Brummer, Benoit
[UCL]
De Vleeschouwer, Christophe
[UCL]
Convolutional autoencoders are now at the forefront of image compression research. To improve their entropy coding, encoder output is typically analyzed with a second autoencoder to generate per-variable parametrized prior probability distributions. We instead propose a compression scheme that uses a single convolutional autoencoder and multiple learned prior distributions working as a competition of experts. Trained prior distributions are stored in a static table of cumulative distribution functions. During inference, this table is used by an entropy coder as a look-up-table to determine the best prior for each spatial location. Our method offers rate-distortion performance comparable to that obtained with a predicted parametrized prior with only a fraction of its entropy coding and decoding complexity.
Bibliographic reference |
Brummer, Benoit ; De Vleeschouwer, Christophe. End-to-end optimized image compression with competition of prior distributions.2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (Nashville, TN, USA, du 19/6/2021 au 25/6/2021). In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Vol. 1, no.1, p. 1890-1894 (2021) |
Permanent URL |
http://hdl.handle.net/2078.1/253437 |