JPEG Artifacts Reduction via Deep Convolutional Sparse Coding

To effectively reduce JPEG compression artifacts, we propose a deep convolutional sparse coding (DCSC) network architecture. We design our DCSC in the framework of classic learned iterative shrinkage-threshold algorithm. To focus on recognizing and separating artifacts only, we sparsely code the fea...

Full description

Saved in:

Bibliographic Details
Published in:	Proceedings / IEEE International Conference on Computer Vision pp. 2501 - 2510
Main Authors:	Fu, Xueyang, Zha, Zheng-Jun, Wu, Feng, Ding, Xinghao, Paisley, John
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.10.2019
Subjects:	Convolution Convolutional codes Encoding Feature extraction Image coding Task analysis Transform coding
ISSN:	2380-7504
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	To effectively reduce JPEG compression artifacts, we propose a deep convolutional sparse coding (DCSC) network architecture. We design our DCSC in the framework of classic learned iterative shrinkage-threshold algorithm. To focus on recognizing and separating artifacts only, we sparsely code the feature maps instead of the raw image. The final de-blocked image is directly reconstructed from the coded features. We use dilated convolution to extract multi-scale image features, which allows our single model to simultaneously handle multiple JPEG compression levels. Since our method integrates model-based convolutional sparse coding with a learning-based deep neural network, the entire network structure is compact and more explainable. The resulting lightweight model generates comparable or better de-blocking results when compared with state-of-the-art methods.
ISSN:	2380-7504
DOI:	10.1109/ICCV.2019.00259