In view of the significant effects of deep learning in graphics and image processing, research on human pose estimation methods using deep learning has attracted much attention, and many method models have been produced one after another. On the basis of tracking and in-depth study of domestic and foreign research results, this paper concentrates on 3D single person pose estimation methods, contrasts and analyzes three methods of end-to-end, staged and hybrid network models, and summarizes the characteristics of the methods. For evaluating method performance, set up an experimental environment, and utilize the Human3.6M data set to test several mainstream methods. The test results indicate that the hybrid network model method has a better performance in the field of human pose estimation.