Generative Joint Source-Channel Coding for Semantic Image Transmission
Top Cited Papers
- 21 June 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Communications
- Vol. 41 (8) , 2645-2657
Abstract
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.Keywords
All Related Versions
Funding Information
- UKRI through the projects AIR (EP/X030806/1)
This publication has 28 references indexed in Scilit:
- Risk-Aware Resource Allocation for URLLC: Challenges and Strategies with Machine LearningIEEE Communications Magazine, 2019
- 5G URLLC: Design Challenges and System Concepts2018
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- A deep learning approach to structured signal recovery2015
- Lossy Joint Source-Channel Coding in the Finite Blocklength RegimeIEEE Transactions on Information Theory, 2013
- Compressed sensingIEEE Transactions on Information Theory, 2006
- Multiscale structural similarity for image quality assessment2004
- The JPEG2000 still image coding system: an overviewIEEE Transactions on Consumer Electronics, 2000
- Low-density parity-check codesIEEE Transactions on Information Theory, 1962
- A Mathematical Theory of CommunicationBell System Technical Journal, 1948