6d pose estimation of industrial parts based on point cloud geometric information prediction for robotic grasping

HIGHLIGHTS

• What: In this paper, a new real-world dataset for pose estimation of low-textured industrial objects is produced to train and evaluate the proposed model approach. The approach presented in this study is built upon the PyTorch deep learnin scenario. In this paper, the evaluation on the ADD-based LineMod dataset is shown in Table 2. Compared to 1.2% higher than the RGBD-based RGBD-based PVN3D PVN3D[8] and andFFB6D FFB6D[17], ,respectively. respectively.Compared Compared 1.2% higher than to other state-of-the-art methods, the method proposed in this paper performs . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.