scenes. To address this issue, we define a virtual dressing (VD) task focused on generating freely editable human images with fixed garments and optional conditions. Meanwhile, we design a comprehensive affinity metric index (CAMI) to evaluate the consistency between generated images and reference garments. Then, we propose IMAGDressing-v1, which incorporates a garment UNet that captures semantic features from CLIP and texture features from VAE. We present a hybrid attention module, including a frozen self-attention and a trainable cross-attention, to integrate garment features from the garment UNet into a frozen denoising UNet, ensuring users can control different scenes through text. IMAGDressing-v1 can be combined with other extension plugins, such as ControlNet and IP-Adapter, to enhance the diversity and controllability of generated images. Furthermore, to address the lack of data, we release the interactive garment pairing (IGPair) dataset, containing over 300,000 pairs of clothing and dressed images, and establish a standard pipeline for data assembly. Extensive experiments demonstrate that our IMAGDressing-v1 achieves state-of-the-art human image synthesis performance under various controlled conditions. The code and model will be available at https://github.com/muzishen/IMAGDressing.
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。
