# Weakly Supervised 3D Object Detection from Lidar Point Cloud

arXiv: https://arxiv.org/abs/2007.11901 · HTML: https://mlsanity.com/paper/2007.11901/

## Key facts

- Cited by 67 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2020.

## Built on by (most cited first, 30 of 67)

- [Offboard 3D Object Detection from Point Cloud Sequences](https://mlsanity.com/paper/2103.05073/) (2021)
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [Scribble-Supervised LiDAR Semantic Segmentation](https://mlsanity.com/paper/2203.08537/) (2022)
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://mlsanity.com/paper/2202.02980/) (2022)
- [Semi-supervised 3D Object Detection with Proficient Teachers](https://mlsanity.com/paper/2207.12655/) (2022)
- [ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2207.12654/) (2022)
- [Auto4D: Learning to Label 4D Objects from Sequential Point Clouds](https://mlsanity.com/paper/2101.06586/) (2021)
- [SkyEye: Self-Supervised Bird's-Eye-View Semantic Mapping Using Monocular Frontal View Images](https://mlsanity.com/paper/2302.04233/) (2023)
- [Pseudo-labeling for Scalable 3D Object Detection](https://mlsanity.com/paper/2103.02093/) (2021)
- [3D Spatial Recognition without Spatially Labeled 3D](https://mlsanity.com/paper/2105.06461/) (2021)
- [FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection](https://mlsanity.com/paper/2105.07647/) (2021)
- [Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detection](https://mlsanity.com/paper/2304.12315/) (2023)
- [BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios](https://mlsanity.com/paper/2212.05758/) (2022)
- [Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments](https://mlsanity.com/paper/2403.13556/) (2024)
- [A Survey of Label-Efficient Deep Learning for 3D Point Clouds](https://mlsanity.com/paper/2305.19812/) (2023)
- [WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection](https://mlsanity.com/paper/2203.08332/) (2022)
- [Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency](https://mlsanity.com/paper/2303.08686/) (2023)
- [Perspective-Invariant 3D Object Detection](https://mlsanity.com/paper/2507.17665/) (2025)
- [Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement](https://mlsanity.com/paper/2203.05238/) (2022)
- [LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels](https://mlsanity.com/paper/2403.15173/) (2024)
- [OLiDM: Object-aware LiDAR Diffusion Models for Autonomous Driving](https://mlsanity.com/paper/2412.17226/) (2024)
- [FAST3D: Flow-Aware Self-Training for 3D Object Detectors](https://mlsanity.com/paper/2110.09355/) (2021)
- [Multimodal Transformer for Automatic 3D Annotation and Object Detection](https://mlsanity.com/paper/2207.09805/) (2022)
- [Weakly Supervised Monocular 3D Detection with a Single-View Image](https://mlsanity.com/paper/2402.19144/) (2024)
- [MAP-Gen: An Automated 3D-Box Annotation Flow with Multimodal Attention Point Generator](https://mlsanity.com/paper/2203.15700/) (2022)
- [WS-3D-Lane: Weakly Supervised 3D Lane Detection With 2D Lane Labels](https://mlsanity.com/paper/2209.11523/) (2022)
- [LWSIS: LiDAR-guided Weakly Supervised Instance Segmentation for Autonomous Driving](https://mlsanity.com/paper/2212.03504/) (2022)
- [Weakly Supervised 3D Object Detection via Multi-Level Visual Guidance](https://mlsanity.com/paper/2312.07530/) (2023)
- [MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2401.16305/) (2024)
- [Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape Data](https://mlsanity.com/paper/2407.10200/) (2024)

## Abstract (arXiv)

It is laborious to manually label point cloud data for training high-quality 3D object detectors. This work proposes a weakly supervised approach for 3D object detection, only requiring a small set of weakly annotated scenes, associated with a few precisely labeled object instances. This is achieved by a two-stage architecture design. Stage-1 learns to generate cylindrical object proposals under weak supervision, i.e., only the horizontal centers of objects are click-annotated on bird's view scenes. Stage-2 learns to refine the cylindrical proposals to get cuboids and confidence scores, using a few well-labeled object instances. Using only 500 weakly annotated scenes and 534 precisely labeled vehicle instances, our method achieves 85-95% the performance of current top-leading, fully supervised detectors (which require 3, 712 exhaustively and precisely annotated scenes with 15, 654 instances). More importantly, with our elaborately designed network architecture, our trained model can be applied as a 3D object annotator, allowing both automatic and active working modes. The annotations generated by our model can be used to train 3D object detectors with over 94% of their original performance (under manually labeled data). Our experiments also show our model's potential in boosting performance given more training data. Above designs make our approach highly practical and introduce new opportunities for learning 3D object detection with reduced annotation burden.