Pose Estimation for Objects with Rotational Symmetry

TL;DR

This paper presents a novel approach for pose estimation of rotationally symmetric objects, leveraging symmetry reasoning during training to improve accuracy on unseen objects with available CAD models.

Contribution

It introduces a method that exploits symmetry information during training using limited labeled data and unlabeled CAD models, enhancing pose estimation performance.

Findings

Outperforms naive neural network approaches on a new dataset

Effectively leverages symmetry information during training

Significantly improves pose estimation accuracy for symmetric objects

Abstract

Pose estimation is a widely explored problem, enabling many robotic tasks such as grasping and manipulation. In this paper, we tackle the problem of pose estimation for objects that exhibit rotational symmetry, which are common in man-made and industrial environments. In particular, our aim is to infer poses for objects not seen at training time, but for which their 3D CAD models are available at test time. Previous work has tackled this problem by learning to compare captured views of real objects with the rendered views of their 3D CAD models, by embedding them in a joint latent space using neural networks. We show that sidestepping the issue of symmetry in this scenario during training leads to poor performance at test time. We propose a model that reasons about rotational symmetry during training by having access to only a small set of symmetry-labeled objects, whereby exploiting a large collection of unlabeled CAD models. We demonstrate that our approach significantly outperforms a naively trained neural network on a new pose dataset containing images of tools and hardware.