• Publications
  • Influence
From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose
TLDR
We present a generative appearance-based method for recognizing human faces under variation in lighting and viewpoint. Expand
From few to many: generative models for recognition under variable pose and illumination
TLDR
This paper presents appearance-based methods which, unlike previous appearance- based approaches, require only a small set of training images to generate a rich representation that models this variability. Expand
Illumination cones for recognition under variable lighting: faces
TLDR
This paper presents an appearance-based method for modeling the variability due to illumination in the images of objects. Expand
Incorporating the Torrance and Sparrow model of reflectance in uncalibrated photometric stereo
  • A. Georghiades
  • Computer Science
  • Proceedings Ninth IEEE International Conference…
  • 13 October 2003
TLDR
We consider the use of a more general reflectance model, namely the Torrance and Sparrow model, in uncalibrated photometric stereo to resolve the GBR ambiguity up to the binary convex/concave ambiguity. Expand
Recovering 3-D Shape and Reflectance From a Small Number of Photographs
TLDR
We present an image based technique that uses only a small number of example images, and assumes a parametric model of reflectance, to simultaneously and reliably recover the Bidirectional Reflectance Distributions Function (BRDF) and the 3-D shape of non-Lambertian objects. Expand
Edge-Directed Hardware Architecture for Real-Time Disparity Map Computation
TLDR
In this paper, we present a disparity map computation architecture targeting embedded stereo vision applications with hard real-time requirements in emerging embedded vision systems. Expand
Context-aware textures
TLDR
We show the results of complex, geometry-dependent textures evolving on synthetic objects as the result of external chemical, mechanical, and biological agents. Expand
Illumination-based image synthesis: creating novel images of human faces under differing pose and lighting
TLDR
We present an illumination-based method for synthesizing images of an object under novel viewing conditions. Expand
Towards hardware stereoscopic 3D reconstruction a real-time FPGA computation of the disparity map
TLDR
We present an architecture of a 3D reconstruction system for stereoscopic images, which is configurable in terms of various application parameters, making it suitable for a number of application environments. Expand
Observing and Transferring Material Histories
We consider the problem of modeling objects composed of materials that change over the course of time. First principles simulation of the processes that cause material change are eitherExpand
...
1
2
...