Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals

TL;DR

This paper introduces TEMU-VTOFF, a novel framework for inverse virtual try-on that reconstructs standardized garment images from clothed person photos, addressing ambiguity and detail loss issues with multimodal and alignment modules.

Contribution

The paper presents TEMU-VTOFF, the first multi-category inverse virtual try-on model utilizing multimodal attention and structure-texture alignment for improved realism and consistency.

Findings

Achieves state-of-the-art results on VITON-HD and Dress Code datasets.

Significantly improves visual realism and garment consistency.

Effectively resolves visual ambiguities using multimodal cues.

Abstract

Virtual try-on (VTON) has been widely explored for rendering garments onto person images, while its inverse task, virtual try-off (VTOFF), remains largely overlooked. VTOFF aims to recover standardized product images of garments directly from photos of clothed individuals. This capability is of great practical importance for e-commerce platforms, large-scale dataset curation, and the training of foundation models. Unlike VTON, which must handle diverse poses and styles, VTOFF naturally benefits from a consistent output format in the form of flat garment images. However, existing methods face two major limitations: (i) exclusive reliance on visual cues from a single photo often leads to ambiguity, and (ii) generated images usually suffer from loss of fine details, limiting their real-world applicability. To address these challenges, we introduce TEMU-VTOFF, a Text-Enhanced MUlti-category framework for VTOFF. Our architecture is built on a dual DiT-based backbone equipped with a multimodal attention mechanism that jointly exploits image, text, and mask information to resolve visual ambiguities and enable robust feature learning across garment categories. To explicitly mitigate detail degradation, we further design an alignment module that refines garment structures and textures, ensuring high-quality outputs. Extensive experiments on VITON-HD and Dress Code show that TEMU-VTOFF achieves new state-of-the-art performance, substantially improving both visual realism and consistency with target garments.