CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assembly

TL;DR

CAPRI-Net is a neural network that learns to reconstruct 3D CAD models as compact assemblies of primitives, using adaptive training and self-supervision, achieving high-quality, interpretable results without ground-truth assemblies.

Contribution

It introduces a novel adaptive training approach for neural CAD reconstruction that handles structural variations and produces interpretable primitive assemblies.

Findings

Achieves faithful 3D reconstructions with sharp edges.

Outperforms existing methods on ShapeNet and ABC datasets.

Produces compact and interpretable CSG trees.

Abstract

We introduce CAPRI-Net, a neural network for learning compact and interpretable implicit representations of 3D computer-aided design (CAD) models, in the form of adaptive primitive assemblies. Our network takes an input 3D shape that can be provided as a point cloud or voxel grids, and reconstructs it by a compact assembly of quadric surface primitives via constructive solid geometry (CSG) operations. The network is self-supervised with a reconstruction loss, leading to faithful 3D reconstructions with sharp edges and plausible CSG trees, without any ground-truth shape assemblies. While the parametric nature of CAD models does make them more predictable locally, at the shape level, there is a great deal of structural and topological variations, which present a significant generalizability challenge to state-of-the-art neural models for 3D shapes. 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, in terms of reconstruction quality, shape edges, compactness, and interpretability, to demonstrate superiority over current alternatives suitable for neural CAD reconstruction.