Fine-grained Attention and Feature-sharing Generative Adversarial Networks for Single Image Super-Resolution

1 code implementation • 25 Nov 2019 • Yitong Yan, Chuangchuang Liu, Changyou Chen, Xianfang Sun, Longcun Jin, Xiang Zhou

Firstly, instead of producing a single score to discriminate images between real and fake, we propose a variant, called Fine-grained Attention Generative Adversarial Network for image super-resolution (FASRGAN), to discriminate each pixel between real and fake.

Generative Adversarial Network Image Super-Resolution +1