arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2101.09116cs.CV
收藏

混合旋转平均:一种快速鲁棒的旋转平均方法

Hybrid Rotation Averaging: A Fast and Robust Rotation Averaging Approach

Peking University(北京大学);TuSimple(图森未来);ShanghaiTech University(上海科技大学)

Yu Chen, Ji Zhao, Laurent Kneip

摘要:

我们解决旋转平均(RA)及其应用到现实世界的三维重建。基于局部优化的方法是事实上的选择,尽管它们只能保证局部最优。全局优化器确保在低噪声条件下的全局最优性,但它们效率低下,并且可能容易在异常值或噪声水平升高的影响下偏离。我们推动旋转平均的信封,利用全球RA方法和本地RA方法的优点。结合快速视图图过滤作为预处理,所提出的混合方法对离群点具有鲁棒性。我们进一步将所提出的混合旋转平均方法应用于增量式运动恢复结构(SfM),通过将所得到的全局旋转作为正则化因子加入到光束法平差中,提高了SfM的精度和鲁棒性。总的来说,我们证明了所提出的方法的实用性,因为坏的相机姿势被有效地校正,漂移被减少。

英文摘要:

We address rotation averaging (RA) and its application to real-world 3D reconstruction. Local optimisation based approaches are the de facto choice, though they only guarantee a local optimum. Global optimisers ensure global optimality in low noise conditions, but they are inefficient and may easily deviate under the influence of outliers or elevated noise levels. We push the envelope of rotation averaging by leveraging the advantages of a global RA method and a local RA method. Combined with a fast view graph filtering as preprocessing, the proposed hybrid approach is robust to outliers. We further apply the proposed hybrid rotation averaging approach to incremental Structure from Motion (SfM), the accuracy and robustness of SfM are both improved by adding the resulting global rotations as regularisers to bundle adjustment. Overall, we demonstrate high practicality of the proposed method as bad camera poses are effectively corrected and drift is reduced.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑