Existing hands datasets are largely short-range and the interaction is weak due to the self-occlusion and self-similarity of hands, which can not yet fit the need for interacting hands motion generation. To rescue the data scarcity, we propose HandDiffuse12.5M, a novel dataset that consists of temporal sequences with strong two-hand interactions. HandDiffuse12.5M has the largest scale and richest interactions among the existing two-hand datasets. We further present a strong baseline method HandDiffuse for the controllable motion generation of interacting hands using various controllers. Specifically, we apply the diffusion model as the backbone and design two motion representations for different controllers. To reduce artifacts, we also propose Interaction Loss which explicitly quantifies the dynamic interaction process. Our HandDiffuse enables various applications with vivid two-hand interactions, i.e., motion in-betweening and trajectory control. Experiments show that our method outperforms the state-of-the-art techniques in motion generation and can also contribute to data augmentation for other datasets. Our dataset, corresponding codes, and pre-trained models will be disseminated to the community for future research towards two-hand interaction modeling.

翻译：现有的手部数据集大多局限于短程交互且交互强度较弱，这是由于手部的自遮挡和自相似性所致，无法满足交互式手部运动生成的需求。为解决数据匮乏问题，我们提出HandDiffuse12.5M——一个包含强双手交互时序序列的新型数据集。该数据集在现有双手数据集中规模最大、交互最为丰富。我们进一步提出基线方法HandDiffuse，通过多种控制器实现交互手部的可控运动生成。具体而言，我们采用扩散模型作为主干网络，针对不同控制器设计了两种运动表征。为减少伪影，我们引入交互损失函数显式量化动态交互过程。HandDiffuse支持多种生动的双手交互应用，如运动插值和轨迹控制。实验表明，我们的方法在运动生成方面优于现有技术，并能有效扩充其他数据集。我们将公开数据集、相关代码及预训练模型，以推动双手交互建模领域的未来研究。