基于Stable Diffusion的开源图像压缩方法，低码率下更保真。
PerCo (SD): Open Perceptual Compression
- 用Stable Diffusion v2.1实现感知压缩，替代闭源模型。
- 在MSCOCO-30k上，低码率下感知质量优于原版PerCo。
- 代码与模型开源，适合研究感知压缩与扩散模型应用者。
我们提出PerCo (SD)，一种基于Stable Diffusion v2.1的感知图像压缩方法，针对超低比特率场景。PerCo (SD) 作为当前先进方法PerCo的开源且可竞争的替代方案，后者依赖闭源的GLIDE变体。本文回顾理论基础，分析将PerCo适配至Stable Diffusion生态的关键工程决策，并进行定量与定性综合对比。在MSCOCO-30k数据集上，PerCo (SD) 在更高失真代价下展现出更优的感知特性。我们部分归因于模型容量差异（866M vs. 1.4B）。期望本工作推动对底层机制的理解，并为该领域未来发展铺路。代码与训练模型将公开于https://github.com/Nikolai10/PerCo。
原文摘要 · Abstract (English)
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.
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。