RegistrationMamba: A Mamba-based Registration Framework Integrating Multi-Expert Feature Learning for Cross-Modal Remote Sensing Images

2025-07-06

AI Summary

Cross-modal remote sensing image (CRSI) registration faces two major challenges: substantial nonlinear radiometric discrepancies and weak feature discriminability due to texture scarcity. Existing CNN-based methods lack sufficient capacity to model long-range dependencies, while Transformer-based approaches incur prohibitive computational overhead, hindering scalability to high-resolution remote sensing data. To address these issues, we propose RegistrationMamba—a novel framework that introduces state space models (SSMs) with linear complexity into CRSI registration for the first time. It employs multi-directional cross-scanning to efficiently capture long-range contextual relationships. We further design a learnable soft-routing mechanism for multi-expert feature learning (MEFL) to enhance robust representation under texture-limited conditions, and integrate a multi-level feature aggregation (MFA) module to jointly optimize global consistency and local detail fidelity. Extensive experiments on multi-scale CRSI benchmarks demonstrate that RegistrationMamba significantly outperforms state-of-the-art methods in accuracy, generalization, and deployment feasibility.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Cross-modal remote sensing image (CRSI) registration is critical for multi-modal image applications. However, CRSI mainly faces two challenges: significant nonlinear radiometric variations between cross-modal images and limited textures hindering the discriminative information extraction. Existing methods mainly adopt convolutional neural networks (CNNs) or Transformer architectures to extract discriminative features for registration. However, CNNs with the local receptive field fail to capture global contextual features, and Transformers have high computational complexity and restrict their application to high-resolution CRSI. To solve these issues, this paper proposes RegistrationMamba, a novel Mamba architecture based on state space models (SSMs) integrating multi-expert feature learning for improving the accuracy of CRSI registration. Specifically, RegistrationMamba employs a multi-directional cross-scanning strategy to capture global contextual relationships with linear complexity. To enhance the performance of RegistrationMamba under texture-limited scenarios, we propose a multi-expert feature learning (MEFL) strategy to capture features from various augmented image variants through multiple feature experts. MEFL leverages a learnable soft router to dynamically fuse the features from multiple experts, thereby enriching feature representations and improving registration performance. Notably, MEFL can be seamlessly integrated into various frameworks, substantially boosting registration performance. Additionally, RegistrationMamba integrates a multi-level feature aggregation (MFA) module to extract fine-grained local information and enable effective interaction between global and local features. Extensive experiments on CRSI with varying image resolutions have demonstrated that RegistrationMamba has superior performance and robustness compared to state-of-the-art methods.

Problem

• Addresses nonlinear radiometric variations in cross-modal remote sensing images
• Overcomes texture limitations for discriminative feature extraction
• Reduces computational complexity in high-resolution image registration

Innovation

• Mamba architecture with state space models
• Multi-expert feature learning strategy
• Multi-level feature aggregation module