CADC：内容自适应的基于扩散的生成式图像压缩
CADC: Content Adaptive Diffusion-Based Generative Image Compression
把扩散先验用于极低码率图像压缩时，可用空间不确定性图驱动量化步长、并用轻量辅助解码器约束主潜变量通道的信息保留，这套「内容自适应量化+信息集中」思路可迁移到任何需要潜变量压缩的生成式编码流程。
原文依据 an Uncertainty-Guided Adaptive Quantization (UGAQ) method that learns spatial uncertainty maps to adaptively align quantization distortion with content characteristics
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于扩散的生成式图像压缩在超低码率下实现逼真重建方面已展现出显著潜力。释放这一潜力的关键在于使整个压缩过程具备内容自适应性，确保编码器的表示与解码器的生成先验能够与输入图像的语义和结构特征动态对齐。然而，现有方法存在三项关键局限，阻碍了有效的内容自适应。第一，各向同性量化采用统一的量化步长，无法适应图像内容在空间上的复杂度变化，并与扩散模型依赖噪声水平的先验产生错位。第二，信息集中瓶颈——源于高维含噪潜变量与扩散解码器固定输入之间的维度不匹配——使模型无法在主通道中自适应地保留关键语义信息。第三，现有的文本条件策略要么需要可观的文本码率开销，要么依赖通用的、与内容无关的文本提示，因而无法高效地提供自适应语义引导。为克服上述局限，我们提出一种内容自适应的基于扩散的图像编解码器（CADC），包含三项技术创新：1）不确定性引导的自适应量化（UGAQ）方法，学习空间不确定性图，使量化失真与内容特征自适应对齐；2）辅助解码器引导的信息集中（ADGIC）方法，利用轻量级辅助解码器在主潜变量通道中强制实现内容感知的信息保留；3）免码率的自适应文本条件（BFATC）方法，从辅助重建图像中导出内容感知的文本描述，从而在不增加码率开销的情况下提供语义引导。大量实验结果表明，我们的编解码器在超低码率下达到了最优的感知质量。
英文原文摘要 2056 字符
Diffusion-based generative image compression has demonstrated remarkable potential for achieving realistic reconstruction at ultra-low bitrates. The key to unlocking this potential lies in making the entire compression process content-adaptive, ensuring that the encoder's representation and the decoder's generative prior are dynamically aligned with the semantic and structural characteristics of the input image. However, existing methods suffer from three critical limitations that prevent effective content adaptation. First, isotropic quantization applies a uniform quantization step, failing to adapt to the spatially varying complexity of image content and creating a misalignment with the diffusion model's noise-dependent prior. Second, the information concentration bottleneck---arising from the dimensional mismatch between the high-dimensional noisy latent and the diffusion decoder's fixed input---prevents the model from adaptively preserving essential semantic information in the primary channels. Third, existing textual conditioning strategies either need significant textual bitrate overhead or rely on generic, content-agnostic textual prompts, thereby failing to provide adaptive semantic guidance efficiently. To overcome these limitations, we propose a content-adaptive diffusion-based image codec (CADC) with three technical innovations: 1) an Uncertainty-Guided Adaptive Quantization (UGAQ) method that learns spatial uncertainty maps to adaptively align quantization distortion with content characteristics; 2) an Auxiliary Decoder-Guided Information Concentration (ADGIC) method that uses a lightweight auxiliary decoder to enforce content-aware information preservation in the primary latent channels; and 3) a Bitrate-Free Adaptive Textual Conditioning (BFATC) method that derives content-aware textual descriptions from the auxiliary reconstructed image, enabling semantic guidance without bitrate cost. Comprehensive experimental results show that our codec achieves state-of-the-art perceptual quality at ultra-low bitrates.