image-geolocation

An agent skill that finds where a photo was taken — OpenStreetMap geometry, elevation skylines, satellite imagery and street view — and shows its work. Works with Claude Code, Codex, Cursor, Gemini CLI, OpenCode and GitHub Copilot.

HoloGeo: Evidence-driven VLM for robust image geo-localization and landmark-bias mitigation.

Research toolkit for pixels-only image geolocation, retrieval, and evaluation

Free, open-source desktop app that estimates where a photo was taken. Self-contained, Windows, no paid APIs.

Open-source AI image geolocation & OSINT tool which can find GPS coordinates from any photo by matching against street view panoramas using MegaLoc + MASt3R

Self-hosted tool that predicts where any photo was taken, using the GeoCLIP neural network. Runs entirely on your own machine — no uploads, no telemetry. Writes ESTIMATED coordinates into EXIF.

Campus-scale image geolocation using ResNet-50, grid-based localization, soft top-k decoding, FastAPI, and Streamlit.

Image Geolocation using Pillow library in Python. Searching for exact coordinates embedded in exif data of an image, and extracting it.

Single-image geolocalization: DINOv3 geocell classifier + gated retrieval over 1.2M Street View images. 34.1 km median error, runs offline on a phone.

Sub-5M-parameter European image geolocation with hierarchical classification and spherical decoding.

Research implementation of image geolocation using CLIP visual embeddings and S2 Geometry concepts.

Where was this photo taken — and when? An agent skill that geolocates photos and verifies against real map data.