Skip to yearly menu bar Skip to main content


Poster

Scale-Free Image Keypoints Using Differentiable Persistent Homology

Giovanni Barbarani · Francesco Vaccarino · Gabriele Trivigno · Marco Guerra · Gabriele Berton · Carlo Masone

Hall C 4-9 #102
[ ] [ Paper PDF ]
Wed 24 Jul 2:30 a.m. PDT — 4 a.m. PDT

Abstract:

In computer vision, keypoint detection is a fundamental task, with applications spanning from robotics to image retrieval; however, existing learning-based methods suffer from scale dependency, and lack flexibility. This paper introduces a novel approach that leverages Morse theory and persistent homology, powerful tools rooted in algebraic topology. We propose a novel loss function based on the recent introduction of a notion of subgradient in persistent homology, paving the way towards topological learning. Our detector, MorseDet, is the first topology-based learning model for feature detection, which achieves competitive performance in keypoint repeatability and introduces a principled and theoretically robust approach to the problem.

Chat is not available.