# Object-Aware Centroid Voting for Monocular 3D Object Detection

arXiv: https://arxiv.org/abs/2007.09836 · HTML: https://mlsanity.com/paper/2007.09836/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jul 2020.

## Built on by (most cited first, 9 of 9)

- [Geometry Uncertainty Projection Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2107.13774/) (2021)
- [Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection](https://mlsanity.com/paper/2112.04628/) (2021)
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://mlsanity.com/paper/2202.02980/) (2022)
- [OpenTAL: Towards Open Set Temporal Action Localization](https://mlsanity.com/paper/2203.05114/) (2022)
- [MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors](https://mlsanity.com/paper/2410.19590/) (2024)
- [Neighbor-Vote: Improving Monocular 3D Object Detection through Neighbor Distance Voting](https://mlsanity.com/paper/2107.02493/) (2021)
- [GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2310.15624/) (2023)
- [DFR-FastMOT: Detection Failure Resistant Tracker for Fast Multi-Object Tracking Based on Sensor Fusion](https://mlsanity.com/paper/2302.14807/) (2023)
- [SoK: Vehicle Orientation Representations for Deep Rotation Estimation](https://mlsanity.com/paper/2112.04421/) (2021)

## Abstract (arXiv)

Monocular 3D object detection aims to detect objects in a 3D physical world from a single camera. However, recent approaches either rely on expensive LiDAR devices, or resort to dense pixel-wise depth estimation that causes prohibitive computational cost. In this paper, we propose an end-to-end trainable monocular 3D object detector without learning the dense depth. Specifically, the grid coordinates of a 2D box are first projected back to 3D space with the pinhole model as 3D centroids proposals. Then, a novel object-aware voting approach is introduced, which considers both the region-wise appearance attention and the geometric projection distribution, to vote the 3D centroid proposals for 3D object localization. With the late fusion and the predicted 3D orientation and dimension, the 3D bounding boxes of objects can be detected from a single RGB image. The method is straightforward yet significantly superior to other monocular-based methods. Extensive experimental results on the challenging KITTI benchmark validate the effectiveness of the proposed method.