Image Super-Resolution via Dual-Dictionary Learning and Sparse Representation (ISCAS 2013) [pdf]

Abstract

Learning-based image super-resolution aims to reconstruct high-frequency (HF) details from the prior model trained by a set of high- and low-resolution image patches. In this paper, HF to be estimated is considered as a combination of two components: main high-frequency (MHF) and residual high-frequency (RHF), and we propose a novel image super-resolution method via dual-dictionary learning and sparse representation, which consists of the main dictionary learning and the residual dictionary learning, to recover MHF and RHF respectively. Extensive experimental results on test images validate that by employing the proposed two-layer progressive scheme, more image details can be recovered and much better results can be achieved than the state-of-the-art algorithms in terms of both PSNR and visual perception.

Citation

If you find our code helpful in your resarch or work, please cite our paper.

@inproceedings{zhang2012image,
  title={Image super-resolution via dual-dictionary learning and sparse representation},
  author={Zhang, Jian and Zhao, Chen and Xiong, Ruiqin and Ma, Siwei and Zhao, Debin},
  booktitle={Circuits and Systems (ISCAS), 2012 IEEE International Symposium on},
  pages={1688--1691},
  year={2012},
  organization={IEEE}
}