Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913939507380224 |
|---|---|
| author | Guo, Jinpei Chen, Zheng Li, Wenbo Guo, Yong Zhang, Yulun |
| author_facet | Guo, Jinpei Chen, Zheng Li, Wenbo Guo, Yong Zhang, Yulun |
| contents | Diffusion models have demonstrated remarkable success in image restoration tasks. However, their multi-step denoising process introduces significant computational overhead, limiting their practical deployment. Furthermore, existing methods struggle to effectively remove severe JPEG artifact, especially in highly compressed images. To address these challenges, we propose CODiff, a compression-aware one-step diffusion model for JPEG artifact removal. The core of CODiff is the compression-aware visual embedder (CaVE), which extracts and leverages JPEG compression priors to guide the diffusion model. We propose a dual learning strategy that combines explicit and implicit learning. Specifically, explicit learning enforces a quality prediction objective to differentiate low-quality images with different compression levels. Implicit learning employs a reconstruction objective that enhances the model's generalization. This dual learning allows for a deeper and more comprehensive understanding of JPEG compression. Experimental results demonstrate that CODiff surpasses recent leading methods in both quantitative and visual quality metrics. The code is released at https://github.com/jp-guo/CODiff. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_09873 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal Guo, Jinpei Chen, Zheng Li, Wenbo Guo, Yong Zhang, Yulun Computer Vision and Pattern Recognition Diffusion models have demonstrated remarkable success in image restoration tasks. However, their multi-step denoising process introduces significant computational overhead, limiting their practical deployment. Furthermore, existing methods struggle to effectively remove severe JPEG artifact, especially in highly compressed images. To address these challenges, we propose CODiff, a compression-aware one-step diffusion model for JPEG artifact removal. The core of CODiff is the compression-aware visual embedder (CaVE), which extracts and leverages JPEG compression priors to guide the diffusion model. We propose a dual learning strategy that combines explicit and implicit learning. Specifically, explicit learning enforces a quality prediction objective to differentiate low-quality images with different compression levels. Implicit learning employs a reconstruction objective that enhances the model's generalization. This dual learning allows for a deeper and more comprehensive understanding of JPEG compression. Experimental results demonstrate that CODiff surpasses recent leading methods in both quantitative and visual quality metrics. The code is released at https://github.com/jp-guo/CODiff. |
| title | Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.09873 |