Shape from texture has received much attention in the past few decades. We propose a computationally efficient method to extract the 3D shape of developable surfaces from the spect...
We explore the possibility of recognizing the surface material from a single image with unknown illumination, given the shape of the surface. Model-based PCA is used to create a lo...
A spatio-temporal representation for complex optical flow events is developed that generalizes traditional parameterized motion models (e.g. affine). These generative spatio-tempo...
SIFT has been proven to be the most robust local invariant feature descriptor. SIFT is designed mainly for gray images. However, color provides valuable information in object desc...
In this paper, we present a system to detect passenger cars in aerial images where car appears small. We post the detection as a 3D object recognition problem to account for the v...