# Reg-TTR, Test-Time Refinement for Fast, Robust and Accurate Image Registration

arXiv: https://arxiv.org/abs/2601.19114 · HTML: https://mlsanity.com/paper/2601.19114/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 22 references that are in the map.
- First posted on arXiv 27 Jan 2026.

## Builds on (most cited first, 11 of 11)

- [VoxelMorph: A Learning Framework for Deformable Medical Image Registration](https://mlsanity.com/paper/1809.05231/) (2018)
- [Efficient Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2403.18293/) (2024)
- [uniGradICON: A Foundation Model for Medical Image Registration](https://mlsanity.com/paper/2403.05780/) (2024)
- [Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registration](https://mlsanity.com/paper/2406.00123/) (2024)
- [TEA: Test-time Energy Adaptation](https://mlsanity.com/paper/2311.14402/) (2023)
- [Fourier-Net: Fast Image Registration with Band-limited Deformation](https://mlsanity.com/paper/2211.16342/) (2022)
- [Spatially Covariant Image Registration with Text Prompts](https://mlsanity.com/paper/2311.15607/) (2023)
- [A Deep Discontinuity-Preserving Image Registration Network](https://mlsanity.com/paper/2107.04440/) (2021)
- [MemWarp: Discontinuity-Preserving Cardiac Registration with Memorized Anatomical Filters](https://mlsanity.com/paper/2407.08093/) (2024)
- [One registration is worth two segmentations](https://mlsanity.com/paper/2405.10879/) (2024)
- [Encoder-Only Image Registration](https://mlsanity.com/paper/2509.00451/) (2025)

## Abstract (arXiv)

Traditional image registration methods are robust but slow due to their iterative nature. While deep learning has accelerated inference, it often struggles with domain shifts. Emerging registration foundation models offer a balance of speed and robustness, yet typically cannot match the peak accuracy of specialized models trained on specific datasets. To mitigate this limitation, we propose Reg-TTR, a test-time refinement framework that synergizes the complementary strengths of both deep learning and conventional registration techniques. By refining the predictions of pre-trained models at inference, our method delivers significantly improved registration accuracy at a modest computational cost, requiring only 21% additional inference time (0.56s). We evaluate Reg-TTR on two distinct tasks and show that it achieves state-of-the-art (SOTA) performance while maintaining inference speeds close to previous deep learning methods. As foundation models continue to emerge, our framework offers an efficient strategy to narrow the performance gap between registration foundation models and SOTA methods trained on specialized datasets. The source code will be publicly available following the acceptance of this work.