Accurate Motion Estimation through Random Sample Aggregated Consensus

TL;DR

This paper introduces RANSAAC, a novel framework that enhances motion estimation accuracy by aggregating multiple hypotheses generated by RANSAC, leading to significant performance improvements with minimal additional computation.

Contribution

The paper proposes RANSAAC, a new hypothesis aggregation method that systematically improves RANSAC's accuracy in 2D transformation estimation tasks.

Findings

RANSAAC outperforms RANSAC and variants in accuracy.

Aggregation of hypotheses yields significant performance gains.

Method maintains low computational overhead.

Abstract

We reconsider the classic problem of estimating accurately a 2D transformation from point matches between images containing outliers. RANSAC discriminates outliers by randomly generating minimalistic sampled hypotheses and verifying their consensus over the input data. Its response is based on the single hypothesis that obtained the largest inlier support. In this article we show that the resulting accuracy can be improved by aggregating all generated hypotheses. This yields RANSAAC, a framework that improves systematically over RANSAC and its state-of-the-art variants by statistically aggregating hypotheses. To this end, we introduce a simple strategy that allows to rapidly average 2D transformations, leading to an almost negligible extra computational cost. We give practical applications on projective transforms and homography+distortion models and demonstrate a significant performance gain in both cases.