About me

I am a research scientist at Hikvision, and I am looking for interns right now! Please contact me if you are interested.
I worked at Light for 2 years to make an innovative camera. The camera is already in the market!!
I received my Phd in Computer Science at University of California, Merced, working with Prof. Ming-Hsuan Yang.
My research interests include computational photography and computer vision, especially on developing algorithms for image restoration.

Here is my CV and Google Scholar page.

__________________________________________________________________________

Experience

• 2017.08 - current, Research Scientist @ Hikvision

• 2015.10 - 2017.07, Research Scientist @ Light

• 2015.05 - 2015.08, Intern @ Light

• 2014.05 - 2014.08, Research Intern @ Microsoft Research Asia

• 2013.05 - 2013.08, Research Intern @ Adobe

__________________________________________________________________________

Education

• 2009.08 - 2015.08, Ph.D. in Computer Science @ University of California, Merced

• 2005.08 - 2009.06, B.S. in Mathematics (Honor) @ Zhejiang University

__________________________________________________________________________

Publications

• Deblurring Low-light Images with Light Streaks
  Zhe Hu, Sunghyun Cho, Jue Wang and Ming-Hsuan Yang
  submitted in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).
  

• L0-Regularized Intensity and Gradient Prior for Deblurring Text Images and Beyond
  Jinshan Pan, Zhe Hu, Zhixun Su and Ming-Hsuan Yang
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2016.
  

• Image Deblurring using Smartphone Inertial Sensors
  Zhe Hu, Lu Yuan, Steve Lin and Ming-Hsuan Yang
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016) , Las Vegas, US, 2016.
  

• A Comparative Study for Single-Image Blind Deblurring
  Wei-Sheng Lai, Jia-Bin Huang, Zhe Hu, Narendra Ahuja and Ming-Hsuan Yang
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016) , Las Vegas, US, 2016. (Spotlight oral presentation)
  

• Soft-Segmentation Guided Object Motion Deblurring
  Jinshan Pan, Zhe Hu, Zhixun Su, Hsin-Ying Lee and Ming-Hsuan Yang
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016) , Las Vegas, US, 2016.
  

• Deblurring Face Images with Exemplars
  Jinshan Pan*, Zhe Hu*, Zhixun Su and Ming-Hsuan Yang (* indicates equal contribution)
  Proceedings of European Conference on Computer Vision (ECCV 2014) , Zurich, Switzerland, 2014.
  [Project page] [PDF] [MATLAB code]

• Deblurring Low-light Images with Light Streaks
  Zhe Hu, Sunghyun Cho, Jue Wang and Ming-Hsuan Yang
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014), Columbus, Ohio, US, 2014.
  [Project page] [PDF] [MATLAB code]

• Joint Depth Estimation and Camera Shake Removal from Single Blurry Image
  Zhe Hu, Li Xu and Ming-Hsuan Yang
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014), Columbus, Ohio, US, 2014.
  [Project page] [PDF] MATLAB code

• Deblurring Text Images via L0-Regularized Intensity and Gradient Prior
  Jinshan Pan, Zhe Hu, Zhixun Su and Ming-Hsuan Yang
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014), Columbus, Ohio, US, 2014.
  [Project page] [PDF] [MATLAB code]

• Good Regions to Deblur
  Zhe Hu and Ming-Hsuan Yang
  Proceedings of European Conference on Computer Vision (ECCV 2012), Firenze, Italy, October, 2012. (Oral presentation, Acceptance rate: 2.8%)
  [Project page] [PDF] [MATLAB code]
  Learning Good Regions to Deblur Image
  Zhe Hu and Ming-Hsuan Yang
  International Journal on Computer Vision (IJCV) 2015
  

• Fast Non-uniform Deblurring using Constrained Camera Pose Subspace
  Zhe Hu and Ming-Hsuan Yang
  Proceedings of British Machine Vision Conference (BMVC 2012), Guildford, UK, September, 2012. (Oral presentation, Acceptance rate: 8.0%)
  [Project page] [PDF] [MATLAB code]

• Single Image Deblurring with Adaptive Dictionary Learning
  Zhe Hu, Jia-Bin Huang and Ming-Hsuan Yang
  Proceedings of IEEE International Conference on Image Processing (ICIP 2010), Hong Kong, China, September, 2010.
  [Project page] [PDF] [Poster] [MATLAB code]