4D-Net for Learned Multi-Modal Alignment

AJ Piergiovanni; Vincent Casser; Michael S. Ryoo; Anelia Angelova

ICCV 2021poster85 citations

4D-Net for Learned Multi-Modal Alignment

AJ Piergiovanni, Vincent Casser, Michael S. Ryoo, Anelia Angelova

Abstract

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 and 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. We will open source the code.

BibTeX

@inproceedings{iccv2021_4dnetforlearnedm,
  title = {4D-Net for Learned Multi-Modal Alignment},
  author = {AJ Piergiovanni and Vincent Casser and Michael S. Ryoo and Anelia Angelova},
  booktitle = {ICCV 2021},
  year = {2021}
}