Gradual Batch Alternation for Effective Domain Adaptation in LiDAR-Based 3D Object Detection

M Rochan, X Chen, A Grandhi… - 2024 IEEE Intelligent …, 2024 - ieeexplore.ieee.org
We address the challenge of domain adaptation in LiDAR-based 3D object detection by
introducing a simple yet effective training strategy known as Gradual Batch Alternation. This …

Effects of Range-based LiDAR Point Cloud Density Manipulation on 3D Object Detection

ER Corral-Soto, A Grandhi, YY He… - 2024 IEEE Intelligent …, 2024 - ieeexplore.ieee.org
In recent years, much progress has been made in LiDAR-based 3D object detection mainly
due to advances in detector architecture designs and availability of large-scale LiDAR …

3D Can Be Explored In 2D: Pseudo-Label Generation for LiDAR Point Clouds Using Sensor-Intensity-Based 2D Semantic Segmentation

A Caunes, T Chateau, V Frémont - 2024 IEEE Intelligent …, 2024 - ieeexplore.ieee.org
Semantic segmentation of 3D LiDAR point clouds, essential for autonomous driving and
infrastructure management, is best achieved by supervised learning, which demands …