3,102 Hits in 5.6 sec

Learning from irregularly sampled data for endomicroscopy super-resolution: a comparative study of sparse and dense approaches

Agnieszka Barbara Szczotka, Dzhoshkun Ismail Shakir, Daniele Ravì, Matthew J. Clarkson, Stephen P. Pereira, Tom Vercauteren
2020 International Journal of Computer Assisted Radiology and Surgery  
We compare pCLE reconstruction and super-resolution (SR) methods taking irregularly sampled or reconstructed pCLE images as input.  ...  We also implement trainable generalised NW kernel regression as a novel sparse approach. We also generated synthetic data for training pCLE SR.  ...  Tom Vercauteren is supported by a Medtronic/Royal Academy of Engineering Research Chair: RCSRF1819/7/34.  ... 
doi:10.1007/s11548-020-02170-7 pmid:32415459 pmcid:PMC7316691 fatcat:5gqre4oyuvcixmqeaezay575nm

Context-Sensitive Super-Resolution for Fast Fetal Magnetic Resonance Imaging [chapter]

Steven McDonagh, Benjamin Hou, Amir Alansary, Ozan Oktay, Konstantinos Kamnitsas, Mary Rutherford, Jo V. Hajnal, Bernhard Kainz
2017 Lecture Notes in Computer Science  
for the generation of high resolution images with sharp edges and fine scale detail.  ...  3D Magnetic Resonance Imaging (MRI) is often a trade-off between fast but low-resolution image acquisition and highly detailed but slow image acquisition.  ...  Future work will look to investigate the generalisability of the proposed framework to additional problem domains. Fig. 1 . 1 Our proposed CNN network architecture for MRI super-resolution.  ... 
doi:10.1007/978-3-319-67564-0_12 fatcat:rxm4bt7nqfav5nnynpmme2utji

Characteristic Regularisation for Super-Resolving Face Images [article]

Zhiyi Cheng, Xiatian Zhu, Shaogang Gong
2019 arXiv   pre-print
Existing facial image super-resolution (SR) methods focus mostly on improving artificially down-sampled low-resolution (LR) imagery.  ...  Specifically, we separate and control the optimisations for characteristics consistifying and image super-resolving by introducing Characteristic Regularisation (CR) between them.  ...  This work was partially supported by the Alan Turing Institute Turing Fellowship, the Innovate UK Industrial Challenge Project on Developing and Commercialising Intelligent Video Analytics Solutions for  ... 
arXiv:1912.12987v1 fatcat:24vpvwmdqfbntkhnwoqfro4aby

Multiple Classifier Boosting and Tree-Structured Classifiers [chapter]

Tae-Kyun Kim, Roberto Cipolla
2013 Studies in Computational Intelligence  
Section 4 presents a tree-structured classifier, called Super tree, to further speed up the classification time of a standard boosting classifier.  ...  The method is extended into an online version for object tracking in Section 3.  ...  Recently a class of techniques using discriminative tracking has been shown to yield good results by treating tracking as a classification framework [21, 22, 24, 26] (see Figure 2) .  ... 
doi:10.1007/978-3-642-28661-2_7 fatcat:bg7dd5hbvvdvtamzwzscdlbg74

A Unified Neural Architecture for Instrumental Audio Tasks [article]

Steven Spratley, Daniel Beck, Trevor Cohn
2019 arXiv   pre-print
Within Music Information Retrieval (MIR), prominent tasks -- including pitch-tracking, source-separation, super-resolution, and synthesis -- typically call for specialised methods, despite their similarities  ...  Conditional Generative Adversarial Networks (cGANs) have been shown to be highly versatile in learning general image-to-image translations, but have not yet been adapted across MIR.  ...  Harmonic Addition: Super-Resolution and Synthesis For super-resolution, as in [25] we used interpolative baselines (linear, cubic b-spline) [26] , which were compared against our pipeline using all  ... 
arXiv:1903.00142v1 fatcat:c6njrzq53vcdpikpjit2ldw6bm

Resolving crossing fibres using constrained spherical deconvolution: Validation using diffusion-weighted imaging phantom data

J.-Donald Tournier, Chun-Hung Yeh, Fernando Calamante, Kuan-Hung Cho, Alan Connelly, Ching-Po Lin
2008 NeuroImage  
A number of approaches have recently been proposed to address this issue, based on high angular resolution diffusion-weighted imaging (HARDI) data.  ...  A key requirement for fibre tracking is the accurate estimation of white matter fibre orientations within each imaging voxel.  ...  JDT, FC and AC are grateful to the National Health and Medical Research Council (NHMRC) of Australia and Austin Health for support.  ... 
doi:10.1016/j.neuroimage.2008.05.002 pmid:18583153 fatcat:ihc2s4f4xvh4hf2hkcgffyfvre

Multi-feature super-resolution network for cloth wrinkle synthesis [article]

Lan Chen, Xiaopeng Zhang, Juntao Ye
2020 arXiv   pre-print
With these image pairs, we design a multi-feature super-resolution (MFSR) network that jointly train an upsampling synthesizer for the three features.  ...  In this paper we propose a deep learning based method for synthesizing cloth animation with high resolution meshes.  ...  A, et al. Photo-realistic single image super-resolution using a generative [45] Kim, J, Kwon Lee, J, Mu Lee, K.  ... 
arXiv:2004.04351v1 fatcat:v3fnxtdtpbdlxmpejndslu7ghu

Degenerative Adversarial NeuroImage Nets for Brain Scan Simulations: Application in Ageing and Dementia [article]

Daniele Ravi, Stefano B. Blumberg, Silvia Ingala, Frederik Barkhof, Daniel C. Alexander, Neil P. Oxtoby
2021 arXiv   pre-print
Weight Functions (PWFs), ii) a 3D super-resolution module and iii) a transfer learning strategy to fine-tune the system for a given individual.  ...  To evaluate our approach, we trained the framework on 9852 T1-weighted MRI scans from 876 participants in the Alzheimer's Disease Neuroimaging Initiative dataset and held out a separate test set of 1283  ...  Acknowledgements The authors would like to thank NVIDIA Corporation for the donation of one of the GPUs used for this research.  ... 
arXiv:1912.01526v5 fatcat:kwltawwk6ra7lfwypzavz4qsvi

Making a Shallow Network Deep: Conversion of a Boosting Classifier into a Decision Tree by Boolean Optimisation

Tae-Kyun Kim, Ignas Budvytis, Roberto Cipolla
2011 International Journal of Computer Vision  
The proposed method is further demonstrated for fast-moving object tracking and segmentation problems.  ...  The tree provides many short paths for speeding up while preserving the reasonably smooth decision regions of the boosting classifier for good generalisation.  ...  The benefit of using Super tree for rapid tracking would be bigger when a higher frame rate camera is available.  ... 
doi:10.1007/s11263-011-0461-z fatcat:vouvh2tdmvbghea6z75vhd2h6a

Confocal Laser-Scanning Fluorescence-Lifetime Single-Molecule Localisation Microscopy [article]

Jan Christoph Thiele, Dominic Helmerich, Nazar Oleksiievets, Roman Tsukanov, Eugenia Butkevich, Markus Sauer, Oleksii Nevskyi, Joerg Enderlein
2020 bioRxiv   pre-print
Here, we combine Fluorescence-Lifetime Confocal Laser-Scanning Microscopy (FL-CLSM) with SMLM for realising single-molecule localisation-based fluorescence-lifetime super-resolution imaging (FL-SMLM).  ...  Besides yielding images with a spatial resolution much beyond the diffraction limit, it determines the fluorescence lifetime of all localised molecules.  ...  J.E. and O.N. acknowledge financial support by the Deutsche Forschungsgemeinschaft (DFG) via project "Super-resolution microscopy through single molecule localization at cryogenic temperature" (EN297/15  ... 
doi:10.1101/2020.08.25.266387 fatcat:huv47crbpbghnhj7ulyvsfyvdq

Super-resolution land cover pattern prediction using a Hopfield neural network

A Tatem
2002 Remote Sensing of Environment  
Results show that the new approach represents a simple, robust, and efficient tool for super-resolution land cover pattern prediction from remotely sensed imagery. D  ...  We recently described the application of a Hopfield neural network technique to super-resolution mapping of land cover features larger than a pixel, using information of pixel composition determined from  ...  Both super-resolution techniques were again run for the proportions in Figs. 5(c) and 6(c).  ... 
doi:10.1016/s0034-4257(01)00229-2 fatcat:fbizar3kwbetnba4lsyczhkxyq

NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Image [article]

Boaz Arad, Radu Timofte, Ohad Ben-Shahar, Yi-Tun Lin, Graham Finlayson, Shai Givati, others
2020 arXiv   pre-print
As in the previous challenge, two tracks were provided: (i) a "Clean" track where HS images are estimated from noise-free RGBs, the RGB images are themselves calculated numerically using the ground-truth  ...  HS images and supplied spectral sensitivity functions (ii) a "Real World" track, simulating capture by an uncalibrated and unknown camera, where the HS images are recovered from noisy JPEG-compressed  ...  Graham Finlayson is grateful for the support of EPSRC grant EP S028730. Ohad Ben-Shahar gratefully acknowledges the support of the ISF-FIRST program grant 555/19.  ... 
arXiv:2005.03412v1 fatcat:m2bjorfghbc4jicby5gonuhgyu

Super-resolution of Sentinel-2 images: Learning a globally applicable deep neural network

Charis Lanaras, José Bioucas-Dias, Silvano Galliani, Emmanuel Baltsavias, Konrad Schindler
2018 ISPRS journal of photogrammetry and remote sensing (Print)  
We use data sampled globally over a wide range of geographical locations, to obtain a network that generalises across different climate zones and land-cover types, and can super-resolve arbitrary Sentinel  ...  The aim of this research is to super-resolve the lower-resolution (20 m and 60 m Ground Sampling Distance - GSD) bands to 10 m GSD, so as to obtain a complete data cube at the maximal sensor resolution  ...  The second group of methods attacks super-resolution as an inverse imaging problem under the variational, respectively Bayesian, inference frameworks.  ... 
doi:10.1016/j.isprsjprs.2018.09.018 fatcat:qmofkkgtsnadvolzpuutcvk3ny

Variational Multi-Task MRI Reconstruction: Joint Reconstruction, Registration and Super-Resolution [article]

Veronica Corona, Angelica I. Aviles-Rivero, Noémie Debroux, Carole Le Guyader, Carola-Bibiane Schönlieb
2019 arXiv   pre-print
In this work, we present for the first time a variational multi-task framework that allows joining three relevant tasks in MRI: reconstruction, registration and super-resolution.  ...  Motion degradation is a central problem in Magnetic Resonance Imaging (MRI).  ...  In a multi-frame variational framework, super-resolution is the problem of restoring a high-resolution image from several low quality images that are corrupted by motion.  ... 
arXiv:1908.05911v1 fatcat:ir7t3htkbjeozmdvnz4itkdlq4

Marker-Less Stage Drift Correction in Super-Resolution Microscopy Using the Single-Cluster PHD Filter

Isabel Schlangen, Jose Franco, Jeremie Houssineau, William T. E. Pitkeathly, Daniel Clark, Ihor Smal, Colin Rickman
2016 IEEE Journal on Selected Topics in Signal Processing  
Another consideration is that for the study of intracellular dynamics, multiple particles must be tracked at the same time, which is a challenging task due to problems such as the presence of false positives  ...  In this paper, a Bayesian approach is used to simultaneously track the locations of objects with different motion behaviors and the stage drift using image data obtained from fluorescence microscopy experiments  ...  ACKNOWLEDGMENT The authors would like to thank Francesco Tonolini, Isabella McKenna and Rachael Tobin (SUPA, Heriot-Watt University, Edinburgh) for their support and their work on object detection.  ... 
doi:10.1109/jstsp.2015.2506402 fatcat:pievbxiym5cetmgfirxqmisz2q
« Previous Showing results 1 — 15 out of 3,102 results