mlsanityData to 7 Oct 2026

Robust Physics-Guided Diffusion for Full-Waveform Inversion

arXiv 2603.16393 ↗First posted 17 Mar 2026math.NA cs.AI cs.NAcited by 3

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

We develop a robust physics-guided diffusion framework for full-waveform inversion that combines a score-based generative prior with likelihood guidance computed through wave-equation simulations. We adopt a transport-based data-consistency potential (Wasserstein-2), incorporating wavefield enhancement via bounded weighting and observation-dependent normalization, thereby improving robustness to amplitude imbalance and time/phase misalignment. On the inference side, we introduce a preconditioned guided reverse-diffusion scheme that adapts the guidance strength and spatial scaling throughout the reverse-time dynamics, yielding a more stable and effective data-consistency guidance step than standard diffusion posterior sampling (DPS). Numerical experiments on OpenFWI datasets demonstrate improved reconstruction quality over deterministic optimization baselines and standard DPS under comparable computational budgets.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 10 of its 48 references that are in the map. First posted on arXiv 17 Mar 2026.

Builds on

10 of 48 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Controllable seismic velocity synthesis using generative diffusion models9 Feb

Other references · 9

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  5. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  6. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 514
  7. 2018Stochastic seismic waveform inversion using generative adversarial networks as a geological priorcited by 47
  8. 2021OpenFWI: Large-Scale Multi-Structural Benchmark Datasets for Seismic Full Waveform Inversioncited by 44
  9. 2020Optimal Transport Based Seismic Inversion: Beyond Cycle Skippingcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Decoupled Latent Optimization of Diffusion Models for Full Waveform Inversioncited by 2
  2. 2026Physical-State-Guided Diffusion Sampling for Full-Waveform Inversioncited by 0
  3. 2026Geometry-Aware Diffusion Guidance via Curvature-Adaptive Tubular Correctioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Diffusion prior as a direct regularization term for FWI
  2. 2025Diffusion Model-Based Posterior Sampling in Full Waveform Inversion
  3. 2026HarmoCore: Functional Latent Diffusion for Sparse Reconstruction of Oscillatory Wave Fields
  4. 2024Back-Projection Diffusion: Solving the Wideband Inverse Scattering Problem with Diffusion Models
  5. 2025Acoustic Waveform Inversion with Image-to-Image Schr"odinger Bridges
  6. 2023A prior regularized full waveform inversion using generative diffusion models
  7. 2024Geological and Well prior assisted full waveform inversion using conditional diffusion models
  8. 2026Posterior Continuation with Noise-Conditioned Frequency Exposure for Diffusion Inverse Problems