# P2CADNet: An End-to-End Reconstruction Network for Parametric 3D CAD Model from Point Clouds

arXiv: https://arxiv.org/abs/2310.02638 · HTML: https://mlsanity.com/paper/2310.02638/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 45 references that are in the map.
- First posted on arXiv 4 Oct 2023.

## Builds on (most cited first, 26 of 26)

- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [ABC: A Big CAD Model Dataset For Geometric Deep Learning](https://mlsanity.com/paper/1812.06216/) (2018)
- [DeepCAD: A Deep Generative Network for Computer-Aided Design Models](https://mlsanity.com/paper/2105.09492/) (2021)
- [Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference](https://mlsanity.com/paper/1902.10556/) (2019)
- [NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video](https://mlsanity.com/paper/2104.00681/) (2021)
- [Learning to Recover 3D Scene Shape from a Single Image](https://mlsanity.com/paper/2012.09365/) (2020)
- [Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction](https://mlsanity.com/paper/1706.07036/) (2017)
- [CSGNet: Neural Shape Parser for Constructive Solid Geometry](https://mlsanity.com/paper/1712.08290/) (2017)
- [Computer-Aided Design as Language](https://mlsanity.com/paper/2105.02769/) (2021)
- [SolidGen: An Autoregressive Model for Direct B-rep Synthesis](https://mlsanity.com/paper/2203.13944/) (2022)
- [UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Tree](https://mlsanity.com/paper/2006.09102/) (2020)
- [MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depth](https://mlsanity.com/paper/2208.02541/) (2022)
- [CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing](https://mlsanity.com/paper/2108.11305/) (2021)
- [3D Shape Reconstruction from 2D Images with Disentangled Attribute Flow](https://mlsanity.com/paper/2203.15190/) (2022)
- [Multi-View Mesh Reconstruction with Neural Deferred Shading](https://mlsanity.com/paper/2212.04386/) (2022)
- [Surface Reconstruction from Point Clouds: A Survey and a Benchmark](https://mlsanity.com/paper/2205.02413/) (2022)
- [Reconstructing editable prismatic CAD from rounded voxel models](https://mlsanity.com/paper/2209.01161/) (2022)
- [Self-Supervised Representation Learning for CAD](https://mlsanity.com/paper/2210.10807/) (2022)
- [Neural Shape Parsers for Constructive Solid Geometry](https://mlsanity.com/paper/1912.11393/) (2019)
- [Reverse engineering of CAD models via clustering and approximate implicitization](https://mlsanity.com/paper/1810.07451/) (2018)
- [A Survey of Methods for Converting Unstructured Data to CSG Models](https://mlsanity.com/paper/2305.01220/) (2023)
- [Topologically robust CAD model generation for structural optimisation](https://mlsanity.com/paper/1906.07631/) (2019)
- [XVoxel-Based Parametric Design Optimization of Feature Models](https://mlsanity.com/paper/2303.15316/) (2023)

## Built on by (most cited first, 1 of 1)

- [View2CAD: Reconstructing View-Centric CAD Models from Single RGB-D Scans](https://mlsanity.com/paper/2504.04000/) (2025)

## Abstract (arXiv)

Computer Aided Design (CAD), especially the feature-based parametric CAD, plays an important role in modern industry and society. However, the reconstruction of featured CAD model is more challenging than the reconstruction of other CAD models. To this end, this paper proposes an end-to-end network to reconstruct featured CAD model from point cloud (P2CADNet). Initially, the proposed P2CADNet architecture combines a point cloud feature extractor, a CAD sequence reconstructor and a parameter optimizer. Subsequently, in order to reconstruct the featured CAD model in an autoregressive way, the CAD sequence reconstructor applies two transformer decoders, one with target mask and the other without mask. Finally, for predicting parameters more precisely, we design a parameter optimizer with cross-attention mechanism to further refine the CAD feature parameters. We evaluate P2CADNet on the public dataset, and the experimental results show that P2CADNet has excellent reconstruction quality and accuracy. To our best knowledge, P2CADNet is the first end-to-end network to reconstruct featured CAD model from point cloud, and can be regarded as baseline for future works. Therefore, we open the source code at https://github.com/Blice0415/P2CADNet.