SignAvatar: Sign Language 3D Motion Reconstruction and Generation
This work addresses the challenge of creating realistic 3D sign language animations for applications in accessibility and communication, though it is incremental as it builds on existing methods for motion generation.
The paper tackles the problem of 3D motion reconstruction and generation for isolated sign words by introducing SignAvatar, a transformer-based conditional variational autoencoder framework, which achieves superior performance in both tasks as demonstrated through extensive experiments.
Achieving expressive 3D motion reconstruction and automatic generation for isolated sign words can be challenging, due to the lack of real-world 3D sign-word data, the complex nuances of signing motions, and the cross-modal understanding of sign language semantics. To address these challenges, we introduce SignAvatar, a framework capable of both word-level sign language reconstruction and generation. SignAvatar employs a transformer-based conditional variational autoencoder architecture, effectively establishing relationships across different semantic modalities. Additionally, this approach incorporates a curriculum learning strategy to enhance the model's robustness and generalization, resulting in more realistic motions. Furthermore, we contribute the ASL3DWord dataset, composed of 3D joint rotation data for the body, hands, and face, for unique sign words. We demonstrate the effectiveness of SignAvatar through extensive experiments, showcasing its superior reconstruction and automatic generation capabilities. The code and dataset are available on the project page.