Data-Driven Simulation Methods in Computer Graphics: Cloth, Tissue and Faces

Abstract

In recent years, the field of computer animation has witnessed the invention of multiple simulation methods that exploit pre-recorded data to improve the performance and/or realism of dynamic deformations. Various methods have been presented concurrently, and they present differences, but also similarities, that have not yet been analyzed or discussed. This course focuses on the application of data-driven methods to three areas of computer animation, namely dynamic deformation of faces, soft volumetric tissue, and cloth. The course describes the particular challenges tackled in a data-driven manner, classifies the various methods, and also shares insights for the application to other settings.

The explosion of data-driven animation methods and the success of their results make this course extremely timely. Up till now, the proposed methods have remained familiar only at the research context, and have not made their way through computer graphics industry. This course aims to fit two main purposes. First, present a common theory and understanding of data-driven methods for dynamic deformations that may inspire the development of novel solutions, and second, bridge the gap with industry, by making data-driven approaches accessible. The course targets an audience consisting of both researchers and programmers in computer animation.


Speakers

Miguel A. Otaduy
Miguel A. Otaduy is an associate professor in the Department of Computer Science at Universidad Rey Juan Carlos (URJC Madrid). His main research areas are physically based computer animation and haptic rendering. He obtained his BS (2000) on electrical engineering from Mondragon University, and MS (2003) and PhD (2004) on computer science from the University of North Carolina at Chapel Hill. From 2005 to 2008 he was a research associate at ETH Zurich, and then he joined URJC Madrid. He has published over 50 papers in computer graphics and haptics, and has recently co-chaired the program committees for the ACM SIGGRAPH / Eurographics Symposium on Computer Animation (2010) and the Spanish Computer Graphics Conference (2010). He also leads the ERC Starting Grant Animetrics, on measurement-based modeling of complex mechanical phenomena

Bernd Bickel
Bernd Bickel is a part-time visiting professor at TU Berlin and a post-doctoral researcher at Disney Research Zurich. His research interests include computer graphics and its applications in animation, biomechanics, material science,and computational design for digital fabrication. Recent work includes next generation 3D surface scanner devices, performance capture, measuring and modeling the deformation behavior of soft tissue, and animation tools. Bernd received a M.Sc. in Computer Science in 2006 and spent nine month at Mitsubishi Electric Research Laboratories under the supervision of Prof. Hanspeter Pfister. He wrote his PhD thesis at ETH Zurich in the Computer Graphics Lab headed by Prof. Markus Gross and defended in November 2010.

Derek Bradley
Derek Bradley is a postdoctoral researcher at Disney Research Zurich. He completed his Bachelor of Computer Science in 2003 and Master of Computer Science in 2005, both at Carleton University in Canada. In 2010, Derek obtained a PhD from the University of British Columbia in Canada, and then started with Disney Research Zurich in September 2010. Derek’s main research interest is real-world modeling and animation, primarily through computer vision techniques. He works on various 3D reconstruction projects including multiview stereo, facial performance capture, and data-driven simulation.

Huamin Wang
Huamin Wang is an assistant professor in the department of Computer Science and Engineering, at the Ohio State University. Previously, he was a postdoctoral researcher in the EECS department, at the University of California, Berkeley. He received his Ph.D. from Georgia Institute of Technology in 2009, M.S. from Stanford University in 2004 and B.Eng. from Zhejiang University in 2002. His research interests are in computer graphics, computer vision, and image processing techniques that are related to graphics and visualization applications. He is particularly interested in incorporating real-world data into physically based simulation techniques, so animations can be efficiently and realistically generated.


Course Schedule

Tentative schedule. Final date and times TBA.


Course Notes

High resolution (142Mb) [PDF]

Low resolution (15Mb) [PDF]


Selected References


Selected Images

Modeling Nonlinear Soft Tissue from Captured Mechanical Data

Soft Tissue Soft Tissue Soft Tissue

Data-Driven Modeling of Nonlinear Elasticity in Cloth

Data-Driven Cloth Data-Driven Cloth Data-Driven Cloth

Animation of Faces with Data-Driven Wrinkles

Face Wrinkles

Clothing Animation with Wrinkle Synthesis from Examples

Wrinkles from Examples

Capturing Geometry and Forces in Real Deformation Examples

Capturing Geometry Capturing Geometry Capturing Geometry