Temporal Parameter-free Deep Skinning of Animated Meshes
This work addresses animation compression in computer graphics, offering a parameter-free solution that improves efficiency for storage and streaming applications, though it appears incremental as it builds on existing skinning techniques.
The paper tackles animation compression for efficient storage and streaming of animated meshes by introducing a deep learning method that assigns vertices to bone-influenced clusters and derives weights from training data, resulting in significantly lower approximation error and fewer bones compared to previous methods.
In computer graphics, animation compression is essential for efficient storage, streaming and reproduction of animated meshes. Previous work has presented efficient techniques for compression by deriving skinning transformations and weights using clustering of vertices based on geometric features of vertices over time. In this work we present a novel approach that assigns vertices to bone-influenced clusters and derives weights using deep learning through a training set that consists of pairs of vertex trajectories (temporal vertex sequences) and the corresponding weights drawn from fully rigged animated characters. The approximation error of the resulting linear blend skinning scheme is significantly lower than the error of competent previous methods by producing at the same time a minimal number of bones. Furthermore, the optimal set of transformation and vertices is derived in fewer iterations due to the better initial positioning in the multidimensional variable space. Our method requires no parameters to be determined or tuned by the user during the entire process of compressing a mesh animation sequence.