FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection.

Danila Rukhovich Anna Vorontsova Anton Konushin

Published in: CoRR (2021)

Keyphrases

d objects
viewpoint
object recognition
pose estimation
three dimensional
range data
shape descriptors
multi view
multiple views
object detection
cad models
d mesh
image contours
line drawings
topological information
control points
integral imaging
detection method
object classes
pose normalization
physically plausible