Dexterous Manipulation Policies from RGB Human Videos via 3D Hand-Object Trajectory Reconstruction
- URL: http://arxiv.org/abs/2602.09013v2
- Date: Wed, 11 Feb 2026 23:32:41 GMT
- Title: Dexterous Manipulation Policies from RGB Human Videos via 3D Hand-Object Trajectory Reconstruction
- Authors: Hongyi Chen, Tony Dong, Tiancheng Wu, Liquan Wang, Yash Jangir, Yaru Niu, Yufei Ye, Homanga Bharadhwaj, Zackory Erickson, Jeffrey Ichnowski,
- Abstract summary: We propose VIDEOMANIP, a device-free framework that learns dexterous manipulation directly from RGB human videos.<n>In simulation, the learned grasping model achieves a 70.25% success rate across 20 diverse objects using the Inspire Hand.<n>In the real world, manipulation policies trained from RGB videos achieve an average 62.86% success rate across seven tasks using the LEAP Hand.
- Score: 24.49384094440561
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Multi-finger robotic hand manipulation and grasping are challenging due to the high-dimensional action space and the difficulty of acquiring large-scale training data. Existing approaches largely rely on human teleoperation with wearable devices or specialized sensing equipment to capture hand-object interactions, which limits scalability. In this work, we propose VIDEOMANIP, a device-free framework that learns dexterous manipulation directly from RGB human videos. Leveraging recent advances in computer vision, VIDEOMANIP reconstructs explicit 3D robot-object trajectories from monocular videos by estimating human hand poses, object meshes, and retargets the reconstructed human motions to robotic hands for manipulation learning. To make the reconstructed robot data suitable for dexterous manipulation training, we introduce hand-object contact optimization with interaction-centric grasp modeling, as well as a demonstration synthesis strategy that generates diverse training trajectories from a single video, enabling generalizable policy learning without additional robot demonstrations. In simulation, the learned grasping model achieves a 70.25% success rate across 20 diverse objects using the Inspire Hand. In the real world, manipulation policies trained from RGB videos achieve an average 62.86% success rate across seven tasks using the LEAP Hand, outperforming retargeting-based methods by 15.87%. Project videos are available at videomanip.github.io.
Related papers
- H2R-Grounder: A Paired-Data-Free Paradigm for Translating Human Interaction Videos into Physically Grounded Robot Videos [58.006918399913665]
We propose a video-to-video translation framework that converts ordinary human-object interaction videos into motion-consistent robot manipulation videos.<n>Our approach does not require any paired human-robot videos for training only a set of unpaired robot videos, making the system easy to scale.<n>At test time, we apply the same process to human videos (inpainting the person and overlaying human pose cues) and generate high-quality robot videos that mimic the human's actions.
arXiv Detail & Related papers (2025-12-10T07:59:45Z) - Dexterity from Smart Lenses: Multi-Fingered Robot Manipulation with In-the-Wild Human Demonstrations [52.29884993824894]
Learning multi-fingered robot policies from humans performing daily tasks in natural environments has long been a grand goal in the robotics community.<n>AINA enables learning multi-fingered policies from data collected by anyone, anywhere, and in any environment using Aria Gen 2 glasses.
arXiv Detail & Related papers (2025-11-20T18:59:02Z) - Object-centric 3D Motion Field for Robot Learning from Human Videos [56.9436352861611]
We propose to use object-centric 3D motion field to represent actions for robot learning from human videos.<n>We present a novel framework for extracting this representation from videos for zero-shot control.<n> Experiments show that our method reduces 3D motion estimation error by over 50% compared to the latest method.
arXiv Detail & Related papers (2025-06-04T17:59:06Z) - VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation [53.63540587160549]
VidBot is a framework enabling zero-shot robotic manipulation using learned 3D affordance from in-the-wild monocular RGB-only human videos.<n> VidBot paves the way for leveraging everyday human videos to make robot learning more scalable.
arXiv Detail & Related papers (2025-03-10T10:04:58Z) - OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation [35.97702591413093]
We introduce OKAMI, a method that generates a manipulation plan from a single RGB-D video.
OKAMI uses open-world vision models to identify task-relevant objects and retarget the body motions and hand poses separately.
arXiv Detail & Related papers (2024-10-15T17:17:54Z) - Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstruction [51.49400490437258]
This work develops a method for imitating articulated object manipulation from a single monocular RGB human demonstration.
We first propose 4D Differentiable Part Models (4D-DPM), a method for recovering 3D part motion from a monocular video.
Given this 4D reconstruction, the robot replicates object trajectories by planning bimanual arm motions that induce the demonstrated object part motion.
We evaluate 4D-DPM's 3D tracking accuracy on ground truth annotated 3D part trajectories and RSRD's physical execution performance on 9 objects across 10 trials each on a bimanual YuMi robot.
arXiv Detail & Related papers (2024-09-26T17:57:16Z) - Learning Reward Functions for Robotic Manipulation by Observing Humans [92.30657414416527]
We use unlabeled videos of humans solving a wide range of manipulation tasks to learn a task-agnostic reward function for robotic manipulation policies.
The learned rewards are based on distances to a goal in an embedding space learned using a time-contrastive objective.
arXiv Detail & Related papers (2022-11-16T16:26:48Z) - From One Hand to Multiple Hands: Imitation Learning for Dexterous
Manipulation from Single-Camera Teleoperation [26.738893736520364]
We introduce a novel single-camera teleoperation system to collect the 3D demonstrations efficiently with only an iPad and a computer.
We construct a customized robot hand for each user in the physical simulator, which is a manipulator resembling the same kinematics structure and shape of the operator's hand.
With imitation learning using our data, we show large improvement over baselines with multiple complex manipulation tasks.
arXiv Detail & Related papers (2022-04-26T17:59:51Z) - Towards unconstrained joint hand-object reconstruction from RGB videos [81.97694449736414]
Reconstructing hand-object manipulations holds a great potential for robotics and learning from human demonstrations.
We first propose a learning-free fitting approach for hand-object reconstruction which can seamlessly handle two-hand object interactions.
arXiv Detail & Related papers (2021-08-16T12:26:34Z)
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.