🎯 The first awesome list featuring visual paper previews - see research at a glance.
📚 We have also included a selection of papers that, while not strictly falling within the CAD domain, demonstrate relevant techniques and methodologies that could benefit CAD research and applications.
🏠 You can also check our Project Homepage.
🔥🔥🔥 Also check out our awesome list about 3D generation.
Generation • Reconstruction • Abstraction • Analysis • Others • Dataset
| Preview | Title | Publication | Links |
|---|---|---|---|
![]() |
Autoregressive B-Rep Shape Generation with Parametric Surfaces | SIGGRAPH 2026 | Paper Code |
![]() |
BrepForge: Factorized B-rep Synthesis via Wireframe Composition and Boundary-Conditioned Surface Instantiation | SIGGRAPH 2026 | Paper |
![]() |
Towards High-Fidelity CAD Generation via LLM-Driven Program Generation and Text-Based B-Rep Primitive Grounding | ICML 2026 | Paper Code |
![]() |
CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generation | CVPR 2026 | Paper |
![]() |
STEP-LLM: Generating CAD STEP Models from Natural Language with Large Language Models | arXiv 2026 | Paper Code |
![]() |
CADEvolve: Creating Realistic CAD via Program Evolution | arXiv 2026 | Paper Code |
![]() |
Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation | arXiv 2026 | Paper |
![]() |
CADmium: Fine-Tuning Code Language Models for Text-Driven Sequential CAD Design | TMLR 2026 | Paper |
![]() |
ReCAD: Reinforcement Learning Enhanced Parametric CAD Model Generation with Vision-Language Models | arXiv 2025 | Paper |
![]() |
BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patch | SIGGRAPH Asia 2025 | Paper Code |
![]() |
AutoBrep: Autoregressive B-Rep Generation with Unified Topology and Geometry | SIGGRAPH Asia 2025 | Paper Code |
![]() |
GeoCAD: Local Geometry-Controllable CAD Generation | NeurIPS 2025 | Paper Code |
![]() |
CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward | arXiv 2025 | Paper |
![]() |
Stitch-A-Shape: Bottom-up Learning for B-Rep Generation | SIGGRAPH 2025 | Paper |
![]() |
BrepDiff: Single-stage B-rep Diffusion Model | SIGGRAPH 2025 | Paper Project |
![]() |
HoLa: B-Rep Generation using a Holistic Latent Representation | SIGGRAPH 2025 | Paper Project |
![]() |
CLR-Wire: Towards Continuous Latent Representations for 3D Curve Wireframe Generation | SIGGRAPH 2025 | Paper Code |
![]() |
DTGBrepGen: A Novel B-rep Generative Model through Decoupling Topology and Geometry | CVPR 2025 | Paper Code Project |
![]() |
CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images | CVPR 2025 | Paper |
![]() |
CADDreamer: CAD object Generation from Single-view Images | CVPR 2025 | Paper Project |
![]() |
CAD-GPT: Synthesising CAD Construction Sequence with Spatial Reasoning-Enhanced Multimodal LLMs | arXiv 2025 | Paper Project |
![]() |
Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models | arXiv 2025 | Paper |
![]() |
Revisiting CAD Model Generation by Learning Raster Sketch | AAAI 2025 | Paper Dataset |
![]() |
FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Models | ICLR 2025 | Paper Code |
![]() |
Generating CAD Code with Vision-Language Models for 3D Designs | ICLR 2025 | Paper Code |
![]() |
Don’t Mesh with Me: Generating Constructive Solid Geometry Instead of Meshes by Fine-Tuning a Code-Generation LLM | arXiv 2024 | Paper |
![]() |
CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM | arXiv 2024 | Paper Project |
![]() |
Text2CAD: Text to 3D CAD Generation via Technical Drawings | NeurIPS 2024 | Paper Code Project |
![]() |
CadVLM: Bridging Language and Vision in the Generation of Parametric CAD Sketches | ECCV 2024 | Paper |
![]() |
BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometry | SIGGRAPH 2024 | Paper Code |
![]() |
Learn to Create Simple LEGO Micro Buildings | SIGGRAPH Asia 2024 | Paper Code |
![]() |
Generating 3D House Wireframes with Semantics | ECCV 2024 | Paper Project |
![]() |
SolidGen: An Autoregressive Model for Direct B-rep Synthesis | ICLR 2024 | Paper |
![]() |
Brep2Seq: A Dataset and Hierarchical Deep Learning Network for Reconstruction and Generation of Computer-Aided Design Models | JCDE 2024 | Paper Code |
![]() |
VQ-CAD: Computer-Aided Design model generation with vector quantized diffusion | CAGD 2024 | Paper |
![]() |
PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervision | CVPR 2023 | Paper Code Project |
![]() |
SketchGen: Generating Constrained CAD Sketches | ICCV 2023 | Paper Code |
![]() |
Hierarchical Neural Coding for Controllable CAD Model Generation | ICML 2023 | Paper Code Project |
![]() |
SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks | ICML 2022 | Paper Code Project |
![]() |
Discovering Design Concepts for CAD Sketches | NeurIPS 2022 | Paper Code |
![]() |
CAD2Sketch: Generating Concept Sketches from CAD Sequences | SIGGRAPH Asia 2022 | Paper Code Project |
![]() |
Free2CAD: Parsing Freehand Drawings into CAD Commands | SIGGRAPH 2022 | Code Project |
![]() |
DeepCAD: A Deep Generative Network for Computer-Aided Design Models | ICCV 2021 | Paper Code Project |
![]() |
Engineering Sketch Generation for Computer-Aided Design | CVPR 2021 workshop | Paper |
![]() |
Roof-GAN: Learning to Generate Roof Geometry and Relations for Residential Houses | CVPR 2021 | Paper Code |
![]() |
Computer-aided design as language | NeurIPS 2021 | Paper |
![]() |
DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation | NeurIPS 2020 | Paper Code Project |
![]() |
SDM-NET: Deep Generative Network for Structured Deformable Mesh | TOG 2019 | Paper Code |
![]() |
StructureNet: Hierarchical Graph Networks for 3D Shape Generation | Siggraph Asia 2019 | Paper Code Project |
![]() |
AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation | CVPR 2018 | Paper Code Project |
| Preview | Title | Publication | Links |
|---|---|---|---|
![]() |
Parametric Point Cloud Completion for Polygonal Surface Reconstruction | CVPR 2025 | Paper Project |
![]() |
From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach | AAAI 2025 | Paper Project |
![]() |
BGPSeg: Boundary-Guided Primitive Instance Segmentation of Point Clouds | TIP 2025 | Paper |
![]() |
CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solvers | ICCV 2025 | Paper |
![]() |
PICASSO: A Feed-Forward Framework for Parametric Inference of CAD Sketches via Rendering Self-Supervision | WACV 2025 | Paper |
![]() |
CAD-Recode: Reverse Engineering CAD Code from Point Clouds | ICCV 2025 | Paper Code |
![]() |
DAVINCI: A Single-Stage Architecture for Constrained CAD Sketch Inference | BMVC 2024 | Paper |
![]() |
Img2CAD: Conditioned 3D CAD Model Generation from Single Image with Structured Visual Geometry | arXiv 2024 | Paper |
![]() |
PS-CAD: Local Geometry Guidance via Prompting and Selection for CAD Reconstruction | arXiv 2024 | Paper |
![]() |
Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorization | arXiv 2024 | Paper Project |
![]() |
Draw Step by Step: Reconstructing CAD Construction Sequences from Point Clouds via Multimodal Diffusion | CVPR 2024 | Paper |
![]() |
CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention | CVPR 2024 | Paper |
![]() |
Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds | CVPR 2024 | Paper Code Project |
![]() |
SfmCAD: Unsupervised CAD Reconstruction by Learning Sketch-based Feature Modeling Operations | CVPR 2024 | Paper |
![]() |
DPA-Net: Structured 3D Abstraction from Sparse Views via Differentiable Primitive Assembly | ECCV 2024 | Paper |
![]() |
Differentiable Convex Polyhedra Optimization from Multi-view Images | ECCV 2024 | Paper Code |
![]() |
PolyGNN: Polyhedron-based Graph Neural Network for 3D Building Reconstruction from Point Clouds | ISPRS 2024 | Paper Code |
![]() |
Split-and-Fit: Learning B-Reps via Structure-Aware Voronoi Partitioning | SIGGRAPH 2024 | Paper Code |
![]() |
D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts | Neurips 2024 | Paper Code |
![]() |
SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operations | CVPR 2023 | Paper Code |
![]() |
PlankAssembly: Robust 3D Reconstruction from Three Orthographic Views with Learnt Shape Programs | ICCV 2023 | Paper Code Project |
![]() |
Surface and Edge Detection for Primitive Fitting of Point Clouds | SIGGRAPH 2023 | Code |
![]() |
BPNet: Bézier Primitive Segmentation on 3D Point Clouds | IJCAI 2023 | Paper Code |
![]() |
Vitruvion: A Generative Model of Parametric CAD Sketches | ICLR 2022 | Paper Code |
![]() |
Reconstructing compact building models from point clouds using deep implicit fields | ISPRS 2022 | Paper Code |
![]() |
CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representations | 3DV 2022 | Paper |
![]() |
Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinders | CVPR 2022 | Paper Code Project |
![]() |
ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsing | ECCV 2022 | Paper Code Project |
![]() |
Unsupervised Learning of Shape Programs with Repeatable Implicit Parts | NeurIPS 2022 | Paper Project |
![]() |
Reconstructing editable prismatic CAD from rounded voxel models | SIGGRAPH Asia 2022 | Paper |
![]() |
ComplexGen: CAD Reconstruction by B-Rep Chain Complex Generation | SIGGRAPH 2022 | Paper Code Project |
![]() |
CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assembly | CVPR 2022 | Paper Code Project |
![]() |
LC2WF:Learning to Construct 3D Building Wireframes from 3D Line Clouds | BMVC 2022 | Paper Code |
![]() |
HPNet: Deep Primitive Segmentation Using Hybrid Representations | ICCV 2021 | Paper Code |
![]() |
CPFN: Cascaded Primitive Fitting Networks for High-Resolution Point Clouds | ICCV 2021 | Paper Code |
![]() |
CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing | ICCV 2021 | Paper Code Project |
![]() |
PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds | ICLR 2021 | Paper Code |
![]() |
Intuitive and Efficient Roof Modeling for Reconstruction and Synthesis | SIGGRAPH Asia 2021 | Paper Code |
![]() |
Sketch2CAD: Sequential CAD Modeling by Sketching in Context | SIGGRAPH Asia 2020 | Paper Code Project |
![]() |
CvxNet: Learnable Convex Decomposition | CVPR 2020 | Paper Code Project |
![]() |
BSP-Net: Generating Compact Meshes via Binary Space Partitioning | CVPR 2020 oral | Paper Code Project |
![]() |
PIE-NET: Parametric Inference of Point Cloud Edges | Neurips 2020 | Paper Code |
![]() |
UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Tree | Neurips 2020 | Paper Code Project |
![]() |
ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds | ECCV 2020 | Paper Code Project |
![]() |
Supervised Fitting of Geometric Primitives to 3D Point Clouds | CVPR 2019 oral | Paper Code |
![]() |
CSGNet: Neural Shape Parser for Constructive Solid Geometry | CVPR 2018 | Paper Code |
| Preview | Title | Publication | Links |
|---|---|---|---|
![]() |
HiT: Hierarchical Transformers for Unsupervised 3D Shape Abstraction | 3DV 2026 | Paper Project |
![]() |
PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive Transformer | SIGGRAPH 2025 | Paper Code Project |
![]() |
ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modeling | NeurIPS 2025 | Paper Project |
![]() |
SuperDec: 3D Scene Decomposition with Superquadric Primitives | ICCV 2025 | Paper Code Project |
![]() |
Light-SQ: Structure-aware Shape Abstraction with Superquadrics for Generated Meshes | SIGGRAPH Asia 2025 | Paper Code |
![]() |
ShapeLib: Designing a library of procedural 3D shape abstractions with Large Language Models | arxiv 2025 | Paper |
![]() |
Improving Unsupervised Visual Program Inference with Code Rewriting Families | ICCV 2023 (oral) | Paper Code Project |
![]() |
SweepNet: Unsupervised Learning Shape Abstraction via Neural Sweepers | ECCV 2024 | Paper Code Project |
![]() |
ShapeMOD: Macro Operation Discovery for 3D Shape Programs | SIGGRAPH 2021 | Paper Code Project |
![]() |
Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image | CVPR 2020 | Paper Code |
![]() |
ShapeAssembly: Learning to Generate Programs for 3D Shape Structure Synthesis | SIGGRAPH Asia 2020 | Paper Code Project |
![]() |
Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids | CVPR 2019 | Paper Code Project |
![]() |
Im2Struct: Recovering 3D Shape Structure from a Single RGB Image | CVPR 2018 | Paper Code |
![]() |
Learning Shape Abstractions by Assembling Volumetric Primitives | CVPR 2017 | Paper Code Project |
| Preview | Title | Publication | Links |
|---|---|---|---|
![]() |
DeFillet: Detection and Removal of Fillet Regions in Polygonal CAD Models | Siggraph 2025 | Paper Code Project |
![]() |
QueryCAD: Grounded Question Answering for CAD Models | arxiv 2025 | Paper |
![]() |
BrepMFR: Enhancing machining feature recognition in B-rep models through deep learning and domain adaptation | CAGD 2024 | Paper Code |
![]() |
CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programs | CVPR 2024 | Paper Code Project |
![]() |
Robust Symmetry Detection via Riemannian Langevin Dynamics | SIGGRAPH Asia 2024 | Paper Code Project |
![]() |
FuS-GCN: Efficient B-rep based graph convolutional networks for 3D-CAD model classification and retrieval | AEI 2023 | Paper |
![]() |
GAT-CADNet: Graph Attention Network for Panoptic Symbol Spotting in CAD Drawings | CVPR 2022 | Paper Code |
![]() |
UV-Net: Learning from Boundary Representations | CVPR 2021 | Paper Code |
![]() |
BRepNet: A Topological Message Passing System for Solid Models | CVPR 2021 | Paper Code |
| Preview | Title | Publication | Links |
|---|---|---|---|
![]() |
B-repLer: Language-guided Editing of CAD Models | SIGGRAPH 2026 | Paper Code Project |
![]() |
CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing | arXiv 2025 | Paper |
![]() |
CAD-Estate: Large-scale CAD Model Annotation in RGB Videos | ICCV 2023 | Paper Code |
![]() |
ROCA: Robust CAD Model Retrieval and Alignment from a Single Image | CVPR 2022 | Paper Code Project |
![]() |
JoinABLe: Learning Bottom-up Assembly of Parametric CAD Joints | CVPR 2022 | Paper Code |
![]() |
SceneCAD: Predicting Object Alignments and Layouts in RGB-D Scans | ECCV 2020 | Paper Code |
![]() |
CAD-Deform: Deformable Fitting of CAD Models to 3D Scans | ECCV 2020 | Paper Code |
![]() |
End-to-End CAD Model Retrieval and 9DoF Alignment in 3D Scans | ICCV 2019 | Paper Project |
![]() |
Joint Embedding of 3D Scan and CAD Objects | ICCV 2019 | Paper Project |
![]() |
Scan2CAD: Learning CAD Model Alignment in RGB-D Scans | CVPR 2019 (Oral) | Paper Code Project |
| Preview | Title | Publication | Links |
|---|---|---|---|
![]() |
ArchCAD-400K: An Open Large-Scale Architectural CAD Dataset and New Baseline for Panoptic Symbol Spotting | NeurIPS 2025 | Paper Dataset |
![]() |
VideoCAD: A Dataset and Model for Learning Long-Horizon 3D CAD UI Interactions from Video | NeurIPS 2025 | Paper Code Project |
![]() |
HistCAD: Geometrically Constrained Parametric History-based CAD Dataset | arXiv 2026 | Paper |
![]() |
Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Construction from Human Design Sequences (Assembly Dataset) | CVPR 2022 | Paper Code Project |
![]() |
Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Construction from Human Design Sequences (Reconstruction Dataset) | SIGGRAPH 2021 | Paper Project |
![]() |
Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Construction from Human Design Sequences (Segmentation Dataset) | CVPR 2021 | Paper Project |
![]() |
DeepCAD: A Deep Generative Network for Computer-Aided Design Models | ICCV 2021 | Paper Code Project |
![]() |
ABC: A Big CAD Model Dataset For Geometric Deep Learning | CVPR 2019 | Paper Project |
![]() |
Slice-100K: A Multimodal Dataset for Extrusion-based 3D Printing | NeurIPS 2024 | Paper Code Project |








































































































































