ESSP: An Efficient Approach to Minimizing Dense and Nonsubmodular Energy Functions

TL;DR

This paper introduces ESSP, an efficient method for optimizing dense, nonsubmodular binary MRFs in computer vision, outperforming existing techniques in energy minimization tasks.

Contribution

The paper presents a novel optimization approach, ESSP, capable of handling arbitrary pairwise potentials, including dense and nonsubmodular energies, with superior performance.

Findings

ESSP achieves lower energy solutions than existing methods.

The approach is efficient and suitable for dense, nonsubmodular energies.

Combining methods yields best results in different scenarios.

Abstract

Many recent advances in computer vision have demonstrated the impressive power of dense and nonsubmodular energy functions in solving visual labeling problems. However, minimizing such energies is challenging. None of existing techniques (such as s-t graph cut, QPBO, BP and TRW-S) can individually do this well. In this paper, we present an efficient method, namely ESSP, to optimize binary MRFs with arbitrary pairwise potentials, which could be nonsubmodular and with dense connectivity. We also provide a comparative study of our approach and several recent promising methods. From our study, we make some reasonable recommendations of combining existing methods that perform the best in different situations for this challenging problem. Experimental results validate that for dense and nonsubmodular energy functions, the proposed approach can usually obtain lower energies than the best combination of other techniques using comparably reasonable time.