Search papers, labs, and topics across Lattice.
This paper introduces GeoBridge, a novel conditioning mechanism that enhances generative image geolocalization by decoupling semantic reasoning from coordinate generation. By addressing the role conflict between discrete semantic labels and the continuous nature of geolocation, GeoBridge effectively integrates geographic priors while maintaining the integrity of the spherical decoder. The method achieves significant improvements on the IM2GPS3K dataset, surpassing traditional place-name-to-API approaches and reasoning-augmented predictions at critical precision thresholds.
GeoBridge achieves a remarkable 70.37% accuracy at the 750 km threshold, revolutionizing how we connect semantic reasoning to precise geolocation in images.
Multimodal large language models (MLLMs) have advanced image geolocalization mainly by improving how they reason about geographic cues. How that reasoning isdecoded into coordinates, however, has lagged behind. Predicting a place name for a geocoding API is discrete and lossy: it ignores image evidence and collapses multi-granular semantics into a coarse lookup. We argue that the bottleneck has shifted from what a model reasons to how that reasoning is represented for a continuous, geometry-aware decoder. We present GeoBridge, a role-decoupled conditioning mechanism that connects a frozen semantic MLLM to a frozen Riemannian flow-matching head that generates coordinates on the sphere. The central obstacle is arole conflict: supervising the condition with discrete semantic labels biases its representation toward class-discriminative geometry, at odds with the smooth manifold the generative head requires. GeoBridge keeps the semantic supervision decoupled from the condition interface: a separate projection forms the continuous condition the frozen head expects, injecting geographic priors without disturbing the spherical decoder. On IM2GPS3K, GeoBridge reaches 38.67/52.89/70.37 at the 25/200/750 km thresholds, improving over a place-name-to-API pipeline and reasoning-augmented direct prediction at these precision-relevant scales. GeoBridge is a decode-side algorithmic contribution, orthogonal and complementary to chain-of-thought reasoning. Code will be made publicly available.
