Controlling Avatar Diffusion with Learnable Gaussian Embedding
This work addresses the challenge of generating realistic and consistent digital avatars for applications in animation, gaming, and virtual reality, representing an incremental improvement over prior methods.
The paper tackles the problem of maintaining 3D consistency, temporal coherence, and motion accuracy in diffusion-based digital human generation by introducing a learnable neural Gaussian embedding as a novel control signal, and it shows that the model outperforms existing methods in realism, expressiveness, and 3D consistency through extensive experiments.
Recent advances in diffusion models have made significant progress in digital human generation. However, most existing models still struggle to maintain 3D consistency, temporal coherence, and motion accuracy. A key reason for these shortcomings is the limited representation ability of commonly used control signals(e.g., landmarks, depth maps, etc.). In addition, the lack of diversity in identity and pose variations in public datasets further hinders progress in this area. In this paper, we analyze the shortcomings of current control signals and introduce a novel control signal representation that is optimizable, dense, expressive, and 3D consistent. Our method embeds a learnable neural Gaussian onto a parametric head surface, which greatly enhances the consistency and expressiveness of diffusion-based head models. Regarding the dataset, we synthesize a large-scale dataset with multiple poses and identities. In addition, we use real/synthetic labels to effectively distinguish real and synthetic data, minimizing the impact of imperfections in synthetic data on the generated head images. Extensive experiments show that our model outperforms existing methods in terms of realism, expressiveness, and 3D consistency. Our code, synthetic datasets, and pre-trained models will be released in our project page: https://ustc3dv.github.io/Learn2Control/