# ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels Only

arXiv: https://arxiv.org/abs/2407.17197 · HTML: https://mlsanity.com/paper/2407.17197/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 24 Jul 2024.

## Builds on (most cited first, 22 of 22)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [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)
- [Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection](https://mlsanity.com/paper/2012.15712/) (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)
- [Stereo R-CNN based 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1902.09738/) (2019)
- [Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection](https://mlsanity.com/paper/1903.01864/) (2019)
- [FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection](https://mlsanity.com/paper/2105.07647/) (2021)
- [Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer](https://mlsanity.com/paper/2007.07986/) (2020)
- [Transferable Semi-supervised 3D Object Detection from RGB-D Data](https://mlsanity.com/paper/1904.10300/) (2019)
- [PLUMENet: Efficient 3D Object Detection from Stereo Images](https://mlsanity.com/paper/2101.06594/) (2021)
- [Semi-supervised 3D Object Detection via Temporal Graph Neural Networks](https://mlsanity.com/paper/2202.00182/) (2022)
- [MAP-Gen: An Automated 3D-Box Annotation Flow with Multimodal Attention Point Generator](https://mlsanity.com/paper/2203.15700/) (2022)
- [Scaling Novel Object Detection with Weakly Supervised Detection Transformers](https://mlsanity.com/paper/2207.05205/) (2022)
- [What Can be Seen is What You Get: Structure Aware Point Cloud Augmentation](https://mlsanity.com/paper/2206.09664/) (2022)
- [Not Every Side Is Equal: Localization Uncertainty Estimation for Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/2312.10390/) (2023)
- [Context-Aware Transformer for 3D Point Cloud Automatic Annotation](https://mlsanity.com/paper/2303.14893/) (2023)

## Built on by (most cited first, 1 of 1)

- [MVAT: Multi-View Aware Teacher for Weakly Supervised 3D Object Detection](https://mlsanity.com/paper/2509.07507/) (2025)

## Abstract (arXiv)

3D object detection plays a crucial role in various applications such as autonomous vehicles, robotics and augmented reality. However, training 3D detectors requires a costly precise annotation, which is a hindrance to scaling annotation to large datasets. To address this challenge, we propose a weakly supervised 3D annotator that relies solely on 2D bounding box annotations from images, along with size priors. One major problem is that supervising a 3D detection model using only 2D boxes is not reliable due to ambiguities between different 3D poses and their identical 2D projection. We introduce a simple yet effective and generic solution: we build 3D proxy objects with annotations by construction and add them to the training dataset. Our method requires only size priors to adapt to new classes. To better align 2D supervision with 3D detection, our method ensures depth invariance with a novel expression of the 2D losses. Finally, to detect more challenging instances, our annotator follows an offline pseudo-labelling scheme which gradually improves its 3D pseudo-labels. Extensive experiments on the KITTI dataset demonstrate that our method not only performs on-par or above previous works on the Car category, but also achieves performance close to fully supervised methods on more challenging classes. We further demonstrate the effectiveness and robustness of our method by being the first to experiment on the more challenging nuScenes dataset. We additionally propose a setting where weak labels are obtained from a 2D detector pre-trained on MS-COCO instead of human annotations. The code is available at https://github.com/CEA-LIST/ALPI