Far-field super-resolution ghost imaging with a deep neural network constraint
TLDR
In this paper , a far-field super-resolution Ghost Imaging (GI) technique was proposed that incorporates the physical model for GI image formation into a deep neural network, and the resulting hybrid neural network does not need to pre-train on any dataset, and allows the reconstruction of a farfield image with the resolution beyond the diffraction limit.Abstract:
Abstract Ghost imaging (GI) facilitates image acquisition under low-light conditions by single-pixel measurements and thus has great potential in applications in various fields ranging from biomedical imaging to remote sensing. However, GI usually requires a large amount of single-pixel samplings in order to reconstruct a high-resolution image, imposing a practical limit for its applications. Here we propose a far-field super-resolution GI technique that incorporates the physical model for GI image formation into a deep neural network. The resulting hybrid neural network does not need to pre-train on any dataset, and allows the reconstruction of a far-field image with the resolution beyond the diffraction limit. Furthermore, the physical model imposes a constraint to the network output, making it effectively interpretable. We experimentally demonstrate the proposed GI technique by imaging a flying drone, and show that it outperforms some other widespread GI techniques in terms of both spatial resolution and sampling ratio. We believe that this study provides a new framework for GI, and paves a way for its practical applications. read more
Citations
More filters
Journal ArticleDOI
Next generation lanthanide doped nanoscintillators and photon converters
TL;DR: In this paper , the authors discuss design strategies and nanostructures that allow manipulation of excitation dynamics in a core-shell geometry to simultaneously produce XEOL, XEPL, as well as photon upconversion and downshifting, enabling emission at multiple wavelengths with a varying time scale profile.
Journal ArticleDOI
Deep Learning Enhances Multiparametric Dynamic Volumetric Photoacoustic Computed Tomography In Vivo (DL‐PACT)
Seong-Hwan Choi,Jinge Yang,Soo Young Lee,Jiwoong Kim,Jihye Lee,Won Jong Kim,Seung-Chul Lee,Chulhong Kim +7 more
TL;DR: In this paper , a deep learning-enhanced multiparametric dynamic volumetric PACT approach, called DL•PACT, is proposed to obtain high-quality static structural and dynamic contrastenhanced whole-body images as well as dynamic functional brain images of live animals and humans.
Journal ArticleDOI
Deep holography
TL;DR: In this article , a comprehensive literature review on the recent progress of deep holography, an emerging interdisciplinary research field that is mutually inspired by holographic and deep neural networks is presented.
Journal ArticleDOI
Manipulation of time-dependent multicolour evolution of X-ray excited afterglow in lanthanide-doped fluoride nanoparticles
Lei Lei,Yubin Wang,Wei-Xiu Xu,Renguang Ye,Youjie Hua,Degang Deng,Liang Chen,Paras N. Prasad,Shiqing Xu +8 more
TL;DR: In this paper , a core/multi-shell nanostructures can be designed to simultaneously generate afterglow, upconversion and downshifting to realize multimode time-dependent multicolour evolutions.
Journal ArticleDOI
Time-overlapping structured-light projection: high performance on 3D shape measurement for complex dynamic scenes.
TL;DR: In this paper , a time-overlapping structured-light 3D shape measuring technique is proposed to realize high-speed and highperformance measurement on complex dynamic scenes, including collapsing wood blocks, free-falling foam snowflakes and flying water balloon towards metal grids.
References
More filters
Book ChapterDOI
U-Net: Convolutional Networks for Biomedical Image Segmentation
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Journal ArticleDOI
Deep learning
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
Posted Content
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Andrew Howard,Menglong Zhu,Bo Chen,Dmitry Kalenichenko,Weijun Wang,Tobias Weyand,M. Andreetto,Hartwig Adam +7 more
TL;DR: This work introduces two simple global hyper-parameters that efficiently trade off between latency and accuracy and demonstrates the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization.
Journal ArticleDOI
Stable signal recovery from incomplete and inaccurate measurements
TL;DR: In this paper, the authors considered the problem of recovering a vector x ∈ R^m from incomplete and contaminated observations y = Ax ∈ e + e, where e is an error term.
Posted Content
Stable Signal Recovery from Incomplete and Inaccurate Measurements
TL;DR: It is shown that it is possible to recover x0 accurately based on the data y from incomplete and contaminated observations.