# RaLiFlow: Scene Flow Estimation with 4D Radar and LiDAR Point Clouds

arXiv: https://arxiv.org/abs/2512.10376 · HTML: https://mlsanity.com/paper/2512.10376/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 58 references that are in the map.
- First posted on arXiv 11 Dec 2025.

## Builds on (most cited first, 30 of 39)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [FlowNet3D: Learning Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/1806.01411/) (2018)
- [SPLATNet: Sparse Lattice Networks for Point Cloud Processing](https://mlsanity.com/paper/1802.08275/) (2018)
- [Neural Scene Flow Prior](https://mlsanity.com/paper/2111.01253/) (2021)
- [Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2006.12052/) (2020)
- [CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation](https://mlsanity.com/paper/2111.10502/) (2021)
- [Scalable Scene Flow from Point Clouds in the Real World](https://mlsanity.com/paper/2103.01306/) (2021)
- [Global Attention Mechanism: Retain Information to Enhance Channel-Spatial Interactions](https://mlsanity.com/paper/2112.05561/) (2021)
- [SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving](https://mlsanity.com/paper/2407.01702/) (2024)
- [Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation](https://mlsanity.com/paper/2207.07522/) (2022)
- [Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision](https://mlsanity.com/paper/2303.00462/) (2023)
- [ICP-Flow: LiDAR Scene Flow Estimation with ICP](https://mlsanity.com/paper/2402.17351/) (2024)
- [DeFlow: Decoder of Scene Flow Network in Autonomous Driving](https://mlsanity.com/paper/2401.16122/) (2024)
- [Self-Supervised Scene Flow Estimation with 4-D Automotive Radar](https://mlsanity.com/paper/2203.01137/) (2022)
- [Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds](https://mlsanity.com/paper/2203.16895/) (2022)
- [Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detection](https://mlsanity.com/paper/2306.01438/) (2023)
- [RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimation](https://mlsanity.com/paper/2309.15082/) (2023)
- [SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation](https://mlsanity.com/paper/2105.04447/) (2021)
- [Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation](https://mlsanity.com/paper/2407.07995/) (2024)
- [EffiScene: Efficient Per-Pixel Rigidity Inference for Unsupervised Joint Learning of Optical Flow, Depth, Camera Pose and Motion Segmentation](https://mlsanity.com/paper/2011.08332/) (2020)
- [I Can't Believe It's Not Scene Flow!](https://mlsanity.com/paper/2403.04739/) (2024)
- [Zero-Shot Monocular Scene Flow Estimation in the Wild](https://mlsanity.com/paper/2501.10357/) (2025)
- [milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing](https://mlsanity.com/paper/2306.17010/) (2023)

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

- [Weakly Supervised Cross-Modal Learning for 4D Radar Scene Flow Estimation](https://mlsanity.com/paper/2605.18507/) (2026)
- [STAR-VLM: Spatiotemporal Grounding Vision-Language Models for Motion and Velocity Estimation via Automotive Radar Supervision](https://mlsanity.com/paper/2608.01535/) (2026)
- [4D Radar Perception Algorithms for Autonomous Driving: A Review](https://mlsanity.com/paper/2609.19216/) (2026)

## Abstract (arXiv)

Recent multimodal fusion methods, integrating images with LiDAR point clouds, have shown promise in scene flow estimation. However, the fusion of 4D millimeter wave radar and LiDAR remains unexplored. Unlike LiDAR, radar is cheaper, more robust in various weather conditions and can detect point-wise velocity, making it a valuable complement to LiDAR. However, radar inputs pose challenges due to noise, low resolution, and sparsity. Moreover, there is currently no dataset that combines LiDAR and radar data specifically for scene flow estimation. To address this gap, we construct a Radar-LiDAR scene flow dataset based on a public real-world automotive dataset. We propose an effective preprocessing strategy for radar denoising and scene flow label generation, deriving more reliable flow ground truth for radar points out of the object boundaries. Additionally, we introduce RaLiFlow, the first joint scene flow learning framework for 4D radar and LiDAR, which achieves effective radar-LiDAR fusion through a novel Dynamic-aware Bidirectional Cross-modal Fusion (DBCF) module and a carefully designed set of loss functions. The DBCF module integrates dynamic cues from radar into the local cross-attention mechanism, enabling the propagation of contextual information across modalities. Meanwhile, the proposed loss functions mitigate the adverse effects of unreliable radar data during training and enhance the instance-level consistency in scene flow predictions from both modalities, particularly for dynamic foreground areas. Extensive experiments on the repurposed scene flow dataset demonstrate that our method outperforms existing LiDAR-based and radar-based single-modal methods by a significant margin.