FBRNN: Feedback Recurrent Neural Network for Extreme Image Super-Resolution

Junyeop Lee, Jaihyun Park, Kanghyu Lee, Jeongki Min, Gwantae Kim, Bokyeung Lee, Bonhwa Ku, David K. Han, Hanseok Ko; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020, pp. 488-489

Single image extreme Super Resolution(SR) is a difficult task as scale factors in the order of 10X or greater is typically attempted. For instance, in the case of 16x upscale of an image,a single pixel from a low resolution image gets expanded to a 16x16 image patch. Such attempts often result fuzzy quality and loss in details in reconstructed images. To handle this difficulties, we propose a network architecture composed of a series of connected blocks in recurrent and feedback fashions for enhanced SR reconstruction. By use of a recurrent network, an SR image is refined over a sequence of enhancement stages in a coarse to fine manner. Additionally, each stage involves back projection of SR image to LR images for continuously being refined during the sequence. According to the preliminary results of NTIRE 2020 perceptual extreme challenge, our team (KU ISPLB) secured 6th place by PSNR and 7th place by SSIM among all participants.