We present 4D-Net, a 3D object detection approach, which utilizes 3D Point Cloud and RGB sensing information, both in time. We are able to incorporate the 4D information by performing a novel dynamic connection learning across various feature representations and levels of abstraction, as well as by observing geometric constraints. Our approach outperforms the state-of-the-art and strong baselines on the Waymo Open Dataset. 4D-Net is better able to use motion cues and dense image information to detect distant objects more successfully.
@article{arxiv.2109.01066,
title = {4D-Net for Learned Multi-Modal Alignment},
author = {AJ Piergiovanni and Vincent Casser and Michael S. Ryoo and Anelia Angelova},
journal= {arXiv preprint arXiv:2109.01066},
year = {2021}
}