Scalable Cluster-Consistency Statistics for Robust Multi-Object Matching

TL;DR

This paper introduces scalable cluster-consistency statistics that improve robustness in multi-object matching by effectively filtering corrupted keypoints, enhancing accuracy and efficiency in structure from motion pipelines.

Contribution

The paper presents novel cluster-consistency based statistics and an iterative reweighting scheme for robust keypoint filtering in large-scale structure from motion tasks.

Findings

Achieves state-of-the-art accuracy in synthetic and real datasets

Demonstrates high efficiency and scalability for massive datasets

Outperforms existing filtering methods in robustness and speed

Abstract

We develop new statistics for robustly filtering corrupted keypoint matches in the structure from motion pipeline. The statistics are based on consistency constraints that arise within the clustered structure of the graph of keypoint matches. The statistics are designed to give smaller values to corrupted matches and than uncorrupted matches. These new statistics are combined with an iterative reweighting scheme to filter keypoints, which can then be fed into any standard structure from motion pipeline. This filtering method can be efficiently implemented and scaled to massive datasets as it only requires sparse matrix multiplication. We demonstrate the efficacy of this method on synthetic and real structure from motion datasets and show that it achieves state-of-the-art accuracy and speed in these tasks.