You Only Look at One: Category-Level Object Representations for Pose Estimation From a Single Example

TL;DR

This paper introduces a real-time, category-level 6D pose estimation method that requires only a single example per category, enabling robots to interact with unseen objects through active perception and continual learning.

Contribution

The authors propose a novel approach for category-level pose estimation from a single object example, outperforming prior methods and supporting online, continual learning in robotic manipulation.

Findings

Achieves accurate pose estimation for unseen objects within a category.

Operates in real-time on RGBD sensors for robotic applications.

Supports continual learning with active perception for new categories.

Abstract

In order to meaningfully interact with the world, robot manipulators must be able to interpret objects they encounter. A critical aspect of this interpretation is pose estimation: inferring quantities that describe the position and orientation of an object in 3D space. Most existing approaches to pose estimation make limiting assumptions, often working only for specific, known object instances, or at best generalising to an object category using large pose-labelled datasets. In this work, we present a method for achieving category-level pose estimation by inspection of just a single object from a desired category. We show that we can subsequently perform accurate pose estimation for unseen objects from an inspected category, and considerably outperform prior work by exploiting multi-view correspondences. We demonstrate that our method runs in real-time, enabling a robot manipulator equipped with an RGBD sensor to perform online 6D pose estimation for novel objects. Finally, we showcase our method in a continual learning setting, with a robot able to determine whether objects belong to known categories, and if not, use active perception to produce a one-shot category representation for subsequent pose estimation.