Depth-Wise Asymmetric Bottleneck With Point-Wise Aggregation Decoder for Real-Time Semantic Segmentation in Urban Scenes.

Gen LiShenlu JiangInyong YunJonghyun KimJoongkyu Kim
Published in: IEEE Access (2020)
Keyphrases
  • semantic segmentation
  • urban scenes
  • pointwise
  • point cloud
  • conditional random fields
  • structure from motion
  • superpixels
  • vision system
  • scene understanding
  • pairwise
  • viewpoint
  • depth map