# Iterative training of neural networks for intra prediction

arXiv: https://arxiv.org/abs/2003.06812 · HTML: https://mlsanity.com/paper/2003.06812/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Mar 2020.

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

- [Compressing Sign Information in DCT-based Image Coding via Deep Sign Retrieval](https://mlsanity.com/paper/2209.10712/) (2022)
- [Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimization](https://mlsanity.com/paper/2405.14221/) (2024)
- [Deep Learning-Based Intra Mode Derivation for Versatile Video Coding](https://mlsanity.com/paper/2204.04059/) (2022)
- [Joint Reference Frame Synthesis and Post Filter Enhancement for Versatile Video Coding](https://mlsanity.com/paper/2404.18058/) (2024)
- [Neural Network based Inter bi-prediction Blending](https://mlsanity.com/paper/2202.03149/) (2022)

## Abstract (arXiv)

This paper presents an iterative training of neural networks for intra prediction in a block-based image and video codec. First, the neural networks are trained on blocks arising from the codec partitioning of images, each paired with its context. Then, iteratively, blocks are collected from the partitioning of images via the codec including the neural networks trained at the previous iteration, each paired with its context, and the neural networks are retrained on the new pairs. Thanks to this training, the neural networks can learn intra prediction functions that both stand out from those already in the initial codec and boost the codec in terms of rate-distortion. Moreover, the iterative process allows the design of training data cleansings essential for the neural network training. When the iteratively trained neural networks are put into H.265 (HM-16.15), -4.2% of mean dB-rate reduction is obtained. By moving them into H.266 (VTM-5.0), the mean dB-rate reduction reaches -1.9%.