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

• Published in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 10693 - 10703
• Main Authors: Zheng, Linfang, Elden Tse, Tze Ho, Wang, Chen, Sun, Yinghan, Chen, Hua, Leonardis, Ales, Zhang, Wei, Chang, Hyung Jin
• Format: Conference Proceeding
• Language: English
• Published: IEEE 16.06.2024
• Subjects: Computer architecture; Computer vision; Point cloud compression; Pose estimation; Predictive models; Shape; Soft sensors
• ISSN: 2575-7075
• DOI: 10.1109/CVPR52733.2024.01017

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. 1 1 Project page: https://lynne-zheng-linfang.github.io/georef.github.io