用测试时精修提升图像配准速度与精度，兼顾高效与鲁棒。
Reg-TTR, Test-Time Refinement for Fast, Robust and Accurate Image Registration
- 在推理时对预训练模型输出进行优化，融合深度学习与传统方法优势。
- 仅增加21%推理时间（0.56秒），实现超越现有方法的配准精度。
- 适合希望快速提升通用配准模型性能的研究者与应用开发者。
传统图像配准方法虽鲁棒但速度慢，因依赖迭代过程；深度学习虽加速推理，却常受领域偏移影响。新兴的注册基础模型在速度与鲁棒性间取得平衡，但通常无法达到针对特定数据集训练的专用模型的峰值精度。为缓解此问题，我们提出 Reg-TTR——一种测试时精修框架，通过在推理阶段优化预训练模型的预测结果，显著提升配准精度，同时计算开销极小，仅需额外 21% 推理时间（0.56 秒）。我们在两个不同任务上评估了 Reg-TTR，结果表明其在保持接近先前深度学习方法推理速度的同时，实现了当前最优（SOTA）性能。随着注册基础模型的不断发展，该框架为缩小其与专用模型之间的性能差距提供了高效策略。代码将在论文录用后公开。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。