mlsanityData to 7 Oct 2026

TerraSky3D: Multi-View Reconstructions of European Landmarks in 4K

arXiv 2603.28287 ↗First posted 30 Mar 2026cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Despite the growing need for data of more and more sophisticated 3D reconstruction pipelines, we can still observe a scarcity of suitable public datasets. Existing 3D datasets are either low resolution, limited to a small amount of scenes, based on images of varying quality because retrieved from the internet, or limited to specific capturing scenarios. Motivated by this lack of suitable 3D datasets, we captured TerraSky3D, a high-resolution large-scale 3D reconstruction dataset comprising 50,000 images divided into 150 ground, aerial, and mixed scenes. The dataset focuses on European landmarks and comes with curated calibration data, camera poses, and depth maps. TerraSky3D tries to answer the need for challenging dataset that can be used to train and evaluate 3D reconstruction-related pipelines.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 27 of its 36 references that are in the map. First posted on arXiv 30 Mar 2026.

Builds on

27 of 36 references.

References · 27

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  3. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  4. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  5. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  6. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  7. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  8. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  9. 2023LightGlue: Local Feature Matching at Light Speedcited by 583
  10. 2020DISK: Learning local features with policy gradientcited by 310
  11. 2023RoMa: Robust Dense Feature Matchingcited by 296
  12. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 295
15 more
  1. 2025π3: Permutation-Equivariant Visual Geometry Learningcited by 292
  2. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 261
  3. 2020Image Matching across Wide Baselines: From Paper to Practicecited by 224
  4. 2024Global Structure-from-Motion Revisitedcited by 215
  5. 2018Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarkingcited by 189
  6. 2020University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localizationcited by 152
  7. 2023ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformationcited by 120
  8. 2023DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matchingcited by 62
  9. 2024MegaScenes: Scene-Level View Synthesis at Scalecited by 58
  10. 2025RoMa v2: Harder Better Faster Denser Feature Matchingcited by 44
  11. 2025AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesiscited by 39
  12. 2023S-TREK: Sequential Translation and Rotation Equivariant Keypoints for local feature extractioncited by 13
  13. 2025RDD: Robust Feature Detector and Descriptor using Deformable Transformercited by 13
  14. 2025CVD-SfM: A Cross-View Deep Front-end Structure-from-Motion System for Sparse Localization in Multi-Altitude Scenescited by 2
  15. 2026A Streamlined Attention-Based Network for Descriptor Extractioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026EPO: Boosting 3D Foundation Models with Edge-based Pose Optimizationcited by 0
  2. 2026Polis: 3D Self-Supervision at City Scalecited by 0