Deep neural networks are a very powerful tool for many computer vision tasks, including image restoration, exhibiting state-of-the-art results. However, the performance of deep learning methods tends to drop once the observation model used in training mismatches the one in test time. In addition, most deep learning methods require vast amounts of training data, which are not accessible in many applications. To mitigate these disadvantages, we propose to combine two image restoration approaches: (i) Deep Image Prior (DIP), which trains a convolutional neural network (CNN) from scratch in test time using the given degraded image. It does not require any training data and builds on the implicit prior imposed by the CNN architecture; and (ii) a backprojection (BP) fidelity term, which is an alternative to the standard least squares loss that is usually used in previous DIP works. We demonstrate the performance of the proposed method, termed BP-DIP, on the deblurring task and show its advantages over the plain DIP, with both higher PSNR values and better inference run-time.
Tada-DIP: Input-adaptive Deep Image Prior for One-shot 3D Image Reconstruction
1 Dept. of Computational Mathematics, Science \& Engineering, Michigan State University, East Lansing, MI, USA 2 Dept. of Electrical Engineering；Computer Science, University of Michigan, Ann Arbor, MI, USA 3 Dept. of Biomedical Engineering, Michigan State University, East Lansing, MI, USA
Hyperspectral Denoising Using Unsupervised Disentangled Spatio-Spectral Deep Priors
University of Electronic Science and Technology of China（电子科技大学）；Oregon State University（俄勒冈州立大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）
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）
Preventing Overfitting in Deep Image Prior for Hyperspectral Image Denoising
Robotics Institute, Athena Research and Innovation Center（雅典娜研究与创新中心机器人研究所）；School of Electrical and Computer Engineering, National Technical University of Athens（雅典国家技术大学电气与计算机工程学院）
Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg（生物医学工程人工智能系，埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；Department of Biomedical Engineering, The Ohio State University（生物医学工程系，俄亥俄州立大学）；Research & Clinical Translation, Magnetic Resonance, Siemens Healthineers AG（研究与临床转化，磁共振，西门子医疗有限公司）；Division of Cardiovascular Medicine, The Ohio State University（心血管医学系，俄亥俄州立大学）
Denoising method for dynamic contrast-enhanced CT perfusion studies using three-dimensional deep image prior as a simultaneous spatial and temporal regularizer
Deep Image Priors for Magnetic Resonance Fingerprinting with pretrained Bloch-consistent denoising autoencoders
University of Bristol（布里斯托大学）；INFN Pisa division（意大利国家核物理研究所比萨分部）；University of Bath（巴斯大学）；GE HealthCare（GE医疗）；University of Zurich（苏黎世大学）；IRCCS Stella Maris（斯特拉·马里斯住院与治疗科学研究所）
A Baseline Method for Removing Invisible Image Watermarks using Deep Image Prior
Electrical and Computer Engineering University of Minnesota, Twin Cities（电气与计算机工程大学明尼苏达大学，双城分校）；Computer Science and Engineering University of Minnesota, Twin Cities（计算机科学与工程大学明尼苏达大学，双城分校）
Recursive Deep Prior Video: a Super Resolution algorithm for Time-Lapse Microscopy of organ-on-chip experiments
University of Bologna（博洛尼亚大学）；University of Tor Vergata（罗马第二大学（托尔·韦尔加塔大学））；Institute Curie Centre de Recherche（居里研究所研究中心）；Paris Sciences et Lettres Research University（巴黎文理研究大学）
Deep image prior for undersampling high-speed photoacoustic microscopy
Duke University（杜克大学）；Tsinghua University（清华大学）；Brigham and Women’s Hospital（布列根和妇女医院）；Harvard Medical School（哈佛医学院）；University of Southern California（南加州大学）
StoDIP: Efficient 3D MRF image reconstruction with deep image priors and stochastic iterations
University of Bristol（布里斯托尔大学）；INFN Pisa division（意大利国家核物理研究院比萨分部）；GE HealthCare（GE医疗）；Technische Hochschule Ingolstadt（英戈尔施塔特应用科学大学）；IRCCS Stella Maris（斯特拉·马里斯国立卫生研究所）；University of Zurich（苏黎世大学）
