# CenterNet3D: An Anchor Free Object Detector for Point Cloud

arXiv: https://arxiv.org/abs/2007.07214 · HTML: https://mlsanity.com/paper/2007.07214/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2020.

## Built on by (most cited first, 7 of 7)

- [PointSmile: Point Self-supervised Learning via Curriculum Mutual Information](https://mlsanity.com/paper/2301.12744/) (2023)
- [MaskBEV: Joint Object Detection and Footprint Completion for Bird's-eye View 3D Point Clouds](https://mlsanity.com/paper/2307.01864/) (2023)
- [CascadeV-Det: Cascade Point Voting for 3D Object Detection](https://mlsanity.com/paper/2401.07477/) (2024)
- [Scenario Engineering for Autonomous Transportation: A New Stage in Open-Pit Mines](https://mlsanity.com/paper/2405.15772/) (2024)
- [Boundary Distribution Estimation for Precise Object Detection](https://mlsanity.com/paper/2111.01396/) (2021)
- [Feature-based model selection for object detection from point cloud data](https://mlsanity.com/paper/2209.12419/) (2022)
- [MoCA3D: Monocular 3D Bounding Box Prediction in the Image Plane](https://mlsanity.com/paper/2603.19538/) (2026)

## Abstract (arXiv)

Accurate and fast 3D object detection from point clouds is a key task in autonomous driving. Existing one-stage 3D object detection methods can achieve real-time performance, however, they are dominated by anchor-based detectors which are inefficient and require additional post-processing. In this paper, we eliminate anchors and model an object as a single point--the center point of its bounding box. Based on the center point, we propose an anchor-free CenterNet3D network that performs 3D object detection without anchors. Our CenterNet3D uses keypoint estimation to find center points and directly regresses 3D bounding boxes. However, because inherent sparsity of point clouds, 3D object center points are likely to be in empty space which makes it difficult to estimate accurate boundaries. To solve this issue, we propose an extra corner attention module to enforce the CNN backbone to pay more attention to object boundaries. Besides, considering that one-stage detectors suffer from the discordance between the predicted bounding boxes and corresponding classification confidences, we develop an efficient keypoint-sensitive warping operation to align the confidences to the predicted bounding boxes. Our proposed CenterNet3D is non-maximum suppression free which makes it more efficient and simpler. We evaluate CenterNet3D on the widely used KITTI dataset and more challenging nuScenes dataset. Our method outperforms all state-of-the-art anchor-based one-stage methods and has comparable performance to two-stage methods as well. It has an inference speed of 20 FPS and achieves the best speed and accuracy trade-off. Our source code will be released at https://github.com/wangguojun2018/CenterNet3d.