Related papers: OpenStreetView-5M: The Many Roads to Global Visual…
Detecting vehicles in satellite images is crucial for traffic management, urban planning, and disaster response. However, current models struggle with real-world diversity, particularly across different regions. This challenge is amplified…
Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, especially in the context of deep learning. For semantic urban…
Cross-view image retrieval, particularly street-to-satellite matching, is a critical task for applications such as autonomous navigation, urban planning, and localization in GPS-denied environments. However, existing approaches often…
Visual Geo-localization (VG) is the task of estimating the position where a given photo was taken by comparing it with a large database of images of known locations. To investigate how existing techniques would perform on a real-world…
Three-dimensional (3D) understanding of objects and scenes play a key role in humans' ability to interact with the world and has been an active area of research in computer vision, graphics, and robotics. Large scale synthetic and…
Visual-Language Models (VLMs) have shown remarkable performance across various tasks, particularly in recognizing geographic information from images. However, VLMs still show regional biases in this task. To systematically evaluate these…
Accurately determining the geographic location where a single image was taken, visual geolocation, remains a formidable challenge due to the planet's vastness and the deceptive similarity among distant locations. We introduce GeoLocSFT, a…
The prevalence of Vision-Language Models (VLMs) raises important questions about privacy in an era where visual information is increasingly available. While foundation VLMs demonstrate broad knowledge and learned capabilities, we…
Waterways shape earth system processes and human societies, and a better understanding of their distribution can assist in a range of applications from earth system modeling to human development and disaster response. Most efforts to date…
Visually recognising a traversed route - regardless of whether seen during the day or night, in clear or inclement conditions, or in summer or winter - is an important capability for navigating robots. Since SeqSLAM was introduced in 2012,…
Worldwide Geo-localization aims to pinpoint the precise location of images taken anywhere on Earth. This task has considerable challenges due to immense variation in geographic landscapes. The image-to-image retrieval-based approaches fail…
This paper presents the Rail-5k dataset for benchmarking the performance of visual algorithms in a real-world application scenario, namely the rail surface defects detection task. We collected over 5k high-quality images from railways…
Cross-modal Geo-localization (CMGL) matches ground-level text descriptions with geo-tagged aerial imagery, which is crucial for pedestrian navigation and emergency response. However, existing researches are constrained by narrow geographic…
Global registration of multi-view robot data is a challenging task. Appearance-based global localization approaches often fail under drastic view-point changes, as representations have limited view-point invariance. This work is based on…
Maps are powerful carriers of structured and contextual knowledge, encompassing geography, demographics, infrastructure, and environmental patterns. Reasoning over such knowledge requires models to integrate spatial relationships, visual…
Existing visual place recognition (VPR) datasets predominantly rely on vehicle-mounted imagery, offer limited multimodal diversity, and underrepresent dense pedestrian street scenes, particularly in non-Western urban contexts. We introduce…
Traffic signs are essential map features globally in the era of autonomous driving and smart cities. To develop accurate and robust algorithms for traffic sign detection and classification, a large-scale and diverse benchmark dataset is…
Federated learning is a new machine learning paradigm which allows data parties to build machine learning models collaboratively while keeping their data secure and private. While research efforts on federated learning have been growing…
Worldwide image geolocalization, which aims to predict the GPS coordinates of any image on Earth, remains challenging due to global visual diversity. Recent generative approaches based on Retrieval-Augmented Generation (RAG) and Large…
OpenStreetMap (OSM), a rich and versatile source of volunteered geographic information (VGI), facilitates human self-localization and scene understanding by integrating nearby visual observations with vectorized map data. However, the…