Benutzer: Gast  Login
Titel:

UnCRtainTS: Uncertainty Quantification for Cloud Removal in Optical Satellite Time Series

Dokumenttyp:
Konferenzbeitrag
Autor(en):
Ebel, Patrick; Garnot, Vivien Sainte Fare; Schmitt, Michael; Wegner, Jan; Zhu, Xiao Xiang
Abstract:
Clouds and haze often occlude optical satellite images, hindering continuous, dense monitoring of the Earth's surface. Although modern deep learning methods can implicitly learn to ignore such occlusions, explicit cloud removal as pre-processing enables manual interpretation and allows training models when only few annotations are available. Cloud removal is challenging due to the wide range of occlusion scenarios -- from scenes partially visible through haze, to completely opaque cloud coverage...     »
Dewey-Dezimalklassifikation:
000 Informatik, Wissen, Systeme
Kongress- / Buchtitel:
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops
Ausrichter der Konferenz:
IEEE
Jahr:
2023
WWW:
https://arxiv.org/abs/2304.05464
 BibTeX