paper-with-me

홈 › Papers

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

2024-08-12 · Uditangshu Aurangabadkar, Darren Ramsook, Anil Kokaram

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.

📄 PDF Abstract BibTeX arXiv:2408.06014

Code (1)

aurangau/mmsp2024 공식 구현 tf

Methods 이 논문이 사용한 방법론

MAE 설명 없음

Similar Papers 제목 키워드 기반

A Subjective Study on a New Sharpness Informed Class of Metrics

2026-08-14 · Uditangshu Aurangabadkar, Vibhoothi Vibhoothi, Darren Ramsook, Anil Kokaram arxiv

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 subje…

Image Quality Assessment

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

2024-06-17 · Uditangshu Aurangabadkar, Anil Kokaram

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 h…

DeblurringDenoisingImage DeblurringImage Denoising+4

Reference-based Motion Blur Removal: Learning to Utilize Sharpness in the Reference Image

2023-07-06 · Han Zou, Masanori Suganuma, Takayuki Okatani

Despite the recent advancement in the study of removing motion blur in an image, it is still hard to deal with strong blurs. While there are limits in removing blurs from a single image, it has more potential to use mult…

DeblurringImage DeblurringSingle Image DeblurringVideo Deblurring

Clean Images are Hard to Reblur: Exploiting the Ill-Posed Inverse Task for Dynamic Scene Deblurring

2021-04-26 · ICLR 2022 4 · Seungjun Nah, Sanghyun Son, Jaerin Lee, Kyoung Mu Lee

The goal of dynamic scene deblurring is to remove the motion blur in a given image. Typical learning-based approaches implement their solutions by minimizing the L1 or L2 distance between the output and the reference sha…

Deblurring

Adaptive Window Pruning for Efficient Local Motion Deblurring

2023-06-25 · Haoying Li, Jixin Zhao, Shangchen Zhou, Huajun Feng 외

Local motion blur commonly occurs in real-world photography due to the mixing between moving objects and stationary backgrounds during exposure. Existing image deblurring methods predominantly focus on global deblurring,…

DeblurringImage Deblurring