Robust and Accurate Superquadric Recovery: a Probabilistic Approach
Authors:
Preprint
Abstract
Interpreting objects with basic geometric primitives has long been studied in computer vision. Among geometric primitives, superquadrics are well known for their ability to represent a wide range of shapes with few parameters. However, as the first and foremost step, recovering superquadrics accurately and robustly from 3D data still remains challenging. The existing methods are subject to local optima and sensitive to noise and outliers in real-world scenarios, resulting in frequent failure in capturing geometric shapes. In this paper, we propose the first probabilistic method to recover superquadrics from point clouds. Our method builds a Gaussian-uniform mixture model (GUM) on the parametric surface of a superquadric, which explicitly models the generation of outliers and noise. The superquadric recovery is formulated as a Maximum Likelihood Estimation (MLE) problem. We propose an algorithm, Expectation, Maximization, and Switching (EMS), to solve this problem, where: (1) outliers are predicted from the posterior perspective; (2) the superquadric parameter is optimized by the trust-region reflective algorithm; and (3) local optima are avoided by globally searching and switching among parameters encoding similar superquadrics. We show that our method can be extended to the multi-superquadrics recovery for complex objects. The proposed method outperforms the state-of-the-art in terms of accuracy, efficiency, and robustness on both synthetic and real-world datasets. The code is at http://github.com/bmlklwx/EMS-superquadric_fitting.git.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Closed-form Minkowski sums of convex bodies with smooth positively curved boundariesComputer-Aided Design, 2022
- Learning to Predict Superquadric Parameters From Depth Images With Explicit and Implicit SupervisionIEEE Access, 2020
- Revisiting Superquadric Fitting: A Numerically Stable FormulationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- The KIT object models database: An object model database for object recognition, localization and manipulation in service roboticsThe International Journal of Robotics Research, 2012
- Superquadrics for segmenting and modeling range dataIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997
- An Interior Trust Region Approach for Nonlinear Minimization Subject to BoundsSIAM Journal on Optimization, 1996
- Recovery of parametric models from range images: the case for superquadrics with global deformationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1990
- Recognition-by-components: A theory of human image understanding.Psychological Review, 1987
- Maximum Likelihood from Incomplete Data Via the EM AlgorithmJournal of the Royal Statistical Society Series B: Statistical Methodology, 1977
- A method for the solution of certain non-linear problems in least squaresQuarterly of Applied Mathematics, 1944