← All projects
Computer Vision · Geospatial AI
Image Geolocalization
Learning visual representations to estimate where a photograph was captured.
Research directionOverview
A research direction focused on image-to-location retrieval and geographic reasoning. The system explores image–GPS representation learning, large-scale visual retrieval, and candidate reranking.
Methods & topics
Highlights
- Exploring pretrained vision encoders for image–location representation learning.
- Building large-scale image and GPS retrieval pipelines.
- Evaluating retrieval quality across geographic distance thresholds.