Urban canvas: Unfreezing street-view imagery with semantically compressed LIDAR pointclouds

Abstract

Detailed 3D scans of urban environments are increasingly being collected with the goal of bringing more location-aware content to mobile users. This work converts large collections of LIDAR scans and street-view panoramas into a representation that extracts semantically meaningful components of the scene. Compressing this data by an order of magnitude or more enables rich user interactions with mobile applications that have a very good knowledge of the scene around them. These representations are suitable for integrating into physics engines and transmission over mobile networks — key components of modern AR entertainment solutions.