Sketch-based instancing of parameterized 3D models

We present a system for constructing 3D models from simple hand-drawn sketches. The system exploits a priori knowledge about the type of object being sketched. In particular, we assume that the class of object being drawn is known, (e.g., a rocket ship) and that the object will be drawn using a fixe...

Full description

Bibliographic Details
Main Author: Xiao, Dan
Format: Others
Language:English
Published: 2009
Online Access:http://hdl.handle.net/2429/15812
id ndltd-UBC-oai-circle.library.ubc.ca-2429-15812
record_format oai_dc
spelling ndltd-UBC-oai-circle.library.ubc.ca-2429-158122018-01-05T17:37:58Z Sketch-based instancing of parameterized 3D models Xiao, Dan We present a system for constructing 3D models from simple hand-drawn sketches. The system exploits a priori knowledge about the type of object being sketched. In particular, we assume that the class of object being drawn is known, (e.g., a rocket ship) and that the object will be drawn using a fixed number of known components. By using these assumptions, we show that we can build a sketch-based modeling system that, while object specific, is capable of quickly creating geometric models that are beyond the scope of current sketch-based modeling approaches. Key to our approach is the use of a K-means classifier for labeling each drawn stroke as being a particular component in the generic model. We demonstrate our approach by applying this classifier to face and rocket sketches. Science, Faculty of Computer Science, Department of Graduate 2009-11-26T20:59:53Z 2009-11-26T20:59:53Z 2004 2004-11 Text Thesis/Dissertation http://hdl.handle.net/2429/15812 eng For non-commercial purposes only, such as research, private study and education. Additional conditions apply, see Terms of Use https://open.library.ubc.ca/terms_of_use. 3387561 bytes application/pdf
collection NDLTD
language English
format Others
sources NDLTD
description We present a system for constructing 3D models from simple hand-drawn sketches. The system exploits a priori knowledge about the type of object being sketched. In particular, we assume that the class of object being drawn is known, (e.g., a rocket ship) and that the object will be drawn using a fixed number of known components. By using these assumptions, we show that we can build a sketch-based modeling system that, while object specific, is capable of quickly creating geometric models that are beyond the scope of current sketch-based modeling approaches. Key to our approach is the use of a K-means classifier for labeling each drawn stroke as being a particular component in the generic model. We demonstrate our approach by applying this classifier to face and rocket sketches. === Science, Faculty of === Computer Science, Department of === Graduate
author Xiao, Dan
spellingShingle Xiao, Dan
Sketch-based instancing of parameterized 3D models
author_facet Xiao, Dan
author_sort Xiao, Dan
title Sketch-based instancing of parameterized 3D models
title_short Sketch-based instancing of parameterized 3D models
title_full Sketch-based instancing of parameterized 3D models
title_fullStr Sketch-based instancing of parameterized 3D models
title_full_unstemmed Sketch-based instancing of parameterized 3D models
title_sort sketch-based instancing of parameterized 3d models
publishDate 2009
url http://hdl.handle.net/2429/15812
work_keys_str_mv AT xiaodan sketchbasedinstancingofparameterized3dmodels
_version_ 1718590017421443072