C2BG-Net: Cross-modality and cross-scale balance network with global semantics for multi-modal 3D object detection.
Bonan DingJin XieJing NieYulong WuJiale CaoPublished in: Neural Networks (2024)
Keyphrases
- multi modal
- d objects
- viewpoint
- multi view
- multi modality
- object recognition
- range data
- three dimensional
- pose estimation
- shape descriptors
- multiple views
- cad models
- cross modal
- physically plausible
- object detection
- topological information
- object classes
- computer vision
- network structure
- image contours
- object features
- multiple modalities
- complex networks
- three dimensional objects
- d mesh
- community structure
- semantic information
- image segmentation
- feature selection