Deeply Improved Sparse Coding for Image Super-Resolution

By Zhaowen Wang, Ding Liu, Jianchao Yang, Wei Han, Thomas S. Huang. 2015

39 citations recorded by the source corpus.

Deep learning techniques have been successfully applied in many areas of computer vision, including low-level image restoration problems. For image super-resolution, several models based on deep neural networks have been recently proposed and attained superior performance that overshadows all previous handcrafted models. The question then arises whether large-capacity and data-driven models have become the dominant solution to the ill-posed super-resolution problem. In this paper, we argue that domain expertise represented by the conventional sparse coding model is still valuable, and it can be combined with the key ingredients of deep learning to achieve further improved results. We show that a sparse coding model particularly designed for super-resolution can be incarnated as a neural network, and trained in a cascaded structure from end to end. The interpretation of the network based on sparse coding leads to much more efficient and effective training, as well as a reduced model size. Our model is evaluated on a wide range of images, and shows clear advantage over existing state-of-the-art methods in terms of both restoration accuracy and human subjective quality.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Chen Change Loy
3. Ming-Hsuan Yang
4. Radu Timofte
5. Chao Dong
6. Lei Zhang
7. Dacheng Tao
8. Xiaogang Wang

In Media Technology

1. Chao Dong
2. Radu Timofte
3. Chen Change Loy
4. Ferenc Huszár
5. Lei Zhang
6. Luc Van Gool
7. Kai Zhang
8. Wangmeng Zuo

Citations in the corpus

• Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (2016, background): “In the context of SISR it was also shown that learning upscaling filters is beneficial both in terms of speed and accuracy [51, 40].”
• Accelerating the Super-Resolution Convolutional Neural Network (2016, methodology): “Furthermore, all these networks [8,18,19] need to process the bicubic-upscaled LR images.”