This paper outlines an end-to-end optimized lossy image compression framework using diffusion generative models. The approach relies on the transform coding paradigm, where an image is mapped into a latent space for entropy coding and, from there, mapped back to the data space for reconstruction. In contrast to VAE-based neural compression, where the (mean) decoder is a deterministic neural network, our decoder is a conditional diffusion model. Our approach thus introduces an additional ``content'' latent variable on which the reverse diffusion process is conditioned and uses this variable to store information about the image. The remaining ``texture'' variables characterizing the diffusion process are synthesized at decoding time. We show that the model's performance can be tuned toward perceptual metrics of interest. Our extensive experiments involving multiple datasets and image quality assessment metrics show that our approach yields stronger reported FID scores than the GAN-based model, while also yielding competitive performance with VAE-based models in several distortion metrics. Furthermore, training the diffusion with $\mathcal{X}$-parameterization enables high-quality reconstructions in only a handful of decoding steps, greatly affecting the model's practicality. Our code is available at: \url{https://github.com/buggyyang/CDC_compression}

翻译：本文提出了一种基于扩散生成模型的端到端优化有损图像压缩框架。该方法采用变换编码范式：将图像映射至潜在空间进行熵编码，再由此映射回数据空间以实现重建。与基于VAE的神经压缩方法（其均值解码器为确定性神经网络）不同，我们的解码器采用条件扩散模型。该方法引入了一个额外的“内容”潜变量，逆向扩散过程以此变量为条件，并通过该变量存储图像信息。描述扩散过程的其余“纹理”变量在解码阶段合成。研究表明，该模型的性能可根据目标感知指标进行调优。我们基于多数据集与图像质量评估指标的大规模实验表明：该方法在FID得分上优于基于GAN的模型，同时在多项失真指标上与基于VAE的模型表现相当。此外，采用$\mathcal{X}$参数化训练的扩散模型仅需少量解码步骤即可实现高质量重建，显著提升了模型的实用性。代码已开源：\url{https://github.com/buggyyang/CDC_compression}