AFDet: Anchor Free One Stage 3D Object Detection
This work addresses efficiency challenges in 3D object detection for robotics applications like autonomous driving, offering a more streamlined approach.
The paper tackles the drawbacks of anchor-based 3D object detection, such as complex post-processing and tricky parameter tuning, by proposing AFDet, an anchor-free and NMS-free one-stage detector that performs competitively on KITTI and Waymo validation sets.
High-efficiency point cloud 3D object detection operated on embedded systems is important for many robotics applications including autonomous driving. Most previous works try to solve it using anchor-based detection methods which come with two drawbacks: post-processing is relatively complex and computationally expensive; tuning anchor parameters is tricky. We are the first to address these drawbacks with an anchor free and Non-Maximum Suppression free one stage detector called AFDet. The entire AFDet can be processed efficiently on a CNN accelerator or a GPU with the simplified post-processing. Without bells and whistles, our proposed AFDet performs competitively with other one stage anchor-based methods on KITTI validation set and Waymo Open Dataset validation set.