Educational Background：

• 08/2006 –12/2008   The Chinese University of Hong Kong, Hong Kong
  Doctor of Philosophy in Computer Science, December 2008
  Supervisor: Prof. Michael R. Lyu
• 09/2002 – 03/2005   University of Macau, Macau
  Master of Science in Electrical and Electronics Engineering, March 2005
  Supervisor: Prof. Mang I Vai and Prof. Peng Un Mak.

Work Experience：

• 01/2019- present     Professor, College of Computer Science, Zhejiang University, China
• 12/2011- 12/2018    Associate Professor, College of Computer Science, Zhejiang University, China
• 09/2010- 12/2011    Assistant Professor, College of Computer Science, Zhejiang University, China
• 01/2010- 08/2010    Postdoc, Computer Science and Engineering Department,The Chinese University of Hong Kong   Supervised by Prof. Michael R. Lyu
• 01/2009-01/2010    Postdoc, Computer Vision Laboratory,Information Technology and Electrical Engineering, ETH Zurich, Switzerland Supervised by Prof. Luc Van Gool

Jianke Zhu is a Professor in College of Computer Science at Zhejiang University. He received his Ph.D degree in Computer Science and Engineering from The Chinese University of Hong Kong. He was a postdoc in BIWI Computer Vision Lab at ETH Zurich. Dr. Zhu's research interests include computer vision and machine learning. He is a senior member of the IEEE.

[1]    Wentong Li, Yuqian Yuan, Jian liu, Dongqi Tang, Song Wang, Jie Qin, Jianke Zhu*, Lei Zhang, “TokenPacker: Efficient Visual Projector for Multimodal LLM”, International Journal of Computer Vision (IJCV), 2025.

[2]    Yisu Zhang, Jianke Zhu*, and Lixiang Lin, “FastMESH: Fast Surface Reconstruction by Hexagonal Mesh-based Neural Rendering”, Comput. Vis. Image Underst., 2025.

[3]    Zhuopeng Li, Chunming Wu, Liangjun Zhang, and Jianke Zhu*, “DGNR: Density-Guided Neural Point Rendering of Large Driving Scenes”, IEEE Trans. on Automation Science and Engineering, 2025.

[4]    Hanxun Yu, Wentong Li, Song Wang, Junbo Chen, Jianke Zhu*, “Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning”, CVPR2025.

[5]    Qijun Gan, Song Wang, Shengtao Wu, Jianke Zhu*, “PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance”, ICLR 2025.

[6]    Wentong Li, Wenyu Liu, Jianke Zhu*, Miaomiao Cui, Risheng Yu, Lei Zhang, and Xiansheng Hua, “Box2Mask: Instance Segmentation by Level Set Evolution”, IEEE Trans. on Pattern Analysis and Machine Intelligences (T-PAMI), 2024.

[7]    Xin Zheng and Jianke Zhu*, “Traj-LO: In Defense of LiDAR-Only Odometry Using an Effective Continuous-Time Trajectory", IEEE Robotics and Automation Letters (RA-L), 2024.

[8]    Yuqian Yuan, Wentong Li, Jian liu, Dongqi Tang, Xinjie Luo, Chi Qin, Lei Zhang, and Jianke Zhu*, “Osprey: Pixel Understanding with Visual Instruction Tuning”, CVPR2024.

[9]    Zhuopeng Li, Yilin Zhang, Chunming Wu, Jianke Zhu*, and Liangjun Zhang, “HO-Gaussian: Hybrid Optimization of 3D Gaussian Splatting for Urban Scenes”, ECCV2024.

[10]    Lixiang Lin, Yisu Zhang, and Jianke Zhu*, “Efficient Textured Mesh Recovery from Multiple Views with Differentiable Rendering,” IEEE Trans. Circuits Syst. Video Techn., 2023.

[11]    Wenyu Liu, Gaofeng Ren, Runsheng Yu, Shi Guo, Jianke Zhu*, Lei Zhang, “Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions”, AAAI2022.

[12]    Wentong Li, Yijie Chen, Kaixuan Hu and Jianke Zhu*, “Oriented RepPoints for Aerial Object Detection,”, CVPR2022.

[13]    Xinrui Zhan, Yang Li, Yueran Liu, and Jianke Zhu*, “Homography Decomposition Networks for Planar Object Tracking”, AAAI2022.

[14]    Yang Li, Jianke Zhu*, Steven Hoi, Wenjie Song, Zhefeng Wang and Hantang Liu, “Robust Estimation of Similarity Transformation for Visual Object Tracking”, AAAI 2019: 8666-8673.

[15]    Jianke Zhu, “Image Gradient-based Joint Direct Visual Odometry for Stereo Camera,” IJCAI 2017.  

[16]    Hantang Liu, Jialiang Zhang, Jianke Zhu*, Steven C. H. Hoi, “DeepFacade: A Deep Learning Approach to Facade Parsing,” IJCAI 2017. 

[17]    Yang Li and Jianke Zhu, “A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration”, ECCV 2014 Workshop: VOT’14 Challenge.

[18]    Jianke Zhu, Michael R. Lyu and Thomas S. Huang, "A Fast 2D Shape Recovery Approach by Fusing Features and Appearance," IEEE Trans. on Pattern Analysis and Machine Intelligences (T-PAMI), vol. 31, July 2009, pp.1210-1224.

[19]    Jianke Zhu, Luc Van Gool and Steven C.H. Hoi, “Unsupervised Face Alignment by Robust Nonrigid Mapping,” IEEE International Conference on Computer Vision (ICCV2009).

[20]    Jianke Zhu and Michael R. Lyu, "Progressive Finite Newton Approach to Real-time Nonrigid Surface Detection," IEEE Conference on Computer Vision and Pattern Recognition (CVPR2007), June 19-21, 2007. 

Patent

 [1] Method for object size and rotation estimation based on log-polar space, PCT-US Patent,PCT/CN2017/118845, US 10,818,032 

[2] Stereo visual odometry method based on image gradient joint optimization, PCT-US Patent,PCT/CN2017/118849, US 10,762,645 

[3]一种基于对数极空间的图像物体大小和旋转估计计算方法, 授权专利, 编号 ZL201710685725.2 

[4]用编码向量的行人图像检测自适应非极大值抑制处理方法, 公开专利, 编号 CN201910936327.2 

[5]一种基于图像梯度联合优化的双目视觉历程计算方法, 授权专利, 编号 ZL201710685724.8