Robust Deep Joint Source-Channel Coding for Video Transmission over Multipath Fading Channel

TL;DR

This work addresses the challenge of reliable video transmission over multipath fading channels by proposing a robust DeepJSCC framework that integrates OFDM modulation, conditional context coding with multi-scale Gaussian warped features, and a lightweight denoising-based decoder. The architecture splits video frames into key-frame and interpolation-frame paths, leveraging reference-frame contexts and scale-space warping to efficiently exploit temporal redundancy under strict bandwidth constraints. A denoising-aided decoding strategy decouples channel estimation from semantic reconstruction, accelerating convergence and improving reconstruction quality. Empirical results show significant gains over existing DeepJSCC approaches in fading environments (e.g., an average improvement of 5.13 dB in reconstruction quality) and demonstrate favorable complexity and convergence properties, highlighting practical impact for robust, bandwidth-efficient wireless video delivery in future networks.

Abstract

To address the challenges of wireless video transmission over multipath fading channels, we propose a robust deep joint source-channel coding (DeepJSCC) framework by effectively exploiting temporal redundancy and incorporating robust innovations at the modulation, coding, and decoding stages. At the modulation stage, tailored orthogonal frequency division multiplexing (OFDM) for robust video transmission is employed, decomposing wideband signals into orthogonal frequency-flat sub-channels to effectively mitigate frequency-selective fading. At the coding stage, conditional contextual coding with multi-scale Gaussian warped features is introduced to efficiently model temporal redundancy, significantly improving reconstruction quality under strict bandwidth constraints. At the decoding stage, a lightweight denoising module is integrated to robustly simplify signal restoration and accelerate convergence, addressing the suboptimality and slow convergence typically associated with simultaneously performing channel estimation, equalization, and semantic reconstruction. Experimental results demonstrate that the proposed robust framework significantly outperforms state-of-the-art video DeepJSCC methods, achieving an average reconstruction quality gain of 5.13 dB under challenging multipath fading channel conditions.

Figures (6)

• Figure 1: Architecture of the proposed robust OFDM-based DeepJSCC framework for video transmission. It consists of two parallel coding paths: key-frame and interpolation-frame codecs. Dashed lines indicate reference frame inputs for interpolation coding and reconstruction.
• Figure 2: Architecture of the interpolation network. Scale-space volume $\bar{\mathbf{X}}_{i\pm t}$ generated via Gaussian smoothing provides multi-scale features, warped by SSF $\boldsymbol{\delta}_{i\pm t}$ to obtain robust contextual conditions $\mathbf{c}_{i\pm t}$. The dashed lines at the decoding end indicate the same generation process of $\bar{\mathbf{X}}_{i\pm t}$ as that at the encoding end.
• Figure 3: Architecture of the denoising module $f_{denoise}$.
• Figure 4: MSE loss curves, validating that the denoising module accelerates convergence.
• Figure 5: PSNR comparison of the proposed framework to the baseline and its ablated variants.