We present an analytic solution to the problem of estimating multiple 2-D and 3-D motion models from two-view correspondences or optical flow. The key to our approach is to view th...
Mean shift is a popular method to segment images and videos. Pixels are represented by feature points, and the segmentation is driven by the point density in feature space. In thi...
We present a learning-based, sliding window-style approach for the problem of detecting humans in still images. Instead of traditional concatenation-style image location-based feat...
We present an unsupervised approach for learning a generative layered representation of a scene from a video for motion segmentation. The learnt model is a composition of layers, ...
M. Pawan Kumar, Philip H. S. Torr, Andrew Zisserma...
A novel stereo matching algorithm is proposed that utilizes color segmentation on the reference image and a selfadapting matching score that maximizes the number of reliable corre...