The Library
Graph-based transforms based on graph neural networks for predictive transform coding
Tools
Tools
Tools
Roy, Debaleena, Guha, Tanaya and Sanchez Silva, Victor (2021) Graph-based transforms based on graph neural networks for predictive transform coding. In: Data Compression Conference (DCC) 2021, Snowbird, UT, USA, 23-26 Mar 2021. Published in: 2021 Data Compression Conference (DCC) doi:10.1109/DCC50243.2021.00079 ISSN 2375-0359.
|
PDF (Poster presentation)
WRAP-Poster-presentation-2021.pdf - Other - Requires a PDF viewer. Download (358Kb) | Preview |
Official URL: https://doi.org/10.1109/DCC50243.2021.00079
Abstract
This paper introduces the GBT-NN, a novel class of Graph-based Transform within the context of block-based predictive transform coding using intra-prediction. The GBT-NN is constructed by learning a mapping function to map a graph Laplacian representing the covariance matrix of the current block. Our objective of learning such a mapping function is to design a GBT that performs as well as the KLT without requiring to explicitly compute the covariance matrix for each residual block to be transformed. To avoid signalling any additional information required to compute the inverse GBT-NN, we also introduce a coding framework that uses a template-based prediction to predict residuals at the decoder. Evaluation results on several video frames and medical images, in terms of the percentage of preserved energy and mean square error, show that the GBT-NN can outperform the DST and DCT.
| Item Type: | Conference Item (Poster) | ||||||
|---|---|---|---|---|---|---|---|
| Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science | ||||||
| Journal or Publication Title: | 2021 Data Compression Conference (DCC) | ||||||
| Publisher: | IEEE | ||||||
| ISSN: | 2375-0359 | ||||||
| Official Date: | 10 May 2021 | ||||||
| Dates: |
|
||||||
| DOI: | 10.1109/DCC50243.2021.00079 | ||||||
| Status: | Peer Reviewed | ||||||
| Publication Status: | Published | ||||||
| Access rights to Published version: | Restricted or Subscription Access | ||||||
| Is Part Of: | 1 | ||||||
| Conference Paper Type: | Poster | ||||||
| Title of Event: | Data Compression Conference (DCC) 2021 | ||||||
| Type of Event: | Conference | ||||||
| Location of Event: | Snowbird, UT, USA | ||||||
| Date(s) of Event: | 23-26 Mar 2021 |
Request changes or add full text files to a record
Repository staff actions (login required)
 |
View Item |
