RT-Focuser: A Real-Time Lightweight Model for Edge-side Image Deblurring
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_ | 1866915694787952640 |
|---|---|
| author | Wu, Zhuoyu Ou, Wenhui Zheng, Qiawei Yang, Jiayan Wang, Quanjun Fang, Wenqi Wang, Zheng Yang, Yongkui Li, Heshan |
| author_facet | Wu, Zhuoyu Ou, Wenhui Zheng, Qiawei Yang, Jiayan Wang, Quanjun Fang, Wenqi Wang, Zheng Yang, Yongkui Li, Heshan |
| contents | Motion blur caused by camera or object movement severely degrades image quality and poses challenges for real-time applications such as autonomous driving, UAV perception, and medical imaging. In this paper, a lightweight U-shaped network tailored for real-time deblurring is presented and named RT-Focuser. To balance speed and accuracy, we design three key components: Lightweight Deblurring Block (LD) for edge-aware feature extraction, Multi-Level Integrated Aggregation module (MLIA) for encoder integration, and Cross-source Fusion Block (X-Fuse) for progressive decoder refinement. Trained on a single blurred input, RT-Focuser achieves 30.67 dB PSNR with only 5.85M parameters and 15.76 GMACs. It runs 6ms per frame on GPU and mobile, exceeds 140 FPS on both, showing strong potential for deployment on the edge. The official code and usage are available on: https://github.com/ReaganWu/RT-Focuser. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_21975 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RT-Focuser: A Real-Time Lightweight Model for Edge-side Image Deblurring Wu, Zhuoyu Ou, Wenhui Zheng, Qiawei Yang, Jiayan Wang, Quanjun Fang, Wenqi Wang, Zheng Yang, Yongkui Li, Heshan Image and Video Processing Computer Vision and Pattern Recognition Motion blur caused by camera or object movement severely degrades image quality and poses challenges for real-time applications such as autonomous driving, UAV perception, and medical imaging. In this paper, a lightweight U-shaped network tailored for real-time deblurring is presented and named RT-Focuser. To balance speed and accuracy, we design three key components: Lightweight Deblurring Block (LD) for edge-aware feature extraction, Multi-Level Integrated Aggregation module (MLIA) for encoder integration, and Cross-source Fusion Block (X-Fuse) for progressive decoder refinement. Trained on a single blurred input, RT-Focuser achieves 30.67 dB PSNR with only 5.85M parameters and 15.76 GMACs. It runs 6ms per frame on GPU and mobile, exceeds 140 FPS on both, showing strong potential for deployment on the edge. The official code and usage are available on: https://github.com/ReaganWu/RT-Focuser. |
| title | RT-Focuser: A Real-Time Lightweight Model for Edge-side Image Deblurring |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.21975 |