A system and method for creating 3D graphics representations from video. The method includes: generating a skeletal model for each of at least one non-rigid object shown in a video feed, wherein the video feed illustrates a sports event in which at least one of the non-rigid objects is moving; determining at least one 3D rigged model for the at least one skeletal model; and rendering the at least one skeletal model as a 3D representation of the sports event, wherein rendering the 3D skeletal model further comprises wrapping each of at least one 3D skeletal model with one of the at least one 3D rigged model, each 3D skeletal model corresponding to one of the at least one skeletal model, wherein each 3D rigged model is moved according to the movement of the respective skeletal model when the 3D skeletal model is wrapped with the 3D rigged model.