paper-with-me

홈 › Papers

MAGSAC: marginalizing sample consensus

2018-03-20 · CVPR 2019 6 · Daniel Barath, Jana Noskova, Jiri Matas

A method called, sigma-consensus, is proposed to eliminate the need for a user-defined inlier-outlier threshold in RANSAC. Instead of estimating the noise sigma, it is marginalized over a range of noise scales. The optimized model is obtained by weighted least-squares fitting where the weights come from the marginalization over sigma of the point likelihoods of being inliers. A new quality function is proposed not requiring sigma and, thus, a set of inliers to determine the model quality. Also, a new termination criterion for RANSAC is built on the proposed marginalization approach. Applying sigma-consensus, MAGSAC is proposed with no need for a user-defined sigma and improving the accuracy of robust estimation significantly. It is superior to the state-of-the-art in terms of geometric accuracy on publicly available real-world datasets for epipolar geometry (F and E) and homography estimation. In addition, applying sigma-consensus only once as a post-processing step to the RANSAC output always improved the model quality on a wide range of vision problems without noticeable deterioration in processing time, adding a few milliseconds. The source code is at https://github.com/danini/magsac.

📄 PDF Abstract BibTeX arXiv:1803.07469

Code (2)

danini/magsac 공식 구현
ducha-aiki/pymagsac

Tasks

Homography Estimation

Similar Papers 제목 키워드 기반

Adaptive Reordering Sampler with Neurally Guided MAGSAC

2021-11-28 · ICCV 2023 1 · Tong Wei, Jiri Matas, Daniel Barath

We propose a new sampler for robust estimators that always selects the sample with the highest probability of consisting only of inliers. After every unsuccessful iteration, the inlier probabilities are updated in a prin…

DS-SAC: Density Search for Sample Consensus

2026-07-04 · Suraj Thapa, Muhammad Aminul Islam arxiv

Robust geometric model estimation is a fundamental problem in computer vision. RANSAC and its variants remain widely used for this task; however, they rely on stochastic minimal sampling. In this article, we propose Dens…

MAGSAC++, a fast, reliable and accurate robust estimator

2019-12-11 · CVPR 2020 6 · Daniel Barath, Jana Noskova, Maksym Ivashechkin, Jiri Matas

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 it…

Learning To Find Good Models in RANSAC

2022-01-01 · CVPR 2022 1 · Daniel Barath, Luca Cavalli, Marc Pollefeys

We propose the Model Quality Network, MQ-Net in short, for predicting the quality, e.g. the pose error of essential matrices, of models generated inside RANSAC. It replaces the traditionally used scoring techniques, …

Pose Estimation

Two-View Geometry Scoring Without Correspondences

2023-06-02 · CVPR 2023 1 · Axel Barroso-Laguna, Eric Brachmann, Victor Adrian Prisacariu, Gabriel J. Brostow 외

Camera pose estimation for two-view geometry traditionally relies on RANSAC. Normally, a multitude of image correspondences leads to a pool of proposed hypotheses, which are then scored to find a winning model. The inlie…

Camera Pose EstimationPose Estimation