GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinement

Linfang Zheng1,2; Tze Ho Elden Tse2; Chen Wang1,3; Yinghan Sun1; Hua Chen1; Ales Leonardis2; Wei Zhang1; Hyung Jin Chang2

10.1109/CVPR52733.2024.01017

2024-06-22

1063-6919

979-8-3503-5301-3

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

16-22 June 2024

Seattle, WA, USA

Object pose refinement is essential for robust object pose estimation. Previous work has made significant progress to-wards instance-level object pose refinement. Yet, category-level pose refinement is a more challenging problem due to large shape variations within a category and the discrep-ancies between the target object and the shape prior. To address these challenges, we introduce a novel architecture for category-level object pose refinement. Our approach in-tegrates an HS-Iayer and learnable affine transformations, which aims to enhance the extraction and alignment of Geometric information. Additionally, we introduce a cross-cloud transformation mechanism that efficiently merges di-verse data sources. Finally, we push the limits of our model by incorporating the shape prior information for translation and size error prediction. We conducted extensive ex-periments to demonstrate the effectiveness of the proposed framework. Through extensive quantitative experiments, we demonstrate significant improvement over the baseline method by a large margin across all metrics.11Project page: https://lynne-zheng-linfang.github.io/georef.github.io

第一

1.Shenzhen Key Laboratory of Control Theory and Intelligent Systems, School of System Design and Intelligent Manufacturing, Southern University of Science and Technology, China
2.School of Computer Science. University of Birmigsham, UK
3.Department of Computer Science, the University of Hong Kong, China

Linfang Zheng,Tze Ho Elden Tse,Chen Wang,et al. GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinement[C],2024.