Articulated Kinematics Distillation from Video Diffusion Models
This work addresses the challenge of producing physically plausible and consistent articulated motions for 3D character animation, representing an incremental improvement over prior methods.
The paper tackles the problem of generating high-fidelity character animations by merging skeleton-based animation with generative models, resulting in superior 3D consistency and motion quality compared to existing text-to-4D generation methods.
We present Articulated Kinematics Distillation (AKD), a framework for generating high-fidelity character animations by merging the strengths of skeleton-based animation and modern generative models. AKD uses a skeleton-based representation for rigged 3D assets, drastically reducing the Degrees of Freedom (DoFs) by focusing on joint-level control, which allows for efficient, consistent motion synthesis. Through Score Distillation Sampling (SDS) with pre-trained video diffusion models, AKD distills complex, articulated motions while maintaining structural integrity, overcoming challenges faced by 4D neural deformation fields in preserving shape consistency. This approach is naturally compatible with physics-based simulation, ensuring physically plausible interactions. Experiments show that AKD achieves superior 3D consistency and motion quality compared with existing works on text-to-4D generation. Project page: https://research.nvidia.com/labs/dir/akd/