Learned Image Transmission with Hierarchical Variational Autoencoder

TL;DR

This paper presents a hierarchical variational autoencoder framework for image transmission that improves rate-distortion performance and robustness over noisy channels by adaptively encoding multiple hierarchical representations.

Contribution

It introduces a novel hierarchical joint source-channel coding framework with feedback modeling, enhancing adaptability and performance in image transmission.

Findings

Outperforms existing methods in rate-distortion metrics

Demonstrates robustness against channel noise

Enables dynamic adjustment of transmission bandwidth

Abstract

In this paper, we introduce an innovative hierarchical joint source-channel coding (HJSCC) framework for image transmission, utilizing a hierarchical variational autoencoder (VAE). Our approach leverages a combination of bottom-up and top-down paths at the transmitter to autoregressively generate multiple hierarchical representations of the original image. These representations are then directly mapped to channel symbols for transmission by the JSCC encoder. We extend this framework to scenarios with a feedback link, modeling transmission over a noisy channel as a probabilistic sampling process and deriving a novel generative formulation for JSCC with feedback. Compared with existing approaches, our proposed HJSCC provides enhanced adaptability by dynamically adjusting transmission bandwidth, encoding these representations into varying amounts of channel symbols. Extensive experiments on images of varying resolutions demonstrate that our proposed model outperforms existing baselines in rate-distortion performance and maintains robustness against channel noise. The source code will be made available upon acceptance.