Just Add $100 More: Augmenting NeRF-based Pseudo-LiDAR Point Cloud for Resolving Class-imbalance Problem

arXiv:2403.11573v1 Announce Type: new
Abstract: Typical LiDAR-based 3D object detection models are trained in a supervised manner with real-world data collection, which is often imbalanced over classes (or long-tailed). To deal with it, augmenting minority-class examples by sampling ground truth (GT) LiDAR points from a database and pasting them into a scene of interest is often used, but challenges still remain: inflexibility in locating GT samples and limited sample diversity. In this work, we propose to leverage pseudo-LiDAR point clouds …

3d object 3d object detection abstract arxiv class class-imbalance cloud collection cs.cv data database data collection deal detection examples lidar nerf object sampling truth type world