Yebin Liu's homepage (刘烨斌)

Yebin Liu 刘烨斌

Assistant Professor

Broadband Network & Digital Media Lab, Department of Automation, Tsinghua University, Beijing 100084, China

Telephone: +86-10-6278-8613 ext 816 (o)
Mobile: +86-18910685906
E-Mail: liuyebin@tsinghua.edu.cn

招聘实习生

招聘外校保送直博生、博士后

Background

Jan. 2010 ~ April. 2011, Max-Planck Institute Informatk, Saarbucken, Germany.
Ph.D. Sep. 2005 ~ July. 2009, Department of Automation, Tsinghua University, Beijing, China.
M.D. Sep. 2002 ~ July. 2005, Department of Automation, Tsinghua University, Beijing, China.
B.Eng. Sep. 1998 ~ July 2002, School of Automation, Beijing University of Posts & Telecommunication (BUPT), Beijing, China.

Research Interests

Markerless Motion Capture
Image-based Modeling and Rendering
Photometric Stereo and Relighting

Research Projects

Noisy Depth Maps Fusion for Multi-view Stereo via Matrix Completion IEEE Journal of Selected Topics in Signal Processing
This paper introduces a matrix completion framework to fuse noisy point clouds from multi-view images of the same object.

A Data-driven Approach for Facial Expression Synthesis in Video CVPR 2012
This paper presents a data driven method to synthesize a realistic facial animation of a target person, driven by a facial performance video of another person.

Shading-based Dynamic Shape Refinement from Multi-view Video under General Illumination ICCV 2011 video
We present an approach to add true fine-scale spatiotemporal shape detail to dynamic scene geometry captured from multi-view video footage.

Video-based Characters - Creating New Human Performances from a Multi-view Video Database SIGGRAPH 2011
We present a data driven method to synthesize plausible video sequences of humans according to user-defined body motions and viewpoints.

	Markerless Motion Capture of Interacting Characters Using Multi-view Image Segmentation CVPR 2011(Oral) We present a markerless motion capture approach that reconstructs the skeletal motion and detailed time-varying surface geometry of two closely interacting people from multi-view video.
	Dynamic Shape Capture via Periodical-illumination Optical Flow Estimation and Multi-view Photometric Stereo 3DIMPVT 2011 We present an optical flow estimation approach which works under periodically varying illuminations, and in cooperation with photometric stereo, enables high-quality 3D reconstruction of dynamic objects.
	Fusing Multiview and Photometric Stereo for 3D Reconstruction under Uncalibrated Illumination TVCG 2011 We propose a method to obtain a complete and accurate 3D model from multi-view images captured under a variety of unknown illuminations. .
	Continuous Depth Estimation for Multi-view Stereo CVPR09 This paper presents a variational multi-view depth estimation method for multi-view 3D reconstruction.
	Point Cloud Based MVS for Free-viewpoint Video TVCG09 We propose a point cloud based multi-view stereo algorithm for free-viewpoint video.
	Multi-camera and Multi-Lighting Dome ICME09a ICME09b ICME09c We construct a dome to record the geometry, texture and motion of human actors in a dedicated multiple-camera studio with controlled lighting and a chromakey background.
	Light Field Camera Array and Dynamic Light Field Streaming EUROSIP08 VCIP07 ICME06 We present a flexible 3DTV system in which multi-view video streams are captured, compressed, transmitted, and finally converted to high-quality 3D video in real time.

Talks

1. "Vision Field Capturing ", Tutorial, 3DTV Conference, in Tampere, Finland, June 7-9 2010.

2. "Geometry, Motion and Appearance Modeling in Multi-camera and Multi-lighting (MVML) Dome".This talk has been presented in the following research groups: (Download Slides)

MPI Computer Graphics, Saarbruchen, Germany; Nov.3, 2009.
ETHZ Computer Vision and Geometry Group , Zurich, Switzerland; Nov.5, 2009.
HHI Computer Vision and Graphics, Berlin, Germany; Nov.6, 2009.
Philips Research Aachen, Aachen, Germany; Nov.9, 2009.
RWTH Computer Graphics and Multimedia, Aachen, Germany; Nov.9, 2009.
INRIA Willow Team, Paris, France; Nov.12, 2009.
EPFL AudioVisual Communications Lab , Laussanne, Switzerland; Nov.13, 2009.
SURREY CVSSP , Guildford, UK; Nov.16, 2009.

3. "Multi-view Image based Scene Reconstruction and Rendering".

International Symposium on Pattern Recognition and Multimedia Computing, Graduate University of Chinese Academic of Sciences, Beijing, China, June 27,2011

Committee Member

Data, Tool and Code

Code: Camera display software for calibration parameter. Updated by July.23, 2009.

Data: 4x8 dynamic light filed dataset. Filmed in 2005.

Data: Free-viewpoint video on a ring. Updated by Aug.6, 2009.

Data: Multi-view multi-lighting datasets. Updated by July.23, 2009.

Publications

Kai Li, Feng Xu, Jue Wang, Qionghai Dai, Yebin Liu, A Data-driven Approach for Facial Expression Synthesis in Video, in IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2012.
Yue Deng, Yebin Liu, Qionghai Dai, Zengke Zhang, Yao Wang, Noisy Depth Maps Fusion for Multi-view Stereo via Matrix Completion, accepted in IEEE Journal of Selected Topics in Signal Processing, 2012.
Chenglei Wu, Kiran Varanasi, Yebin Liu, Hans-Peter Seidel and Christian Theobalt, Shading-based Dynamic Shape Refinement from Multi-view Video under General Illumination, IEEE Int'l Conf. Computer Vision, ICCV 2011, Barcelona, Spain, Nov. 6-13, 2011
Feng Xu, Yebin Liu, Carsten Stoll, James Tompkin, Gaurav Bharaj, Qionghai Dai, Hans-Peter Seidel, Jan Kautz and Christian Theobalt, Video-based Characters - Creating New Human Performances from a Multi-view Video Database, SIGGRAPH 2011, also in ACM Trans. Graphics .
Yebin Liu, Carsten Stoll, Guergen Gall, Hans-Peter Seidel, Christian Theobalt, "Markerless Motion Capture of Interacting Characters Using Multi-view Image Segmentation", IEEE Int'l Conf. Computer Vision and Pattern Recognition, CVPR 2011 (Oral), Colorado Springs, June 21-23, 2011
Yebin Liu, Qionghai Dai and Wenli Xu, "A Point-Cloud-Based Multi-View Stereo Algorithm For Free-viewpoint Video", IEEE trans. Visualization and Computer Graphics, May/June 2010, vol.16 no.3, pp. 407-418.
Chenglei Wu, Yebin Liu and Qionghai Dai, "Fusing Multiview and Photometric Stereo for 3D Reconstruction under Uncalibrated Illumination", IEEE Trans. Visualization and Computer Graphics, August 2011, vol.17 no.8, pp. 1082-1095.
Ying Fu, Yebin Liu, Qionghai Dai, "Dynamic Shape Capture via Periodical-illumination Optical Flow Estimation and Multi-view Photometric Stereo", International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2011, Hangzhou, China, May 17-21, 2011.
Yebin Liu, Xun Cao, Qionghai Dai and Wenli Xu, "Continuous Depth Estimation for Multi-view Stereo", IEEE Int'l Conf. Computer Vision and Pattern Recognition, CVPR 2009, Florida, USA, June, 2009.
Chenglei Wu, Yebin Liu, Xiangyang Ji, Qionghai Dai, "Multi-view Reconstruction under Varying Illumination Conditions", Oral, IEEE Int'l Conf. Multimedia Expo, ICME'09, Canjun, Mexico, June 29-July3, 2009.
Guangwei Yang, Yebin Liu, "3D Object Relighting based on Multi-view Stereo and Image based Relighting Technique", Oral, IEEE Int'l Conf. Multimedia Expo, ICME'09,Canjun, Mexico, June 29-July3, 2009.
Xiaoduan Feng, Yebin Liu, Qionghai Dai, 'Point-cloud Refinement Via Exact Matching", Oral, IEEE Int'l Conf. Multimedia Expo, ICME'09, Canjun, Mexico, June 29-July3, 2009.
Yebin Liu, Qionghai Dai and Wenli Xu, "Graph-Cuts Fusion of Distance Fidelity Maps for Volumetric Multi-view Stereo", Chinese Journal Of Electronics, 18(3), pp449-454, 2009 (SCI)
Yebin Liu, Qionghai Dai and Wenli Xu, "A Wide Base Line Multiple Camera System for High Performance 3D Video and Free Viewpoint Video", Chinese Journal Of Electronics 2009, 18(2):275-280. (SCI)
Qionghai Dai, Yebin Liu and Xu Wenli, "Data Compression of Light Field Using Multiscale Edges", Chinese Journal Of Electronics, Vol.16, No.1, pp101-106, 2007 (SCI)
Xun Cao, Yebin Liu and Qionghai Dai，"A Flexible Client-Driven 3DTV System for Real-Time Acquisition, Transmission, and Display of Dynamic Scenes", EURASIP Journal on Advances in Signal Processing, Volume 2009, Article ID 351452, doi:10.1155/2009/351452.

资助与获奖

2010年国家自然科学基金面上项目“基于视觉场计算的复杂场景重建研究”
2010年中国博士后科学基金特别资助
2009年中国博士后科学基金面上资助一等资助
2009年深圳市高层次专业人才认定“国家级领军人才”
2008年国家技术发明奖,“基于融合网络的流媒体服务新技术”获国家技术发明二等奖(第3完成人)
2008年清华大学信息科学与技术国家实验室杰出贡献一等奖
2008年 “人体运动恢复与分析”获第三届由田机器视觉奖创新类第2名
2007年中国电子学会，电子信息科学技术奖二等奖
2006年广东省科学技术奖,“IPTV综合服务系统”获广东省科学技术二等奖
2005年 “基于移动互联网的手机电视”获清华大学第23届挑战杯三等奖
2004年 “视频编码传输仿真平台”获清华大学学生实验室建设贡献奖
2001年美国国际数学建模竞赛一等奖
2001年应用计算机建模竞赛全国二等奖
2001年全国大学生英语竞赛三等奖
1999年北京市大学生大学物理竞赛一等奖
1999年北京市大学生高等数学竞赛特等奖 (唯一特等奖)

Patents

一种用于跨网段传输视频码流的容错转码控制方法. 中国发明专利, 授权号:ZL 200310101663.4.
一种基于光场渲染的自由视点视频在IP网传输方法. 中国发明专利, 授权号:ZL 200610165243.6.
一种交互式三维重建方法. 中国发明专利, 授权号:ZL 200810105344.3.
一种适用于球形相机阵列的相机颜色较准方法. 中国发明专利, 授权号:ZL 200810103683.8.
基于光流场的平面视频转立体视频的方法. 中国发明专利, 授权号:ZL 200710117654.2
变化光照动态场景三维采集系统. 中国发明专利, 授权号:ZL 200810104943.3.
采用环形低帧率摄像机阵列对高速运动物体建模的方法. 中国发明专利, 授权号:ZL 200810103684.2.
一种环形摄像机阵列校准系统及其方法.中国发明专利,授权号:ZL 200710121782.4.
三维影像显示深度调整方法. 中国发明专利, 授权号:ZL 200810112454.2.
多摄像机阵列几何校准软件，中华人民共和国国家版权局计算机软件著作权，2010

Links

Broadband Network and Digital Media Lab
Tsinghua University