Data Augmentation using Random Image Cropping for High-resolution Virtual Try-On (VITON-CROP)
This addresses the issue of generating realistic virtual try-on images for users, but it appears incremental as it builds on existing methods with a specific augmentation technique.
The paper tackles the problem of unrealistic synthetic images in virtual try-on, particularly misrepresented necks and garment style changes, by proposing VITON-CROP, which integrates random crop augmentation to achieve more robust synthesis and shows superiority over VITON-HD in experiments.
Image-based virtual try-on provides the capacity to transfer a clothing item onto a photo of a given person, which is usually accomplished by warping the item to a given human pose and adjusting the warped item to the person. However, the results of real-world synthetic images (e.g., selfies) from the previous method is not realistic because of the limitations which result in the neck being misrepresented and significant changes to the style of the garment. To address these challenges, we propose a novel method to solve this unique issue, called VITON-CROP. VITON-CROP synthesizes images more robustly when integrated with random crop augmentation compared to the existing state-of-the-art virtual try-on models. In the experiments, we demonstrate that VITON-CROP is superior to VITON-HD both qualitatively and quantitatively.