Masked Extended Attention for Zero-Shot Virtual Try-On In The Wild
This addresses the need for more generalizable and computationally efficient virtual try-on solutions for e-commerce and fashion applications, representing a novel approach rather than an incremental improvement.
The paper tackles the problem of virtual try-on by introducing a zero-shot, training-free method that uses a diffusion model with extended attention and masking to inpaint clothing garments from reference images, achieving superior image quality and garment preservation compared to state-of-the-art approaches.
Virtual Try-On (VTON) is a highly active line of research, with increasing demand. It aims to replace a piece of garment in an image with one from another, while preserving person and garment characteristics as well as image fidelity. Current literature takes a supervised approach for the task, impairing generalization and imposing heavy computation. In this paper, we present a novel zero-shot training-free method for inpainting a clothing garment by reference. Our approach employs the prior of a diffusion model with no additional training, fully leveraging its native generalization capabilities. The method employs extended attention to transfer image information from reference to target images, overcoming two significant challenges. We first initially warp the reference garment over the target human using deep features, alleviating "texture sticking". We then leverage the extended attention mechanism with careful masking, eliminating leakage of reference background and unwanted influence. Through a user study, qualitative, and quantitative comparison to state-of-the-art approaches, we demonstrate superior image quality and garment preservation compared unseen clothing pieces or human figures.