Max-Planck Institute of Molecular Cell Biology and Genetics(马克斯·普朗克分子细胞生物学与遗传学研究所);Center for Systems Biology Dresden (CSBD)(德累斯顿系统生物学中心);Fondazione Human Technopole(人类技术城基金会);Max Planck Institute for the Physics of Complex Systems(马克斯·普朗克复杂系统物理研究所)
Anna S. Goncharova, Alf Honigmann, Florian Jug, Alexander Krull
Many microscopy applications are limited by the total amount of usable light and are consequently challenged by the resulting levels of noise in the acquired images. This problem is often addressed via (supervised) deep learning based denoising. Recently, by making assumptions about the noise statistics, self-supervised methods have emerged. Such methods are trained directly on the images that are to be denoised and do not require additional paired training data. While achieving remarkable results, self-supervised methods can produce high-frequency artifacts and achieve inferior results compared to supervised approaches. Here we present a novel way to improve the quality of self-supervised denoising. Considering that light microscopy images are usually diffraction-limited, we propose to include this knowledge in the denoising process. We assume the clean image to be the result of a convolution with a point spread function (PSF) and explicitly include this operation at the end of our neural network. As a consequence, we are able to eliminate high-frequency artifacts and achieve self-supervised results that are very close to the ones achieved with traditional supervised methods.
Patch-based Non-Local Bayesian Networks for Blind Confocal Microscopy Denoising
Simon Fraser University(西蒙弗雷泽大学)
共聚焦显微镜对于组织病理学细胞可视化和量化至关重要。尽管其在生物学中的重要作用,荧光共聚焦显微镜遭受的固有噪声的存在下,在图像采集。非局部块式贝叶斯均值滤波(NLB)直到最近才成为最先进的去噪方法。然而,近年来,经典的去噪方法已经被神经网络超越。在这项工作中,我们建议在贝叶斯深度学习的框架中利用NLB的优势。我们通过设计一个卷积神经网络并训练它来学习高斯模型的参数,该模型近似于无噪声补丁上的先验,给出了它们最近的、相似的但非局部的邻居。然后,我们应用贝叶斯推理,利用先验知识和信息的噪声补丁的过程中近似的无噪声补丁。具体来说,我们使用封闭形式的解析\textit{maximum a posteriori}(MAP)估计的NLB算法,以获得最大化后验分布的无噪声补丁。我们所提出的方法的性能进行评估,共焦显微镜图像与真实噪声泊松-高斯噪声。我们的实验揭示了我们的方法对最先进的无监督去噪技术的优越性。
View Blind-spot as Inpainting: Self-Supervised Denoising with Mask Guided Residual Convolution
McGill University(麦吉尔大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Shenzhen Institute of Artificial Intelligence and Robotics for Society(深圳人工智能与机器人研究院)
Blind-Spot Collision Detection System for Commercial Vehicles Using Multi Deep CNN Architecture
Universiti Teknologi PETRONAS(马来西亚石油科技大学);Université Paris-Est Créteil (UPEC)(巴黎东克雷泰伊大学);COMSATS University Islamabad, Lahore Campus(伊斯兰堡COMSATS大学拉合尔校区)
A CNN-Based Blind Denoising Method for Endoscopic Images
Institute of Microelectronics, Tsinghua University(清华大学微电子学研究所);Graduate School at Shenzhen, Tsinghua University(清华大学深圳国际研究生院);Department of Electronic Engineering, Tsinghua University(清华大学电子工程系)
YOND: Practical Blind Raw Image Denoising Free from Camera-Specific Data Dependency
School of Computer Science and Technology, Beijing Institute of Technology(计算机科学与技术学院,北京理工大学);School of Artificial Intelligence, Beijing Normal University(人工智能学院,北京师范大学)
Joint self-supervised blind denoising and noise estimation
SABILab(SABI实验室);École Polytechnique(巴黎综合理工学院);Institut Polytechnique de Paris(巴黎理工学院);Université Paris-Saclay(巴黎萨克雷大学);CNRS(法国国家科学研究中心);Laboratoire de mathématiques d’Orsay(奥赛数学实验室);Laboratoire J. A. Dieudonné(J·A·迪厄多内实验室);Université Côte d’Azur(蔚蓝海岸大学);Télécom SudParis(南巴黎电信学院)
Robust and interpretable blind image denoising via bias-free convolutional neural networks
Center for Data Science(数据科学中心);New York University(纽约大学);Center for Neural Science(神经科学中心);Howard Hughes Medical Institute(霍华德·休斯医学研究所);Courant Inst. of Mathematical Sciences(库朗数学科学研究所)
Blind Image Denoising and Inpainting Using Robust Hadamard Autoencoders
Worcester Polytechnic Institute(伍斯特理工学院);Colorado State University(科罗拉多州立大学)
在本文中,我们演示了深度自动编码器如何推广到修复和去噪的情况,即使没有干净的训练数据可用。特别是,我们展示了如何训练神经网络同时执行所有这些任务。虽然通过神经网络实现的深度自动编码器已经证明了去噪和异常检测的潜力,但标准自动编码器的缺点是需要访问干净的数据进行训练。然而,最近在Robust Deep Autoencoders(RDAE)中的工作展示了如何训练自动编码器来消除数据集中的离群值和噪声,而无需访问任何干净的训练数据。受这项工作的启发,我们将RDAE扩展到数据不仅有噪声和离群值,而且只有部分观察到的情况。此外,我们训练神经网络的数据集具有所有条目都有噪声的属性,一些条目被大错误损坏,许多条目甚至不知道。给定这样的算法,许多标准任务,如去噪,图像修复和未观察到的条目插补,都可以在同一个框架内同时完成。在本文中,我们将在标准机器学习任务上演示这些技术,例如MNIST和CIFAR10数据集的图像修复和去噪。然而,这些方法不仅适用于图像处理问题,而且对由真实世界问题产生的数据集具有广泛的影响,例如制造和网络处理,其中自然会出现有噪声的部分观察数据。