DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation

10/11/2022
by   Hongyang Li, et al.
0

Establishment of point correspondence between camera and object coordinate systems is a promising way to solve 6D object poses. However, surrogate objectives of correspondence learning in 3D space are a step away from the true ones of object pose estimation, making the learning suboptimal for the end task. In this paper, we address this shortcoming by introducing a new method of Deep Correspondence Learning Network for direct 6D object pose estimation, shortened as DCL-Net. Specifically, DCL-Net employs dual newly proposed Feature Disengagement and Alignment (FDA) modules to establish, in the feature space, partial-to-partial correspondence and complete-to-complete one for partial object observation and its complete CAD model, respectively, which result in aggregated pose and match feature pairs from two coordinate systems; these two FDA modules thus bring complementary advantages. The match feature pairs are used to learn confidence scores for measuring the qualities of deep correspondence, while the pose feature pairs are weighted by confidence scores for direct object pose regression. A confidence-based pose refinement network is also proposed to further improve pose precision in an iterative manner. Extensive experiments show that DCL-Net outperforms existing methods on three benchmarking datasets, including YCB-Video, LineMOD, and Oclussion-LineMOD; ablation studies also confirm the efficacy of our novel designs.

READ FULL TEXT

page 12

page 13

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
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
08/19/2023

VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations

Rotation estimation of high precision from an RGB-D object observation i...
research
06/07/2023

Learning Probabilistic Coordinate Fields for Robust Correspondences

We introduce Probabilistic Coordinate Fields (PCFs), a novel geometric-i...
research
03/24/2022

RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization

6-DoF object pose estimation from a monocular image is challenging, and ...
research
04/29/2019

DeepHMap++: Combined Projection Grouping and Correspondence Learning for Full DoF Pose Estimation

In recent years, estimating the 6D pose of object instances with convolu...
research
08/16/2023

Exploiting Point-Wise Attention in 6D Object Pose Estimation Based on Bidirectional Prediction

Traditional geometric registration based estimation methods only exploit...

Please sign up or login with your details

Forgot password? Click here to reset