Robust Cloth Warping via Multi-Scale Patch Adversarial Loss for Virtual Try-On Framework

With the rapid growth of online commerce, image-based virtual try-on systems for fitting new in-shop garments onto a person image presents an exciting opportunity to deliver interactive customer experience. Current state-of-the-art methods achieve this in a two-stage pipeline, where the first stage transforms the in-shop cloth into fitting the body shape of the target person and the second stage employs an image composition module to seamlessly integrate the transformed in-shop cloth onto the target person image. In the present work, we introduce a multi-scale patch adversarial loss for training the warping module of a state-of-the-art virtual try-on network. We show that the proposed loss produces robust transformation of clothes to fit the body shape while preserving texture details, which in turn improves image composition in the second stage. We perform extensive evaluations of the proposed loss on the try-on performance and show significant performance improvement over the existing state-of-the-art method.