LACV-Net: Semantic Segmentation of Large-Scale Point Cloud Scene via Local Adaptive and Comprehensive VLAD.
Ziyin ZengYongyang XuZhong XieWei TangJie WanWeichao WuPublished in: CoRR (2022)
Keyphrases
- point cloud
- semantic segmentation
- scene classification
- laser scanner
- superpixels
- structure from motion
- image set
- d scene
- weakly supervised
- point sets
- single image
- visual words
- natural scenes
- multiple images
- conditional random fields
- graphical models
- object recognition
- video sequences
- input image
- image representation
- image classification
- machine learning
- object class
- sparse reconstruction
- bounding box
- object categories
- image regions
- image features
- moving objects
- training set
- computer vision