mlsanityData to 7 Oct 2026

Img2CAD: Conditioned 3D CAD Model Generation from Single Image with Structured Visual Geometry

arXiv 2410.03417 ↗First posted 4 Oct 2024cs.CVcited by 35

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose Img2CAD, the first approach to our knowledge that uses 2D image inputs to generate CAD models with editable parameters. Unlike existing AI methods for 3D model generation using text or image inputs often rely on mesh-based representations, which are incompatible with CAD tools and lack editability and fine control, Img2CAD enables seamless integration between AI-based 3D reconstruction and CAD software. We have identified an innovative intermediate representation called Structured Visual Geometry (SVG), characterized by vectorized wireframes extracted from objects. This representation significantly enhances the performance of generating conditioned CAD models. Additionally, we introduce two new datasets to further support research in this area: ABC-mono, the largest known dataset comprising over 200,000 3D CAD models with rendered images, and KOCAD, the first dataset featuring real-world captured objects alongside their ground truth CAD models, supporting further research in conditioned CAD model generation.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 47 of its 64 references that are in the map. First posted on arXiv 4 Oct 2024.

Builds on

47 of 64 references.

References · 47

  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  2. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  3. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  4. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  5. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  6. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  7. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 837
  8. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
  9. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  10. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  11. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 682
  12. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 638
35 more
  1. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 555
  2. 2023Shap-E: Generating Conditional 3D Implicit Functionscited by 379
  3. 2023Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Priorcited by 341
  4. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  5. 2023RealFusion: 360deg Reconstruction of Any Object from a Single Imagecited by 305
  6. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  7. 2023LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matchingcited by 290
  8. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 266
  9. 2024TripoSR: Fast 3D Object Reconstruction from a Single Imagecited by 227
  10. 2024CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Modelcited by 214
  11. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  12. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  13. 2023NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusioncited by 179
  14. 2022SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebookscited by 121
  15. 2017CSGNet: Neural Shape Parser for Constructive Solid Geometrycited by 106
  16. 2024BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometrycited by 101
  17. 2020ParSeNet: A Parametric Surface Fitting Network for 3D Point Cloudscited by 96
  18. 2021BRepNet: A topological message passing system for solid modelscited by 92
  19. 2023Hierarchical Neural Coding for Controllable CAD Model Generationcited by 84
  20. 2022SolidGen: An Autoregressive Model for Direct B-rep Synthesiscited by 78
  21. 2020UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Treecited by 77
  22. 2020Holistically-Attracted Wireframe Parsingcited by 63
  23. 2021CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assemblycited by 62
  24. 2022AutoRF: Learning 3D Object Radiance Fields from Single View Observationscited by 59
  25. 2021CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsingcited by 51
  26. 2021Inferring CAD Modeling Sequences Using Zone Graphscited by 50
  27. 2023SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operationscited by 46
  28. 2023D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropoutscited by 39
  29. 2022ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsingcited by 38
  30. 2023GaussianDiffusion: 3D Gaussian Splatting for Denoising Diffusion Probabilistic Models with Structured Noisecited by 30
  31. 2022Cross-Modal 3D Shape Generation and Manipulationcited by 27
  32. 2022Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learningcited by 26
  33. 2023Slice3D: Multi-Slice, Occlusion-Revealing, Single View 3D Reconstructioncited by 13
  34. 2022HoW-3D: Holistic 3D Wireframe Perception from a Single Imagecited by 12
  35. 2023Reality3DSketch: Rapid 3D Modeling of Objects from Single Freehand Sketchescited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 14; 2026: 20.

35 papers.

Sort:

By area:

  1. 2024CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLMcited by 74
  2. 2025Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilitiescited by 43
  3. 2025CADCrafter: Generating Computer-Aided Design Models from Unconstrained Imagescited by 31
  4. 2025HoLa: B-Rep Generation using a Holistic Latent Representationcited by 29
  5. 2025CADDreamer: CAD Object Generation from Single-view Imagescited by 22
  6. 2025AutoBrep: Autoregressive B-Rep Generation with Unified Topology and Geometrycited by 16
  7. 2025cadrille: Multi-modal CAD Reconstruction with Reinforcement Learningcited by 14
  8. 2025BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patchcited by 12
  9. 2026Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selectioncited by 9
  10. 2025CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generationcited by 6
  11. 2025NURBGen: High-Fidelity Text-to-CAD Generation through LLM-Driven NURBS Modelingcited by 5
  12. 2026CADReasoner: Iterative Program Editing for CAD Reverse Engineeringcited by 4
23 more
  1. 2025PHT-CAD: Efficient CAD Parametric Primitive Analysis with Progressive Hierarchical Tuningcited by 3
  2. 2025VULCAN: Tool-Augmented Multi Agents for Iterative 3D Object Arrangementcited by 3
  3. 2026BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoningcited by 3
  4. 2026Deep Sketch-Based 3D Modeling: A Surveycited by 3
  5. 2026Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Designcited by 3
  6. 2026UniCAD: A Unified Benchmark and Universal Model for Multi-Modal Multi-Task CADcited by 3
  7. 2026Autoregressive B-Rep Shape Generation with Parametric Surfacescited by 2
  8. 20253DFroMLLM: 3D Prototype Generation only from Pretrained Multimodal LLMscited by 1
  9. 2026ViSculpt: Visual-Centric Agentic Geometry Editingcited by 1
  10. 2025Breaking the Box: Enhancing Remote Sensing Image Segmentation with Freehand Sketchescited by 0
  11. 2025View2CAD: Reconstructing View-Centric CAD Models from Single RGB-D Scanscited by 0
  12. 2026Computer-Aided Design Generation by Cascaded Discrete Diffusion Modelcited by 0
  13. 2026Text-to-CAD Retrieval: a Strong Baselinecited by 0
  14. 2026GuideCAD: A Lightweight Multimodal Framework for 3D CAD Model Generation via Prefix Embeddingcited by 0
  15. 2026Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precisioncited by 0
  16. 2026HiFi-BRep: High-Fidelity Latent Representation for Robust B-Rep Generationcited by 0
  17. 2026aDSL: Agentic 3D Creation via Joint Agent-Program Designcited by 0
  18. 2026LLM-Aided Design for Manufacturing: A Multi-Agent System for Intent-Preserving Redesign of CAD for Improved Manufacturabilitycited by 0
  19. 20263DHarnessBench: Probing Agentic 3D-to-Code Capabilities of Frontier Vision-Language Modelscited by 0
  20. 2026NeuSOGA3D: A Neuro-Symbolic Framework for Explainable 3D Geometric Reconstructioncited by 0
  21. 2026VGGT-CAD: Reconstructing Parametric CAD 3D Model with Geometric Groundingcited by 0
  22. 2026Vision2CAD: A Visual Agent Harness for Explicit Geometry Referencing and Localization in Parametric CAD Modelingcited by 0
  23. 2026Reinforcement Learning from Intermediate Renders for Image-to-Code Generationcited by 0