🤖 AI Summary
This work addresses the overreliance on random sampling in robust geometric model estimation for computer vision by proposing a deterministic robust estimation framework. The method introduces, for the first time, deterministic dense-region search into the sample consensus paradigm, efficiently exploring high-consensus models through an initial-model-guided local forward-backward search combined with recursive partitioning based on signed residuals. This approach eliminates randomness while guaranteeing polynomial time complexity. Evaluated on homography, fundamental matrix, and essential matrix estimation tasks, the proposed method consistently outperforms mainstream approaches such as RANSAC and MAGSAC in terms of area under the cumulative error curve (AUC), median pose error, and computational speed.
📝 Abstract
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 Density Search Sample Consensus (DS-SAC), a deterministic robust estimation framework, that avoids repeated random sampling by searching dense regions. Starting from an initial model estimated from the available points, the method performs local exploration via forward and backward search. To facilitate global exploration, DS-SAC recursively partitions the point set using signed residuals and searches each valid partition for high-consensus models. We show that DS-SAC has polynomial complexity with respect to the number of points, making it an efficient alternative to stochastic consensus-based methods. Experiments on large-scale real-world datasets for homography, fundamental matrix, and essential matrix estimation show that DS-SAC achieves higher AUC scores, competitive or lower median pose errors, and faster runtime compared with widely used robust estimators, including RANSAC, MAGSAC, LO-RANSAC, and GC-RANSAC.