USACv20: robust essential, fundamental and homography matrix estimation

TL;DR

USACv20 is a new, modular, and optimized RANSAC-based algorithm that achieves state-of-the-art accuracy and speed in estimating essential, fundamental, and homography matrices across multiple datasets.

Contribution

It introduces USACv20, a modular and optimized framework combining recent RANSAC variants for improved robustness and efficiency in geometric model estimation.

Findings

USACv20 outperforms previous methods in accuracy.

USACv20 is the fastest among tested estimators.

Significant performance improvements over the original USAC.

Abstract

We review the most recent RANSAC-like hypothesize-and-verify robust estimators. The best performing ones are combined to create a state-of-the-art version of the Universal Sample Consensus (USAC) algorithm. A recent objective is to implement a modular and optimized framework, making future RANSAC modules easy to be included. The proposed method, USACv20, is tested on eight publicly available real-world datasets, estimating homographies, fundamental and essential matrices. On average, USACv20 leads to the most geometrically accurate models and it is the fastest in comparison to the state-of-the-art robust estimators. All reported properties improved performance of original USAC algorithm significantly. The pipeline will be made available after publication.