REDE: End-to-end Object 6D Pose Robust Estimation Using Differentiable Outliers Elimination

10/24/2020
by   Weitong Hua, et al.
0

Object 6D pose estimation is a fundamental task in many applications. Conventional methods solve the task by detecting and matching the keypoints, then estimating the pose. Recent efforts bringing deep learning into the problem mainly overcome the vulnerability of conventional methods to environmental variation due to the hand-crafted feature design. However, these methods cannot achieve end-to-end learning and good interpretability at the same time. In this paper, we propose REDE, a novel end-to-end object pose estimator using RGB-D data, which utilizes network for keypoint regression, and a differentiable geometric pose estimator for pose error back-propagation. Besides, to achieve better robustness when outlier keypoint prediction occurs, we further propose a differentiable outliers elimination method that regresses the candidate result and the confidence simultaneously. Via confidence weighted aggregation of multiple candidates, we can reduce the effect from the outliers in the final estimation. Finally, following the conventional method, we apply a learnable refinement process to further improve the estimation. The experimental results on three benchmark datasets show that REDE slightly outperforms the state-of-the-art approaches and is more robust to object occlusion.

READ FULL TEXT

page 1

page 6

page 8

research
07/29/2020

Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints

Estimating relative camera poses from consecutive frames is a fundamenta...
research
01/23/2022

FN-Net:Remove the Outliers by Filtering the Noise

Establishing the correspondence between two images is an important resea...
research
09/13/2019

BPnP: Further Empowering End-to-End Learning with Back-Propagatable Geometric Optimization

In this paper we present BPnP, a novel method to do back-propagation thr...
research
04/26/2022

Coupled Iterative Refinement for 6D Multi-Object Pose Estimation

We address the task of 6D multi-object pose: given a set of known 3D obj...
research
05/08/2021

Improving Robustness for Pose Estimation via Stable Heatmap Regression

Deep learning methods have achieved excellent performance in pose estima...
research
07/05/2018

Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning

This paper presents KeypointNet, an end-to-end geometric reasoning frame...
research
05/04/2015

See the Difference: Direct Pre-Image Reconstruction and Pose Estimation by Differentiating HOG

The Histogram of Oriented Gradient (HOG) descriptor has led to many adva...

Please sign up or login with your details

Forgot password? Click here to reset