Iterative Clustering with Game-Theoretic Matching for Robust Multi-consistency Correspondence

TL;DR

This paper introduces an end-to-end framework called ic-GTM that formulates multi-consistency feature matching as a clustering problem, effectively handling dynamic scenes with multiple consistent correspondences.

Contribution

The paper proposes a novel game-theoretic clustering approach for robust multi-consistency matching, extending beyond static scene assumptions and introducing new evaluation metrics.

Findings

Outperforms state-of-the-art methods on multi-consistency datasets

Effectively handles dynamic scenes with multiple correspondences

Provides new metrics for multi-consistency matching evaluation

Abstract

Matching corresponding features between two images is a fundamental task to computer vision with numerous applications in object recognition, robotics, and 3D reconstruction. Current state of the art in image feature matching has focused on establishing a single consistency in static scenes; by contrast, finding multiple consistencies in dynamic scenes has been under-researched. In this paper, we present an end-to-end optimization framework named "iterative clustering with Game-Theoretic Matching" (ic-GTM) for robust multi-consistency correspondence. The key idea is to formulate multi-consistency matching as a generalized clustering problem for an image pair. In our formulation, several local matching games are simultaneously carried out in different corresponding block pairs under the guidance of a novel payoff function consisting of both geometric and descriptive compatibility; the global matching results are further iteratively refined by clustering and thresholding with respect to a payoff matrix. We also propose three new metrics for evaluating the performance of multi-consistency image feature matching. Extensive experimental results have shown that the proposed framework significantly outperforms previous state-of-the-art approaches on both singleconsistency and multi-consistency datasets.