MMLandmarks: a Cross-View Instance-Level Benchmark for Geo-Spatial Understanding

🎉 Accepted at CVPR 2026 🎉

Oskar Kristoffersen1,2, Alba Reinders Sánchez1, Morten Rieger Hannemose1,2, Anders Bjorholm Dahl1,2, Dim P. Papadopoulos1,2
1Technical University of Denmark, 2Pioneer Center for AI
Paper arXiv Code Dataset Explore Dataset

TL;DR - What is MMLandmarks ?

  • ✓Four modalities: Ground, Satellite, GPS and Text
  • ✓18,557 unique landmark instances
  • ✓Continental Scale: United States of America
  • ✓Open Access - Publicly Available
  • ✓CC / Public domain licenses

MMLandmarks is a large-scale multimodal benchmark for geo-spatial understanding, uniquely combining four complementary modalities—ground-level imagery, aerial/satellite imagery, GPS coordinates, and Wikipedia text—for the same set of landmarks. Unlike prior datasets that focus on a single view or modality, MMLandmarks enables cross-view and cross-modal retrieval at the instance level. All 18,557 landmarks are geographically distributed across the United States, sourced from OpenStreetMap and Wikimedia Commons under open licenses, making the dataset fully reproducible and suitable for academic research.

Main paper figure

MMLandmarks: We present four distinct data modalities: ground-view images, aerial-view images, GPS coordinates, and textual descriptions, collected from 18,557 unique landmarks in the United States. Data sources are included alongside each modality.

Main paper figure

Collection Pipeline: Tags from OpenStreetMaps are used to collect Wiki-identifiers, ensuring that landmarks have a Wikipedia and Wikimedia Commons page. If both are available, we check that the longest edge of the landmark’s bounding box is smaller than 400 meters to keep an even size distribution across the dataset. Every resulting landmark has a Wikimedia Commons page (ground), a Wikipedia page (text), a box size and center (coordinates), and associated aerial imagery (satellite).

Dataset

Dataset comparison. Modality abbreviations: S - Satellite, G - Ground, T - Text, C - Coordinates, D - Drone. In the Scale column, the number in parentheses indicates the number of cities.
Task Dataset Year Train(G/S) Index(G/S) Instances Scale (Cities) Modalities Open-access License
Geo
localization		 IM2GPS 2008 6.4M/- - - Global G,C ✗ N/A
YFCC100M 2016 100M/- - - Global G,C ✓ Flickr TC
PlaNet 2016 126M/- - - Global G,C ✗ N/A
MP16 2017 4.7M/- - - Global G,C ✓ Flickr TC
OSV-5M 2017 5.1M/- - - Global G,C ✓ CC-BY-SA
Cross-View
Retrieval		 CVUSA 2015 35k/35k 8.8k/8.8k - USA(1) G,S ✓ Flickr TC
Vo. 2016 450k/450k 70k/70k - USA(11) G,S ✓ N/A
CVACT 2019 44k/44k 92k/92k - Australia(1) G,S ✓ N/A
Uni-1652 2020 11.6k/701 5.5k/1652 1652 72 Universities G,S,D ✓ N/A
VIGOR 2021 51k/44k 53k/46k - USA(4) G,S ✓ N/A
CV-Cities 2024 162k/162k 61k/61k - Global(16) G,S ✓ N/A
CVGlobal 2024 134k/134k - - Global(7) G,S ✓ N/A
Landmark
Retrieval		 R-Oxford 2018 - 5k + 1M/- 11 Oxford G ✓ Flickr TC/CC
R-Paris 2018 - 6k + 1M/- 11 Paris G ✓ Flickr TC/CC
GLDv1 2018 1.2M/- 1.1M/- 30k Global G ✗ Multiple
GLDv2 2020 4.1M/- 764k/- 200k Global G ✓ CC/Public-domain
MMLandmarks 2026 329k/197k 714k/100k 18,557 USA G,S,T,C ✓ CC/Public-domain

Examples

BibTeX

@InProceedings{Kristoffersen_2026_MMLandmarks,
  author    = {Oskar Kristoffersen and Alba Reinders and Morten R. Hannemose and Anders B. Dahl and Dim P. Papadopoulos},
  title     = {MMLandmarks: a Cross-View Instance-Level Benchmark for Geo-Spatial Understanding},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month     = {June},
  year      = {2026},
}