CLFT: Camera-LiDAR Fusion Transformer for Semantic Segmentation in Autonomous Driving.
Junyi GuMauro BelloneTomás PivonkaRaivo SellPublished in: CoRR (2024)
Keyphrases
- semantic segmentation
- autonomous driving
- street scenes
- grand challenge
- superpixels
- stereo vision
- conditional random fields
- scene classification
- object categories
- real time
- vision system
- depth estimation
- object class
- weakly supervised
- object classes
- urban traffic
- object recognition
- pascal voc
- image understanding
- image fusion
- multiple images
- image set
- high resolution
- object segmentation
- segmentation method
- object detection
- multiscale
- image segmentation
- machine learning