Compact Latent Representation for Image Compression (CLRIC)
Ameen AA, Richter T, Kaup A (2025)
Publication Type: Conference contribution
Publication year: 2025
Journal
Publisher: IEEE Computer Society
Pages Range: 349-354
Conference Proceedings Title: Proceedings - International Conference on Image Processing, ICIP
Event location: Anchorage, AK, USA
ISBN: 9798331523794
DOI: 10.1109/ICIP55913.2025.11084424
Abstract
—Current image compression models often require separate models for each quality level, making them resource-intensive in terms of both training and storage. To address these limitations, we propose an innovative approach that utilizes latent variables from pre-existing trained models (such as the Stable Diffusion Variational Autoencoder) for perceptual image compression. Our method eliminates the need for distinct models dedicated to different quality levels. We employ overfitted learnable functions to compress the latent representation from the target model at any desired quality level. These overfitted functions operate in the latent space, ensuring low computational complexity, around 25.5 MAC/pixel for a forward pass on images with dimensions (1363 × 2048) pixels. This approach efficiently utilizes resources during both training and decoding. Our method achieves comparable perceptual quality to state-of-the-art learned image compression models while being both model-agnostic and resolution-agnostic. This opens up new possibilities for the development of innovative image compression methods.
Authors with CRIS profile
Involved external institutions
Germany (DE)How to cite
APA:
Ameen, A.A., Richter, T., & Kaup, A. (2025). Compact Latent Representation for Image Compression (CLRIC). In Proceedings - International Conference on Image Processing, ICIP (pp. 349-354). Anchorage, AK, USA: IEEE Computer Society.
MLA:
Ameen, Ayman A., Thomas Richter, and André Kaup. "Compact Latent Representation for Image Compression (CLRIC)." Proceedings of the 32nd IEEE International Conference on Image Processing, ICIP 2025, Anchorage, AK, USA IEEE Computer Society, 2025. 349-354.
BibTeX: Download