# HO-3D

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

- id: `ho-3d`
- kind: egocentric
- robot or device: one or several fixed RGB-D cameras (not egocentric) (class: other)
- how collected: markerless joint optimisation of hand and object pose over RGB-D sequences
- size as stated: 77,558 frames, 68 sequences, 10 persons, 10 objects
- hours: not stated | hours only claimed: none | episodes: not stated
- year: 2019
- organisation: TU Graz
- licence: not stated (class: not stated)
- access: open (class: open)
- link (paper): https://arxiv.org/abs/1907.01481
- note: Third-person, not egocentric. Parent of the two-hand H2O-3D set.

Confirm the licence at the link before relying on it.