Soft Colour Segmentation On Light Fields
Citation:
Matysiak, P., Grogan, M., Aenchbacher, W., Smolic, A., "Soft Colour Segmentation On Light Fields", 2020 IEEE International Conference on Image Processing (ICIP), Abu Dhabi, United Arab Emirates, 2020, pp. 2621-2625Download Item:
Matysiak_LFSoftcolourSeg_CameraReady.pdf (AAM(peer reviewed)) 4.731Mb
Abstract:
In this work we explore methods for allowing advanced colour editing on light field images to be performed. This investigation is twofold. First we look at soft colour algorithms to decompose images into colour layers and the various ways it could be applied to light field data in order to ensure spatially consistent results. Then, with the purpose of colour editing in mind, we present an object-based layer separation method so that editing a layer does not wrongly affect specific objects. We further discuss the advantages and drawbacks that light field data present over regular single-view images for this purpose. Finally we present some editing results to show that our methods allow us to obtain visually appealing images that remain consistent across all light field views and minimise the colour artefacts inherent to layer decomposition methods.
Sponsor
Grant Number
Science Foundation Ireland (SFI)
15/RP/2776
Author's Homepage:
http://people.tcd.ie/smolica
Author: Smolic, Aljosa
Type of material:
Conference PaperCollections:
Availability:
Full text availableSubject (TCD):
Creative Technologies , Computer Education/Literacy , Information technology in education , Multimedia & CreativityDOI:
10.1109/ICIP40778.2020.9190716Licences: