U-shaped network based on Transformer for 3D point clouds semantic segmentation.
Jiazhe ZhangXingwei LiXianfa ZhaoYizhi GeZheng ZhangPublished in: ICVIP (2021)
Keyphrases
- semantic segmentation
- street scenes
- conditional random fields
- superpixels
- label transfer
- scene classification
- weakly supervised
- object class
- object categories
- object classes
- depth map
- image understanding
- image set
- computer vision
- multi class
- image patches
- natural images
- pascal voc
- object detection
- multiscale
- long range
- object recognition