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