用新模块提升动漫人物生成质量，效果优于主流模型。
Enhanced Anime Image Generation Using USE-CMHSA-GAN
- 在DCGAN基础上加入USE与CMHSA模块增强特征提取。
- 在anime-face-dataset上FID和IS得分优于DCGAN、VAE-GAN、WGAN。
- 适合关注动漫图像生成与生成模型改进的研究者。
随着ACG（动漫、漫画、游戏）文化的日益流行，生成高质量的动漫角色图像已成为重要研究课题。本文提出一种新型生成对抗网络模型USE-CMHSA-GAN，旨在生成高质量动漫角色图像。该模型基于传统DCGAN框架，引入USE和CMHSA模块以增强对动漫角色图像的特征提取能力。在anime-face-dataset上的实验表明，USE-CMHSA-GAN在FID和IS评分上均优于DCGAN、VAE-GAN和WGAN等基准模型，显示出更优的图像质量。结果表明，USE-CMHSA-GAN在动漫角色图像生成方面具有显著有效性，并为提升生成模型质量提供了新思路。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。