3D Symmetry Submissions

Why is 3D Symmetry detection useful?

Symmetries and repeating structures pose additional ambiguities in the matching process of structure-from-motion (SfM) approaches as well as in dense multi-view stereo methods and are mostly rejected as outliers. Current methods often break down because the matching problem be solved correctly. Nevertheless, detecting symmetries in 3D data can be extremely useful, e.g.

The 3D symmetry detection challenge provides multiple datasets for real and synthetic data in combination with local and global symmetries. Each of them containing training and test data.

Challenge Submission

We expect the submission of detection results for any of multiple of the following test data sets:

1. Global reflection symmetry (synthetic data)
2. Local reflection symmetry (synthetic data)
3. Global reflection symmetry (real data)
4. Local reflection symmetry (real data)

Along with the challenge submission, we expect a short 4-page report for novel algorithms, or a paper reference for published methods. Paper submission guidelines and document templates are provided on the submission page.

References

• [Cohen et al. CVPR 2012] A. Cohen, C. Zach, S. Sinha, M. Pollefeys, Discovering and Exploiting 3D Symmetries in Structure from Motion, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012 [PDF] [Website] [Video]
• [Koeser et al. DAGM 2011] Kevin Koeser, Christopher Zach, Marc Pollefeys, Dense 3d reconstruction of symmetric scenes from a single image, DAGM Symposium, 2011 [PDF]
• [Liu et al. 2010] Yanxi Liu, Hagit Hel-Or, Craig S. Kaplan and Luc Van Gool, Computational Symmetry in Computer Vision and Computer Graphics. Foundations and Trends in Computer Graphics and Vision, 2010 [PDF]
• [Mitra et al. TOG 2006] Niloy J. Mitra, Leonidas Guibas, Mark Pauly, Partial and approximate symmetry detection for 3d geometry, ACM Transactions on Graphics (TOG) - Proceedings of ACM SIGGRAPH, 2006 [PDF]
• [Mitra et al. CGF 2013] Niloy J. Mitra, Mark Pauly, Michael Wand, Duygu Ceylan. Symmetry in 3d geometry: Extraction and applications, Comput. Graph. Forum 32(6), 1–23, 2013 [PDF]
• [Speciale et al. ECCV 2016] P. Speciale, M. R. Oswald, A. Cohen, M. Pollefeys, A Symmetry Prior for Convex Variational 3D Reconstruction, European Conference on Computer Vision (ECCV), 2016 [PDF] [Website] [Youtube]