Login / Signup

D2T-Net: A dual-domain transformer network exploiting spatial and channel dimensions for semantic segmentation of urban mobile laser scanning point clouds.

Ziwei LuoZiyin ZengJie WanWei TangZhongge JinZhong XieYongyang Xu
Published in: Int. J. Appl. Earth Obs. Geoinformation (2024)
Keyphrases
  • point cloud
  • semantic segmentation
  • laser scanning
  • structure from motion
  • surface reconstruction
  • point sets
  • superpixels
  • visual inspection
  • conditional random fields
  • spatial information
  • multi channel