Sketch-Based Tree Modeling Using Markov Random Field

被引:60
作者
Chen, Xuejin [1 ]
Neubert, Boris [2 ]
Xu, Ying-Qing
Deussen, Oliver [2 ]
Kang, Sing Bing
机构
[1] Univ Sci & Technol China, Hefei, Peoples R China
[2] Univ Konstanz, D-7750 Constance, Germany
来源
ACM TRANSACTIONS ON GRAPHICS | 2008年 / 27卷 / 05期
关键词
Sketching; tree modeling; geometric modeling; Markov random field;
D O I
10.1145/1409060.1409062
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
In this paper, we describe a new system for converting a user's freehand sketch of a tree into a full 3D model that is both complex and realistic-looking. Our system does this by probabilistic optimization based on parameters obtained from a database of tree models. The best matching model is selected by comparing its 2D projections with the sketch. Branch interaction is modeled by a Markov random field, subject to the constraint of 3D projection to sketch. Our system then uses the notion of self-similarity to add new branches before finally populating all branches with leaves of the user's choice. We show a variety of natural-looking tree models generated from freehand sketches with only a few strokes.
引用
收藏
页数:9
相关论文
共 19 条
[1]  
[Anonymous], SIGGRAPH, DOI DOI 10.1145/237170.237279
[2]  
Bishop C. M., 2006, Pattern Recognition and Machine Learning, P179
[3]  
de Reffye P., 1988, Computer Graphics, V22, P151, DOI 10.1145/378456.378505
[4]   STRANDS, GRAVITY AND BOTANICAL TREE IMAGERY [J].
HOLTON, M .
COMPUTER GRAPHICS FORUM, 1994, 13 (01) :57-67
[5]  
Ijiri T, 2006, LECT NOTES COMPUT SC, V4073, P138
[6]  
Jirasek C., 2000, PLANT BIOMECHANICS 2, P615
[7]  
LAMDAN Y, 1988, COMPUTER VISION PATT, P335, DOI DOI 10.1109/CVPR.1988.196257
[9]   Interactive modeling of plants [J].
Lintermann, B ;
Deussen, O .
IEEE COMPUTER GRAPHICS AND APPLICATIONS, 1999, 19 (01) :56-65
[10]   Approximate image-based tree-modeling using particle flows [J].
Neubert, Boris ;
Franken, Thomas ;
Deussen, Oliver .
ACM TRANSACTIONS ON GRAPHICS, 2007, 26 (03)