In the computer animation based on motion capture, most of the available approaches to edit motion only deal with single character motion, which are mostly planned beforehand. Thus, characters lack the capability of responding to the environments. To improve the characters’ ability to sense and respond to the environment, collaborate with each other, a new concept of motion fusion, which fuses multiple single-character motions captured in the structured environment into one unstructured virtual one, is presented in this paper. Based on the architecture of multi-character motion fusion with virtual scene which covers motion decision, motion collaboration, motion solving and motion execution, the key issues such as motion capture, planning, collaboration and generation of continuous movement and discrete movement are discussed in detail in this paper. The experimental results demonstrate that the presented method can efficiently fuse the motion of characters with virtual scenes. The independent collaboration of animated characters and high reuse enable the application of the presented idea into computer animation and game.