A Caltech Library Service

Creating Generative Models from Range Images

Ramamoorthi, Ravi (1998) Creating Generative Models from Range Images. Computer Science Technical Reports, 1998.05. California Institute of Technology , Pasadena, CA. (Unpublished)

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


We describe a new approach for creating concise high-level generative models from one or more approximate range images. Using simple acquisition techniques and a user-defined class of models, our method produces a simple and intuitive object description that is relatively insensitive to noise and is easy to manipulate and edit. The algorithm has two inter-related phases -- recognition, which chooses an appropriate model within a given hierarchy, and parameter estimation, which adjusts the model to fit the data. We give a simple method for automatically making tradeoffs between simplicity and accuracy to determine the best model. We also describe general techniques to optimize a specific generative model. In particular, we address the problem of creating a suitable objective function that is sufficiently continuous for use with finite-difference based optimization techniques. Our technique for model recovery and subsequent manipulation and editing is demonstrated on real objects -- a spoon, bowl, ladle, and cup -- using a simple tree of possible generative models. We believe that higher-level model representations are extremely important, and their recovery for actual objects is a fertile area of research towards which this thesis is a step. However, our work is preliminary and there are currently several limitations. The user is required to create a model hierarchy (and supply methods to provide an initial guess for model parameters within this hierarchy); the use of a large pre-defined class of models can help alleviate this problem. Further, we have demonstrated our technique on only a simple tree of generative models. While our approach is fairly general, a real system would require a tree that is significantly larger. Our methods work only where the entire object can be accurately represented as a single generative model; future work could use constructive solid geometry operations on simple generative models to represent more complicated shapes. We believe that many of the above limitations can be addressed in future work, allowing us to easily acquire and process three-dimensional shape in a simple, intuitive and efficient manner.

Item Type:Report or Paper (Technical Report)
Related URLs:
URLURL TypeDescription ItemCaltech Masters thesis
Additional Information:Firstly, I would like to thank my advisor, Jim Arvo, for being a constant source of ideas and inspiration, and for creating many of the illustrations in the text. My former advisor, Al Barr, deserves special mention for guiding me during my first steps in research, and for many preliminary discussions on the subject matter contained in these pages. Jean-Yves Bouguet provided many helpful hints for data acquisition, and made many insightful comments that have significantly improved the quality of exposition. This thesis represents only one part of the wonderful experience I’ve had these past 4 years as an undergraduate at Caltech, and I would like to take this opportunity to thank other faculty members who have mentored me during the course of research projects—Brad Werner, and K. Mani Chandy. Tom Tombrello deserves special thanks for the Phil program, a model for undergraduate research. I would like to thank all the students of the Computer Science Department for support over the years, and especially the members of the Graphics Group. Most of my years as an undergraduate here have been spent in Blacker Hovse, and I thank each of its inhabitants for making it such a great place to live in. I thank my sister, Roopa, for her advice and unflagging encouragement; and my parents for their unwavering support.
Group:Computer Science Technical Reports
Series Name:Computer Science Technical Reports
Issue or Number:1998.05
Record Number:CaltechCSTR:1998.cs-tr-98-05
Persistent URL:
Usage Policy:You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.
ID Code:26837
Deposited By: Tony Diaz
Deposited On:30 Apr 2001
Last Modified:03 Oct 2019 03:18

Repository Staff Only: item control page