# Dense Object Nets data

From the catalogue. Listed by one researcher from one source page.

- id: `dense-object-nets-data`
- kind: real manipulation scripted or autonomous
- robot or device: robot-mounted RGBD scans of objects (class: single arm)
- how collected: autonomous robot scanning
- size as stated: not stated
- hours: not stated | hours only claimed: none | episodes: not stated
- year: 2018
- organisation: MIT
- licence: see repo LICENSE (class: unclear)
- access: open (class: open)
- link (dataset): https://github.com/RobotLocomotion/pytorch-dense-correspondence
- note: Self-supervised dense descriptor training scenes.

Confirm the licence at the link before relying on it.