Sciweavers

326 search results - page 30 / 66
» Recovering Intrinsic Images using an Illumination Invariant ...
Sort
View
AAAI
1993
14 years 11 months ago
Learning Object Models from Appearance
We address the problem of automatically learning object models for recognition and pose estimation. In contrast to the traditional approach, we formulate the recognition problem a...
Hiroshi Murase, Shree K. Nayar
ECCV
2002
Springer
1127views Computer Vision» more  ECCV 2002»
15 years 11 months ago
Removing Shadows from Images
Illumination conditions cause problems for many computer vision algorithms. Inparticular, shadows in an image can cause segmentation, tracking, or recognition algorithms to fail. I...
Graham D. Finlayson, Steven D. Hordley, Mark S. Dr...
CVPR
2005
IEEE
15 years 11 months ago
Indexing with Unknown Illumination and Pose
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...
Ira Kemelmacher, Ronen Basri
CVPR
2012
IEEE
13 years 4 days ago
Intrinsic shape context descriptors for deformable shapes
In this work, we present intrinsic shape context (ISC) descriptors for 3D shapes. We generalize to surfaces the polar sampling of the image domain used in shape contexts: for this...
Iasonas Kokkinos, Michael M. Bronstein, Roee Litma...
ECCV
2008
Springer
15 years 11 months ago
Compressive Structured Light for Recovering Inhomogeneous Participating Media
We propose a new method named compressive structured light for recovering inhomogeneous participating media. Whereas conventional structured light methods emit coded light patterns...
Jinwei Gu, Shree K. Nayar, Eitan Grinspun, Peter N...