Wavelet-Based Dual Recursive Network for Image Super-Resolution
- 27 October 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 33 (2) , 707-720
Abstract
Although remarkable progress has been made on single-image super-resolution (SISR), deep learning methods cannot be easily applied to real-world applications due to the requirement of its heavy computation, especially for mobile devices. Focusing on the fewer parameters and faster inference SISR approach, we propose an efficient and time-saving wavelet transform-based network architecture, where the image super-resolution (SR) processing is carried out in the wavelet domain. Different from the existing methods that directly infer high-resolution (HR) image with the input low-resolution (LR) image, our approach first decomposes the LR image into a series of wavelet coefficients (WCs) and the network learns to predict the corresponding series of HR WCs and then reconstructs the HR image. Particularly, in order to further enhance the relationship between WCs and image deep characteristics, we propose two novel modules [wavelet feature mapping block (WFMB) and wavelet coefficients reconstruction block (WCRB)] and a dual recursive framework for joint learning strategy, thus forming a WCs prediction model to realize the efficient and accurate reconstruction of HR WCs. Experimental results show that the proposed method can outperform state-of-the-art methods with more than a $2\times $ reduction in model parameters and computational complexity.Keywords
Funding Information
- National Key Research and Development Program of China (2018AAA0103202)
- National Natural Science Foundation of China (61922066, 61876142, 61671339, 61772402, U1605252, 61976166, 62036007)
- National High-Level Talents Special Support Program of China (CS31117200001)
- Fundamental Research Funds for the Central Universities (JB190117)
- Xidian University Intellifusion Joint Innovation Laboratory of Artificial Intelligence
- Innovation Fund of Xidian University
This publication has 44 references indexed in Scilit:
- Single image super-resolution from transformed self-exemplars2015
- Image Super-Resolution Using Deep Convolutional NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution2015
- Image Interpolation via Graph-Based Bayesian Label PropagationIEEE Transactions on Image Processing, 2013
- Anchored Neighborhood Regression for Fast Example-Based Super-Resolution2013
- Cardiac Image Super-Resolution with Global Correspondence Using Multi-Atlas PatchMatch2013
- On Single Image Scale-Up Using Sparse-Representations2012
- Sub‐pixel mapping of rural land cover objects from fine spatial resolution satellite sensor imagery using super‐resolution pixel‐swappingInternational Journal of Remote Sensing, 2006
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics2002