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

Yajie Xing Jingbo Wang Gang 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