Given an arbitrary image, our goal is to segment all distinct
texture subimages. This is done by discovering distinct,
cohesive groups of spatially repeating patterns, called tex...
Particle filters have proven to be an effective tool for visual tracking in non-gaussian, cluttered environments. Conventional particle filters however do not scale to the problem...
Jonathan Deutscher, Andrew J. Davison, Ian D. Reid
This paper presents a novel approach for reconstructing free-form, texture-mapped, 3D scene models from a single painting or photograph. Given a sparse set of user-specified const...
Li Zhang, Guillaume Dugas-Phocion, Jean-Sebastien ...
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...
We present a parameter free approach that utilizes multiple cues for image segmentation. Beginning with an image, we execute a sequence of bottom-up aggregation steps in which pix...