Paper published in a book (Scientific congresses, symposiums and conference proceedings)
Low-light image enhancement of permanently shadowed lunar regions with physics-based machine learning
Moseley, Ben; Bickel, Valentin; Lopez-Francos, Ignacio et al.
2020In Low-light image enhancement of permanently shadowed lunar regions with physics-based machine learning
Peer reviewed
 

Files


Full Text
m4g2_neurips.pdf
Author preprint (4.18 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
Machine learning; Remote sensing; Lunar exploration
Abstract :
[en] Finding water(-ice) on the Moon is key to enabling a sustainable human presence on the Moon and beyond. There is evidence that water-ice is abundant in and around the Moon’s Permanently Shadowed Regions (PSRs), however, direct visual detection has not yet been possible. Surface ice or related physical features could potentially be directly detected from high-resolution optical imagery, but, due to the extremely low-light conditions in these areas, high levels of sensor and photon noise make this very challenging. In this work we generate high-resolution, low-noise optical images over lunar PSRs by using two physics-based deep neural networks to model and remove CCD-related and photon noise in existing low-light optical imagery, potentially paving the way for a direct water-ice detection method.
Disciplines :
Computer science
Author, co-author :
Moseley, Ben;  University of Oxford
Bickel, Valentin;  MPS Goettingen & ETH Zurich
Lopez-Francos, Ignacio;  NASA Ames Research Center
Rana, Loveneesh ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > Remote Sensing
Olivares Mendez, Miguel Angel ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > Space Robotics
Wingo, Dennis;  Skycorp Inc.
Zuniga, Allison;  NASA Ames Research Center
Subtil, Nuno;  Nvidia
D’Eon, Eugene;  Nvidia
External co-authors :
yes
Language :
English
Title :
Low-light image enhancement of permanently shadowed lunar regions with physics-based machine learning
Publication date :
December 2020
Event name :
Conference on Neural Information Processing Systems, NeurIPS
Event date :
from 6-12-2020 to 12-12-2020
Main work title :
Low-light image enhancement of permanently shadowed lunar regions with physics-based machine learning
Peer reviewed :
Peer reviewed
Available on ORBilu :
since 15 January 2021

Statistics


Number of views
401 (61 by Unilu)
Number of downloads
316 (26 by Unilu)

Bibliography


Similar publications



Contact ORBilu