# RMS-FlowNet: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds

arXiv: https://arxiv.org/abs/2204.00354 · HTML: https://mlsanity.com/paper/2204.00354/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 35 references that are in the map.
- First posted on arXiv 1 Apr 2022.

## Builds on (most cited first, 28 of 28)

- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [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)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [FlowNet3D: Learning Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/1806.01411/) (2018)
- [Optimal Transport for structured data with application on graphs](https://mlsanity.com/paper/1805.09114/) (2018)
- [FLOT: Scene Flow on Point Clouds Guided by Optimal Transport](https://mlsanity.com/paper/2007.11142/) (2020)
- [MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences](https://mlsanity.com/paper/1910.09165/) (2019)
- [HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds](https://mlsanity.com/paper/1906.05332/) (2019)
- [Just Go with the Flow: Self-Supervised Scene Flow Estimation](https://mlsanity.com/paper/1912.00497/) (2019)
- [PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds](https://mlsanity.com/paper/2012.00987/) (2020)
- [FlowStep3D: Model Unrolling for Self-Supervised Scene Flow Estimation](https://mlsanity.com/paper/2011.10147/) (2020)
- [Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation](https://mlsanity.com/paper/1808.01838/) (2018)
- [PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval](https://mlsanity.com/paper/1904.09793/) (2019)
- [Self-Supervised Monocular Scene Flow Estimation](https://mlsanity.com/paper/2004.04143/) (2020)
- [Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction](https://mlsanity.com/paper/1808.00758/) (2018)
- [Scene Flow from Point Clouds with or without Learning](https://mlsanity.com/paper/2011.00320/) (2020)
- [Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walk](https://mlsanity.com/paper/2105.08248/) (2021)
- [SENSE: a Shared Encoder Network for Scene-flow Estimation](https://mlsanity.com/paper/1910.12361/) (2019)
- [HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embedding](https://mlsanity.com/paper/2105.07751/) (2021)
- [Hierarchical Attention Learning of Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/2010.05762/) (2020)
- [Mono-SF: Multi-View Geometry Meets Single-View Depth for Monocular Scene Flow Estimation of Dynamic Traffic Scenes](https://mlsanity.com/paper/1908.06316/) (2019)
- [PWOC-3D: Deep Occlusion-Aware End-to-End Scene Flow Estimation](https://mlsanity.com/paper/1904.06116/) (2019)
- [Learning End-To-End Scene Flow by Distilling Single Tasks Knowledge](https://mlsanity.com/paper/1911.10090/) (2019)
- [A Deep Temporal Fusion Framework for Scene Flow Using a Learnable Motion Model and Occlusions](https://mlsanity.com/paper/2011.01603/) (2020)
- [SceneFlowFields: Dense Interpolation of Sparse Scene Flow Correspondences](https://mlsanity.com/paper/1710.10096/) (2017)

## Built on by (most cited first, 13 of 13)

- [Self-Supervised 3D Scene Flow Estimation Guided by Superpoints](https://mlsanity.com/paper/2305.02528/) (2023)
- [Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation](https://mlsanity.com/paper/2407.07995/) (2024)
- [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)
- [Re-Evaluating LiDAR Scene Flow for Autonomous Driving](https://mlsanity.com/paper/2304.02150/) (2023)
- [Neural Eulerian Scene Flow Fields](https://mlsanity.com/paper/2410.02031/) (2024)
- [ZeroFlow: Scalable Scene Flow via Distillation](https://mlsanity.com/paper/2305.10424/) (2023)
- [Multi-Body Neural Scene Flow](https://mlsanity.com/paper/2310.10301/) (2023)
- [Exploiting Implicit Rigidity Constraints via Weight-Sharing Aggregation for Scene Flow Estimation from Point Clouds](https://mlsanity.com/paper/2303.02454/) (2023)
- [RMS-FlowNet++: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds](https://mlsanity.com/paper/2407.01129/) (2024)
- [STARFlow: Spatial Temporal Feature Re-embedding with Attentive Learning for Real-world Scene Flow](https://mlsanity.com/paper/2403.07032/) (2024)
- [SSRFlow: Semantic-aware Fusion with Spatial Temporal Re-embedding for Real-world Scene Flow](https://mlsanity.com/paper/2408.07825/) (2024)
- [RAFT-MSF++: Temporal Geometry-Motion Feature Fusion for Self-Supervised Monocular Scene Flow](https://mlsanity.com/paper/2604.19349/) (2026)

## Abstract (arXiv)

The proposed RMS-FlowNet is a novel end-to-end learning-based architecture for accurate and efficient scene flow estimation which can operate on point clouds of high density. For hierarchical scene flow estimation, the existing methods depend on either expensive Farthest-Point-Sampling (FPS) or structure-based scaling which decrease their ability to handle a large number of points. Unlike these methods, we base our fully supervised architecture on Random-Sampling (RS) for multiscale scene flow prediction. To this end, we propose a novel flow embedding design which can predict more robust scene flow in conjunction with RS. Exhibiting high accuracy, our RMS-FlowNet provides a faster prediction than state-of-the-art methods and works efficiently on consecutive dense point clouds of more than 250K points at once. Our comprehensive experiments verify the accuracy of RMS-FlowNet on the established FlyingThings3D data set with different point cloud densities and validate our design choices. Additionally, we show that our model presents a competitive ability to generalize towards the real-world scenes of KITTI data set without fine-tuning.