无需重训练扩散模型，实时自适应调整采样权重提升图像重建质量
Automated Tuning for Diffusion Inverse Problem Solvers without Generative Prior Retraining
- 测试时优化噪声调度下的数据保真度权重
- 在fastMRI膝关节数据集上超越传统与扩散方法
- 适用于任意采样节奏，无需额外训练
扩散/基于得分的模型近期被用作求解反问题的强大生成先验，如加速MRI重建。尽管其灵活性实现了测量模型与学习先验的解耦，但性能高度依赖于精心调校的数据保真度权重，尤其在快速采样（少去噪步骤）时更为敏感。现有方法多依赖启发式或固定权重，难以在不同测量条件和非规则时间步调度下泛化。本文提出零样本自适应扩散采样（ZADS），一种测试时优化方法，可在不重训练扩散先验的前提下，自适应调整任意噪声调度下的保真度权重。ZADS将去噪过程视为固定展开的采样器，仅使用欠采样测量值进行自监督优化。在fastMRI膝关节数据集上的实验表明，ZADS始终优于传统压缩感知及近期扩散方法，在多种噪声调度与采集设置下均能实现高保真重建。
原文摘要 · Abstract (English)
Diffusion/score-based models have recently emerged as powerful generative priors for solving inverse problems, including accelerated MRI reconstruction. While their flexibility allows decoupling the measurement model from the learned prior, their performance heavily depends on carefully tuned data fidelity weights, especially under fast sampling schedules with few denoising steps. Existing approaches often rely on heuristics or fixed weights, which fail to generalize across varying measurement conditions and irregular timestep schedules. In this work, we propose Zero-shot Adaptive Diffusion Sampling (ZADS), a test-time optimization method that adaptively tunes fidelity weights across arbitrary noise schedules without requiring retraining of the diffusion prior. ZADS treats the denoising process as a fixed unrolled sampler and optimizes fidelity weights in a self-supervised manner using only undersampled measurements. Experiments on the fastMRI knee dataset demonstrate that ZADS consistently outperforms both traditional compressed sensing and recent diffusion-based methods, showcasing its ability to deliver high-fidelity reconstructions across varying noise schedules and acquisition settings.
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。