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

arXiv: https://arxiv.org/abs/2604.05689 · HTML: https://mlsanity.com/paper/2604.05689/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 67 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Builds on (most cited first, 30 of 37)

- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images](https://mlsanity.com/paper/2403.14627/) (2024)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [FlowFormer: A Transformer Architecture for Optical Flow](https://mlsanity.com/paper/2203.16194/) (2022)
- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [DKM: Dense Kernelized Feature Matching for Geometry Estimation](https://mlsanity.com/paper/2202.00667/) (2022)
- [Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed](https://mlsanity.com/paper/2403.04765/) (2024)
- [GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving](https://mlsanity.com/paper/2503.05689/) (2025)
- [FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation](https://mlsanity.com/paper/2303.01237/) (2023)
- [XFeat: Accelerated Features for Lightweight Image Matching](https://mlsanity.com/paper/2404.19174/) (2024)
- [Single-Model and Any-Modality for Video Object Tracking](https://mlsanity.com/paper/2311.15851/) (2023)
- [OmniGlue: Generalizable Feature Matching with Foundation Model Guidance](https://mlsanity.com/paper/2405.12979/) (2024)
- [A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyond](https://mlsanity.com/paper/2307.15615/) (2023)
- [SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection](https://mlsanity.com/paper/2403.06534/) (2024)
- [XoFTR: Cross-modal Feature Matching Transformer](https://mlsanity.com/paper/2404.09692/) (2024)
- [MINIMA: Modality Invariant Image Matching](https://mlsanity.com/paper/2412.19412/) (2024)
- [MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation based Distillation](https://mlsanity.com/paper/2503.09950/) (2025)
- [DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework](https://mlsanity.com/paper/2503.14880/) (2025)
- [Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment](https://mlsanity.com/paper/2506.02221/) (2025)
- [ReDFeat: Recoupling Detection and Description for Multimodal Feature Learning](https://mlsanity.com/paper/2205.07439/) (2022)
- [Dense-SfM: Structure from Motion with Dense Consistent Matching](https://mlsanity.com/paper/2501.14277/) (2025)
- [MUST: The First Dataset and Unified Framework for Multispectral UAV Single Object Tracking](https://mlsanity.com/paper/2503.17699/) (2025)
- [From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point Supervision](https://mlsanity.com/paper/2412.11154/) (2024)
- [RIFT2: Speeding-up RIFT with A New Rotation-Invariance Technique](https://mlsanity.com/paper/2303.00319/) (2023)

## Built on by (most cited first, 3 of 3)

- [RBE-Flow: Recurrent Bayesian Estimation on Feature Manifolds for Cross-Modal Registration](https://mlsanity.com/paper/2606.30492/) (2026)
- [Modality-Invariant Coarse-to-Fine Retinal Image Registration](https://mlsanity.com/paper/2608.14829/) (2026)
- [Diff-RF: Mutually Reinforced Image Registration and Fusion via Degradation-Aware Learning](https://mlsanity.com/paper/2609.28235/) (2026)

## Abstract (arXiv)

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.