Linearly Transformed Color Guide for Low-Bitrate Diffusion-Based Image Compression
IEEE Transactions on Image Processing · 2025 · 34 · 468-482
DOI: 10.1109/tip.2024.3521301 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Tom Bordin und 1 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: French National Research Agency.
Abstract (Originalsprache)
This study addresses the challenge of controlling the global color aspect of images generated by a diffusion model without training or fine-tuning. We rewrite the guidance equations to ensure that the outputs are closer to a known color map, without compromising the quality of the generation. Our method results in new guidance equations. In the context of color guidance, we show that the scaling of the guidance should not decrease but rather increase throughout the diffusion process. In a second contribution, our guidance is applied in a compression framework, where we combine both semantic and general color information of the image to decode at low cost. We show that our method is effective in improving the fidelity and realism of compressed images at extremely low bit rates (10-2bpp), performing better on these criteria when compared to other classical or more semantically oriented approaches. The implementation of our method is available on gitlab1.
Förderung
- French National Research Agency
Zitieren
APA
Bordin, T., & Maugey, T. (2025). Linearly Transformed Color Guide for Low-Bitrate Diffusion-Based Image Compression. IEEE Transactions on Image Processing, 34, 468-482. https://doi.org/10.1109/tip.2024.3521301
Vancouver
Bordin T, Maugey T. Linearly Transformed Color Guide for Low-Bitrate Diffusion-Based Image Compression. IEEE Transactions on Image Processing. 2025;34:468-482. doi:10.1109/tip.2024.3521301
BibTeX
@article{Bordin2025,
author = {Bordin, Tom and Maugey, Thomas},
title = {Linearly Transformed Color Guide for Low-Bitrate Diffusion-Based Image Compression},
journal = {IEEE Transactions on Image Processing},
year = {2025},
volume = {34},
pages = {468--482},
doi = {10.1109/tip.2024.3521301}
}
EUVIMED