用预训练扩散模型实现快速图像有损压缩，无需额外训练。
Lossy Compression with Pretrained Diffusion Models
- 利用预训练扩散模型直接做压缩，跳过传统编码瓶颈。
- 在低于10秒内完成压缩解压，低比特率下表现媲美顶尖方法。
- 适合追求高速、低资源图像压缩的研究与应用者。
我们将DiffC算法（Theis等，2022）应用于Stable Diffusion 1.5、2.1、XL和Flux-dev，证明这些预训练模型具备出色的图像有损压缩能力。尽管自Ho等（2020）起已有理论框架，但反向通道编码难题长期阻碍其实现。本文提出简单解决方案，首次完整实现DiffC，可在10秒内完成图像压缩与解压。该方法无需额外训练，在超低比特率下仍可达到当前先进生成式压缩方法的性能水平。
原文摘要 · Abstract (English)
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.
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。