PerCo (SD): Open Perceptual Compression
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916415766790144 |
|---|---|
| author | Körber, Nikolai Kromer, Eduard Siebert, Andreas Hauke, Sascha Mueller-Gritschneder, Daniel Schuller, Björn |
| author_facet | Körber, Nikolai Kromer, Eduard Siebert, Andreas Hauke, Sascha Mueller-Gritschneder, Daniel Schuller, Björn |
| contents | 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 https://github.com/Nikolai10/PerCo. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_20255 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PerCo (SD): Open Perceptual Compression Körber, Nikolai Kromer, Eduard Siebert, Andreas Hauke, Sascha Mueller-Gritschneder, Daniel Schuller, Björn Computer Vision and Pattern Recognition 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 https://github.com/Nikolai10/PerCo. |
| title | PerCo (SD): Open Perceptual Compression |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.20255 |