rundiwu/DeepCAD
code for our ICCV 2021 paper "DeepCAD: A Deep Generative Network for Computer-Aided Design Models"
This project helps product designers and mechanical engineers generate new, unique 3D CAD models. By feeding in existing CAD designs (like Onshape JSON files or vectorized representations), it can learn their characteristics and then produce entirely new CAD sequences, which can be exported as standard .step files for use in any modern CAD software. The ideal user is someone involved in conceptual design, exploring variations, or automating parts of the design process.
706 stars. No commits in the last 6 months.
Use this if you need to rapidly explore a wide range of novel 3D CAD model variations or generate new designs that align with patterns learned from your existing design database.
Not ideal if you need to modify existing CAD models directly, perform precise engineering simulations, or if you don't have access to an NVIDIA GPU and Linux environment.
Stars
706
Forks
142
Language
Python
License
MIT
Category
Last pushed
Apr 12, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/rundiwu/DeepCAD"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
XingangPan/GAN2Shape
Code for GAN2Shape (ICLR2021 oral)
ayaanzhaque/instruct-nerf2nerf
Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions (ICCV 2023)
compphoto/Intrinsic
Repo for the papers "Intrinsic Image Decomposition via Ordinal Shading" (TOG 2023) and "Colorful...
mworchel/differentiable-shadow-mapping
Differentiable Shadow Mapping for Efficient Inverse Graphics (CVPR 2023)
cgtuebingen/SIGNeRF
SIGNeRF: Scene Integrated Generation for Neural Radiance Fields