Structural Symmetries from Motion for Scene Reconstruction and Understanding

Natesh Srinivasan, Luca Carlone and Frank Dellaert

Abstract

The identification and description of partial symmetries in man-made structures is a powerful tool to improve the quality of 3D reconstruction from unordered images and to enable high-level understanding of scene geometry. In this work we propose an approach to identify symmetries and exploit them in Structure from Motion (SfM). Our first contribution is a symmetry detection approach that uses the 3D geometry of the scene as well as 2D appearance clues. We show that a particular parametrization of the transformation space (space in which each point represents a candidate symmetry relation) exposes the dominant symmetries in the scene. Then, we use appearance information to prune incorrect symmetry hypotheses. The second contribution is a constrained bundle adjustment (CBA) scheme that jointly optimizes for the best 3D reconstruction and the symmetry generators. Contrarily to related work on CBA, our approach models n-fold (rotational and translational) repetitions of architectural elements, and allows estimating a generative model of the 3D geometry. Experimental results confirm that our method can correctly identify and exploit partial symmetries in noisy and incomplete SfM datasets.

Session

Poster 2

Files

Extended Abstract (PDF, 5M)
Paper (PDF, 9M)

DOI

10.5244/C.29.136
https://dx.doi.org/10.5244/C.29.136

Citation

Bibtex

@inproceedings{BMVC2015_136,
	title={Structural Symmetries from Motion for Scene Reconstruction and Understanding},
	author={Natesh Srinivasan and Luca Carlone and Frank Dellaert},
	year={2015},
	month={September},
	pages={136.1-136.13},
	articleno={136},
	numpages={13},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.136},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.136}
}