Enregistré dans:
Détails bibliographiques
Auteurs principaux: Bieri, Valentin, Zamboni, Marco, Blumer, Nicolas S., Chen, Qingxuan, Engelmann, Francis
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2503.16776
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909547177705472
author Bieri, Valentin
Zamboni, Marco
Blumer, Nicolas S.
Chen, Qingxuan
Engelmann, Francis
author_facet Bieri, Valentin
Zamboni, Marco
Blumer, Nicolas S.
Chen, Qingxuan
Engelmann, Francis
contents Vision-language models (VLMs) show great promise for 3D scene understanding but are mainly applied to indoor spaces or autonomous driving, focusing on low-level tasks like segmentation. This work expands their use to urban-scale environments by leveraging 3D reconstructions from multi-view aerial imagery. We propose OpenCity3D, an approach that addresses high-level tasks, such as population density estimation, building age classification, property price prediction, crime rate assessment, and noise pollution evaluation. Our findings highlight OpenCity3D's impressive zero-shot and few-shot capabilities, showcasing adaptability to new contexts. This research establishes a new paradigm for language-driven urban analytics, enabling applications in planning, policy, and environmental monitoring. See our project page: opencity3d.github.io
format Preprint
id arxiv_https___arxiv_org_abs_2503_16776
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OpenCity3D: What do Vision-Language Models know about Urban Environments?
Bieri, Valentin
Zamboni, Marco
Blumer, Nicolas S.
Chen, Qingxuan
Engelmann, Francis
Computer Vision and Pattern Recognition
Vision-language models (VLMs) show great promise for 3D scene understanding but are mainly applied to indoor spaces or autonomous driving, focusing on low-level tasks like segmentation. This work expands their use to urban-scale environments by leveraging 3D reconstructions from multi-view aerial imagery. We propose OpenCity3D, an approach that addresses high-level tasks, such as population density estimation, building age classification, property price prediction, crime rate assessment, and noise pollution evaluation. Our findings highlight OpenCity3D's impressive zero-shot and few-shot capabilities, showcasing adaptability to new contexts. This research establishes a new paradigm for language-driven urban analytics, enabling applications in planning, policy, and environmental monitoring. See our project page: opencity3d.github.io
title OpenCity3D: What do Vision-Language Models know about Urban Environments?
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.16776