Non-Minimal Sampling and Consensus for Prohibitively Large Datasets

TL;DR

NONSAC is a flexible framework that enhances robustness and scalability in model estimation from large, noisy datasets by combining non-minimal sampling with hypothesis scoring, applicable to various geometric problems.

Contribution

It introduces a estimator-agnostic, scalable approach that integrates with existing algorithms like RANSAC, improving outlier robustness and enabling correspondence-free registration.

Findings

NONSAC improves robustness in camera pose estimation.

It effectively handles large datasets with high outlier ratios.

The framework is applicable to multiple geometric estimation tasks.

Abstract

We introduce NONSAC (Non-Minimal Sampling and Consensus), a general framework for robust and scalable model estimation from arbitrarily large datasets contaminated with noise and outliers. NONSAC repeatedly samples non-minimal subsets of data and generates model hypotheses using a robust estimator, producing multiple candidate models. The final model is selected based on a predefined scoring rule that evaluates hypothesis quality. Our framework is estimator-agnostic and can be integrated with existing geometric fitting algorithms such as RANSAC to improve both scalability and robustness to outliers. We propose and evaluate various scoring rules for NONSAC on relative camera pose estimation, Perspective-n-Point, and point cloud registration. Furthermore, we showcase the applicability of NONSAC to correspondence-free point cloud registration by hypothesizing all-to-all correspondences.