VITON-DRR: Details Retention Virtual Try-on via Non-rigid Registration

TL;DR

VITON-DRR introduces a non-rigid registration approach for virtual try-on, significantly improving detail preservation and alignment accuracy in fitting garments onto diverse human poses.

Contribution

The paper presents a novel non-rigid registration method with a dual-pyramid feature extractor and deformation module for enhanced garment detail retention in virtual try-on.

Findings

Outperforms state-of-the-art methods in accuracy.

Better preservation of clothing details.

More realistic fitting results.

Abstract

Image-based virtual try-on aims to fit a target garment to a specific person image and has attracted extensive research attention because of its huge application potential in the e-commerce and fashion industries. To generate high-quality try-on results, accurately warping the clothing item to fit the human body plays a significant role, as slight misalignment may lead to unrealistic artifacts in the fitting image. Most existing methods warp the clothing by feature matching and thin-plate spline (TPS). However, it often fails to preserve clothing details due to self-occlusion, severe misalignment between poses, etc. To address these challenges, this paper proposes a detail retention virtual try-on method via accurate non-rigid registration (VITON-DRR) for diverse human poses. Specifically, we reconstruct a human semantic segmentation using a dual-pyramid-structured feature extractor. Then, a novel Deformation Module is designed for extracting the cloth key points and warping them through an accurate non-rigid registration algorithm. Finally, the Image Synthesis Module is designed to synthesize the deformed garment image and generate the human pose information adaptively. {Compared with} traditional methods, the proposed VITON-DRR can make the deformation of fitting images more accurate and retain more garment details. The experimental results demonstrate that the proposed method performs better than state-of-the-art methods.