Deqing Sun

Deqing Sun is a Senior Research Scientist at the Learning and Perception Research group at NVIDIA.  He was a postdoctoral research fellow in Prof. Hanspeter Pfister’s Visual Computing group from Aug. 2012 to Oct. 2015 (and is a visiting researcher). He received his B.Eng. degree in Electronic and Information Engineering from Harbin Institute of Technology, his M.Phil. degree in Electronic Engineering from the Chinese University of Hong Kong, and his M.S. and Ph.D. degrees in Computer Science from Brown University working with Prof. Michael J. Black. He was a research intern at Microsoft Research New England in 2010 working with Dr. Ce Liu. His research interests include computer vision, machine learning, and computational photography, particularly motion estimation and segmentation and the applications to computational video. He regularly serves on program committees and reviews papers for major computer vision, machine learning, and computer graphics conferences. He is serving as an area chair for ECCV 2018 and CVPR 2019 and co-organizing "what is optical flow for?" workshop at ECCV 2018. He and his collaborators received a best paper honorable mention award from CVPR 2018 for their work on sparse lattice networks for point cloud processing.

For my publications before joining NVIDIA, please check here.

Recent Updates
SPLATNet received a best paper honorable mention award from CVPR 2018
PWC-Net won first place in the optical flow track of the robust vision challenge
Press coverage for Super SloMoCNET, ExtremeTech, PCGamesN, The Inquirer, Ubergizmo, Android HeadlinesPetaPixel, Motherboard, and Lowyat.NET etc.
Serving as an area chair at ECCV 2018 and CVPR 2019
Co-organizing "What is optical flow for?" workshop at ECCV 2018

Code and Software
Caffe and PyTorch Code for PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume  CVPR 2018
Matlab Code for  Blind Image Deblurring Using Dark Channel Prior CVPR 2016.
Matlab Code for Optical Flow with Semantic Segmentation and Localized Layers CVPR 2016.
Code for Blind Video Temporal Consistency SIGGRAPH Asia 2015. 
Matlab Code for Layered RGBD Scene Flow Estimation CVPR 2015.
Matlab Code for A Quantitative Analysis of Current Practices in Optical Flow Estimation and the Principles Behind Them IJCV 2014.
Matlab Code for Secrets of Optical Flow Estimation and Their Principles CVPR 2010.
Matlab Code for Black and Anandan method
Matlab Code for Horn and Schunck method
Matlab Code for Postprocessing of Low Bit Rate Block DCT Coded Images based on a Fields of Experts Prior TIP 2007.