Lossy Compression with Pretrained Diffusion Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915106940518400 |
|---|---|
| author | Vonderfecht, Jeremy Liu, Feng |
| author_facet | Vonderfecht, Jeremy Liu, Feng |
| contents | We apply the DiffC algorithm (Theis et al. 2022) to Stable Diffusion 1.5, 2.1, XL, and Flux-dev, and demonstrate that these pretrained models are remarkably capable lossy image compressors. A principled algorithm for lossy compression using pretrained diffusion models has been understood since at least Ho et al. 2020, but challenges in reverse-channel coding have prevented such algorithms from ever being fully implemented. We introduce simple workarounds that lead to the first complete implementation of DiffC, which is capable of compressing and decompressing images using Stable Diffusion in under 10 seconds. Despite requiring no additional training, our method is competitive with other state-of-the-art generative compression methods at low ultra-low bitrates. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_09815 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Lossy Compression with Pretrained Diffusion Models Vonderfecht, Jeremy Liu, Feng Computer Vision and Pattern Recognition Image and Video Processing We apply the DiffC algorithm (Theis et al. 2022) to Stable Diffusion 1.5, 2.1, XL, and Flux-dev, and demonstrate that these pretrained models are remarkably capable lossy image compressors. A principled algorithm for lossy compression using pretrained diffusion models has been understood since at least Ho et al. 2020, but challenges in reverse-channel coding have prevented such algorithms from ever being fully implemented. We introduce simple workarounds that lead to the first complete implementation of DiffC, which is capable of compressing and decompressing images using Stable Diffusion in under 10 seconds. Despite requiring no additional training, our method is competitive with other state-of-the-art generative compression methods at low ultra-low bitrates. |
| title | Lossy Compression with Pretrained Diffusion Models |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2501.09815 |