IVCVAug 12, 2024

A Sharpness Based Loss Function for Removing Out-of-Focus Blur

arXiv:2408.06014v14 citationsh-index: 4
Originality Incremental advance
AI Analysis

This addresses image restoration for photography or vision applications, but it is incremental as it builds on existing sharpness metrics and datasets.

The paper tackles the problem of removing out-of-focus blur from images by proposing a sharpness-based loss function, resulting in a 7.5% increase in perceptual quality, a 6.7% increase in sharpness, and a 7.25% increase in PSNR over state-of-the-art methods.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes