Deep Objective Quality Assessment Driven Single Image Super-Resolution
- 3 May 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 21 (11) , 2957-2971
Abstract
Single-image super-resolution (SISR) is a classic problem in the image processing community, which aims at generating a high-resolution image from a low-resolution one. In recent years, deep learning based SISR methods emerged and achieved a performance leap than previous methods. However, because the evaluation metrics of SISR methods is peak signal-to-noise ratio (PSNR), previous methods usually choose L2-norm as the loss function. This leads to a significant improvement in the final PSNR value but little improvement in perceptual quality. In this paper, in order to achieve better results in both perceptual quality and PSNR values, we propose an objective quality assessment driven SISR method. First, we propose a novel full-reference image quality assessment approach for SISR and employ it as a loss function, namely super-resolution image quality assessment (SR-IQA) loss. Then, we combine SR-IQA loss with L2-norm to guide our proposed SISR method to achieve better results. Besides that, our proposed SISR method consists of several proposed highway units. Furthermore, in order to verify the generalization ability of our new kind of loss function, we integrate SR-IQA loss to generative adversarial networks based SR method and achieve better perceptual quality. Experimental results prove that our proposed SISR method achieves better performance than other methods both qualitatively and quantitatively in most of the cases.Keywords
Funding Information
- National Natural Science Foundation of China (61772137)
This publication has 84 references indexed in Scilit:
- Blind Image Quality Assessment Based on Multichannel Feature Fusion and Label TransferIEEE Transactions on Circuits and Systems for Video Technology, 2015
- Fast Single Image Super-Resolution via Self-Example Learning and Sparse RepresentationIEEE Transactions on Multimedia, 2014
- Single-Image Super-Resolution: A Benchmark2014
- SSIM-inspired image restoration using sparse representationEURASIP Journal on Advances in Signal Processing, 2012
- On Single Image Scale-Up Using Sparse-Representations2012
- Fast image/video upsamplingACM Transactions on Graphics, 2008
- Efficient Spatial Image Watermarking via New Perceptual Masking and Blind Detection SchemesIEEE Transactions on Information Forensics and Security, 2006
- Incorporating Image Quality in Multi-algorithm Fingerprint Verification2005
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Improving resolution by image registrationCVGIP: Graphical Models and Image Processing, 1991