Newcombe, R., Fox, D., Seitz, S.: DynamicFusion: reconstruction and tracking of non-rigid scenes in real-time. In Proceedings of the 24th Annual ACM Symposium on User Interface Software and Technology (2011) Izadi, S., Kim, D.: Kinectfusion: real-time 3d reconstruction and interaction using a moving depth camera. The experiments on benchmark datasets Human 3.6 M, LSP and a wild dataset demonstrate that our model achieves an accurate and robust estimation of the 3D human body and outperforms the popular competing algorithms in precision and robustness. Furthermore, we use the estimation results given by an end-to-end regression network as the initial values of the parameters, which has been proved to speed up the optimization process. Firstly, a new combined objective function of SMPL parameters is proposed to involve four loss terms on 2D joints, 3D joints, facial landmarks and pose priori, respectively, which increase the reliability of the evaluation results dramatically. All the evaluation tasks are established on the basis of the classic parametric 3D body model SMPL. In this paper, we present an optimization-based algorithm and an innovative framework to reconstruct 3D human body from a single monocular image. Recovering 3D human pose and body shape from a monocular image is a challenging task in computer vision.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |