Roy, D., Guha, T. and Sanchez, V. (2022) Graph-based Transform based on 3D Convolutional Neural Network for Intra-Prediction of Imaging Data. In: 2022 Data Compression Conference (DCC), Snowbird, UT, USA, 22-25 March 2022, pp. 212-221. ISBN 9781665478939 (doi: 10.1109/DCC52660.2022.00029)
Text
276562.pdf - Accepted Version 1MB |
Abstract
This paper presents a novel class of Graph-based Transform based on 3D convolutional neural networks (GBT-CNN) within the context of block-based predictive transform coding of imaging data. The proposed GBT-CNN uses a 3D convolutional neural network (3D-CNN) to predict the graph information needed to compute the transform and its inverse, thus reducing the signalling cost to reconstruct the data after transformation. The GBT-CNN outperforms the DCT and DCT /DST, which are commonly employed in current video codecs, in terms of the percentage of energy preserved by a subset of transform coefficients, the mean squared error of the reconstructed data, and the transform coding gain according to evaluations on several video frames and medical images.
Item Type: | Conference Proceedings |
---|---|
Status: | Published |
Refereed: | Yes |
Glasgow Author(s) Enlighten ID: | Guha, Dr Tanaya |
Authors: | Roy, D., Guha, T., and Sanchez, V. |
College/School: | College of Science and Engineering > School of Computing Science |
ISSN: | 2375-0359 |
ISBN: | 9781665478939 |
Published Online: | 04 July 2022 |
Copyright Holders: | Copyright © 2022 IEEE |
Publisher Policy: | Reproduced in accordance with the publisher copyright policy |
Related URLs: |
University Staff: Request a correction | Enlighten Editors: Update this record