用统一模型实现图像与视频虚拟试衣，兼顾质量与效率。
CatV2TON: Taming Diffusion Transformers for Vision-Based Virtual Try-On with Temporal Concatenation
- 通过时序拼接衣物与人物输入，统一建模图像与视频试衣。
- 在长视频生成中实现稳定时序一致性，资源消耗更低。
- 提出新数据集ViViD-S，提升视频试衣的连续性表现。
虚拟试衣（VTON）技术因有望改变在线零售而受到关注，可实现图像和视频中服装的逼真可视化。然而，现有方法在图像与视频试衣任务中难以同时取得高质量结果，尤其在长视频场景下表现不佳。本文提出CatV2TON，一种基于扩散变换器的简单高效视觉虚拟试衣方法，支持单模型完成图像与视频试衣任务。通过时序拼接衣物与人物输入，并在图像与视频数据混合训练，实现静态与动态场景下的稳健试衣性能。为提升长视频生成效率，提出基于重叠片段的推理策略，结合逐帧引导与自适应片段归一化（AdaCN），在降低资源消耗的同时保持时序一致性。此外，构建了经筛选背向帧并应用3D掩码平滑的改进视频试衣数据集ViViD-S，以增强时间连贯性。大量实验表明，CatV2TON在图像与视频试衣任务中均优于现有方法，提供了一种通用可靠的逼真虚拟试衣解决方案。
原文摘要 · Abstract (English)
Virtual try-on (VTON) technology has gained attention due to its potential to transform online retail by enabling realistic clothing visualization of images and videos. However, most existing methods struggle to achieve high-quality results across image and video try-on tasks, especially in long video scenarios. In this work, we introduce CatV2TON, a simple and effective vision-based virtual try-on (V2TON) method that supports both image and video try-on tasks with a single diffusion transformer model. By temporally concatenating garment and person inputs and training on a mix of image and video datasets, CatV2TON achieves robust try-on performance across static and dynamic settings. For efficient long-video generation, we propose an overlapping clip-based inference strategy that uses sequential frame guidance and Adaptive Clip Normalization (AdaCN) to maintain temporal consistency with reduced resource demands. We also present ViViD-S, a refined video try-on dataset, achieved by filtering back-facing frames and applying 3D mask smoothing for enhanced temporal consistency. Comprehensive experiments demonstrate that CatV2TON outperforms existing methods in both image and video try-on tasks, offering a versatile and reliable solution for realistic virtual try-ons across diverse scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。