metadata
library_name: diffusers
license: apache-2.0
pipeline_tag: image-to-video
RoboTransfer: Geometry-Consistent Video Diffusion for Robotic Visual Policy Transfer
π Abstract
RoboTransfer is a novel diffusion-based video generation framework tailored for robotic visual policy transfer. Unlike conventional approaches, RoboTransfer introduces geometry-aware synthesis by injecting depth and normal priors, ensuring multi-view consistency across dynamic robotic scenes. The method further supports explicit control over scene components, such as background editing, object identity swapping, and motion specification, offering a fine-grained video generation pipeline that benefits embodied learning.
π§ Key Features
- π Geometry-Consistent Diffusion: Injects global 3D cues (depth, normal) and cross-view interactions for multi-view realism.
- 𧩠Scene Component Control: Enables manipulation of object attributes (pose, identity) and background features.
- π Cross-View Conditioning: Learns representations from multiple camera views with spatial correspondence.
- π€ Robotic Policy Transfer: Facilitates domain adaptation by generating synthetic training data in target domains.
π BibTeX
@article{liu2025robotransfer,
title={RoboTransfer: Geometry-Consistent Video Diffusion for Robotic Visual Policy Transfer},
author={Liu, Liu and Wang, Xiaofeng and Zhao, Guosheng and Li, Keyu Li, Wenkang Qin, Jiaxiong Qiu, Zheng Zhu, Guan Huang, Zhizhong Su},
journal={arXiv preprint arXiv:2505.23171},
year={2025}
}