Intrinsic Image Evaluation On Synthetic Complex Scenes
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-truth
procedures 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 data
set we aim to motivate researchers to further explore intrinsic
image decomposition in complex scenes.
Images and movies
BibTex references
@InProceedings\{BSV2013, author = "Shida Beigpour and Marc Serra and Joost van de Weijer and Robert Benavente and Maria Vanrell and Olivier Penacchio and Dimitris Samaras", title = "Intrinsic Image Evaluation On Synthetic Complex Scenes", booktitle = "IEEE International Conference on Image Processing (ICIP 2013)", year = "2013", address = "Melbourne, Australia", abstract = "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-truth procedures 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 data set we aim to motivate researchers to further explore intrinsic image decomposition in complex scenes.", url = "http://cat.cvc.uab.es/Public/Publications/2013/BSV2013" }