Deep Iterative Surface Normal Estimation
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 11244-11253
Abstract
This paper presents an end-to-end differentiable algorithm for robust and detail-preserving surface normal estimation on unstructured point-clouds. We utilize graph neural networks to iteratively parameterize an adaptive anisotropic kernel that produces point weights for weighted least-squares plane fitting in local neighborhoods. The approach retains the interpretability and efficiency of traditional sequential plane fitting while benefiting from adaptation to data set statistics through deep learning. This results in a state-of-the-art surface normal estimator that is robust to noise, outliers and point density variation, preserves sharp features through anisotropic kernels and equivariance through a local quaternion-based spatial transformer. Contrary to previous deep learning methods, the proposed approach does not require any hand-crafted features or preprocessing. It improves on the state-of-the-art results while being more than two orders of magnitude faster and more parameter efficient.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- A Review of Point Cloud Registration Algorithms for Mobile RoboticsFoundations and Trends in Robotics, 2015
- Edge-aware point set resamplingACM Transactions on Graphics, 2013
- Fast and Robust Normal Estimation for Point Clouds with Sharp FeaturesComputer Graphics Forum, 2012
- Signing the Unsigned: Robust Surface Reconstruction from Raw PointsetsComputer Graphics Forum, 2010
- Collected Matrix Derivative Results for Forward and Reverse Mode Algorithmic Differentiation2008
- Algebraic point set surfacesACM Transactions on Graphics, 2007
- Estimating differential quantities using polynomial fitting of osculating jetsComputer Aided Geometric Design, 2005
- ESTIMATING SURFACE NORMALS IN NOISY POINT CLOUD DATAInternational Journal of Computational Geometry & Applications, 2004
- The approximation power of moving least-squaresMathematics of Computation, 1998
- Robust regression using iteratively reweighted least-squaresCommunications in Statistics - Theory and Methods, 1977