# Monocular 3D Object Detection via Geometric Reasoning on Keypoints

arXiv: https://arxiv.org/abs/1905.05618 · HTML: https://mlsanity.com/paper/1905.05618/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 May 2019.

## Built on by (most cited first, 30 of 31)

- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [Is Pseudo-Lidar needed for Monocular 3D Object detection?](https://mlsanity.com/paper/2108.06417/) (2021)
- [Objects are Different: Flexible Monocular 3D Object Detection](https://mlsanity.com/paper/2104.02323/) (2021)
- [Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection](https://mlsanity.com/paper/2210.02443/) (2022)
- [Geometry Uncertainty Projection Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2107.13774/) (2021)
- [MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries](https://mlsanity.com/paper/2205.00613/) (2022)
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://mlsanity.com/paper/2202.02980/) (2022)
- [M3DSSD: Monocular 3D Single Stage Object Detector](https://mlsanity.com/paper/2103.13164/) (2021)
- [MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection](https://mlsanity.com/paper/2308.09421/) (2023)
- [Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/2203.02112/) (2022)
- [MonoGAE: Roadside Monocular 3D Object Detection with Ground-Aware Embeddings](https://mlsanity.com/paper/2310.00400/) (2023)
- [MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors](https://mlsanity.com/paper/2410.19590/) (2024)
- [MonoGRNet: A General Framework for Monocular 3D Object Detection](https://mlsanity.com/paper/2104.08797/) (2021)
- [Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection](https://mlsanity.com/paper/2107.13931/) (2021)
- [Viewpoint Equivariance for Multi-View 3D Object Detection](https://mlsanity.com/paper/2303.14548/) (2023)
- [MonoCInIS: Camera Independent Monocular 3D Object Detection using Instance Segmentation](https://mlsanity.com/paper/2110.00464/) (2021)
- [Weakly Supervised Training of Monocular 3D Object Detectors Using Wide Baseline Multi-view Traffic Camera Data](https://mlsanity.com/paper/2110.10966/) (2021)
- [MoGDE: Boosting Mobile Monocular 3D Object Detection with Ground Depth Estimation](https://mlsanity.com/paper/2303.13561/) (2023)
- [Vision-Based Environmental Perception for Autonomous Driving](https://mlsanity.com/paper/2212.11453/) (2022)
- [Ground Plane Matters: Picking Up Ground Plane Prior in Monocular 3D Object Detection](https://mlsanity.com/paper/2211.01556/) (2022)
- [BEVUDA: Multi-geometric Space Alignments for Domain Adaptive BEV 3D Object Detection](https://mlsanity.com/paper/2211.17126/) (2022)
- [GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2310.15624/) (2023)
- [Depth Is All You Need for Monocular 3D Detection](https://mlsanity.com/paper/2210.02493/) (2022)
- [Survey and Systematization of 3D Object Detection Models and Methods](https://mlsanity.com/paper/2201.09354/) (2022)
- [CenterLoc3D: Monocular 3D Vehicle Localization Network for Roadside Surveillance Cameras](https://mlsanity.com/paper/2203.14550/) (2022)
- [HeightFormer: Learning Height Prediction in Voxel Features for Roadside Vision Centric 3D Object Detection via Transformer](https://mlsanity.com/paper/2503.10777/) (2025)
- [SoK: Vehicle Orientation Representations for Deep Rotation Estimation](https://mlsanity.com/paper/2112.04421/) (2021)
- [3D Keypoint Estimation Using Implicit Representation Learning](https://mlsanity.com/paper/2306.11529/) (2023)
- [BEVUDA++: Geometric-aware Unsupervised Domain Adaptation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2509.14151/) (2025)
- [Analysis of voxel-based 3D object detection methods efficiency for real-time embedded systems](https://mlsanity.com/paper/2105.10316/) (2021)

## Abstract (arXiv)

Monocular 3D object detection is well-known to be a challenging vision task due to the loss of depth information; attempts to recover depth using separate image-only approaches lead to unstable and noisy depth estimates, harming 3D detections. In this paper, we propose a novel keypoint-based approach for 3D object detection and localization from a single RGB image. We build our multi-branch model around 2D keypoint detection in images and complement it with a conceptually simple geometric reasoning method. Our network performs in an end-to-end manner, simultaneously and interdependently estimating 2D characteristics, such as 2D bounding boxes, keypoints, and orientation, along with full 3D pose in the scene. We fuse the outputs of distinct branches, applying a reprojection consistency loss during training. The experimental evaluation on the challenging KITTI dataset benchmark demonstrates that our network achieves state-of-the-art results among other monocular 3D detectors.