arXiv subjects

Uditangshu Aurangabadkar

Publications and source records attributed to Uditangshu Aurangabadkar.

4 recordsLinked to original sources

arXiv2026

A Subjective Study on a New Sharpness Informed Class of Metrics

Perceptual loss functions in Deep Neural Network (DNN) deblurring architectures improve the overall quality of restored images. However, few focus on explicitly targeting sharpness in the restorations. We conduct a subjective study of models trained with and without losses which explicitly target sharpness using a four-protocol approach, exploring preferred sharpness levels and effects on image quality. We introduce a novel dataset of images with uniform sharpness increments along with Difference Mean Opinion Scores (DMOS). Additionally, we propose a novel class of Sharpness Informed (SI) Image Quality Assessment (IQA) metrics which properly penalize over-sharpening. Our new SI-PSNR metric outperforms all other PSNR variants in terms of correlation statistics on IQA benchmarking datasets. We show that, on average, images restored using a sharpness-aware composite loss are preferred in 67% of binarized comparisons, as opposed to losses that do not explicitly target sharpness.

eess.IV↗

arXiv2025

Impact of a Sharpness Based Loss Function for Removing Out-of-Focus Blur

Recent research has explored complex loss functions for deblurring. In this work, we explore the impact of a previously introduced loss function - Q which explicitly addresses sharpness and employ it to fine-tune State-of-the-Art (SOTA) deblurring models. Standard image quality metrics such as PSNR or SSIM do not distinguish sharpness from ringing. Therefore, we propose a novel full-reference image quality metric Omega that combines PSNR with Q. This metric is sensitive to ringing artefacts, but not to a slight increase in sharpness, thus making it a fair metric for comparing restorations from deblurring mechanisms. Our approach shows an increase of 15 percent in sharpness (Q) and up to 10 percent in Omega over the use of standard losses.

eess.IV↗

arXiv2024

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

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.

eess.IV↗

arXiv2024

A Dictionary Based Approach for Removing Out-of-Focus Blur

The field of image deblurring has seen tremendous progress with the rise of deep learning models. These models, albeit efficient, are computationally expensive and energy consuming. Dictionary based learning approaches have shown promising results in image denoising and Single Image Super-Resolution. We propose an extension of the Rapid and Accurate Image Super-Resolution (RAISR) algorithm introduced by Isidoro, Romano and Milanfar for the task of out-of-focus blur removal. We define a sharpness quality measure which aligns well with the perceptual quality of an image. A metric based blending strategy based on asset allocation management is also proposed. Our method demonstrates an average increase of approximately 13% (PSNR) and 10% (SSIM) compared to popular deblurring methods. Furthermore, our blending scheme curtails ringing artefacts post restoration.

eess.IV↗