BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training
This work addresses virtual try-on for e-commerce and fashion applications by introducing a novel training paradigm that improves performance in complex, real-world settings, though it is incremental as it builds on existing diffusion models.
The paper tackles the problem of image-based virtual try-on by proposing a mask-free approach to avoid spatial information loss and artifacts in in-the-wild scenarios, resulting in state-of-the-art try-on quality without parsing costs as demonstrated through extensive experiments.
Image-based virtual try-on is an increasingly popular and important task to generate realistic try-on images of the specific person. Recent methods model virtual try-on as image mask-inpaint task, which requires masking the person image and results in significant loss of spatial information. Especially, for in-the-wild try-on scenarios with complex poses and occlusions, mask-based methods often introduce noticeable artifacts. Our research found that a mask-free approach can fully leverage spatial and lighting information from the original person image, enabling high-quality virtual try-on. Consequently, we propose a novel training paradigm for a mask-free try-on diffusion model. We ensure the model's mask-free try-on capability by creating high-quality pseudo-data and further enhance its handling of complex spatial information through effective in-the-wild data augmentation. Besides, a try-on localization loss is designed to concentrate on try-on area while suppressing garment features in non-try-on areas, ensuring precise rendering of garments and preservation of fore/back-ground. In the end, we introduce BooW-VTON, the mask-free virtual try-on diffusion model, which delivers SOTA try-on quality without parsing cost. Extensive qualitative and quantitative experiments have demonstrated superior performance in wild scenarios with such a low-demand input.