This paper introduces an extension of Hartley's selfcalibration technique [8] based on properties of the essential matrix, allowing for the stable computation of varying foca...
We consider learning models for object recognition from examples. Our method is motivated by systems that use the Hausdorff distance as a shape comparison measure. Typically an ob...
We present a general method of catadioptric sensor design for realizing prescribed projections. Our method makes use of geometric distributions in 3-dimensional space, which are g...
We consider the problem of estimating the shape and radiance of an object from a calibrated set of views under the assumption that the reflectance of the object is nonLambertian. ...
We develop a multi-class object detection framework whose core component is a nearest neighbor search over object part classes. The performance of the overall system is critically...