We propose MHR-Net, a novel method for recovering Non-Rigid Shapes from Motion (NRSfM). MHR-Net aims to find a set of reasonable reconstructions for a 2D view, and it also selects the most likely reconstruction from the set. To deal with the challenging unsupervised generation of non-rigid shapes, we develop a new Deterministic Basis and Stochastic Deformation scheme in MHR-Net. The non-rigid shape is first expressed as the sum of a coarse shape basis and a flexible shape deformation, then multiple hypotheses are generated with uncertainty modeling of the deformation part. MHR-Net is optimized with reprojection loss on the basis and the best hypothesis. Furthermore, we design a new Procrustean Residual Loss, which reduces the rigid rotations between similar shapes and further improves the performance. Experiments show that MHR-Net achieves state-of-the-art reconstruction accuracy on Human3.6M, SURREAL and 300-VW datasets.
@article{arxiv.2207.09086,
title = {MHR-Net: Multiple-Hypothesis Reconstruction of Non-Rigid Shapes from 2D Views},
author = {Haitian Zeng and Xin Yu and Jiaxu Miao and Yi Yang},
journal= {arXiv preprint arXiv:2207.09086},
year = {2023}
}
Comments
Accepted to ECCV 2022; code: https://github.com/haitianzeng/MHR-Net