Monte-Carlo Convolutions on Foveated Images

Killick, G., Aragon-Camarasa, G. and Siebert, J. P. (2022) Monte-Carlo Convolutions on Foveated Images. In: Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4 VISAPP, 6-8 February 2022, pp. 444-451. ISBN 9789897585555 (doi: 10.5220/0010832400003124)

[img] Text
259770.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.



Foveated vision captures a visual scene at space-variant resolution. This makes the application of parameterized convolutions to foveated images difficult as they do not have a dense-grid representation in cartesian space. Log-polar space is frequently used to create a dense grid representation of foveated images, however this image representation may not be appropriate for all applications. In this paper we rephrase the convolution operation as the Monte-Carlo estimation of the filter response of the foveated image and a continuous filter kernel, an idea that has seen frequent use for deep learning on point clouds. We subsume our convolution operation into a simple CNN architecture that processes foveated images in cartesian space. We evaluate our system in the context of image classification and show that our approach significantly outperforms an equivalent CNN processing a foveated image in log-polar space.

Item Type:Conference Proceedings
Glasgow Author(s) Enlighten ID:Siebert, Dr Paul and Aragon Camarasa, Dr Gerardo and Killick, George
Authors: Killick, G., Aragon-Camarasa, G., and Siebert, J. P.
College/School:College of Science and Engineering > School of Computing Science
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record