FW-VTON: Flattening-and-Warping for Person-to-Person Virtual Try-on

TL;DR

This paper presents FW-VTON, a novel method for person-to-person virtual try-on that extracts, warps, and seamlessly integrates garments from one person onto another, achieving state-of-the-art results.

Contribution

Introduces FW-VTON, a three-stage approach for person-to-person virtual try-on, and provides a new dataset for this specific task.

Findings

Achieves superior qualitative and quantitative performance.

Excels in garment extraction subtasks.

Outperforms existing methods in realism and accuracy.

Abstract

Traditional virtual try-on methods primarily focus on the garment-to-person try-on task, which requires flat garment representations. In contrast, this paper introduces a novel approach to the person-to-person try-on task. Unlike the garment-to-person try-on task, the person-to-person task only involves two input images: one depicting the target person and the other showing the garment worn by a different individual. The goal is to generate a realistic combination of the target person with the desired garment. To this end, we propose Flattening-and-Warping Virtual Try-On (\textbf{FW-VTON}), a method that operates in three stages: (1) extracting the flattened garment image from the source image; (2) warping the garment to align with the target pose; and (3) integrating the warped garment seamlessly onto the target person. To overcome the challenges posed by the lack of high-quality datasets for this task, we introduce a new dataset specifically designed for person-to-person try-on scenarios. Experimental evaluations demonstrate that FW-VTON achieves state-of-the-art performance, with superior results in both qualitative and quantitative assessments, and also excels in garment extraction subtasks.