conference paper

Conference/ProceedingsIrish Machine Vision and Image Processing Conference
Start date29.08.2018
End date31.08.2018
AddressBelfast, North Ireland
Author(s)Simone Croci, Mairead Grogan, Sebastian Knorr, Aljosa Smolic
TitleColour Correction for Stereoscopic Omnidirectional Images
AbstractStereoscopic omnidirectional images (ODI) when viewed with a head-mounted display are a way to generate an immersive experience. Unfortunately, their creation is not an easy process, and different problems can be present in the ODI that can reduce the quality of experience. A common problem is colour mismatch, which occurs when the colours of the objects in the scene are different between the two stereoscopic views. In this paper we propose a novel method for the correction of colour mismatch based on the subdivision of ODIs into patches, where local colour correction transformations are fitted and then globally combined. The results presented in the paper show that the proposed method is able to reduce the colour mismatch in stereoscopic ODIs.
Key wordsVirtual reality, 360-video, colour matching, binocular rivalry, stereoscopic 3D