%0 Conference Proceedings
%T Intrinsic Image Evaluation On Synthetic Complex Scenes
%A Shida Beigpour
%A Marc Serra
%A Joost Van de Weijer
%A Robert Benavente
%A Maria Vanrell
%A Olivier Penacchio
%A Dimitris Samaras
%B 20th IEEE International Conference on Image Processing
%D 2013
%F Shida Beigpour2013
%O CIC; 600.048; 600.052; 600.051
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2264), last updated on Fri, 04 Feb 2022 13:09:01 +0100
%X Scene decomposition into its illuminant, shading, and reflectance intrinsic images is an essential step for scene understanding. Collecting intrinsic image groundtruth data is a laborious task. The assumptions on which the ground-truthprocedures are based limit their application to simple scenes with a single object taken in the absence of indirect lighting and interreflections. We investigate synthetic data for intrinsic image research since the extraction of ground truth is straightforward, and it allows for scenes in more realistic situations (e.g, multiple illuminants and interreflections). With this dataset we aim to motivate researchers to further explore intrinsic image decomposition in complex scenes.
%U http://refbase.cvc.uab.es/files/BSW2013.pdf
%U http://dx.doi.org/10.1109/ICIP.2013.6738059
%P 285-289