[2003.00052] Learning Nonparametric Human Mesh Reconstruction from a Single Image without Ground Truth Meshescontact arXivarXiv Twitter

Nonparametric approaches have shown promising results on reconstructing 3D human mesh from a single monocular image. Unlike previous approaches that use a parametric human model like skinned multi-person linear model (SMPL), and attempt to regress the model parameters, nonparametric approaches relax the heavy reliance on the parametric space. However, existing nonparametric methods require ground truth meshes as their regression target for each vertex, and obtaining ground truth mesh labels is very expensive. In this paper, we propose a novel approach to learn human mesh reconstruction without any ground truth meshes. 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 reconstructed mesh. The second term is the part segmentation loss that forces the projected region of the reconstructed mesh to match the part segmentation. Experimental resul

2 mentions: @hiroharu_kato
Date: 2020/03/03 12:54

Related Entries

Read more [2001.04552] Deep Learning Stereo Vision at the edgecontact arXivarXiv Twitter
0 users, 1 mentions 2020/01/17 00:51
Read more [2004.08440] Parallelization Techniques for Verifying Neural Networksopen searchopen navigation menu...
0 users, 2 mentions 2020/04/21 17:21
Read more [2004.11419] End-to-end speech-to-dialog-act recognitionopen searchopen navigation menucontact arXiv...
0 users, 1 mentions 2020/05/02 14:21
Read more [2009.07332] Analog vs. Digital Spatial Transforms: A Throughput, Power, and Area Comparisonopen sea...
0 users, 1 mentions 2020/09/17 02:21
Read more [2010.12627] Anchor-based Bilingual Word Embeddings for Low-Resource Languagesopen searchopen naviga...
0 users, 1 mentions 2020/10/27 15:51