Denoising low-light images is a challenging task due to the high noise level. When the illumination is low, digital cameras increase the ISO (electronic gain) to amplify the brightness of captured data. However, this in turn amplifies the noise, arising from read, shot, and defective pixel sources. In the raw domain, read and shot noise are effectively modeled using Gaussian and Poisson distributions respectively, whereas defective pixels can be modeled with impulsive noise. In low-light imaging, noise removal becomes a critical challenge to produce a high-quality, detailed image with low noise. for this task, we use a residual neural network for image denoising based on the densely connected hierarchical network. The encoding and decoding layers of the network consist of connected convolutional layers to reuse the feature maps and local residual learning to avoid the vanishing gradient problem and speed up the learning process. Moreover, global residual learning is adapted such that, instead of directly predicting the denoised image, the model predicts the residual noise of the corrupted image.

Denoising low-light images is a challenging task due to the high noise level. When the illumination is low, digital cameras increase the ISO (electronic gain) to amplify the brightness of captured data. However, this in turn amplifies the noise, arising from read, shot, and defective pixel sources. In the raw domain, read and shot noise are effectively modeled using Gaussian and Poisson distributions respectively, whereas defective pixels can be modeled with impulsive noise. In low-light imaging, noise removal becomes a critical challenge to produce a high-quality, detailed image with low noise. for this task, we use a residual neural network for image denoising based on the densely connected hierarchical network. The encoding and decoding layers of the network consist of connected convolutional layers to reuse the feature maps and local residual learning to avoid the vanishing gradient problem and speed up the learning process. Moreover, global residual learning is adapted such that, instead of directly predicting the denoised image, the model predicts the residual noise of the corrupted image.

Learning-based Low Light Image Denoising

ALNAJJAR, ESRAA M B
2022/2023

Abstract

Denoising low-light images is a challenging task due to the high noise level. When the illumination is low, digital cameras increase the ISO (electronic gain) to amplify the brightness of captured data. However, this in turn amplifies the noise, arising from read, shot, and defective pixel sources. In the raw domain, read and shot noise are effectively modeled using Gaussian and Poisson distributions respectively, whereas defective pixels can be modeled with impulsive noise. In low-light imaging, noise removal becomes a critical challenge to produce a high-quality, detailed image with low noise. for this task, we use a residual neural network for image denoising based on the densely connected hierarchical network. The encoding and decoding layers of the network consist of connected convolutional layers to reuse the feature maps and local residual learning to avoid the vanishing gradient problem and speed up the learning process. Moreover, global residual learning is adapted such that, instead of directly predicting the denoised image, the model predicts the residual noise of the corrupted image.
2022
Learning-based Low Light Image Denoising
Denoising low-light images is a challenging task due to the high noise level. When the illumination is low, digital cameras increase the ISO (electronic gain) to amplify the brightness of captured data. However, this in turn amplifies the noise, arising from read, shot, and defective pixel sources. In the raw domain, read and shot noise are effectively modeled using Gaussian and Poisson distributions respectively, whereas defective pixels can be modeled with impulsive noise. In low-light imaging, noise removal becomes a critical challenge to produce a high-quality, detailed image with low noise. for this task, we use a residual neural network for image denoising based on the densely connected hierarchical network. The encoding and decoding layers of the network consist of connected convolutional layers to reuse the feature maps and local residual learning to avoid the vanishing gradient problem and speed up the learning process. Moreover, global residual learning is adapted such that, instead of directly predicting the denoised image, the model predicts the residual noise of the corrupted image.
Image Denoising
Deep Learning
Low Light Imaging
File in questo prodotto:
File Dimensione Formato  
Alnajjar_Esraa.pdf

Open Access dal 20/04/2024

Dimensione 4.88 MB
Formato Adobe PDF
4.88 MB Adobe PDF Visualizza/Apri

The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12608/46068