full-waveform-inversion

This paper applies Flow Matching, a generative AI technique, to probabilistic inversion for seismic full-waveform inversion, demonstrating its effectiveness on synthetic datasets.

Introduces Decoupled Latent Optimization (DLO) for full waveform inversion, which relaxes latent optimization into a quadratic-penalty objective, outperforming classical and diffusion-based methods on benchmarks while preserving smoothed-velocity initialization.