File(s) under permanent embargo
Single image spectral reconstruction for multimedia applications
conference contribution
posted on 2015-01-01, 00:00 authored by Antonio Robles-KellyAntonio Robles-KellyIn this paper, we present a method which can perform spectral reconstruction and illuminant recovery from a single colour image making use of an unlabelled training set of hyperspectral images. Our method employs colour and appearance information to drive the reconstruction process subject to the material properties of the objects in the scene. The idea is to reconstruct the image spectral irradiance making use of a set of prototypes extracted from the training set. These spectra, together with a set of convolutional features are hence obtained using sparse coding so as to reconstruct the image irradiance. With the reconstructed spectra in hand, we proceed to compute the illuminant power spectrum using a quadratic optimisation approach. We provide a quantitative analysis for our method and compare to a number of alternatives. We also show sample results on illuminant substitution and transfer, film simulation and image recolouring using mood board colour schemes.
History
Event
Multimedia. International Conference (23rd : 2015 : Brisbane, Queensland)Pagination
251 - 260Publisher
ACMLocation
Brisbane, QueenslandPlace of publication
New York, N.Y.Publisher DOI
Start date
2015-10-26End date
2015-10-30ISBN-13
9781450334594Language
engPublication classification
E1.1 Full written paper - refereedCopyright notice
2015, ACMTitle of proceedings
MM 2015 : Proceedings of the 23rd ACM International Conference on MultimediaUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC