- Conference Paper
Rights / licenseIn Copyright - Non-Commercial Use Permitted
Recent deep learning approaches to single image super-resolution have achieved impressive results in terms of traditional error measures and perceptual quality. However, in each case it remains challenging to achieve high quality results for large upsampling factors. To this end, we propose a method (ProSR) that is progressive both in architecture and training: the network upsamples an image in intermediate steps, while the learning process is organized from easy to hard, as is done in curriculum learning. To obtain more photorealistic results, we design a generative adversarial network (GAN), named ProGanSR, that follows the same progressive multi-scale design principle. This not only allows to scale well to high upsampling factors (e.g., 8×) but constitutes a principled multi-scale approach that increases the reconstruction quality for all upsampling factors simultaneously. In particular ProSR ranks 2nd in terms of SSIM and 4th in terms of PSNR in the NTIRE2018 SISR challenge. Compared to the top-ranking team, our model is marginally lower, but runs 5 times faster. Show more
Book title2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Pages / Article No.
Subjectimage super-resolution; deep learning
Organisational unit03911 - Sorkine Hornung, Olga / Sorkine Hornung, Olga
MoreShow all metadata