Joint-attention Discriminator for Accurate Super-resolution via Adversarial Training
Proceedings of the 27th ACM International Conference on Multimedia, pp. 711-719, 2019.
cross-layer attention dense channel-wise attention generative adversarial network image super-resolution joint-attention discriminator
Tremendous progress has been witnessed on single image super-resolution (SR), where existing deep SR models achieve impressive performance in objective criteria, e.g., PSNR and SSIM. However, most of the SR methods are limited in visual perception, for example, they look too smooth. Generative adversarial network (GAN) favors SR visual ef...More
Full Text (Upload PDF)
PPT (Upload PPT)