Enriching point clouds with implicit representations for 3d classification and segmentation

HIGHLIGHTS

• who: Zexin Yang and collaborators from the College of Surveying and Geo-Informatics, Tongji University, Shanghai, China have published the Article: Enriching Point Clouds with Implicit Representations for 3D Classification and Segmentation, in the Journal: (JOURNAL)
• what: The authors propose a new point cloud representation by integrating the 3D Cartesian coordinates with the intrinsic geometric information encapsulated in its implicit field. The major challenge lies in that continuous implicit fields do not match the discrete and irregular data structure of point clouds and are thus incompatible with existing point-based deep learning architectures designed for . . .
  

   

  

  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.