TD-TOG

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

• id: td-tog
• kind: grasping
• robot or device: real RGB-D scenes with affordances and planar grasps (class: sensor only)
• how collected: real capture, hand annotation
• size as stated: 1,449 scenes; 30 categories; 120 subcategories
• hours: not stated | hours only claimed: none | episodes: not stated
• year: 2025
• organisation: not stated
• licence: not stated (class: not stated)
• access: not stated (class: not stated)
• link (paper): https://arxiv.org/abs/2506.05576
• note: Task-oriented grasping benchmark.

Confirm the licence at the link before relying on it.