# SF-UDA3D: Source-Free Unsupervised Domain Adaptation for LiDAR-Based 3D Object Detection

arXiv: https://arxiv.org/abs/2010.08243 · HTML: https://mlsanity.com/paper/2010.08243/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2020.

## Built on by (most cited first, 25 of 25)

- [ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection](https://mlsanity.com/paper/2103.05346/) (2021)
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency](https://mlsanity.com/paper/2107.11355/) (2021)
- [ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection](https://mlsanity.com/paper/2108.06682/) (2021)
- [LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection](https://mlsanity.com/paper/2203.14956/) (2022)
- [Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection](https://mlsanity.com/paper/2203.15793/) (2022)
- [A Survey on Deep Domain Adaptation for LiDAR Perception](https://mlsanity.com/paper/2106.02377/) (2021)
- [GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation](https://mlsanity.com/paper/2207.09763/) (2022)
- [Data-Free Knowledge Transfer: A Survey](https://mlsanity.com/paper/2112.15278/) (2021)
- [Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection](https://mlsanity.com/paper/2304.09446/) (2023)
- [Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling](https://mlsanity.com/paper/2307.07944/) (2023)
- [Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning](https://mlsanity.com/paper/2110.03143/) (2021)
- [Uncertainty-aware Mean Teacher for Source-free Unsupervised Domain Adaptive 3D Object Detection](https://mlsanity.com/paper/2109.14651/) (2021)
- [See Eye to Eye: A Lidar-Agnostic 3D Detection Framework for Unsupervised Multi-Target Domain Adaptation](https://mlsanity.com/paper/2111.09450/) (2021)
- [Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection](https://mlsanity.com/paper/2111.15656/) (2021)
- [Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2304.11705/) (2023)
- [FAST3D: Flow-Aware Self-Training for 3D Object Detectors](https://mlsanity.com/paper/2110.09355/) (2021)
- [Online Unsupervised Domain Adaptation for Person Re-identification](https://mlsanity.com/paper/2205.04383/) (2022)
- [MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection](https://mlsanity.com/paper/2406.14878/) (2024)
- [You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation](https://mlsanity.com/paper/2304.11762/) (2023)
- [TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models](https://mlsanity.com/paper/2403.11691/) (2024)
- [DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detection](https://mlsanity.com/paper/2406.13891/) (2024)
- [LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectives](https://mlsanity.com/paper/2503.18384/) (2025)
- [Time-to-Label: Temporal Consistency for Self-Supervised Monocular 3D Object Detection](https://mlsanity.com/paper/2203.02193/) (2022)

## Abstract (arXiv)

3D object detectors based only on LiDAR point clouds hold the state-of-the-art on modern street-view benchmarks. However, LiDAR-based detectors poorly generalize across domains due to domain shift. In the case of LiDAR, in fact, domain shift is not only due to changes in the environment and in the object appearances, as for visual data from RGB cameras, but is also related to the geometry of the point clouds (e.g., point density variations). This paper proposes SF-UDA3D, the first Source-Free Unsupervised Domain Adaptation (SF-UDA) framework to domain-adapt the state-of-the-art PointRCNN 3D detector to target domains for which we have no annotations (unsupervised), neither we hold images nor annotations of the source domain (source-free). SF-UDA3D is novel on both aspects. Our approach is based on pseudo-annotations, reversible scale-transformations and motion coherency. SF-UDA3D outperforms both previous domain adaptation techniques based on features alignment and state-of-the-art 3D object detection methods which additionally use few-shot target annotations or target annotation statistics. This is demonstrated by extensive experiments on two large-scale datasets, i.e., KITTI and nuScenes.