Papers › PlaNet - Photo Geolocation with Convolutional Neural Networks

PlaNet - Photo Geolocation with Convolutional Neural Networks

17 Feb 2016arXiv:1602.05314archive 2025-07-28

Tobias Weyand, Ilya Kostrikov, James Philbin

Is it possible to build a system to determine the location where a photo was taken using just its pixels? In general, the problem seems exceptionally difficult: it is trivial to construct situations where no location can be inferred. Yet images often contain informative cues such as landmarks, weather patterns, vegetation, road markings, and architectural details, which in combination may allow one to determine an approximate location and occasionally an exact location. Websites such as GeoGuessr and View from your Window suggest that humans are relatively good at integrating these cues to geolocate images, especially en-masse. In computer vision, the photo geolocation problem is usually approached using image retrieval methods. In contrast, we pose the problem as one of classification by subdividing the surface of the earth into thousands of multi-scale geographic cells, and train a deep network using millions of geotagged images. While previous approaches only recognize landmarks or perform approximate matching using global image descriptors, our model is able to use and integrate multiple visible cues. We show that the resulting model, called PlaNet, outperforms previous approaches and even attains superhuman levels of accuracy in some cases. Moreover, we extend our model to photo albums by combining it with a long short-term memory (LSTM) architecture. By learning to exploit temporal coherence to geolocate uncertain photos, we demonstrate that this model achieves a 50% performance improvement over the single-image model.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

gjacopo/poppysite mentioned on GitHubEUPL-1.1 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image RetrievalPhoto geolocation estimationRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Photo geolocation estimation Im2GPS PlaNet (91M) City level (25 km) 24.5 #8 of 11 Archive leaderboard report
Photo geolocation estimation Im2GPS PlaNet (91M) Continent level (2500 km) 71.3 #8 of 11 Archive leaderboard report
Photo geolocation estimation Im2GPS PlaNet (91M) Country level (750 km) 53.6 #8 of 11 Archive leaderboard report
Photo geolocation estimation Im2GPS PlaNet (91M) Reference images 0 #8 of 11 Archive leaderboard report
Photo geolocation estimation Im2GPS PlaNet (91M) Region level (200 km) 37.6 #8 of 11 Archive leaderboard report
Photo geolocation estimation Im2GPS PlaNet (91M) Street level (1 km) 8.4 #8 of 11 Archive leaderboard report
Photo geolocation estimation Im2GPS PlaNet (91M) Training images 91M #8 of 11 Archive leaderboard report
Photo geolocation estimation Im2GPS PlaNet (6.2M) City level (25 km) 18.1 #10 of 11 Archive leaderboard report
Photo geolocation estimation Im2GPS PlaNet (6.2M) Continent level (2500 km) 65.8 #10 of 11 Archive leaderboard report
Photo geolocation estimation Im2GPS PlaNet (6.2M) Country level (750 km) 45.6 #10 of 11 Archive leaderboard report
Photo geolocation estimation Im2GPS PlaNet (6.2M) Reference images 0 #10 of 11 Archive leaderboard report
Photo geolocation estimation Im2GPS PlaNet (6.2M) Region level (200 km) 30.0 #10 of 11 Archive leaderboard report
Photo geolocation estimation Im2GPS PlaNet (6.2M) Street level (1 km) 6.3 #10 of 11 Archive leaderboard report
Photo geolocation estimation Im2GPS PlaNet (6.2M) Training images 6.2M #10 of 11 Archive leaderboard report
Photo geolocation estimation YFCC26k PlaNet City level (25 km) 11.0 #6 of 6 Archive leaderboard report
Photo geolocation estimation YFCC26k PlaNet Continent level (2500 km) 47.7 #6 of 6 Archive leaderboard report
Photo geolocation estimation YFCC26k PlaNet Country level (750 km) 28.5 #6 of 6 Archive leaderboard report
Photo geolocation estimation YFCC26k PlaNet Region level (200 km) 16.9 #6 of 6 Archive leaderboard report
Photo geolocation estimation YFCC26k PlaNet Street level (1 km) 4.4 #6 of 6 Archive leaderboard report
Photo geolocation estimation YFCC26k PlaNet Training Images 30.3M #6 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections