Abstract
In this paper we investigate the problems that Convolutional Neural Networks (CNN) based pose estimators have with symmetric objects. We find that the CNN's output representation has to form a closed loop when continuously rotating by one step of symmetry. Otherwise the CNN has to learn 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 previous algorithm including a method to disambiguate symmetric equivalents during the final pose estimation. The algorithm handles continuous rotational symmetry (i.e. a bottle) and discrete rotational symmetry (general boxes, boxes with a square face, uniform prims, but no cubes). It is evaluated on the T-LESS dataset.
Abstract (translated)
URL
https://arxiv.org/abs/2011.13209
