# DistillMatch: Leveraging Knowledge Distillation from Vision Foundation Model for Multimodal Image Matching

arXiv: https://arxiv.org/abs/2509.16017 · HTML: https://mlsanity.com/paper/2509.16017/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal distillation, one of 12 directions in Knowledge distillation.
- Builds on 20 of its 45 references that are in the map.
- First posted on arXiv 19 Sep 2025.

## Placed in

- Knowledge distillation / [Multimodal distillation](https://mlsanity.com/distill/multimodal-distillation/)

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation](https://mlsanity.com/paper/2308.02097/) (2023)
- [Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed](https://mlsanity.com/paper/2403.04765/) (2024)
- [MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training](https://mlsanity.com/paper/2501.07556/) (2025)
- [SFD2: Semantic-guided Feature Detection and Description](https://mlsanity.com/paper/2304.14845/) (2023)
- [StyleBooth: Image Style Editing with Multimodal Instruction](https://mlsanity.com/paper/2404.12154/) (2024)
- [ReDFeat: Recoupling Detection and Description for Multimodal Feature Learning](https://mlsanity.com/paper/2205.07439/) (2022)
- [MESA: Matching Everything by Segmenting Anything](https://mlsanity.com/paper/2401.16741/) (2024)
- [Thermal Infrared Image Colorization for Nighttime Driving Scenes with Top-Down Guided Attention](https://mlsanity.com/paper/2104.14374/) (2021)
- [Segment Anything Model is a Good Teacher for Local Feature Learning](https://mlsanity.com/paper/2309.16992/) (2023)
- [VMLoc: Variational Fusion For Learning-Based Multimodal Camera Localization](https://mlsanity.com/paper/2003.07289/) (2020)
- [LiftFeat: 3D Geometry-Aware Local Feature Matching](https://mlsanity.com/paper/2505.03422/) (2025)
- [Deep Learning Reforms Image Matching: A Survey and Outlook](https://mlsanity.com/paper/2506.04619/) (2025)
- [Learning Affine Correspondences by Integrating Geometric Constraints](https://mlsanity.com/paper/2504.04834/) (2025)
- [XPoint: A Self-Supervised Visual-State-Space based Architecture for Multispectral Image Registration](https://mlsanity.com/paper/2411.07430/) (2024)

## Built on by (most cited first, 4 of 4)

- [SGMatch: Semantic-Guided Non-Rigid Shape Matching with Flow Regularization](https://mlsanity.com/paper/2603.12937/) (2026)
- [No Calibration, No Depth, No Problem: Cross-Sensor View Synthesis with 3D Consistency](https://mlsanity.com/paper/2602.23559/) (2026)
- [FreqKD: Frequency-Decoupled Cross-Modal Knowledge Distillation for Infrared Object Detection](https://mlsanity.com/paper/2606.11572/) (2026)
- [Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives](https://mlsanity.com/paper/2608.11093/) (2026)

## Abstract (arXiv)

Multimodal image matching seeks pixel-level correspondences between images of different modalities, crucial for cross-modal perception, fusion and analysis. However, the significant appearance differences between modalities make this task challenging. Due to the scarcity of high-quality annotated datasets, existing deep learning methods that extract modality-common features for matching perform poorly and lack adaptability to diverse scenarios. Vision Foundation Model (VFM), trained on large-scale data, yields generalizable and robust feature representations adapted to data and tasks of various modalities, including multimodal matching. Thus, we propose DistillMatch, a multimodal image matching method using knowledge distillation from VFM. DistillMatch employs knowledge distillation to build a lightweight student model that extracts high-level semantic features from VFM (including DINOv2 and DINOv3) to assist matching across modalities. To retain modality-specific information, it extracts and injects modality category information into the other modality's features, which enhances the model's understanding of cross-modal correlations. Furthermore, we design V2I-GAN to boost the model's generalization by translating visible to pseudo-infrared images for data augmentation. Experiments show that DistillMatch outperforms existing algorithms on public datasets.