arXiv:2511.18775v1 Announce Type: new 
Abstract: Virtual Try-On (VTON) is the task of synthesizing an image of a person wearing a target garment, conditioned on a person image and a garment image. While diffusion-based VTON models featuring a Dual UNet architecture demonstrate superior fidelity compared to single UNet models, they incur substantial computational and memory overhead due to their heavy structure. In this study, through visualization analysis and theoretical analysis, we derived three hypotheses regarding the learning of context features to condition the denoising process. Based on these hypotheses, we developed Re-CatVTON, an efficient single UNet model that achieves high performance. We further enhance the model by introducing a modified classifier-free guidance strategy tailored for VTON's spatial concatenation conditioning, and by directly injecting the ground-truth garment latent derived from the clean garment latent to prevent the accumulation of prediction error. The proposed Re-CatVTON significantly improves performance compared to its predecessor (CatVTON) and requires less computation and memory than the high-performance Dual UNet model, Leffa. Our results demonstrate improved FID, KID, and LPIPS scores, with only a marginal decrease in SSIM, establishing a new efficiency-performance trade-off for single UNet VTON models.

قدمت دراسة جديدة نموذج Re-CatVTON، وهو نموذج UNet أحادي فعال لتجربة الملابس الافتراضية (VTON) الذي يحسن عملية تكييف الملابس مع تقليل الحمل الحاسوبي. يعتمد هذا النموذج على الأفكار المستخلصة من تحليل الميزات السياقية في VTON القائم على الانتشار، الذي كان يعتمد سابقًا على هياكل Dual UNet الأكثر تعقيدًا.

Un nuevo estudio ha presentado Re-CatVTON, un modelo UNet único y eficiente para el ensayo virtual (VTON) que mejora el proceso de acondicionamiento de prendas mientras reduce la carga computacional. Este modelo se basa en los conocimientos obtenidos al analizar características contextuales en VTON basado en difusión, que anteriormente dependía de arquitecturas Dual UNet más complejas.

Une nouvelle étude a introduit Re-CatVTON, un modèle UNet simple et efficace pour l'essayage virtuel (VTON) qui améliore le processus de conditionnement des vêtements tout en réduisant la charge computationnelle. Ce modèle s'appuie sur les connaissances acquises grâce à l'analyse des caractéristiques contextuelles dans le VTON basé sur la diffusion, qui reposait auparavant sur des architectures Dual UNet plus complexes.

A new study has introduced Re-CatVTON, an efficient single UNet model for Virtual Try-On (VTON) that enhances the garment conditioning process while reducing computational overhead. This model builds on the insights gained from analyzing context features in diffusion-based VTON, which previously relied on more complex Dual UNet architectures.

Rethinking Garment Conditioning in Diffusion-based Virtual Try-On

Was this article worth reading? Share it

SwapAnything.io

Uwear

Postugc