A Spatiotemporal Decomposition of a Video Stream Based on the Retina-Inspired Filter

The goal of this work is to propose a simple yet efficient way to dynamically transform a video stream according to the functional properties of the visual system. To achieve this goal, we extend to video sequences the Retina-Inspired Filter (RIF), which we have recently proposed for still images. Under the assumption that the input signal remains constant for a given time, the RIF decomposition was proven to be in-vertible, meaning that the image could be perfectly recovered. In this paper, we relax this assumption into a piece-wise constant input and analytically prove that the RIF can be applied to a group of pictures (GOP). We experimentally show that the size of GOP is important when motion appears, as some artifacts are generated. However, in the absence of motion among the GOP frames we can still perfectly reconstruct the video frames reducing the computational cost of the whole process.