PerCo (SD): Open Perceptual Compression.
Autoren |
Nikolai Körber |
|---|---|
Medien | Workshop on Machine Learning and Compression, Advances in Neural Information Processing Systems 37 (NeurIPS 2024) |
Veröffentlichungsjahr | 2024 |
Band | 2024 |
Seiten | 1-20 |
Veröffentlichungsart | Sonstige Veröffentlichungen |
Forschungsprojekt | KIEBITZ |
Zitierung | Körber, Nikolai; Kromer, Eduard; Siebert, Andreas; Hauke, Sascha; Mueller-Gritschneder, Daniel; Schuller, Björn (2024): PerCo (SD): Open Perceptual Compression.. Workshop on Machine Learning and Compression, Advances in Neural Information Processing Systems 37 (NeurIPS 2024) 2024, S. 1-20. |
Peer Reviewed | Ja |
PerCo (SD): Open Perceptual Compression.
Abstract
We introduce PerCo (SD), a perceptual image compression method based on Stable Diffusion v2.1, targeting the ultra-low bit range. PerCo (SD) serves as an open and competitive alternative to the state-of-the-art method PerCo, which relies on a proprietary variant of GLIDE and remains closed to the public. In this work, we review the theoretical foundations, discuss key engineering decisions in adapting PerCo to the Stable Diffusion ecosystem, and provide a comprehensive comparison, both quantitatively and qualitatively. On the MSCOCO-30k dataset, PerCo (SD) demonstrates improved perceptual characteristics at the cost of higher distortion. We partly attribute this gap to the different model capacities being used (866M vs. 1.4B). We hope our work contributes to a deeper understanding of the underlying mechanisms and paves the way for future advancements in the field. Code and trained models will be released at github.com/Nikolai10/PerCo.