SMIFormer: Learning Spatial Feature Representation for 3D Object Detection from 4D Imaging Radar via Multi-View Interactive Transformers.
Weigang ShiZiming ZhuKezhi ZhangHuanlei ChenZhuoping YuYu ZhuPublished in: Sensors (2023)
Keyphrases
- multi view
- d objects
- multiple views
- feature representation
- multi view learning
- single view
- three dimensional
- depth map
- viewpoint
- object recognition
- semi supervised
- learning algorithm
- shape descriptors
- surface reconstruction
- d mesh
- range images
- range data
- pairwise
- visual hull
- feature extraction
- generative model
- detection method
- multi views