Anime-to-Real Clothing: Cosplay Costume Generation via Image-to-Image Translation

TL;DR

This paper introduces a novel GAN-based method for converting anime images into realistic cosplay costumes, addressing diverse styles and shapes with improved quality and realism compared to existing approaches.

Contribution

The paper presents a new GAN architecture and a dataset preprocessing pipeline for high-quality anime-to-real costume image translation.

Findings

Outperforms existing methods in quality metrics

Generates more realistic cosplay images

Effective handling of diverse clothing styles

Abstract

Cosplay has grown from its origins at fan conventions into a billion-dollar global dress phenomenon. To facilitate imagination and reinterpretation from animated images to real garments, this paper presents an automatic costume image generation method based on image-to-image translation. Cosplay items can be significantly diverse in their styles and shapes, and conventional methods cannot be directly applied to the wide variation in clothing images that are the focus of this study. To solve this problem, our method starts by collecting and preprocessing web images to prepare a cleaned, paired dataset of the anime and real domains. Then, we present a novel architecture for generative adversarial networks (GANs) to facilitate high-quality cosplay image generation. Our GAN consists of several effective techniques to fill the gap between the two domains and improve both the global and local consistency of generated images. Experiments demonstrated that, with two types of evaluation metrics, the proposed GAN achieves better performance than existing methods. We also showed that the images generated by the proposed method are more realistic than those generated by the conventional methods. Our codes and pretrained model are available on the web.