SeD: Semantic-Aware Discriminator for Image Super-Resolution

arXiv:2402.19387v1 Announce Type: cross
Abstract: Generative Adversarial Networks (GANs) have been widely used to recover vivid textures in image super-resolution (SR) tasks. In particular, one discriminator is utilized to enable the SR network to learn the distribution of real-world high-quality images in an adversarial training manner. However, the distribution learning is overly coarse-grained, which is susceptible to virtual textures and causes counter-intuitive generation results. To mitigate this, we propose the simple and effective Semantic-aware Discriminator (denoted as SeD), which encourages …

abstract adversarial adversarial training arxiv cs.cv distribution eess.iv gans generative generative adversarial networks image images learn network networks quality semantic tasks training type world