English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Some robust point cloud registration approaches with controllable poserefinement magnitude, such as ICP and its variants, are commonly used toimprove 6D pose estimation accuracy. However, the effectiveness of thesemethods gradually diminishes with the advancement of deep learning techniquesand the enhancement of initial pose accuracy, primarily due to their lack ofspecific design for pose refinement. In this paper, we propose Point CloudCompletion and Keypoint Refinement with Fusion Data (PCKRF), a new poserefinement pipeline for 6D pose estimation. The pipeline consists of two steps.First, it completes the input point clouds via a novel pose-sensitive pointcompletion network. The network uses both local and global features with poseinformation during point completion. Then, it registers the completed objectpoint cloud with the corresponding target point cloud by our proposed Colorsupported Iterative KeyPoint (CIKP) method. The CIKP method introduces colorinformation into registration and registers a point cloud around each keypointto increase stability. The PCKRF pipeline can be integrated with existingpopular 6D pose estimation methods, such as the full flow bidirectional fusionnetwork, to further improve their pose estimation accuracy. Experimentsdemonstrate that our method exhibits superior stability compared to existingapproaches when optimizing initial poses with relatively high precision.Notably, the results indicate that our method effectively complements mostexisting pose estimation techniques, leading to improved performance in mostcases. Furthermore, our method achieves promising results even in challengingscenarios involving textureless and symmetrical objects. Our source code isavailable at https://github.com/zhanhz/KRF.

PCKRF: Point Cloud Completion and Keypoint Refinement With Fusion Data for 6D Pose Estimation