# MF-MOS: A Motion-Focused Model for Moving Object Segmentation

arXiv: https://arxiv.org/abs/2401.17023 · HTML: https://mlsanity.com/paper/2401.17023/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 30 Jan 2024.

## Builds on (most cited first, 12 of 12)

- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)
- [SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving](https://mlsanity.com/paper/2003.03653/) (2020)
- [RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2103.10039/) (2021)
- [Motion Guided Attention for Video Salient Object Detection](https://mlsanity.com/paper/1909.07061/) (2019)
- [Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting Sequential Data](https://mlsanity.com/paper/2105.08971/) (2021)
- [Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutions](https://mlsanity.com/paper/2206.04129/) (2022)
- [ERASOR: Egocentric Ratio of Pseudo Occupancy-based Dynamic Object Removal for Static 3D Point Cloud Map Building](https://mlsanity.com/paper/2103.04316/) (2021)
- [Efficient Spatial-Temporal Information Fusion for LiDAR-Based 3D Moving Object Segmentation](https://mlsanity.com/paper/2207.02201/) (2022)
- [Automatic Labeling to Generate Training Data for Online LiDAR-based Moving Object Segmentation](https://mlsanity.com/paper/2201.04501/) (2022)
- [InsMOS: Instance-Aware Moving Object Segmentation in LiDAR Data](https://mlsanity.com/paper/2303.03909/) (2023)
- [MotionBEV: Attention-Aware Online LiDAR Moving Object Segmentation with Bird's Eye View based Appearance and Motion Features](https://mlsanity.com/paper/2305.07336/) (2023)

## Built on by (most cited first, 23 of 23)

- [MambaMOS: LiDAR-based 3D Moving Object Segmentation with Motion-aware State Space Model](https://mlsanity.com/paper/2404.12794/) (2024)
- [HiMo: High-Speed Objects Motion Compensation in Point Clouds](https://mlsanity.com/paper/2503.00803/) (2025)
- [MambaFlow: A Novel and Flow-guided State Space Model for Scene Flow Estimation](https://mlsanity.com/paper/2502.16907/) (2025)
- [BeautyMap: Binary-Encoded Adaptable Ground Matrix for Dynamic Points Removal in Global Maps](https://mlsanity.com/paper/2405.07283/) (2024)
- [SegNet4D: Efficient Instance-Aware 4D Semantic Segmentation for LiDAR Point Cloud](https://mlsanity.com/paper/2406.16279/) (2024)
- [HeLiMOS: A Dataset for Moving Object Segmentation in 3D Point Clouds From Heterogeneous LiDAR Sensors](https://mlsanity.com/paper/2408.06328/) (2024)
- [StreamMOS: Streaming Moving Object Segmentation with Multi-View Perception and Dual-Span Memory](https://mlsanity.com/paper/2407.17905/) (2024)
- [Scale, Don't Fine-tune: Guiding Multimodal LLMs for Efficient Visual Place Recognition at Test-Time](https://mlsanity.com/paper/2509.02129/) (2025)
- [You Sense Only Once Beneath: Ultra-Light Real-Time Underwater Object Detection](https://mlsanity.com/paper/2504.15694/) (2025)
- [MV-MOS: Multi-View Feature Fusion for 3D Moving Object Segmentation](https://mlsanity.com/paper/2408.10602/) (2024)
- [CV-MOS: A Cross-View Model for Motion Segmentation](https://mlsanity.com/paper/2408.13790/) (2024)
- [Diffusion-Based Restoration for Multi-Modal 3D Object Detection in Adverse Weather](https://mlsanity.com/paper/2512.13107/) (2025)
- [Test-Time Prototype Adaptation for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2608.08290/) (2026)
- [4D-CS: Exploiting Cluster Prior for 4D Spatio-Temporal LiDAR Semantic Segmentation](https://mlsanity.com/paper/2501.02937/) (2025)
- [HIF: Height Interval Filtering for Efficient Dynamic Points Removal](https://mlsanity.com/paper/2503.06863/) (2025)
- [Temporal Overlapping Prediction: A Self-supervised Pre-training Method for LiDAR Moving Object Segmentation](https://mlsanity.com/paper/2503.07167/) (2025)
- [Incorporating GNSS Information with LIDAR-Inertial Odometry for Accurate Land-Vehicle Localization](https://mlsanity.com/paper/2503.23199/) (2025)
- [KDMOS:Knowledge Distillation for Motion Segmentation](https://mlsanity.com/paper/2506.14130/) (2025)
- [ELMAR: Enhancing LiDAR Detection with 4D Radar Motion Awareness and Cross-modal Uncertainty](https://mlsanity.com/paper/2506.17958/) (2025)
- [A Pseudo Global Fusion Paradigm-Based Cross-View Network for LiDAR-Based Place Recognition](https://mlsanity.com/paper/2508.08917/) (2025)
- [Self-Supervised Moving Object Segmentation of Sparse and Noisy Radar Point Clouds](https://mlsanity.com/paper/2511.02395/) (2025)
- [DoublesEval: Diagnosing Multi-Agent Tactical Reasoning in Vision-Language Models via Professional Doubles Badminton](https://mlsanity.com/paper/2608.24439/) (2026)
- [WALT: Learning World-Model-Aligned Latent Trajectories for Autonomous Driving](https://mlsanity.com/paper/2609.30436/) (2026)

## Abstract (arXiv)

Moving object segmentation (MOS) provides a reliable solution for detecting traffic participants and thus is of great interest in the autonomous driving field. Dynamic capture is always critical in the MOS problem. Previous methods capture motion features from the range images directly. Differently, we argue that the residual maps provide greater potential for motion information, while range images contain rich semantic guidance. Based on this intuition, we propose MF-MOS, a novel motion-focused model with a dual-branch structure for LiDAR moving object segmentation. Novelly, we decouple the spatial-temporal information by capturing the motion from residual maps and generating semantic features from range images, which are used as movable object guidance for the motion branch. Our straightforward yet distinctive solution can make the most use of both range images and residual maps, thus greatly improving the performance of the LiDAR-based MOS task. Remarkably, our MF-MOS achieved a leading IoU of 76.7% on the MOS leaderboard of the SemanticKITTI dataset upon submission, demonstrating the current state-of-the-art performance. The implementation of our MF-MOS has been released at https://github.com/SCNU-RISLAB/MF-MOS.