mlsanityData to 7 Oct 2026

Blind Strong Gravitational Lensing Inversion: Joint Inference of Source and Lens Mass with Score-Based Models

arXiv 2511.04792 ↗First posted 6 Nov 2025astro-ph.IM astro-ph.CO cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Score-based models can serve as expressive, data-driven priors for scientific inverse problems. In strong gravitational lensing, they enable posterior inference of a background galaxy from its distorted, multiply-imaged observation. Previous work, however, assumes that the lens mass distribution (and thus the forward operator) is known. We relax this assumption by jointly inferring the source and a parametric lens-mass profile, using a sampler based on GibbsDDRM but operating in continuous time. The resulting reconstructions yield residuals consistent with the observational noise, and the marginal posteriors of the lens parameters recover true values without systematic bias. To our knowledge, this is the first successful demonstration of joint source-and-lens inference with a score-based prior.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 26 of its 61 references that are in the map. First posted on arXiv 6 Nov 2025.

Builds on

26 of 61 references.

References · 26

  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. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  5. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  6. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  7. 2022Denoising Diffusion Restoration Modelscited by 951
  8. 2018Pyro: Deep Universal Probabilistic Programmingcited by 379
  9. 2022Diffusion models as plug-and-play priorscited by 230
  10. 2023Score-Based Diffusion Models as Principled Priors for Inverse Imagingcited by 126
  11. 2022Parallel Diffusion Models of Operator and Image for Blind Inverse Problemscited by 113
  12. 2024Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priorscited by 93
14 more
  1. 2025InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciencescited by 67
  2. 2023GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restorationcited by 58
  3. 2023Sampling-Based Accuracy Testing of Posterior Estimators for General Inferencecited by 45
  4. 2023Fast Diffusion EM: a diffusion model for blind inverse problems with application to deconvolutioncited by 36
  5. 2024Blind Image Restoration via Fast Diffusion Inversioncited by 29
  6. 2022Posterior samples of source galaxies in strong gravitational lenses with score-based priorscited by 20
  7. 2023Variational Bayesian Imaging with an Efficient Surrogate Score-based Priorcited by 16
  8. 2025Stochastic Forward-Backward Deconvolution: Training Diffusion Models with Finite Noisy Datasetscited by 11
  9. 2024PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass Estimationcited by 8
  10. 2024Tackling the Problem of Distributional Shifts: Correcting Misspecified, High-Dimensional Data-Driven Priors for Inverse Problemscited by 5
  11. 2023Diffusion Models for Probabilistic Deconvolution of Galaxy Imagescited by 4
  12. 2025IRIS: A Bayesian Approach for Image Reconstruction in Radio Interferometry with expressive Score-Based priorscited by 3
  13. 2023Echoes in the Noise: Posterior Samples of Faint Galaxy Surface Brightness Profiles with Score-Based Likelihoods and Priorscited by 2
  14. 2025Provable Mixed-Noise Learning with Flow-Matchingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Mapping Dark-Matter Clusters via Physics-Guided Diffusion Modelscited by 1
  2. 2026ShuffleFlow: Scalable Posterior Inference for Bayesian Inverse Imagingcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Strong Gravitational Lensing Posterior Sampling in Pixel-Space Using Diffusion Models and Recurrent Inference Machines
  2. 2026Generative Diffusion Priors for 3D Mapping of the Dark Universe
  3. 2024Flow Matching for Posterior Inference with Simulator Feedback
  4. 2025FlowLensing: Simulating Gravitational Lensing with Flow Matching
  5. 2024Bayesian Deconvolution of Astronomical Images with Diffusion Models: Quantifying Prior-Driven Features in Reconstructions
  6. 2025Null-Space Diffusion Distillation Unlocks Speed, Fidelity and Realism in Lensless Imaging
  7. 2025A Data-Driven Prism: Multi-View Source Separation with Diffusion Model Priors
  8. 2024Using Galaxy Evolution as Source of Physics-Based Ground Truth for Generative Models