Conference Program

Day One Thursday, Apr.16, 2015   Lecture Hall, FIT
09:00 – 09:10 Opening
09:10 – 09:55 Invited talk I: Structure-preserving Image Smoothing
Seungyong Lee
Chair: Nadia Magnenat-Thalmann
Session 1 Vision Focusing on Human
Chair: Jianfei Cai
09:55 – 10:20 Similarity Metric Learning for Face Verification Using Sigmoid Decision Function
Xiaonan Hou, Shouhong Ding, and Lizhuang Ma
10:20 – 10:45 Similarity Learning with Humans in the Loop
Chong Cao, and Haizhou Ai
10:45 – 11:00 Coffee break
Session 2 Image Enhancement
Chair: Seungyong Lee
11:00 – 11:25 PhotoPrev: Unifying Context and Content Cues to Enhance Personal Photo Revisitation
Li Jin, Gangli Liu, Liang Zhao, and Ling Feng
11:25 – 11:50 A Nonlocal Gradient Concentration Method for Image Smoothing
Qian Liu, Caiming Zhang, Qiang Guo, and Yuanfeng Zhou
11:50 – 12:15 Adaptive Sparse Coding on PCA Dictionary for Image Denoising
Qian Liu, Caiming Zhang, Qiang Guo, Hui Xu, and Yuanfeng Zhou
12:15 – 12:40 Least-Square Images for Edge-preserving Smoothing
Hui Wang, Junjie Cao, Xiuping Liu, Jianmin Wang, and Tongrang Fan
12:40 – 14:00 Lunch
Session 3 Geometry
Chair: Guoping Wang
14:00 – 14:25 SymmSketch: Creating Symmetric 3D Free-form Shapes from 2D Sketches
Yongwei Miao, Feixia Hu, Xudong Zhang, Jiazhou Chen, and Renato Pajarola
14:25 – 14:50 3D Ear Shape Matching Using Joint α-Entropy
Xiaopeng Sun, Lu Wang, Feng Han, and Xiaopeng Wei
14:50 – 15:15 Interactive mesh cloning driven by boundary loop
Qian Guiping, Tang Ming, Tong Ruofeng, Zhang Xiaohong, Chu Shaowei, and Pan Ruifang
15:15 – 15:40 Stretch-minimizing Volumetric Parameterization
Yao Jin, Jun Sun, Jieyi Zhao, and Ruofeng Tong
15:40 – 16:00 Coffee break
Session 4 Animation and Simulation
Chair: Lin Lv
16:00 – 16:25 Fast SPH Simulation for Gaseous Fluids
Bo Ren, Xiao Yan, Chenfeng Li, Tao Yang, Ming Lin, and Shi-Min Hu
16:25 – 16:50 Spectral Animation Compression
Chao Wang, Yang Liu, Xiaohu Guo, Zichun Zhong, Binh Le, and Zhigang Deng
16:50 – 17:15 Monocular Video Guided Garment Animation
Faming Li, Xiaowu Chen, Kan Guo, Qiang Fu, Lin Wang, Bin Zhou, and Feixiang Lu
17:15 – 17:40 GPU Accelerated Real-time Collision Handling in Virtual Disassembly
Peng Du, Jieyi Zhao, Zhendong Wang, and Yigang Wang
18:00 – 20:00 Banquet
Day Two Friday, Apr.17, 2015  Lecture Hall, FIT
09:00 – 09:45 Invited talk II: Recognising Objects in Art and Photographs
Peter Hall
Chair: Ralph Martin
Session 5 Video Processing and Editing
Chair: Xiaowu Chen
09:45 – 10:10 Salt and Pepper noise removal in video based on low rank matrix recovery
Yongxia Zhang, Caiming Zhang, and Yi Liu
10:10 – 10:35 Efficient Video Cutout by Paint Selection
Yun Zhang, and Yanlong Tang
10:35 – 10:50 Coffee break
Session 6 Image Editing and Processing
Chair: Ruofeng Tong
10:50 – 11:15 Edge-Preserving Image Decomposition via Joint Weighted Least Squares
Pan Shao, Shouhong Ding, and Lizhuang Ma
11:15 – 11:40 Enlarging Image by Constrained Least Square Approach with Shape Preserving
Fan Zhang, Xin Zhang, Xueying Qin, and Caiming Zhang
11:40 – 12:05 Panorama Completion in Street View
Zhe Zhu, and Shi-Min Hu
12:05 – 12:30 A Nonlocal Optimization Framework for Image Colorization
Hanli Zhao, Guizhi Nie, Xujie Li, Xiaogang Jin, and Zhigeng Pan
12:30 – 14:00 Lunch
Session 7 Sampling and Rendering
Chair: Kun Xu
14:00 – 14:25 Visual Inspection of Multivariate Volume Data based on Multi-class Noise Sampling
Zhiyu Ding, Ziang Ding, Weifeng Chen, Haidong Chen, Yubo Tao, Xin Li, and Wei Chen
14:25 – 14:50 Poisson Disk Sampling through Disk Packing
Guanghui Liang, Lin Lu, Zhonggui Chen, and Chenglei Yang
14:50 – 15:15 Coherent Photon Mapping on the Intel MIC Architecture
Chun-Meng Kang, Lu Wang, Pei Wang, Yan-Ning Xu, Xiang-Xu Meng
Session 8 Fast Presentation for Posters (3 minutes each)
Chair: Songhai Zhang
15:15 – 15:30 Anisotropic Density Estimation for Photon Mapping
Fujun Luan, Lifan Wu, and Kun Xu

Pairwise Constraint Propagationvia Low-Rank Matrix Recovery
Zhenyong Fu, Yun Li, Yunyun Wang, Xianzhong Long, Jian Zhou, and Hua Dai

Image Recoloring using Geodesic Distance based Color Harmonization
Li Xujie, Hanli Zhao, Guizhi Nie, and Hui Huang

New Operators for Describing Image Texture
Fangjun Huang, Xiaochao Qu, Hyoung Joong Kim, and Jiwu Huang

Semantic Movie Summarization based on String of IE-RoleNets
Wen Qu

Disparity-Constrained Stereo Video Retargeting
Liu Yi, Lifeng Sun, and Shiqiang Yang
15:30 – 16:00 Coffee break and poster discussion
Session 9 Stylization
Chair: Peter Hall
16:00 – 16:25 Region-based Structure Line Detection for Cartoons
Xiangyu Mao, Xueting Liu, Tien-Tsin Wong, Xuemiao Xu
16:25 – 16:50 Text-aware Balloon Extraction from Manga
Xueting Liu, Chengze Li, Haichao Zhu, Tien-Tsin Wong, Xuemiao Xu
16:50 – 17:15 Stylized strokes for coherent line drawings
Liming Lou, Lu Wang, and Xiangxu Meng
17:15 – 17:40 Artistic Low Poly Rendering for Images
Meng Gai, and Guoping Wang
17:40 – 18:00 Closing session

Keynote Speaker I:

Prof. Seungyong Lee  

Talk Title:

Structure-preserving Image Smoothing

Talk Abstract:

Structure-preserving image smoothing is an essential operation with a variety of applications in computational photography and image analysis. Such an operation decomposes an image into prominent structure and fine-scale detail, making it easier for subsequent image manipulation such as tone mapping, detail enhancement, visual abstraction, scene understanding, and other tasks. In this talk, I will first review recent structure-preserving smoothing operators that can be classified into local filtering and optimization based solutions. I will then introduce a novel structure-preserving image smoothing operator called bilateral texture filter, which is a simple modification of the original bilateral filter. It performs local patch-based analysis of texture features with the central idea of patch shift and incorporates the analysis results into the range filter kernel. The talk will be concluded with a few applications of structure-preserving image smoothing.

Short Bio:

Seungyong Lee is a professor of computer science and engineering at the Pohang University of Science and Technology (POSTECH), Korea. He received the BS degree in computer science and statistics from Seoul National University in 1988 and the MS and PhD degrees in computer science from the Korea Advanced Institute of Science and Technology (KAIST) in 1990 and 1995, respectively. From 1995 to 1996, he worked at the City College of New York as a postdoctoral researcher. Since 1996, he has been a faculty member of POSTECH, where he leads the Computer Graphics Group. During his sabbatical years, he worked at MPI Informatik (2003~2004) and the Creative Technologies Lab at Adobe Systems (2010~2011). His technologies on image deblurring and photo upright adjustment have been transferred to Adobe Creative Cloud and Adobe Photoshop Lightroom. His current research interests include image and video processing, non-photorealistic rendering, and 3D scene reconstruction.

Keynote Speaker II:

Prof. Peter Hall

Talk Title:

Recognising Objects in Art and Photographs

Talk Abstract:

People posses an astonishing ability that is currently beyond even the best Computer Vision algorithms: people can recognise objects regardless of how they are depicted. People can see a dog as a dog whether it is photographed, painted, drawn, etc. Young children draw recognisable things – their parents, their home, their pets; and young children can recognise things in real life having seen only a simple drawing. Computers can do none of these things. I will explore the problem of recognition regardless of depiction. I will show there is an important literature gap to be addressed, and discuss why filling this gap is difficult. State of the art methods will be explained, and their weaknesses exposed. Applications that might be enabled as a result of filling the literature gap will be explored.

Short Bio:

Dr. Peter Hall is a reader (associate professor) in the department of Computer Science, University of Bath. He is also director of the Media Technology Research Centre, also at Bath. He is interested in automatically processed real photographs and video into art or into 3D animated models. He founded and was chair of the Vision, Video, and Graphics Network. The network ran conferences and meetings as well as providing small grants to support research in the “convergence” area of VVG. He has served as an elected member of the British Machine Vision Association executive committee since 2003. He is also a member of the steering committee of the Computational Aesthetics series of conferences, being co-chair of the technical programme in 2009. He is an EPRSC college member, and review for international funding bodies too.


Workshop associated with CVM 2015

There will be a workshop on Visual Computing for Social and Cognitive Robots on April 15, invited speakers include: Jianfei Cai (NTU, Singapore), Lizhuang Ma(Shanghai Jiaotong University), Nadia Magnenat-Thalmann(NTU Singapore and University of Geneva), Dinesh Manocha(UNC), Jia Pan(The University of Hong Kong), Ruofeng Tong(Zhejiang University), Charlie Wang(The Chinese University of Hong Kong), Hongbin Zha(Peking University).

All participants are welcome to attend the workshop.