# Label-Free Target-Domain Adaptation for Unconstrained Event-Image Feature Matching via Dual-Stage Distillation

arXiv: https://arxiv.org/abs/2607.10082 · HTML: https://mlsanity.com/paper/2607.10082/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 42 references that are in the map.
- First posted on arXiv 11 Jul 2026.

## Builds on (most cited first, 28 of 28)

- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [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)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [DSEC: A Stereo Event Camera Dataset for Driving Scenarios](https://mlsanity.com/paper/2103.06011/) (2021)
- [The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception](https://mlsanity.com/paper/1801.10202/) (2018)
- [The Event-Camera Dataset and Simulator: Event-based Data for Pose Estimation, Visual Odometry, and SLAM](https://mlsanity.com/paper/1610.08336/) (2016)
- [DKM: Dense Kernelized Feature Matching for Geometry Estimation](https://mlsanity.com/paper/2202.00667/) (2022)
- [MatchFormer: Interleaving Attention in Transformers for Feature Matching](https://mlsanity.com/paper/2203.09645/) (2022)
- [ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation](https://mlsanity.com/paper/2304.03608/) (2023)
- [BootsTAP: Bootstrapped Training for Tracking-Any-Point](https://mlsanity.com/paper/2402.00847/) (2024)
- [Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed](https://mlsanity.com/paper/2403.04765/) (2024)
- [Asynchronous, Photometric Feature Tracking using Events and Frames](https://mlsanity.com/paper/1807.09713/) (2018)
- [Sonata: Self-Supervised Learning of Reliable Point Representations](https://mlsanity.com/paper/2503.16429/) (2025)
- [Revisiting Color-Event based Tracking: A Unified Network, Dataset, and Metric](https://mlsanity.com/paper/2211.11010/) (2022)
- [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)
- [TUM-VIE: The TUM Stereo Visual-Inertial Event Dataset](https://mlsanity.com/paper/2108.07329/) (2021)
- [TAPNext: Tracking Any Point (TAP) as Next Token Prediction](https://mlsanity.com/paper/2504.05579/) (2025)
- [ReDFeat: Recoupling Detection and Description for Multimodal Feature Learning](https://mlsanity.com/paper/2205.07439/) (2022)
- [Self-Supervised Any-Point Tracking by Contrastive Random Walks](https://mlsanity.com/paper/2409.16288/) (2024)
- [RIPE: Reinforcement Learning on Unlabeled Image Pairs for Robust Keypoint Extraction](https://mlsanity.com/paper/2507.04839/) (2025)
- [3MOS: Multi-sources, Multi-resolutions, and Multi-scenes dataset for Optical-SAR image matching](https://mlsanity.com/paper/2404.00838/) (2024)
- [MapGlue: Multimodal Remote Sensing Image Matching](https://mlsanity.com/paper/2503.16185/) (2025)
- [Automatic Multi-Sensor Extrinsic Calibration for Mobile Robots](https://mlsanity.com/paper/1906.04670/) (2019)
- [EI-Nexus: Towards Unmediated and Flexible Inter-Modality Local Feature Extraction and Matching for Event-Image Data](https://mlsanity.com/paper/2410.21743/) (2024)

## Abstract (arXiv)

Building pixel-level correspondence between event and image data is a fundamental task for multi-sensor systems. However, existing cross-modal matching methods are largely restricted by their reliance on either matching labels or strictly aligned hardware, which limits them to unlabeled and unconstrained real-world scenarios where neither matching ground truth nor prior sensor relationships are available. To address this, we propose a novel two-stage training paradigm. First, we leverage large-scale data to perform label-agnostic distillation pretraining, upgrading optimization objectives with distribution-based and contrastive losses to learn highly generalizable representations. Second, to tackle unlabeled and unconstrained downstream data, we introduce an epipolar-guided self-distillation framework. By utilizing consistency verification to isolate robust matches and incorporating geometric confidence derived from an external epipolar prior, our model can effectively self-evolve directly on target domains without any supervision. Furthermore, we introduce a rigorous cross-modal evaluation benchmark based on TUM-VIE, featuring physically separated cameras with distinct intrinsic parameters and resolutions. Extensive experiments demonstrate that our proposed method achieves state-of-the-art performance on both MVSEC and TUM-VIE pose estimation tasks. The source code and benchmark will be made publicly available at https://github.com/ZhonghuaYi/nexus2-official.