Single Stage Warped Cloth Learning and Semantic-Contextual Attention Feature Fusion for Virtual TryOn

TL;DR

This paper introduces a novel single-stage virtual try-on framework that uses semantic-contextual attention for efficient cloth warping and body synthesis, improving realism and reducing artifacts in virtual clothing fitting.

Contribution

It proposes a unified single-stage approach with a semantic-contextual fusion attention module and a Warped Cloth Learning Module, eliminating the need for multi-stage processes and explicit labels.

Findings

Enhanced virtual try-on realism and efficiency

Reduced misalignment and artifacts

Improved cloth warping quality

Abstract

Image-based virtual try-on aims to fit an in-shop garment onto a clothed person image. Garment warping, which aligns the target garment with the corresponding body parts in the person image, is a crucial step in achieving this goal. Existing methods often use multi-stage frameworks to handle clothes warping, person body synthesis and tryon generation separately or rely on noisy intermediate parser-based labels. We propose a novel single-stage framework that implicitly learns the same without explicit multi-stage learning. Our approach utilizes a novel semantic-contextual fusion attention module for garment-person feature fusion, enabling efficient and realistic cloth warping and body synthesis from target pose keypoints. By introducing a lightweight linear attention framework that attends to garment regions and fuses multiple sampled flow fields, we also address misalignment and artifacts present in previous methods. To achieve simultaneous learning of warped garment and try-on results, we introduce a Warped Cloth Learning Module. Our proposed approach significantly improves the quality and efficiency of virtual try-on methods, providing users with a more reliable and realistic virtual try-on experience.