Learning sparse representations on the sphere - Archive ouverte HAL Access content directly
Journal Articles Astronomy and Astrophysics - A&A Year : 2019

Learning sparse representations on the sphere

(1) , (2) , (2) , (3, 1) , (2)


Many representation systems on the sphere have been proposed in the past, such as spherical harmonics, wavelets, or curvelets. Each of these data representations is designed to extract a specific set of features, and choosing the best fixed representation system for a given scientific application is challenging. In this paper, we show that one can directly learn a representation system from given data on the sphere. We propose two new adaptive approaches: the first is a (potentially multiscale) patch-based dictionary learning approach, and the second consists in selecting a representation from among a parametrized family of representations, the α-shearlets. We investigate their relative performance to represent and denoise complex structures on different astrophysical data sets on the sphere.
Fichier principal
Vignette du fichier
aa34041-18.pdf (6.05 Mo) Télécharger le fichier
Origin : Publication funded by an institution

Dates and versions

cea-03012045 , version 1 (18-11-2020)



F. Sureau, F. Voigtlaender, M. Wust, J.-L. Starck, G. Kutyniok. Learning sparse representations on the sphere. Astronomy and Astrophysics - A&A, 2019, 621, pp.A73. ⟨10.1051/0004-6361/201834041⟩. ⟨cea-03012045⟩
21 View
33 Download



Gmail Facebook Twitter LinkedIn More