CenterAtt: Fast 2-stage Center Attention Network
This work addresses real-time 3D detection for autonomous driving applications, but it is incremental as it builds on existing methods.
The authors tackled real-time 3D detection on the Waymo Open Dataset by building upon the CenterPoint framework with modifications like a center attention head and feature pyramid network neck, achieving a 6th-place ranking in the competition.
In this technical report, we introduce the methods of HIKVISION_LiDAR_Det in the challenge of waymo open dataset real-time 3D detection. Our solution for the competition are built upon Centerpoint 3D detection framework. Several variants of CenterPoint are explored, including center attention head and feature pyramid network neck. In order to achieve real time detection, methods like batchnorm merge, half-precision floating point network and GPU-accelerated voxelization process are adopted. By using these methods, our team ranks 6th among all the methods on real-time 3D detection challenge in the waymo open dataset.