# WARM-3D: A Weakly-Supervised Sim2Real Domain Adaptation Framework for Roadside Monocular 3D Object Detection

arXiv: https://arxiv.org/abs/2407.20818 · HTML: https://mlsanity.com/paper/2407.20818/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 18 references that are in the map.
- First posted on arXiv 30 Jul 2024.

## Builds on (most cited first, 15 of 15)

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1812.07179/) (2018)
- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection](https://mlsanity.com/paper/2204.05575/) (2022)
- [Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation](https://mlsanity.com/paper/1803.11365/) (2018)
- [MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer](https://mlsanity.com/paper/2203.10981/) (2022)
- [MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection](https://mlsanity.com/paper/2203.13310/) (2022)
- [BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detection](https://mlsanity.com/paper/2303.08498/) (2023)
- [Far3D: Expanding the Horizon for Surround-view 3D Object Detection](https://mlsanity.com/paper/2308.09616/) (2023)
- [A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlook](https://mlsanity.com/paper/2401.01454/) (2024)
- [InfraDet3D: Multi-Modal 3D Object Detection based on Roadside Infrastructure Camera and LiDAR Sensors](https://mlsanity.com/paper/2305.00314/) (2023)
- [Weakly Supervised Adversarial Domain Adaptation for Semantic Segmentation in Urban Scenes](https://mlsanity.com/paper/1904.09092/) (2019)
- [Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training](https://mlsanity.com/paper/2204.11590/) (2022)
- [MonoPGC: Monocular 3D Object Detection with Pixel Geometry Contexts](https://mlsanity.com/paper/2302.10549/) (2023)
- [A9 Intersection Dataset: All You Need for Urban 3D Camera-LiDAR Roadside Perception](https://mlsanity.com/paper/2306.09266/) (2023)

## Built on by (most cited first, 9 of 9)

- [Generative AI for Autonomous Driving: Frontiers and Opportunities](https://mlsanity.com/paper/2505.08854/) (2025)
- [Transfer Learning from Simulated to Real Scenes for Monocular 3D Object Detection](https://mlsanity.com/paper/2408.15637/) (2024)
- [Towards Vision Zero: The TUM Traffic Accid3nD Dataset](https://mlsanity.com/paper/2503.12095/) (2025)
- [MonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models](https://mlsanity.com/paper/2503.13743/) (2025)
- [UrbanTwin: Synthetic Roadside LiDAR Datasets](https://mlsanity.com/paper/2509.06781/) (2025)
- [Enhancing Highway Safety: Accident Detection on the A9 Test Stretch Using Roadside Sensors](https://mlsanity.com/paper/2502.00402/) (2025)
- [FOD-S2R: A FOD Dataset for Sim2Real Transfer Learning based Object Detection](https://mlsanity.com/paper/2512.01315/) (2025)
- [R3ST: A Synthetic 3D Dataset With Realistic Trajectories](https://mlsanity.com/paper/2512.16784/) (2025)
- [SGTA: Scene-Graph Based Multi-Modal Traffic Agent for Video Understanding](https://mlsanity.com/paper/2604.03697/) (2026)

## Abstract (arXiv)

Existing roadside perception systems are limited by the absence of publicly available, large-scale, high-quality 3D datasets. Exploring the use of cost-effective, extensive synthetic datasets offers a viable solution to tackle this challenge and enhance the performance of roadside monocular 3D detection. In this study, we introduce the TUMTraf Synthetic Dataset, offering a diverse and substantial collection of high-quality 3D data to augment scarce real-world datasets. Besides, we present WARM-3D, a concise yet effective framework to aid the Sim2Real domain transfer for roadside monocular 3D detection. Our method leverages cheap synthetic datasets and 2D labels from an off-the-shelf 2D detector for weak supervision. We show that WARM-3D significantly enhances performance, achieving a +12.40% increase in mAP 3D over the baseline with only pseudo-2D supervision. With 2D GT as weak labels, WARM-3D even reaches performance close to the Oracle baseline. Moreover, WARM-3D improves the ability of 3D detectors to unseen sample recognition across various real-world environments, highlighting its potential for practical applications.