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

Graph-based Transform based on 3D Convolutional Neural Network for Intra-Prediction of Imaging Data

Citation Author(s):
Debaleena Roy, Tanaya Guha, Victor Sanchez Silva
Submitted by:
Debaleena Roy
Last updated:
5 March 2022 - 5:07pm
Document Type:
Presentation Slides
Document Year:
2022
Event:
Presenters:
Debaleena Roy
Paper Code:
DCC-197

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.

up
1 user has voted: Debaleena Roy

Files

Presentation Slides

(57)