Algorithms for exploring and controlling procedural models
Abstract/Contents
- Abstract
- Enabling ordinary people to create high-quality 3D models is a long-standing problem in computer graphics. While much recent work has focused on the development of more sophisticated systems for geometric modeling, procedural techniques provide powerful means for generating complex geometric structures such as those commonly found in botany and architecture. Procedural representations are also notoriously difficult to interact with and control. In this thesis, we contribute two algorithms for making procedural modeling more accessible. We first draw from the literature on design and human cognition to better understand the design processes of novice and casual modelers, whose goals and motivations are often distinct from those of professional artists. We use this understanding to propose a collaborative system for exploratory modeling, in which users navigate a complex "design space" of parametric models using a simple, two-dimensional map interface. As users save models for their own personal use, their actions are communicated to a shared repository to improve the performance of the method, resulting in a self-reinforcing system that becomes easier to use as more people participate. Next, we present a method for bringing artistic control to grammar-based procedural models. Given a grammar and a high-level specification of a desired model, our algorithm computes a production from the grammar that conforms to the specification. This production is generated by optimizing over the language of the grammar using trans-dimensional Markov chain Monte Carlo inference. No interaction with the grammar itself is required, and the input specification can take many forms, such as a sketch, a volumetric shape, or an analytical objective.
Description
| Type of resource | text |
|---|---|
| Form | electronic; electronic resource; remote |
| Extent | 1 online resource. |
| Publication date | 2011 |
| Issuance | monographic |
| Language | English |
Creators/Contributors
| Associated with | Talton, Jerry O |
|---|---|
| Associated with | Stanford University, Computer Science Department |
| Primary advisor | Koltun, Vladlen, 1980- |
| Thesis advisor | Koltun, Vladlen, 1980- |
| Thesis advisor | Goodman, Noah |
| Thesis advisor | Hanrahan, P. M. (Patrick Matthew) |
| Advisor | Goodman, Noah |
| Advisor | Hanrahan, P. M. (Patrick Matthew) |
Subjects
| Genre | Theses |
|---|
Bibliographic information
| Statement of responsibility | Jerry O. Talton. |
|---|---|
| Note | Submitted to the Department of Computer Science. |
| Thesis | Ph.D. Stanford University 2011 |
| Location | electronic resource |
Access conditions
- Copyright
- © 2011 by Jerry Oscar Talton
- License
- This work is licensed under a Creative Commons Attribution Non Commercial No Derivatives 3.0 Unported license (CC BY-NC-ND).
Also listed in
Loading usage metrics...