Multi-Reference and Adaptive Nonlinear Transform Source-Channel Coding for Wireless Image Semantic Transmission

TL;DR

This paper introduces MA-NTSCC, a novel adaptive nonlinear transform source-channel coding system that significantly improves wireless image transmission quality and efficiency by leveraging multi-dimensional context-aware entropy modeling.

Contribution

The paper presents a multi-reference, adaptive entropy model for nonlinear transform coding, enhancing rate-distortion performance and robustness across various channel conditions in wireless image transmission.

Findings

Achieves higher PSNR in high-resolution image transmission under low bandwidth.

Demonstrates superior adaptability to different channel conditions compared to traditional models.

Provides efficient bandwidth allocation through mutual information-based entropy estimation.

Abstract

We propose a multi-reference and adaptive nonlinear transform source-channel coding (MA-NTSCC) system for wireless image semantic transmission to improve rate-distortion (RD) performance by introducing multi-dimensional contexts into the entropy model of the state-of-the-art (SOTA) NTSCC system. Improvements in RD performance of the proposed MA-NTSCC system are particularly significant in high-resolution image transmission under low bandwidth constraints. The proposed multi-reference entropy model leverages correlations within the latent representation in both spatial and channel dimensions. In the spatial dimension, the latent representation is divided into anchors and non-anchors in a checkerboard pattern, where anchors serve as reference to estimate the mutual information between anchors and non-anchors. In the channel dimension, the latent representation is partitioned into multiple groups, and features in previous groups are analyzed to estimate the mutual information between features in previous and current groups. Taking mutual information into account, the entropy model provides an accurate estimation on the entropy, which enables efficient bandwidth allocation and enhances RD performance. Additionally, the proposed lightweight adaptation modules enable the proposed MA-NTSCC model to achieve transmission quality comparable to separately trained models across various channel conditions and bandwidth requirements. In contrast, traditional NTSCC models provide signal-to-noise ratio (SNR)-distortion performance degrading with channel quality deviating from the fixed training SNR, and consume inflexible bandwidth to transmit an image. Comprehensive experiments are conducted to verify the peak signal-to-noise ratio (PSNR) performance and adaptability of the proposed MA-NTSCC model superior to SOTA methods over both additive white Gaussian noise channel and Rayleigh fading channel.