RWZC: A Model-Driven Approach for Learning-based Robust Wyner-Ziv Coding

TL;DR

This paper introduces RWZC, a robust, learnable Wyner-Ziv coding framework for distributed image transmission that adapts to non-stationary source correlations, improving image quality and perceptual metrics.

Contribution

It proposes a novel model-driven, learning-based approach that models affine relationships for robust, rate-adaptive coding under non-stationary correlations, outperforming existing methods.

Findings

Achieves 1.5 dB PSNR gain over state-of-the-art.

Improves MS-SSIM by 0.2 points.

Shows superior perceptual quality on real-world samples.

Abstract

In this paper, a novel learning-based Wyner-Ziv coding framework is considered under a distributed image transmission scenario, where the correlated source is only available at the receiver. Unlike other learnable frameworks, our approach demonstrates robustness to non-stationary source correlation, where the overlapping information between image pairs varies. Specifically, we first model the affine relationship between correlated images and leverage this model for learnable mask generation and rate-adaptive joint source-channel coding. Moreover, we also provide a warping-prediction network to remove the distortion from channel interference and affine transform. Intuitively, the observed performance improvement is largely due to focusing on the simple geometric relationship, rather than the complex joint distribution between the sources. Numerical results show that our framework achieves a 1.5 dB gain in PSNR and a 0.2 improvement in MS-SSIM, along with a significant superiority in perceptual metrics, compared to state-of-the-art methods when applied to real-world samples with non-stationary correlations.