TY - GEN
T1 - 4D-Net for Learned Multi-Modal Alignment
AU - Piergiovanni, A. J.
AU - Casser, Vincent
AU - Ryoo, Michael S.
AU - Angelova, Anelia
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - 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. We will open source the code.
AB - 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. We will open source the code.
UR - https://www.scopus.com/pages/publications/85126848462
U2 - 10.1109/ICCV48922.2021.01515
DO - 10.1109/ICCV48922.2021.01515
M3 - Conference contribution
AN - SCOPUS:85126848462
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 15415
EP - 15425
BT - Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021
Y2 - 11 October 2021 through 17 October 2021
ER -