ClothFormer:Taming Video Virtual Try-on in All Module

TL;DR

ClothFormer is a novel framework for video virtual try-on that achieves realistic, harmonious, and temporally consistent results by addressing occlusion, background complexity, and motion smoothing through specialized modules.

Contribution

The paper introduces ClothFormer, a comprehensive video try-on system with three key modules for occlusion handling, flow smoothing, and texture fusion, advancing the state-of-the-art in video virtual try-on.

Findings

Outperforms baselines in video quality metrics

Produces more realistic and consistent try-on videos

Effectively handles occlusions and complex backgrounds

Abstract

The task of video virtual try-on aims to fit the target clothes to a person in the video with spatio-temporal consistency. Despite tremendous progress of image virtual try-on, they lead to inconsistency between frames when applied to videos. Limited work also explored the task of video-based virtual try-on but failed to produce visually pleasing and temporally coherent results. Moreover, there are two other key challenges: 1) how to generate accurate warping when occlusions appear in the clothing region; 2) how to generate clothes and non-target body parts (e.g. arms, neck) in harmony with the complicated background; To address them, we propose a novel video virtual try-on framework, ClothFormer, which successfully synthesizes realistic, harmonious, and spatio-temporal consistent results in complicated environment. In particular, ClothFormer involves three major modules. First, a two-stage anti-occlusion warping module that predicts an accurate dense flow mapping between the body regions and the clothing regions. Second, an appearance-flow tracking module utilizes ridge regression and optical flow correction to smooth the dense flow sequence and generate a temporally smooth warped clothing sequence. Third, a dual-stream transformer extracts and fuses clothing textures, person features, and environment information to generate realistic try-on videos. Through rigorous experiments, we demonstrate that our method highly surpasses the baselines in terms of synthesized video quality both qualitatively and quantitatively.