We introduce a new task-independent framework to model top-down overt visual attention based on graphical models for probabilistic inference and reasoning. We describe a Dynamic B...
Abstract. The problem of searching for a model-based scene interpretation is analyzed within a probabilistic framework. Object models are formulated as generative models for range ...
We present a system for creating and manipulating layered procedural surface editing operations, which is motivated by the limited support for iterative design in free-form modeli...
The reuse of well-tested and optimized design objects is an important aspect for decreasing design times, increasing design quality, and improving the predictability of designs. R...
Two new techniques are proposed to improve stereo matching performance in this work. First, to address the disparity discontinuity problem in occluded regions, we present a dispar...