mlsanityData to 14 Oct 2026

Test-Time Adaptation in Optical Coherence Tomography Using Trajectory-Aligned Time-Independent Flow

arXiv 2606.18876 ↗First posted 17 Jun 2026cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Optical coherence tomography (OCT) is essential in ophthalmology, but inconsistent image quality especially in low-cost devices hinders automated analysis. To address this, we introduce a flow-matching-based test-time adaptation method that generates high-quality surrogate images from noisy inputs. Typically, domain gaps between test and training data cause pixel distribution mismatches during the denoising process. We overcome this by matching the test image's histogram to synthetic reference trajectories, successfully aligning the input with expected distributions. Additionally, we remove the network's time conditioning to account for slight deviations in real-world noise distributions. Our approach achieves state-of-the-art performance in segmenting critical biomarkers for two stages of Age-related Macular Degeneration (AMD). Code is available: https://github.com/Veit21/tta-flow.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 26 references that are in the map. First posted on arXiv 17 Jun 2026.

Builds on

18 of 26 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2022Flow Matching for Generative Modelingcited by 5,702
  5. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,525
  6. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  7. 2022Continual Test-Time Domain Adaptationcited by 525
  8. 2022Medical Image Segmentation Review: The success of U-Netcited by 191
  9. 2024PnP-Flow: Plug-and-Play Image Restoration with Flow Matchingcited by 97
  10. 2022Back to the Source: Diffusion-Driven Test-Time Adaptationcited by 71
  11. 2025Is Noise Conditioning Necessary for Denoising Generative Models?cited by 44
  12. 2025Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Qualitycited by 25
6 more
  1. 2023Content-Preserving Diffusion Model for Unsupervised AS-OCT image Despecklingcited by 5
  2. 2023Self-supervised learning via inter-modal reconstruction and feature projection networks for label-efficient 3D-to-2D segmentationcited by 5
  3. 2023From Question to Exploration: Test-Time Adaptation in Semantic Segmentation?cited by 5
  4. 2024Joint semi-supervised and contrastive learning enables domain generalization and multi-domain segmentationcited by 4
  5. 2025Exploring Structured Semantic Priors Underlying Diffusion Score for Test-time Adaptationcited by 2
  6. 2026Exploiting Intermediate Reconstructions in Optical Coherence Tomography for Test-Time Adaption of Medical Image Segmentationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Retinal OCT Synthesis with Denoising Diffusion Probabilistic Models for Layer Segmentation
  2. 2023Leveraging Complementary Attention maps in vision transformers for OCT image analysis
  3. 2022Unsupervised Denoising of Retinal OCT with Diffusion Probabilistic Model
  4. 2025GARD: Gamma-based Anatomical Restoration and Denoising for Retinal OCT
  5. 2024Denoising OCT Images Using Steered Mixture of Experts with Multi-Model Inference
  6. 2024Memory-efficient High-resolution OCT Volume Synthesis with Cascaded Amortized Latent Diffusion Models
  7. 2024Conditioning 3D Diffusion Models with 2D Images: Towards Standardized OCT Volumes through En Face-Informed Super-Resolution
  8. 2026Super-Resolution and Denoising of Corneal B-Scan OCT Imaging Using Diffusion Model Plug-and-Play Priors