Learning for Video Compression With Recurrent Auto-Encoder and Recurrent Probability Model

@article{Yang2021LearningFV,
  title={Learning for Video Compression With Recurrent Auto-Encoder and Recurrent Probability Model},
  author={R. Yang and Fabian Mentzer and L. Van Gool and R. Timofte},
  journal={IEEE Journal of Selected Topics in Signal Processing},
  year={2021},
  volume={15},
  pages={388-401}
}
The past few years have witnessed increasing interests in applying deep learning to video compression. However, the existing approaches compress a video frame with only a few number of reference frames, which limits their ability to fully exploit the temporal correlation among video frames. To overcome this shortcoming, this paper proposes a Recurrent Learned Video Compression (RLVC) approach with the Recurrent Auto-Encoder (RAE) and Recurrent Probability Model (RPM). Specifically, the RAE… Expand
Nonlinear Transform Coding
ELF-VC: Efficient Learned Flexible-Rate Video Coding
OpenDVC: An Open Source Implementation of the DVC Video Compression Method
FVC: A New Framework towards Deep Video Compression in Feature Space
Hierarchical motion-compensated deep network for video compression
  • Ying Liu, Peng Du, Yuzhu Li
  • Engineering, Computer Science
  • Defense + Commercial Sensing
  • 2021
Learned image and video compression with deep neural networks

References

SHOWING 1-10 OF 66 REFERENCES
Video Compression With Rate-Distortion Autoencoders
Conditional Probability Models for Deep Image Compression
DVC: An End-To-End Deep Video Compression Framework
Neural Inter-Frame Compression for Video Coding
Learning for Video Compression
Learning Image and Video Compression Through Spatial-Temporal Energy Compaction
Learning Convolutional Networks for Content-Weighted Image Compression
...
1
2
3
4
5
...