Rate-Distortion Optimized Learning-Based Image Compression using an Adaptive Hierachical Autoencoder with Conditional Hyperprior

Brand F, Fischer K, Kaup A (2021)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2021

Pages Range: 1-5

Event location: Virtual US

DOI: 10.1109/cvprw53098.2021.00211

Abstract

Deep-learning-based compressive autoencoders consist of a single non-linear function mapping the image to a latent space which is quantized and transmitted. Afterwards, a second non-linear function transforms the received latent space back to a reconstructed image. This method achieves superior quality than many traditional image coders, which is due to a non-linear generalization of linear transforms used in traditional coders. However, modern image and video coder achieve large coding gains by applying rate-distortion optimization on dynamic block-partitioning. In this paper, we present RDONet, a novel approach to achieve similar effects in compression with full image autoencoders by using different hierarchical levels, which are transmitted adaptively after performing an external rate-distortion optimization. Using our model, we are able to save up to 20% rate over comparable non-hierarchical models while maintaining the same quality.

Authors with CRIS profile

Fabian Brand Lehrstuhl für Multimediakommunikation und Signalverarbeitung Kristian Fischer Lehrstuhl für Multimediakommunikation und Signalverarbeitung Andre Kaup Lehrstuhl für Multimediakommunikation und Signalverarbeitung

How to cite

APA:

Brand, F., Fischer, K., & Kaup, A. (2021). Rate-Distortion Optimized Learning-Based Image Compression using an Adaptive Hierachical Autoencoder with Conditional Hyperprior. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (pp. 1-5). Virtual, US.

MLA:

Brand, Fabian, Kristian Fischer, and André Kaup. "Rate-Distortion Optimized Learning-Based Image Compression using an Adaptive Hierachical Autoencoder with Conditional Hyperprior." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Virtual 2021. 1-5.

BibTeX: Download