A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Adaptation Strategies for Applying AWGN-Based Denoiser to Realistic Noise
2019
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
In this paper, we explore multiple strategies for applying an AWGN-based denoiser to realistic noise. ...
To adapt the model to realistic noises, we investigated multi-channel, multi-scale and super-resolution approaches. ...
Multi-channel and Multi-scale Strategy To adapt AWGN-RVIN-based noise model to real noise, we estimated each channel separately and applied pixel-shuffle for subsampling before denoising. ...
doi:10.1609/aaai.v33i01.330110085
fatcat:ysm32bictvbn3ajpildzjhbgse
When AWGN-based Denoiser Meets Real Noises
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We then investigate Pixel-shuffle Down-sampling (PD) strategy to adapt the trained model to real noises. ...
Discriminative learning-based image denoisers have achieved promising performance on synthetic noises such as Additive White Gaussian Noise (AWGN). ...
These two advantages yield the two stages of PD strategy: adaptation and refinement. Adaptation. Learning-based denoiser trained on AWGN is not robust enough to real noises due to domain difference. ...
arXiv:1904.03485v2
fatcat:iywtuqvyk5c5tistmdczipsuhe
When AWGN-Based Denoiser Meets Real Noises
2020
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We then investigate Pixel-shuffle Down-sampling (PD) strategy to adapt the trained model to real noises. ...
Discriminative learning based image denoisers have achieved promising performance on synthetic noises such as Additive White Gaussian Noise (AWGN). ...
These two advantages yield the two stages of PD strategy: adaptation and refinement. Adaptation. Learning-based denoiser trained on AWGN is not robust enough to real noises due to domain difference. ...
doi:10.1609/aaai.v34i07.7009
fatcat:hvkaas4cqzdotffcey5l2cttsq
Estimating Fine-Grained Noise Model via Contrastive Learning
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
To improve the denoising performance in realworld, two typical solutions are used in recent trends: devising better noise models for the synthesis of more realistic training data, and estimating noise ...
Then, we use the estimated noise parameters to model camera-specific noise distribution, and synthesize realistic noisy training data. ...
As a result, we apply our pipeline to real image denoising and facilitate the training process by synthesizing more realistic data. ...
arXiv:2204.01716v1
fatcat:shcoz3uin5bsndei4dtpx3uj5e
Self-supervised training for blind multi-frame video denoising
2021
2021 IEEE Winter Conference on Applications of Computer Vision (WACV)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
We show how this can be expoited to perform joint denoising and noise level estimation for heteroscedastic noise. ...
We use the proposed strategy to denoise a video contaminated with an unknown noise type, by fine-tuning a pre-trained denoising network on the noisy video. ...
We observed that it is easier for the AWGN weights to adapt to other noise types. ...
doi:10.1109/wacv48630.2021.00277
fatcat:wkuujprlrbbxpidh22zdvxd5ii
Learning from Natural Noise to Denoise Micro-Doppler Spectrogram
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
For these methods, noise modelling is the most important part and is used to assist in training. ...
Besides, the idea of learning from natural noise can be applied well to other existing frameworks and demonstrate greater performance than other noise models. ...
In this way, the CNN-based denoiser can be trained with more realistic data to improve the denoising effect. 2) Aside from the denoising, our approach provides a strategy for improving simulated spectrograms ...
arXiv:2102.06887v1
fatcat:ytjrn4bakrdodh7tko56mxla44
Image Denoising in Mixed Poisson–Gaussian Noise
2011
IEEE Transactions on Image Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
We propose a general methodology (PURE-LET) to design and optimize a wide class of transform-domain thresholding algorithms for denoising images corrupted by mixed Poisson-Gaussian noise. ...
We express the denoising process as a linear expansion of thresholds (LET) that we optimize by relying on a purely data-adaptive unbiased estimate of the mean-squared error (MSE), derived in a non-Bayesian ...
ACKNOWLEDGMENT The authors are especially grateful to Prof. L. Jiang and Dr. Y. ...
doi:10.1109/tip.2010.2073477
pmid:20840902
fatcat:ncl245zhqrdqtcpd7y7hwz3qim
Learning Deep Image Priors for Blind Image Denoising
2019
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
It can be used to improve the blind denoising performance in terms of distortion measures (PSNR and SSIM), while pixel-level prior can effectively improve the perceptual quality to ensure the realistic ...
We tackle the domain alignment on two levels. 1) the feature-level prior is to learn domain-invariant features for corrupted images with different level noise; 2) the pixel-level prior is used to push ...
and produce photo-realistic results. • Compared with previous methods, our method significantly improves the generalizability when adapting from synthetic Gaussian denoising to real-world noise removal ...
doi:10.1109/cvprw.2019.00224
dblp:conf/cvpr/HouLLX0GLQ19
fatcat:n3epyl4edzdfhp2ok7ruumr7b4
Self-Supervised training for blind multi-frame video denoising
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2004.06957v3 fatcat:xy7rxrvkyffzpfwfqulwaq2oviOther Versions
We use the proposed strategy for online internal learning, where a pre-trained network is fine-tuned to denoise a new unknown noise type from a single video. ...
In addition, for a wide range of noise types, it can be applied blindly without knowing the noise distribution. ...
trained for AWGN. ...
arXiv:2004.06957v4
fatcat:tyzktotytrhmfezjxdvtovmcnq
SAR Image Despeckling by Deep Neural Networks: from a pre-trained model to an end-to-end training strategy
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The first strategy applies a CNN model, trained to remove additive white Gaussian noise from natural images, to a recently proposed SAR speckle removal framework: MuLoG (MUlti-channel LOgarithm with Gaussian ...
Among the different possible approaches, methods based on convolutional neural networks (CNNs) have recently shown to reach state-of-the-art performance for SAR image restoration. ...
apply CNNs to AWGN suppression. ...
arXiv:2006.15559v3
fatcat:suckj6htp5gpze7cqyxgj4ghcq
Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
To alleviate this problem, this work investigates how to generate realistic noisy images. ...
PNGAN employs a pre-trained real denoiser to map the fake and real noisy images into a nearly noise-free solution space to perform image domain alignment. ...
To alleviate the above problems, this work focuses on learning how to generate realistic noisy images so as to augment the training data for real denoisers. ...
arXiv:2204.02844v1
fatcat:5j2mljhh3rhitkld2yepivfltq
Mixed Noise Removal with Pareto Prior
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Compared to existing methods, the proposed method can estimate the weighting matrix adaptively, accurately, and robust for different level of noises, thus can boost the denoising performance. ...
To address this problem, we exploit the Pareto distribution as the priori of the weighting matrix, based on which an accurate and robust weight estimator is proposed for mixed noise removal. ...
This two-stage strategy (detecting then filtering strategy) has been adopted in [17] , [18] , [19] for mixed noise removal. ...
arXiv:2008.11935v1
fatcat:uktc66i7lfb77ibybalei3x55e
SAR Image Despeckling by Deep Neural Networks: from a Pre-Trained Model to an End-to-End Training Strategy
2020
Remote Sensing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The first strategy applies a CNN model, trained to remove additive white Gaussian noise from natural images, to a recently proposed SAR speckle removal framework: MuLoG (MUlti-channel LOgarithm with Gaussian ...
Among the different possible approaches, methods based on convolutional neural networks (CNNs) have recently shown to reach state-of-the-art performance for SAR image restoration. ...
CNN networks have also been applied to the denoising of natural images, but mostly in the context of additive white Gaussian noise (AWGN). ...
doi:10.3390/rs12162636
fatcat:qp33ccej5nhbfom4t27ohd2wey
Model-blind Video Denoising Via Frame-to-frame Training
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This is achieved by fine-tuning a pre-trained AWGN denoising network to the video with a novel frame-to-frame training strategy. ...
It nonetheless reaches state of the art performance for standard Gaussian noise, and can be used off-line with still better performance. ...
CNNs have been applied successfully to denoise images with non-Gaussian noise [48, 8, 18] . ...
arXiv:1811.12766v3
fatcat:i3y3zgh7ezggph3u7yzlpqwcpa
A Review of an Old Dilemma: Demosaicking First, or Denoising First?
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Yet we prove that this requires an adaptation of classic denoising algorithms to demosaicked noise, which we justify and specify. ...
Hence, the question of how to combine denoising and demosaicking to reconstruct full color images remains very relevant: Is denoising to be applied first, or should that be demosaicking first? ...
In contrast, the demosaicked noise is reduced in the U and V axes, with its variance passing from 400 for AWGN to 168 and 94 for RI, and even down to 43 and 55 for RCNN. ...
arXiv:2004.11577v1
fatcat:2jekny4glndbzj2lhc3ywgdhwa
« Previous
Showing results 1 — 15 out of 244 results