CRFT: Consistent-Recurrent Feature Flow Transformer for Cross-Modal Image Registration

TL;DR

CRFT is a transformer-based framework that achieves robust cross-modal image registration by learning a modality-independent feature flow through a coarse-to-fine, iterative refinement process.

Contribution

It introduces a unified coarse-to-fine transformer architecture with an iterative discrepancy-guided attention mechanism for improved cross-modal registration.

Findings

CRFT outperforms state-of-the-art methods in accuracy and robustness.

It effectively handles large affine and scale variations.

The approach is applicable to remote sensing, navigation, and medical imaging.

Abstract

We present Consistent-Recurrent Feature Flow Transformer (CRFT), a unified coarse-to-fine framework based on feature flow learning for robust cross-modal image registration. CRFT learns a modality-independent feature flow representation within a transformer-based architecture that jointly performs feature alignment and flow estimation. The coarse stage establishes global correspondences through multi-scale feature correlation, while the fine stage refines local details via hierarchical feature fusion and adaptive spatial reasoning. To enhance geometric adaptability, an iterative discrepancy-guided attention mechanism with a Spatial Geometric Transform (SGT) recurrently refines the flow field, progressively capturing subtle spatial inconsistencies and enforcing feature-level consistency. This design enables accurate alignment under large affine and scale variations while maintaining structural coherence across modalities. Extensive experiments on diverse cross-modal datasets demonstrate that CRFT consistently outperforms state-of-the-art registration methods in both accuracy and robustness. Beyond registration, CRFT provides a generalizable paradigm for multimodal spatial correspondence, offering broad applicability to remote sensing, autonomous navigation, and medical imaging. Code and datasets are publicly available at https://github.com/NEU-Liuxuecong/CRFT.