Ego-Exo4D Human Meshes Dataset: 4D Human Motion Reconstruction for Ego-Exo Captures
cs.CV, cs.RO
Submitted: 2026-09-24
Updated: 2026-09-24
Comments: Project website: https://abhiram824.github.io/egoexo4d_human_meshes
Code: https://github.com/zju3dv/EasyMocap
Project page: https://abhiram824.github.io/egoexo4d_human_meshes
License: http://creativecommons.org/licenses/by/4.0/
The gist: Ego-Exo4D is a large-scale dataset providing synchronized egocentric and multi-view exocentric video, a rich resource for skill learning and assessment, procedural activity understanding, and
Terminology
Abstract
Ego-Exo4D is a large-scale dataset providing synchronized egocentric and multi-view exocentric video, a rich resource for skill learning and assessment, procedural activity understanding, and embodied AI. However, the dataset ships with only sparse 3D human pose annotations, and reconstructing dense human motion from its multi-view captures is nontrivial. To this end, we present Ego-Exo4D-HM, a large-scale dataset of 4D human motion reconstructions for Ego-Exo4D's captures, and release the accompanying reconstruction pipeline. The code, dataset, and documentation can be found at https://abhiram824.github.io/egoexo4d human meshes.
Sources
- World Models for Learning Dexterous Hand-Object Interactions from Human Videos
- The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimation
- ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos
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