MHR-Net: Multiple-Hypothesis Reconstruction of Non-Rigid Shapes from 2D Views
This addresses the challenge of reconstructing non-rigid shapes from motion for applications like human pose estimation, though it appears incremental as it builds on existing NRSfM methods.
The paper tackles the problem of recovering non-rigid shapes from 2D views by proposing MHR-Net, which generates multiple hypotheses and selects the most likely one, achieving state-of-the-art reconstruction accuracy on Human3.6M, SURREAL, and 300-VW datasets.
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.