Virtual Try-On for Cultural Clothing: A Benchmarking Study

TL;DR

This paper introduces BD-VITON, a new dataset for virtual try-on of Bangladeshi cultural clothing, and evaluates existing models, highlighting their improved performance on this diverse, complex dataset.

Contribution

The creation of BD-VITON dataset focusing on Bangladeshi garments and the benchmarking of try-on models on this culturally diverse dataset.

Findings

Models show improved performance on BD-VITON compared to zero shot inference.

Complex garment structures pose unique challenges for virtual try-on.

Benchmarking reveals the need for culturally diverse datasets in virtual try-on research.

Abstract

Although existing virtual try-on systems have made significant progress with the advent of diffusion models, the current benchmarks of these models are based on datasets that are dominant in western-style clothing and female models, limiting their ability to generalize culturally diverse clothing styles. In this work, we introduce BD-VITON, a virtual try-on dataset focused on Bangladeshi garments, including saree, panjabi and salwar kameez, covering both male and female categories as well. These garments present unique structural challenges such as complex draping, asymmetric layering, and high deformation complexities which are underrepresented in the original VITON dataset. To establish strong baselines, we retrain and evaluate try-on models, namely StableViton, HR-VITON, and VITON-HD on our dataset. Our experiments demonstrate consistent improvements in terms of both quantitative and qualitative analysis, compared to zero shot inference.