Less Biased Noise Scale Estimation for Threshold-Robust RANSAC
This addresses a practical issue for computer vision researchers and practitioners using RANSAC for robust pose estimation, but it is incremental as it builds on existing noise scale estimation methods.
The paper tackles the problem of automatically determining the optimal inlier threshold for RANSAC in image matching, which is typically set manually and difficult to tune without ground truth. The result is a method that fixes biases in noise scale estimation and extends it with multi-pair filtering, yielding robust performance across thresholds.
The gold-standard for robustly estimating relative pose through image matching is RANSAC. While RANSAC is powerful, it requires setting the inlier threshold that determines whether the error of a correspondence under an estimated model is sufficiently small to be included in its consensus set. Setting this threshold is typically done by hand, and is difficult to tune without an access to ground truth data. Thus, a method capable of automatically determining the optimal threshold would be desirable. In this paper we revisit inlier noise scale estimation, which is an attractive approach as the inlier noise scale is linear to the optimal threshold. We revisit the noise scale estimation method SIMFIT and find bias in the estimate of the noise scale. In particular, we fix underestimates from using the same data for fitting the model as estimating the inlier noise, and from not taking the threshold itself into account. Secondly, since the optimal threshold within a scene is approximately constant we propose a multi-pair extension of SIMFIT++, by filtering of estimates, which improves results. Our approach yields robust performance across a range of thresholds, shown in Figure 1. Code is available at https://github.com/Parskatt/simfitpp