Gromov-Wasserstein Distance based Object Matching: Asymptotic Inference

Understand

In this paper, we aim to provide a statistical theory for object matching based on the Gromov-Wasserstein distance.

• To this end, we model general objects as metric measure spaces.
• Based on this, we propose a simple and efficiently computable asymptotic statistical test for pose invariant object discrimination.
• This is based on an empirical version of a $\beta$-trimmed lower bound of the Gromov-Wasserstein distance.