# Interpreting CNN for Low Complexity Learned Sub-pixel Motion Compensation in Video Coding

arXiv: https://arxiv.org/abs/2006.06392 · HTML: https://mlsanity.com/paper/2006.06392/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2020.

## Built on by (most cited first, 5 of 5)

- [Improved CNN-based Learning of Interpolation Filters for Low-Complexity Inter Prediction in Video Coding](https://mlsanity.com/paper/2106.08936/) (2021)
- [Attention-Based Neural Networks for Chroma Intra Prediction in Video Coding](https://mlsanity.com/paper/2102.04993/) (2021)
- [Editorial: Introduction to the Issue on Deep Learning for Image/Video Restoration and Compression](https://mlsanity.com/paper/2102.06531/) (2021)
- [Towards Transparent Application of Machine Learning in Video Processing](https://mlsanity.com/paper/2105.12700/) (2021)
- [Deep Learning-based Filtering for Video Coding: A Survey on Architectures, Algorithms, and Complexity Analysis](https://mlsanity.com/paper/2607.16319/) (2026)

## Abstract (arXiv)

Deep learning has shown great potential in image and video compression tasks. However, it brings bit savings at the cost of significant increases in coding complexity, which limits its potential for implementation within practical applications. In this paper, a novel neural network-based tool is presented which improves the interpolation of reference samples needed for fractional precision motion compensation. Contrary to previous efforts, the proposed approach focuses on complexity reduction achieved by interpreting the interpolation filters learned by the networks. When the approach is implemented in the Versatile Video Coding (VVC) test model, up to 4.5% BD-rate saving for individual sequences is achieved compared with the baseline VVC, while the complexity of learned interpolation is significantly reduced compared to the application of full neural network.