EatGAN: An Edge-Attention Guided Generative Adversarial Network for Single Image Super-Resolution
EatGAN: 一种基于边缘注意力的生成对抗网络用于单图像超分辨率
机构 * Department of Mathematics, The Chinese University of Hong Kong（香港中文大学数学系）
AI总结 EatGAN通过引入边缘注意力机制，结合边缘先验显式和隐式利用，提升单图像超分辨率的生成质量与稳定性。
Comments 17 pages (8 pages of main text + 3 pages of reference + 6 pages of supplementary material)
