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

Danila Rukhovich Anna Vorontsova Anton Konushin

Published in: ECCV (10) (2022)

Keyphrases

d objects
viewpoint
object recognition
multi view
multiple views
pose estimation
object detection
cad models
three dimensional
shape descriptors
range data
d mesh
image contours
object model
detection method
geometric invariants
spin images
semi supervised
integral imaging
pose normalization