Loading [MathJax]/jax/input/TeX/config.js
Efficient CTU-based intra frame coding for HEVC based on deep learning | IEEE Conference Publication | IEEE Xplore

Efficient CTU-based intra frame coding for HEVC based on deep learning

Publisher: IEEE

Abstract:

To further improve the compression efficiency of HEVC intra frame coding, in this paper, a deep learning-based framework is proposed. Inspired by recently developed deep ...View more

Abstract:

To further improve the compression efficiency of HEVC intra frame coding, in this paper, a deep learning-based framework is proposed. Inspired by recently developed deep learning models for image super-resolution (SR), we propose to train a CNN (convolutional neural network) model to precisely predict the residual information of each CTU (coding tree unit) at the HEVC encoder. As a result, better CTU reconstruction and better prediction for the compression of subsequent CTUs can be achieved. To reduce computational complexity, different from current CNN-based SR works, we propose to skip the non-linear mapping layer, and incorporate the residual learning to obtain better predicted residual for CTU encoding. Experimental results have shown that the proposed method achieves 3.2% bitrate reduction in average BDBR (Bjentegaard delta bit rate) with only 37% encoding complexity increased.
Date of Conference: 12-15 December 2017
Date Added to IEEE Xplore: 08 February 2018
ISBN Information:
Publisher: IEEE
Conference Location: Kuala Lumpur, Malaysia

References

References is not available for this document.