Animating Still Images


We present a means of developing digital image transformations that allow a still image to be turned into a short and visually pleasing animation. Rather than manually augmenting successive frames to create the illusion of motion, the method presented here requires only the input of a few parameters for each transformation. We developed a mathematical framework wherein we defined animations as sequences of still images, and “transformations” as composable functions on such sequences.

To implement this work, we have built a MATLAB library of composable functions that streamline the process of turning still images into novel animations. Examples include manipulation of contrast, intensity, and colors of pixels, as well as warps of contours, positions, and size of select regions. The transformations allow for easy animation of regions of interest, giving some semblance of life to still images by turning them into animated GIFs.

Baltimore, Maryland

This talk was presented in the MAA Contributed Papers Session: At the Intersection of Mathematics and the Arts, as well as during a poster session.

Michael Pilosov
Resident of Denver, CO and several Cloud Providers
see all