CAPRI-Net

This work allows product designers to learn from a dataset of shapes to interpret and reconstruct the input 3D shape as a collection of adaptive primitives. This work is a step forward towards the open research problem of translating arbitrary input shapes into CAD models.

Abstract

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

Fenggen Yu, Zhiqin Chen, Manyi Li, Aditya Sanghi, Hooman Shayani, Ali Mahdavi-Amiri, Hao Zhang

IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2022

We 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.