Deep Learning for Point Clouds

Geometric deep learning with anisotropic operators on unstructured 3D data — bridging exterior calculus with practical point-cloud networks.

Point clouds from LiDAR, depth cameras, and reconstruction pipelines are inherently unordered and irregular. Standard convolutions assume a grid; geometric deep learning must instead define derivatives and neighbourhoods that respect surface and spatial structure.

In collaboration with colleagues at TU Delft, I contributed to DeltaConv, which introduces anisotropic operators inspired by discrete exterior calculus so that learned filters can align with local geometry rather than treating all directions equally. The line of work spans an arXiv preprint, the ACM TOG journal version, and open-source implementations for reproducibility.

Anisotropic operators & CNN architectures for point clouds

We design convolution-like layers whose stencils adapt to estimated tangent and normal structure, improving feature extraction for segmentation, classification, and scene understanding. The goal is to make 3D networks more data-efficient and faithful to curvature while remaining compatible with modern training stacks.

Related publications

3D mapping, recognition, and applications

Better point-cloud networks support autonomous systems, digital twins, and robotics. While my published focus is on the operator design itself, the motivation includes robust object recognition and real-time understanding of large scans where anisotropy and scale vary across the scene.

Related publications

Publications

All papers in this area

DeltaConv line of work; newest first.

2022

DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds

Wiersma, R., Nasikun, A., Eisemann, E., & Hildebrandt, K.

ACM Transactions on Graphics (TOG), 41(4), pp. 1–10 · ACM

2022

DeltaConv: Anisotropic Geometric Deep Learning with Exterior Calculus

Wiersma, R., NASIKUN, A., Eisemann, E., & Hildebrandt, K.

Additional Scholar listing (related to DeltaConv / TOG 2022), 2022

2021

DeltaConv: Anisotropic Point Cloud Learning with Exterior Calculus

Wiersma, R., Nasikun, A., Eisemann, E., & Hildebrandt, K.

arXiv preprint arXiv:2111.08799, 2021

← Full publication list on homepage