# HPNet: Deep Primitive Segmentation Using Hybrid Representations

arXiv: https://arxiv.org/abs/2105.10620 · HTML: https://mlsanity.com/paper/2105.10620/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 40 references that are in the map.
- First posted on arXiv 22 May 2021.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation](https://mlsanity.com/paper/1812.11788/) (2018)
- [ABC: A Big CAD Model Dataset For Geometric Deep Learning](https://mlsanity.com/paper/1812.06216/) (2018)
- [Learning Shape Abstractions by Assembling Volumetric Primitives](https://mlsanity.com/paper/1612.00404/) (2016)
- [H3DNet: 3D Object Detection Using Hybrid Geometric Primitives](https://mlsanity.com/paper/2006.05682/) (2020)
- [Semantic Instance Segmentation with a Discriminative Loss Function](https://mlsanity.com/paper/1708.02551/) (2017)
- [HybridPose: 6D Object Pose Estimation under Hybrid Representations](https://mlsanity.com/paper/2001.01869/) (2020)
- [CSGNet: Neural Shape Parser for Constructive Solid Geometry](https://mlsanity.com/paper/1712.08290/) (2017)
- [ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds](https://mlsanity.com/paper/2003.12181/) (2020)
- [Supervised Fitting of Geometric Primitives to 3D Point Clouds](https://mlsanity.com/paper/1811.08988/) (2018)
- [3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks](https://mlsanity.com/paper/1708.01648/) (2017)
- [Deep Generative Modeling for Scene Synthesis via Hybrid Representations](https://mlsanity.com/paper/1808.02084/) (2018)
- [Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding](https://mlsanity.com/paper/1902.09777/) (2019)
- [Extreme Relative Pose Network under Hybrid Representations](https://mlsanity.com/paper/1912.11695/) (2019)
- [Coupling Explicit and Implicit Surface Representations for Generative 3D Modeling](https://mlsanity.com/paper/2007.10294/) (2020)
- [Path-Invariant Map Networks](https://mlsanity.com/paper/1812.11647/) (2018)

## Built on by (most cited first, 30 of 36)

- [CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention](https://mlsanity.com/paper/2402.17678/) (2024)
- [Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning](https://mlsanity.com/paper/2201.00785/) (2022)
- [SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operations](https://mlsanity.com/paper/2303.10613/) (2023)
- [Reconstructing editable prismatic CAD from rounded voxel models](https://mlsanity.com/paper/2209.01161/) (2022)
- [Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds](https://mlsanity.com/paper/2312.04962/) (2023)
- [Point Primitive Transformer for Long-Term 4D Point Cloud Video Understanding](https://mlsanity.com/paper/2208.00281/) (2022)
- [ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modeling](https://mlsanity.com/paper/2402.06118/) (2024)
- [HoLa: B-Rep Generation using a Holistic Latent Representation](https://mlsanity.com/paper/2504.14257/) (2025)
- [Split-and-Fit: Learning B-Reps via Structure-Aware Voronoi Partitioning](https://mlsanity.com/paper/2406.05261/) (2024)
- [ComplexGen: CAD Reconstruction by B-Rep Chain Complex Generation](https://mlsanity.com/paper/2205.14573/) (2022)
- [3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining](https://mlsanity.com/paper/2304.06911/) (2023)
- [AutoGPart: Intermediate Supervision Search for Generalizable 3D Part Segmentation](https://mlsanity.com/paper/2203.06558/) (2022)
- [PlanarNeRF: Online Learning of Planar Primitives with Neural Radiance Fields](https://mlsanity.com/paper/2401.00871/) (2023)
- [Recognising geometric primitives in 3D point clouds of mechanical CAD objects](https://mlsanity.com/paper/2301.04371/) (2023)
- [A Review of Deep Learning-Powered Mesh Reconstruction Methods](https://mlsanity.com/paper/2303.02879/) (2023)
- [A Survey of Methods for Converting Unstructured Data to CSG Models](https://mlsanity.com/paper/2305.01220/) (2023)
- [Multi-View Representation is What You Need for Point-Cloud Pre-Training](https://mlsanity.com/paper/2306.02558/) (2023)
- [A boundary-aware point clustering approach in Euclidean and embedding spaces for roof plane segmentation](https://mlsanity.com/paper/2309.03722/) (2023)
- [QuadricsNet: Learning Concise Representation for Geometric Primitives in Point Clouds](https://mlsanity.com/paper/2309.14211/) (2023)
- [DualBrep: A Dual-Field Continuous Representation for B-rep Modelling](https://mlsanity.com/paper/2606.31579/) (2026)
- [Autoregressive B-Rep Shape Generation with Parametric Surfaces](https://mlsanity.com/paper/2607.17093/) (2026)
- [BPNet: B'ezier Primitive Segmentation on 3D Point Clouds](https://mlsanity.com/paper/2307.04013/) (2023)
- [3D detection of roof sections from a single satellite image and application to LOD2-building reconstruction](https://mlsanity.com/paper/2307.05409/) (2023)
- [Constraint-Aware Feature Learning for Parametric Point Cloud](https://mlsanity.com/paper/2411.07747/) (2024)
- [View2CAD: Reconstructing View-Centric CAD Models from Single RGB-D Scans](https://mlsanity.com/paper/2504.04000/) (2025)
- [Point Cloud to Mesh Reconstruction: Methods, Trade-offs, and Implementation Guide](https://mlsanity.com/paper/2412.10977/) (2024)
- [Deep Polycuboid Fitting for Compact 3D Representation of Indoor Scenes](https://mlsanity.com/paper/2503.14912/) (2025)
- [Hierarchical Error Assessment of CAD Models for Aircraft Manufacturing-and-Measurement](https://mlsanity.com/paper/2506.10594/) (2025)
- [RoofSeg: An edge-aware transformer-based network for end-to-end roof plane segmentation](https://mlsanity.com/paper/2508.19003/) (2025)
- [Unified Primitive Proxies for Structured Shape Completion](https://mlsanity.com/paper/2601.00759/) (2026)

## Abstract (arXiv)

This paper introduces HPNet, a novel deep-learning approach for segmenting a 3D shape represented as a point cloud into primitive patches. The key to deep primitive segmentation is learning a feature representation that can separate points of different primitives. Unlike utilizing a single feature representation, HPNet leverages hybrid representations that combine one learned semantic descriptor, two spectral descriptors derived from predicted geometric parameters, as well as an adjacency matrix that encodes sharp edges. Moreover, instead of merely concatenating the descriptors, HPNet optimally combines hybrid representations by learning combination weights. This weighting module builds on the entropy of input features. The output primitive segmentation is obtained from a mean-shift clustering module. Experimental results on benchmark datasets ANSI and ABCParts show that HPNet leads to significant performance gains from baseline approaches.