# Center3D: Center-based Monocular 3D Object Detection with Joint Depth Understanding

arXiv: https://arxiv.org/abs/2005.13423 · HTML: https://mlsanity.com/paper/2005.13423/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2020.

## Built on by (most cited first, 25 of 25)

- [Categorical Depth Distribution Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.01100/) (2021)
- [Probabilistic and Geometric Depth: Detecting Objects in Perspective](https://mlsanity.com/paper/2107.14160/) (2021)
- [MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer](https://mlsanity.com/paper/2203.10981/) (2022)
- [OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion](https://mlsanity.com/paper/2302.13540/) (2023)
- [BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detection](https://mlsanity.com/paper/2303.08498/) (2023)
- [Monocular 3D Object Detection: An Extrinsic Parameter Free Approach](https://mlsanity.com/paper/2106.15796/) (2021)
- [GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.17202/) (2021)
- [DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection](https://mlsanity.com/paper/2207.10758/) (2022)
- [Monocular Occupancy Prediction for Scalable Indoor Scenes](https://mlsanity.com/paper/2407.11730/) (2024)
- [BEVHeight++: Toward Robust Visual Centric 3D Object Detection](https://mlsanity.com/paper/2309.16179/) (2023)
- [MVFusion: Multi-View 3D Object Detection with Semantic-aligned Radar and Camera Fusion](https://mlsanity.com/paper/2302.10511/) (2023)
- [IPS300+: a Challenging Multimodal Dataset for Intersection Perception System](https://mlsanity.com/paper/2106.02781/) (2021)
- [Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection](https://mlsanity.com/paper/2210.09615/) (2022)
- [MonoPGC: Monocular 3D Object Detection with Pixel Geometry Contexts](https://mlsanity.com/paper/2302.10549/) (2023)
- [Focal-PETR: Embracing Foreground for Efficient Multi-Camera 3D Object Detection](https://mlsanity.com/paper/2212.05505/) (2022)
- [Lite-FPN for Keypoint-based Monocular 3D Object Detection](https://mlsanity.com/paper/2105.00268/) (2021)
- [CrossDTR: Cross-view and Depth-guided Transformers for 3D Object Detection](https://mlsanity.com/paper/2209.13507/) (2022)
- [URoPE: Universal Relative Position Embedding across Geometric Spaces](https://mlsanity.com/paper/2604.18747/) (2026)
- [OBMO: One Bounding Box Multiple Objects for Monocular 3D Object Detection](https://mlsanity.com/paper/2212.10049/) (2022)
- [NeRF-Det++: Incorporating Semantic Cues and Perspective-aware Depth Supervision for Indoor Multi-View 3D Detection](https://mlsanity.com/paper/2402.14464/) (2024)
- [AuxDepthNet: Real-Time Monocular 3D Object Detection with Depth-Sensitive Features](https://mlsanity.com/paper/2501.03700/) (2025)
- [PTA-Det: Point Transformer Associating Point cloud and Image for 3D Object Detection](https://mlsanity.com/paper/2301.07301/) (2023)
- [OriCon3D: Effective 3D Object Detection using Orientation and Confidence](https://mlsanity.com/paper/2304.14484/) (2023)
- [Revisiting Monocular 3D Object Detection with Depth Thickness Field](https://mlsanity.com/paper/2412.19165/) (2024)
- [DriveCamSim: Generalizable Camera Simulation via Explicit Camera Modeling for Autonomous Driving](https://mlsanity.com/paper/2505.19692/) (2025)

## Abstract (arXiv)

Localizing objects in 3D space and understanding their associated 3D properties is challenging given only monocular RGB images. The situation is compounded by the loss of depth information during perspective projection. We present Center3D, a one-stage anchor-free approach, to efficiently estimate 3D location and depth using only monocular RGB images. By exploiting the difference between 2D and 3D centers, we are able to estimate depth consistently. Center3D uses a combination of classification and regression to understand the hidden depth information more robustly than each method alone. Our method employs two joint approaches: (1) LID: a classification-dominated approach with sequential Linear Increasing Discretization. (2) DepJoint: a regression-dominated approach with multiple Eigen's transformations for depth estimation. Evaluating on KITTI dataset for moderate objects, Center3D improved the AP in BEV from 29.7% to 42.8%, and the AP in 3D from 18.6% to 39.1%. Compared with state-of-the-art detectors, Center3D has achieved the best speed-accuracy trade-off in realtime monocular object detection.