Best-Buddy GANs for Highly Detailed Image Super-resolution


  • Wenbo Li The Chinese University of Hong Kong
  • Kun Zhou SmartMore Technology
  • Lu Qi The Chinese University of Hong Kong
  • Liying Lu The Chinese University of Hong Kong
  • Jiangbo Lu SmartMore Technology



Computer Vision (CV)


We consider the single image super-resolution (SISR) problem, where a high-resolution (HR) image is generated based on a low-resolution (LR) input. Recently, generative adversarial networks (GANs) become popular to hallucinate details. Most methods along this line rely on a predefined single-LR-single-HR mapping, which is not flexible enough for the ill-posed SISR task. Also, GAN-generated fake details may often undermine the realism of the whole image. We address these issues by proposing best-buddy GANs (Beby-GAN) for rich-detail SISR. Relaxing the rigid one-to-one constraint, we allow the estimated patches to dynamically seek trustworthy surrogates of supervision during training, which is beneficial to producing more reasonable details. Besides, we propose a region-aware adversarial learning strategy that directs our model to focus on generating details for textured areas adaptively. Extensive experiments justify the effectiveness of our method. An ultra-high-resolution 4K dataset is also constructed to facilitate future super-resolution research.




How to Cite

Li, W., Zhou, K., Qi, L., Lu, L., & Lu, J. (2022). Best-Buddy GANs for Highly Detailed Image Super-resolution. Proceedings of the AAAI Conference on Artificial Intelligence, 36(2), 1412-1420.



AAAI Technical Track on Computer Vision II