MAGSAC++, a Fast, Reliable and Accurate Robust Estimator

By Daniel Barath, Jana Noskova, Maksym Ivashechkin, Jiri Matas. Computer Vision and Pattern Recognition, 2019

363 citations recorded by the source corpus.

We propose MAGSAC++ and Progressive NAPSAC sampler, P-NAPSAC in short. In MAGSAC++, we replace the model quality and polishing functions of the original method by an iteratively re-weighted least-squares fitting with weights determined via marginalizing over the noise scale. MAGSAC++ is fast -- often an order of magnitude faster -- and more geometrically accurate than MAGSAC. P-NAPSAC merges the advantages of local and global sampling by drawing samples from gradually growing neighborhoods. Exploiting that nearby points are more likely to originate from the same geometric model, P-NAPSAC finds local structures earlier than global samplers. We show that the progressive spatial sampling in P-NAPSAC can be integrated with PROSAC sampling, which is applied to the first, location-defining, point. The methods are tested on homography and fundamental matrix fitting on six publicly available datasets. MAGSAC combined with P-NAPSAC sampler is superior to state-of-the-art robust estimators in terms of speed, accuracy and failure rate.

View Paper: https://www.semanticscholar.org/paper/69bcc03ff0ae7559bd29df88f4d47ce76795300b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Xingyu Jiang
2. Jiayi Ma
3. Junjun Jiang
4. Aoxiang Fan
5. Junchi Yan
6. Hui Li
7. Zixiang Zhao
8. Xingchen Zhang

Citations in the corpus

• RoMa: Robust Dense Feature Matching (2023, unknown): “All methods use MAGSAC++ [2] as implemented in OpenCV.”
• Image Matching from Handcrafted to Deep Features: A Survey (2020, methodology): “Based on above two methods, they introducedMAGSAC++ (Barath et al. 2020) with a new scoring function.”