Indexing with Unknown
Illumination and Pose
Ira Kemelmacher
Ronen Basri
Weizmann Institute of Science
Abstract: The task of identifying
3D objects in 2D images is difficult due to variation in objects’ appearance
with changes in pose and lighting. The task is further complicated by the
presence of occlusion and clutter. Shape indexing is a method for rapid
association between features identified in an image and their corresponding 3D
features stored in a database. Previous indexing methods ignored variations due
to lighting, restricting the approach to polyhedral objects. In this paper, we
further develop these methods to handle variations in both pose and lighting. We
focus on rigid objects undergoing a scaled-orthographic projection and use
spherical harmonics to represent lighting. The resulting integrated algorithm
can recognize 3D objects from a single input image; furthermore, it recovers the
pose and lighting of each familiar object in the given image. The algorithm has
been tested on a database of real objects, demonstrating its performance on
cluttered scenes under a variety of poses and illumination conditions.
Keywords: indexing, identification of 3D objects, arbitrary lighting,
arbitrary pose, single images, recognition of familiar objects.
For each result we
present the input image, image with image points used painted in colors to
indicate the models they have voted for where large concentrations of points
that vote for the correct model are seen in regions where an object appears, and
the output image with winning objects rendered under the recovered
lighting and poses.
Indoor scene:
Outdoor scene:
Night scene:
CVPR'05 Paper: [PDF]
3D laser scans database: [webpage]
Presentation: [PPT]
[PDF]
Reference:
@article{KemelmacherBasri_CVPR05,
author = {"Ira Kemelmacher and Ronen Basri"},
title = {"Indexing with Unknown Illumination and Pose."},
journal = {"IEEE Conference on Computer Vision and Pattern Recognition"},
year = {"2005"}
pages = {"909--916"}
volume={"1"}
}