EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video

• URL: http://arxiv.org/abs/2505.11709v1
• Date: Fri, 16 May 2025 21:34:47 GMT
• Title: EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
• Authors: Ryan Hoque, Peide Huang, David J. Yoon, Mouli Sivapurapu, Jian Zhang,
• Abstract summary: EgoDex is the largest and most diverse dataset of dexterous human manipulation to date.<n>It has 829 hours of egocentric video with paired 3D hand and finger tracking data collected at the time of recording.<n>The dataset covers a wide range of diverse manipulation behaviors with everyday household objects in 194 different tabletop tasks.
• Score: 7.1221123957033905
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Imitation learning for manipulation has a well-known data scarcity problem. Unlike natural language and 2D computer vision, there is no Internet-scale corpus of data for dexterous manipulation. One appealing option is egocentric human video, a passively scalable data source. However, existing large-scale datasets such as Ego4D do not have native hand pose annotations and do not focus on object manipulation. To this end, we use Apple Vision Pro to collect EgoDex: the largest and most diverse dataset of dexterous human manipulation to date. EgoDex has 829 hours of egocentric video with paired 3D hand and finger tracking data collected at the time of recording, where multiple calibrated cameras and on-device SLAM can be used to precisely track the pose of every joint of each hand. The dataset covers a wide range of diverse manipulation behaviors with everyday household objects in 194 different tabletop tasks ranging from tying shoelaces to folding laundry. Furthermore, we train and systematically evaluate imitation learning policies for hand trajectory prediction on the dataset, introducing metrics and benchmarks for measuring progress in this increasingly important area. By releasing this large-scale dataset, we hope to push the frontier of robotics, computer vision, and foundation models.

Related papers

• Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos [66.62109400603394]
  We introduce Being-H0, a dexterous Vision-Language-Action model trained on large-scale human videos.<n>Our approach centers on physical instruction tuning, a novel training paradigm that combines large-scale VLA pretraining from human videos, physical space alignment for 3D reasoning, and post-training adaptation for robotic tasks.<n>We empirically show the excellence of Being-H0 in hand motion generation and instruction following, and it also scales well with model and data sizes.
  arXiv  Detail & Related papers  (2025-07-21T13:19:09Z)
• EgoMimic: Scaling Imitation Learning via Egocentric Video [22.902881956495765]
  We present EgoMimic, a full-stack framework which scales manipulation via human embodiment data. EgoMimic achieves this through: (1) a system to capture human embodiment data using the ergonomic Project Aria glasses, (2) a low-cost bimanual manipulator that minimizes the kinematic gap to human data, and (4) an imitation learning architecture that co-trains on human and robot data.
  arXiv  Detail & Related papers  (2024-10-31T17:59:55Z)
• Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild [66.34146236875822]
  The Nymeria dataset is a large-scale, diverse, richly annotated human motion dataset collected in the wild with multiple multimodal egocentric devices. It contains 1200 recordings of 300 hours of daily activities from 264 participants across 50 locations, travelling a total of 399Km. The motion-language descriptions provide 310.5K sentences in 8.64M words from a vocabulary size of 6545.
  arXiv  Detail & Related papers  (2024-06-14T10:23:53Z)
• EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset [19.496721051685135]
  Embodied tracking is a key component to many egocentric vision problems. EgoTracks is a new dataset for long-term egocentric visual object tracking. We show improvements that can be made to a STARK tracker to significantly increase its performance on egocentric data.
  arXiv  Detail & Related papers  (2023-01-09T09:10:35Z)
• Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats [80.12253291709673]
  We propose a novel affine-combining autoencoder (ACAE) method to perform dimensionality reduction on the number of landmarks. Our approach scales to an extreme multi-dataset regime, where we use 28 3D human pose datasets to supervise one model.
  arXiv  Detail & Related papers  (2022-12-29T22:22:49Z)
• Ego-Body Pose Estimation via Ego-Head Pose Estimation [22.08240141115053]
  Estimating 3D human motion from an egocentric video sequence plays a critical role in human behavior understanding and has various applications in VR/AR. We propose a new method, Ego-Body Pose Estimation via Ego-Head Pose Estimation (EgoEgo), which decomposes the problem into two stages, connected by the head motion as an intermediate representation. This disentanglement of head and body pose eliminates the need for training datasets with paired egocentric videos and 3D human motion.
  arXiv  Detail & Related papers  (2022-12-09T02:25:20Z)
• Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications [20.571026014771828]
  We provide a labeled dataset consisting of 11,243 egocentric images with per-pixel segmentation labels of hands and objects being interacted with. Our dataset is the first to label detailed hand-object contact boundaries. We show that our robust hand-object segmentation model and dataset can serve as a foundational tool to boost or enable several downstream vision applications.
  arXiv  Detail & Related papers  (2022-08-07T21:43:40Z)
• EgoBody: Human Body Shape, Motion and Social Interactions from Head-Mounted Devices [76.50816193153098]
  EgoBody is a novel large-scale dataset for social interactions in complex 3D scenes. We employ Microsoft HoloLens2 headsets to record rich egocentric data streams including RGB, depth, eye gaze, head and hand tracking. To obtain accurate 3D ground-truth, we calibrate the headset with a multi-Kinect rig and fit expressive SMPL-X body meshes to multi-view RGB-D frames.
  arXiv  Detail & Related papers  (2021-12-14T18:41:28Z)
• Understanding Egocentric Hand-Object Interactions from Hand Pose Estimation [24.68535915849555]
  We propose a method to label a dataset which contains the egocentric images pair-wisely. We also use the collected pairwise data to train our encoder-decoder style network which has been proven efficient in.
  arXiv  Detail & Related papers  (2021-09-29T18:34:06Z)
• One Million Scenes for Autonomous Driving: ONCE Dataset [91.94189514073354]
  We introduce the ONCE dataset for 3D object detection in the autonomous driving scenario. The data is selected from 144 driving hours, which is 20x longer than the largest 3D autonomous driving dataset available. We reproduce and evaluate a variety of self-supervised and semi-supervised methods on the ONCE dataset.
  arXiv  Detail & Related papers  (2021-06-21T12:28:08Z)
• Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos [92.38049744463149]
  We introduce an approach for pre-training egocentric video models using large-scale third-person video datasets. Our idea is to discover latent signals in third-person video that are predictive of key egocentric-specific properties. Our experiments show that our Ego-Exo framework can be seamlessly integrated into standard video models.
  arXiv  Detail & Related papers  (2021-04-16T06:10:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.