# Improved CNN-based Learning of Interpolation Filters for Low-Complexity Inter Prediction in Video Coding

arXiv: https://arxiv.org/abs/2106.08936 · HTML: https://mlsanity.com/paper/2106.08936/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 32 references that are in the map.
- First posted on arXiv 16 Jun 2021.

## Builds on (most cited first, 10 of 10)

- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [BVI-DVC: A Training Database for Deep Video Compression](https://mlsanity.com/paper/2003.13552/) (2020)
- [Implicit Rank-Minimizing Autoencoder](https://mlsanity.com/paper/2010.00679/) (2020)
- [A Convolutional Neural Network Approach for Post-Processing in HEVC Intra Coding](https://mlsanity.com/paper/1608.06690/) (2016)
- [Towards Perceptually Optimized End-to-end Adaptive Video Streaming](https://mlsanity.com/paper/1808.03898/) (2018)
- [End-to-End Conditional GAN-based Architectures for Image Colourisation](https://mlsanity.com/paper/1908.09873/) (2019)
- [Interpreting CNN for Low Complexity Learned Sub-pixel Motion Compensation in Video Coding](https://mlsanity.com/paper/2006.06392/) (2020)
- [A Convolutional Neural Network Approach for Half-Pel Interpolation in Video Coding](https://mlsanity.com/paper/1703.03502/) (2017)
- [Analytic Simplification of Neural Network based Intra-Prediction Modes for Video Compression](https://mlsanity.com/paper/2004.11056/) (2020)
- [Attention-Based Neural Networks for Chroma Intra Prediction in Video Coding](https://mlsanity.com/paper/2102.04993/) (2021)

## Built on by (most cited first, 2 of 2)

- [Complexity Reduction of Learned In-Loop Filtering in Video Coding](https://mlsanity.com/paper/2203.08650/) (2022)
- [Deep Learning-based Filtering for Video Coding: A Survey on Architectures, Algorithms, and Complexity Analysis](https://mlsanity.com/paper/2607.16319/) (2026)

## Abstract (arXiv)

The versatility of recent machine learning approaches makes them ideal for improvement of next generation video compression solutions. Unfortunately, these approaches typically bring significant increases in computational complexity and are difficult to interpret into explainable models, affecting their potential for implementation within practical video coding applications. This paper introduces a novel explainable neural network-based inter-prediction scheme, to improve the interpolation of reference samples needed for fractional precision motion compensation. The approach requires a single neural network to be trained from which a full quarter-pixel interpolation filter set is derived, as the network is easily interpretable due to its linear structure. A novel training framework enables each network branch to resemble a specific fractional shift. This practical solution makes it very efficient to use alongside conventional video coding schemes. When implemented in the context of the state-of-the-art Versatile Video Coding (VVC) test model, 0.77%, 1.27% and 2.25% BD-rate savings can be achieved on average for lower resolution sequences under the random access, low-delay B and low-delay P configurations, respectively, while the complexity of the learned interpolation schemes is significantly reduced compared to the interpolation with full CNNs.