Select a photo under "Image Selection" and estimate its geolocation by clicking on the world map.

Under "Image Selection" you can choose an image from a predefined benchmark test set. Your performance compared to our deep learning approach and the scene classification (probabilities for indoor, nature, urban) results are shown in the sections "Statistics" and "Scene Classification", respectively.

Registered users can also upload their own photos. Please note that your application must originate from a verifiable work or university email address and includes a description of your intended use case. Applications sent from personal email addresses will not be considered.

After you have clicked on "Guess Location" the results are calculated and presented. The world map is overlaid with a heat map, where the regions colored in red represent the most likely locations of the photo at hand. In addition, the photo parts that contributed at most to the decision are visualised (blue = “less important” to red = “very important”).