CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assembly
Authors:
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 11758-11768
Abstract
We introduce CAPRI-Net, a self-supervised neural network 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 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, sharp edges, compactness, and interpretability, to demonstrate superiority over current alternatives for neural CAD reconstruction.Keywords
All Related Versions
Funding Information
- NSERC (611370)
This publication has 40 references indexed in Scilit:
- GRASSACM Transactions on Graphics, 2017
- Learning Shape Abstractions by Assembling Volumetric Primitives2017
- GlobFitACM Transactions on Graphics, 2011
- Characterizing structural relationships in scenes using graph kernels2011
- The 3D Hough Transform for plane detection in point clouds: A review and a new accumulator design3D Research, 2011
- Efficient RANSAC for Point‐Cloud Shape DetectionComputer Graphics Forum, 2007
- On Visual Similarity Based 3D Model RetrievalComputer Graphics Forum, 2003
- Reconstruction and representation of 3D objects with radial basis functions2001
- Surface reconstruction from unorganized points1992
- Random sample consensusCommunications of the ACM, 1981