VSAC: Efficient and Accurate Estimator for H and F

TL;DR

VSAC is a fast, robust estimator for two-view geometry that introduces independent inliers and optimized local processing, achieving high accuracy with significantly reduced computation time.

Contribution

It introduces the concept of independent inliers and improves local optimization, leading to a faster and equally accurate estimator compared to state-of-the-art methods.

Findings

Runs in 1-2 ms on CPU

Two orders of magnitude faster than MAGSAC++

Never failed in repeated tests on multiple datasets

Abstract

We present VSAC, a RANSAC-type robust estimator with a number of novelties. It benefits from the introduction of the concept of independent inliers that improves significantly the efficacy of the dominant plane handling and, also, allows near error-free rejection of incorrect models, without false positives. The local optimization process and its application is improved so that it is run on average only once. Further technical improvements include adaptive sequential hypothesis verification and efficient model estimation via Gaussian elimination. Experiments on four standard datasets show that VSAC is significantly faster than all its predecessors and runs on average in 1-2 ms, on a CPU. It is two orders of magnitude faster and yet as precise as MAGSAC++, the currently most accurate estimator of two-view geometry. In the repeated runs on EVD, HPatches, PhotoTourism, and Kusvod2 datasets, it never failed.