3DAeroRelief: The first 3D Benchmark UAV Dataset for Post-Disaster Assessment
Nhut Le, Ehsan Karimi, Maryam Rahnemoonfar · 2026
Read 3DAeroRelief: The first 3D Benchmark UAV Dataset for Post-Disaster Assessment by Nhut Le, Ehsan Karimi, Maryam Rahnemoonfar (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13572395.txt.
Description
After a hurricane, judging which buildings are unsafe still leans on flat photos that hide depth and block views. Nhut Le, Ehsan Karimi, and Maryam Rahnemoonfar present 3DAeroRelief, the first three-dimensional benchmark dataset built for disaster assessment. Cheap drones flew over hurricane-hit areas, and their photos were stitched into dense 3D point clouds. Human labels drawn on the photos were projected into the 3D scenes.
The dataset captures large outdoor areas with fine detail on structural damage, a setting missing from older benchmarks that favor city streets and interiors. The team runs several leading 3D segmentation models on it to show where they struggle and where they shine. They offer the data, published in 2026, as a proving ground for vision systems meant to help real disaster response.
Catalog record
| CREATOR | Nhut Le, Ehsan Karimi, Maryam Rahnemoonfar |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |