C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure from Motion
Abstract
We propose C3DPO, a method for extracting 3D models of deformable objects from 2D keypoint annotations in unconstrained images. We do so by learning a deep network that reconstructs a 3D object from a single view at a time, accounting for partial occlusions, and explicitly factoring the effects of viewpoint changes and object deformations. In order to achieve this factorization, we introduce a novel regularization technique. We first show that the factorization is successful if, and only if, there exists a certain canonicalization function of the reconstructed shapes. Then, we learn the canonicalization function together with the reconstruction one, which constrains the result to be consistent. We demonstrate state-of-the-art reconstruction results for methods that do not use ground-truth 3D supervision for a number of benchmarks, including Up3D and PASCAL3D+.
Cite
Text
Novotny et al. "C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure from Motion." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. doi:10.1109/ICCV.2019.00778Markdown
[Novotny et al. "C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure from Motion." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.](https://mlanthology.org/iccv/2019/novotny2019iccv-c3dpo/) doi:10.1109/ICCV.2019.00778BibTeX
@inproceedings{novotny2019iccv-c3dpo,
title = {{C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure from Motion}},
author = {Novotny, David and Ravi, Nikhila and Graham, Benjamin and Neverova, Natalia and Vedaldi, Andrea},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
year = {2019},
doi = {10.1109/ICCV.2019.00778},
url = {https://mlanthology.org/iccv/2019/novotny2019iccv-c3dpo/}
}