https://github.com/Nikolai10/PerCoV2
PerCoV2: Improved Ultra-Low Bit-Rate Perceptual Image Compression with Implicit Hierarchical Masked Image Modeling
https://github.com/Nikolai10/PerCoV2
Last synced: 3 months ago
JSON representation
PerCoV2: Improved Ultra-Low Bit-Rate Perceptual Image Compression with Implicit Hierarchical Masked Image Modeling
- Host: GitHub
- URL: https://github.com/Nikolai10/PerCoV2
- Owner: Nikolai10
- Created: 2025-03-12T13:22:32.000Z (4 months ago)
- Default Branch: master
- Last Pushed: 2025-03-13T10:00:06.000Z (4 months ago)
- Last Synced: 2025-03-13T11:19:33.048Z (4 months ago)
- Homepage: https://arxiv.org/abs/2503.09368
- Size: 479 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-diffusion-categorized - [Code
README
# PerCoV2 (PyTorch)
> **PerCoV2: Improved Ultra-Low Bit-Rate Perceptual Image Compression with Implicit Hierarchical Masked Image Modeling**
> Nikolai Körber, Eduard Kromer, Andreas Siebert, Sascha Hauke, Daniel Mueller-Gritschneder, Björn Schuller
> ArXiv 2503.09368
## Abstract
We introduce PerCoV2, a novel and open ultra-low bit-rate perceptual image compression system designed for bandwidth- and storage-constrained applications. Building upon prior work by Careil et al., PerCoV2 extends the original formulation to the Stable Diffusion 3 ecosystem and enhances entropy coding efficiency by explicitly modeling the discrete hyper-latent image distribution. To this end, we conduct a comprehensive comparison of recent autoregressive methods (VAR and MaskGIT) for entropy modeling and evaluate our approach on the large-scale MSCOCO-30k benchmark. Compared to previous work, PerCoV2 (i) achieves higher image fidelity at even lower bit-rates while maintaining competitive perceptual quality, (ii) features a hybrid generation mode for further bit-rate savings, and (iii) is built solely on public components. Code and trained models will be released at [https://github.com/Nikolai10/PerCoV2](https://github.com/Nikolai10/PerCoV2).
