MHR-Net: Multiple-Hypothesis Reconstruction of Non-Rigid Shapes from 2D Views
- Publisher:
- Springer Nature Switzerland
- Publication Type:
- Chapter
- Citation:
- Computer Vision – ECCV 2022, 2022, 13662 LNCS, pp. 1-17
- Issue Date:
- 2022-01-01
Closed Access
Filename | Description | Size | |||
---|---|---|---|---|---|
978-3-031-20086-1_1.pdf | Published version | 1.07 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
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.
Please use this identifier to cite or link to this item: