Blind Image Deblurring with FFT-ReLU Sparsity Prior
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916410477772800 |
|---|---|
| author | Radi, Abdul Mohaimen Al Majumder, Prothito Shovon Khan, Md. Mosaddek |
| author_facet | Radi, Abdul Mohaimen Al Majumder, Prothito Shovon Khan, Md. Mosaddek |
| contents | Blind image deblurring is the process of recovering a sharp image from a blurred one without prior knowledge about the blur kernel. It is a small data problem, since the key challenge lies in estimating the unknown degrees of blur from a single image or limited data, instead of learning from large datasets. The solution depends heavily on developing algorithms that effectively model the image degradation process. We introduce a method that leverages a prior which targets the blur kernel to achieve effective deblurring across a wide range of image types. In our extensive empirical analysis, our algorithm achieves results that are competitive with the state-of-the-art blind image deblurring algorithms, and it offers up to two times faster inference, making it a highly efficient solution. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_08344 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Blind Image Deblurring with FFT-ReLU Sparsity Prior Radi, Abdul Mohaimen Al Majumder, Prothito Shovon Khan, Md. Mosaddek Computer Vision and Pattern Recognition Blind image deblurring is the process of recovering a sharp image from a blurred one without prior knowledge about the blur kernel. It is a small data problem, since the key challenge lies in estimating the unknown degrees of blur from a single image or limited data, instead of learning from large datasets. The solution depends heavily on developing algorithms that effectively model the image degradation process. We introduce a method that leverages a prior which targets the blur kernel to achieve effective deblurring across a wide range of image types. In our extensive empirical analysis, our algorithm achieves results that are competitive with the state-of-the-art blind image deblurring algorithms, and it offers up to two times faster inference, making it a highly efficient solution. |
| title | Blind Image Deblurring with FFT-ReLU Sparsity Prior |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.08344 |