Spatially-Adaptive Learning-Based Image Compression with Hierarchical Multi-Scale Latent Spaces

Brand F, Kopte A, Fischer K, Kaup A (2023)

Publication Type: Conference contribution

Publication year: 2023

Publisher: IEEE

Conference Proceedings Title: 2023 IEEE International Conference on Image Processing (ICIP)

Event location: Kuala Lumpur

DOI: 10.1109/ICIP49359.2023.10222756

Abstract

Adaptive block partitioning is responsible for large gains in current image and video compression systems. This method is able to compress large stationary image areas with only a few symbols, while maintaining a high level of quality in more detailed areas. Current state-of-the-art neural-network-based image compression systems however use only one scale to transmit the latent space. In previous publications, we proposed RDONet, a scheme to transmit the latent space in multiple spatial resolutions. Following this principle, we extend a state-of-the-art compression network by a second hierarchical latent-space level to enable multi-scale processing. We extend the existing rate variability capabilities of RDONet by a gain unit. With that we are able to outperform an equivalent traditional autoencoder by 7% rate savings. Furthermore, we show that even though we add an additional latent space, the complexity only increases marginally and the decoding time can potentially even be decreased.

Authors with CRIS profile

How to cite

APA:

Brand, F., Kopte, A., Fischer, K., & Kaup, A. (2023). Spatially-Adaptive Learning-Based Image Compression with Hierarchical Multi-Scale Latent Spaces. In 2023 IEEE International Conference on Image Processing (ICIP). Kuala Lumpur, MY: IEEE.

MLA:

Brand, Fabian, et al. "Spatially-Adaptive Learning-Based Image Compression with Hierarchical Multi-Scale Latent Spaces." Proceedings of the 2023 IEEE International Conference on Image Processing, Kuala Lumpur IEEE, 2023.

BibTeX: Download