mlsanityData to 14 Oct 2026

CAD-Recode: Reverse Engineering CAD Code from Point Clouds

arXiv 2412.14042 ↗First posted 18 Dec 2024cs.CVcited by 66

Not on the map. Why?

Abstract (arXiv)

Computer-Aided Design (CAD) models are typically constructed by sequentially drawing parametric sketches and applying CAD operations to obtain a 3D model. The problem of 3D CAD reverse engineering consists of reconstructing the sketch and CAD operation sequences from 3D representations such as point clouds. In this paper, we address this challenge through novel contributions across three levels: CAD sequence representation, network design, and training dataset. In particular, we represent CAD sketch-extrude sequences as Python code. The proposed CAD-Recode translates a point cloud into Python code that, when executed, reconstructs the CAD model. Taking advantage of the exposure of pre-trained Large Language Models (LLMs) to Python code, we leverage a relatively small LLM as a decoder for CAD-Recode and combine it with a lightweight point cloud projector. CAD-Recode is trained on a procedurally generated dataset of one million CAD sequences. CAD-Recode significantly outperforms existing methods across the DeepCAD, Fusion360 and real-world CC3D datasets. Furthermore, we show that our CAD Python code output is interpretable by off-the-shelf LLMs, enabling CAD editing and CAD-specific question answering from point clouds.

Key facts. Cited by 66 papers in the map (data through 14 Oct 2026). Builds on 41 of its 62 references that are in the map. First posted on arXiv 18 Dec 2024.

Builds on

41 of 62 references.

References · 41

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  2. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  3. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 463
  4. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 341
  5. 2023PointLLM: Empowering Large Language Models to Understand Point Cloudscited by 333
  6. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 271
  7. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 267
  8. 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representationcited by 228
  9. 2023LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planningcited by 210
  10. 2023ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understandingcited by 202
  11. 2022PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learningcited by 187
  12. 2023OneLLM: One Framework to Align All Modalities with Languagecited by 187
29 more
  1. 2023OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understandingcited by 184
  2. 2022SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebookscited by 125
  3. 2020ParSeNet: A Parametric Surface Fitting Network for 3D Point Cloudscited by 96
  4. 2021BRepNet: A topological message passing system for solid modelscited by 95
  5. 2018Supervised Fitting of Geometric Primitives to 3D Point Cloudscited by 91
  6. 2023Hierarchical Neural Coding for Controllable CAD Model Generationcited by 86
  7. 2020UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Treecited by 78
  8. 2020PIE-NET: Parametric Inference of Point Cloud Edgescited by 67
  9. 2021Vitruvion: A Generative Model of Parametric CAD Sketchescited by 66
  10. 2024CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attentioncited by 64
  11. 2024Generating CAD Code with Vision-Language Models for 3D Designscited by 62
  12. 2021Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinderscited by 60
  13. 2021Inferring CAD Modeling Sequences Using Zone Graphscited by 50
  14. 2023SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operationscited by 46
  15. 2022Reconstructing editable prismatic CAD from rounded voxel modelscited by 41
  16. 2023D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropoutscited by 40
  17. 2023ShapeGPT: 3D Shape Generation with A Unified Multi-modal Language Modelcited by 39
  18. 2022ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsingcited by 38
  19. 2024Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorizationcited by 35
  20. 2024Can Large Language Models Understand Symbolic Graphics Programs?cited by 35
  21. 2021PC2WF: 3D Wireframe Reconstruction from Raw Point Cloudscited by 33
  22. 2022CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representationscited by 31
  23. 2024Query2CAD: Generating CAD models using natural language queriescited by 29
  24. 2024TransCAD: A Hierarchical Transformer for CAD Sequence Inference from Point Cloudscited by 29
  25. 2023NerVE: Neural Volumetric Edges for Parametric Curve Extraction from Point Cloudcited by 22
  26. 2021PvDeConv: Point-Voxel Deconvolution for Autoencoding CAD Construction in 3Dcited by 20
  27. 2023SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselinescited by 19
  28. 2023CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programscited by 15
  29. 2023SepicNet: Sharp Edges Recovery by Parametric Inference of Curves in 3D Shapescited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 11; 2026: 55.

66 papers.

Sort:

By area:

  1. 2025Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarkscited by 33
  2. 2025Large Language Models for Computer-Aided Design: A Surveycited by 18
  3. 2025cadrille: Multi-modal CAD Reconstruction with Reinforcement Learningcited by 16
  4. 2026BenchCAD: A Comprehensive, Industry-Standard Benchmark for Programmatic CADcited by 15
  5. 2026Text2CAD-Bench: A Benchmark for LLM-based Text-to-Parametric CAD Generationcited by 12
  6. 2025ReCAD: Reinforcement Learning Enhanced Parametric CAD Model Generation with Vision-Language Modelscited by 11
  7. 2026Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selectioncited by 11
  8. 2026CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generationcited by 11
  9. 2026Text-to-CAD Evaluation with CADTestscited by 10
  10. 2025CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuningcited by 8
  11. 2026ArtiCAD: Articulated CAD Assembly Design via Multi-Agent Code Generationcited by 8
  12. 2026Zero-to-CAD: Agentic Synthesis of Interpretable CAD Programs at Million-Scale Without Real Datacited by 8
38 more
  1. 2025RLCAD: Reinforcement Learning Training Gym for Revolution Involved CAD Command Sequence Generationcited by 7
  2. 2026Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generationcited by 7
  3. 2026Towards High-Fidelity CAD Generation via LLM-Driven Program Generation and Text-Based B-Rep Primitive Groundingcited by 7
  4. 2025NURBGen: High-Fidelity Text-to-CAD Generation through LLM-Driven NURBS Modelingcited by 6
  5. 2026CADReasoner: Iterative Program Editing for CAD Reverse Engineeringcited by 6
  6. 2025MiCADangelo: Fine-Grained Reconstruction of Constrained CAD Models from 3D Scanscited by 5
  7. 2026CADFS: A Big CAD Program Dataset and Framework for Computer-Aided Design with Large Language Modelscited by 5
  8. 2025CADDesigner: Conceptual CAD Model Generation with a General-Purpose Agentcited by 4
  9. 2025LAMP: Data-Efficient Linear Affine Weight-Space Models for Parameter-Controlled 3D Shape Generation and Extrapolationcited by 4
  10. 2026CADFit: Precise Mesh-to-CAD Program Generation with Hybrid Optimizationcited by 4
  11. 2026BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoningcited by 3
  12. 2026GIFT: Bootstrapping Image-to-CAD Program Synthesis via Geometric Feedbackcited by 3
  13. 2026UniCAD: A Unified Benchmark and Universal Model for Multi-Modal Multi-Task CADcited by 3
  14. 2025GACO-CAD: Geometry-Augmented and Conciseness-Optimized CAD Model Generation from Single Imagecited by 2
  15. 2026DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfacescited by 2
  16. 2026Self-Improving CAD Generation Agents with Finite Element Analysis as Feedbackcited by 2
  17. 2026ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigmcited by 2
  18. 2026Autoregressive B-Rep Shape Generation with Parametric Surfacescited by 2
  19. 2026PLLM: Pseudo-Labeling Large Language Models for CAD Program Synthesiscited by 1
  20. 2026ASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detectioncited by 1
  21. 2026FllumaOne: A Code-Native Multimodal CAD Dataset with Executable Programs and Kernel-Validated Feature Historiescited by 1
  22. 2026Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precisioncited by 1
  23. 2026Masked Topology Modeling for Self-Supervised Learning on Parametric CADcited by 1
  24. 2026Dual Inversion for Text-to-Image Diffusion Models: From Both Prompt and Noise Perspectivescited by 1
  25. 2026CADENA: Stepwise CAD Reverse Engineeringcited by 1
  26. 2026CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Designcited by 1
  27. 2026CADForge: Agentic Single-View CAD Reconstruction with Explicit Geometry Reasoningcited by 1
  28. 2026Flatten The Complex: Joint B-Rep Generation via Compositional k-Cell Particlescited by 0
  29. 2026Learning From Design Procedure To Generate CAD Programs for Data Augmentationcited by 0
  30. 2026Design-Specification Tiling for ICL-based CAD Code Generationcited by 0
  31. 2026Computer-Aided Design Generation by Cascaded Discrete Diffusion Modelcited by 0
  32. 2026Extrusion Segmentation Strategy to improve CAD Reconstruction from Point Cloudcited by 0
  33. 2026Memory-Augmented Reinforcement Learning Agent for CAD Generationcited by 0
  34. 2026GuideCAD: A Lightweight Multimodal Framework for 3D CAD Model Generation via Prefix Embeddingcited by 0
  35. 2026Arko-T: A Foundation Model for Text-to-Structured 3D Generationcited by 0
  36. 2026Decomposer: Learning to Decompile Symbolic Music to Programscited by 0
  37. 2026Three-Phase Evaluation of AI-Assisted Software Development Life Cyclecited by 0
  38. 2026Wrong Design Intent Is Worse Than Never Conditioning: A Derangement-Control Diagnosis of Header Conditioning in CAD Program Completioncited by 0

50 most cited of 66 All 66 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds
  2. 2025CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation
  3. 2025CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images
  4. 2025CADReview: Automatically Reviewing CAD Programs with Error Detection and Correction
  5. 2024From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach
  6. 2025Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilities
  7. 2026CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use
  8. 2024OpenECAD: An Efficient Visual Language Model for Editable 3D-CAD Design