Monocular Human Pose and Shape Reconstruction using Part Differentiable Rendering

dc.contributor.authorWang, Minen_US
dc.contributor.authorQiu, Fengen_US
dc.contributor.authorLiu, Wentaoen_US
dc.contributor.authorQian, Chenen_US
dc.contributor.authorZhou, Xiaoweien_US
dc.contributor.authorMa, Lizhuangen_US
dc.contributor.editorEisemann, Elmar and Jacobson, Alec and Zhang, Fang-Lueen_US
dc.description.abstractSuperior human pose and shape reconstruction from monocular images depends on removing the ambiguities caused by occlusions and shape variance. Recent works succeed in regression-based methods which estimate parametric models directly through a deep neural network supervised by 3D ground truth. However, 3D ground truth is neither in abundance nor can efficiently be obtained. In this paper, we introduce body part segmentation as critical supervision. Part segmentation not only indicates the shape of each body part but helps to infer the occlusions among parts as well. To improve the reconstruction with part segmentation, we propose a part-level differentiable renderer that enables part-based models to be supervised by part segmentation in neural networks or optimization loops. We also introduce a general parametric model engaged in the rendering pipeline as an intermediate representation between skeletons and detailed shapes, which consists of primitive geometries for better interpretability. The proposed approach combines parameter regression, body model optimization, and detailed model registration altogether. Experimental results demonstrate that the proposed method achieves balanced evaluation on pose and shape, and outperforms the state-of-the-art approaches on Human3.6M, UP-3D and LSP datasets.en_US
dc.description.sectionheadersHuman Pose
dc.description.seriesinformationComputer Graphics Forum
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputing methodologies
dc.titleMonocular Human Pose and Shape Reconstruction using Part Differentiable Renderingen_US