Welcome to Lei Han's Homepage!

Make sense Make difference

Contact me: lhanaf at connect.ust.hk

I studied Electrical Engineering at the Hong Kong University of Science and Technology (China) and Tsinghua University (China). I received my B.S. degree in July 2013 and joined the Department of Electrical Computing Engineering at the Hong Kong University of Science and Technology in September 2016, where I'm pursuing the PhD degree.

My research interest lies in Multi-view Geometry and 3D computer vision.


Education/Experiences

  • 2016. 9 - Present PhD candidate in Robotics, ECE Department, Hong Kong University of Science and Technology.
  • 2018. 7 - 2018,.12 Visiting Ph.D. student, Technical University of Munich
  • 2014. 12 - 2016. 7 Algorithm engineer, DJI Technology
  • 2009. 9 - 2013. 7 B.Eng, Department of Electronic Engineering, Tsinghua University


Research Projects

FlashFusion: Real-time Globally Consistent Dense 3D Reconstruction using CPU computing (2018 RSS)

OccuSeg: Live Geometric & Semantic 3D Perception (2020 CVPR)

    • First place on Scannet Semantic/Instance segmentation benchmark.

Collaborative Building-scale Dense 3D Perception (2020)

Publications

  • Lei Han, Lu Fang. MILD: Multi-Index Hashing for Loop Closure Detection, Multimedia and Expo (ICME), 2017 IEEE International Conference on. IEEE, 2017. Best Student Paper Award. [Paper, Code]
  • Lei Han, Guyue Zhou, Lan Xu, Lu Fang. Beyond SIFT using binary features in Loop Closure Detection, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems. (IROS 2017), [Paper, Code]
  • Lei Han, Lu Fang. FlashFusion: Real-time Globally Consistent Dense 3D Reconstruction using CPU computing. Robotics: Science and Systems (RSS), 2018. [Paper, Video, Project]
  • Lei Han, Lan XU, Dmytro Bobkov, Eckehard Steinbach, Lu Fang. Fast Global Registration for Globally Consistent SLAM, IEEE Transactions on Robotics (TRO), 2018, accepted. [Paper]
  • Lei Han*, Dawei Zhong*, Lu Fang. iDFusion: Globally Consistent Dense 3D Reconstruction from RGB-D and Inertial Measurements. ACMMM, 2019.
  • Lei Han, Tian Zheng, Yinheng, Zhu, Lan Xu, Lu Fang. Realtime Semantic 3D Perception for Immersive Augmented Reality. Conditionally accepted by TVCG/IEEE VR, 2020.
  • Lei Han, Tian Zheng, Lan Xu, Lu Fang. OccuSeg: Occupancy Aware 3D Instance Segmentation. CVPR 2020. First place on Scannet Semantic Segmentation Benchmark & Instance Segmentation Benchmark.
  • Haitian Zheng, Mengqi Ji, Lei Han, Ziwei Xu, Haoqian Wang, Yebin Liu, Lu Fang. Learning Cross-scale Correspondence and Patch-based Synthesis for Reference-based Super-Resolution. BMVC, 2017.
  • Lan Xu, Zhuo Su, Lei Han, Tao Yu, Yebin Liu, Lu Fang. UnstructuredFusion: Realtime 4D Geometry and Texture Reconstruction using Commercial RGBD Cameras, , IEEE TPAMI 2019.
  • Lan Xu, Wei Cheng, Kaiwen Guo, Lei Han, Yebin Liu and Lu Fang. FlyFusion: Realtime Dynamic Scene Reconstruction Using a single Flying Depth Camera, Transactions on Visualization and Computer Graphics (TVCG), 2019.
  • Wei Cheng, Lan Xu, Lei Han, Yebin Liu and Lu Fang. iHuman3D: Intelligent Human Body 3D Reconstruction using a Single Flying Camera, ACMMM 2018, oral.