Multi-way Particle Swarm Fusion
This work addresses inference efficiency in computer vision for researchers and practitioners, but it is incremental as it builds on established techniques like fusion move.
The paper tackles the problem of MAP inference for Markov Random Fields in parallel computing by proposing Swarm Fusion, a framework that generalizes existing methods like alpha-expansion and fusion move, and demonstrates its effectiveness on stereo, optical flow, and layered depthmap estimation tasks.
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.