RoboEdit: Turning Human Manipulation Videos into Scalable Robot Experience
RoboEdit: Turning Human Manipulation Videos into Scalable Robot Experience
This paper presents RoboEdit, a system that transforms human manipulation videos into physically plausible robot videos with aligned 3D hand states. The method includes a pipeline for cross-embodiment adaptation and a large-scale dataset of 174K video pairs. Experiments show state-of-the-art editing quality and support for real-world robot control policies.
RoboEdit introduces a novel method to convert human manipulation videos into robot-compatible data, enabling scalable training for diverse robot embodiments. The paper presents a dataset of 174K video pairs and a pipeline for cross-embodiment adaptation, with results showing improved editing quality and support for real-world robot control.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
video pairs
174,000
View original evidence
we introduce RoboEdit-ADC, an automatic pipeline that reconstructs and retargets 3D interactions from RGB videos across embodiments. This pipeline generates RoboEdit-14M, a large-scale dataset of 174K aligned video pairs (14M frames) spanning seven robot embodiments, diverse scenes, and interaction types. The core editing engine, RoboEdit-Trans, employs cross-embodiment adaptation modules to preserve temporal cohere
Open source S3frames
14,000,000
View original evidence
we introduce RoboEdit-ADC, an automatic pipeline that reconstructs and retargets 3D interactions from RGB videos across embodiments. This pipeline generates RoboEdit-14M, a large-scale dataset of 174K aligned video pairs (14M frames) spanning seven robot embodiments, diverse scenes, and interaction types. The core editing engine, RoboEdit-Trans, employs cross-embodiment adaptation modules to preserve temporal cohere
Open source S3Robot count
7 robots
View original evidence
we introduce RoboEdit-ADC, an automatic pipeline that reconstructs and retargets 3D interactions from RGB videos across embodiments. This pipeline generates RoboEdit-14M, a large-scale dataset of 174K aligned video pairs (14M frames) spanning seven robot embodiments, diverse scenes, and interaction types. The core editing engine, RoboEdit-Trans, employs cross-embodiment adaptation modules to preserve temporal cohere
Open source S3
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
we introduce RoboEdit-ADC, an automatic pipeline that reconstructs and retargets 3D interactions from RGB videos across embodiments. This pipeline generates RoboEdit-14M, a large-scale dataset of 174K aligned video pairs (14M frames) spanning seven robot embodiments, diverse scenes, and interaction types. The core editing engine, RoboEdit-Trans, employs cross-embodiment adaptation modules to preserve temporal cohere
Open source S3
nce while adapting appearance and motion. It further integrates a 3D Robot-State Decoder to recover per-frame hand states for structured motion supervision. Experiments show that RoboEdit achieves state-of-the-art editing quality and supports downstream robot control policies in real-world manipulation tasks. Ultimately, the RoboEdit suite unlocks the vast potential of unlabeled human videos, providing scalable, high
Open source S4
Source：arXiv Robotics — research abstracts · arxiv.org