DiffSpeaker: Speech-Driven 3D Facial Animation with Diffusion Transformer
This work improves 3D facial animation for multimedia applications, but it is incremental as it builds on existing Diffusion and Transformer methods.
The paper tackled the problem of speech-driven 3D facial animation by addressing the performance limitations of combining Diffusion models and Transformers due to data shortages, resulting in a model that achieves state-of-the-art performance on benchmarks and fast inference speed.
Speech-driven 3D facial animation is important for many multimedia applications. Recent work has shown promise in using either Diffusion models or Transformer architectures for this task. However, their mere aggregation does not lead to improved performance. We suspect this is due to a shortage of paired audio-4D data, which is crucial for the Transformer to effectively perform as a denoiser within the Diffusion framework. To tackle this issue, we present DiffSpeaker, a Transformer-based network equipped with novel biased conditional attention modules. These modules serve as substitutes for the traditional self/cross-attention in standard Transformers, incorporating thoughtfully designed biases that steer the attention mechanisms to concentrate on both the relevant task-specific and diffusion-related conditions. We also explore the trade-off between accurate lip synchronization and non-verbal facial expressions within the Diffusion paradigm. Experiments show our model not only achieves state-of-the-art performance on existing benchmarks, but also fast inference speed owing to its ability to generate facial motions in parallel.