论文标题
在基于CNN的姿势估计中处理对象对称性
Handling Object Symmetries in CNN-based Pose Estimation
论文作者
论文摘要
在本文中，我们调查了基于对称对象的基于卷积神经网络（CNN）的姿势估计器具有的问题。当连续旋转对象时，我们考虑了CNN的输出表示的值，并发现在对称性的每个步骤之后必须形成一个闭环。否则，CNN（本身就是连续的函数）必须复制一个不连续的函数。在一个1多户玩具示例中，我们表明，常用表示形式无法满足这一需求，并分析了造成的问题。特别是，我们发现创建对称性损失的流行的最终符合方法往往不能与基于梯度的优化（即深度学习）搭配得很好。 我们从这些见解中提出了一个称为“封闭对称环”（CSL）的表示，其中相关矢量的角度乘以对称顺序，然后将其推广到6-DOF。该表示形式从[Richter-Klug，ICVS，2019]扩展了我们的算法，其中包括一种在最终姿势估计中消除对称等效物的方法。该算法处理连续旋转对称性（例如，瓶子）和离散的旋转对称性（例如，一个4倍对称盒）。它是在无T的数据集上进行评估的，该数据集可用于基于RGB的方法的最新方法。
In this paper, we investigate the problems that Convolutional Neural Networks (CNN)-based pose estimators have with symmetric objects. We considered the value of the CNN's output representation when continuously rotating the object and found that it has to form a closed loop after each step of symmetry. Otherwise, the CNN (which is itself a continuous function) has to replicate an uncontinuous function. On a 1-DOF toy example we show that commonly used representations do not fulfill this demand and analyze the problems caused thereby. In particular, we find that the popular min-over-symmetries approach for creating a symmetry-aware loss tends not to work well with gradient-based optimization, i.e. deep learning. We propose a representation called "closed symmetry loop" (csl) from these insights, where the angle of relevant vectors is multiplied by the symmetry order and then generalize it to 6-DOF. The representation extends our algorithm from [Richter-Klug, ICVS, 2019] including a method to disambiguate symmetric equivalents during the final pose estimation. The algorithm handles continuous rotational symmetry (e.g. a bottle) and discrete rotational symmetry (e.g. a 4-fold symmetric box). It is evaluated on the T-LESS dataset, where it reaches state-of-the-art for unrefining RGB-based methods.
