"Maximizing Rigidity" Revisited: A Convex Programming Approach for Generic 3D Shape Reconstruction from Multiple Perspective Views
Abstract
Rigid structure-from-motion (RSfM) and non-rigid structure-from-motion (NRSfM) have long been treated in the literature as separate (different) problems. Inspired by a previous work which solved directly for 3D scene structure by factoring the relative camera poses out, we revisit the principle of "maximizing rigidity" in structure-from-motion literature, and develop a unified theory which is applicable to both rigid and non-rigid structure reconstruction in a rigidity-agnostic way. We formulate these problems as a convex semi-definite program, imposing constraints that seek to apply the principle of minimizing non-rigidity. Our results demonstrate the efficacy of the approach, with state-of-the-art accuracy on various 3D reconstruction problems.
Cite
Text
Ji et al. ""Maximizing Rigidity" Revisited: A Convex Programming Approach for Generic 3D Shape Reconstruction from Multiple Perspective Views." International Conference on Computer Vision, 2017.Markdown
[Ji et al. ""Maximizing Rigidity" Revisited: A Convex Programming Approach for Generic 3D Shape Reconstruction from Multiple Perspective Views." International Conference on Computer Vision, 2017.](https://mlanthology.org/iccv/2017/ji2017iccv-maximizing/)BibTeX
@inproceedings{ji2017iccv-maximizing,
title = {{"Maximizing Rigidity" Revisited: A Convex Programming Approach for Generic 3D Shape Reconstruction from Multiple Perspective Views}},
author = {Ji, Pan and Li, Hongdong and Dai, Yuchao and Reid, Ian},
booktitle = {International Conference on Computer Vision},
year = {2017},
url = {https://mlanthology.org/iccv/2017/ji2017iccv-maximizing/}
}