EB-RANSAC: Random Sample Consensus based on Energy-Based Model

TL;DR

EB-RANSAC introduces an energy-based model that simplifies robust estimation by eliminating complex sampling procedures, requiring only one hyperparameter, and demonstrating effectiveness in linear regression and maximum likelihood estimation.

Contribution

This paper proposes EB-RANSAC, a novel energy-based model for robust estimation that simplifies the process and broadens applicability compared to traditional RANSAC.

Findings

Effective in linear regression tasks

Successful in maximum likelihood estimation

Requires only one hyperparameter

Abstract

Random sample consensus (RANSAC), which is based on a repetitive sampling from a given dataset, is one of the most popular robust estimation methods. In this study, an energy-based model (EBM) for robust estimation that has a similar scheme to RANSAC, energy-based RANSAC (EB-RANSAC), is proposed. EB-RANSAC is applicable to a wide range of estimation problems similar to RANSAC. However, unlike RANSAC, EB-RANSAC does not require a troublesome sampling procedure and has only one hyperparameter. The effectiveness of EB-RANSAC is numerically demonstrated in two applications: a linear regression and maximum likelihood estimation.