D3: Deep Dual-Domain Based Fast Restoration of JPEG-Compressed Images
Authors:
- Zhangyang WangZWZhangyang Wang
- Ding LiuDLDing Liu
- Shiyu ChangSCShiyu Chang
- Qing LingQLQing Ling
- Yingzhen YangYYYingzhen Yang
- Thomas S. HuangTHThomas S. Huang
- 1 June 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 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 lightweighted 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.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Convolutional neural networks at constrained time cost2015
- Data-driven sparsity-based restoration of JPEG-compressed images in dual transform-pixel domain2015
- Learning Efficient Sparse and Low Rank ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- A Learning-Based Approach to Reduce JPEG Artifacts in Image Matting2013
- Review of Proposed High Efficiency Video Coding (HEVC) StandardInternational Journal of Computer Applications, 2012
- Image deblocking via sparse representationSignal Processing: Image Communication, 2012
- A Total Variation–Based JPEG Decompression ModelSIAM Journal on Imaging Sciences, 2012
- Tackling Box-Constrained Optimization via a New Projected Quasi-Newton ApproachSIAM Journal on Scientific Computing, 2010
- Iterative Thresholding for Sparse ApproximationsJournal of Fourier Analysis and Applications, 2008
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004