Abstract
In this paper, we present a simple yet effective rotation averaging pipeline, termed Incremental Rotation Averaging (IRA), which is inspired by the well-developed incremental Structure from Motion (SfM) techniques. Unlike the traditional rotation averaging methods which estimate all the absolute rotations simultaneously and focus on designing either robust loss function or outlier filtering strategy, here the absolute rotations are estimated in an incremental way. Similar to the incremental SfM, our IRA is robust to relative rotation outliers and could achieve accurate rotation averaging results. In addition, we propose several key techniques, such as initial triplet and Next-Best-View selection, Weighted Local/Global Optimization, and Re-Rotation Averaging, to push the rotation averaging results one step further. Ablation studies and comparison experiments on the 1DSfM, Campus, and San Francisco datasets demonstrate the effectiveness of our IRA and its advantages over the state-of-the-art rotation averaging methods in accuracy and robustness.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Agarwal, S., Snavely, N., Seitz, S. M., & Szeliski, R. (2010). Bundle adjustment in the large. In European conference on computer vision (ECCV) (pp. 29–42).
Bustos, Á. P., Chin, T., Eriksson, A., & Reid, I. (2019). Visual SLAM: Why bundle adjust? In International conference on robotics and automation (ICRA) (pp. 2385–2391).
Chatterjee, A., & Govindu, V. M. (2013). Efficient and robust large-scale rotation averaging. In IEEE international conference on computer vision (ICCV) (pp. 521–528).
Chatterjee, A., & Govindu, V. M. (2018). Robust relative rotation averaging. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4), 958–972.
Chng, C. K., Parra, A., Chin, T. J., & Latif, Y. (2020). Monocular rotational odometry with incremental rotation averaging and loop closure. In Digital image computing: techniques and applications (DICTA).
Crandall, D., Owens, A., Snavely, N., & Huttenlocher, D. (2013). SfM with MRFs: Discrete-continuous optimization for large-scale structure from motion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(12), 2841–2853.
Cui, H., Gao, X., Shen, S., & Hu, Z. (2017). HSfM: Hybrid structure-from-motion. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 2393–2402).
Cui, H., Shen, S., Gao, X., & Hu, Z. (2017). CSfM: Community-based structure from motion. In IEEE international conference on image processing (ICIP) (pp. 4517–4521).
Cui, H., Shen, S., Gao, W., Liu, H., & Wang, Z. (2019). Efficient and robust large-scale structure-from-motion via track selection and camera prioritization. ISPRS Journal of Photogrammetry and Remote Sensing, 156, 202–214.
Cui, Z., & Tan, P. (2015). Global structure-from-motion by similarity averaging. In IEEE international conference on computer vision (ICCV) (pp. 864–872).
Dong, Q., Gao, X., Cui, H., & Hu, Z. (2020). Robust camera translation estimation via rank enforcement. IEEE Transactions on Cybernetics.
Eriksson, A., Olsson, C., Kahl, F., & Chin, T. (2018). Rotation averaging and strong duality. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 127–135).
Fischler, M. A., & Bolles, R. C. (1981). Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6), 381–395.
Govindu, V. M. (2006). Robustness in motion averaging. In Asian conference on computer vision (ACCV) (pp. 457–466).
Haner, S., & Heyden, A. (2012). Covariance propagation and next best view planning for 3D reconstruction. In European conference on computer vision (ECCV) (pp. 545–556).
Hartley, R., Aftab, K., & Trumpf, J. (2011). L1 rotation averaging using the Weiszfeld algorithm. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 3041–3048).
Hartley, R., Trumpf, J., Dai, Y., & Li, H. (2013). Rotation averaging. International Journal of Computer Vision, 103, 267–305.
Jiang, N., Cui, Z., & Tan, P. (2013). A global linear method for camera pose registration. In IEEE international conference on computer vision (ICCV) (pp. 481–488).
Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91–110.
Moulon, P., Monasse, P., & Marlet, R. (2013). Global fusion of relative motions for robust, accurate and scalable structure from motion. In IEEE international conference on computer vision (ICCV) (pp. 3248–3255).
Nister, D. (2004). An efficient solution to the five-point relative pose problem. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(6), 756–770.
Özyeşil, O., & Singer, A. (2015). Robust camera location estimation by convex programming. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 2674–2683).
Schönberger, J. L., & Frahm, J. M. (2016). Structure-from-motion revisited. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 4104–4113).
Shen, T., Zhu, S., Fang, T., Zhang, R., & Quan, L. (2016). Graph-based consistent matching for structure-from-motion. In European conference on computer vision (ECCV) (pp. 139–155).
Snavely, N., Seitz, S. M., & Szeliski, R. (2008). Modeling the world from Internet photo collections. International Journal of Computer Vision, 80(2), 189–210.
Sweeney, C., Sattler, T., Höllerer, T., Turk, M., & Pollefeys, M. (2015). Optimizing the viewing graph for structure-from-motion. In IEEE international conference on computer vision (ICCV) (pp. 801–809).
Wilson, K., & Snavely, N. (2014). Robust global translations with 1DSfM. In European conference on computer vision (ECCV) (pp. 61–75).
Wilson, K., Bindel, D., & Snavely, N. (2016). When is rotations averaging hard? In European conference on computer vision (ECCV) (pp. 255–270).
Wu, C. (2013). Towards linear-time incremental structure from motion. In International conference on 3D vision (3DV) (pp. 127–134).
Zach, C., Klopschitz, M., & Pollefeys, M. (2010). Disambiguating visual relations using loop constraints. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 1426–1433).
Zhu, S., Zhang, R., Zhou, L., Shen, T., Fang, T., Tan, P., & Quan, L. (2018). Very large-scale global SfM by distributed motion averaging. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 4568–4577).
Acknowledgements
This work was supported by the National Key Research and Development Program of China (2020YFB1313002), the National Science Foundation of China (62003319, 62076026, and 61873265), the Shandong Provincial Natural Science Foundation (ZR2020QF075), the China Postdoctoral Science Foundation (2020M682239), and the Open Projects Program of National Laboratory of Pattern Recognition (202000010). We thank Dr. Zhaopeng Cui for sharing the Campus dataset.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflicts of interest
The authors declare that they have no conflict of interest.
Additional information
Communicated by Yasutaka Furukawa.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Gao, X., Zhu, L., Xie, Z. et al. Incremental Rotation Averaging. Int J Comput Vis 129, 1202–1216 (2021). https://doi.org/10.1007/s11263-020-01427-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11263-020-01427-7