col14m/cadrille
[ICLR2026] cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning
This project helps mechanical engineers, product designers, and researchers automatically convert various inputs into precise CAD models. You can feed it 3D scans (point clouds), images, or text descriptions of a design. It then generates the corresponding CadQuery code, which can be used to reconstruct a 3D CAD model.
110 stars.
Use this if you need to quickly generate parametric CAD models from existing visual data or textual specifications, speeding up your design and reverse engineering workflows.
Not ideal if you require hands-on, manual control over every geometric primitive and feature during the CAD modeling process.
Stars
110
Forks
16
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 01, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/col14m/cadrille"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
filaPro/cad-recode
[ICCV2025] CAD-Recode: Reverse Engineering CAD Code from Point Clouds
pengsongyou/openscene
[CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies
worldbench/3EED
[NeurIPS 2025 DB Track] 3EED: Ground Everything Everywhere in 3D
cambrian-mllm/cambrian-s
Cambrian-S: Towards Spatial Supersensing in Video
Gorilla-Lab-SCUT/PaDT
[ICLR 2026] Official implementation of "Patch-as-Decodable-Token: Towards Unified Multi-Modal...