Kun Zhou 周昆

Ph.D.

Dept. of Computer and Information Engineering
The Chinese University of Hong Kong(Shenzhen)
Shenzhen, Guangdong, China

Email-1: zhoukun AT gmail DOT com
Email-1: kunzhou AT link DOT cuhk DOT edu DOT cn

  


Biography

I obtained my Ph.D. in the Department of SSE, the Chinese University of Hong Kong(Shenzhen), under the supervision of Prof. Xiaoguang Han and Prof. Jiangbo Lu. My research interests lie primarily in computer vision and machine learning. I have done some works about 3d human pose and shape estimation, super-resolution, inpainting, video restoration and frame interpolation.

CV

News

Selected Publications [Google Scholar]

T-PAMI(2), CVPR(4), NeurIPS(2), ICCV(1), ECCV(1), AAAI(1), ICLR(1).

UPS: Unified Projection Sharing for Lightweight Single-Image Super-resolution and Beyond
Kun Zhou,Xinyu Lin, Zhonghang Liu, Xiaoguang Han, Jiangbo Lu
Conference on Neural Information Processing Systems (NeurIPS) 2024
Unveiling Advanced Frequency Disentanglement Paradigm for Low-Light Image Enhancement
Kun Zhou,Xinyu Lin, Wenbo Li, Xiaogang Xu, Yuanhao Cai, Zhonghang Liu, Xiaoguang Han, Jiangbo Lu
Proceedings of the European Conference on Computer Vision (ECCV) 2024
[paper|code]
Enhancing any LLIE frameworks and significantly (up to +7dB) with only extra 88K parameters.
From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer Paradigm
Kun Zhou, Wenbo Li, Nianjuan Jiang, Xiaoguang Han, Jiangbo Lu
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2023

Restoring HQ 4K novel views from any NeRF or even GS models.
[project|paper|Video Demo]
NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer
Kun Zhou*, Wenbo Li*, Yi Wang, Tao Hu, Nianjuan Jiang, Xiaoguang Han, Jiangbo Lu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023

The first general NeRF enhancer.
[project|paper|Slides|code]GitHub stars
Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolation
Kun Zhou , Wenbo Li, Xiaoguang Han, Jiangbo Lu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023
[paper]
Revisiting Temporal Alignment for Video Restoration
Kun Zhou*, Wenbo Li*, Liying Lu, Xiaoguang Han, Jiangbo Lu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022
[paper|code] GitHub stars
HEMlets posh: learning part-centric heatmap triplets for 3D human pose and shape estimation
Kun Zhou, Xiaoguang Han, Nianjuan Jiang, Kui Jia, Jiangbo Lu
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2021
[paper]
Hemlets pose: Learning part-centric heatmap triplets for accurate 3d human pose estimation
Kun Zhou, Xiaoguang Han, Nianjuan Jiang, Kui Jia, Jiangbo Lu
International Conference on Computer Vision (ICCV) 2019
[project|paper|code] GitHub stars
Best-Buddy GANs for Highly Detailed Image Super-Resolution
Wenbo Li*, Kun Zhou*, Lu Qi, Liying Lu, Jiangbo Lu, Jiaya Jia
Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI) 2022 (Oral)
[paper|code] GitHub stars
LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-resolution and Beyond
Wenbo Li*, Kun Zhou*, Lu Qi, Nianjuan Jiang, Jiangbo Lu, Jiaya Jia
Advances in Neural Information Processing Systems (NeurIPS) 2020
[paper|code] GitHub stars
Image Inpainting via Iteratively Decoupled Probabilistic Modeling
Wenbo Li, Xin Yu, Kun Zhou , Yibing Song, Zhe Lin, Jiaya Jia
arXiv:2212.02963
[paper|code] GitHub stars
MAT: Mask-Aware Transformer for Large Hole Image Inpainting
Wenbo Li, Zhe Lin, Kun Zhou, Lu Qi, Yi Wang, Jiaya Jia
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022 (Best Paper Finalists, Oral)
[paper|code|Media Report|Slides|Poster] GitHub stars
Mutual Guidance and Residual Integration for Image Enhancement
Kun Zhou, Wenbo Li, Xiaoguang Han, Jiangbo Lu
arXiv:2211.13919
[paper]
Adversarial 3d human pose estimation via multimodal depth supervision
Kun Zhou, Jinmiao Cai, Yao Li, Yulong Shi, Xiaoguang Han, Nianjuan Jiang, Kui Jia, Jiangbo Lu
Ranked fourth in the ECCV2018 PoseTrack Challenge.
[paper]
Fbi-pose: Towards bridging the gap between 2d images and 3d human poses using forward-or-backward information
Yulong Shi, Xiaoguang Han, Nianjuan Jiang, Kun Zhou , Kui Jia, Jiangbo Lu
In 2018, Fbi-pose achieved the top ranking on the Human3.6M Benchmark (H36M_NOS10).
[paper]
Real-time collision detection method for fluid and cloth
Hui Zang,Zhen Liu, Yanjie Chai,Tingting Liu, Kun Zhou
Journal of Computer Aided Design and Graphics 2018
[paper]

Talk

Academic Service


© Kun Zhou | Last updated: June. 2023