MATNet: Semantic segmentation of 3D point clouds with multiscale adaptive transformer.
Yufei ZhengJian LuXiaogai ChenKaibing ZhangJian ZhouPublished in: Comput. Electr. Eng. (2024)
Keyphrases
- semantic segmentation
- multiscale
- superpixels
- street scenes
- label transfer
- weakly supervised
- pixel level
- natural images
- image representation
- conditional random fields
- scene classification
- object class
- image processing
- object segmentation
- object categories
- depth map
- image understanding
- image classification
- information extraction
- image segmentation