Huan LEI

I received my Doctorate from the University of Western Australia where I was advised by Ajmal Mian and Naveed Akhtar. My PhD was supported by the RTP scholarship of Australian Government. After graduation, I worked as a Research Fellow at the Australian National University and later at AIML, the University of Adelaide.

Email  /  Google Scholar  /  Twitter  /  Github /  CV  /  Slow Science

profile photo

seek wisdom & take the blame

Research Interests

My research focuses on 3D vision, including deep learning for 3D perception from point clouds and meshes, surface reconstruction, efficient surface representations, and 3D generation. I am also interested in self-supervised learning
and multimodal learning for 3D applications.

Publications
prl Level-Set Parameters: Novel Representation for 3D Shape Analysis
Huan Lei, Hongdong Li, Andreas Geiger, Anthony Dick.
Tech Report, 2024.

This tech report explored continuous surface representations beyond the discrete geometric data formats, using the neural parametters of SDF functions, and applied them for 3D shape analysis including classfication, retrieval, and registration.

prl OffsetOPT: Explicit Surface Reconstruction without Normals
Huan Lei.
CVPR 2025. Project/Bibtex

OffsetOPT reconstructs explicit surfaces from 3D point clouds without requiring normals. It generalizes the trained model to unseen data via unsupervised per-point offset optimization, achieving detail-preserving surfaces with strong scalability.

prl Mesh Convolution with Continuous Filters for 3D Surface Parsing
Huan Lei, Naveed Akhtar, Mubarak Shah, Ajmal Mian.
TNNLS, 2023. Project/Code/Bibtex

Picasso and PicassoNet++ for deep learning over heterogeneous 3D meshes. We formulate the continuous filters for mesh convolution using spherical harmonics as orthonormal basis.

prl CircNet: Meshing 3D Point Clouds with Circumcenter Detection
Huan Lei, Ruitao Leng, Liang Zheng, Hongdong Li.
ICLR, 2023. Project/Code/Bibtex

By exploiting the duality between a triangle and its circumcenter, we propose to triangulates 3D point clouds into manifold meshes using a graph neural network, named CircNet. The network detects circumcenters and recovers vertex triplets of each triangle face, reconstructing a primitive mesh. Standard post-processing is then applied to convert the primitive mesh into a manifold surface.

prl Picasso: A CUDA-based Library for Deep Learning over 3D Meshes
Huan Lei, Naveed Akhtar, Ajmal Mian.
CVPR 2021. Project/Code/Bibtex

The preliminary Picasso for geometric deep learning over 3D meshes. Please refer to our TNNLS2023 work for the latest Pytorch codes.

prl SegGCN: Efficient 3D Point Cloud Segmentation with Fuzzy Spherical Kernel
Huan LEI, Naveed Akhtar, Ajmal Mian.
CVPR 2020. Code/Bibtex

Fuzzy modelling makes convolutions robust to varying densities of point clouds.

prl Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds
Huan Lei, Naveed Akhtar, Ajmal Mian.
TPAMI, Mar 2020. Code/Bibtex
prl Octree guided CNN with Spherical Kernels for 3D Point Clouds
Huan Lei, Naveed Akhtar, Ajmal Mian.
CVPR 2019. Bibtex
prl Geometric Deep Learning for 3D Data
Huan Lei. PhD Thesis, Nov 2021.

Professional service

Reviewer for CVPR, TPAMI, TNNLS, TIP.


Created using the source code from Jon Barron's website