MetaGraspNet / MetaGraspNetV2

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

• id: metagraspnet-metagraspnetv2
• kind: grasping
• robot or device: synthetic and real RGBD bin scenes, parallel-jaw and vacuum labels (class: simulation)
• how collected: physics-based synthesis plus real capture
• size as stated: 217k RGBD images, 82 article types; 2.3k+ real images
• hours: not stated | hours only claimed: none | episodes: not stated
• year: 2022
• organisation: KIT, University of Waterloo
• licence: see repo License.txt (class: unclear)
• access: open (class: open)
• link (dataset): https://github.com/maximiliangilles/MetaGraspNet
• note: Ambidextrous bin picking with amodal and manipulation-order labels.

Confirm the licence at the link before relying on it.