HybridPose: 6D Object Pose Estimation under Hybrid Representations

01/07/2020
by   Chen Song, et al.
30

We introduce HybridPose, a novel 6D object pose estimation approach. HybridPose utilizes a hybrid intermediate representation to express different geometric information in the input image, including keypoints, edge vectors, and symmetry correspondences. Compared to a unitary representation, our hybrid representation allows pose regression to exploit more and diverse features when one type of predicted representation is inaccurate (e.g., because of occlusion). HybridPose leverages a robust regression module to filter out outliers in predicted intermediate representation. We show the robustness of HybridPose by demonstrating that all intermediate representations can be predicted by the same simple neural network without sacrificing the overall performance. Compared to state-of-the-art pose estimation approaches, HybridPose is comparable in running time and is significantly more accurate. For example, on Occlusion Linemod dataset, our method achieves a prediction speed of 30 fps with a mean ADD(-S) accuracy of 79.2 improvement from the current state-of-the-art approach. Our implementation of HybridPose is available at https://github.com/chensong1995/HybridPose.

READ FULL TEXT

page 1

page 3

page 6

research
09/30/2019

CullNet: Calibrated and Pose Aware Confidence Scores for Object Pose Estimation

We present a new approach for a single view, image-based object pose est...
research
08/19/2023

3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation

Regression-based methods for 3D human pose estimation directly predict t...
research
10/22/2021

Occlusion-Robust Object Pose Estimation with Holistic Representation

Practical object pose estimation demands robustness against occlusions t...
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
07/19/2017

STag: A Stable Fiducial Marker System

In this paper, we propose STag, a fiducial marker system that provides s...
research
07/27/2015

Occlusion-Aware Object Localization, Segmentation and Pose Estimation

We present a learning approach for localization and segmentation of obje...
research
09/15/2021

Hybrid ICP

ICP algorithms typically involve a fixed choice of data association meth...

Please sign up or login with your details

Forgot password? Click here to reset