cs.CVNov 9, 2026

X Marks the Spot: Diffusion for Image Geolocalization with Location Representations

Authors: Brian Wei, Chih-Chuan Hsu, Tianyi Gao, Daniel Cher, Eric Xing, Danielle Beaulieu, Nathan Jacobs

Organizations: Washington University in St. Louis

Abstract

Image geolocalization predicts the location at which a photo was taken. Accurate geolocalization requires discriminating between both physically and semantically adjacent areas on Earth. However, prior diffusion-based approaches predict locations by generating coordinates, which are semantically unstable over space. We avoid this limitation by learning geolocalization behavior in the pretrained representation spaces of location encoders, which provide both positional and semantic understanding. To make this space usable for coordinate prediction, we introduce a Location Autoencoder (LAE), which pairs a frozen location encoder with a learned decoder mapping embeddings back to coordinates with kilometer-level accuracy worldwide. In the LAE space, we train DIG, a latent diffusion model that transports noise to location embeddings conditioned on image features. DIG consistently outperforms coordinate-based generative models and sets a new state of the art for parametric geolocalization on three benchmarks: OSV-5M, Im2GPS3k, and YFCC4k. Notably, DIG is the first generative model to outperform retrieval-based methods, and further improves retrieve-and-rerank systems when used as a prior. Code and models will be released.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. GeoSearch: Augmenting Worldwide Geolocalization with Web-Scale Reverse Image Search and Image Matching

    Apr 28, 2026Tung-Duong Le-Duc, Hoang-Quoc Nguyen-Son, Minh-Son DaoMultimodal RAGImage Matching

  2. GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalization

    Mar 25, 2026Pengyue Jia, Derong Xu, Yingyi Zhang +5LLM Routing