DPMambaIR: All-in-One Image Restoration via Degradation-Aware Prompt State Space Model
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910012414099456 |
|---|---|
| author | Liu, Zhanwen Zhou, Sai Dai, Yuchao Wang, Yang An, Yisheng Zhao, Xiangmo |
| author_facet | Liu, Zhanwen Zhou, Sai Dai, Yuchao Wang, Yang An, Yisheng Zhao, Xiangmo |
| contents | All-in-One image restoration aims to address multiple image degradation problems using a single model, offering a more practical and versatile solution compared to designing dedicated models for each degradation type. Existing approaches typically rely on Degradation-specific models or coarse-grained degradation prompts to guide image restoration. However, they lack fine-grained modeling of degradation information and face limitations in balancing multi-task conflicts. To overcome these limitations, we propose DPMambaIR, a novel All-in-One image restoration framework that introduces a fine-grained degradation extractor and a Degradation-Aware Prompt State Space Model (DP-SSM). The DP-SSM leverages the fine-grained degradation features captured by the extractor as dynamic prompts, which are then incorporated into the state space modeling process. This enhances the model's adaptability to diverse degradation types, while a complementary High-Frequency Enhancement Block (HEB) recovers local high-frequency details. Extensive experiments on a mixed dataset containing seven degradation types show that DPMambaIR achieves the best performance, with 27.69dB and 0.893 in PSNR and SSIM, respectively. These results highlight the potential and superiority of DPMambaIR as a unified solution for All-in-One image restoration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_17732 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DPMambaIR: All-in-One Image Restoration via Degradation-Aware Prompt State Space Model Liu, Zhanwen Zhou, Sai Dai, Yuchao Wang, Yang An, Yisheng Zhao, Xiangmo Computer Vision and Pattern Recognition I.4.4 All-in-One image restoration aims to address multiple image degradation problems using a single model, offering a more practical and versatile solution compared to designing dedicated models for each degradation type. Existing approaches typically rely on Degradation-specific models or coarse-grained degradation prompts to guide image restoration. However, they lack fine-grained modeling of degradation information and face limitations in balancing multi-task conflicts. To overcome these limitations, we propose DPMambaIR, a novel All-in-One image restoration framework that introduces a fine-grained degradation extractor and a Degradation-Aware Prompt State Space Model (DP-SSM). The DP-SSM leverages the fine-grained degradation features captured by the extractor as dynamic prompts, which are then incorporated into the state space modeling process. This enhances the model's adaptability to diverse degradation types, while a complementary High-Frequency Enhancement Block (HEB) recovers local high-frequency details. Extensive experiments on a mixed dataset containing seven degradation types show that DPMambaIR achieves the best performance, with 27.69dB and 0.893 in PSNR and SSIM, respectively. These results highlight the potential and superiority of DPMambaIR as a unified solution for All-in-One image restoration. |
| title | DPMambaIR: All-in-One Image Restoration via Degradation-Aware Prompt State Space Model |
| topic | Computer Vision and Pattern Recognition I.4.4 |
| url | https://arxiv.org/abs/2504.17732 |