# DINOv3 with Test-Time Training for Medical Image Registration

arXiv: https://arxiv.org/abs/2508.14809 · HTML: https://mlsanity.com/paper/2508.14809/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 20 Aug 2025.

## Builds on (most cited first, 12 of 12)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [VoxelMorph: A Learning Framework for Deformable Medical Image Registration](https://mlsanity.com/paper/1809.05231/) (2018)
- [Learn2Reg: comprehensive multi-task medical image registration challenge, dataset and evaluation in the era of deep learning](https://mlsanity.com/paper/2112.04489/) (2021)
- [A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyond](https://mlsanity.com/paper/2307.15615/) (2023)
- [Vision Foundation Models for Computed Tomography](https://mlsanity.com/paper/2501.09001/) (2025)
- [Fast 3D registration with accurate optimisation and little learning for Learn2Reg 2021](https://mlsanity.com/paper/2112.03053/) (2021)
- [Triad: Vision Foundation Model for 3D Magnetic Resonance Imaging](https://mlsanity.com/paper/2502.14064/) (2025)
- [Embedding Gradient-based Optimization in Image Registration Networks](https://mlsanity.com/paper/2112.03915/) (2021)
- [Unifying Biomedical Vision-Language Expertise: Towards a Generalist Foundation Model via Multi-CLIP Knowledge Distillation](https://mlsanity.com/paper/2506.22567/) (2025)
- [Are Vision Foundation Models Ready for Out-of-the-Box Medical Image Registration?](https://mlsanity.com/paper/2507.11569/) (2025)
- [UTSRMorph: A Unified Transformer and Superresolution Network for Unsupervised Medical Image Registration](https://mlsanity.com/paper/2410.20348/) (2024)

## Built on by (most cited first, 6 of 6)

- [MedDINOv3: How to adapt vision foundation models for medical image segmentation?](https://mlsanity.com/paper/2509.02379/) (2025)
- [SegDINO: An Efficient Design for Medical and Natural Image Segmentation with DINO-V3](https://mlsanity.com/paper/2509.00833/) (2025)
- [Vision4PPG: Emergent PPG Analysis Capability of Vision Foundation Models for Vital Signs like Blood Pressure](https://mlsanity.com/paper/2510.10366/) (2025)
- [LUMOS: Latent Universal Medical Priors for Segmentation](https://mlsanity.com/paper/2603.01115/) (2026)
- [SegDINO: Introducing Multi-Scale Structure into DINO for Efficient Medical Image Segmentation](https://mlsanity.com/paper/2606.17972/) (2026)
- [CMRVision: A Foundation Model for Cardiac MR Image Analysis](https://mlsanity.com/paper/2609.01308/) (2026)

## Abstract (arXiv)

Prior medical image registration approaches, particularly learning-based methods, often require large amounts of training data, which constrains clinical adoption. To overcome this limitation, we propose a training-free pipeline that relies on a frozen DINOv3 encoder and test-time optimization of the deformation field in feature space. Across two representative benchmarks, the method is accurate and yields regular deformations. On Abdomen MR-CT, it attained the best mean Dice score (DSC) of 0.790 together with the lowest 95th percentile Hausdorff Distance (HD95) of 4.9+-5.0 and the lowest standard deviation of Log-Jacobian (SDLogJ) of 0.08+-0.02. On ACDC cardiac MRI, it improves mean DSC to 0.769 and reduces SDLogJ to 0.11 and HD95 to 4.8, a marked gain over the initial alignment. The results indicate that operating in a compact foundation feature space at test time offers a practical and general solution for clinical registration without additional training.