Paved2Paradise: Cost-Effective and Scalable LiDAR Simulation by Factoring the Real World

1 code implementation • 2 Dec 2023 • Michael A. Alcorn, Noah Schwartz

Our key insight is that, by deliberately collecting separate "background" and "object" datasets (i. e., "factoring the real world"), we can intelligently combine them to produce a combinatorially large and diverse training set.

Human Detection Pedestrian Detection