Joint covariance properties under geometric image transformations for spatio-temporal receptive fields according to the generalized Gaussian derivative model for visual receptive fields

arXiv:2311.10543v4 Announce Type: replace
Abstract: The influence of natural image transformations on receptive field responses is crucial for modelling visual operations in computer vision and biological vision. In this regard, covariance properties with respect to geometric image transformations in the earliest layers of the visual hierarchy are essential for expressing robust image operations, and for formulating invariant visual operations at higher levels.
This paper defines and proves a set of joint covariance properties under compositions of spatial scaling transformations, spatial …

abstract arxiv computer computer vision covariance cs.cv fields generalized image influence modelling natural operations q-bio.nc regard responses temporal type vision visual