PCB-RandNet: Rethinking Random Sampling for LIDAR Semantic Segmentation in Autonomous Driving Scene.
Hui-Xian ChengXianfeng HanHang JiangDehong HeGuoqiang XiaoPublished in: CoRR (2022)
Keyphrases
- random sampling
- semantic segmentation
- scene classification
- autonomous driving
- grand challenge
- active learning
- object recognition
- sample size
- image classification
- image set
- superpixels
- conditional random fields
- natural scenes
- stereo vision
- image representation
- input image
- weakly supervised
- three dimensional
- sliding window
- visual words
- multiple images
- object classes
- multiple objects
- single image
- object categories
- video sequences
- image sequences
- object class
- super resolution
- high resolution
- high quality