Title :
The generic viewpoint assumption and planar bias
Author :
Yuille, A.L. ; Coughlan, James M. ; Konishi, S.
Author_Institution :
Stnith-Kettlewell Eye Res. Inst., San Francisco, CA, USA
fDate :
6/1/2003 12:00:00 AM
Abstract :
We show that generic viewpoint and lighting assumptions resolve standard visual ambiguities by biasing toward planar surfaces. Our model uses orthographic projection with a two-dimensional affine warp and Lambertian reflectance functions, including cast and attached shadows. We use uniform priors on nuisance variables such as viewpoint direction and the light source. Limitations of using uniform priors on nuisance variables are discussed.
Keywords :
computational geometry; computer vision; inference mechanisms; lighting; uncertainty handling; Bayesian inference; Lambertian reflectance functions; computer vision; generic viewpoint assumption; light source; lighting; nuisance variables; orthographic projection; planar bias; planar surfaces; shadows; standard visual ambiguities; two-dimensional affine warp; viewpoint direction; Bayesian methods; Cameras; Geometry; Light sources; Photometry; Reflectivity; Shadow mapping; Shape; Surface treatment; Yield estimation;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2003.1201826