Conditional Entropy Coding for Efficient Video Compression

@article{Liu2020ConditionalEC,
  title={Conditional Entropy Coding for Efficient Video Compression},
  author={Jerry Liu and Shenlong Wang and W. Ma and Meet Shah and Rui Hu and Pranaab Dhawan and R. Urtasun},
  journal={ArXiv},
  year={2020},
  volume={abs/2008.09180}
}
We propose a very simple and efficient video compression framework that only focuses on modeling the conditional entropy between frames. Unlike prior learning-based approaches, we reduce complexity by not performing any form of explicit transformations between frames and assume each frame is encoded with an independent state-of-the-art deep image compressor. We first show that a simple architecture modeling the entropy between the image latent codes is as competitive as other neural video… Expand

References

SHOWING 1-10 OF 40 REFERENCES
Neural Inter-Frame Compression for Video Coding
  • 42
  • Highly Influential
  • PDF
DVC: An End-To-End Deep Video Compression Framework
  • 105
  • Highly Influential
  • PDF
Deep Generative Video Compression
  • 22
  • PDF
Learned Video Compression
  • 67
  • Highly Influential
  • PDF
Video Compression With Rate-Distortion Autoencoders
  • 39
  • Highly Influential
  • PDF
Neural Video Compression using Spatio-Temporal Priors.
  • 3
  • PDF
Practical Full Resolution Learned Lossless Image Compression
  • 42
  • PDF
DSIC: Deep Stereo Image Compression
  • 3
  • PDF
Video Compression through Image Interpolation
  • 87
  • Highly Influential
  • PDF
Conditional Probability Models for Deep Image Compression
  • 186
  • PDF
...
1
2
3
4
...