Handling Object Symmetries in CNN-based Pose Estimation

11/26/2020
by   Jesse Richter-Klug, et al.
0

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.

READ FULL TEXT
research
08/20/2019

On Object Symmetries and 6D Pose Estimation from Images

Objects with symmetries are common in our daily life and in industrial c...
research
07/02/2020

Learning Orientation Distributions for Object Pose Estimation

For robots to operate robustly in the real world, they should be aware o...
research
07/01/2023

SyMFM6D: Symmetry-aware Multi-directional Fusion for Multi-View 6D Object Pose Estimation

Detecting objects and estimating their 6D poses is essential for automat...
research
04/01/2021

RePOSE: Real-Time Iterative Rendering and Refinement for 6D Object Pose Estimation

The use of iterative pose refinement is a critical processing step for 6...
research
10/13/2018

Pose Estimation for Objects with Rotational Symmetry

Pose estimation is a widely explored problem, enabling many robotic task...
research
11/16/2015

Convolutional Models for Joint Object Categorization and Pose Estimation

In the task of Object Recognition, there exists a dichotomy between the ...
research
10/20/2017

Ligand Pose Optimization with Atomic Grid-Based Convolutional Neural Networks

Docking is an important tool in computational drug discovery that aims t...

Please sign up or login with your details

Forgot password? Click here to reset