On Surface Completion and Image Inpainting by Biharmonic Functions: Numerical Aspects

Damelin, Steven B.; Hoang, N. S.

doi:10.1155/2018/3950312

Cited by 42 publications

(37 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Once the ionization front is removed from the original image, the gap is expended by a morphological dilation with a 20-pixel-diameter disk and filled using a standard inpainting technique (Damelin & Hoang 2018). This process fills the missing part by selecting similar textures available outside the mask.…”

Section: Ionization Front and H II Regionmentioning

confidence: 99%

Simulated JWST Data Sets for Multispectral and Hyperspectral Image Fusion

Guilloteau

Oberlin

Berné

et al. 2020

View full text Add to dashboard Cite

The James Webb Space Telescope (JWST) will provide multispectral and hyperspectral infrared images of a large number of astrophysical scenes. Multispectral images will have the highest angular resolution, while hyperspectral images (e.g., with integral field unit spectrometers) will provide the best spectral resolution. This paper aims at providing a comprehensive framework to generate an astrophysical scene and to simulate realistic hyperspectral and multispectral data acquired by two JWST instruments, namely, NIRCam Imager and NIRSpec IFU. We want to show that this simulation framework can be resorted to assess the benefits of fusing these images to recover an image of high spatial and spectral resolutions. To do so, we make a synthetic scene associated with a canonical infrared source, the Orion Bar. We develop forward models including corresponding noises for the two JWST instruments based on their physical features. JWST observations are then simulated by applying the forward models to the aforementioned synthetic scene. We test a dedicated fusion algorithm we developed on these simulated observations. We show that the fusion process reconstructs the high spatio-spectral resolution scene with a good accuracy on most areas, and we identify some limitations of the method to be tackled in future works. The synthetic scene and observations presented in the paper can be used, for instance, to evaluate instrument models, pipelines, or more sophisticated algorithms dedicated to JWST data analysis. Besides, fusion methods such as the one presented in this paper are shown to be promising tools to fully exploit the unprecedented capabilities of the JWST.

show abstract

Section: Ionization Front and H II Regionmentioning

confidence: 99%

Simulated JWST Data Sets for Multispectral and Hyperspectral Image Fusion

Guilloteau

Oberlin

Berné

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In order to obtain a simplistic, representation of the scalp map they were re-shaped into a 7x11 matrix that kept the spatial relation between electrodes. Missing values within this scalp matrix were inpainted (Damelin and Hoang (2018)) using the scikit-image library for Python. These low-resolution scalp maps were used as input for ConvDip (see Appendix 1 left column for an example).…”

Section: Convolutional Neural Network I/o Of Convdipmentioning

confidence: 99%

ConvDip: A convolutional neural network for better EEG Source Imaging

Hecker

Rupprecht

Elst

et al. 2020

Preprint

View full text Add to dashboard Cite

EEG and MEG are well-established non-invasive methods in neuroscientific research and clinical diagnostics. Both methods provide a high temporal but low spatial resolution of brain activity. In order to gain insight about the spatial dynamics of the M/EEG one has to solve the inverse problem, which means that more than one configuration of neural sources can evoke one and the same distribution of EEG activity on the scalp. Artificial neural networks have been previously used successfully to find either one or two dipoles sources. These approaches, however, have never solved the inverse problem in a distributed dipole model with more than two dipole sources. We present ConvDip, a novel convolutional neural network (CNN) architecture that solves the EEG inverse problem in a distributed dipole model based on simulated EEG data. We show that (1) ConvDip learned to produce inverse solutions from a single time point of EEG data and (2) outperforms state-of-the-art methods (eLORETA and LCMV beamforming) on all focused performance measures. (3) It is more flexible when dealing with varying number of sources, produces less ghost sources and misses less real sources than the comparison methods. (4) It produces plausible inverse solutions for real-world EEG recordings and needs less than 40 ms for a single forward pass. Our results qualify ConvDip as an efficient and easy-to-apply novel method for source localization in EEG and MEG data, with high relevance for clinical applications, e.g. in epileptology and real time applications.

show abstract

“…For the basic inpainting processes that we described in the previous paragraph, we tested three methods that had available software implementations. These were based on the fast marching [62], Navier-Stokes [63], and biharmonic [64] algorithms. Even though a quantitative comparison of the color correctness of the results is beyond the scope of this paper, we can state that the three methods create visually consistent and appealing urban footprints for our purpose, i.e., providing an engaging visual context to inform a policy maker or stakeholder of what might happen to a city and its surroundings across time and space.…”

Section: Urban Footprint Estimationmentioning

confidence: 99%

Spatiotemporal Modeling of Urban Growth Using Machine Learning

et al. 2019

View full text Add to dashboard Cite

This paper presents a general framework for modeling the growth of three important variables for cities: population distribution, binary urban footprint, and urban footprint in color. The framework models the population distribution as a spatiotemporal regression problem using machine learning, and it obtains the binary urban footprint from the population distribution through a binary classifier plus a temporal correction for existing urban regions. The framework estimates the urban footprint in color from its previous value, as well as from past and current values of the binary urban footprint using a semantic inpainting algorithm. By combining this framework with free data from the Landsat archive and the Global Human Settlement Layer framework, interested users can get approximate growth predictions of any city in the world. These predictions can be improved with the inclusion in the framework of additional spatially distributed input variables over time subject to availability. Unlike widely used growth models based on cellular automata, there are two main advantages of using the proposed machine learning-based framework. Firstly, it does not require to define rules a priori because the model learns the dynamics of growth directly from the historical data. Secondly, it is very easy to train new machine learning models using different explanatory input variables to assess their impact. As a proof of concept, we tested the framework in Valledupar and Rionegro, two Latin American cities located in Colombia with different geomorphological characteristics, and found that the model predictions were in close agreement with the ground-truth based on performance metrics, such as the root-mean-square error, zero-mean normalized cross-correlation, Pearson's correlation coefficient for continuous variables, and a few others for discrete variables such as the intersection over union, accuracy, and the f 1 metric. In summary, our framework for modeling urban growth is flexible, allows sensitivity analyses, and can help policymakers worldwide to assess different what-if scenarios during the planning cycle of sustainable and resilient cities.cities are also beacons of hope as they provide opportunities to their inhabitants to access to basic utilities (e.g., water, electricity, gas, internet), health facilities, employment with competitive wages, financial services, entertainment, technical training, formal education, and much more [13,14]. When diverse and skilled human capital interacts, cities can boost ecosystems of research, development, innovation, and entrepreneurship [15][16][17]. It is this duality between the challenges and benefits of cities that makes the understanding of their growth so important for us.To predict how cities are going to look like in the future, urban planners rely on historical data and urban growth models [10,[18][19][20] . These models can have multiple outputs, but they commonly provide estimations of binary urban footprints (i.e., maps with urban or non-urban categories) or population distr...

show abstract

On Surface Completion and Image Inpainting by Biharmonic Functions: Numerical Aspects

Cited by 42 publications

References 18 publications

Simulated JWST Data Sets for Multispectral and Hyperspectral Image Fusion

Simulated JWST Data Sets for Multispectral and Hyperspectral Image Fusion

ConvDip: A convolutional neural network for better EEG Source Imaging

Spatiotemporal Modeling of Urban Growth Using Machine Learning

Contact Info

Product

Resources

About