DGECN: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimation

04/21/2022
by   Tuo Cao, et al.
13

Monocular 6D pose estimation is a fundamental task in computer vision. Existing works often adopt a two-stage pipeline by establishing correspondences and utilizing a RANSAC algorithm to calculate 6 degrees-of-freedom (6DoF) pose. Recent works try to integrate differentiable RANSAC algorithms to achieve an end-to-end 6D pose estimation. However, most of them hardly consider the geometric features in 3D space, and ignore the topology cues when performing differentiable RANSAC algorithms. To this end, we proposed a Depth-Guided Edge Convolutional Network (DGECN) for 6D pose estimation task. We have made efforts from the following three aspects: 1) We take advantages ofestimated depth information to guide both the correspondences-extraction process and the cascaded differentiable RANSAC algorithm with geometric information. 2)We leverage the uncertainty ofthe estimated depth map to improve accuracy and robustness ofthe output 6D pose. 3) We propose a differentiable Perspective-n-Point(PnP) algorithm via edge convolution to explore the topology relations between 2D-3D correspondences. Experiments demonstrate that our proposed network outperforms current works on both effectiveness and efficiency.

READ FULL TEXT

page 1

page 3

page 6

page 7

research
07/21/2023

KVN: Keypoints Voting Network with Differentiable RANSAC for Stereo Pose Estimation

Object pose estimation is a fundamental computer vision task exploited i...
research
02/24/2021

GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation

6D pose estimation from a single RGB image is a fundamental task in comp...
research
03/24/2022

EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation

Locating 3D objects from a single RGB image via Perspective-n-Points (Pn...
research
07/28/2023

Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimation

Recent works on 6D object pose estimation focus on learning keypoint cor...
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...
research
08/18/2021

SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation

Directly regressing all 6 degrees-of-freedom (6DoF) for the object pose ...
research
03/25/2019

A Novel Method for the Absolute Pose Problem with Pairwise Constraints

Absolute pose estimation is a fundamental problem in computer vision, an...

Please sign up or login with your details

Forgot password? Click here to reset