{"ID":6536315,"CreatedAt":"2026-07-14T01:21:01.169441415Z","UpdatedAt":"2026-07-14T01:36:59.12045529Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.10082","arxiv_id":"2607.10082","title":"Label-Free Target-Domain Adaptation for Unconstrained Event-Image Feature Matching via Dual-Stage Distillation","abstract":"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.","short_abstract":"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 sce...","url_abs":"https://arxiv.org/abs/2607.10082","url_pdf":"https://arxiv.org/pdf/2607.10082v1","authors":"[\"Zhonghua Yi\",\"Hao Shi\",\"Qi Jiang\",\"Yufan Zhang\",\"Kailun Yang\",\"Kaiwei Wang\"]","published":"2026-07-11T02:23:11Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.MM\",\"cs.RO\",\"eess.IV\"]","methods":"[]","has_code":false,"code_links":[{"ID":614156,"CreatedAt":"2026-07-14T01:21:01.169441415Z","UpdatedAt":"2026-07-14T01:21:01.169441415Z","DeletedAt":null,"paper_id":6536315,"paper_url":"https://arxiv.org/abs/2607.10082","paper_title":"Label-Free Target-Domain Adaptation for Unconstrained Event-Image Feature Matching via Dual-Stage Distillation","repo_url":"https://github.com/ZhonghuaYi/nexus2-official","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}