June 11, 2024, 4:50 a.m. | Thomas Dag\`es, Michael Lindenbaum, Alfred M. Bruckstein

cs.CV updates on arXiv.org arxiv.org

arXiv:2406.05400v1 Announce Type: new
Abstract: Standard convolutions are prevalent in image processing and deep learning, but their fixed kernel design limits adaptability. Several deformation strategies of the reference kernel grid have been proposed. Yet, they lack a unified theoretical framework. By returning to a metric perspective for images, now seen as two-dimensional manifolds equipped with notions of local and geodesic distances, either symmetric (Riemannian metrics) or not (Finsler metrics), we provide a unifying principle: the kernel positions are samples of …

abstract adaptability arxiv cs.cv deep learning design framework grid image image processing images kernel math.dg perspective processing reference standard strategies theory type

Senior Data Engineer

@ Displate | Warsaw

Automation and AI Strategist (Remote - US)

@ MSD | USA - New Jersey - Rahway

Assistant Manager - Prognostics Development

@ Bosch Group | Bengaluru, India

Analytics Engineer - Data Solutions

@ MSD | IND - Maharashtra - Pune (Wework)

Jr. Data Engineer (temporary)

@ MSD | COL - Cundinamarca - Bogotá (Colpatria)

Senior Data Engineer

@ KION Group | Atlanta, GA, United States