# Learning Monocular 3D Vehicle Detection without 3D Bounding Box Labels

arXiv: https://arxiv.org/abs/2010.03506 · HTML: https://mlsanity.com/paper/2010.03506/

## Key facts

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

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

- [CADSim: Robust and Scalable in-the-wild 3D Reconstruction for Controllable Sensor Simulation](https://mlsanity.com/paper/2311.01447/) (2023)
- [Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency](https://mlsanity.com/paper/2303.08686/) (2023)
- [LiDARTouch: Monocular metric depth estimation with a few-beam LiDAR](https://mlsanity.com/paper/2109.03569/) (2021)
- [Lifting 2D Object Locations to 3D by Discounting LiDAR Outliers across Objects and Views](https://mlsanity.com/paper/2109.07945/) (2021)
- [Time-to-Label: Temporal Consistency for Self-Supervised Monocular 3D Object Detection](https://mlsanity.com/paper/2203.02193/) (2022)
- [Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable Approach for Continuous Markov Random Fields](https://mlsanity.com/paper/2107.06028/) (2021)
- [View-to-Label: Multi-View Consistency for Self-Supervised 3D Object Detection](https://mlsanity.com/paper/2305.17972/) (2023)

## Abstract (arXiv)

The training of deep-learning-based 3D object detectors requires large datasets with 3D bounding box labels for supervision that have to be generated by hand-labeling. We propose a network architecture and training procedure for learning monocular 3D object detection without 3D bounding box labels. By representing the objects as triangular meshes and employing differentiable shape rendering, we define loss functions based on depth maps, segmentation masks, and ego- and object-motion, which are generated by pre-trained, off-the-shelf networks. We evaluate the proposed algorithm on the real-world KITTI dataset and achieve promising performance in comparison to state-of-the-art methods requiring 3D bounding box labels for training and superior performance to conventional baseline methods.