Login / Signup

Malleable 2.5D Convolution: Learning Receptive Fields Along the Depth-Axis for RGB-D Scene Parsing.

Yajie XingJingbo WangGang Zeng
Published in: ECCV (19) (2020)
Keyphrases
  • d scene
  • depth map
  • receptive fields
  • neural network
  • single image
  • data sets
  • three dimensional
  • high quality
  • object recognition
  • optical flow
  • natural images
  • scene geometry