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

TL;DR

Reg-TTR is a test-time refinement framework that enhances deep learning-based image registration accuracy by combining traditional and modern methods, achieving state-of-the-art results with minimal additional inference time.

Contribution

We introduce Reg-TTR, a novel test-time refinement approach that improves registration accuracy of foundation models while maintaining fast inference speeds.

Findings

Achieves state-of-the-art registration performance.

Requires only 21% additional inference time.

Effectively narrows the gap between foundation models and specialized methods.

Abstract

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.