HO-Cap: Multi-View RGB-D Hand-Object Interaction Dataset Without Motion Capture
YuXiang_IRVL · x · 2026-08-16
HO-Cap is a dataset for 3D reconstruction and pose tracking of hand-object interaction, released by UT Dallas and NVIDIA. The system uses multiple RGB-D cameras and a HoloLens headset for data collection, avoiding expensive 3D scanners or mocap systems. A semi-automatic annotation method significantly reduces annotation time. The dataset includes videos of humans interacting with objects for tasks like pick-and-place, handovers, and affordance usage, serving as human demonstrations for embodied AI and robot manipulation.
More from Embodied
- China's robo-dogs evolve to 3-in-1 in new demo — TinfoilTricorn · 2026-08-24
- WatchGPT app updated with OpenAI's latest real-time speech models — AIandDesign · 2026-08-24
- Delivered a Complete Humanoid Robot Project in Just 30 Days — yongqianme · 2026-08-24
- VR Set Offers Solution for Indoor Cycling During Rainy Season — AryHHAry · 2026-08-24
- Figure Robot Demonstrates Fully Autonomous Stair Climbing — DeryaTR_ · 2026-08-24
- User deploys Qwen 27B locally, connects to HomeAssistant — sshwifty · 2026-08-24