{"ID":5676757,"CreatedAt":"2026-07-03T03:29:23.032456456Z","UpdatedAt":"2026-07-07T01:06:03.009715918Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.02486","arxiv_id":"2607.02486","title":"GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Training","abstract":"Descriptor-free visual localization eliminates high-dimensional descriptor storage, preserves scene privacy, and simplifies map maintenance, yet its accuracy still lags far behind descriptor-based pipelines. We identify this gap to insufficient geometric discriminability in geometry-only matching. Without visual appearance, current methods underutilize local geometry cues, lack the global context among keypoints, and overfit to a single keypoint detector. We further observe that descriptor-free matching naturally enables multi-detector training, as heterogeneous keypoints can be optimized in a shared geometry-only space without aligning descriptor spaces. Building on these insights, we propose GeoMix, a descriptor-free 2D-3D matching framework that strengthens geometric discriminability at three levels. Locally, directional and distance-aware embeddings enrich neighborhood aggregation with fine-grained spatial structure. Globally, learnable context nodes aggregate and redistribute scene-wide information via cross-attention to resolve ambiguities beyond local receptive fields. At the training level, Mix-Training exploits this detector-agnostic geometry space to learn representations across multiple keypoint detectors. Extensive experiments on MegaDepth, Cambridge Landmarks, 7Scenes, and Aachen Day-Night show that GeoMix sets a new state of the art among descriptor-free methods, reducing 75th-percentile rotation error by 89\\% and translation error by up to 90\\% over the previous best, while generalizing zero-shot to unseen detectors and narrowing the gap to descriptor-based pipelines. Code is available at $\\href{https://github.com/YejunZhang/Geomix}{\\text{this links}}$.","short_abstract":"Descriptor-free visual localization eliminates high-dimensional descriptor storage, preserves scene privacy, and simplifies map maintenance, yet its accuracy still lags far behind descriptor-based pipelines. We identify this gap to insufficient geometric discriminability in geometry-only matching. Without visual appear...","url_abs":"https://arxiv.org/abs/2607.02486","url_pdf":"https://arxiv.org/pdf/2607.02486v1","authors":"[\"Yejun Zhang\",\"Xinjue Wang\",\"Zihan Wang\",\"Esa Rahtu\",\"Juho Kannala\"]","published":"2026-07-02T17:52:41Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":613918,"CreatedAt":"2026-07-03T03:29:23.032456456Z","UpdatedAt":"2026-07-03T03:29:23.032456456Z","DeletedAt":null,"paper_id":5676757,"paper_url":"https://arxiv.org/abs/2607.02486","paper_title":"GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Training","repo_url":"https://github.com/YejunZhang/Geomix","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}