Program
Tutorial (FIT Building Room 1-312)
| Nov 7 2012, Wednesday |
| Recent work in urban and architectural modeling 14:00-15:00 Peter Wonka, Arizona State University and King Abdullah University of Science and Technology (KAUST) |
| Modelling awareness for social robots and virtual humans 15:00-17:00 Nadia Magnenat Thalmann, MIRALab, University of Geneva and NTU, Singapore Daniel Thalmann, EPFL, Switzerland and NTU, Singapore |
Conference Program (FIT Building Conference Hall)
| Nov 8 2012, Thursday | Nov 9 2012, Friday |
| 08:00-09:00 Registration 09:00-09:10 Opening |
08:00-09:00 Registration |
| 09:10-09:50 Invited Talk I(Nadia Magnenat-Thalmann) | 09:00-09:40 Invited Talk IV(Leif Kobbelt) |
| 09:50-10:30 Invited Talk II(Diego Gutierrez) | 09:40-10:30 Perception and Learning |
| 10:30-10:50 Coffee Break | 10:30-10:50 Coffee Break |
| 10:50-12:30 Image Processing I | 10:50-12:30 Geometry Processing II |
| 12:30-14:00 Lunch | 12:30-14:00 Lunch |
| 14:00-14:40 Invited Talk III(Vladlen Koltun) | 14:00-14:40 Invited Talk V(Yiying Tong) |
| 14:40-15:55 Geometry Processing I | 14:40-15:30 Saliency |
| 15:55-16:30 Poster Session & Coffee Break | 15:30-15:50 Coffee Break |
| 16:30-18:10 Synthesis and Fusion | 15:50-16:40 Image Processing II |
| 18:30-20:30 Banquet and Best Paper Announcement | 16:40-17:55 Media Retrieval 17:55-18:10 Closing session |
Tutorial
Recent work in urban and architectural modeling
Peter Wonka, Arizona State University and King Abdullah University of Science and Technology (KAUST)
Abstract
I will talk about selected urban and architectural modeling projects I was involved in over the last 1-2 years: interactive sketch-based modeling of buildings using procedural extrusions (similar to the straight skeleton), facade re-layouting by optimization, and quad mesh layouts on free-form architecture.
Biography
Dr. Peter Wonka received his doctorate from the Technical University of Vienna in computer science in 2001 under the guidance of Prof. Schmalstieg. Additionally he received a Masters of Science in Urban Planning from the same institution. Prior to coming to ASU, he was a postdoctorate researcher at the Georgia Institute of Technology for two years. His research interests include various topics in computer graphics, visualization, and image-processing. Peter Wonka is a member of the PRISM lab. He is now Associate Professor at Arizona State University and King Abdullah University of Science and Technology (KAUST).
Modelling awareness for social robots and virtual humans
Nadia Magnenat Thalmann, MIRALab, University of Geneva and NTU, Singapore
Daniel Thalmann, EPFL, Switzerland and NTU, Singapore
Abstract
The objective of this tutorial is to explain the methods to make autonomous virtual humans and social robots (I-companions) communicate with real users and share their world. The autonomous virtual humans and social robots are supposed to give a partial illusion that they are real. This implies that these autonomous virtual humans and social robots should look the same as the real human, speaks with the same intonation, and be aware of the real situation, the real participants, and the task currently performed. The autonomous virtual humans and social robots should react at the right time based on the perception he/she has from the real participants. It implies to evaluate what each real participant is doing. Perception will be obtained by visual and audio input and recognition. Each autonomous virtual humans or social robots should also be aware of the other autonomous virtual humans and social robots, which needs to introduce a synthetic perception for the virtual humans. The autonomous virtual humans and social robots react according to the input and its current knowledge. Their reactions encompass animation (body and facial gestures) and speech synthesis. A common platform for autonomous virtual humans and robots will be presented. In this tutorial we will address the following topics:
- Fundamental of virtual humans
- Fundamental of social robots
- Perception and awareness of the real world
- Action recognition and analysis
- Recognizing and creating emotions
- Perception of the virtual world, virtual senses
- Defining memory process and relationship models
- Decision process
- Generation of motion and animation
- A common platform for autonomous virtual humans and social robots
Session 1 Image processing I
Semantic Image Clustering Using Object Relation Network
Na Chen and Viktor K. Prasanna
Clothed and Naked Human Shapes Estimation from a Single Image
Yu Guo, Xiaowu Chen, Bin Zhou, and Qinping Zhao
Image Colorization with an Affective Word
Xiaohui Wang, Jia Jia, Hanyu Liao, and Lianhong Cai
A Novel Customized Recompression Framework for Massive Internet Images
Shouhong Ding, Feiyue Huang, Zhifeng Xie, Yongjian Wu, and Lizhuang Ma
Session 2 Geometry Processing I
Modeling Residential Urban Areas from Dense Aerial LiDAR Point Clouds
Qian-Yi Zhou and Ulrich Neumann
A Robust Algorithm for Denoising Meshes with High-Resolution Details
Hanqi Fan, Qunsheng Peng, and Yizhou Yu
Mesh Segmentation for Parallel Decompression on GPU
Jieyi Zhao, Min Tang, and Ruofeng Tong
Session 3 Synthesis and Fusion
Efficient Solid Texture Synthesis Using Gradient Solids
Guo-Xin Zhang, Yu-Kun Lai, and Shi-Min Hu
Constrained Texture Mapping on Subdivision Surfaces
Yanlin Weng, Dongping Li, and Yiying Tong
Real-Time Recombination Method of Complex 3D Tree Model Information on Visual Perception Preserving
Dong Tianyang, Fan Yunyi, Fan Jing, and Ji Lei
A Memory-Efficient KinectFusion Using Octree
Ming Zeng, Fukai Zhao, Jiaxiang Zheng, and Xinguo Liu
Session 4 Perception and Learning
Incremental Shared Subspace Learning for Multi-label Classification
Lei Zhang, Yao Zhao, and Zhenfeng Zhu
2D-Line-Drawing-Based 3D Object Recognition
Yong-Jin Liu, Qiu-Fang Fu, Ye Liu, and Xiao-Lan Fu
Session 5 Geometry Processing II
Efficient Spherical Parametrization Using Progressive Optimization
Shenghua Wan, Tengfei Ye, Maoqing Li, Hongchao Zhang, and Xin Li
Curve Skeleton Extraction by Graph Contraction
Wei Jiang, Kai Xu, Zhi-Quan Cheng, Ralph R. Martin, and Gang Dang
Robust Feature Extraction Based on Principal Curvature Direction
Jin-Jiang Li and Hui Fan
Compact Combinatorial Maps in 3D
Xin Feng, Yuanzhen Wang, Yanlin Weng, and Yiying Tong
Session 6 Saliency
A Shape Enhancement Technique Based on Multi-channel Salience Measure
Yongwei Miao, Jieqing Feng, Jinrong Wang, and Renato Pajarola
Multi-scale Salient Feature Extraction on Mesh Models
Yong-Liang Yang and Chao-Hui Shen
Session 7 Image Processing II
Decomposition Equation of Basis Images with Consideration of Global Illumination
Xueying Qin, Rui Zhang, Lili Lin, Fan Zhong, Guanyu Xing, and Qunsheng Peng
Identifying Shifted Double JPEG Compression Artifacts for Non-intrusive Digital Image Forensics
Zhenhua Qu, Weiqi Luo, and Jiwu Huang
Session 8 Media Retrieval
Towards Large Scale Cross-Media Retrieval via Modeling Heterogeneous Information and Exploring an Efficient Indexing Scheme
Bo Lu, Guoren Wang, and Ye Yuan
Design and Implementation of a Context-Based Media Retrieval System
Liang Zhao, Tangjian Deng, Hao Wang, Qingwei Liu, and Ling Feng
Robust Place Recognition by Avoiding Confusing Features and Fast Geometric Re-ranking
Mingying Gong, Lifeng Sun, Shiqiang Yang, and Yun Yang
Poster Session
Similar Region Contrast based Salient Region Detection
Qiang Fan and Chun Qi
A Game-Theoretical Approach to Image Segmentation
Jing Li and Gang Zeng
Graph Regularized ICA for Over-complete Feature Learning
Yanhui Xiao, Zhenfeng Zhu and Yao Zhao
Global Contrast of Superpixels based Salient Region Detection
Jie Wang and Yu Wei
Intuitive Volume Eraser
En-Ya Shen, Zhi-Quan Cheng, Jiazhi Xia and Sikun Li
Accurate Depth-of-Field Rendering Using Adaptive Bilateral Depth Filtering
Shang Wu, Kai Yu, Bin Sheng and Lizhuang Ma
Intrinsic Image Decomposition With Local Smooth Assumption and Global Color Assumption
Zhongqiang Wang and Li Zhu
Determining Personality Traits from Renren Status Usage Behavior
Shuotian Bai, Rui Gao and Tingshao Zhu