LEARD-Net: Semantic segmentation for large-scale point cloud scene.
Ziyin ZengYongyang XuZhong XieWei TangJie WanWeichao WuPublished in: Int. J. Appl. Earth Obs. Geoinformation (2022)
Keyphrases
- point cloud
- semantic segmentation
- scene classification
- laser scanner
- image set
- object recognition
- structure from motion
- superpixels
- conditional random fields
- natural scenes
- point sets
- image classification
- object categories
- input image
- weakly supervised
- scene understanding
- image sequences
- visual words
- three dimensional
- d scene
- object class
- high resolution
- sparse reconstruction
- object classes
- multiple images
- object detection
- moving objects
- pairwise
- bag of words
- object segmentation
- viewpoint