MAGSAC++, a fast, reliable and accurate robust estimator
This work addresses robust estimation problems in computer vision, such as image matching and 3D reconstruction, with incremental improvements over existing methods.
The paper tackled robust estimation in computer vision by proposing MAGSAC++, which introduces a new model quality function without inlier-outlier decisions and a Progressive NAPSAC sampler, resulting in faster, more accurate, and more reliable performance on homography and fundamental matrix fitting across six datasets.
A new method for robust estimation, MAGSAC++, is proposed. It introduces a new model quality (scoring) function that does not require the inlier-outlier decision, and a novel marginalization procedure formulated as an iteratively re-weighted least-squares approach. We also propose a new sampler, Progressive NAPSAC, for RANSAC-like robust estimators. Exploiting the fact that nearby points often originate from the same model in real-world data, it finds local structures earlier than global samplers. The progressive transition from local to global sampling does not suffer from the weaknesses of purely localized samplers. On six publicly available real-world datasets for homography and fundamental matrix fitting, MAGSAC++ produces results superior to state-of-the-art robust methods. It is faster, more geometrically accurate and fails less often.