Cited 0 time in
Cited 20 time in
SRFeat: Single Image Super-Resolution with Feature Discrimination
- SRFeat: Single Image Super-Resolution with Feature Discrimination
- Park, S.-J.; Son, H.; Cho, Sunghyun; Hong, K.-S.; Lee, S.
- DGIST Authors
- Cho, Sunghyun
- Issue Date
- European Conference on Computer Vision (spotlight/poster), 455-471
- Generative adversarial networks (GANs) have recently been adopted to single image super-resolution (SISR) and showed impressive results with realistically synthesized high-frequency textures. However, the results of such GAN-based approaches tend to include less meaningful high-frequency noise that is irrelevant to the input image. In this paper, we propose a novel GAN-based SISR method that overcomes the limitation and produces more realistic results by attaching an additional discriminator that works in the feature domain. Our additional discriminator encourages the generator to produce structural high-frequency features rather than noisy artifacts as it distinguishes synthetic and real images in terms of features. We also design a new generator that utilizes long-range skip connections so that information between distant layers can be transferred more effectively. Experiments show that our method achieves the state-of-the-art performance in terms of both PSNR and perceptual quality compared to recent GAN-based methods. © 2018, Springer Nature Switzerland AG.
- Springer Verlag
There are no files associated with this item.
- Department of Information and Communication EngineeringVisual Computing Lab2. Conference Papers
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.