TY - GEN
T1 - D3
T2 - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
AU - Wang, Zhangyang
AU - Liu, Ding
AU - Chang, Shiyu
AU - Ling, Qing
AU - Yang, Yingzhen
AU - Huang, Thomas S.
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/12/9
Y1 - 2016/12/9
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84986267163&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84986267163&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2016.302
DO - 10.1109/CVPR.2016.302
M3 - Conference contribution
AN - SCOPUS:84986267163
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 2764
EP - 2772
BT - Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
PB - IEEE Computer Society
Y2 - 26 June 2016 through 1 July 2016
ER -