RDFNet: RGB-D Multi-level Residual Feature Fusion for Indoor Semantic Segmentation.

Seungyong Lee Seong-Jin Park Ki-Sang Hong

Published in: ICCV (2017)

Keyphrases

semantic segmentation
feature fusion
superpixels
conditional random fields
feature extraction
multiple features
scene classification
object segmentation
object categories
image understanding
object classes
multiscale
object recognition
viewpoint
feature vectors
higher order
feature space
three dimensional