无需训练即可在压缩率、清晰度和感知质量间自由切换的扩散模型新方法。
Training-Free Rate-Distortion-Perception Traversal With Diffusion
- 用预训练扩散模型结合反向信道编码，实现无重训练的压缩路径遍历。
- 在多个数据集上验证，能灵活控制三者平衡，性能优于固定点压缩方法。
- 理论证明其在高斯噪声下最优，适合需要感知优化的自适应压缩场景。
率失真感知（RDP）权衡描述了有损压缩的基本极限，同时考虑比特率、重建保真度和感知质量。尽管近年来神经压缩方法提升了感知性能，但通常只能在RDP曲面上的固定点运行，需重新训练才能适配不同权衡。本文提出一种无需训练的框架，利用预训练扩散模型遍历整个RDP表面。方法结合反向信道编码（RCC）模块与新型得分缩放概率流常微分方程（ODE）解码器。理论上证明该扩散解码器在高斯白噪声（AWGN）观测下对失真-感知权衡最优，且整体框架在高斯情况下达到最优RDP函数。多数据集实证表明，该框架可借助预训练扩散模型有效导航三元RDP权衡，具备灵活性与高效性。结果建立了一种实用且理论完备的自适应感知压缩新范式。
原文摘要 · Abstract (English)
The rate-distortion-perception (RDP) tradeoff characterizes the fundamental limits of lossy compression by jointly considering bitrate, reconstruction fidelity, and perceptual quality. While recent neural compression methods have improved perceptual performance, they typically operate at fixed points on the RDP surface, requiring retraining to target different tradeoffs. In this work, we propose a training-free framework that leverages pre-trained diffusion models to traverse the entire RDP surface. Our approach integrates a reverse channel coding (RCC) module with a novel score-scaled probability flow ODE decoder. We theoretically prove that the proposed diffusion decoder is optimal for the distortion-perception tradeoff under AWGN observations and that the overall framework with the RCC module achieves the optimal RDP function in the Gaussian case. Empirical results across multiple datasets demonstrate the framework's flexibility and effectiveness in navigating the ternary RDP tradeoff using pre-trained diffusion models. Our results establish a practical and theoretically grounded approach to adaptive, perception-aware compression.
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。