Affordable Access

deepdyve-link
Publisher Website

Iterative Training of Neural Networks for Intra Prediction.

Authors
  • Dumas, Thierry
  • Galpin, Franck
  • Bordes, Philippe
Type
Published Article
Journal
IEEE Transactions on Image Processing
Publisher
Institute of Electrical and Electronics Engineers
Publication Date
Jan 01, 2021
Volume
30
Pages
697–711
Identifiers
DOI: 10.1109/TIP.2020.3038348
PMID: 33226940
Source
Medline
Language
English
License
Unknown

Abstract

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 BD-rate reduction is obtained, i.e. -1.8% above the state-of-the-art. By moving them into H.266 (VTM-5.0), the mean BD-rate reduction reaches -1.9%.

Report this publication

Statistics

Seen <100 times