Towards Robust 3D Pose Transfer with Adversarial Learning

Figure 1. Examples of our 3D pose transfer results on various pose sources, show strong robustness and generalizability. The pose source includes clean mesh (top left) and point clouds with Gaussian noise (bottom left) from SMPL-NPT dataset [41], the adversarial sample of point cloud generated by our method (top right), and raw scan (bottom right) from DFAUST dataset [5]. Identity meshes are from the SMPL-NPT dataset [41] and the FAUST [3] (bottom right) dataset. Our method can achieve promising pose transfer performance even on the extremely challenging incomplete raw scan (bottom right). See more results and details in the Supplementary Materials.