SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection.
Yichen XieChenfeng XuMarie-Julie RakotosaonaPatrick RimFederico TombariKurt KeutzerMasayoshi TomizukaWei ZhanPublished in: CoRR (2023)
Keyphrases
- multi modal
- d objects
- multi sensor
- sparse representation
- fusion method
- dictionary learning
- viewpoint
- data fusion
- object recognition
- infrared
- multi view
- multiple views
- multi sensor fusion
- three dimensional
- shape descriptors
- image classification
- pose estimation
- object detection
- image fusion
- image representation
- image patches
- signal processing
- dimensionality reduction
- face recognition
- multi modality
- image annotation
- pattern recognition
- object classes
- visual information
- image sequences
- computer vision