mlsanityData to 7 Oct 2026

Active Diffusion Matching: Score-based Iterative Alignment of Cross-Modal Retinal Images

arXiv 2604.10084 ↗First posted 11 Apr 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Objective: The study aims to address the challenge of aligning Standard Fundus Images (SFIs) and Ultra-Widefield Fundus Images (UWFIs), which is difficult due to their substantial differences in viewing range and the amorphous appearance of the retina. Currently, no specialized method exists for this task, and existing image alignment techniques lack accuracy. Methods: We propose Active Diffusion Matching (ADM), a novel cross-modal alignment method. ADM integrates two interdependent score-based diffusion models to jointly estimate global transformations and local deformations via an iterative Langevin Markov chain. This approach facilitates a stochastic, progressive search for optimal alignment. Additionally, custom sampling strategies are introduced to enhance the adaptability of ADM to given input image pairs. Results: Comparative experimental evaluations demonstrate that ADM achieves state-of-the-art alignment accuracy. This was validated on two datasets: a private dataset of SFI-UWFI pairs and a public dataset of SFI-SFI pairs, with mAUC improvements of 5.2 and 0.4 points on the private and public datasets, respectively, compared to existing state-of-the-art methods. Conclusion: ADM effectively bridges the gap in aligning SFIs and UWFIs, providing an innovative solution to a previously unaddressed challenge. The method's ability to jointly optimize global and local alignment makes it highly effective for cross-modal image alignment tasks. Significance: ADM has the potential to transform the integrated analysis of SFIs and UWFIs, enabling better clinical utility and supporting learning-based image enhancements. This advancement could significantly improve diagnostic accuracy and patient outcomes in ophthalmology.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 49 of its 84 references that are in the map. First posted on arXiv 11 Apr 2026.

Builds on

49 of 84 references.

References · 49

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  7. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  8. 2022Scalable Diffusion Models with Transformerscited by 5,931
  9. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  10. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  11. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  12. 2023Consistency Modelscited by 1,778
37 more
  1. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  2. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  3. 2015Spatial Transformer Networkscited by 1,423
  4. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  5. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  6. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  7. 2021CvT: Introducing Convolutions to Vision Transformerscited by 946
  8. 2022On Distillation of Guided Diffusion Modelscited by 721
  9. 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 657
  10. 2023LightGlue: Local Feature Matching at Light Speedcited by 583
  11. 2018Learning to See in the Darkcited by 459
  12. 2021GMFlow: Learning Optical Flow via Global Matchingcited by 324
  13. 2022FlowFormer: A Transformer Architecture for Optical Flowcited by 273
  14. 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 206
  15. 2022DKM: Dense Kernelized Feature Matching for Geometry Estimationcited by 174
  16. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 170
  17. 2018A Deep Learning Framework for Unsupervised Affine and Deformable Image Registrationcited by 160
  18. 2018An Unsupervised Learning Model for Deformable Medical Image Registrationcited by 150
  19. 2023PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustmentcited by 146
  20. 2016Deep Image Homography Estimationcited by 135
  21. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 129
  22. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  23. 2018Weakly-Supervised Convolutional Neural Networks for Multimodal Image Registrationcited by 90
  24. 2024Understanding Hallucinations in Diffusion Models through Mode Interpolationcited by 87
  25. 2020CycleMorph: Cycle Consistent Unsupervised Deformable Image Registrationcited by 78
  26. 2019DeepAtlas: Joint Semi-Supervised Learning of Image Registration and Segmentationcited by 66
  27. 2021DiffuseMorph: Unsupervised Deformable Image Registration Using Diffusion Modelcited by 57
  28. 2022SparsePose: Sparse-View Camera Pose Regression and Refinementcited by 53
  29. 2024Tutorial on Diffusion Models for Imaging and Visioncited by 49
  30. 2022Iterative Deep Homography Estimationcited by 45
  31. 2021Deep Lucas-Kanade Homography for Multimodal Image Alignmentcited by 38
  32. 2019Image-and-Spatial Transformer Networks for Structure-Guided Image Registrationcited by 36
  33. 2019GLAMpoints: Greedily Learned Accurate Match pointscited by 30
  34. 2022Semi-Supervised Keypoint Detector and Descriptor for Retinal Image Matchingcited by 27
  35. 2024Progressive Retinal Image Registration via Global and Local Deformable Transformationscited by 6
  36. 2018Learning to Align Images using Weak Geometric Supervisioncited by 4
  37. 2024Medical Image Registration and Its Application in Retinal Images: A Reviewcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Particle Diffusion Matching: Random Walk Correspondence Search for the Alignment of Standard and Ultra-Widefield Fundus Images
  2. 2024RetinaRegNet: A Zero-Shot Approach for Retinal Image Registration
  3. 2026Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers
  4. 2026MaskAlign: Token-Subset Representation Alignment for Efficient Diffusion Training
  5. 2025IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance
  6. 2023Generating Realistic Counterfactuals for Retinal Fundus and OCT Images using Diffusion Models
  7. 2026FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs
  8. 2026DMAligner: Enhancing Image Alignment via Diffusion Model Based View Synthesis