# Self-Supervised Moving Object Segmentation of Sparse and Noisy Radar Point Clouds

arXiv: https://arxiv.org/abs/2511.02395 · HTML: https://mlsanity.com/paper/2511.02395/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 4 Nov 2025.

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

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds](https://mlsanity.com/paper/2109.00179/) (2021)
- [A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation](https://mlsanity.com/paper/1810.07842/) (2018)
- [Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection](https://mlsanity.com/paper/2201.07131/) (2022)
- [FLOT: Scene Flow on Point Clouds Guided by Optimal Transport](https://mlsanity.com/paper/2007.11142/) (2020)
- [Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting Sequential Data](https://mlsanity.com/paper/2105.08971/) (2021)
- [RadarScenes: A Real-World Radar Point Cloud Data Set for Automotive Applications](https://mlsanity.com/paper/2104.02493/) (2021)
- [FlowNet3D++: Geometric Losses For Deep Scene Flow Estimation](https://mlsanity.com/paper/1912.01438/) (2019)
- [Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutions](https://mlsanity.com/paper/2206.04129/) (2022)
- [Self-Supervised Scene Flow Estimation with 4-D Automotive Radar](https://mlsanity.com/paper/2203.01137/) (2022)
- [Efficient Spatial-Temporal Information Fusion for LiDAR-Based 3D Moving Object Segmentation](https://mlsanity.com/paper/2207.02201/) (2022)
- [GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding](https://mlsanity.com/paper/2403.09639/) (2024)
- [MF-MOS: A Motion-Focused Model for Moving Object Segmentation](https://mlsanity.com/paper/2401.17023/) (2024)
- [InsMOS: Instance-Aware Moving Object Segmentation in LiDAR Data](https://mlsanity.com/paper/2303.03909/) (2023)
- [Gaussian Radar Transformer for Semantic Segmentation in Noisy Radar Data](https://mlsanity.com/paper/2212.03690/) (2022)
- [Radar Instance Transformer: Reliable Moving Instance Segmentation in Sparse Radar Point Clouds](https://mlsanity.com/paper/2309.16435/) (2023)
- [Bootstrapping Autonomous Driving Radars with Self-Supervised Learning](https://mlsanity.com/paper/2312.04519/) (2023)
- [RadarMOSEVE: A Spatial-Temporal Transformer Network for Radar-Only Moving Object Segmentation and Ego-Velocity Estimation](https://mlsanity.com/paper/2402.14380/) (2024)
- [Radar Velocity Transformer: Single-scan Moving Object Segmentation in Noisy Radar Point Clouds](https://mlsanity.com/paper/2507.03463/) (2025)

## Abstract (arXiv)

Moving object segmentation is a crucial task for safe and reliable autonomous mobile systems like self-driving cars, improving the reliability and robustness of subsequent tasks like SLAM or path planning. While the segmentation of camera or LiDAR data is widely researched and achieves great results, it often introduces an increased latency by requiring the accumulation of temporal sequences to gain the necessary temporal context. Radar sensors overcome this problem with their ability to provide a direct measurement of a point's Doppler velocity, which can be exploited for single-scan moving object segmentation. However, radar point clouds are often sparse and noisy, making data annotation for use in supervised learning very tedious, time-consuming, and cost-intensive. To overcome this problem, we address the task of self-supervised moving object segmentation of sparse and noisy radar point clouds. We follow a two-step approach of contrastive self-supervised representation learning with subsequent supervised fine-tuning using limited amounts of annotated data. We propose a novel clustering-based contrastive loss function with cluster refinement based on dynamic points removal to pretrain the network to produce motion-aware representations of the radar data. Our method improves label efficiency after fine-tuning, effectively boosting state-of-the-art performance by self-supervised pretraining.