AI 中文总结
研究提出在全波形反演（FWI）中用预训练扩散模型作正则化器，比较三种引导策略，通过多种实验表明分裂吉布斯扩散采样（SGDS）能提升重建质量，扩散引导优化可作实用正则化策略并保留波动方程建模循环。
AI 中文摘要
我们展示了一项扩散引导的全波形反演（FWI）研究，其中预训练的扩散生成模型在偏微分方程约束的地震反演循环中用作学习正则化器。我们比较了三种无需训练的引导策略：流形保持引导扩散（MPGD）、基于SDEdit的初始化以及分裂吉布斯扩散采样（SGDS），后者在FWI似然更新和扩散先验去噪之间交替。所提出的工作流程在反演循环中保留波动方程建模，并使用地质先验来稳定受地震数据约束较弱的模型组件。可控的GeoFWI实验、基准规模的Marmousi和逆掩断层测试、困难的Sigsbee2A盐丘测试以及噪声退化研究表明，在干净和中等噪声的合成设置中，SGDS相对于传统的L2和总变差正则化FWI提高了重建质量。总体而言，这些实验表明扩散引导优化可以作为合成FWI基准的实用学习正则化策略，同时保留波动方程建模循环。
英文摘要
We present a diffusion-guided full waveform inversion (FWI) study in which pretrained diffusion generative models are used as learned regularizers inside a PDE-constrained seismic inversion loop. We compare three training-free guidance strategies: Manifold-Preserving Guided Diffusion (MPGD), SDEdit-based initialization, and Split Gibbs Diffusion Sampling (SGDS), which alternates between FWI likelihood updates and diffusion-prior denoising. The proposed workflow keeps wave-equation modeling in the inversion loop and uses a geological prior to stabilize model components that are weakly constrained by the seismic data. Controlled GeoFWI experiments, benchmark-scale Marmousi and Overthrust tests, a difficult Sigsbee2A salt test, and noise-degradation studies show that SGDS improves reconstruction quality relative to conventional L2 and total-variation regularized FWI in clean and moderately noisy synthetic settings. Overall, these experiments demonstrate that diffusion-guided optimization can serve as a practical learned regularization strategy for synthetic FWI benchmarks while preserving the wave-equation modeling loop.
Comments32 pages, 16 figures. Source code: https://github.com/shenyiran91/SGDS-FWI
