Search papers, labs, and topics across Lattice.
This paper introduces GeoMix, a novel descriptor-free visual localization framework that enhances geometric discriminability through multi-detector training and global context integration. By employing directional and distance-aware embeddings, along with learnable context nodes for cross-attention, GeoMix significantly improves the accuracy of geometry-only matching methods. Experimental results demonstrate that GeoMix achieves a new state of the art in descriptor-free localization, reducing rotation and translation errors by up to 90% compared to previous methods while maintaining robustness across different keypoint detectors.
GeoMix slashes localization errors by up to 90% in descriptor-free visual matching, challenging the dominance of traditional descriptor-based approaches.
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 $\href{https://github.com/YejunZhang/Geomix}{\text{this links}}$.
