HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation

Linfang Zheng1; Chen Wang1; Yinghan Sun1; Esha Dasgupta2; Hua Chen1; Aleš Leonardis2; Wei Zhang1; Hyung Jin Chang2

10.1109/CVPR52729.2023.01646

2023

1063-6919

979-8-3503-0130-4

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

2023-June

17163-17173

17-24 June 2023

Vancouver, BC, Canada

In this paper, we focus on the problem of category-level object pose estimation, which is challenging due to the large intra-category shape variation. 3D graph convolution (3D-GC) based methods have been widely used to extract local geometric features, but they have limitations for complex shaped objects and are sensitive to noise. Moreover, the scale and translation invariant properties of 3D-GC restrict the perception of an object's size and translation information. In this paper, we propose a simple network structure, the HS-layer, which extends 3D-GC to extract hybrid scope latent features from point cloud data for category-level object pose estimation tasks. The proposed HS-layer: 1) is able to perceive local-global geometric structure and global information, 2) is robust to noise, and 3) can encode size and translation information. Our experiments show that the simple replacement of the 3D-GC layer with the proposed HS-layer on the baseline method (GPV-Pose) achieves a significant improvement, with the performance increased by 14.5% on 5°2cm metric and 10.3% on IoU75. Our method outperforms the state-of-the-art methods by a large margin (8.3% on 5°2cm, 6.9% on IoU75) on REAL275 dataset and runs in real-time (50 FPS)11Codeisavailable: https://github.com/Lynne-Zheng-Linfang/HS-Pose.

3D from single images

第一

CPCI-S ; EI

WOS:001062531301045

20234114867532

IEEE

1.Department of Mechanical and Energy Engineering, Southern University of Science and Technology
2.School of Computer Science, University of Birmingham

Linfang Zheng,Chen Wang,Yinghan Sun,et al. HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation[C],2023:17163-17173.