GAEA: A Geolocation Aware Conversational Model
Ron Campos, Ashmal Vayani, Parth Parag Kulkarni, Rohit Gupta, Aritra Dutta, Mubarak Shah
2025-03-24
Summary
This paper is about creating an AI model that can not only identify the location of a picture but also chat with you about it.
What's the problem?
Existing AI models can tell you the GPS coordinates of a photo, but they can't really understand the location or have a conversation about it with you.
What's the solution?
The researchers developed a new AI model called GAEA that can provide information about the location in a picture and answer questions about it in a conversational way.
Why it matters?
This work matters because it makes AI more useful for understanding and interacting with the world around us.
Abstract
Image geolocalization, in which, traditionally, an AI model predicts the precise GPS coordinates of an image is a challenging task with many downstream applications. However, the user cannot utilize the model to further their knowledge other than the GPS coordinate; the model lacks an understanding of the location and the conversational ability to communicate with the user. In recent days, with tremendous progress of large multimodal models (LMMs) proprietary and open-source researchers have attempted to geolocalize images via LMMs. However, the issues remain unaddressed; beyond general tasks, for more specialized downstream tasks, one of which is geolocalization, LMMs struggle. In this work, we propose to solve this problem by introducing a conversational model GAEA that can provide information regarding the location of an image, as required by a user. No large-scale dataset enabling the training of such a model exists. Thus we propose a comprehensive dataset GAEA with 800K images and around 1.6M question answer pairs constructed by leveraging OpenStreetMap (OSM) attributes and geographical context clues. For quantitative evaluation, we propose a diverse benchmark comprising 4K image-text pairs to evaluate conversational capabilities equipped with diverse question types. We consider 11 state-of-the-art open-source and proprietary LMMs and demonstrate that GAEA significantly outperforms the best open-source model, LLaVA-OneVision by 25.69% and the best proprietary model, GPT-4o by 8.28%. Our dataset, model and codes are available