# QuadricsNet: Learning Concise Representation for Geometric Primitives in Point Clouds

arXiv: https://arxiv.org/abs/2309.14211 · HTML: https://mlsanity.com/paper/2309.14211/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 25 Sep 2023.

## Builds on (most cited first, 19 of 19)

- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [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)
- [Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids](https://mlsanity.com/paper/1904.09970/) (2019)
- [CSGNet: Neural Shape Parser for Constructive Solid Geometry](https://mlsanity.com/paper/1712.08290/) (2017)
- [CubeSLAM: Monocular 3D Object SLAM](https://mlsanity.com/paper/1806.00557/) (2018)
- [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)
- [QuadricSLAM: Dual Quadrics from Object Detections as Landmarks in Object-oriented SLAM](https://mlsanity.com/paper/1804.04011/) (2018)
- [3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks](https://mlsanity.com/paper/1708.01648/) (2017)
- [Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinders](https://mlsanity.com/paper/2112.09329/) (2021)
- [HPNet: Deep Primitive Segmentation Using Hybrid Representations](https://mlsanity.com/paper/2105.10620/) (2021)
- [CPFN: Cascaded Primitive Fitting Networks for High-Resolution Point Clouds](https://mlsanity.com/paper/2109.00113/) (2021)
- [Neural Shape Parsers for Constructive Solid Geometry](https://mlsanity.com/paper/1912.11393/) (2019)
- [Generic Primitive Detection in Point Clouds Using Novel Minimal Quadric Fits](https://mlsanity.com/paper/1901.01255/) (2019)
- [From Planes to Corners: Multi-Purpose Primitive Detection in Unorganized 3D Point Clouds](https://mlsanity.com/paper/2001.07360/) (2020)
- [Unified Representation of Geometric Primitives for Graph-SLAM Optimization Using Decomposed Quadrics](https://mlsanity.com/paper/2108.08957/) (2021)
- [PrimiTect: Fast Continuous Hough Voting for Primitive Detection](https://mlsanity.com/paper/2005.07457/) (2020)

## Built on by (most cited first, 2 of 2)

- [PoNQ: a Neural QEM-based Mesh Representation](https://mlsanity.com/paper/2403.12870/) (2024)
- [QuadricsReg: Large-Scale Point Cloud Registration using Quadric Primitives](https://mlsanity.com/paper/2412.02998/) (2024)

## Abstract (arXiv)

This paper presents a novel framework to learn a concise geometric primitive representation for 3D point clouds. Different from representing each type of primitive individually, we focus on the challenging problem of how to achieve a concise and uniform representation robustly. We employ quadrics to represent diverse primitives with only 10 parameters and propose the first end-to-end learning-based framework, namely QuadricsNet, to parse quadrics in point clouds. The relationships between quadrics mathematical formulation and geometric attributes, including the type, scale and pose, are insightfully integrated for effective supervision of QuaidricsNet. Besides, a novel pattern-comprehensive dataset with quadrics segments and objects is collected for training and evaluation. Experiments demonstrate the effectiveness of our concise representation and the robustness of QuadricsNet. Our code is available at urlhttps://github.com/MichaelWu99-lab/QuadricsNet