# Understanding the Domain Gap in LiDAR Object Detection Networks

arXiv: https://arxiv.org/abs/2204.10024 · HTML: https://mlsanity.com/paper/2204.10024/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 15 references that are in the map.
- First posted on arXiv 21 Apr 2022.

## Builds on (most cited first, 10 of 10)

- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [PIXOR: Real-time 3D Object Detection from Point Clouds](https://mlsanity.com/paper/1902.06326/) (2019)
- [Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges](https://mlsanity.com/paper/1902.07830/) (2019)
- [Learning to Learn from Noisy Labeled Data](https://mlsanity.com/paper/1812.05214/) (2018)
- [PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation](https://mlsanity.com/paper/1911.02744/) (2019)
- [SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation](https://mlsanity.com/paper/2108.06709/) (2021)
- [A Survey on Deep Domain Adaptation for LiDAR Perception](https://mlsanity.com/paper/2106.02377/) (2021)
- [Object Detection Under Rainy Conditions for Autonomous Vehicles: A Review of State-of-the-Art and Emerging Techniques](https://mlsanity.com/paper/2006.16471/) (2020)
- [Single-Stage Object Detection from Top-View Grid Maps on Custom Sensor Setups](https://mlsanity.com/paper/2002.00667/) (2020)

## Built on by (most cited first, 3 of 3)

- [MDT3D: Multi-Dataset Training for LiDAR 3D Object Detection Generalization](https://mlsanity.com/paper/2308.01000/) (2023)
- [RESOLVE: A Multi-Resolution and Multi-Modal Dataset for Roadside Cooperative Perception](https://mlsanity.com/paper/2606.31895/) (2026)
- [An Investigation of Beam Density on LiDAR Object Detection Performance](https://mlsanity.com/paper/2503.15087/) (2025)

## Abstract (arXiv)

In order to make autonomous driving a reality, artificial neural networks have to work reliably in the open-world. However, the open-world is vast and continuously changing, so it is not technically feasible to collect and annotate training datasets which accurately represent this domain. Therefore, there are always domain gaps between training datasets and the open-world which must be understood. In this work, we investigate the domain gaps between high-resolution and low-resolution LiDAR sensors in object detection networks. Using a unique dataset, which enables us to study sensor resolution domain gaps independent of other effects, we show two distinct domain gaps - an inference domain gap and a training domain gap. The inference domain gap is characterised by a strong dependence on the number of LiDAR points per object, while the training gap shows no such dependence. These fndings show that different approaches are required to close these inference and training domain gaps.