1D-SalsaSAN: Semantic Segmentation of LiDAR Point Cloud with Self-Attention.
Takahiro SuzukiTsubasa HirakawaTakayoshi YamashitaHironobu FujiyoshiPublished in: VISIGRAPP (5: VISAPP) (2023)
Keyphrases
- point cloud
- semantic segmentation
- superpixels
- point sets
- conditional random fields
- weakly supervised
- structure from motion
- point cloud data
- laser scanner
- object categories
- pascal voc
- scene classification
- image set
- object class
- high resolution
- object recognition
- learning algorithm
- object detection
- high quality
- multiscale
- video sequences
- visual attention
- point correspondences
- ground truth
- input image