Self-Supervised Pre-Training Boosts Semantic Scene Segmentation on LiDAR data.

Mariona Carós Ariadna Just Santi Seguí Jordi Vitrià

Published in: MVA (2023)

Keyphrases

scene segmentation
lidar data
indoor scenes
visual information
point cloud
semantic information
object tracking
video sequences
urban environments
hyperspectral imagery
high resolution
image representation
urban areas
structural analysis
multi view
watershed segmentation
training set