D3: Deep Dual-Domain Based Fast Restoration of JPEG-Compressed Images

Zhangyang Wang, Ding Liu, Shiyu Chang, Qing Ling, Yingzhen Yang, Thomas S. Huang; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 2764-2772

Abstract


In this paper, we design a Deep Dual-Domain (D3) based fast restoration model to remove artifacts of JPEG compressed images. It leverages the large learning capacity of deep networks, as well as the problem-specific expertise that was hardly incorporated in the past design of deep architectures. For the latter, we take into consideration both the prior knowledge of the JPEG compression scheme, and the successful practice of the sparsity-based dual-domain approach. We further design the One-Step Sparse Inference (1-SI) module, as an efficient and light-weighted feed-forward approximation of sparse coding. Extensive experiments verify the superiority of the proposed D3 model over several state-of-the-art methods. Specifically, our best model is capable of outperforming the latest deep model for around 1 dB in PSNR, and is 30 times faster.

Related Material


[pdf]
[bibtex]
@InProceedings{Wang_2016_CVPR,
author = {Wang, Zhangyang and Liu, Ding and Chang, Shiyu and Ling, Qing and Yang, Yingzhen and Huang, Thomas S.},
title = {D3: Deep Dual-Domain Based Fast Restoration of JPEG-Compressed Images},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2016}
}