The lack of interpretability in current deep learning models causes serious concerns as they are extensively used for various life-critical applications. Hence, it is of paramount importance to develop interpretable deep learning models. In this paper, we consider the problem of blind deconvolution and propose a novel model-aware deep architecture that allows for the recovery of both the blur kernel and the sharp image from the blurred image. In particular, we propose the Deep Unfolded Richardson-Lucy (Deep-URL) framework -- an interpretable deep-learning architecture that can be seen as an amalgamation of classical estimation technique and deep neural network, and consequently leads to improved performance. Our numerical investigations demonstrate significant improvement compared to state-of-the-art algorithms.
LUCYD: A Feature-Driven Richardson-Lucy Deconvolution Network
Technical University of Munich（慕尼黑工业大学）；Helmholtz AI（亥姆霍兹人工智能）；Helmholtz Munich - German Research Center for Environmental Health（亥姆霍兹慕尼黑中心-德国环境健康研究中心）；Georg-August-University Göttingen（哥廷根大学）；GEOMAR Helmholtz Centre for Ocean Research Kiel（基尔亥姆霍兹海洋研究中心）
Stanford University（斯坦福大学）；Queensland University of Technology（昆士兰科技大学）；ARC Centre of Excellence for Robotic Vision（澳大利亚研究委员会机器人视觉卓越中心）
We generalize Richardson-Lucy (RL) deblurring to 4-D light fields by replacing the convolution steps with light field rendering of motion blur. The method deals correctly with blur caused by 6-degree-of-freedom camera motion in complex 3-D scenes, without performing depth estimation. We introduce a novel regularization term that maintains parallax information in the light field while reducing noise and ringing. We demonstrate the method operating effectively on rendered scenes and scenes captured using an off-the-shelf light field camera. An industrial robot arm provides repeatable and known t…
Restoration of digital images from their degraded measurements has always been a problem of great theoretical and practical importance in numerous applications of imaging sciences. A specific solution to the problem of image restoration is generally determined by the nature of degradation phenomenon as well as by the statistical properties of measurement noises. The present study is concerned with the case in which the images of interest are corrupted by convolutional blurs and Poisson noises. To deal with such problems, there exists a range of solution methods which are based on the principle…
University for Health Sciences, Medical Informatics and Technology (UMIT)（健康科学、医学信息学与技术大学（UMIT））
In this paper, an iterative method for robust deconvolution with positivity constraints is discussed. It is based on the known variational interpretation of the Richardson-Lucy iterative deconvolution as fixed-point iteration for the minimisation of an information divergence functional under a multiplicative perturbation model. The asymmetric penaliser function involved in this functional is then modified into a robust penaliser, and complemented with a regulariser. The resulting functional gives rise to a fixed point iteration that we call robust and regularised Richardson-Lucy deconvolution.…
Deep Richardson-Lucy Deconvolution for Low-Light Image Deblurring
The University of Adelaide（阿德莱德大学）；Sensetime（商汤科技）；Sensetime research（商汤科技研究院）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；East China Normal University（华东师范大学）；Nanjing University of Science and Technology（南京理工大学）
Re-thinking Richardson-Lucy without Iteration Cutoffs: Physically Motivated Bayesian Deconvolution
Center for Biological Physics, Arizona State University（亚利桑那州立大学生物物理中心）；Department of Physics, Arizona State University（亚利桑那州立大学物理系）；School of Molecular Sciences, Arizona State University（亚利桑那州立大学分子科学学院）
Idiap Research Institute（伊迪亚普研究所）；University of California, Santa Barbara（加州大学圣巴巴拉分校）
We present a semi-blind, spatially-variant deconvolution technique aimed at optical microscopy that combines a local estimation step of the point spread function (PSF) and deconvolution using a spatially variant, regularized Richardson-Lucy algorithm. To find the local PSF map in a computationally tractable way, we train a convolutional neural network to perform regression of an optical parametric model on synthetically blurred image patches. We deconvolved both synthetic and experimentally-acquired data, and achieved an improvement of image SNR of 1.00 dB on average, compared to other deconvo…
We propose a general framework for solving inverse problems in the presence of noise that requires no signal prior, no noise estimate, and no clean training data. We only require that the forward model be available and that the noise be statistically independent across measurement dimensions. We build upon the theory of $\mathcal{J}$-invariant functions (Batson & Royer 2019, arXiv:1901.11365) and show how self-supervised denoising \emph{à la} Noise2Self is a special case of learning a noise-tolerant pseudo-inverse of the identity. We demonstrate our approach by showing how a convolutional neur…
Modular Transformer Architecture for Precision Agriculture Imaging
University Park The Pennsylvania State University PA, United States（帕克大学帕萨迪纳分校）；Engineering Division, Great Valley The Pennsylvania State University PA, United States（工程部，大山谷帕萨迪纳分校）
Institute for Biomedical Image Analysis, University for Medical Informatics and Technology (UMIT)（医学信息与技术大学（UMIT）生物医学图像分析研究所）；TOMAXX GmbH（TOMAXX 有限公司）
We investigate efficient algorithmic realisations for robust deconvolution of grey-value images with known space-invariant point-spread function, with emphasis on 1D motion blur scenarios. The goal is to make deconvolution suitable as preprocessing step in automated image processing environments with tight time constraints. Candidate deconvolution methods are selected for their restoration quality, robustness and efficiency. Evaluation of restoration quality and robustness on synthetic and real-world test images leads us to focus on a combination of Wiener filtering with few iterations of robu…
Center for Systems Biology Dresden（德累斯顿系统生物学中心）；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）
The quality of microscopy images often suffers from optical aberrations. These aberrations and their associated point spread functions have to be quantitatively estimated to restore aberrated images. The recent state-of-the-art method PhaseNet, based on a convolutional neural network, can quantify aberrations accurately but is limited to images of point light sources, e.g. fluorescent beads. In this research, we describe an extension of PhaseNet enabling its use on 3D images of biological samples. To this end, our method incorporates object-specific information into the simulated images used f…
A Zero-Shot Deep Image Prior Framework for Denoising and Deconvolution in Fluorescence Microscopy
Wenzhou Key Laboratory of Biomedical Imaging（温州生物医学成像重点实验室）；Zhejiang Key Laboratory of Soft Matter Biomedical Materials（浙江软物质生物医学材料重点实验室）；Wenzhou Institute, University of Chinese Academy of Sciences（中国科学院大学温州研究院）；Postgraduate Training Base Alliance of Wenzhou Medical University（温州医学院研究生联合培养基地联盟）
Leveraging Classic Deconvolution and Feature Extraction in Zero-Shot Image Restoration
Technical University of Munich（慕尼黑工业大学）；Helmholtz AI, Helmholtz Munich - German Research Center for Environmental Health（亥姆霍兹人工智能平台，亥姆霍兹慕尼黑中心——德国环境健康研究中心）；Georg-August-University Göttingen（哥廷根乔治-奥古斯特大学）；GEOMAR Helmholtz Centre for Ocean Research Kiel（基尔亥姆霍兹海洋研究中心）
Image blurring refers to the degradation of an image wherein the image's overall sharpness decreases. Image blurring is caused by several factors. Additionally, during the image acquisition process, noise may get added to the image. Such a noisy and blurred image can be represented as the image resulting from the convolution of the original image with the associated point spread function, along with additive noise. However, the blurred image often contains inadequate information to uniquely determine the plausible original image. Based on the availability of blurring information, image deblurr…
Idiap Research Institute（IDIAP研究所）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）；University of California, Santa Barbara（加州大学圣巴巴拉分校）
Optical microscopy is an essential tool in biology and medicine. Imaging thin, yet non-flat objects in a single shot (without relying on more sophisticated sectioning setups) remains challenging as the shallow depth of field that comes with high-resolution microscopes leads to unsharp image regions and makes depth localization and quantitative image interpretation difficult. Here, we present a method that improves the resolution of light microscopy images of such objects by locally estimating image distortion while jointly estimating object distance to the focal plane. Specifically, we estimat…
Resolution Enhancement of Under-sampled Photoacoustic Microscopy Images using Implicit Neural Representations
School of Information Science and Technology, ShanghaiTech University（上海科技大学信息科学与技术学院）；Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉与成像工程技术研究中心）；Suzhou Institute for Advanced Research, University of Science and Technology of China（中国科学技术大学苏州高等研究院）
Enhanced Confocal Laser Scanning Microscopy with Adaptive Physics Informed Deep Autoencoders
Georgia State University（佐治亚州立大学）；Riphah International University（里法国际大学）；Roots IVY（鲁茨艾维）；Arid Agriculture University（干旱农业大学）；University of Central Florida（中佛罗里达大学）
Solving the inverse problem of microscopy deconvolution with a residual Beylkin-Coifman-Rokhlin neural network
Center for Advanced Systems Understanding (CASUS)（先进系统理解中心）；Helmholtz-Zentrum Dresden-Rossendorf e. V. (HZDR)（德累斯顿-罗斯托克研究所）；Max Delbrück Center for Molecular Medicine in the Helmholtz Association（马克斯·德尔布吕克分子医学研究中心）；Institute of Medical Physics and Biophysics, Charite-Universitätsmedizin（医学物理与生物物理研究所）；Institute of Computer Science, University of Wrocław（沃林福大学计算机科学研究所）
