|Abstract / Kurzbeschreibung:
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 CNNâ€™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 â€śclosed symmetry loopâ€ť (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  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.