HYB-VITON: A Hybrid Approach to Virtual Try-On Combining Explicit and Implicit Warping

TL;DR

HYB-VITON introduces a hybrid virtual try-on system that combines explicit and implicit warping techniques to improve garment detail preservation and realism in virtual fitting images.

Contribution

It presents a novel hybrid approach that integrates explicit and implicit warping, along with a preprocessing pipeline and training options, to enhance virtual try-on quality.

Findings

Preserves garment details more faithfully than diffusion-based methods.

Produces more realistic images than existing explicit warping methods.

Effectively combines advantages of both explicit and implicit warping.

Abstract

Virtual try-on systems have significant potential in e-commerce, allowing customers to visualize garments on themselves. Existing image-based methods fall into two categories: those that directly warp garment-images onto person-images (explicit warping), and those using cross-attention to reconstruct given garments (implicit warping). Explicit warping preserves garment details but often produces unrealistic output, while implicit warping achieves natural reconstruction but struggles with fine details. We propose HYB-VITON, a novel approach that combines the advantages of each method and includes both a preprocessing pipeline for warped garments and a novel training option. These components allow us to utilize beneficial regions of explicitly warped garments while leveraging the natural reconstruction of implicit warping. A series of experiments demonstrates that HYB-VITON preserves garment details more faithfully than recent diffusion-based methods, while producing more realistic results than a state-of-the-art explicit warping method.