Mifnet: Learning Modality-invariant Features For Generalizable Multimodal Image Matching

Abstract

Many keypoint detection and description methods have been proposed for image matching or registration. While these methods demonstrate promising performance for single-modality image matching, they often struggle with multimodal data because the descriptors trained on single-modality data tend to lack robustness against the non-linear variations present in multimodal data. Extending such methods to multimodal image matching often requires well-aligned multimodal data to learn modality-invariant descriptors. However, acquiring such data is often costly and impractical in many real-world scenarios. To address this challenge, we propose a modality-invariant feature learning network (MIFNet) to compute modality-invariant features for keypoint descriptions in multimodal image matching using only single-modality training data. Specifically, we propose a novel latent feature aggregation module and a cumulative hybrid aggregation module to enhance the base keypoint descriptors trained on singl

Stats

• citations6
• S2 citations—
• github stars18
• HF likes0
• heat score8.90
• arxiv keyliu2025mifnet

Related papers

• If-net: An Illumination-invariant Feature Network (2020)6.77
• Modality-aware Feature Matching: A Comprehensive Review Of Single- And Cross-modality Techniques (2025)0.00
• Modality Curation: Building Universal Embeddings For Advanced Multimodal Information Retrieval (2025)0.00
• Modal-aware Features For Multimodal Hashing (2019)0.00
• Enhancing Image-text Matching With Adaptive Feature Aggregation (2024)6.34
• Mdreid: Modality-decoupled Learning For Any-to-any Multi-modal Object Re-identification (2025)0.00
• Mire: Enhancing Multimodal Queries Representation Via Fusion-free Modality Interaction For Multimodal Retrieval (2024)3.81
• Indexing Multimodal Language Models For Large-scale Image Retrieval (2026)0.00