18 Papers
46 Citations
Lei Han is an academic researcher from Hong Kong University of Science and Technology. The author has contributed to research in topics: Computer science & 3D reconstruction. The author has an hindex of 8, co-authored 18 publications. Previous affiliations of Lei Han include Tsinghua University.
Chat about Author
Papers
OccuSeg: Occupancy-Aware 3D Instance Segmentation
Lei Han,Tian Zheng,Lan Xu,Lu Fang +3 more
- 14 Jun 2020
TL;DR: In this article, an occupancy-aware 3D instance segmentation scheme is proposed, where multi-task learning produces both occupancy signal and embedding representations, where the training of spatial and feature embeddings varies with their difference in scale-aware.
UnstructuredFusion: Realtime 4D Geometry and Texture Reconstruction Using Commercial RGBD Cameras
TL;DR: The proposed UnstructuredFusion achieves high-quality 4D geometry and texture reconstruction without tiresome pre-calibration, liberating the cumbersome hardware and software restrictions in conventional structured multi-camera system, while eliminating the inherent occlusion issues of the single camera setup.
98
Live Semantic 3D Perception for Immersive Augmented Reality
TL;DR: A chunk-based sparse convolution scheme is proposed to reuse the neighboring points within each spatially organized chunk, and an efficient multi-layer adaptive fusion module is further proposed for employing the spatial consistency cue of 3D data to further reduce the computational burden.
71
FlyFusion: Realtime Dynamic Scene Reconstruction Using a Flying Depth Camera
TL;DR: FlyFusion is proposed through a real-time and robust dynamic fusion scheme using a single flying depth camera, denoted as FlyFusion, to enable intelligent viewpoint selection based on the immediate dynamic reconstruction result.
56
Real-Time Global Registration for Globally Consistent RGB-D SLAM
TL;DR: Experiments show that the proposed algorithm achieves globally consistent pose estimation in real-time via CPU computing, and owns comparable accuracy as state-of-the-art that use GPU computing, enabling the practical usage of globally consistent RGB-D SLAM on highly computationally constrained devices.
50