# PS-CAD: Local Geometry Guidance via Prompting and Selection for CAD Reconstruction

arXiv: https://arxiv.org/abs/2405.15188 · HTML: https://mlsanity.com/paper/2405.15188/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 48 references that are in the map.
- First posted on arXiv 24 May 2024.

## Builds on (most cited first, 25 of 25)

- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Masked Autoencoders for Point Cloud Self-supervised Learning](https://mlsanity.com/paper/2203.06604/) (2022)
- [DeepCAD: A Deep Generative Network for Computer-Aided Design Models](https://mlsanity.com/paper/2105.09492/) (2021)
- [Learning Shape Abstractions by Assembling Volumetric Primitives](https://mlsanity.com/paper/1612.00404/) (2016)
- [CvxNet: Learnable Convex Decomposition](https://mlsanity.com/paper/1909.05736/) (2019)
- [SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks](https://mlsanity.com/paper/2207.04632/) (2022)
- [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)
- [ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds](https://mlsanity.com/paper/2003.12181/) (2020)
- [Write, Execute, Assess: Program Synthesis with a REPL](https://mlsanity.com/paper/1906.04604/) (2019)
- [Supervised Fitting of Geometric Primitives to 3D Point Clouds](https://mlsanity.com/paper/1811.08988/) (2018)
- [Hierarchical Neural Coding for Controllable CAD Model Generation](https://mlsanity.com/paper/2307.00149/) (2023)
- [UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Tree](https://mlsanity.com/paper/2006.09102/) (2020)
- [PIE-NET: Parametric Inference of Point Cloud Edges](https://mlsanity.com/paper/2007.04883/) (2020)
- [CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention](https://mlsanity.com/paper/2402.17678/) (2024)
- [CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing](https://mlsanity.com/paper/2108.11305/) (2021)
- [Inferring CAD Modeling Sequences Using Zone Graphs](https://mlsanity.com/paper/2104.03900/) (2021)
- [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)
- [D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts](https://mlsanity.com/paper/2301.11497/) (2023)
- [ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsing](https://mlsanity.com/paper/2209.15632/) (2022)
- [PLAD: Learning to Infer Shape Programs with Pseudo-Labels and Approximate Distributions](https://mlsanity.com/paper/2011.13045/) (2020)
- [Neural Shape Parsers for Constructive Solid Geometry](https://mlsanity.com/paper/1912.11393/) (2019)
- [Implicit Conversion of Manifold B-Rep Solids by Neural Halfspace Representation](https://mlsanity.com/paper/2209.10191/) (2022)

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

- [LLM-Guided Material Inference for 3D Point Clouds](https://mlsanity.com/paper/2512.03237/) (2025)

## Abstract (arXiv)

Reverse engineering CAD models from raw geometry is a classic but challenging research problem. In particular, reconstructing the CAD modeling sequence from point clouds provides great interpretability and convenience for editing. To improve upon this problem, we introduce geometric guidance into the reconstruction network. Our proposed model, PS-CAD, reconstructs the CAD modeling sequence one step at a time. At each step, we provide two forms of geometric guidance. First, we provide the geometry of surfaces where the current reconstruction differs from the complete model as a point cloud. This helps the framework to focus on regions that still need work. Second, we use geometric analysis to extract a set of planar prompts, that correspond to candidate surfaces where a CAD extrusion step could be started. Our framework has three major components. Geometric guidance computation extracts the two types of geometric guidance. Single-step reconstruction computes a single candidate CAD modeling step for each provided prompt. Single-step selection selects among the candidate CAD modeling steps. The process continues until the reconstruction is completed. Our quantitative results show a significant improvement across all metrics. For example, on the dataset DeepCAD, PS-CAD improves upon the best published SOTA method by reducing the geometry errors (CD and HD) by 10%, and the structural error (ECD metric) by about 15%.