Skip to content

Latest commit

 

History

History
27 lines (18 loc) · 1.3 KB

File metadata and controls

27 lines (18 loc) · 1.3 KB

June 2020

tl;dr: Visibility augmented deep voxel representation, with occupancy grid feature map.

Overall impression

Representing point cloud as xyz fundamentally destroys the difference of free space and uncertainty space (both contains no lidar points). Convolution cannot differentiate such difference based on such a representation.

WYSIWYG adds a occupancy grid feature map to the existing feature map, very much like coord conv and cam conv.

Key ideas

  • Fast ray casting via voxel traversal --> visibility volume
  • Visibility over multiple ldiar sweeps: bayesian filtering
  • data augmentation
    • Naive data augmentation: copy and paste rare objects such as buses. But it violates visibility rules.
    • Visibility aware data augmentation
  • The idea of ray casting is widely used in generating lidar simulated data, such as lidar sim.

Technical details

Notes