Multi-way Particle Swarm Fusion

TL;DR

This paper introduces Swarm Fusion, a parallel MAP inference framework for MRFs that generalizes existing methods by allowing multi-way fusion among multiple solutions in multi-threaded environments.

Contribution

It presents a flexible, general framework for parallel MAP inference that unifies and extends several existing inference techniques.

Findings

Effective on stereo, optical flow, and layered depthmap estimation problems.

Outperforms competing methods in various problem settings.

Demonstrates scalability and flexibility of the proposed framework.

Abstract

This paper proposes a novel MAP inference framework for Markov Random Field (MRF) in parallel computing environments. The inference framework, dubbed Swarm Fusion, is a natural generalization of the Fusion Move method. Every thread (in a case of multi-threading environments) maintains and updates a solution. At each iteration, a thread can generate arbitrary number of solution proposals and take arbitrary number of concurrent solutions from the other threads to perform multi-way fusion in updating its solution. The framework is general, making popular existing inference techniques such as alpha-expansion, fusion move, parallel alpha-expansion, and hierarchical fusion, its special cases. We have evaluated the effectiveness of our approach against competing methods on three problems of varying difficulties, in particular, the stereo, the optical flow, and the layered depthmap estimation problems.