提出可自适应调节的模块，提升扩散模型在图像修复中的表现。
SAIP: A Plug-and-Play Scale-adaptive Module in Diffusion-based Inverse Problems
- 通过动态调整先验与似然项的权重平衡，实现无需重训练的自适应优化
- 在多种图像修复任务中显著提升重建质量，尤其在复杂场景下表现优异
- 即插即用设计，兼容现有扩散采样器，适合图像恢复研究者使用
基于扩散模型求解逆问题在图像修复等任务中展现出潜力。通常采用贝叶斯框架，通过结合先验得分与似然得分来从后验分布采样。由于似然项难以直接计算，常用估计方法如DPS、DMPS和πGDM。但这些方法依赖固定且人工调优的尺度来平衡先验与似然贡献，而这种静态设计在不同时间步和任务中均不理想，限制了性能与泛化能力。为此，本文提出SAIP——一个无需重训练或修改扩散主干即可在每一步自适应调节尺度的即插即用模块。SAIP可无缝集成至现有采样器，在多种图像修复任务中持续提升重建质量，包括挑战性场景。
原文摘要 · Abstract (English)
Solving inverse problems with diffusion models has shown promise in tasks such as image restoration. A common approach is to formulate the problem in a Bayesian framework and sample from the posterior by combining the prior score with the likelihood score. Since the likelihood term is often intractable, estimators like DPS, DMPS, and $π$GDM are widely adopted. However, these methods rely on a fixed, manually tuned scale to balance prior and likelihood contributions. Such a static design is suboptimal, as the ideal balance varies across timesteps and tasks, limiting performance and generalization. To address this issue, we propose SAIP, a plug-and-play module that adaptively refines the scale at each timestep without retraining or altering the diffusion backbone. SAIP integrates seamlessly into existing samplers and consistently improves reconstruction quality across diverse image restoration tasks, including challenging scenarios.
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。