Scale-Free Image Keypoints Using Differentiable Persistent Homology

Autor:	Barbarani, Giovanni, Vaccarino, Francesco, Trivigno, Gabriele, Guerra, Marco, Berton, Gabriele, Masone, Carlo
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning Mathematics - Algebraic Topology 55N31 I.2.10
Druh dokumentu:	Working Paper
Popis:	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 toward 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. Comment: Accepted to ICML 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2406.01315 Zobrazit plný text záznamu View this record from Arxiv