Jingyi Yu (虞晶怡)

Professor, Executive Dean

School of Information Science and Technology
ShanghaiTech University
DGene Inc.

  • Office: Room 1A-217, SIST ShanghaiTech
  • Email: yujingyi@@shanghaitech.edu.cn
  • Tel: (021) 20685380

Bio

Prof. Jingyi Yu is currently the Faculty Search Committee Directora and the SIST Tenure & Promotion Committee Director. Prof. Jingyi Yu is a professor and executive dean of the School of Information Science and Technology at ShanghaiTech University. He received B.S. from Caltech in 2000 and Ph.D. from MIT in 2005. He is also affiliated with the University of Delaware.

His research interests span a range of topics in computer vision and computer graphics, especially on computational photography and non-conventional optics and camera designs. He has published over 120 papers at highly refereed conferences and journals including over 70 papers at the premiere conferences and journals CVPR/ICCV/ECCV/TPAMI.

He has also been granted 10 US patents. His research has been generously supported by the National Science Foundation (NSF), the National Institute of Health, the Army Research Office, and the Air Force Office of Scientific Research (AFOSR). He is a recipient of the NSF CAREER Award, the AFOSR YIP Award, and the Outstanding Junior Faculty Award at the University of Delaware. He has served as general chair, program chair, and area chair of many international conferences such as CVPR, ICCV, ECCV, ICCP and NIPS. He is currently an Associate Editor of IEEE TPAMI, IEEE TIP and Elsevier CVIU, and will be program chair of ICPR 2020 and IEEE CVPR 2021.

Teaching

ShanghaiTech(2015-present):
Undergraduate Computer Graphics(Spring 17)
Introduction to Algorithms (Fall 16)
Graduate Computer Graphics (Spring 16)
Computational Photography (Fall 15,17)
University of Delaware(2005-2015):
CISC 320 Introduction to Algorithms (S09, S14)
CISC 849 Advanced Computer Graphics (F08)
CISC 829 Computational Geometry/Advanced Computational Photography (S08, S10, F12)
CISC 849 Computational Photography and Videos (F05, F06, F07, S09, S12, F13)
CISC 440/640 Computer Graphics (S06, F06, S07, F07, S10, F10, S11, S13)

Advising

ShanghaiTech University:
Xi Luo, Xin Chen, Ruiyang Liu, Shi Jin, Huangjie Yu, Anpei Chen, Jie Lu, Mingye Wu, Yingliang Zhang, Zhong Li, Zhang Chen, Mingyuan Zhou, Ziran Xin, Zhengzhong Sun, Yu Zhu, Kang Zhu, Peihong Yu, Yuwei Li, Guli Zhang, Cen Wang, Siyuan Li, Yuanxi Ma
University of Delaware:
Haiting Lin, (PostDoc, graduated 2017)
Wei Yang (Ph.D., graduated 2017)
Nianyi Li (Ph.D., graduated 2017)
Yang Yang (Ph.D., graduated 2017)
Can Chen (Ph.D., graduated 2017)
Bilin Sun (Ph.D., graduated 2017)
Yu Ji (Ph.D., graduated 2015)
Xinqing Guo (Ph. D., graduated 2017)
Peter Huang (M.S., graduated 2015)
Jinwei Ye (Ph.D., graduated 2013)
Zhan Yu (Ph.D., PostDoc,graduated 2013)
Luis D. Lopez (Ph.D., graduated 2013)
Xuan Yu (Ph.D., graduated 2012)
Miao Tang (M.S., graduated 2012)
Feng Li (Ph.D., graduated 2011)
Christopher Thorpe (M.S., graduated 2011)
Yuanyuan Ding (Ph.D., graduated 2010)
Yuqi Wang (M.S., graduated 2009)
Kevin Kreiser (M.S., graduated 2009)

Professional Activity

Conference Organizations
- Program Chair, 2021 IEEE Conference on Computer Vision and Pattern Recognition.
- Area Chair, 2017 IEEE Conference on Computer Vision and Pattern Recognition./dd>
- Area Chair, 2017 International Conference on Computer Vision (ICCV '17)
- Area Chair, 2017 Conference on Neural Information Processing Systems (NIPS '17).
- Program Chair, the 2nd Workshop on Light Field for Computer Vision (LF4CV '17) in conjunction with CVPR 2017.
- Workshop Chair, 2015 International Conference on Computer Vision (ICCV '17).
- Program Chair, 2016 International Conference on Computational Photography (ICCP '16).
- Area Chair, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR '16).
- Area Chair, 2015 Conference Neural Information Processing Systems (NIPS '15).
- Area Chair, the 15th International Conference on Computer Vision (ICCV '15).
- Area Chair, 2015 Neural Information Processing Systems Conference (NIPS '15).
- Program Chair, the 4th International Workshop on Computational Camera and Displays (CCD '15).
- Finance Chair, the 2015 International Conference on Computational Photography (ICCP '15).
- Area Chair, the 2014 Asian Conference on Computer Vision (ACCV '14).
- Technology Chair, the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR '14).
- Industry Chair, the 2014 International Confernce on Computational Photography (ICCP '14).
- Area Chair, the 13th International Conference on Computer Vision (ICCV '11).
- Program Chair, the 11th International Workshop on Omnidirectional Vision, Camera Networks and Non-classical Cameras (OMNIVIS '11), in Conjunction with ICCV 2011.
- General Chair, the 6th International Workshop on Projector-Camera Systems (PROCAMS '09), in Conjunction with CVPR 2009.
Program Committees
- ACM SIGGRAPH Interactive 3D Graphics
- International Conference on Computational Photography
- ACM Multimedia
- IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- The Pacific Conference on Computer Graphics and Applications (PG)
- Shape Modeling International (SMI)
- The International Conference on Computer Graphics, Imaging, and Visualization (CGIV)
- Computer Animation and Social Agents (CASA)
- International Conference on Computer Vision (ICCV)
- European Conference on Computer Vision (ECCV)
- Asian Conference on Computer Vision (ACCV)

Recent Publication

Sparse Photometric 3D Face Reconstruction Guided by Morphable Models
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
Xuan Cao, Zhang Chen, Anpei Chen, Xin Chen, Shiying Li and Jingyi Yu.
4D Human Body Correspondences from Panoramic Depth Maps
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
Zhong Li, Minye Wu, Wangyiteng Zhou and Jingyi Yu.
Automatic 3D Indoor Scene Modeling from Single Panorama
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
Yang Yang, Shi Jin, Ruiyang Liu, Sing Bing Kang and Jingyi Yu.
Gaze Prediction in Dynamic 360° Immersive Videos
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
Yanyu Xu, Yanbing Dong, Junru Wu, Zhengzhong Sun, Zhiru Shi, Jingyi Yu, and Shenghua Gao.
Hyperspectral Light Field Stereo Matching
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018
Kang Zhu, Yujia Xue, Qiang Fu, Sing Bing Kang, Xilin Chen and Jingyi Yu.
Deep Surface Light Fields
ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games, 2018
Anpei Chen, Minye Wu, Yingliang Zhang, Nianyi Li, Jie Lu, Shenghua Gao and Jingyi Yu.
Content Aware Image Pre-Compensation
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018
Jinwei Ye, Yu Ji, Mingyuan Zhou, Sing Bing Kang and Jingyi Yu.

Complete List

Research

Computational Cameras and Projectors
Computational Cameras and Projectors: Camera models are fundamental to computer vision and graphics. The classical pinhole camera model has long served as the workhorse of 3D imaging applications. My research aims to develop new imaging systems and algorithms beyond pinhole optics to more effectively acquire, represent, analyze, and utilize the 3D imagery data. For example, I have developed multi-perspective imaging systems,crossed-slit imaging theory and applications, coded aperture/shutter/flash cameras, light field camera and camera array, catadiotropic cameras and projectors, and hybrid sensors to overcome the limitations on speed, focus, field-of-view, perspective, dynamic range, etc., in commodity cameras and projectors. I have organized a number of premiere workshops on this topic.
Light Field Imaging for Vision and Graphics
Light Field Imaging for Vision and Graphics: Light fields are image-based representations of scenes. While the original goal of acquiring a light field is to conduct image-based modeling and rendering (e.g., to produce after-capture refocusing), my focus has been to apply light field imaging in various applications in computer vision and robotics, including stereo matching and 3D reconstruction , stereoscopy synthesis, effective line-art illustrations, saliency detection, surveillance and recognition, etc. The key tool that I have used for designing these solutions is a novel ray differential geometry framework. This new theory is explicitly developed to characterize light field structures and to correlate surface differential geometry with ray geometry. In addition, I have organized the first Light Field for Computer Vision (LF4CV) workshop in conjunction with ECCV ’14.
Recovering “Invisible” Objects
Recovering “Invisible” Objects: Faithfully acquiring invisible or transparent objects such as 3D fluid wavefronts or gas density can greatly benefit fluid mechanics, oceanography, and computer animation. My focus is to develop non-intrusive solutions by coupling computational cameras with new computer vision algorithms. For example, we have constructed a light field camera array along with a new shape-from-distortion framework for reconstructing fast evolving fluid wavefronts and volumetric gas flows. Along with a new fluid-dynamics based optical flow technique, our solution can further predict fluid motions and verify fluid dynamics models. I have given multiple tutorials and published an online book on this topic.
Privacy-Preserving Surveillance
Video surveillance in public spaces has increased dramatically in recent history. So has concern about the potential for abuse and the general loss of privacy. We explore new solutions on the acquisition front: we aim to design computational cameras that will produce features that are recognizable at the category level but not at the object level, i.e., the acquired imagery data can be recognized by computer but not by human. The two solutions we have developed thus far are extracting occlusion contours to hide the identity information and applying strategic convolutional blurs to achieve multi-level identity obscuring.
Biomedical Imaging and Bioinformatics
My computational camera work also finds it uses in biomedical imaging and bioinformatics. For example, we have developed a multi-flash endoscope to robustly extract tumor contours and we are currently designing a multiresolution, multi-focus microscope based on the light field camera. In the field of bioinformatics, my focus is to apply visual analytics techniques to systematically tackle gene functions and complex regulatory processes. For example, we have combined image processing and machine learning to archive and retrieve biomedical documents on protein-protein interactions.