Imagine you have a magic painting that can transform into different shapes and sizes. Now, let’s say you have a special pair of glasses that can see things differently depending on the shape of the painting. Well, in the world of vision science, researchers have been studying how our brains process visual information under different image transformations. A recent study focuses on a model called the generalised Gaussian derivative model for visual receptive fields, which is like those special glasses for our brain! This model demonstrates ‘covariance properties’, meaning that it remains consistent even after transforming the input image in various ways. Just like our glasses can still see the transformed painting clearly, this model can perceive the visual world regardless of spatial scaling, spatial affine transformations, Galilean transformations, or temporal scaling. This has exciting implications for understanding how our brains handle the deformations of images and videos in real-life scenarios. The research also suggests that these covariance properties might be connected to the variabilities of spatial and spatio-temporal structures in natural images. If you’re curious to learn more about this fascinating research, check out the full article!

The property of covariance, also referred to as equivariance, means that an image operator is well-behaved under image transformations, in the sense that the result of applying the image operator to a transformed input image gives essentially a similar result as applying the same image transformation to the output of applying the image operator to the original image. This paper presents a theory of geometric covariance properties in vision, developed for a generalised Gaussian derivative model of receptive fields in the primary visual cortex and the lateral geniculate nucleus, which, in turn, enable geometric invariance properties at higher levels in the visual hierarchy. It is shown how the studied generalised Gaussian derivative model for visual receptive fields obeys true covariance properties under spatial scaling transformations, spatial affine transformations, Galilean transformations and temporal scaling transformations. These covariance properties imply that a vision system, based on image and video measurements in terms of the receptive fields according to the generalised Gaussian derivative model, can, to first order of approximation, handle the image and video deformations between multiple views of objects delimited by smooth surfaces, as well as between multiple views of spatio-temporal events, under varying relative motions between the objects and events in the world and the observer. We conclude by describing implications of the presented theory for biological vision, regarding connections between the variabilities of the shapes of biological visual receptive fields and the variabilities of spatial and spatio-temporal image structures under natural image transformations. Specifically, we formulate experimentally testable biological hypotheses as well as needs for measuring population statistics of receptive field characteristics, originating from predictions from the presented theory, concerning the extent to which the shapes of the biological receptive fields in the primary visual cortex span the variabilities of spatial and spatio-temporal image structures induced by natural image transformations, based on geometric covariance properties.

Read Full Article (External Site)