HYB-VITON: A Hybrid Approach to Virtual Try-On Combining Explicit and Implicit Warping
This addresses a key challenge in e-commerce for customers and retailers by improving visualization accuracy, though it is incremental as it builds on existing warping techniques.
The paper tackles the problem of virtual try-on by proposing HYB-VITON, a hybrid approach that combines explicit and implicit warping to preserve garment details and produce realistic results, outperforming recent diffusion-based and explicit warping methods in experiments.
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.