We describe a hierarchical probabilistic model for the detection and recognition of objects in cluttered, natural scenes. The model is based on a set of parts which describe the e...
Erik B. Sudderth, Antonio B. Torralba, William T. ...
In this paper we propose a new motion compensated prediction technique that enables successful predictive encoding during fades, blended scenes, temporally decorrelated noise, and...
Graphical structures such as Bayesian networks or Markov networks are very useful tools for representing irrelevance or independency relationships, and they may be used to e cientl...
We present Build-by-Number, a technique for quickly designing architectural structures that can be rendered photorealistically at interactive rates. We combine image-based capturi...
We have made a computer graphics model of Chang'an City when it was the capital of China during the Tang Dynasty (7-10th century). The real-time rendered images are projected...