RWZC: A Model-Driven Approach for Learning-based Robust Wyner-Ziv Coding
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929698651504640 |
|---|---|
| author | Shi, Yuxuan Shao, Shuo Wu, Yongpeng Zhang, Wenjun Debbah, Merouane |
| author_facet | Shi, Yuxuan Shao, Shuo Wu, Yongpeng Zhang, Wenjun Debbah, Merouane |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_09520 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RWZC: A Model-Driven Approach for Learning-based Robust Wyner-Ziv Coding Shi, Yuxuan Shao, Shuo Wu, Yongpeng Zhang, Wenjun Debbah, Merouane Information Theory 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. |
| title | RWZC: A Model-Driven Approach for Learning-based Robust Wyner-Ziv Coding |
| topic | Information Theory |
| url | https://arxiv.org/abs/2501.09520 |