Image geolocalization is a fundamental yet challenging task, aiming at inferring the geolocation on Earth where an image is taken. State-of-the-art methods employ either grid-based classification or gallery-based image-location retrieval, whose spatial generalizability significantly suffers if the spatial distribution of test images does not align with the choices of grids and galleries. Recently emerging generative approaches, while getting rid of grids and galleries, use raw geographical coordinates and suffer quality losses due to their lack of multi-scale information. To address these limitations, we propose a multi-scale latent diffusion model called LocDiff for image geolocalization. We developed a novel positional encoding-decoding framework called Spherical Harmonics Dirac Delta (SHDD) Representations, which encodes points on a spherical surface (e.g., geolocations on Earth) into a Hilbert space of Spherical Harmonics coefficients and decodes points (geolocations) by mode-seeking on spherical probability distributions. We also propose a novel SirenNet-based architecture (CS-UNet) to learn an image-based conditional backward process in the latent SHDD space by minimizing a latent KL-divergence loss. To the best of our knowledge, LocDiff is the first image geolocalization model that performs latent diffusion in a multi-scale location encoding space and generates geolocations under the guidance of images. Experimental results show that LocDiff can outperform all state-of-the-art grid-based, retrieval-based, and diffusion-based baselines across 5 challenging global-scale image geolocalization datasets, and demonstrates significantly stronger generalizability to unseen geolocations.

Worldwide image geolocalization--the task of predicting GPS coordinates from images taken anywhere on Earth--poses a fundamental challenge due to the vast diversity in visual content across regions. While recent approaches adopt a twostage pipeline of retrieving candidates and selecting the best match, they typically rely on simplistic similarity heuristics and point-wise supervision, failing to model spatial relationships among candidates. In this paper, we propose GeoRanker, a distance-aware ranking framework that leverages large vision-language models to jointly encode query-candidate interactions and predict geographic proximity. In addition, we introduce a multi-order distance loss that ranks both absolute and relative distances, enabling the model to reason over structured spatial relationships. To support this, we curate GeoRanking, the first dataset explicitly designed for geographic ranking tasks with multimodal candidate information. GeoRanker achieves state-of-the-art results on two well-established benchmarks (IM2GPS3K and YFCC4K), significantly outperforming current best methods. We also release our code, checkpoint, and dataset online2 for ease of reproduction.

As a result, existing studies have clear limitations whenscaledtoaworldwidecontext.

Image geolocalization, the task of determining an image's geographic origin, poses significant challenges, largely due to visual similarities across disparate locations and the large search space. To address these issues, we propose a hierarchical sequence prediction approach inspired by how humans narrow down locations from broad regions to specific addresses. Analogously, our model predicts geographic tokens hierarchically, first identifying a general region and then sequentially refining predictions to increasingly precise locations. Rather than relying on explicit semantic partitions, our method uses S2 cells, a nested, multiresolution global grid, and sequentially predicts finer-level cells conditioned on visual inputs and previous predictions. This procedure mirrors autoregressive text generation in large language models. Much like in language modeling, final performance depends not only on training but also on inference-time strategy. We investigate multiple top-down traversal methods for autoregressive sampling, incorporating techniques from test-time compute scaling used in language models. Specifically, we integrate beam search and multi-sample inference while exploring various selection strategies to determine the final output. This enables the model to manage uncertainty by exploring multiple plausible paths through the hierarchy. We evaluate our method on the Im2GPS3k and YFCC4k datasets against two distinct sets of baselines: those that operate without a Multimodal Large Language Model (MLLM) and those that leverage one. In the MLLM-free setting, our model surpasses other comparable baselines on nearly all metrics, achieving state-of-the-art performance with accuracy gains of up to 13.9%. When augmented with an MLLM, our model outperforms all baselines, setting a new state-of-the-art across all metrics. The source code is available at https://github.com/NNargesNN/GeoToken.

Determining the precise geographic location of an image at a global scale remains an unsolved challenge. Standard image retrieval techniques are inefficient due to the sheer volume of images (>100M) and fail when coverage is insufficient. Scalable solutions, however, involve a trade-off: global classification typically yields coarse results (10+ kilometers), while cross-view retrieval between ground and aerial imagery suffers from a domain gap and has been primarily studied on smaller regions. This paper introduces a hybrid approach that achieves fine-grained geo-localization across a large geographic expanse the size of a continent. We leverage a proxy classification task during training to learn rich feature representations that implicitly encode precise location information. We combine these learned prototypes with embeddings of aerial imagery to increase robustness to the sparsity of ground-level data. This enables direct, fine-grained retrieval over areas spanning multiple countries. Our extensive evaluation demonstrates that our approach can localize within 200m more than 68\% of queries of a dataset covering a large part of Europe. The code is publicly available at https://scaling-geoloc.github.io.

Accurate and robust image-based geo-localization at a global scale is challenging due to diverse environments, visually ambiguous scenes, and the lack of distinctive landmarks in many regions. While contrastive learning methods show promising performance by aligning features between street-view images and corresponding locations, they neglect the underlying spatial dependency in the geographic space. As a result, they fail to address the issue of false negatives -- image pairs that are both visually and geographically similar but labeled as negatives, and struggle to effectively distinguish hard negatives, which are visually similar but geographically distant. To address this issue, we propose a novel spatially regularized contrastive learning strategy that integrates a semivariogram, which is a geostatistical tool for modeling how spatial correlation changes with distance. We fit the semivariogram by relating the distance of images in feature space to their geographical distance, capturing the expected visual content in a spatial correlation. With the fitted semivariogram, we define the expected visual dissimilarity at a given spatial distance as reference to identify hard negatives and false negatives. We integrate this strategy into GeoCLIP and evaluate it on the OSV5M dataset, demonstrating that explicitly modeling spatial priors improves image-based geo-localization performance, particularly at finer granularity.

--Street-level geolocalization from images is crucial for a wide range of essential applications and services, such as navigation, location-based recommendations, and urban planning. With the growing popularity of social media data and cameras embedded in smartphones, applying traditional computer vision techniques to localize images has become increasingly challenging, yet highly valuable. This paper introduces a novel approach that integrates open-weight and publicly accessible multimodal large language models with retrieval-augmented generation. Query images are augmented with prompts containing both similar and dissimilar geolocation information retrieved from this database before being processed by the multimodal large language models. Our approach has demonstrated state-of-the-art performance, achieving higher accuracy compared against three widely used benchmark datasets (IM2GPS, IM2GPS3k, and YFCC4k). Importantly, our solution eliminates the need for expensive fine-tuning or retraining and scales seamlessly to incorporate new data sources. The effectiveness of retrieval-augmented generation-based multimodal large language models in geolocation estimation demonstrated by this paper suggests an alternative path to the traditional methods which rely on the training models from scratch, opening new possibilities for more accessible and scalable solutions in GeoAI. TREET -LEVEL geolocalization refers to the task of determining the precise geographic location of a scene from one single image [1].

Image geolocalization is a fundamental yet challenging task, aiming at inferring the geolocation on Earth where an image is taken. Existing methods approach it either via grid-based classification or via image retrieval. Their performance significantly suffers when the spatial distribution of test images does not align with such choices. To address these limitations, we propose to leverage diffusion as a mechanism for image geolocalization. To avoid the problematic manifold reprojection step in diffusion, we developed a novel spherical positional encoding-decoding framework, which encodes points on a spherical surface (e.g., geolocations on Earth) into a Hilbert space of Spherical Harmonics coefficients and decodes points (geolocations) by mode-seeking. We call this type of position encoding Spherical Harmonics Dirac Delta (SHDD) Representation. We also propose a novel SirenNet-based architecture called CS-UNet to learn the conditional backward process in the latent SHDD space by minimizing a latent KL-divergence loss. We train a conditional latent diffusion model called LocDiffusion that generates geolocations under the guidance of images -- to the best of our knowledge, the first generative model for image geolocalization by diffusing geolocation information in a hidden location embedding space. We evaluate our method against SOTA image geolocalization baselines. LocDiffusion achieves competitive geolocalization performance and demonstrates significantly stronger generalizability to unseen geolocations.

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