Learning a Single Convolutional Super-Resolution Network for Multiple Degradations

CVPR 2018  ·  Kai Zhang, WangMeng Zuo, Lei Zhang ·

Recent years have witnessed the unprecedented success of deep convolutional neural networks (CNNs) in single image super-resolution (SISR). However, existing CNN-based SISR methods mostly assume that a low-resolution (LR) image is bicubicly downsampled from a high-resolution (HR) image, thus inevitably giving rise to poor performance when the true degradation does not follow this assumption. Moreover, they lack scalability in learning a single model to non-blindly deal with multiple degradations. To address these issues, we propose a general framework with dimensionality stretching strategy that enables a single convolutional super-resolution network to take two key factors of the SISR degradation process, i.e., blur kernel and noise level, as input. Consequently, the super-resolver can handle multiple and even spatially variant degradations, which significantly improves the practicability. Extensive experimental results on synthetic and real LR images show that the proposed convolutional super-resolution network not only can produce favorable results on multiple degradations but also is computationally efficient, providing a highly effective and scalable solution to practical SISR applications.

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Super-Resolution BSD100 - 4x upscaling SRMDNF PSNR 27.49 # 30
SSIM 0.734 # 32
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration SRMD Subjective score 3.468 # 27
ERQAv1.0 0.594 # 28
QRCRv1.0 0 # 21
SSIM 0.834 # 15
PSNR 27.672 # 14
FPS 5.882 # 1
1 - LPIPS 0.877 # 16
Video Super-Resolution MSU Video Upscalers: Quality Enhancement SRMD PSNR 30.96 # 10
LPIPS 0.349 # 30
SSIM 0.852 # 15
Image Super-Resolution Set14 - 4x upscaling SRMDNF PSNR 28.35 # 50
SSIM 0.777 # 48
Image Super-Resolution Urban100 - 4x upscaling SRMDNF PSNR 25.68 # 34
SSIM 0.773 # 30

Methods


No methods listed for this paper. Add relevant methods here