Appearance Sampling for Obtaining A Set of Basis Images for Variable Illumination

• Authors: Imari Sato;Takahiro Okabe;Yoichi Sato;Katsushi Ikeuchi
• Venue: ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
• Year: 2003

Previous studies have demonstrated that the appearance ofan object under varying illumination conditions can be representedby a low-dimensional linear subspace. A set ofbasis images spanning such a linear subspace can be obtainedby applying the principal component analysis (PCA)for a large number of images taken under different lightingconditions. While the approaches based on PCA havebeen used successfully for object recognition under varyingillumination conditions, little is known about how many imageswould be required in order to obtain the basis imagescorrectly. In this study, we present a novel method for analyticallyobtaining a set of basis images of an object forarbitrary illumination from input images of the object takenunder a point light source. The main contribution of ourwork is that we show that a set of lighting directions canbe determined for sampling images of an object dependingon the spectrum of the object's BRDF in the angularfrequency domain such that a set of harmonic images canbe obtained analytically based on the sampling theorem onspherical harmonics. In addition, unlike the previously proposedtechniques based on spherical harmonics, our methoddoes not require the 3D shape and reflectance properties ofan object used for rendering harmonics images of the objectsynthetically.