Program

CVM 2020 Programme

Conference venue: Online Conference by Tencent/VooV + Bilibili

Download PDF conference programme

     
Day One   Thursday, 3 September 2020
   
9:00 - 9:20 Opening session (Session Chair: Hon-Cheng Wong)
9:20-10:05 Keynote 1 (Session Chair: Shi-Min Hu)
 Gordon Wetzstein (Stanford University)
 Towards Neural Imaging and Display
   
Session 1   Cognitive Media (Session Chair: Weiming Dong)
10:05 - 10:25 Qiang Fu, Hongbo Fu, Hai Yan, Bin Zhou, Xiaowu Chen, Xueming Li
 Human-Centric Metrics for Indoor Scene Assessment and Synthesis
10:25 - 10:45 Rui-Song Zhang, Wei-Ze Quan, Lu-Bin Fan, Li-Ming Hu, Dong-Ming Yan
 Distinguishing Computer-Generated Images from Natural Images Using Channel and Pixel Correlation
10:45 - 11:05 Song-Hai Zhang, Zheng-Ping Zhou, Bin Liu, Xi Dong, Peter Hall
 What and Where: A Context-based Recommendation System for Object Insertion
   
Session 2  Neural Rendering (Session Chair: Kun Xu)
11:05 - 11:25   Zheng Zeng, Lu Wang, Beibei Wang, Chunmeng Kang, Yanning Xu
 Denoising Stochastic Progressive Photon Mapping Renderings Using a Multi-Residual Network
11:25 - 11: 45   Weiheng Lin, Beibei Wang, Lu Wang, Nicolas Holzschuch
  A Detail Preserving Neural Network Model for Monte Carlo Denoising
   
Session 3  Detection, Classification and Recognition (Session Chair: Sio Long Lo)
14:00-14:20   Ruochen Fan, Xuanrun Wang, Qibin Hou, Hanchao Liu, Tai-jiang Mu
  SpinNet: Spinning convolutional network for lane boundary detection
14:20-14:40 Jin-Gong Jia, Yuan-Feng Zhou, Xing-Wei Hao, Feng Li, Christian Desrosiers, Cai-Ming Zhang
 Two-Stream Temporal Convolutional Networks for Skeleton-Based Human Action Recognition
14:40-15:00 Xinxin Liu, Yunfeng Zhang, Fangxun Bao, Kai Shao, Ziyi Sun, Caiming Zhang
  Kernel-blending connection approximated by a neural network for image classification
15:00-15:20 Chuan-Kang Li, Hong-Xin Zhang, Jia-Xin Liu, Yuan-Qing Zhang, Shan-Chen Zou, Yu-Tong Fang
  Window Detection in Facades using Heatmap Fusion
   
Session 4   Image Resizing and Super-resolution (Session Chair: Junhui Hou)
15:20-15:40 Huan-Jing Yue, Sheng Shen, Jing-Yu Yang, Hao-Feng Hu, Yan-Fang Chen
 Reference Image Guided Super-Resolution via Progressive Channel Attention Networks
15:40-16:00 Chuang-Ye Zhang, Yan Niu, Tie-Ru Wu, Xi-Ming Li
 Color Image Super-Resolution and Enhancement with Inter-Channel Details at Trivial Cost
16:00-16:20 Shuai Liu, Ruipeng Gang, Chenghua Li, Ruixia Song
 Adaptive Deep Residual Network for Single Image Super-Resolution
   
Session 5   Mathematics and Algorithms (Session Chair: Yang Liu)
16:20-16:40 Dejun Zhang, Linchao He, Mengting Luo, Zhanya Xu, Fazhi He
  Weight Asynchronous Update: Improves the Diversity of Filters in Deep Convolutional Network
16:40-17:00  Chao Zhang, Xuequan Lu, Katsuya Hotta, Xi Yang
  G2MF-WA: Geometric Multi-Model Fitting with Weakly Annotated Data
17:00-17:20 Xiaohan Liu, Lei Ma, Jianwei Guo, Dong-Ming Yan
 Parallel Computation of 3D Clipped Voronoi Diagrams
   
     
Day Two   Friday, 4 September 2020
   
Session 6  Reconstruction and Segmentation (Session Chair: Chi-Wing Fu)
9:00-9:20 Jianda Zhang, Chunpeng Li, Qiang Song, Lin Gao, Yu-kun Lai
 Automatic 3D tooth segmentation using convolutional neural networks in harmonic parameter space
9:20-9:40 Lili Cheng, Zhuo Wei, Mingchao Sun, Shiqing Xin, Andrei Sharf, Yangyan Li, Baoquan Chen, Changhe Tu
 DeepPipes: Learning 3D PipeLines Reconstruction from Point Clouds
9:40-10:00 Jiahui Huang, Zheng-Fei Kuang, Fang-Lue Zhang, Tai-Jiang Mu
 WallNet: Reconstructing General Room Layouts from RGB Images
   
Session 7  Simulation and Materials (Session Chair: Lvdi Wang)
10:00-10:20 Jianwei Jiang, Bin Sheng, Ping Li, Lizhuang Ma, Xin Tong, Enhua Wu
  Real-Time Hair Simulation with Heptadiagonal Decomposition on Mass Spring System
10:20-10:40 Xiaorui Chen, min Tang, cheng li, Dinesh Manocha, RuoFeng Tong
 BADF: BVH-Centric Adaptive Distance Field Computation for Deformable Objects on GPUs
10:40-11:00 Hong Deng, Beibei Wang, Rui Wang, Nicolas Holzschuch
 A Practical Path Guiding Method for Participating Media
   
Session 8  Shape and Curves (Session Chair: Jianmin Zheng)
11:00-11:20 Zhiyang Dou, Shiqing Xin, Rui Xu, Jian Xu, Yuanfeng Zhou, Shuang-min Chen, Wenping Wang, Xiuyang Zhao, Changhe Tu
 Top-Down Shape Abstraction Based on Greedy Pole Selection
11:20-11:40 Aizeng Wang, Chuan He, Fei Hou, Zhanchuan Cai, Gang Zhao
 Designing planar cubic B-spline curves with monotonic curvature for curve interpolation
11:40-12:00 Fan Zhang, Jinjiang Li, Peiqiang Liu, Hui Fan
 Computing Knots by Quadratic and Cubic Polynomial Curves
   
Session 9  Image Processing and Sythesis (Session Chair: Lei Zhang)
14:00-14:20 Xian Wu, Xiao-Nan Fang, Tao Chen, Fang-Lue Zhang
  JMNet: A Joint Matting Network for Automatic Human Matting
14:20-14:40  Yuting Wang, Shiqing Xin, Shanshan Gao, Yuanfeng Zhou
  Skeletal Saliency Map Computation Based on Projection Symmetry Analysis
14:40-15:00 Xiaoce Wu, Bingyin Zhou, Qingyun Ren, Wei Guo
 Multispectral Image Denoising using Sparse and Graph Laplacian Tucker Decomposition
15:00-15:20 Fei Fang, Fei Luo, Hong-pan Zhang, Hua-jian Zhou, Alix L.H. Chow, Chun-xia Xiao
 A Comprehensive Pipeline for Complex Text-to-Image Synthesis
   
Session 10  SLAM and Motion Capture (Session Chair: Changhe Tu)
15:20-15:40  Zheng-Jun Du, Shi-Sheng Huang, Tai-Jiang Mu, Qunhe Zhao, Ralph R. Martin, Kun Xu
  Accurate RGB-D SLAM in Dynamic Environments using Observationally Consistent Conditional Random Fields
15:40-16:00  Kun Li, Yali Mao, Yunke Liu, Ruizhi Shao, Yebin Liu
  Full-body Motion Capture for Multiple Closely Interacting Persons
16:00-16:20  Miaopeng Li, Zimeng Zhou, Xinguo Liu
  3D Hypothesis Clustering for Cross-view Matching in Multi-person Motion Capture
   
16:20-17:05 Keynote 2 (Session Chair: Belen Masia)
  Christian Theobalt (MPI Informatik)
 New methods for Reconstruction and Neural Rendering of Real World Scenes
     
Day Three   Saturday, 5 September 2020
   
9:00-09:45 Keynote 3 (Session Chair: Ying He)
  Ruizhen Hu (Shenzhen University)
 Shape analysis via functionality and mobility inference
   
Session 11  Video Understanding (Session Chair: Miao Wang)
9:45-10:05 Yaohua Pan, Zhibin Niu, Jing Wu, Jiawan Zhang
 InSocialNet: Interactive Visual Analytics for Role-Event Videos
10:05-10:25 Hui-si Wu, Meng-shu Liu, Lu-lu Yin, Ping Li, Zhen-kun Wen, Hon-Cheng Wong
 Automatic Video Segmentation Based on Information Centroid and Optimized SaliencyCut
10:25-10:45 Yongqing Liang, Navid Jafari, Xing Luo, Qin Chen, Yanpeng Cao, Xin Li
  WaterNet: An adaptive matching pipeline for segmenting water with volatile appearance
   
Session 12  Visualization and Visual Analysis (Session Chair: Jiazhi Xia)
10:45-11:05 Naoki Kita, Gregoire Cliquet, Kazunori Miyata
 Mapping Two-Dimensional Plots to a Spherical Surface using Elliptical Grid Mapping
11:05-11:25 Songye Han, Shaojie Ye, Hongxin Zhang
 Visual exploration of Internet news via sentiment score and topic models
11:25-11:45 Cui-Xia Ma, Jian-Cheng Song, Qian Zhu, Kevin Maher, Ze-Yuan Huang, Hong-An Wang
 EmotionMap: Visual Analysis of Video Emotional Content on a Map
11:45-12:00  Closing Session (Session Chair: Ying He)
     
     

Keynote Speakers

Gordon Wetzstein, Stanford University

Title:

Towards Neural Imaging and Display

Abstract:

Computational imaging leverages the co-design of hardware and software to re-define next-generation camera and display systems. In this talk, we discuss recent advances in computational single-photon imaging to enable non-line-of-sight vision and 3D imaging through highly scattering media. We also discuss how the emerging paradigm of end-to-end optimization of optics and imaging processing algorithms unlocks unprecedented capabilities in HDR and depth imaging as well as hybrid optical-electronic computing. Finally, similar end-to-end design strategies also allow us to define next-generation displays, such as holographic near-eye systems for virtual and augmented reality applications, which we will discuss in this talk.

Speaker's Biography:

Gordon Wetzstein is an Assistant Professor of Electrical Engineering and, by courtesy, of Computer Science at Stanford University. He is the leader of the Stanford Computational Imaging Lab and a faculty co-director of the Stanford Center for Image Systems Engineering. At the intersection of computer graphics and vision, computational optics, and applied vision science, Prof. Wetzstein's research has a wide range of applications in next-generation imaging, display, wearable computing, and microscopy systems. Prior to joining Stanford in 2014, Prof. Wetzstein was a Research Scientist in the Camera Culture Group at MIT. He received a Ph.D. in Computer Science from the University of British Columbia in 2011 and graduated with Honors from the Bauhaus in Weimar, Germany before that. He is the recipient of an NSF CAREER Award, an Alfred P. Sloan Fellowship, an ACM SIGGRAPH Significant New Researcher Award, a Presidential Early Career Award for Scientists and Engineers (PECASE), an SPIE Early Career Achievement Award, a Terman Fellowship, an Okawa Research Grant, the Electronic Imaging Scientist of the Year 2017 Award, an Alain Fournier Ph.D. Dissertation Award, and a Laval Virtual Award as well as Best Paper and Demo Awards at ICCP 2011, 2014, and 2016 and at ICIP 2016.


Christian Theobalt, MPII Saarbrucken, Germany

Title:

New methods for Reconstruction and Neural Rendering of Real World Scenes

Abstract:

In this presentation, I will talk about some of the recent work we did on new methods for reconstructing computer graphics models of specific classes of dynamic real world scenes from sparse or even monocular video data. I will also talk about how neural rendering approaches that combine model-based and neural network based concepts for image formation in new ways enable new ways synthesize highly realistic imagery and videos of real work scenes under user control. My talk will exemplify these concepts using work we did on human faces and face video, but will also briefly illustrate how we began to extend these concepts to a broader range of scenes.

Speaker's Biography:

Christian Theobalt is a Professor of Computer Science and the head of the research group "Graphics, Vision, & Video" at the Max-Planck-Institute (MPI) for Informatics, Saarbrucken, Germany. He is also a Professor of Computer Science at Saarland University, Germany. From 2007 until 2009 he was a Visiting Assistant Professor in the Department of Computer Science at Stanford University. He received his MSc degree in Artificial Intelligence from the University of Edinburgh, his Diplom (MS) degree in Computer Science from Saarland University, and his PhD (Dr.-Ing.) from the Max-Planck-Institute for Informatics. In his research he looks at algorithmic problems that lie at the intersection of Computer Graphics, Computer Vision and machine learning, such as: static and dynamic 3D scene reconstruction, marker-less motion and performance capture, virtual and augmented reality, computer animation, appearance and reflectance modelling, intrinsic video and inverse rendering, machine learning for graphics and vision, new sensors for 3D acquisition, advanced video processing, as well as image- and physically-based rendering. He is also interested in using reconstruction techniques for human computer interaction. For his work, he received several awards, including the Otto Hahn Medal of the Max-Planck Society in 2007, the EUROGRAPHICS Young Researcher Award in 2009, the German Pattern Recognition Award 2012, and the Karl Heinz Beckurts Award in 2017. He received two ERC grants, an ERC Starting Grant in 2013 and an ERC Consolidator Grant in 2017. In 2015, he was elected as one of the top 40 innovation leaders under 40 in Germany by the business magazine Capital. Christian Theobalt is also a co-founder of an award-winning spin-off company from his group - www.thecaptury.com - that is commercializing one of the most advanced solutions for marker-less motion capture.


Ruizhen Hu, Shenzhen University

Title:

Shape analysis via functionality and mobility inference

Abstract:

The computational power, especially neural network processing power of mobile devices will be advanced significantly in the near future. Combined with better camera sensors and new camera module designs, it provides an exciting opportunity to revamp the traditional mobile imaging technologies, and brings new and exciting photography experiences to virtually everyone around the world. It is a brand new chapter in the history of photography, and it has never been a better time to work in this area. In this talk, I will introduce a series of new mobile photography technologies and applications that we are developing in-house, many will soon be released to tens of millions of end users worldwide. I will also shed some light on where the industry is going moving forward.
One of the goals of computer graphics is to provide tools for designing and simulating real or imagined artifacts, such as man-made objects. Such artifacts are usually functional, and thus an understanding of functionality is paramount for simulating and validating different designs of artifacts. Moreover, in recent years, computer graphics and related fields, such as computer vision and robotics, have also devoted much attention to the inference of possible motions of 3D objects and their parts, since this problem is closely related to an understanding of object and functionality. In this talk, I will introduce a series of works on analysis and understanding of shape functionality and part mobility with interaction as the key component, and discuss its potential applications in modeling, fabrication and robotics.

Speaker's Biography:

Ruizhen Hu is an Assistant Professor at Shenzhen University, China. She received her Ph.D. from the Department of Mathematics, Zhejiang University. Before that, she spent two years visiting Simon Fraser University, Canada. Her research interests are in computer graphics, with a recent focus on applying machine learning to advance the understanding and generative modeling of visual data including 3D shapes and indoor scenes. She has received several research awards including the Asia Graphics “Young Researcher Award” in 2019, among others.