GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Training
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
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorYejun Zhang →
GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Training
- Linked via arxiv authorXinjue Wang →
GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Training
- Linked via arxiv authorZihan Wang →
GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Training
- Linked via arxiv authorEsa Rahtu →
GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Training
- Linked via arxiv authorJuho Kannala →
GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Training