AFDet: Anchor Free One Stage 3D Object Detection

Abstract

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.

Accepted on May 6th, 2020 by CVPRW 2020, published on June 7th, 2020; Baseline detector for the 1st place solutions of Waymo Open Dataset Challenges 2020

References in corpus (3)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds
• RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving

Cited by in corpus (6)

• 1st Place Solution for Waymo Open Dataset Challenge -- 3D Detection and Domain Adaptation
• 1st Place Solutions for Waymo Open Dataset Challenges -- 2D and 3D Tracking
• 3D-MAN: 3D Multi-frame Attention Network for Object Detection
• Pseudo-labeling for Scalable 3D Object Detection
• LiDAR R-CNN: An Efficient and Universal 3D Object Detector
• A two-stage data association approach for 3D Multi-object Tracking