Abstract: 

Complex reflectance phenomena such as specular reflections confound many vision problems since they produce image `features' that do not correspond directly to intrinsic surface properties such as shape and spectral reflectance. A common approach to mitigate these effects is to explore functions of an image that are invariant to these photometric events. In this paper we describe two such invariants— one invariant to specular reflections, and the other invariant to both specular reflections and diffuse shading—that result from exploiting color information in images of dichromatic surfaces. These invariants are derived from subspaces of RGB color space, and they enable the application of Lambertian-based vision techniques to a broad class of specular, non-Lambertian scenes. Using implementations of recent algorithms taken from the literature, we demonstrate the practical utility of these invariants for a wide variety of applications, including stereo, shape from shading, material-based segmentation, and motion estimation.

Results: Stereo   Optical Flow   Generalized Hue

RGB Color Image	Blue Invariant	Yellow Invariant	Specular Invariant

Publications: 

• Todd Zickler, Satya P. Mallick, David J. Kriegman, and Peter N. Belhumeur "Color Subspaces as Photometric Invariants.", submitted to International Journal of Computer Vision.

• Todd Zickler, Satya P. Mallick, David J. Kriegman, and Peter N. Belhumeur "Color Subspaces as Photometric Invariants.", Computer Vision and Pattern Recongnition, Volume II, Pages 2000-2010, June 2006, New York.