Generative Joint Source-Channel Coding for Semantic Image Transmission

Recent works have shown that joint source-channel coding (JSCC) schemes using deep neural networks (DNNs), called DeepJSCC, provide promising results in wireless image transmission. However, these methods mostly focus on the distortion of the reconstructed signals with respect to the input image, ra...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE journal on selected areas in communications Jg. 41; H. 8; S. 2645 - 2657
Hauptverfasser: Erdemir, Ecenaz, Tung, Tze-Yang, Dragotti, Pier Luigi, Gunduz, Deniz
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 01.08.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Artificial neural networks
Channel coding
Coders
Compression ratio
Distortion
Generative adversarial networks
Generators
Image coding
Image reconstruction
Image transmission
Inverse problems
joint source-channel coding
Optimization
perceptual similarity
Semantic communication
Semantics
Signal to noise ratio
StyleGAN
Training
Wireless communication
ISSN:0733-8716, 1558-0008
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Recent works have shown that joint source-channel coding (JSCC) schemes using deep neural networks (DNNs), called DeepJSCC, provide promising results in wireless image transmission. However, these methods mostly focus on the distortion of the reconstructed signals with respect to the input image, rather than their perception by humans. However, focusing on traditional distortion metrics alone does not necessarily result in high perceptual quality, especially in extreme physical conditions, such as very low bandwidth compression ratio (BCR) and low signal-to-noise ratio (SNR) regimes. In this work, we propose two novel JSCC schemes that leverage the perceptual quality of deep generative models (DGMs) for wireless image transmission, namely InverseJSCC and GenerativeJSCC. While the former is an inverse problem approach to DeepJSCC, the latter is an end-to-end optimized JSCC scheme. In both, we optimize a weighted sum of mean squared error (MSE) and learned perceptual image patch similarity (LPIPS) losses, which capture more semantic similarities than other distortion metrics. InverseJSCC performs denoising on the distorted reconstructions of a DeepJSCC model by solving an inverse optimization problem using the pre-trained style-based generative adversarial network (StyleGAN). Our simulation results show that InverseJSCC significantly improves the state-of-the-art DeepJSCC in terms of perceptual quality in edge cases. In GenerativeJSCC, we carry out end-to-end training of an encoder and a StyleGAN-based decoder, and show that GenerativeJSCC significantly outperforms DeepJSCC both in terms of distortion and perceptual quality.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0733-8716
1558-0008
DOI:10.1109/JSAC.2023.3288243