ML Anthology

Combine Traditional Compression Method with Convolutional Neural Networks

Jianhua Hu, Ming Li, Changsheng Xia, Yundong Zhang
CVPRW 2018 pp. 2563-2566
/cvprw/2018/hu2018cvprw-combine/

Abstract

Deep learning, e.g., convolutional neural networks (CNNs), has achieved great success in image processing and computer vision tasks like classification, detection and image compression. We propose a method by combining convolution neural networks and traditional compression method. The prepositive compression comes from the SVAC2(which is drafted and maintained by VimicroAI and China's Ministry of Public Security) video codec. We further improve the SVAC2 by adopting a recovering CNN network after the reconstruction. Our approach outperforms JPEG/JPEG2000/WebP standards, and is equivalent to BPG.

PDF CVPRW Semantic Scholar

Cite

Text

Hu et al. "Combine Traditional Compression Method with Convolutional Neural Networks." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.

Markdown

[Hu et al. "Combine Traditional Compression Method with Convolutional Neural Networks." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.](https://mlanthology.org/cvprw/2018/hu2018cvprw-combine/)

BibTeX

@inproceedings{hu2018cvprw-combine,
  title     = {{Combine Traditional Compression Method with Convolutional Neural Networks}},
  author    = {Hu, Jianhua and Li, Ming and Xia, Changsheng and Zhang, Yundong},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2018},
  pages     = {2563-2566},
  url       = {https://mlanthology.org/cvprw/2018/hu2018cvprw-combine/}
}