Zero-Shot Category-Level Object Pose Estimation

04/07/2022
by   Walter Goodwin, et al.
3

Object pose estimation is an important component of most vision pipelines for embodied agents, as well as in 3D vision more generally. In this paper we tackle the problem of estimating the pose of novel object categories in a zero-shot manner. This extends much of the existing literature by removing the need for pose-labelled datasets or category-specific CAD models for training or inference. Specifically, we make the following contributions. First, we formalise the zero-shot, category-level pose estimation problem and frame it in a way that is most applicable to real-world embodied agents. Secondly, we propose a novel method based on semantic correspondences from a self-supervised vision transformer to solve the pose estimation problem. We further re-purpose the recent CO3D dataset to present a controlled and realistic test setting. Finally, we demonstrate that all baselines for our proposed task perform poorly, and show that our method provides a six-fold improvement in average rotation accuracy at 30 degrees. Our code is available at https://github.com/applied-ai-lab/zero-shot-pose.

READ FULL TEXT

page 1

page 5

page 14

page 22

research
01/18/2022

OSSID: Online Self-Supervised Instance Detection by (and for) Pose Estimation

Real-time object pose estimation is necessary for many robot manipulatio...
research
05/29/2023

3D Model-based Zero-Shot Pose Estimation Pipeline

Most existing learning-based pose estimation methods are typically devel...
research
05/25/2023

POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Reference

Despite the significant progress in six degrees-of-freedom (6DoF) object...
research
03/14/2022

Panoptic animal pose estimators are zero-shot performers

Animal pose estimation is critical in applications ranging from life sci...
research
11/24/2022

Go Beyond Point Pairs: A General and Accurate Sim2Real Object Pose Voting Method with Efficient Online Synthetic Training

Object pose estimation is an important topic in 3D vision. Though most c...
research
04/28/2021

ZePHyR: Zero-shot Pose Hypothesis Rating

Pose estimation is a basic module in many robot manipulation pipelines. ...
research
03/07/2022

CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild

In this paper, we tackle the problem of category-level 9D pose estimatio...

Please sign up or login with your details

Forgot password? Click here to reset