End-to-End Learning of Geometric Deformations of Feature Maps for Virtual Try-On

TL;DR

This paper introduces WUTON, an end-to-end trainable neural network that improves 2D virtual try-on by accurately warping clothing images onto persons, resulting in more realistic and artifact-free images.

Contribution

It proposes a novel siamese U-net architecture with geometric transformations trained jointly with a multi-task loss, advancing virtual try-on image quality.

Findings

Outperforms state-of-the-art methods in visual quality

Achieves higher LPIPS scores indicating better perceptual similarity

Generates more realistic and detailed virtual try-on images

Abstract

The 2D virtual try-on task has recently attracted a lot of interest from the research community, for its direct potential applications in online shopping as well as for its inherent and non-addressed scientific challenges. This task requires to fit an in-shop cloth image on the image of a person. It is highly challenging because it requires to warp the cloth on the target person while preserving its patterns and characteristics, and to compose the item with the person in a realistic manner. Current state-of-the-art models generate images with visible artifacts, due either to a pixel-level composition step or to the geometric transformation. In this paper, we propose WUTON: a Warping U-net for a Virtual Try-On system. It is a siamese U-net generator whose skip connections are geometrically transformed by a convolutional geometric matcher. The whole architecture is trained end-to-end with a multi-task loss including an adversarial one. This enables our network to generate and use realistic spatial transformations of the cloth to synthesize images of high visual quality. The proposed architecture can be trained end-to-end and allows us to advance towards a detail-preserving and photo-realistic 2D virtual try-on system. Our method outperforms the current state-of-the-art with visual results as well as with the Learned Perceptual Image Similarity (LPIPS) metric.