EgoWholeView: Camera-Only Head-Mounted Capture of Body and Bimanual Hand Motion for Embodied Demonstrations
cs.CV
Submitted: 2026-10-12
Updated: 2026-10-12
Comments: 17 pages, 9 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- The Monado SLAM Dataset for Egocentric Visual-Inertial Tracking
- Project Aria: A New Tool for Egocentric Multi-Modal AI Research
- OmniHands: Towards Robust 4D Hand Mesh Recovery via A Versatile Transformer
- GeoHand: Unlocking Prior Geometry Knowledge for Monocular 3D Hand Reconstruction
- Self-Avatar Animation in Virtual Reality: Impact of Motion Signals Artifacts on the Full-Body Pose Reconstruction
- Towards Egocentric 3D Hand Pose Estimation in Unseen Domains
- Egocentric Whole-Body Human Mesh Recovery with Prior-Guided Learning
- WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild
- Ego-Exo 3D Hand Tracking in the Wild with a Mobile Multi-Camera Rig
- MultiCol-SLAM - A Modular Real-Time Multi-Camera SLAM System
- SurfaceXR: Fusing Smartwatch IMUs and Egocentric Hand Pose for Seamless Surface Interactions
- HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos
- RoboWheel: A Data Engine from Real-World Human Demonstrations for Cross-Embodiment Robotic Learning
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models