Dataset · YijingGuo
Aerial city panoramas and depth maps for 3D reconstruction
YijingGuo/PanoCity
A large dataset of aerial urban panoramic images and matching depth maps for 3D scene understanding.
What's inside
This massive 1.4 TB dataset includes 119,537 panoramic RGB images and an equal number of depth maps at 2048×4096 resolution in PNG format. The data covers urban blocks across three Chinese cities: Beijing (20 blocks), Jinan (76 blocks), and Ningbo (41 blocks). The repository also provides official train and test splits.
What you can do with it
- Training depth estimation models on panoramic imagery
- Developing image-to-3D urban scene reconstruction algorithms
- Tasks
- Depth estimation, Image → 3d
- Languages
- English
- Size
- 100K–1M rows
- Downloads this month
- 31.5K
- Likes
- 14
How to load it
from datasets import load_dataset
ds = load_dataset("YijingGuo/PanoCity")