# Hierarchical Space Partition for Surface Reconstruction

arXiv: https://arxiv.org/abs/2606.04891 · HTML: https://mlsanity.com/paper/2606.04891/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 42 references that are in the map.
- First posted on arXiv 3 Jun 2026.

## Builds on (most cited first, 8 of 8)

- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [JoinABLe: Learning Bottom-up Assembly of Parametric CAD Joints](https://mlsanity.com/paper/2111.12772/) (2021)
- [Reconstructing Compact Building Models from Point Clouds Using Deep Implicit Fields](https://mlsanity.com/paper/2112.13142/) (2021)
- [Surface Reconstruction from 3D Line Segments](https://mlsanity.com/paper/1911.00451/) (2019)
- [Concise Plane Arrangements for Low-Poly Surface and Volume Modelling](https://mlsanity.com/paper/2404.06154/) (2024)
- [WindPoly: Polygonal Mesh Reconstruction via Winding Numbers](https://mlsanity.com/paper/2407.19208/) (2024)
- [Building LOD Representation for 3D Urban Scenes](https://mlsanity.com/paper/2505.15190/) (2025)

## Abstract (arXiv)

Generating compact polygonal models from point clouds is a key problem in 3D vision and computer graphics. However, due to inherent limitations of LiDAR scanning (e.g. range constraints and occlusions), critical scene information is often missing, leading to degraded reconstruction accuracy. To address this, we propose a plane assembling strategy that effectively recovers missing details while maintaining model compactness. We classify all the planes extracted from the scene into three categories: highly visible, barely visible, and invisible. The invisible planes, which are recovered by scene structure analysis, indicate the missing details. The three types of planes correspond to the three growth priorities. Each plane grows according to the priority level, and the space is partitioned progressively, namely, the hierarchical partition. Subsequently, we generate a watertight polygonal mesh from the partition via a min-cut-based optimization. Finally, comparisons on public datasets show the effectiveness and superiority of our method against mainstream approaches. The project page is available at https://hsr-3dv.github.io/.