CoD：面向图像压缩的扩散基础模型
CoD: A Diffusion Foundation Model for Image Compression
CoD 提供了一个从零训练、面向压缩的扩散基础模型，可替代 Stable Diffusion 作为下游扩散编解码器的骨干，尤其在超低码率下提升压缩效率；其像素空间扩散实现 VTM 级 PSNR 与高感知质量的发现，为图像压缩与生成联合优化提供了新思路。
原文依据 we introduce CoD, the first Compression-oriented Diffusion foundation model, trained from scratch to enable end-to-end optimization of both compression and generation.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有的扩散编解码器通常构建在 Stable Diffusion 等文本到图像扩散基础模型之上。然而，从压缩的角度来看，文本条件并非最优，这阻碍了下游扩散编解码器的潜力，尤其是在超低码率下。为了解决这个问题，我们提出了 CoD，这是首个面向压缩的扩散基础模型，从头训练以实现压缩和生成的端到端优化。CoD 不是一个固定的编解码器，而是一个为各种基于扩散的编解码器设计的通用基础模型。它具有以下几个优势：高压缩效率，在 DiffC 等下游编解码器中用 CoD 替代 Stable Diffusion 可达到 SOTA 结果，尤其是在超低码率下（例如 0.0039 bpp）；低成本且可复现的训练，在完全开放的纯图像数据集上，训练速度比 Stable Diffusion 快 300 倍（20 对 6250 A100 GPU 天）；提供新的见解，例如我们发现像素空间扩散可以在高感知质量下达到 VTM 级峰值信噪比，并且可以使用更少的参数超越基于 GAN 的编解码器。我们希望 CoD 为未来的扩散编解码器研究奠定基础。代码已发布于 https://github.com/microsoft/GenCodec/tree/main/CoD。
英文原文摘要 1224 字符
Existing diffusion codecs typically build on text-to-image diffusion foundation models like Stable Diffusion.However, text conditioning is suboptimal from a compression perspective, hindering the potential of downstream diffusion codecs, particularly at ultra-low bitrates.To address it, we introduce CoD, the first Compression-oriented Diffusion foundation model, trained from scratch to enable end-to-end optimization of both compression and generation. CoD is not a fixed codec but a general foundation model designed for various diffusion-based codecs.It offers several advantages: High compression efficiency, replacing Stable Diffusion with CoD in downstream codecs like DiffC achieves SOTA results, especially at ultra-low bitrates (e.g., 0.0039 bpp); Low-cost and reproducible training, 300x faster training than Stable Diffusion ( 20 vs. 6,250 A100 GPU days) on entirely open image-only datasets; Providing new insights, e.g., We find pixel-space diffusion can achieve VTM-level PSNR with high perceptual quality and can outperform GAN-based codecs using fewer parameters.We hope CoD lays the foundation for future diffusion codec research. Codes are released at https://github.com/microsoft/GenCodec/tree/main/CoD.