AI Paper Atlas

Research map / 3D vision / 3D generation

AirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Vision

Xiaoya Cheng, Rouwan Wu, Xinyi Liu, Zeyu Cui, Yan Liu, Na Zhao, Yu Liu, Maojun Zhang, Shen Yan

ECCV 2026 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fine-tune on AirZooMegaLoc · UAV-VisLoc (real, zero-shot)Recall@1: 26.91 -> 28.64Improved
fine-tune on AirZooMegaLoc · AirZoo-Real geo-localization (real, zero-shot)Recall@1: 6.46 -> 18.66Improved
fine-tune on AirZooMegaLoc · AirZoo-Real geo-localization (real, zero-shot)Recall@5: 22.16 -> 50.53Improved
fine-tune on AirZooMegaLoc · UAV-VisLoc Scene 7Recall@1: 38.46 -> 26.92Hurt
fine-tune on AirZoo (with MegaDepth)RoMa · AerialExtreMatch 6-DoF localization (5m, 1deg)pose recall (5m, 1deg): 95.83 -> 96.21Improved
fine-tune on AirZoo (with MegaDepth)RoMa · AirZoo-Real translation matchingacc@5m: 44.95 -> 79.78Improved
fine-tune on AirZoo (with MegaDepth)RoMa · AirZoo-Real translation matchingmedian translation error (m): 5.87 -> 3.03Improved
use AirZoo fine-tuning instead of GIM video-trained RoMaRoMa · AerialExtreMatch 6-DoF localization (5m, 1deg)pose recall (5m, 1deg): 94.32 -> 96.21Improved
fine-tune on AirZooVGGT · UrbanScene3DF1: 43.38 -> 52.61Improved
fine-tune on AirZooVGGT · AirZoo-Test (synthetic)F1: 67.67 -> 77.32Improved
fine-tune on AirZooVGGT · UAVScenesF1: 86.20 -> 86.98Improved
fine-tune on AirZooVGGT · AirZoo-Real reconstructionF1: 42.48 -> 43.67Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy