Skip to content

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")