ACM Home Page
Please provide us with feedback. Feedback
Data-driven curvature for real-time line drawing of dynamic scenes
Full text PdfPdf (17.57 MB)
Source
ACM Transactions on Graphics (TOG) archive
Volume 28 ,  Issue 1  (January 2009) table of contents
Article No. 11  
Year of Publication: 2009
ISSN:0730-0301
Authors
Evangelos Kalogerakis  University of Toronto, Ontario, Canada
Derek Nowrouzezahrai  University of Toronto, Ontario, Canada
Patricio Simari  University of Toronto, Ontario, Canada
James Mccrae  University of Toronto, Ontario, Canada
Aaron Hertzmann  University of Toronto, Ontario, Canada
Karan Singh  University of Toronto, Ontario, Canada
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 30,   Downloads (12 Months): 367,   Citation Count: 1
Additional Information:

appendices and supplements   abstract   references   cited by   index terms   collaborative colleagues  

Tools and Actions: Request Permissions Request Permissions    Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/1477926.1477937
What is a DOI?

APPENDICES and SUPPLEMENTS
Ist supplemental movie file for Data-driven curvature for real-time line drawing of dynamic scenes


ABSTRACT

This article presents a method for real-time line drawing of deforming objects. Object-space line drawing algorithms for many types of curves, including suggestive contours, highlights, ridges, and valleys, rely on surface curvature and curvature derivatives. Unfortunately, these curvatures and their derivatives cannot be computed in real-time for animated, deforming objects. In a preprocessing step, our method learns the mapping from a low-dimensional set of animation parameters (e.g., joint angles) to surface curvatures for a deforming 3D mesh. The learned model can then accurately and efficiently predict curvatures and their derivatives, enabling real-time object-space rendering of suggestive contours and other such curves. This represents an order-of-magnitude speedup over the fastest existing algorithm capable of estimating curvatures and their derivatives accurately enough for many different types of line drawings. The learned model can generalize to novel animation sequences and is also very compact, typically requiring a few megabytes of storage at runtime. We demonstrate our method for various types of animated objects, including skeleton-based characters, cloth simulation, and blend-shape facial animation, using a variety of nonphotorealistic rendering styles.

An important component of our system is the use of dimensionality reduction for differential mesh data. We show that Independent Component Analysis (ICA) yields localized basis functions, and gives superior generalization performance to that of Principal Component Analysis (PCA).


REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

 
1
Bartlett, M., Movellan, J., and Sejnowski, T. 2002. Face recognition by independent component analysis. IEEE Trans. Neural Netw. 13, 6, 1450--1464.
 
2
Bell, A. J. and Sejnowski, T. J. 1997. The independent components of natural scenes are edge filters. Vision Res. 37, 3327--3338.
 
3
 
4
5
 
6
 
7
8
9
10
 
11
 
12
Eigensatz, M., Sumner, R. W., and Pauly, M. 2008. Curvature-Domain shape processing. In Proceedings of the EuroGraphics Computer Graphics Forum 27, 2, 241--250.
13
14
15
 
16
 
17
 
18
Hyvärinen, A. 1999. Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans. Neural Netw. 10, 3, 626--634.
 
19
20
21
22
 
23
24
 
25
 
26
 
27
Meyer, M., Desbrun, M., Schröder, P., and Barr, A. H. 2002. Discrete differential-geometry operators for triangulated 2-manifolds. In Visualization and Mathematics III, 35--57.
28
29
 
30
Nocedal, J. and Wright, S. J. 1999. Numerical Optimization. Springer-Verlag.
31
 
32
Nowrouzezahrai, D., Kalogerakis, E., and Fiume, E. 2009. Shadowing dynamic scenes with arbitrary BRDFs. In Proceedings of the EuroGraphics Conference. To appear.
 
33
Nowrouzezahrai, D., Kalogerakis, E., Simari, P., and Fiume, E. 2008. Shadowed relighting of dynamic geometry with 1d BRDFs. In Proceedings of the EuroGraphics Conference .
34
35
 
36
Pauly, M., Keiser, R., and Gross, M. 2003. Multi-Scale feature extraction on point-sampled surfaces. In Proceedings of EuroGraphics Conference. 281--289.
 
37
Polthier, K. 2002. Polyhedral surfaces of constant mean curvature. Ph.D. thesis, TU-Berlin.
 
38
 
39
Rusinkiewicz, S. 2007. Trimesh2 library. http://www.cs.princeton.edu/gfx/proj/trimesh2/.
40
41
42
 
43
 
44
45
46
 
47
Weisberg, S. 2003. Applied Linear Regression, 3rd ed. Wiley/Interscience.
48
 
49
 
50


Collaborative Colleagues:
Evangelos Kalogerakis: colleagues
Derek Nowrouzezahrai: colleagues
Patricio Simari: colleagues
James Mccrae: colleagues
Aaron Hertzmann: colleagues
Karan Singh: colleagues