# ZeroFlow: Scalable Scene Flow via Distillation

arXiv: https://arxiv.org/abs/2305.10424 · HTML: https://mlsanity.com/paper/2305.10424/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 52 references that are in the map.
- First posted on arXiv 17 May 2023.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [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)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training](https://mlsanity.com/paper/2210.00030/) (2022)
- [FlowNet3D: Learning Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/1806.01411/) (2018)
- [FLOT: Scene Flow on Point Clouds Guided by Optimal Transport](https://mlsanity.com/paper/2007.11142/) (2020)
- [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)
- [Neural Scene Flow Prior](https://mlsanity.com/paper/2111.01253/) (2021)
- [Smooth Shells: Multi-Scale Shape Registration with Functional Maps](https://mlsanity.com/paper/1905.12512/) (2019)
- [FlowStep3D: Model Unrolling for Self-Supervised Scene Flow Estimation](https://mlsanity.com/paper/2011.10147/) (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)
- [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)
- [Scene Flow from Point Clouds with or without Learning](https://mlsanity.com/paper/2011.00320/) (2020)
- [Self-Supervised Learning of Non-Rigid Residual Flow and Ego-Motion](https://mlsanity.com/paper/2009.10467/) (2020)
- [HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embedding](https://mlsanity.com/paper/2105.07751/) (2021)
- [Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds](https://mlsanity.com/paper/2203.16895/) (2022)
- [3D Object Detection with a Self-supervised Lidar Scene Flow Backbone](https://mlsanity.com/paper/2205.00705/) (2022)
- [RMS-FlowNet: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds](https://mlsanity.com/paper/2204.00354/) (2022)
- [Sparse PointPillars: Maintaining and Exploiting Input Sparsity to Improve Runtime on Embedded Systems](https://mlsanity.com/paper/2106.06882/) (2021)
- [FlowMOT: 3D Multi-Object Tracking by Scene Flow Association](https://mlsanity.com/paper/2012.07541/) (2020)

## Built on by (most cited first, 14 of 14)

- [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)
- [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)
- [Floxels: Fast Unsupervised Voxel Based Scene Flow Estimation](https://mlsanity.com/paper/2503.04718/) (2025)
- [DoGFlow: Self-Supervised LiDAR Scene Flow via Cross-Modal Doppler Guidance](https://mlsanity.com/paper/2508.18506/) (2025)
- [Let-It-Flow: Simultaneous Optimization of 3D Flow and Object Clustering](https://mlsanity.com/paper/2404.08363/) (2024)
- [SemanticFlow: A Self-Supervised Framework for Joint Scene Flow Prediction and Instance Segmentation in Dynamic Environments](https://mlsanity.com/paper/2503.14837/) (2025)
- [Regularizing Self-supervised 3D Scene Flows with Surface Awareness and Cyclic Consistency](https://mlsanity.com/paper/2312.08879/) (2023)
- [4DSegStreamer: Streaming 4D Panoptic Segmentation via Dual Threads](https://mlsanity.com/paper/2510.17664/) (2025)
- [H-Flow: Self-supervised Human Scene Flow via Physics-inspired Joint Multi-modal Learning](https://mlsanity.com/paper/2605.22629/) (2026)
- [TriO: Tri-Modal Unsupervised Occupancy World Model for Anything Perception](https://mlsanity.com/paper/2609.32013/) (2026)
- [MeshBind: Point-to-Mesh Binding for Non-Rigid Scene Flow Automatic Annotation](https://mlsanity.com/paper/2610.12895/) (2026)

## Abstract (arXiv)

Scene flow estimation is the task of describing the 3D motion field between temporally successive point clouds. State-of-the-art methods use strong priors and test-time optimization techniques, but require on the order of tens of seconds to process full-size point clouds, making them unusable as computer vision primitives for real-time applications such as open world object detection. Feedforward methods are considerably faster, running on the order of tens to hundreds of milliseconds for full-size point clouds, but require expensive human supervision. To address both limitations, we propose Scene Flow via Distillation, a simple, scalable distillation framework that uses a label-free optimization method to produce pseudo-labels to supervise a feedforward model. Our instantiation of this framework, ZeroFlow, achieves state-of-the-art performance on the Argoverse 2 Self-Supervised Scene Flow Challenge while using zero human labels by simply training on large-scale, diverse unlabeled data. At test-time, ZeroFlow is over 1000x faster than label-free state-of-the-art optimization-based methods on full-size point clouds (34 FPS vs 0.028 FPS) and over 1000x cheaper to train on unlabeled data compared to the cost of human annotation (394 vs ~750,000). To facilitate further research, we release our code, trained model weights, and high quality pseudo-labels for the Argoverse 2 and Waymo Open datasets at https://vedder.io/zeroflow.html