Supervised Fitting of Geometric Primitives to 3D Point Clouds
Preprint
Abstract
Fitting geometric primitives to 3D point cloud data bridges a gap between low-level digitized 3D data and high-level structural information on the underlying 3D shapes. As such, it enables many downstream applications in 3D data processing. For a long time, RANSAC-based methods have been the gold standard for such primitive fitting problems, but they require careful per-input parameter tuning and thus do not scale well for large datasets with diverse shapes. In this work, we introduce Supervised Primitive Fitting Network (SPFN), an end-to-end neural network that can robustly detect a varying number of primitives at different scales without any user control. The network is supervised using ground truth primitive surfaces and primitive membership for the input points. Instead of directly predicting the primitives, our architecture first predicts per-point properties and then uses a differential model estimation module to compute the primitive type and parameters. We evaluate our approach on a novel benchmark of ANSI 3D mechanical component models and demonstrate a significant improvement over both the state-of-the-art RANSAC-based methods and the direct neural prediction.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Deep Fundamental Matrix Estimation2018
- Parsing Geometry Using Structure-Aware Shape Templates2018
- DSAC — Differentiable RANSAC for Camera Localization2017
- Learning Shape Abstractions by Assembling Volumetric Primitives2017
- Marr Revisited: 2D-3D Alignment via Surface Normal Prediction2016
- Matching with PROSAC — Progressive Sample Consensus2005
- Estimating differential quantities using polynomial fitting of osculating jetsComputer Aided Geometric Design, 2005
- MLESAC: A New Robust Estimator with Application to Estimating Image GeometryComputer Vision and Image Understanding, 2000
- Faithful least-squares fitting of spheres, cylinders, cones and tori for reliable segmentation1998
- Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography1987