Skip to content

Dataset · sanjay810

Multi-View Urban Scenes from Cars and Drones

sanjay810/mv2-dataset

Synchronized ground and aerial road images with camera parameters for 3D reconstruction and neural rendering.

What's inside

Contains synchronized urban scene image sequences captured simultaneously from multiple viewpoints—ground vehicles and aerial platforms—along with camera parameters. The data volume ranges from 10,000 to 100,000 samples, with descriptions in English. The dataset is designed for academic research in autonomous vehicle perception.

What you can do with it

  • Training novel view synthesis and urban scene 3D reconstruction models
  • Developing depth estimation and segmentation algorithms for autonomous driving
Tasks
Image → image, Depth estimation, Image segmentation
Languages
English
Size
10K–100K rows
Downloads this month
81.7K
Likes
3

How to load it

from datasets import load_dataset

ds = load_dataset("sanjay810/mv2-dataset")