Qi Zhang 张琦 iMUSE Lab · SZU

iMUSE Lab

intelligent MUlti-Sensing lab — where “MUSE” also means inspiration.

iMUSE Lab is a computer vision research group at Shenzhen University working on multi-view crowd intelligence, robust 3D scene understanding, and camera-only 4D occupancy forecasting.

The lab has 4 Ph.D. and 9 master’s students. The 7 who have graduated went to Ph.D. programs (Shenzhen University, NJUPT) or to Huawei, Bilibili, Qihoo 360 and Alibaba’s Linxi Games.

iMUSE Lab group photo, 2025

Group photo, 2025.

Principal Investigator

Qi Zhang
Qi Zhang 张琦

Associate Professor (Tenured) and doctoral supervisor, Shenzhen University. Founder and principal investigator of iMUSE Lab. Research: multi-view crowd intelligence, robust 3D scene understanding, and dynamic-scene modelling.

Full profile CV

Research by group members

All 27 papers →

Six papers across the lab’s directions with group members as first author or key contributor; bold marks the group members.

Figure from Multi-view Crowd Tracking Transformer with View-Ground Interactions Under Large Real-World Scenes
Qi Zhang, Jixuan Chen, Kaiyi Zhang, Xinquan Yu, Antoni B. Chan and Hui Huang
CVPR 2026pp. 13626-13635PDFarXivCode
Figure from SynMVCrowd: A Large Synthetic Benchmark for Multi-view Crowd Counting and Localization
Qi Zhang, Daijie Chen, Yunfei Gong and Hui Huang*
IJCV 2026134(4): 1912 citationsarXivPublisherCode
Figure from WSCF-MVCC: Weakly-supervised Calibration-free Multi-view Crowd Counting
Bin Li, Daijie Chen and Qi Zhang*
PRCV 2025pp. 83-98LNCS 162871 citationsarXivPublisherCode
Figure from Mahalanobis Distance-based Multi-view Optimal Transport for Multi-view Crowd Localization
Qi Zhang, Kaiyi Zhang, Antoni B. Chan and Hui Huang*
ECCV 202415 citationsPDFarXivProject

Ph.D. Students

Zhenpeng Li
Zhenpeng Li
Point Cloud Processing
since 2022.09 · joint supervision with Prof. Hui Huang
Ruiji Xue
Ruiji Xue
Computer Vision
since 2026.09

Master’s Students

Bingxue Zhao
Bingxue Zhao
Crowd Simulation
since 2024.09
Jixuan Chen
Jixuan Chen
Computer Vision
since 2024.09
Weiyuan Zhang
Weiyuan Zhang
Point Cloud Processing
since 2024.09
Xinquan Yu
Xinquan Yu
3D Vision
since 2024.09
Yanyifan Wang
Yanyifan Wang
3D Vision
since 2024.09
Zhizi Wang
Zhizi Wang
3D Vision
since 2025.09
Jiechao He
Jiechao He
3D Vision
since 2025.09
Songjun Mai
Songjun Mai
3D Vision
since 2025.09
Pingqing Hou
Pingqing Hou
Computer Vision
since 2026.09

Alumni

NameDegreeNext
Yunfei Gong M.Eng. 2022.04-2024.06 Ph.D. at Shenzhen University
Zhidan Xie M.Eng. 2022.04-2024.06 Qihoo 360
Daijie Chen M.Eng. 2022.09-2025.06 Linxi Games (Alibaba)
Kaiyi Zhang M.Eng. 2022.09-2025.06 Ph.D. at Shenzhen University
Zhouhang Luo M.Eng. 2022.09-2025.06 Huawei
Bin Li M.Eng. 2023.09-2026.06 Ph.D. at NJUPT
Tao Yu M.Eng. 2023.09-2026.06 Bilibili

Join iMUSE

We take Ph.D. and master’s students every year. Prospective students normally join one of three efforts: crowd simulation and generation, multi-view 3D reconstruction, or 4D occupancy forecasting from cameras only. We also host motivated undergraduates on research or competition projects — computer vision, embedded AI and mobile application work — with the opportunity to develop that work toward a publication when it is ready. Undergraduates working with us have won provincial competition prizes and had graduation projects selected among the university’s outstanding undergraduate theses.

Ph.D. intake. The 2026 quota is full. Enquiries for 2027 are welcome now; pre-admission follows the college’s own schedule, and university and college scholarships are available. Write to qizhang@szu.edu.cn, my institutional address and the one the college’s admissions office recognises.

What matters to us: you can read a paper and reproduce part of it, you are comfortable with PyTorch and geometry, and you are willing to build reproducible research and release code or data when appropriate. If that describes you, write to qi.zhang.opt@gmail.com with a transcript, one project you are proud of, and which of the three above you want to work on.

Write to me Research agenda

Past calls: 2024 (PDF) · 2023 (PDF). The earlier version of this page was built with the help of my wife. Thank you.