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

1Southern University of Science and Technology, China
2The University of Hong Kong, China
3The University of Birmingham, UK
The IEEE / CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024

*Indicates corresponding author.


Object pose refinement is essential for robust object pose estimation. Previous work has made significant progress towards 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 discrepancies 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 integrates an HS-layer 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 diverse 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 experiments 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.



      title={GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinement}, 
      author={Linfang Zheng and Tze Ho Elden Tse and Chen Wang and Yinghan Sun and Hua Chen and Ales Leonardis and Wei Zhang},