Automatic Stylized Action Generation in Animation Using Deep Learning

The style of animation plays a pivotal role in character animation, reflecting various aspects of a character such as emotions, personality, or traits. However, capturing these stylized actions is challenging due to the subjective perceptions of human observers and the resource-intensive nature of traditional methods like action capture devices and manual animation. This study proposes a novel approach utilizing semi-supervision learning to generate high-quality stylized animations. Specifically, our method combines labeled and unlabeled animation data to train stylization models, employing spatiotemporal graph convolutional networks (ST-GCN) and StyleNet modules. The ST-GCN leverages the topological information of the character skeleton to enhance network representation capabilities, while StyleNet modules enable the transfer of both global and local styles. By incorporating content coherence loss, style triplet margin loss, content retention loss, and stylization loss, our approach ensures coherent stylization and improved generalization to unknown content animations. Experimental results demonstrate that our method significantly outperforms existing techniques in generating high-quality, coherent stylized animations.