PerCoV2实现超低码率图像压缩，保真度更高且完全开源。
PerCoV2: Improved Ultra-Low Bit-Rate Perceptual Image Compression with Implicit Hierarchical Masked Image Modeling
- 基于稳定扩散3生态，显式建模离散超隐变量分布提升编码效率。
- 在MSCOCO-30k上实现更低码率下更高图像保真度，感知质量保持领先。
- 支持混合生成模式进一步压缩码率，仅使用公开组件可复现。
我们提出PerCoV2，一种新型开放的超低码率感知图像压缩系统，适用于带宽与存储受限场景。基于Careil等人前期工作，PerCoV2将原方法扩展至Stable Diffusion 3生态系统，并通过显式建模离散超隐变量分布提升熵编码效率。为此，我们对比了最新的自回归方法（VAR与MaskGIT）在熵建模中的表现，并在大规模MSCOCO-30k基准上评估了该方法。相较于先前工作，PerCoV2（i）在更低码率下实现更高图像保真度，同时保持竞争力的感知质量；（ii）引入混合生成模式以进一步降低码率；（iii）仅依赖公开组件构建。代码与训练模型将于https://github.com/Nikolai10/PerCoV2发布。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。