RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving.
Angelika AndoSpyros GidarisAndrei BursucGilles PuyAlexandre BoulchRenaud MarletPublished in: CoRR (2023)
Keyphrases
- semantic segmentation
- autonomous driving
- grand challenge
- conditional random fields
- superpixels
- scene classification
- label transfer
- weakly supervised
- stereo vision
- vision system
- computer vision
- pascal voc
- object categories
- image processing
- real time
- object classes
- object class
- image set
- multiscale
- image understanding
- vision algorithms
- urban traffic
- bag of words
- natural images
- object detection
- object recognition
- biologically inspired
- three dimensional
- object segmentation