👋 About Me
I am currently a Research Fellow at the MIT Media Lab and Harvard Medical School, working with Prof. Paul Liang, Prof. Mengyu Wang, and Prof. Fadel Adib. Previously, I earned my Ph.D. in Computer Science at the University of Oxford under the supervision of Prof. Niki Trigoni and Prof. Andrew Markham, and graduated with First Class Honours (Top 10%) from the Department of Computing at Imperial College London, where I worked with Prof. Yike Guo.
🔍 Research Directions
Understanding Dynamic 3D Worlds: Developing models that can accurately see and understand changing real-world environments — including geometry, motion, and object interactions — in real time.
Building Intelligent Robots That Can Act: Creating robots that use perception to guide their actions, correct mistakes, handle occlusions or disturbances, and collaborate smoothly with humans.
Predictive World Models: Designing systems that can imagine future events, predict how scenes will change, and reason about human intentions — enabling safer, more reliable, long-horizon decision making.
🏆 Award
ACM MobiSys 2025 — Around 2.5% – Best Paper Nominee. [Link]
IROS 2024 — Around 0.1% – Finalist for Best Application Paper Award. [Link]
IROS 2024 — Excellent Practice Award at EDM Workshop. [Link]
Smartathon 2023 — 2nd place out of ~5000 participants.
AWS Lighthouse Scholarship 2020 — Fully funded for Oxford DPhil Program.
🧑🎓 Students
Advaith Ravishankar (Harvard)
Yuzhen Chen (Harvard)
Gaspard Beaudouin (Harvard)
Weihan Xu (Incoming UCB)
Yuhan Wang (Imperial College)
Jiadong Zhang (CMU)
Xinhai Chang (PKU)
📖 Publication
 | PAGE-4D: Disentangled Pose and Geometry Estimation for VGGT-4D Perception Kaichen Zhou, Yuhan Wang, Grace Chen, Xinhai Chang, Gaspard Beaudouin, Fangneng Zhan, Paul Pu Liang, Mengyu Wang arXiv 2025 Paper · Webpage |
 | RISE: Single Static Radar-based Indoor Scene Understanding Kaichen Zhou, Laura Dodds, Sayed Saad Afzal, Fadel Adib arXiv 2025 Paper |
 | Non-Line-of-Sight 3D Object Reconstruction via mmWave Surface Normal Estimation Laura Dodds, Tara Boroushaki, Kaichen Zhou, Fadel Adib ACM MobiSys 2025 – Best Paper Nominee Paper · Code · Webpage |
 | SCANet: Correcting LEGO Assembly Errors with Self-Correct Assembly Network Yuxuan Wan, Kaichen Zhou (Co-First), jinhong Chen, Hao Dong IROS 2024 – Finalist for Best Application Paper Award Paper · Code · Webpage |
 | Spherical Mask: Coarse-to-Fine 3D Point Cloud Instance Segmentation with Spherical Representation Sangyun Shin, Kaichen Zhou (Co-First), Madhu Vankadari, Andrew Markham, Niki Trigoni CVPR 2024 Paper · Code |
 | Manydepth2: Motion-Aware Self-Supervised Monocular Depth Estimation in Dynamic Scenes Kaichen Zhou, Jia-Wang Bian, Jian-Qing Zheng, Qian Xie, Niki Trigoni, Andrew Markham RAL 2024 Paper · Code |
 | DynPoint: Dynamic Neural Point For View Synthesis Kaichen Zhou, Jia-Xing Zhong, Sangyun Shin, Kai Lu, Yiyuan Yang, Andrew Markham, Niki Trigoni Neurips 2023 Paper · Code |
 | DevNet: Self-supervised Monocular Depth Learning via Density Volume Construction Kaichen Zhou, Lanqing Hong, Changhao Chen, Hang Xu, Chaoqiang Ye, Qingyong Hu, Zhenguo Li ECCV 2022 Paper · Code |
 | DHA: End-to-End Joint Optimization of Data Augmentation Policy, Hyper-parameter and Architecture Kaichen Zhou, Lanqing Hong, Shoukang Hu, Fengwei Zhou, Binxin Ru, Jiashi Feng, Zhenguo Li TMLR 2022 Paper |