Single image super-resolution based on adaptive convolutional sparse coding and convolutional neural networks

• Published in: Journal of visual communication and image representation Vol. 58; pp. 651 - 661
• Main Authors: Zhao, Jianwei, Chen, Chen, Zhou, Zhenghua, Cao, Feilong
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.01.2019
• Subjects: Adaptive; Convolutional neural network; Convolutional sparse coding; Super-resolution; Super-resolution; Adaptive; 94A08; 92B20; Convolutional sparse coding; Convolutional neural network
• ISSN: 1047-3203; 1095-9076
• DOI: 10.1016/j.jvcir.2018.12.036

•Propose a new super-resolution method based on CSC and CNN.•Use CNN to reconstruct the high resolution image for the low-frequency part.•Propose an ACSC to reconstruct high resolution image for high-frequency part.•Integrate and develope the advantages of the CSC method and CNN. The convolutional sparse coding-based super-resolution (CSC-SR) method has shown its good performance in single image super-resolution. It divides the low-resolution (LR) image into low-frequency part and the high-frequency part, and reconstructs their corresponding high-resolution (HR) image with bicubic interpolation and convolutional sparse coding (CSC) method, respectively. This paper is devoted to improve the performance of CSC-SR method. As convolutional neural network (CNN) can reveal the mapping relation between the LR image and the HR image for the low-frequency part better, we replace the bicubic interpolation with CNN to reconstruct the HR image for the low-frequency part. In addition, we propose an adaptive CSC method to reconstruct the HR image for the high-frequency part. We name our proposed super-resolution method as hybrid adaptive convolutional sparse coding-based super-resolution (HACSC-SR) method. Many comparison experiments illustrate that our proposed HACSC-SR method is superior to CSC-SR, CNN as well as several existing super-resolution methods.