OpenStreetView-5M: The Many Roads to Global Visual Geolocation
- URL: http://arxiv.org/abs/2404.18873v1
- Date: Mon, 29 Apr 2024 17:06:44 GMT
- Title: OpenStreetView-5M: The Many Roads to Global Visual Geolocation
- Authors: Guillaume Astruc, Nicolas Dufour, Ioannis Siglidis, Constantin Aronssohn, Nacim Bouia, Stephanie Fu, Romain Loiseau, Van Nguyen Nguyen, Charles Raude, Elliot Vincent, Lintao XU, Hongyu Zhou, Loic Landrieu,
- Abstract summary: We introduce OpenStreetView-5M, a large-scale, open-access dataset comprising over 5.1 million geo-referenced street view images.
In contrast to existing benchmarks, we enforce a strict train/test separation, allowing us to evaluate the relevance of learned geographical features.
To demonstrate the utility of our dataset, we conduct an extensive benchmark of various state-of-the-art image encoders, spatial representations, and training strategies.
- Score: 16.468438245804684
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Determining the location of an image anywhere on Earth is a complex visual task, which makes it particularly relevant for evaluating computer vision algorithms. Yet, the absence of standard, large-scale, open-access datasets with reliably localizable images has limited its potential. To address this issue, we introduce OpenStreetView-5M, a large-scale, open-access dataset comprising over 5.1 million geo-referenced street view images, covering 225 countries and territories. In contrast to existing benchmarks, we enforce a strict train/test separation, allowing us to evaluate the relevance of learned geographical features beyond mere memorization. To demonstrate the utility of our dataset, we conduct an extensive benchmark of various state-of-the-art image encoders, spatial representations, and training strategies. All associated codes and models can be found at https://github.com/gastruc/osv5m.
Related papers
- Towards Vision-Language Geo-Foundation Model: A Survey [65.70547895998541]
Vision-Language Foundation Models (VLFMs) have made remarkable progress on various multimodal tasks.
This paper thoroughly reviews VLGFMs, summarizing and analyzing recent developments in the field.
arXiv Detail & Related papers (2024-06-13T17:57:30Z) - GeoCLIP: Clip-Inspired Alignment between Locations and Images for
Effective Worldwide Geo-localization [61.10806364001535]
Worldwide Geo-localization aims to pinpoint the precise location of images taken anywhere on Earth.
Existing approaches divide the globe into discrete geographic cells, transforming the problem into a classification task.
We propose GeoCLIP, a novel CLIP-inspired Image-to-GPS retrieval approach that enforces alignment between the image and its corresponding GPS locations.
arXiv Detail & Related papers (2023-09-27T20:54:56Z) - Where We Are and What We're Looking At: Query Based Worldwide Image
Geo-localization Using Hierarchies and Scenes [53.53712888703834]
We introduce an end-to-end transformer-based architecture that exploits the relationship between different geographic levels.
We achieve state of the art street level accuracy on 4 standard geo-localization datasets.
arXiv Detail & Related papers (2023-03-07T21:47:58Z) - G^3: Geolocation via Guidebook Grounding [92.46774241823562]
We study explicit knowledge from human-written guidebooks that describe the salient and class-discriminative visual features humans use for geolocation.
We propose the task of Geolocation via Guidebook Grounding that uses a dataset of StreetView images from a diverse set of locations.
Our approach substantially outperforms a state-of-the-art image-only geolocation method, with an improvement of over 5% in Top-1 accuracy.
arXiv Detail & Related papers (2022-11-28T16:34:40Z) - Where in the World is this Image? Transformer-based Geo-localization in
the Wild [48.69031054573838]
Predicting the geographic location (geo-localization) from a single ground-level RGB image taken anywhere in the world is a very challenging problem.
We propose TransLocator, a unified dual-branch transformer network that attends to tiny details over the entire image.
We evaluate TransLocator on four benchmark datasets - Im2GPS, Im2GPS3k, YFCC4k, YFCC26k and obtain 5.5%, 14.1%, 4.9%, 9.9% continent-level accuracy improvement.
arXiv Detail & Related papers (2022-04-29T03:27:23Z) - Danish Airs and Grounds: A Dataset for Aerial-to-Street-Level Place
Recognition and Localization [9.834635805575584]
We contribute with the emphDanish Airs and Grounds dataset, a large collection of street-level and aerial images targeting such cases.
The dataset is larger and more diverse than current publicly available data, including more than 50 km of road in urban, suburban and rural areas.
We propose a map-to-image re-localization pipeline, that first estimates a dense 3D reconstruction from the aerial images and then matches query street-level images to street-level renderings of the 3D model.
arXiv Detail & Related papers (2022-02-03T19:58:09Z) - Visual and Object Geo-localization: A Comprehensive Survey [11.120155713865918]
Geo-localization refers to the process of determining where on earth some entity' is located.
This paper provides a comprehensive survey of geo-localization involving images, which involves either determining from where an image has been captured (Image geo-localization) or geo-locating objects within an image (Object geo-localization)
We will provide an in-depth study, including a summary of popular algorithms, a description of proposed datasets, and an analysis of performance results to illustrate the current state of each field.
arXiv Detail & Related papers (2021-12-30T20:46:53Z) - Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset,
Benchmarks and Challenges [52.624157840253204]
We present an urban-scale photogrammetric point cloud dataset with nearly three billion richly annotated points.
Our dataset consists of large areas from three UK cities, covering about 7.6 km2 of the city landscape.
We evaluate the performance of state-of-the-art algorithms on our dataset and provide a comprehensive analysis of the results.
arXiv Detail & Related papers (2020-09-07T14:47:07Z) - Google Landmarks Dataset v2 -- A Large-Scale Benchmark for
Instance-Level Recognition and Retrieval [9.922132565411664]
We introduce the Google Landmarks dataset v2 (GLDv2), a new benchmark for large-scale, fine-grained instance recognition and image retrieval.
GLDv2 is the largest such dataset to date by a large margin, including over 5M images and 200k distinct instance labels.
The dataset is sourced from Wikimedia Commons, the world's largest crowdsourced collection of landmark photos.
arXiv Detail & Related papers (2020-04-03T22:52:17Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.