Jihyeok Mun  Taesoo Kwon

10.5626/JOK.2019.46.7.606

Hybrid Approach animation Motion Capture walking motion

A hybrid method that integrates both motion capture based method and physics-based method allows natural walking motion. The hybrid method has the advantage of generating diverse walking motions from limited data. However, limited by recorded data, one of the disadvantage associated with hybrid method is that, only the walking style similar to capture motion could be performed. This disadvantage prevents the character from following a specific user-specified path. In a bid to overcome this problem we propose a method that generates a new walking motion by modifying the recorded data. In the learning step, some variables related to a walking style is obtained by analyzing the captured walking and running data. In the synthesis step, we generated a new walking style such as sidesteps or backward walks by modifying those variables. The proposed algorithm can generate a specific path-following motion which cannot be generated using existing approaches.