Enhanced Anime Image Generation Using USE-CMHSA-GAN

TL;DR

This paper presents USE-CMHSA-GAN, a novel GAN model that enhances anime image generation quality by integrating USE and CMHSA modules, outperforming existing models on standard benchmarks.

Contribution

Introduces USE-CMHSA-GAN, a new GAN architecture combining USE and CMHSA modules for improved anime image synthesis.

Findings

Outperforms DCGAN, VAE-GAN, and WGAN in FID and IS scores

Demonstrates superior quality in anime character image generation

Provides insights for future improvements in generative models

Abstract

With the growing popularity of ACG (Anime, Comics, and Games) culture, generating high-quality anime character images has become an important research topic. This paper introduces a novel Generative Adversarial Network model, USE-CMHSA-GAN, designed to produce high-quality anime character images. The model builds upon the traditional DCGAN framework, incorporating USE and CMHSA modules to enhance feature extraction capabilities for anime character images. Experiments were conducted on the anime-face-dataset, and the results demonstrate that USE-CMHSA-GAN outperforms other benchmark models, including DCGAN, VAE-GAN, and WGAN, in terms of FID and IS scores, indicating superior image quality. These findings suggest that USE-CMHSA-GAN is highly effective for anime character image generation and provides new insights for further improving the quality of generative models.