Wide-activated Deep Residual Networks based Restoration for BPG-compressed Images

We investigate a simple pipeline to achieve high-quality image compression under very low bit-rate. The pipeline is a stack of BPG image compression and deep network based restoration. Wide-activated deep residual networks from recent advances in image super-resolution are adopted for image restoration. Experiments demonstrate that the pipeline significantly reduces the quantity loss and remove visual artifacts for compressed images.

[1]  Xianming Liu,et al.  Robust Video Super-Resolution with Learned Temporal Dynamics , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[2]  Luca Benini,et al.  CAS-CNN: A deep convolutional neural network for image compression artifact suppression , 2016, 2017 International Joint Conference on Neural Networks (IJCNN).

[3]  Thomas S. Huang,et al.  Balanced Two-Stage Residual Networks for Image Super-Resolution , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[4]  Alex Graves,et al.  Conditional Image Generation with PixelCNN Decoders , 2016, NIPS.

[5]  Jian Yang,et al.  MemNet: A Persistent Memory Network for Image Restoration , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[6]  Pavel Zemcík,et al.  Compression Artifacts Removal Using Convolutional Neural Networks , 2016, J. WSCG.

[7]  Tim Salimans,et al.  Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks , 2016, NIPS.

[8]  Valero Laparra,et al.  End-to-end Optimized Image Compression , 2016, ICLR.

[9]  Thomas S. Huang,et al.  Generative Image Inpainting with Contextual Attention , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[10]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[11]  Xiaoou Tang,et al.  Compression Artifacts Reduction by a Deep Convolutional Network , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[12]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Luc Van Gool,et al.  Conditional Probability Models for Deep Image Compression , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[14]  Lubomir D. Bourdev,et al.  Real-Time Adaptive Image Compression , 2017, ICML.

[15]  Kyoung Mu Lee,et al.  Enhanced Deep Residual Networks for Single Image Super-Resolution , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[16]  Luc Van Gool,et al.  NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[17]  Lucas Theis,et al.  Lossy Image Compression with Compressive Autoencoders , 2017, ICLR.

[18]  David Zhang,et al.  Learning Convolutional Networks for Content-Weighted Image Compression , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[19]  Eirikur Agustsson,et al.  NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).