Toward Low Artifact Virtual Try-On Via Pre-Warping Partitioned Clothing Alignment

Most image-based try-on methods adopt a warping model to deform the in-shop clothes directly, but they often encounter distortion or corrupt results when dealing with complex body poses or testing on wild data. To address the challenge, we propose a pre-warping partitioned clothing alignment method toward artifact-free virtual try-on in wild data. Specifically, we use perspective transformation to warp different parts of the in-shop clothes and then adjust the results using the Warping-Parsing Condition Generator module, simultaneously generating human parsing. This approach simplifies the learning objectives of the clothing warping module, eliminating the need for significant displacements or rotations when dealing with complex poses. Experimental results demonstrate that our approach is more stable and reduces artifacts compared to state-of-the-art methods.

1. Introduction

Online sales play an increasingly pivotal role in the retail industry. In 2022, e-commerce accounted for nearly 19% of global retail sales. Forecasts indicate that by 2027, online sales will constitute nearly a quarter of the global retail total [1]. The pandemic has accelerated the shift of physical stores toward concurrent operations in both physical and online e-commerce. However, online clothing purchases often incur higher return rates compared to physical stores due to the lack of a try-on experience. Return costs include shipping and time, especially impacting seasonal items whose value may diminish after returns due to obsolescence.