zhenngbolun/IDCN

Implicit Dual-domain Convolutional Network for Robust Color Image Compression Artifact Reduction (IEEE TCSVT 2019)

IDCN

Implicit Dual-domain Convolutional Network for Robust Color Image Compression Artifact Reduction

B. Zheng, Y. Chen, X. Tian, F. Zhou and X. Liu, "Implicit Dual-domain Convolutional Network for Robust Color Image Compression Artifact Reduction," in IEEE Transactions on Circuits and Systems for Video Technology.
doi: 10.1109/TCSVT.2019.2931045

@article{zheng2019implicit, title={Implicit dual-domain convolutional network for robust color image compression artifact reduction}, author={Zheng, Bolun and Chen, Yaowu and Tian, Xiang and Zhou, Fan and Liu, Xuesong}, journal={IEEE Transactions on Circuits and Systems for Video Technology}, volume={30}, number={11}, pages={3982--3994}, year={2019}, publisher={IEEE} }

Network Architecture

Architecture

Dual-domain Correction Unit

Position Labeling

Results

• Here all the results of compared methods are REPRODUCED by ourself.
• All the methods are trained on DIV2K with learning rate from 0.0001 to 0.000001.
• Several pre-trained models can be downloaded at https://pan.baidu.com/s/1SK26KzV4SfyWSc09ehwnrg password: hp6v

Runing Times

Dual-domain Correction

Robust JPEG Compression Artifact Reduction

Qualitative Results