首个统一穿衣与脱衣生成的扩散框架，实现双向服装迁移。
Two-Way Garment Transfer: Unified Diffusion Framework for Dressing and Undressing Synthesis
- 通过双向特征解耦，统一处理带掩码穿衣和无掩码脱衣任务。
- 在DressCode和VITON-HD上均达到领先性能，验证框架有效性。
- 适合研究虚拟试衣、服装生成与对称图像合成的学者使用。
尽管虚拟试衣（VTON）近年在将服装迁移到人体上取得了逼真效果，但其逆任务——虚拟脱衣（VTOFF），即从着装人体重建标准服装模板，仍严重缺乏系统研究。现有工作多将二者视为孤立任务：VTON关注穿衣，VTOFF专注取衣，忽视了它们的互补对称性。为此，我们提出首个统一的双向服装迁移模型（TWGTM），通过双向特征解耦，同时解决带掩码的VTON与无掩码的VTOFF问题。框架利用参考图像在潜在空间与像素空间的双重条件引导，无缝衔接两任务；并设计分阶段训练策略，逐步弥合两者间的掩码依赖不对称性。在DressCode与VITON-HD数据集上的大量定性与定量实验验证了方法的有效性与竞争力。
原文摘要 · Abstract (English)
While recent advances in virtual try-on (VTON) have achieved realistic garment transfer to human subjects, its inverse task, virtual try-off (VTOFF), which aims to reconstruct canonical garment templates from dressed humans, remains critically underexplored and lacks systematic investigation. Existing works predominantly treat them as isolated tasks: VTON focuses on garment dressing while VTOFF addresses garment extraction, thereby neglecting their complementary symmetry. To bridge this fundamental gap, we propose the Two-Way Garment Transfer Model (TWGTM), to the best of our knowledge, the first unified framework for joint clothing-centric image synthesis that simultaneously resolves both mask-guided VTON and mask-free VTOFF through bidirectional feature disentanglement. Specifically, our framework employs dual-conditioned guidance from both latent and pixel spaces of reference images to seamlessly bridge the dual tasks. On the other hand, to resolve the inherent mask dependency asymmetry between mask-guided VTON and mask-free VTOFF, we devise a phased training paradigm that progressively bridges this modality gap. Extensive qualitative and quantitative experiments conducted across the DressCode and VITON-HD datasets validate the efficacy and competitive edge of our proposed approach.
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。