Real-time 3D Object Detection using Feature Map Flow

Add code
Jun 26, 2021
Youshaa Murhij, Dmitry Yudin
Figure 1 for Real-time 3D Object Detection using Feature Map Flow
Figure 2 for Real-time 3D Object Detection using Feature Map Flow
Figure 3 for Real-time 3D Object Detection using Feature Map Flow
Figure 4 for Real-time 3D Object Detection using Feature Map Flow

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

In this paper, we present a real-time 3D detection approach considering time-spatial feature map aggregation from different time steps of deep neural model inference (named feature map flow, FMF). Proposed approach improves the quality of 3D detection center-based baseline and provides real-time performance on the nuScenes and Waymo benchmark. Code is available at https://github.com/YoushaaMurhij/FMFNet

* CVPR 2021 Workshop on autonomous driving (Waymo Real-time 3D Detection)  
View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon