Sorry, you need to enable JavaScript to visit this website.

Graph Based Transforms based on Graph Neural Networks for Predictive Transform Coding

Citation Author(s):
Debaleena Roy, Tanaya Guha, Victor Sanchez
Submitted by:
Debaleena Roy
Last updated:
1 March 2021 - 6:40pm
Document Type:
Poster
Document Year:
2021
Event:
Presenters Name:
Debaleena Roy
Paper Code:
188

Abstract 

Abstract: 

This paper introduces the GBT-NN, a novel class of Graph-based Transform within thecontext of block-based predictive transform coding using intra-prediction. The GBT-NNis constructed by learning a mapping function to map a graph Laplacian representing thecovariance matrix of the current block. Our objective of learning such a mapping functionis to design a GBT that performs as well as the KLT without requiring to explicitly com-pute the covariance matrix for each residual block to be transformed. To avoid signallingany additional information required to compute the inverse GBT-NN, we also introduce acoding 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 percentageof preserved energy and mean square error, show that the GBT-NN can outperform theDST and DCT.

up
0 users have voted:

Comments

Thanks for watching !

Dataset Files

GBT-NN_Debaleena_Roy_DCC2021

(62)