Towards Pointless Structure From Motion: 3D Reconstruction and Camera Parameters From General 3D Curves

Irina Nurutdinova, Andrew Fitzgibbon; The IEEE International Conference on Computer Vision (ICCV), 2015, pp. 2363-2371

Abstract


Modern structure from motion (SfM) remains dependent on point features to recover camera positions, meaning that reconstruction is severely hampered in low-texture environments, for example scanning a plain coffee cup on an uncluttered table. We show how 3D curves can be used to refine camera position estimation in challenging low-texture scenes. In contrast to previous work, we allow the curves to be partially observed in all images, meaning that for the first time, curve-based SfM can be demonstrated in realistic scenes. The algorithm is based on bundle adjustment, so needs an initial estimate, but even a poor estimate from a few point correspondences can be substantially improved by including curves, suggesting that this method would benefit many existing systems.

Related Material


[pdf]
[bibtex]
@InProceedings{Nurutdinova_2015_ICCV,
author = {Nurutdinova, Irina and Fitzgibbon, Andrew},
title = {Towards Pointless Structure From Motion: 3D Reconstruction and Camera Parameters From General 3D Curves},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2015}
}