• Home
  • Attending
  • Authors
  • Program
  • Organizers
  • Supports
          Call for PapersSubmissionPresenting
         Important DatesProgramSocial Events
                        CommitteePrior Conference





  • 2011/09/21-23
  • Conference
  • 2011/07/27
  • Camera-Ready Paper
  • 2011/07/24
  • Final Acceptance Notification
  • 2011/07/13
  • Revision for Second Review
  • 2011/06/22
  • Author Notification
  • 2011/04/30 (GMT)22:00
  • Paper Submission
  • 2011/04/24
  • Abstract Submission


The Conference Program :

Day 1, 21 September
Day 2, 22 September
Day 3, 23 September
Keynote Speech I
Keynote Speech II
Keynote Speech III
Session A
Image Enhancement
Session D
Session G
Image & Video Editing
Session B
Lighting & Rendering
Session E
Model Reconstruction & Analysis
Session H
Mesh Segmentation & Processing
Session C
Non Photorealistic Rendering & GPU computing
Session F
Procedural Modeling & Natural Phenomena
Session I
Welcome Reception


Keynote Speech:

Keynote Speech I :
Chair: Ming C. Lin (University of North Carolina at Chapel Hill)
Rob Cook

Vice President of Advanced Technology, Pixar Animation Studios

Title: Behind the Scenes at Pixar


This talk takes you behind the scenes at Pixar Animation Studios for a look at how its 3D computer graphics films are made. The process starts with the development of the story and continues with modeling the geometry, animating the characters, simulating things like water and cloth and hair, defining the look of the surfaces, putting lights in the scene, and rendering the images. Making a computer animated film requires a close collaboration between artists and technical experts in many areas of expertise and is a great example of the value of bringing different disciplines together.


Rob Cook was the co-architect and primary author of Pixar's RenderMan software, which creates photo-realistic computer images. In 2001, he and two colleagues received Oscars for their contributions, the first ever given for software. For 16 years, every film nominated for a Visual Effects Academy Award used RenderMan. He has a Bachelors degree in physics from Duke University and a Masters degree in Computer Graphics from Cornell University. At Cornell, he worked on simulating realistic surfaces, taking computer-generated images beyond the distinctive plastic look they had at the time. In 1981, he joined Lucasfilm/Pixar, where he developed the first programmable shader; programmable shading is now an essential part of GPUs and game engines as well as high-end renderers. He was the first to use Monte Carlo techniques in computer graphics, which was essential for simulation of complex, realistic lights and camera effects. The latter proved particularly important in the special effects industry, because it allowed computer-generated imagery to match the motion blur and depth of field of the live-action footage with which it was combined. In 1987, he received the ACM SIGGRAPH Computer Graphics Achievement Award in recognition of these contributions, and in 2009, he received the ACM SIGGRAPH Stephen A. Coons Award for his lifetime contributions to the field. In 1999, he was inducted as a Fellow of the Association for Computing Machinery. He has been named to the Academy of Motion Picture Arts and Sciences and to the National Academy of Engineering.

Keynote Speech II :
Chair: Ming Ouhyoung (National Taiwan University)
Heinrich Bülthoff

Director, Max Planck Institute for Biological Cybernetics

Title: Perceptual Graphics: closing the loop between Perception, Graphics and Computer Vision


In our Perceptual Graphics group at the Max Planck Institute for Biological Cybernetics we integrate methods from psychophysics, computer graphics and computer vision in order to understand fundamental perceptual and cognitive processes. The fusion of methods from these research areas has the potential to greatly advance our understanding of perception and cognition. Highly controllable, yet realistic computer generated stimuli offer novel ways for psychophysical investigations. The results from those experiments can in turn be used to derive perceptual "shortcuts" to more efficient rendering approaches. Computer vision and machine learning algorithms can be used to model human cognition and action while conversely, the results from perceptual experiments can inform computer scientists how the brain solves problems and thus can lead to more efficient solutions of hard problems like recognition and categorization. In this presentation, I will highlight how the latest tools in computer vision, computer graphics, and virtual reality technology can be used to systematically understand the factors that determine how humans behave and solve tasks in realistic scenarios.


Heinrich Bülthoff is scientific member of the Max Planck Society and director at the Max Planck Institute for Biological Cybernetics in Tübingen. He is head of the Department Human Perception, Cognition and Action in which a group of about 70 researchers investigate psychophysical and computational aspects of higher level visual processes in object and face recognition, sensory-motor integration, spatial cognition, and perception and action in virtual environments. He holds a Ph.D. degree in the natural sciences from the Eberhard-Karls-Universität in Tübingen. From 1980 to 1988 he worked as a research scientist at the Max Planck Institute for Biological Cybernetics and the Massachusetts Institute of Technology and from 1988-1993 he was Assistant, Associate and Full Professor of Cognitive Science at Brown University in Providence. He is Honorary Professor at the Eberhard-Karls-Universität (Tübingen) and Korea University (Seoul) and Editor of several international journals.

Keynote Speech III :
Chair: Eugene Fiume (University of Toronto)
Kun Zhou

Professor, Zhejiang University

Title: Gradient Domain Shape Deformation


Shape deformation is a useful tool in a variety of applications in shape modeling and computer animation. In recent years we have witnessed an increasing research interest in applying gradient domain techniques to shape deformation. Unlike traditional techniques such as FFD and multi-resolution methods which directly modify shape positions, gradient domain algorithms first modify shape gradients (or differential coordinates) and then reconstruct shape positions from the modified gradients. Such algorithms are able to preserve surface details and produce visually pleasing deformation results by distributing errors smoothly through global optimization. In this talk, I will review the origin of gradient domain shape deformation algorithms and give an overview of our recent research in this continuously evolving area.


Kun Zhou is a Cheung Kong Professor in the computer science department of Zhejiang University, and a member of the State Key Laboratory of CAD&CG, where he leads the Graphics and Parallel Systems Lab. Prior to joining Zhejiang University in 2008, he was a Lead Researcher of the Internet Graphics Group at Microsoft Research Asia. He received his BS degree and PhD degree from Zhejiang University in 1997 and 2002, respectively. His research interests include computer graphics and parallel computing, in the areas of geometry processing, real-time rendering and GPU parallel computing. Please refer to http://kunzhou.net for more details about his research.


Short Paper Short Presentation
Session A - Image Enhancement :
Chair: Yung-Yu Chuang (National Taiwan University)
Motion Deblurring from a Single Image using Circular Sensor Motion
Yosuke BandoBing-Yu ChenTomoyuki Nishita
TOSHIBA / The University of TokyoNational Taiwan UniversityThe University of Tokyo


Edge-Optimized À-TrousWavelets for Local Contrast Enhancement with Robust Denoising
Johannes HanikaHolger DammertzHendrik Lensch
Ulm University / Weta DigitalUlm University / RTT AGUlm University


Exposure Fusion for Time-Of-Flight Imaging
Uwe HahneMarc Alexa
Technische Universität Berlin


Rephotography Using Image Collections
Kun-Ting LeeSheng-Jie LuoBing-Yu Chen
National Taiwan University


Session B - Lighting & Rendering :
Chair: Wei-Chao Chen (SDI / National Taiwan University)
Improving Performance and Accuracy of Local PCA
Václav GassenbauerJaroslav KrivánekKadi BouatouchChristian BouvilleChristian BouvilleMickaël Ribardière
IRISA - INRIA Rennes / Czech Technical University in PragueCharles UniversityIRISA - INRIA Rennes


Toward Optimal Space Partitioning for Unbiased, Adaptive Free Path Sampling of Inhomogeneous Participating Media
Yonghao YueKei IwasakiBing-Yu ChenYoshinori DobashiTomoyuki Nishita
The University of TokyoWakayama UniversityNational Taiwan UniversityHokkaido UniversityThe University of Tokyo


Interactive Indirect Illumination Using Voxel Cone Tracing
Cyril CrassinFabrice Neyret Miguel SainzSimon GreenElmar Eisemann
INRIA Rhone-Alpes & LJK / Grenoble UniversityINRIA Rhone-Alpes & LJK / CNRSNVIDIATelecom ParisTech


Spatio-Temporal Filtering of Indirect Illumination for Real-Time Global Illumination
Ying-Chieh ChenSu Ian Eugene LeiChun-Fa Chang
National Tsing Hua UniversityNational Taiwan Normal University


Real-time Realistic Voxel-based Rendering
S.-H. ChangYu-Chi LaiYuzhen NiuFeng LiuK.-L. Hua
National Taiwan University of Science and TechnologyPortland State UniversityNational Taiwan University of Science and Technology


An Image-based Hair Styling System Using Layered Texture Pieces
Hiroki WatanabeYoshihiro KanamoriJun MitaniYukio Fukui
University of Tsukuba


Session C - Non Photorealistic Rendering & GPU computing:
Chair: Pedro Sander (The Hong Kong University of Science and Technology)
A Graph-based Approach to Continuous Line Illustrations with Variable Levels of Detail
Fernando J. WongShigeo Takahashi
The University of Tokyo


An Illustrative Visualization Framework for 3D Vector Fields
Cheng-Kai ChenShi YanHongfeng YuNelson MaxKwan-Liu Ma
University of California, DavisSandia National LaboratoriesUniversity of California, Davis


Perceptually-based Stroke Pattern Synthesis
Dongwei LiuJunsong ZhangChangle Zhou
Xiamen University


Fast Level Set Image Segmentation Using New Evolution Indicator Operators
Chunxia XiaoJiajia GanXiangyun Hu
Wuhan University


Fast Computing Adaptively Sampled Distance Field on GPU
Kangxue YinYouquan LiuEnhua Wu
Chang'an UniveristyChang'an Univeristy / Chinese Academy of Sciences Chinese Academy of Sciences / University of Macau


Two Simple Single-pass GPU methods for Multi-channel Surface Voxelization of Dynamic Scenes
Athanasios GaitatzesPavlos MavridisGeorgios Papaioannou
University of CyprusAthens University of Economics & Business


Session D - Animation :
Chair: Yu-Shuen Wang (National Chiao Tung University)
Motion Retrieval Using Low-Rank Subspace Decomposition of Motion Volume
Chuan SunImran JunejoHassan Foroosh
University of Central FloridaUniversity of SharjahUniversity of Central Florida


Flexible Splicing of Upper-Body Motion Spaces on Locomotion
Ben J. H. van BastenArjan Egges
Utrecht University


Creating Fluid Animation from a Single Image using Video Database
Makoto OkabeKen AnjyoRikio Onai
The University of Electro-Communications / JST PRESTOOLM Digital / JST CRESTThe University of Electro-Communications


Asynchronous Evolution for Fully-Implicit and Semi-Implicit Time Integration
Craig SchroederNipun KwatraWen ZhengRon Fedkiw
Stanford UniversityStanford University / Industrial Light+Magic


Session E - Model Reconstruction & Analysis :
Chair: Shigeo Takahashi (The University of Tokyo)
SSD: Smooth Signed Distance Surface Reconstruction
Fatih CalakliGabriel Taubin
Brown University


Bipartite Polar Classification for Surface Reconstruction
Yi-Ling ChenTung-Ying LeeBing-Yu ChenShang-Hong Lai
Industrial Technology Research Institute / National Tsing Hua UniversityNational Tsing Hua UniversityNational Taiwan UniversityNational Tsing Hua University


Discriminative Sketch-based 3D Model Retrieval via Robust Shape Matching
Tianjia ShaoWeiwei XuKangkang YinJingdong WangKun ZhouBaining Guo
Tsinghua UniversityMicrosoft Research AsiaNational University of SingaporeMicrosoft Research AsiaZhejiang UniversityMicrosoft Research Asia


An Effective and Efficient Contour-based Corner Detector using Simple Triangular Theory
R. M. Najmus SadatShyh Wei TengGuojun Lu
Monash University


Feature Adaptive Surfel Set Simplification
Yan HuangFeihu YanBei WangJingliang Peng
Shandong UniversityIntelShandong University


Feature-Aware Reconstruction of Volume Data via Trivariate Splines
Bo LiHong Qin
Stony Brook University


Session F - Procedural Modeling & Natural Phenomena:
Chair: Tomoyuki Nishita (The University of Tokyo)
Authoring Hierarchical Road Networks
Eric GalinAdrien PeytavieEric GuérinBedrich Beneš
LIRIS - CNRS - Université Lumière LyonLIRIS - CNRS - Université Claude Bernard LyonLIRIS - CNRS - INSA LyonPurdue University


River Networks for Instant Procedural Planets
Evgenij DerzapfBjörn GansterMichael GutheReinhard Klein
Philipps-Universität MarburgUniversität BonnPhilipps-Universität MarburgUniversität Bonn


Virtual City Map Generation using Area Subdivision
Kerstin MüllerLuc HeischbourgChristoph FünfzigSebastian PetschHans Hagen
Technische Universität Kaiserslautern


Local Poisson SPH For Viscous Incompressibility Fluids
Xiaowei HeNing LiuSheng LiHongan WangGuoping Wang
Peking University


Sketch-based Breaking Waves
Guijuan ZhangGaojin WenDengming ZhuDianjie LuShengzhong Feng
Chinese Academy of Sciences


A Fast Simulation Method Using SPH and Wavelet for Sub-Particle-Scale Turbulent Flow
Makoto FujisawaGo MimuraToshiyuki AmanoJun MiyazakiHirokazu Kato
University of TsukubaNintendoYamagata UniversityNara Institute of Science and Technology


Real-time Rendering of Endless Cloud Animation
Kei IwasakiTakanori NishinoYoshinori Dobashi
Wakayama UniversityHokkaido University


Session G - Image & Video Editing:
Chair: Shang-Hong Lai (National Tsing Hua University)
Real Time Edit Propagation by Efficient Sampling
Xiaohui BieHaoda HuangWencheng Wang
Chinese Academy of SciencesMicrosoft Research AsiaChinese Academy of Sciences


Video Brush: A Novel Interface for Efficient Video Cutout
Ruo-Feng TongYun ZhangMeng Ding
Zhejiang University


RepSnapping: Efficient Image Cutout for Repeated Scene Elements
Hua HuangLei ZhangHong-Chao Zhang
Xi'an Jiaotong Unversity


A Single Image Representation Model for Efficient Stereoscopic Image Creation
Younghui KimHwi-ryong JungSungwoo ChoiJungjin LeeJunyong Noh
Korea Advanced Institute of Science and Technology


Session H - Mesh Segmentation & Processing:
Chair: Wenping Wang (The University of Hong Kong)
Optimized Topological Surgery for Unfolding 3D Meshes
Shigeo TakahashiHsiang-Yun WuSeow Hui SawChun-Cheng LinHsu-Chun Yen
The University of TokyoNational Chiao Tung UniversityNational Taiwan University


Computing 3D Shape Guarding and Star Decomposition
Wuyi YuXin Li
Xiamen UniversityLouisiana State University


HeatWalk: Robust Salient Segmentation of Non-rigid Shapes
William BenjaminAndrew Wood PolkS. V. N. VishwanathanKarthik Ramani
Purdue University


Interactive Design of Planar Curved Folding by Reflection
Jun MitaniTakeo Igarashi
University of Tsukuba / JST ERATOThe University of Tokyo / JST ERATO


Feature-Aware Mesh for Image Retargeting
Yuzhen NiuFeng LiuYu-chi Lai
Portland State UniversityNational Taiwan University of Science and Technology


Facial Retargeting by Adding Supplemental Blendshapes
Paul Hyunjin KimYeongho SeolJaewon SongJunyong Noh
Korea Advanced Institute of Science and Technology


Session I - Visualization:
Chair: Chuan-kai Yang (National Taiwan University of Science and Technology)
Intelligent GPGPU Classification in Volume Visualization: A framework based on Error-Correcting Output Codes
Sergio EscaleraAnna PuigOscar AmorosMaria Salamó
Universitat de Barcelona


Efficient Opacity Specification Based on Feature Visibilities in Direct Volume Rendering
Yunhai WangJian ZhangWei ChenHuai ZhangXuebin Chi
Chinese Academy of ScienceZhejiang UniversityChinese Academy of Science


Diffusion Tensor Weighted Harmonic Fields for Feature Classification
Shengfa WangTingbo HouZhixun SuHong Qin
Dalian University of Technology / Stony Brook UniversityStony Brook UniversityDalian University of TechnologyStony Brook University


Visualizing LocalWeather Characteristics Interpreted from Glider GPS Flight Logs
Tung-Ju HsiehFalko KuesterTara Hutchinson
National Taipei University of TechnologyUniversity of California, San Diego


Illustrative Line Styles for Flow Visualization
Maarten H. EvertsHenk BekkerJos B. T. M. RoerdinkTobias Isenberg
University of GroningenUniversity of Groningen / DIGITEO/CNRS/INRIA