# ICP-Flow: LiDAR Scene Flow Estimation with ICP

arXiv: https://arxiv.org/abs/2402.17351 · HTML: https://mlsanity.com/paper/2402.17351/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 61 references that are in the map.
- First posted on arXiv 27 Feb 2024.

## Builds on (most cited first, 30 of 36)

- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [TEASER: Fast and Certifiable Point Cloud Registration](https://mlsanity.com/paper/2001.07715/) (2020)
- [FlowNet3D: Learning Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/1806.01411/) (2018)
- [Deep Global Registration](https://mlsanity.com/paper/2004.11540/) (2020)
- [KISS-ICP: In Defense of Point-to-Point ICP -- Simple, Accurate, and Robust Registration If Done the Right Way](https://mlsanity.com/paper/2209.15397/) (2022)
- [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)
- [Accelerated Hierarchical Density Clustering](https://mlsanity.com/paper/1705.07321/) (2017)
- [Just Go with the Flow: Self-Supervised Scene Flow Estimation](https://mlsanity.com/paper/1912.00497/) (2019)
- [Neural Scene Flow Prior](https://mlsanity.com/paper/2111.01253/) (2021)
- [3D Registration with Maximal Cliques](https://mlsanity.com/paper/2305.10854/) (2023)
- [FlowStep3D: Model Unrolling for Self-Supervised Scene Flow Estimation](https://mlsanity.com/paper/2011.10147/) (2020)
- [AB3DMOT: A Baseline for 3D Multi-Object Tracking and New Evaluation Metrics](https://mlsanity.com/paper/2008.08063/) (2020)
- [Weakly Supervised Learning of Rigid 3D Scene Flow](https://mlsanity.com/paper/2102.08945/) (2021)
- [Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving](https://mlsanity.com/paper/2210.08061/) (2022)
- [FlowNet3D++: Geometric Losses For Deep Scene Flow Estimation](https://mlsanity.com/paper/1912.01438/) (2019)
- [CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations](https://mlsanity.com/paper/2008.02792/) (2020)
- [Scalable Scene Flow from Point Clouds in the Real World](https://mlsanity.com/paper/2103.01306/) (2021)
- [Dynamic 3D Scene Analysis by Point Cloud Accumulation](https://mlsanity.com/paper/2207.12394/) (2022)
- [Self-Supervised Learning of Non-Rigid Residual Flow and Ego-Motion](https://mlsanity.com/paper/2009.10467/) (2020)
- [Fast Neural Scene Flow](https://mlsanity.com/paper/2304.09121/) (2023)
- [Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walk](https://mlsanity.com/paper/2105.08248/) (2021)
- [Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation](https://mlsanity.com/paper/2207.07522/) (2022)
- [FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Clouds](https://mlsanity.com/paper/2104.00798/) (2021)

## Built on by (most cited first, 30 of 35)

- [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)
- [UNION: Unsupervised 3D Object Detection using Object Appearance-based Pseudo-Classes](https://mlsanity.com/paper/2405.15688/) (2024)
- [FlowDreamer: A RGB-D World Model with Flow-based Motion Representations for Robot Manipulation](https://mlsanity.com/paper/2505.10075/) (2025)
- [Neural Eulerian Scene Flow Fields](https://mlsanity.com/paper/2410.02031/) (2024)
- [SSF: Sparse Long-Range Scene Flow for Autonomous Driving](https://mlsanity.com/paper/2501.17821/) (2025)
- [SLCF-Net: Sequential LiDAR-Camera Fusion for Semantic Scene Completion using a 3D Recurrent U-Net](https://mlsanity.com/paper/2403.08885/) (2024)
- [HiMo: High-Speed Objects Motion Compensation in Point Clouds](https://mlsanity.com/paper/2503.00803/) (2025)
- [VoteFlow: Enforcing Local Rigidity in Self-Supervised Scene Flow](https://mlsanity.com/paper/2503.22328/) (2025)
- [Floxels: Fast Unsupervised Voxel Based Scene Flow Estimation](https://mlsanity.com/paper/2503.04718/) (2025)
- [MambaFlow: A Novel and Flow-guided State Space Model for Scene Flow Estimation](https://mlsanity.com/paper/2502.16907/) (2025)
- [DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method](https://mlsanity.com/paper/2508.17054/) (2025)
- [TeFlow: Enabling Multi-frame Supervision for Self-Supervised Feed-forward Scene Flow Estimation](https://mlsanity.com/paper/2602.19053/) (2026)
- [DoGFlow: Self-Supervised LiDAR Scene Flow via Cross-Modal Doppler Guidance](https://mlsanity.com/paper/2508.18506/) (2025)
- [Label-Efficient 3D Object Detection For Road-Side Units](https://mlsanity.com/paper/2404.06256/) (2024)
- [Let-It-Flow: Simultaneous Optimization of 3D Flow and Object Clustering](https://mlsanity.com/paper/2404.08363/) (2024)
- [TARS: Traffic-Aware Radar Scene Flow Estimation](https://mlsanity.com/paper/2503.10210/) (2025)
- [SemanticFlow: A Self-Supervised Framework for Joint Scene Flow Prediction and Instance Segmentation in Dynamic Environments](https://mlsanity.com/paper/2503.14837/) (2025)
- [RaLiFlow: Scene Flow Estimation with 4D Radar and LiDAR Point Clouds](https://mlsanity.com/paper/2512.10376/) (2025)
- [SynFlow: Scaling Up LiDAR Scene Flow Estimation with Synthetic Data](https://mlsanity.com/paper/2604.09411/) (2026)
- [Dual-frame Fluid Motion Estimation with Test-time Optimization and Zero-divergence Loss](https://mlsanity.com/paper/2410.11934/) (2024)
- [Estimating Scene Flow in Robot Surroundings with Distributed Miniaturized Time-of-Flight Sensors](https://mlsanity.com/paper/2504.02439/) (2025)
- [UniLiPs: Unified LiDAR Pseudo-Labeling with Geometry-Grounded Dynamic Scene Decomposition](https://mlsanity.com/paper/2601.05105/) (2026)
- [Temporal Overlapping Prediction: A Self-supervised Pre-training Method for LiDAR Moving Object Segmentation](https://mlsanity.com/paper/2503.07167/) (2025)
- [xMOD: Cross-Modal Distillation for 2D/3D Multi-Object Discovery from 2D motion](https://mlsanity.com/paper/2503.15022/) (2025)
- [VITON-DRR: Details Retention Virtual Try-on via Non-rigid Registration](https://mlsanity.com/paper/2505.23439/) (2025)
- [UniFlow: Zero-Shot LiDAR Scene Flow for Autonomous Vehicles](https://mlsanity.com/paper/2511.18254/) (2025)
- [Training-Free Global Geometric Association for 4D LiDAR Panoptic Segmentation](https://mlsanity.com/paper/2512.18991/) (2025)
- [Motion Cues from Image-based Point Tracking for LiDAR Scene Flow Estimation](https://mlsanity.com/paper/2605.16922/) (2026)
- [Weakly Supervised Cross-Modal Learning for 4D Radar Scene Flow Estimation](https://mlsanity.com/paper/2605.18507/) (2026)

## Abstract (arXiv)

Scene flow characterizes the 3D motion between two LiDAR scans captured by an autonomous vehicle at nearby timesteps. Prevalent methods consider scene flow as point-wise unconstrained flow vectors that can be learned by either large-scale training beforehand or time-consuming optimization at inference. However, these methods do not take into account that objects in autonomous driving often move rigidly. We incorporate this rigid-motion assumption into our design, where the goal is to associate objects over scans and then estimate the locally rigid transformations. We propose ICP-Flow, a learning-free flow estimator. The core of our design is the conventional Iterative Closest Point (ICP) algorithm, which aligns the objects over time and outputs the corresponding rigid transformations. Crucially, to aid ICP, we propose a histogram-based initialization that discovers the most likely translation, thus providing a good starting point for ICP. The complete scene flow is then recovered from the rigid transformations. We outperform state-of-the-art baselines, including supervised models, on the Waymo dataset and perform competitively on Argoverse-v2 and nuScenes. Further, we train a feedforward neural network, supervised by the pseudo labels from our model, and achieve top performance among all models capable of real-time inference. We validate the advantage of our model on scene flow estimation with longer temporal gaps, up to 0.4 seconds where other models fail to deliver meaningful results.