Comparing deep learning models for low-light natural scene image enhancement and their impact on object detection and classification: Overview, empirical …

R Al Sobbahi, J Tekli - Signal Processing: Image Communication, 2022 - Elsevier
Low-light image (LLI) enhancement is an important image processing task that aims at
improving the illumination of images taken under low-light conditions. Recently, a …

From heuristic optimization to dictionary learning: A review and comprehensive comparison of image denoising algorithms

L Shao, R Yan, X Li, Y Liu - IEEE transactions on cybernetics, 2013 - ieeexplore.ieee.org
Image denoising is a well explored topic in the field of image processing. In the past several
decades, the progress made in image denoising has benefited from the improved modeling …

Image blind denoising with generative adversarial network based noise modeling

J Chen, J Chen, H Chao… - Proceedings of the IEEE …, 2018 - openaccess.thecvf.com
In this paper, we consider a typical image blind denoising problem, which is to remove
unknown noise from noisy images. As we all know, discriminative learning based methods …

High-resolution MRI synthesis using a data-driven framework with denoising diffusion probabilistic modeling

CW Chang, J Peng, M Safari, E Salari… - Physics in Medicine …, 2024 - iopscience.iop.org
Objective. High-resolution magnetic resonance imaging (MRI) can enhance lesion
diagnosis, prognosis, and delineation. However, gradient power and hardware limitations …

Hybrid no-reference quality metric for singly and multiply distorted images

K Gu, G Zhai, X Yang, W Zhang - IEEE Transactions on …, 2014 - ieeexplore.ieee.org
In a typical image communication system, the visual signal presented to the end users may
undergo the steps of acquisition, compression and transmission which cause the artifacts of …

TRQ3DNet: A 3D quasi-recurrent and transformer based network for hyperspectral image denoising

L Pang, W Gu, X Cao - Remote Sensing, 2022 - mdpi.com
We propose a new deep neural network termed TRQ3DNet which combines convolutional
neural network (CNN) and transformer for hyperspectral image (HSI) denoising. The network …

Complexity classes in communication complexity theory

L Babai, P Frankl, J Simon - 27th Annual Symposium on …, 1986 - ieeexplore.ieee.org
We take a complexity theoretic view of AC Yao's theory of communication complexity. A rich
structure of natural complexity classes is introduced. Besides providing a more structured …

No-reference image and video quality assessment: a classification and review of recent approaches

M Shahid, A Rossholm, B Lövström… - EURASIP Journal on …, 2014 - Springer
The field of perceptual quality assessment has gone through a wide range of developments
and it is still growing. In particular, the area of no-reference (NR) image and video quality …

Optimal co-clinical radiomics: Sensitivity of radiomic features to tumour volume, image noise and resolution in co-clinical T1-weighted and T2-weighted magnetic …

S Roy, TD Whitehead, JD Quirk, A Salter… - …, 2020 - thelancet.com
Background Radiomics analyses has been proposed to interrogate the biology of tumour as
well as to predict/assess response to therapy in vivo. The objective of this work was to …

Exposing region splicing forgeries with blind local noise estimation

S Lyu, X Pan, X Zhang - International journal of computer vision, 2014 - Springer
Region splicing is a simple and common digital image tampering operation, where a chosen
region from one image is composited into another image with the aim to modify the original …