A Fully Progressive Approach to Single-Image Super-Resolution

Abstract

We set a new benchmark for single-image super-resolution by exploiting progressiveness both in architecture and training. The proposed multi-scale models, ProSR and ProSRGan, improve the reconstruction quality in terms of PSNR and visual quality respectively. ProSR is one of the winning teams.

Publication
The IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Date

Results

benchmark

MsLapSRN: Lai, Wei-Sheng, et al. “Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks.” arXiv preprint arXiv:1710.01992 (2017).

EDSR, MDSR: Lim, Bee, et al. “Enhanced deep residual networks for single image super-resolution.” The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. Vol. 1. No. 2. 2017.

RDN:Zhang, Yulun, et al. “Residual Dense Network for Image Super-Resolution.” The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2018.

Downloads

ProSR$_\ell$ BSD100 DIV2K val Set5 Set14 Urban100

Accompanying Video

(Best to be viewed in full-screen mode)