Open AccessDOI
Supplementary Material for "Is Deep Image Prior in Need of a Good Education?"
TLDR
This work develops a two-stage learning paradigm to address the computational challenge: (i) a supervised pretraining of the network on a synthetic dataset; (ii) it fine-tune the network’s parameters to adapt to the target reconstruction.Abstract:
Deep image prior [55] was recently introduced as an effective prior for image reconstruction. It represents the image to be recovered as the output of a deep convolutional neural network, and learns the network’s parameters such that the output fits the corrupted observation. Despite its impressive reconstructive properties, the approach is slow when compared to learned or traditional reconstruction techniques. Our work develops a two-stage learning paradigm to address the computational challenge: (i) we perform a supervised pretraining of the network on a synthetic dataset; (ii) we fine-tune the network’s parameters to adapt to the target reconstruction. We showcase that pretraining considerably speeds up the subsequent reconstruction from real-measured micro computed tomography data of biological specimens. The code and additional experimental materials are available at educateddip.github.io/docs.educated_deep_image_prior/.read more
Citations
More filters
Regularization Of Inverse Problems
TL;DR: The regularization of inverse problems is universally compatible with any devices to read and is available in the book collection an online access to it is set as public so you can download it instantly.
Journal ArticleDOI
A Self-Supervised Deep Learning Reconstruction for Shortening the Breathhold and Acquisition Window in Cardiac Magnetic Resonance Fingerprinting
TL;DR: An extension of the deep image prior framework for cardiac MRF tissue property mapping is introduced, which does not require pre-training with in vivo scans, and has the potential to reduce motion artifacts by enabling a shortened breathhold and acquisition window.
Journal ArticleDOI
Untrained Neural Network Priors for Inverse Imaging Problems: A Survey
TL;DR: A comprehensive review of new paradigm of training deep models using a single image, named untrained neural network prior (UNNP) has been proposed to solve a variety of inverse tasks, e.g., restoration and inpainting.
Journal ArticleDOI
Bayesian Experimental Design for Computed Tomography with the Linearised Deep Image Prior
Riccardo Barbano,Johannes Leuschner,Javier Antor'an,Bangti Jin,Jos'e Miguel Hern'andez-Lobato +4 more
TL;DR: This work proposes a novel approach using the linearised deep image prior that allows incorporating information from the pilot measurements into the angle selection criteria, while maintaining the tractability of a conjugate Gaussian-linear model.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Journal ArticleDOI
Image quality assessment: from error visibility to structural similarity
TL;DR: In this article, a structural similarity index is proposed for image quality assessment based on the degradation of structural information, which can be applied to both subjective ratings and objective methods on a database of images compressed with JPEG and JPEG2000.
Proceedings ArticleDOI
You Only Look Once: Unified, Real-Time Object Detection
TL;DR: Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
Journal ArticleDOI
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TL;DR: This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.