Improved Semantic Segmentation of Low-Resolution 3D Point Clouds Using Supervised Domain Adaptation.
Asmaa ElhadidyMohamed AfifiMohammed HassoubahYara AliMohamed ElHelwPublished in: NILES (2020)
Keyphrases
- low resolution
- semantic segmentation
- high resolution
- super resolution
- depth map
- superpixels
- image patches
- conditional random fields
- semi supervised
- labeled data
- high quality
- object recognition
- object categories
- face images
- unsupervised learning
- training data
- learning algorithm
- higher order
- supervised learning
- point cloud
- active learning
- object segmentation
- target domain
- machine learning
- input image
- test images
- small number
- object classes
- object class