ML for CAD

• [2412.14042] CAD-Recode: Reverse Engineering CAD Code from Point Clouds

• CADSpotting: Robust Panoptic Symbol Spotting on Large-Scale CAD Drawings

• ArchCAD-400K: An Open Large-Scale Architectural CAD Dataset and New Baseline for Panoptic Symbol Spotting

• CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing

• Blueprint CAD analysis resources

• awv-informatik/buerli-examples: Examples that show what buerli and ClassCAD can do

• awv-informatik/buerligons: buerli’s CAD application

• bertjiazheng/Awesome-CAD: 😎 A list of awesome Computer-Aided Design (CAD) papers

• microsoft/CAD-Editor

• rundiwu/DeepCAD: code for our ICCV 2021 paper “DeepCAD: A Deep Generative Network for Computer-Aided Design Models”

• samxuxiang/hnc-cad: [ICML 2023] Official PyTorch Implementation of “Hierarchical Neural Coding for Controllable CAD Model Generation”.

• samxuxiang/SkexGen: [ICML 2022] Official PyTorch Implementation of “SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks”.

• AR-CADhk (AR-CAD R&D)

• CADCODER/GenCAD-Code · Datasets at Hugging Face

• Paper page - GenCAD: Image-Conditioned Computer-Aided Design Generation with Transformer-Based Contrastive Representation and Diffusion Priors

• Paper page - CadVLM: Bridging Language and Vision in the Generation of Parametric CAD Sketches

• Paper page - From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach

• Paper page - CAD-Recode: Reverse Engineering CAD Code from Point Clouds

• Paper page - CADDreamer: CAD object Generation from Single-view Images

• Paper page - CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images

• Paper page - CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generation

• Paper page - Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilities

• Paper page - CADReview: Automatically Reviewing CAD Programs with Error Detection and Correction

• Paper page - cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning

• Paper page - Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings

• Paper page - CAD-Tokenizer: Towards Text-based CAD Prototyping via Modality-Specific Tokenization

• FloorPlanCAD: A Large-Scale CAD Drawing Dataset for Panoptic Symbol Spotting

• AR-CAD

• Dmytro Mishkin 🇺🇦 on X: “Great overview of the workshops and tutorials. My favorites: 1) CAD representation 2) synthetic data to help city-scale reconstruction 3) trends in 3D vision 4) visual chain-of-thoughts? https://t.co/4kr9BUpp3i” / X

• [2508.14879] MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

• SpatialGen

• [2503.14786] SketchSplat: 3D Edge Reconstruction via Differentiable Multi-view Sketch Splatting

Floorplan Parsing

• [2412.00955v2] WAFFLE: Multimodal Floorplan Understanding in the Wild
• [2407.10439] PolyRoom: Room-aware Transformer for Floorplan Reconstruction**

Datasets

• CubiCasa5K: A Dataset and an Improved Multi-task Model for Floorplan Image Analysis | Image Analysis

• Structured3D Dataset

• GitHub - andyeske/How-to-CAD-Almost-Anything: Welcome to How to CAD Almost Anything! In this repository, you’ll find the workshop’s slides, recordings and Solidworks files.

CAD Formats

• µcad: New open source programming language that can generate 2D sketches and 3D | Hacker News