Quantum Motion Segmentation

TL;DR

This paper presents a novel quantum algorithm for motion segmentation, leveraging adiabatic quantum optimization to identify independent motions in images, matching state-of-the-art performance on suitable problem instances.

Contribution

It introduces the first quantum-based approach for motion segmentation, utilizing adiabatic quantum optimization to solve the problem efficiently.

Findings

Achieves comparable performance to classical methods on certain instances.

Demonstrates feasibility of quantum algorithms for motion segmentation.

Maps problem instances effectively to quantum annealers.

Abstract

Motion segmentation is a challenging problem that seeks to identify independent motions in two or several input images. This paper introduces the first algorithm for motion segmentation that relies on adiabatic quantum optimization of the objective function. The proposed method achieves on-par performance with the state of the art on problem instances which can be mapped to modern quantum annealers.