HandDiffuse: Generative Controllers for Two-Hand Interactions via Diffusion Models
This addresses data scarcity and weak interactions in two-hand motion generation for applications like animation and robotics, though it is incremental as it builds on existing diffusion models.
The authors tackled the problem of generating realistic two-hand interactions by creating HandDiffuse12.5M, a large-scale dataset with strong interactions, and developed a diffusion-based method that outperforms state-of-the-art techniques in motion generation.
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.