Learning Compact CAD Shapes with Adaptive Primitive Assembly

AbstractWe introduce CAPRI-Net, a self-supervised neural net-work for learning compact and interpretable implicit representations of 3D computer-aided design (CAD) models, in the form of adaptive primitive assemblies. Given an input 3D shape, our network reconstructs it by an assembly of quadric surface primitives via constructive solid geometry (CSG) operations. Without any ground-truth shape assemblies, our self-supervised network is trained with a reconstruction loss, leading to faithful 3D reconstructions with sharp edges and plausible CSG trees. While the parametric nature of CAD models does make them more predictable locally, at the shape level, there is much structural and topological variation, which presents a significant generalizability challenge to state-of-the-art neural models for 3Dshapes. Our network addresses this challenge by adaptive training with respect to each test shape, with which we fine-tune the network that was pre-trained on a model collection. We evaluate our learning framework on both ShapeNet and ABC, the largest and most diverse CAD dataset to date, interms of reconstruction quality, sharp edges, compactness, and interpretability, to demonstrate superiority over current alternatives for neural CAD reconstruction.

Download publication

Related Resources



Mesh Processing

Computer representations of geometry are at the core of most problems…



3D User Interfaces: Human Experience in 3D Environments

Designing user interfaces for interacting with 3D data involves a…



Why is applying Artificial Intelligence in Construction so difficult?

While applying AI in construction can be challenging, Kasia Borowska…



Autodesk Research and DAISY AI at Greenbuild 2022

Learn how Autodesk Research and DAISY AI Inc recently showcased the…

Get in touch

Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.

Contact us