Kai Zhang (张 凯)

Computer Vision Lab
Department of Information Technology and Electrical Engineering, ETH Zurich

ETF D117, Sternwartstrasse 7, ETH Zentrum 8092, Zurich, Switzerland

Email: cskaizhang@gmail.com
[Google Scholar] [Github] [ResearchGate]

Biography

I am currently a postdoctoral researcher at Computer Vision Lab, ETH Zurich, Switzerland, working with Prof. Luc Van Gool and Dr. Radu Timofte. Before that, I received my Ph.D. degree from School of Computer Science and Technology, Harbin Institute of Technology, China, in 2019, under the supervision of Prof. Lei Zhang and Prof. Wangmeng Zuo. I was a research assistant from July, 2015 to July, 2017 and from July, 2018 to April, 2019 in Department of Computing of The Hong Kong Polytechnic University.

Research Interest

I work in the field of image processing, specializing in particular on developing deep learning techniques for inverse problems in low-level computer vision. I mainly investigate how to incorporate traditional model-based method and deep learning-based method for flexible, effective, efficient and interpretable image restoration. Recently, I focus on the following research topics:

PyTorch Toolbox for Image Restoration

News

Selected Publications

 

Designing a Practical Degradation Model for Deep Blind Image Super-Resolution

Kai Zhang, Jingyun Liang, Luc Van Gool and Radu Timofte
ArXiv, 2021.
[Paper] [PyTorch Code] [BibTex]

 

Flow-based Kernel Prior with Application to Blind Super-Resolution

Jingyun Liang, Kai Zhang, Shuhang Gu, Luc Van Gool, Radu Timofte
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
[Paper] [PyTorch Code] [BibTex]

 

Plug-and-Play Image Restoration with Deep Denoiser Prior

Kai Zhang, Yawei Li, Wangmeng Zuo, Lei Zhang, Luc Van Gool and Radu Timofte
ArXiv, 2020.
[Paper] [PyTorch Code] [BibTex]

 

AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results

Kai Zhang, Martin Danelljan, Yawei Li, Radu Timofte and others
European Conference on Computer Vision Workshops (ECCVW), 2020.
[Paper] [BibTex]

 

Deep Unfolding Network for Image Super-Resolution

Kai Zhang, Luc Van Gool, Radu Timofte
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
[Paper] [PyTorch Code] [BibTex]

 

Neural Blind Deconvolution Using Deep Priors

Dongwei Ren, Kai Zhang, Qilong Wang, Qinghua Hu, Wangmeng Zuo
IEEE International Conference on Computer Vision and Pattern Recognition(CVPR), 2020.
[Paper] [PyTorch Code] [BibTex]

 

NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results

Kai Zhang, Shuhang Gu, Radu Timofte, and others
IEEE International Conference on Computer Vision and Pattern Recognition Workshops(CVPRW), 2020.
[Paper] [BibTex]

 

AIM 2019 Challenge on Constrained Super-Resolution: Methods and Results

Kai Zhang, Shuhang Gu, Radu Timofte, and others
IEEE International Conference on Computer Vision Workshops (ICCVW), 2019.
[Paper] [PyTorch Code of Winner] [BibTex]

 

Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels

Kai Zhang, Wangmeng Zuo, Lei Zhang
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[Paper] [PyTorch Code] [BibTex]

 

Learning a Single Convolutional Super-Resolution Network for Multiple Degradations

Kai Zhang, Wangmeng Zuo, Lei Zhang
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
[Paper] [Matlab Code] [PyTorch Code] [BibTex] [Citations: 150+]

 

Learning Deep CNN Denoiser Prior for Image Restoration

Kai Zhang, Wangmeng Zuo, Shuhang Gu, Lei Zhang
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
[Paper] [Matlab Code] [BibTex] [Citations: 500+]

 

FFDNet: Toward a Fast and Flexible Solution for CNN-based Image Denoising

Kai Zhang, Wangmeng Zuo, Lei Zhang
IEEE Transactions on Image Processing (TIP), 27(9): 4608-4622, 2018.
[Paper] [Matlab Code] [PyTorch Code] [BibTex] [Citations: 300+]

 

Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

Kai Zhang, Wangmeng Zuo, Yunjin Chen, Deyu Meng, Lei Zhang
IEEE Transactions on Image Processing (TIP), 26(7): 3142-3155, 2017.
[Paper] [Matlab Code] [PyTorch Code] [BibTex] [Citations: 1700+]

 

End-to-End Blind Image Quality Assessment Using Deep Neural Networks

Kede Ma, Wentao Liu, Kai Zhang, Zhengfang Duanmu, Zhou Wang, Wangmeng Zuo
IEEE Transactions on Image Processing (TIP), 27(3): 1202-1213, 2017.
[Paper] [Project Page] [BibTex] [Citations: 90+]

 

Toward Convolutional Blind Denoising of Real Photographs

Shi Guo, Zifei Yan, Kai Zhang, Wangmeng Zuo, Lei Zhang
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[Paper] [Code] [BibTex] [Citations: 80+]

 

Convolutional Neural Networks for Image Denoising and Restoration (Book chapter)

Wangmeng Zuo, Kai Zhang, Lei Zhang
In: M. Bertalmio (eds.), Denoising of Photographic Images and Video: Fundamentals, Open Challenges and New Trends, Springer, 2018.
[Paper] [BibTex]

 

Joint Learning of Multiple Regressors for Single Image Super-Resolution

Kai Zhang, Baoquan Wang, Wangmeng Zuo, Hongzhi Zhang, Lei Zhang.
IEEE Signal Processing Letters (SPL), 23, (1): 102-106, 2016.
[Paper] [BibTex] [Citations: 30+]

 

Revisiting Single Image Super-Resolution Under Internet Environment: Blur Kernels and Reconstruction Algorithms

Kai Zhang, Xiaoyu Zhou, Hongzhi Zhang, Wangmeng Zuo.
Pacific Rim Conference on Multimedia (PCM), 2015: 677-687
[Paper] [BibTex]

Services

Workshop Organizers:

  • Co-organizer of ECCV 2020 Workshop on Advanced Image Manipulation (AIM).

  • Co-organizer of CVPR 2020 Workshop on New Trends in Image Restoration and Enhancement (NTIRE).

  • Co-organizer of ICCV 2019 Workshop on Advanced Image Manipulation (AIM).

Journal Reviewer:

  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  • International Journal of Computer Vision (IJCV)
  • IEEE Transactions on Image Processing (TIP)
  • IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
  • IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
  • Computer Vision and Image Understanding (CVIU)
  • Signal Processing Letters (SPL)

Conference Reviewer:

  • IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • International Conference on Computer Vision (ICCV)
  • European Conference on Computer Vision (ECCV)
  • AAAI Conference on Artificial Intelligence (AAAI)
  • International Joint Conferences on Artificial Intelligence (IJCAI)

Awards

  • First Prize of Natural Science Award of Heilongjiang Province, 2020
  • Outstanding student paper award of HIT, 2018
  • Fourth place of NTIRE 2018 challenge on single image super-resolution, 2018
  • National scholarship for doctoral students, 2017
  • Outstanding student paper award of HIT, 2017
  • First prize of GUANGXI International Academic Forum, 2017
  • Best poster award of Valse2017, 2017

Collaborators