# FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection

arXiv: https://arxiv.org/abs/2105.07647 · HTML: https://mlsanity.com/paper/2105.07647/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 54 references that are in the map.
- First posted on arXiv 17 May 2021.

## Builds on (most cited first, 30 of 46)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [Frustum PointNets for 3D Object Detection from RGB-D Data](https://mlsanity.com/paper/1711.08488/) (2017)
- [Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1812.07179/) (2018)
- [3DSSD: Point-based 3D Single Stage Object Detector](https://mlsanity.com/paper/2002.10187/) (2020)
- [From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network](https://mlsanity.com/paper/1907.03670/) (2019)
- [Joint 3D Proposal Generation and Object Detection from View Aggregation](https://mlsanity.com/paper/1712.02294/) (2017)
- [STD: Sparse-to-Dense 3D Object Detector for Point Cloud](https://mlsanity.com/paper/1907.10471/) (2019)
- [3D Bounding Box Estimation Using Deep Learning and Geometry](https://mlsanity.com/paper/1612.00496/) (2016)
- [M3D-RPN: Monocular 3D Region Proposal Network for Object Detection](https://mlsanity.com/paper/1907.06038/) (2019)
- [Disentangling Monocular 3D Object Detection](https://mlsanity.com/paper/1905.12365/) (2019)
- [Multi-Task Multi-Sensor Fusion for 3D Object Detection](https://mlsanity.com/paper/2012.12397/) (2020)
- [Stereo R-CNN based 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1902.09738/) (2019)
- [IoU Loss for 2D/3D Object Detection](https://mlsanity.com/paper/1908.03851/) (2019)
- [Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection](https://mlsanity.com/paper/1903.01864/) (2019)
- [Fully Convolutional Instance-aware Semantic Segmentation](https://mlsanity.com/paper/1611.07709/) (2016)
- [Fast Point R-CNN](https://mlsanity.com/paper/1908.02990/) (2019)
- [GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving](https://mlsanity.com/paper/1903.10955/) (2019)

## Built on by (most cited first, 29 of 29)

- [NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo](https://mlsanity.com/paper/2109.01129/) (2021)
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (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)
- [DDS3D: Dense Pseudo-Labels with Dynamic Threshold for Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/2303.05079/) (2023)
- [Multimodal Transformer for Automatic 3D Annotation and Object Detection](https://mlsanity.com/paper/2207.09805/) (2022)
- [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)
- [Weakly Supervised 3D Object Detection via Multi-Level Visual Guidance](https://mlsanity.com/paper/2312.07530/) (2023)
- [Approaching Outside: Scaling Unsupervised 3D Object Detection from 2D Scene](https://mlsanity.com/paper/2407.08569/) (2024)
- [General Geometry-aware Weakly Supervised 3D Object Detection](https://mlsanity.com/paper/2407.13748/) (2024)
- [Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels](https://mlsanity.com/paper/2503.08421/) (2025)
- [Segment, Lift and Fit: Automatic 3D Shape Labeling from 2D Prompts](https://mlsanity.com/paper/2407.11382/) (2024)
- [OpenBox: Annotate Any Bounding Boxes in 3D](https://mlsanity.com/paper/2512.01352/) (2025)
- [Context-Aware Transformer for 3D Point Cloud Automatic Annotation](https://mlsanity.com/paper/2303.14893/) (2023)
- [MWSIS: Multimodal Weakly Supervised Instance Segmentation with 2D Box Annotations for Autonomous Driving](https://mlsanity.com/paper/2312.06988/) (2023)
- [LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectives](https://mlsanity.com/paper/2503.18384/) (2025)
- [Towards 3D Object Detection with 2D Supervision](https://mlsanity.com/paper/2211.08287/) (2022)
- [Are Dense Labels Always Necessary for 3D Object Detection from Point Cloud?](https://mlsanity.com/paper/2403.02818/) (2024)
- [Vision-Driven 2D Supervised Fine-Tuning Framework for Bird's Eye View Perception](https://mlsanity.com/paper/2409.05834/) (2024)
- [MonoSOWA: Scalable monocular 3D Object detector Without human Annotations](https://mlsanity.com/paper/2501.09481/) (2025)
- [ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels Only](https://mlsanity.com/paper/2407.17197/) (2024)
- [CA-W3D: Leveraging Context-Aware Knowledge for Weakly Supervised Monocular 3D Detection](https://mlsanity.com/paper/2503.04154/) (2025)
- [Multi-Modal Assistance for Unsupervised Domain Adaptation on Point Cloud 3D Object Detection](https://mlsanity.com/paper/2511.07966/) (2025)
- [MEDL-U: Uncertainty-aware 3D Automatic Annotation based on Evidential Deep Learning](https://mlsanity.com/paper/2309.09599/) (2023)
- [2DDATA: 2D Detection Annotations Transmittable Aggregation for Semantic Segmentation on Point Cloud](https://mlsanity.com/paper/2309.11755/) (2023)
- [WLST: Weak Labels Guided Self-training for Weakly-supervised Domain Adaptation on 3D Object Detection](https://mlsanity.com/paper/2310.03821/) (2023)
- [MVAT: Multi-View Aware Teacher for Weakly Supervised 3D Object Detection](https://mlsanity.com/paper/2509.07507/) (2025)
- [Unified Unsupervised and Sparsely-Supervised 3D Object Detection by Semantic Pseudo-Labeling and Prototype Learning](https://mlsanity.com/paper/2602.21484/) (2026)

## Abstract (arXiv)

In this paper, we investigate the problem of weakly supervised 3D vehicle detection. Conventional methods for 3D object detection need vast amounts of manually labelled 3D data as supervision signals. However, annotating large datasets requires huge human efforts, especially for 3D area. To tackle this problem, we propose frustum-aware geometric reasoning (FGR) to detect vehicles in point clouds without any 3D annotations. Our method consists of two stages: coarse 3D segmentation and 3D bounding box estimation. For the first stage, a context-aware adaptive region growing algorithm is designed to segment objects based on 2D bounding boxes. Leveraging predicted segmentation masks, we develop an anti-noise approach to estimate 3D bounding boxes in the second stage. Finally 3D pseudo labels generated by our method are utilized to train a 3D detector. Independent of any 3D groundtruth, FGR reaches comparable performance with fully supervised methods on the KITTI dataset. The findings indicate that it is able to accurately detect objects in 3D space with only 2D bounding boxes and sparse point clouds.