Title | ||
---|---|---|
Graph Based Transforms based on Graph Neural Networks for Predictive Transform Coding |
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 with... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/DCC50243.2021.00079 | 2021 Data Compression Conference (DCC) |
Keywords | DocType | ISSN |
Laplace equations,Transform coding,Transforms,Mean square error methods,Artificial neural networks,Graph neural networks,Decoding | Conference | 1068-0314 |
ISBN | Citations | PageRank |
978-1-6654-0333-7 | 1 | 0.37 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Debaleena Roy | 1 | 5 | 1.83 |
Tanaya Guha | 2 | 4 | 3.83 |
Victor Sanchez | 3 | 144 | 31.22 |