PCB-RandNet: Rethinking Random Sampling for LiDAR Semantic Segmentation in Autonomous Driving Scene.
Xian-Feng HanHui-Xian ChengHang JiangDehong HeGuoqiang XiaoPublished in: ICRA (2024)
Keyphrases
- random sampling
- semantic segmentation
- scene classification
- autonomous driving
- grand challenge
- object recognition
- active learning
- superpixels
- natural scenes
- stereo vision
- sample size
- image set
- weakly supervised
- image classification
- image representation
- conditional random fields
- input image
- sliding window
- three dimensional
- multiple images
- object categories
- single image
- video sequences
- multiple objects
- object class
- data sets
- object classes
- object segmentation
- visual words
- bag of words
- segmentation algorithm
- multi view
- learning process