HOT3D
Meta research
Multi-view egocentric recordings of human hands interacting with objects, with tracking annotations.
What you can explore
Explore hand–object tracking, multi-view perception and the associated hand-tracking toolkit.
Before you use it
These are human observations, not robot action trajectories. Dataset access and MANO or UmeTrack models have their own terms.
Original contributors
HOT3D authors and dataset contributors
License / access: Dataset: HOT3D license agreement · toolkit: Apache 2.0
Keep exploring
Hand Tracking Toolkit
Tools for reading, visualizing and evaluating hand-tracking data and model outputs.
AssemblyHands
Egocentric hand-pose resources for assembly activities and interaction understanding.
DexYCB
Human hand–object RGB-D data for grasp perception and handover research. Explore downloads, annotation fields, official splits and a first Python inspection.
Editorial reference · checked 2026-09-22