Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2408.06014 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911983992832000 |
|---|---|
| author | Aurangabadkar, Uditangshu Ramsook, Darren Kokaram, Anil |
| author_facet | Aurangabadkar, Uditangshu Ramsook, Darren Kokaram, Anil |
| contents | The success of modern Deep Neural Network (DNN) approaches can be attributed to the use of complex optimization criteria beyond standard losses such as mean absolute error (MAE) or mean squared error (MSE). In this work, we propose a novel method of utilising a no-reference sharpness metric Q introduced by Zhu and Milanfar for removing out-of-focus blur from images. We also introduce a novel dataset of real-world out-of-focus images for assessing restoration models. Our fine-tuned method produces images with a 7.5 % increase in perceptual quality (LPIPS) as compared to a standard model trained only on MAE. Furthermore, we observe a 6.7 % increase in Q (reflecting sharper restorations) and 7.25 % increase in PSNR over most state-of-the-art (SOTA) methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_06014 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Sharpness Based Loss Function for Removing Out-of-Focus Blur Aurangabadkar, Uditangshu Ramsook, Darren Kokaram, Anil Image and Video Processing Computer Vision and Pattern Recognition The success of modern Deep Neural Network (DNN) approaches can be attributed to the use of complex optimization criteria beyond standard losses such as mean absolute error (MAE) or mean squared error (MSE). In this work, we propose a novel method of utilising a no-reference sharpness metric Q introduced by Zhu and Milanfar for removing out-of-focus blur from images. We also introduce a novel dataset of real-world out-of-focus images for assessing restoration models. Our fine-tuned method produces images with a 7.5 % increase in perceptual quality (LPIPS) as compared to a standard model trained only on MAE. Furthermore, we observe a 6.7 % increase in Q (reflecting sharper restorations) and 7.25 % increase in PSNR over most state-of-the-art (SOTA) methods. |
| title | A Sharpness Based Loss Function for Removing Out-of-Focus Blur |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.06014 |