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

Yajie Xing Jingbo Wang Gang Zeng

Published in: CoRR (2020)

Keyphrases

d scene
depth map
receptive fields
learning algorithm
neural network
active learning
natural images
feature extraction
spatio temporal
range images
depth information