RealDex
4DVLab / RealDex team
Real-world dexterous robot grasp recordings for learning human-like manipulation.
What you can explore
Explore the documented capture setup, multimodal observations and learning pipeline.
Before you use it
Results depend on the recorded hand and task distribution. Confirm current file access and data permissions before training or redistribution.
Original contributors
RealDex authors and dataset contributors
License / access: Check original code, model and data terms before reuse
Keep exploring
DexH2R
A benchmark for dynamic human-to-robot handovers with dexterous hands.
DexYCB
Human hand–object RGB-D data for grasp perception and handover research. Explore downloads, annotation fields, official splits and a first Python inspection.
DexGraspNet
Synthetic dexterous grasp configurations generated for a Shadow Hand and validated in simulation.
Editorial reference · checked 2026-09-22