Despite advances in hand-object interaction modeling, generating realistic dexterous manipulation data for robotic hands remains a challenge. Retargeting methods often suffer from low accuracy and fail to account for hand-object interactions, leading to artifacts like interpenetration. Generative methods, lacking human hand priors, produce limited and unnatural poses. We propose a data transformation pipeline that combines human hand and object data from multiple sources for high-precision retargeting. Our approach uses a differential loss constraint to ensure temporal consistency and generates contact maps to refine hand-object interactions. Experiments show our method significantly improves pose accuracy, naturalness, and diversity, providing a robust solution for hand-object interaction modeling.
@article{arxiv.2505.01083,
title = {DexFlow: A Unified Approach for Dexterous Hand Pose Retargeting and Interaction},
author = {Xiaoyi Lin and Kunpeng Yao and Lixin Xu and Xueqiang Wang and Xuetao Li and Yuchen Wang and Miao Li},
journal= {arXiv preprint arXiv:2505.01083},
year = {2025}
}