arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1912.04485cs.CV
收藏

NeuRoRA:神经鲁棒旋转平均

NeuRoRA: Neural Robust Rotation Averaging

The University of Adelaide(阿德莱德大学)

Pulak Purkait, Tat-Jun Chin, Ian Reid

摘要:

多旋转平均是运动恢复结构、映射和机器人导航的基本任务。我们的任务是估计几个摄像机的绝对方向给出了他们的一些嘈杂的相对方向测量。用于此任务的常规方法根据鲁棒成本函数寻求与所观察到的噪声测量最佳一致的绝对取向的参数。这些鲁棒的成本函数是高度非线性的,并且是基于关于噪声和离群值分布的某些假设而设计的。在这项工作中,我们的目标是建立一个神经网络,学习噪声模式的数据和预测/回归的模型参数从嘈杂的相对方向。所提出的网络是两个网络的组合:(1)视图图清理网络,其检测视图图中的离群边缘并校正噪声测量;以及(2)微调网络,其在单步的中微调从清理的图引导的绝对方向的初始化。该组合网络不仅速度快,而且在大量合成图上进行训练,比传统的迭代优化方法具有更高的精度。虽然用基于图的网络代替鲁棒优化方法的想法只在多次旋转平均中得到证明,但它可以很容易地扩展到其他基于图的几何问题,例如姿势图优化。

英文摘要:

Multiple rotation averaging is an essential task for structure from motion, mapping, and robot navigation. The task is to estimate the absolute orientations of several cameras given some of their noisy relative orientation measurements. The conventional methods for this task seek parameters of the absolute orientations that agree best with the observed noisy measurements according to a robust cost function. These robust cost functions are highly nonlinear and are designed based on certain assumptions about the noise and outlier distributions. In this work, we aim to build a neural network that learns the noise patterns from the data and predict/regress the model parameters from the noisy relative orientations. The proposed network is a combination of two networks: (1) a view-graph cleaning network, which detects outlier edges in the view-graph and rectifies noisy measurements; and (2) a fine-tuning network, which fine-tunes an initialization of absolute orientations bootstrapped from the cleaned graph, in a single step. The proposed combined network is very fast, moreover, being trained on a large number of synthetic graphs, it is more accurate than the conventional iterative optimization methods. Although the idea of replacing robust optimization methods by a graph-based network is demonstrated only for multiple rotation averaging, it could easily be extended to other graph-based geometric problems, for example, pose-graph optimization.

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。

↑