mlsanityData to 7 Oct 2026

Score-based diffusion priors for multi-target detection

arXiv 2312.08500 ↗First posted 13 Dec 2023eess.SPcited by 1

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

Multi-target detection (MTD) is the problem of estimating an image from a large, noisy measurement that contains randomly translated and rotated copies of the image. Motivated by the single-particle cryo-electron microscopy technology, we design data-driven diffusion priors for the MTD problem, derived from score-based stochastic differential equations models. We then integrate the prior into the approximate expectation-maximization algorithm. In particular, our method alternates between an expectation step that approximates the expected log-likelihood and a maximization step that balances the approximated log-likelihood with the learned log-prior. We show on two datasets that adding the data-driven prior substantially reduces the estimation error, in particular in high noise regimes.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 18 of its 40 references that are in the map. First posted on arXiv 13 Dec 2023.

Builds on

18 of 40 references.

References · 18

  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. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  8. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 348
  9. 2021SegDiff: Image Segmentation with Diffusion Probabilistic Modelscited by 279
  10. 2016A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluationcited by 236
  11. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 195
  12. 2016Fundamental Limits in Multi-image Alignmentcited by 6
6 more
  1. 2019Image recovery from rotational and translational invariantscited by 3
  2. 2019Multi-target Detection with an Arbitrary Spacing Distributioncited by 2
  3. 2021Two-dimensional multi-target detection: an autocorrelation analysis approachcited by 2
  4. 2023Expectation-maximization for structure determination directly from cryo-EM micrographscited by 2
  5. 2021Multi-target detection with rotationscited by 1
  6. 2021An approximate expectation-maximization for two-dimensional multi-target detectioncited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Solving ill-conditioned polynomial equations using score-based priors with application to multi-target detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Score-Based Diffusion Models as Principled Priors for Inverse Imaging
  2. 2024Learning Diffusion Model from Noisy Measurement using Principled Expectation-Maximization Method
  3. 2025Diffusion Reconstruction-based Data Likelihood Estimation for Core-Set Selection
  4. 2024Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction
  5. 2023Variational Bayesian Imaging with an Efficient Surrogate Score-based Prior
  6. 2023Diffusion Models With Learned Adaptive Noise
  7. 2023Score-based Diffusion Models for Bayesian Image Reconstruction
  8. 2026Diffusion Path Samplers via Sequential Monte Carlo