TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models

TL;DR

This paper presents TryOffDiff, a diffusion model-based approach for high-fidelity garment reconstruction from single images, enabling standardized garment image generation and improving evaluation of generative models.

Contribution

It introduces VTOFF, a new task for garment image reconstruction, and proposes TryOffDiff, adapting Stable Diffusion with SigLIP conditioning for superior results.

Findings

Outperforms pose transfer and VTON baselines on datasets

DISTS metric better reflects reconstruction quality than SSIM

Potential to enhance e-commerce imagery and model evaluation

Abstract

This paper introduces Virtual Try-Off (VTOFF), a novel task generating standardized garment images from single photos of clothed individuals. Unlike Virtual Try-On (VTON), which digitally dresses models, VTOFF extracts canonical garment images, demanding precise reconstruction of shape, texture, and complex patterns, enabling robust evaluation of generative model fidelity. We propose TryOffDiff, adapting Stable Diffusion with SigLIP-based visual conditioning to deliver high-fidelity reconstructions. Experiments on VITON-HD and Dress Code datasets show that TryOffDiff outperforms adapted pose transfer and VTON baselines. We observe that traditional metrics such as SSIM inadequately reflect reconstruction quality, prompting our use of DISTS for reliable assessment. Our findings highlight VTOFF's potential to improve e-commerce product imagery, advance generative model evaluation, and guide future research on high-fidelity reconstruction. Demo, code, and models are available at: https://rizavelioglu.github.io/tryoffdiff