mlsanityData to 7 Oct 2026

TransCAD: A Hierarchical Transformer for CAD Sequence Inference from Point Clouds

arXiv 2407.12702 ↗First posted 17 Jul 2024cs.CV cs.AIcited by 29

Not on the map. Why?

Abstract (arXiv)

3D reverse engineering, in which a CAD model is inferred given a 3D scan of a physical object, is a research direction that offers many promising practical applications. This paper proposes TransCAD, an end-to-end transformer-based architecture that predicts the CAD sequence from a point cloud. TransCAD leverages the structure of CAD sequences by using a hierarchical learning strategy. A loop refiner is also introduced to regress sketch primitive parameters. Rigorous experimentation on the DeepCAD and Fusion360 datasets show that TransCAD achieves state-of-the-art results. The result analysis is supported with a proposed metric for CAD sequence, the mean Average Precision of CAD Sequence, that addresses the limitations of existing metrics.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 39 of its 53 references that are in the map. First posted on arXiv 17 Jul 2024.

Builds on

39 of 53 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  7. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  8. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  9. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  10. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  11. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  12. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 339
27 more
  1. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 267
  2. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 266
  3. 2020Learning Gradient Fields for Shape Generationcited by 245
  4. 2020DeepSVG: A Hierarchical Generative Network for Vector Graphics Animationcited by 158
  5. 2022SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebookscited by 121
  6. 2019PQ-NET: A Generative Part Seq2Seq Network for 3D Shapescited by 118
  7. 2024BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometrycited by 101
  8. 2020ParSeNet: A Parametric Surface Fitting Network for 3D Point Cloudscited by 96
  9. 2021BRepNet: A topological message passing system for solid modelscited by 92
  10. 2018Supervised Fitting of Geometric Primitives to 3D Point Cloudscited by 90
  11. 2018EC-Net: an Edge-aware Point set Consolidation Networkcited by 84
  12. 2023Hierarchical Neural Coding for Controllable CAD Model Generationcited by 84
  13. 2022SolidGen: An Autoregressive Model for Direct B-rep Synthesiscited by 78
  14. 2020UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Treecited by 77
  15. 2020PIE-NET: Parametric Inference of Point Cloud Edgescited by 67
  16. 2024CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attentioncited by 62
  17. 2021Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinderscited by 59
  18. 2021Inferring CAD Modeling Sequences Using Zone Graphscited by 50
  19. 2023SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operationscited by 46
  20. 2022Reconstructing editable prismatic CAD from rounded voxel modelscited by 41
  21. 2023D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropoutscited by 39
  22. 2022ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsingcited by 38
  23. 2021PC2WF: 3D Wireframe Reconstruction from Raw Point Cloudscited by 33
  24. 2022CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representationscited by 30
  25. 2023NerVE: Neural Volumetric Edges for Parametric Curve Extraction from Point Cloudcited by 22
  26. 2023SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselinescited by 19
  27. 2023SepicNet: Sharp Edges Recovery by Parametric Inference of Curves in 3D Shapescited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 6; 2026: 19.

29 papers.

Sort:

By area:

  1. 2024CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLMcited by 74
  2. 2024CAD-Recode: Reverse Engineering CAD Code from Point Cloudscited by 63
  3. 2024CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solverscited by 40
  4. 2025CADmium: Fine-Tuning Code Language Models for Text-Driven Sequential CAD Designcited by 23
  5. 2025Seek-CAD: A Self-refined Generative Modeling for 3D Parametric CAD Using Local Inference via DeepSeekcited by 22
  6. 2025cadrille: Multi-modal CAD Reconstruction with Reinforcement Learningcited by 14
  7. 2024PICASSO: A Feed-Forward Framework for Parametric Inference of CAD Sketches via Rendering Self-Supervisioncited by 9
  8. 2025Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawingscited by 9
  9. 2026Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selectioncited by 9
  10. 2026Text-to-CAD Evaluation with CADTestscited by 9
  11. 2026ArtiCAD: Articulated CAD Assembly Design via Multi-Agent Code Generationcited by 7
  12. 2026Zero-to-CAD: Agentic Synthesis of Interpretable CAD Programs at Million-Scale Without Real Datacited by 7
17 more
  1. 2026CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generationcited by 7
  2. 2025CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generationcited by 6
  3. 2025NURBGen: High-Fidelity Text-to-CAD Generation through LLM-Driven NURBS Modelingcited by 5
  4. 2026CADFS: A Big CAD Program Dataset and Framework for Computer-Aided Design with Large Language Modelscited by 4
  5. 2026BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoningcited by 3
  6. 2026GIFT: Bootstrapping Image-to-CAD Program Synthesis via Geometric Feedbackcited by 3
  7. 2026Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Designcited by 3
  8. 2026UniCAD: A Unified Benchmark and Universal Model for Multi-Modal Multi-Task CADcited by 3
  9. 2026ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigmcited by 2
  10. 2026DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfacescited by 1
  11. 2026BIM-Edit: Benchmarking Large Language Models for IFC-Based Building Information Modelingcited by 1
  12. 2026HierCAD: Hierarchical Text-to-CAD Design via Structure Alignment and Parameter Groundingcited by 1
  13. 2026SharpNet: Enhancing MLPs to Represent Functions with Controlled Non-differentiabilitycited by 0
  14. 2026Computer-Aided Design Generation by Cascaded Discrete Diffusion Modelcited by 0
  15. 2026Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precisioncited by 0
  16. 2026AIMold: An Autonomous AI-based Pipeline for Complex Mold Designcited by 0
  17. 2026AgenticCADedit: A Stateful, Tool-Mediated Agentic Approach to Multimodal 3D CAD Editingcited by 0