Diffusion-OAMP for Joint Image Compression and Wireless Transmission
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914521215401984 |
|---|---|
| author | Hou, Wentao Bai, Yimin Luo, Zelei Hong, Jiadong Liu, Lei |
| author_facet | Hou, Wentao Bai, Yimin Luo, Zelei Hong, Jiadong Liu, Lei |
| contents | Joint image compression and wireless transmission remain relatively underexplored compared to generic image restoration, despite its importance in practical communication systems. We formulate this problem under an equivalent linear model, and propose Diffusion-OAMP, a training-free reconstruction framework that embeds a pre-trained diffusion model into the OAMP algorithm. In Diffusion-OAMP, the OAMP linear estimator produces pseudo-AWGN observations, while the diffusion model serves as a nonlinear estimator under an SNR-matching rule. This framework offers a way to incorporate multiple generative priors into OAMP. Experiments with varying compression ratios and noise levels show that Diffusion-OAMP performs favorably against classic methods in the evaluated settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_27952 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Diffusion-OAMP for Joint Image Compression and Wireless Transmission Hou, Wentao Bai, Yimin Luo, Zelei Hong, Jiadong Liu, Lei Image and Video Processing Information Theory Machine Learning Joint image compression and wireless transmission remain relatively underexplored compared to generic image restoration, despite its importance in practical communication systems. We formulate this problem under an equivalent linear model, and propose Diffusion-OAMP, a training-free reconstruction framework that embeds a pre-trained diffusion model into the OAMP algorithm. In Diffusion-OAMP, the OAMP linear estimator produces pseudo-AWGN observations, while the diffusion model serves as a nonlinear estimator under an SNR-matching rule. This framework offers a way to incorporate multiple generative priors into OAMP. Experiments with varying compression ratios and noise levels show that Diffusion-OAMP performs favorably against classic methods in the evaluated settings. |
| title | Diffusion-OAMP for Joint Image Compression and Wireless Transmission |
| topic | Image and Video Processing Information Theory Machine Learning |
| url | https://arxiv.org/abs/2604.27952 |