Mode-Seeking on Hypergraphs for Robust Geometric Model Fitting

TL;DR

This paper introduces Mode-Seeking on Hypergraphs (MSH), a robust geometric model fitting method that effectively detects multiple structures in data with outliers by formulating the problem as mode seeking on a hypergraph.

Contribution

The paper presents a novel hypergraph-based mode seeking algorithm for geometric model fitting, incorporating a similarity measure and weight-aware sampling for improved robustness and scalability.

Findings

MSH outperforms state-of-the-art methods on synthetic data.

MSH effectively handles multi-structure data with severe outliers.

The method is scalable to large datasets.

Abstract

In this paper, we propose a novel geometric model fitting method, called Mode-Seeking on Hypergraphs (MSH),to deal with multi-structure data even in the presence of severe outliers. The proposed method formulates geometric model fitting as a mode seeking problem on a hypergraph in which vertices represent model hypotheses and hyperedges denote data points. MSH intuitively detects model instances by a simple and effective mode seeking algorithm. In addition to the mode seeking algorithm, MSH includes a similarity measure between vertices on the hypergraph and a weight-aware sampling technique. The proposed method not only alleviates sensitivity to the data distribution, but also is scalable to large scale problems. Experimental results further demonstrate that the proposed method has significant superiority over the state-of-the-art fitting methods on both synthetic data and real images.