Efficiently Planning Coherent Visual Discourse

Michelle X. Zhou and Steven K. Feiner

Department of Computer Science
Columbia University 500 West 120th St.,
450 CS Building
New York, NY 10027
+1 212 939 7000
{zhou, feiner}@cs.columbia.edu


A visual discourse is a series of connected visual displays. A coherent visual discourse is characterized by smooth transitions between displays, consistent design within and across displays, and successful integration of new information into existing displays. We use a top-down, hierarchical decomposition, partial order planner to efficiently construct a visual discourse from scratch, taking advantage of parametrized primitive visual objects that serve as building blocks in the design process. Visual representations are modeled as visual objects, graphical techniques are employed as planning operators, and design policies are encoded as constraints. This approach not only improves computational efficiency compared to search-based approaches, but also facilitates knowledge encoding, and ensures global coherency.


The research described in this overview is supported in part by DARPA Contract DAAL01-94-K-0119, the Columbia Univeristy Center for Advanced Technology in High Performance Computing and Communications in Healthcare (funded by the New York State Science and Technology Foundation), the Columbia Center for Telecommunications Research under NSF Grant ECD-88-11111, ONR Contract N00014-97-1-0838.

Get a PostScript copy of the full version text and the figures.