Bridging the Gap between Gaussian Diffusion Models and Universal Quantization for Image Compression
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913775408381952 |
|---|---|
| author | Relic, Lucas Azevedo, Roberto Zhang, Yang Gross, Markus Schroers, Christopher |
| author_facet | Relic, Lucas Azevedo, Roberto Zhang, Yang Gross, Markus Schroers, Christopher |
| contents | Generative neural image compression supports data representation at extremely low bitrate, synthesizing details at the client and consistently producing highly realistic images. By leveraging the similarities between quantization error and additive noise, diffusion-based generative image compression codecs can be built using a latent diffusion model to "denoise" the artifacts introduced by quantization. However, we identify three critical gaps in previous approaches following this paradigm (namely, the noise level, noise type, and discretization gaps) that result in the quantized data falling out of the data distribution known by the diffusion model. In this work, we propose a novel quantization-based forward diffusion process with theoretical foundations that tackles all three aforementioned gaps. We achieve this through universal quantization with a carefully tailored quantization schedule and a diffusion model trained with uniform noise. Compared to previous work, our proposal produces consistently realistic and detailed reconstructions, even at very low bitrates. In such a regime, we achieve the best rate-distortion-realism performance, outperforming previous related works. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_02579 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bridging the Gap between Gaussian Diffusion Models and Universal Quantization for Image Compression Relic, Lucas Azevedo, Roberto Zhang, Yang Gross, Markus Schroers, Christopher Image and Video Processing Generative neural image compression supports data representation at extremely low bitrate, synthesizing details at the client and consistently producing highly realistic images. By leveraging the similarities between quantization error and additive noise, diffusion-based generative image compression codecs can be built using a latent diffusion model to "denoise" the artifacts introduced by quantization. However, we identify three critical gaps in previous approaches following this paradigm (namely, the noise level, noise type, and discretization gaps) that result in the quantized data falling out of the data distribution known by the diffusion model. In this work, we propose a novel quantization-based forward diffusion process with theoretical foundations that tackles all three aforementioned gaps. We achieve this through universal quantization with a carefully tailored quantization schedule and a diffusion model trained with uniform noise. Compared to previous work, our proposal produces consistently realistic and detailed reconstructions, even at very low bitrates. In such a regime, we achieve the best rate-distortion-realism performance, outperforming previous related works. |
| title | Bridging the Gap between Gaussian Diffusion Models and Universal Quantization for Image Compression |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2504.02579 |