This thesis presents algorithmic solutions for some of the problems that arise in the creation of high quality animation of real-world people using multi-view video data. First a
method for creating realistic personalized human avatar is described. Afterward, enhancements for producing high quality relightable 3D videos are presented. Thereafter, a
method to add high quality time-varying details to dynamic geometry is described. Finally, a dense 3D correspondence finding method that enables spatio-temporally coherent
reconstruction of surface animations directly from multi-view video data is presented.