Learning Nonparametric Human Mesh Reconstruction From A Single Image Without Ground Truth Meshes

We present a novel approach to learn human mesh reconstruction without ground truth mesh labels. This is made possible by introducing two new terms into the loss function of a graph convolutional neural network (Graph CNN). The first term is the Laplacian prior that acts as a regularizer on the mesh reconstruction. The second term is the part segmentation loss that forces the projected region of the reconstructed mesh to match the part segmentation. Extensive experiments validate the effectiveness of the proposed approach.