Combined Neural Network-based Intra Prediction and Transform Selection

The interactions between different tools added successively to a block-based video codec are critical to its ratedistortion efficiency. In particular, when deep neural network-based intra prediction modes are inserted into a block-based video codec, as the neural network-based prediction function ca...

Full description

Saved in:
Bibliographic Details
Published in2021 Picture Coding Symposium (PCS) pp. 1 - 5
Main Authors Dumas, Thierry, Galpin, Franck, Bordes, Philippe
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2021
Subjects
Correlation
intra prediction
Neural networks
Predictive models
Rate-distortion
Transform signaling
Transforms
Versatile Video Coding
Video coding
Online AccessGet full text

Cover

More Information
Summary:The interactions between different tools added successively to a block-based video codec are critical to its ratedistortion efficiency. In particular, when deep neural network-based intra prediction modes are inserted into a block-based video codec, as the neural network-based prediction function cannot be easily characterized, the adaptation of the transform selection process to the new modes can hardly be performed manually. That is why this paper presents a combined neural network-based intra prediction and transform selection for a block-based video codec. When putting a single neural network-based intra prediction mode and the learned prediction of the selected LFNST pair index into VTM-8.0, -3.71%, -3.17%, and -3.37% of mean BD-rate reduction in all-intra is obtained.
ISSN:2472-7822
DOI:10.1109/PCS50896.2021.9477455