Segmentation Improves 3D Object Classification in Graph Convolutional Networks.
Clara HolzhüterFlorian TeichFlorentin WörgötterPublished in: VISIGRAPP (4: VISAPP) (2022)
Keyphrases
- d objects
- topological information
- point distribution
- viewpoint
- object recognition
- image segmentation
- multi view
- multiple views
- object contours
- cad models
- range data
- three dimensional
- segmentation algorithm
- social networks
- partial matching
- pose estimation
- image classification
- feature extraction
- machine learning
- physically plausible
- d mesh
- segmentation method
- feature vectors
- shape prior
- object classes
- shape descriptors
- perceptual grouping
- network structure
- object matching
- surface properties
- pose normalization
- line drawings
- object segmentation
- three dimensional objects
- spatial information
- object detection
- feature space