# Dilated convolutional neural network-based deep reference picture generation for video compression

arXiv: https://arxiv.org/abs/2202.05514 · HTML: https://mlsanity.com/paper/2202.05514/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 23 references that are in the map.
- First posted on arXiv 11 Feb 2022.

## Builds on (most cited first, 5 of 5)

- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Receptive Field Block Net for Accurate and Fast Object Detection](https://mlsanity.com/paper/1711.07767/) (2017)
- [Image and Video Compression with Neural Networks: A Review](https://mlsanity.com/paper/1904.03567/) (2019)
- [A Convolutional Neural Network Approach for Post-Processing in HEVC Intra Coding](https://mlsanity.com/paper/1608.06690/) (2016)
- [Deep Reference Generation with Multi-Domain Hierarchical Constraints for Inter Prediction](https://mlsanity.com/paper/1905.06567/) (2019)

## Abstract (arXiv)

Motion estimation and motion compensation are indispensable parts of inter prediction in video coding. Since the motion vector of objects is mostly in fractional pixel units, original reference pictures may not accurately provide a suitable reference for motion compensation. In this paper, we propose a deep reference picture generator which can create a picture that is more relevant to the current encoding frame, thereby further reducing temporal redundancy and improving video compression efficiency. Inspired by the recent progress of Convolutional Neural Network(CNN), this paper proposes to use a dilated CNN to build the generator. Moreover, we insert the generated deep picture into Versatile Video Coding(VVC) as a reference picture and perform a comprehensive set of experiments to evaluate the effectiveness of our network on the latest VVC Test Model VTM. The experimental results demonstrate that our proposed method achieves on average 9.7% bit saving compared with VVC under low-delay P configuration.