# What Matters for 3D Scene Flow Network

arXiv: https://arxiv.org/abs/2207.09143 · HTML: https://mlsanity.com/paper/2207.09143/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 54 references that are in the map.
- First posted on arXiv 19 Jul 2022.

## Builds on (most cited first, 30 of 33)

- [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)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [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)
- [FLOT: Scene Flow on Point Clouds Guided by Optimal Transport](https://mlsanity.com/paper/2007.11142/) (2020)
- [What Matters in Unsupervised Optical Flow](https://mlsanity.com/paper/2006.04902/) (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)
- [SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition](https://mlsanity.com/paper/2011.12430/) (2020)
- [Self-Supervised Monocular Scene Flow Estimation](https://mlsanity.com/paper/2004.04143/) (2020)
- [Deep Rigid Instance Scene Flow](https://mlsanity.com/paper/1904.08913/) (2019)
- [Learning to Segment Rigid Motions from Two Frames](https://mlsanity.com/paper/2101.03694/) (2021)
- [Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walk](https://mlsanity.com/paper/2105.08248/) (2021)
- [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)
- [PWCLO-Net: Deep LiDAR Odometry in 3D Point Clouds Using Hierarchical Embedding Mask Optimization](https://mlsanity.com/paper/2012.00972/) (2020)
- [FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Clouds](https://mlsanity.com/paper/2104.00798/) (2021)
- [Self-Supervised Multi-Frame Monocular Scene Flow](https://mlsanity.com/paper/2105.02216/) (2021)
- [Efficient 3D Deep LiDAR Odometry](https://mlsanity.com/paper/2111.02135/) (2021)
- [PointTrackNet: An End-to-End Network For 3-D Object Detection and Tracking From Point Clouds](https://mlsanity.com/paper/2002.11559/) (2020)
- [Anchor-Based Spatio-Temporal Attention 3D Convolutional Networks for Dynamic 3D Point Cloud Sequences](https://mlsanity.com/paper/2012.10860/) (2020)
- [Unsupervised Learning of 3D Scene Flow from Monocular Camera](https://mlsanity.com/paper/2206.03673/) (2022)

## Built on by (most cited first, 30 of 31)

- [RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration](https://mlsanity.com/paper/2303.12384/) (2023)
- [Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision](https://mlsanity.com/paper/2303.00462/) (2023)
- [SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flow](https://mlsanity.com/paper/2211.14020/) (2022)
- [Self-Supervised 3D Scene Flow Estimation Guided by Superpoints](https://mlsanity.com/paper/2305.02528/) (2023)
- [Zero-Shot Monocular Scene Flow Estimation in the Wild](https://mlsanity.com/paper/2501.10357/) (2025)
- [Align then Adapt: Rethinking Parameter-Efficient Transfer Learning in 4D Perception](https://mlsanity.com/paper/2602.23069/) (2026)
- [Re-Evaluating LiDAR Scene Flow for Autonomous Driving](https://mlsanity.com/paper/2304.02150/) (2023)
- [3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling](https://mlsanity.com/paper/2402.18146/) (2024)
- [GMSF: Global Matching Scene Flow](https://mlsanity.com/paper/2305.17432/) (2023)
- [DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds](https://mlsanity.com/paper/2308.04383/) (2023)
- [Multi-Body Neural Scene Flow](https://mlsanity.com/paper/2310.10301/) (2023)
- [DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Diffusion Model](https://mlsanity.com/paper/2311.17456/) (2023)
- [ManiFoundation Model for General-Purpose Robotic Manipulation of Contact Synthesis with Arbitrary Objects and Robots](https://mlsanity.com/paper/2405.06964/) (2024)
- [End-to-end 2D-3D Registration between Image and LiDAR Point Cloud for Vehicle Localization](https://mlsanity.com/paper/2306.11346/) (2023)
- [DiffSF: Diffusion Models for Scene Flow Estimation](https://mlsanity.com/paper/2403.05327/) (2024)
- [OptFlow: Fast Optimization-based Scene Flow Estimation without Supervision](https://mlsanity.com/paper/2401.02550/) (2024)
- [FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagation](https://mlsanity.com/paper/2412.17366/) (2024)
- [EMR-MSF: Self-Supervised Recurrent Monocular Scene Flow Exploiting Ego-Motion Rigidity](https://mlsanity.com/paper/2309.01296/) (2023)
- [Self-Supervised Multi-Frame Neural Scene Flow](https://mlsanity.com/paper/2403.16116/) (2024)
- [RegFormer++: An Efficient Large-Scale 3D LiDAR Point Registration Network with Projection-Aware 2D Transformer](https://mlsanity.com/paper/2603.14290/) (2026)
- [Unsupervised Learning of 3D Scene Flow with 3D Odometry Assistance](https://mlsanity.com/paper/2209.04945/) (2022)
- [Self-Supervised 3D Scene Flow Estimation and Motion Prediction using Local Rigidity Prior](https://mlsanity.com/paper/2310.11284/) (2023)
- [Weakly and Self-Supervised Class-Agnostic Motion Prediction for Autonomous Driving](https://mlsanity.com/paper/2509.13116/) (2025)
- [Exploiting Implicit Rigidity Constraints via Weight-Sharing Aggregation for Scene Flow Estimation from Point Clouds](https://mlsanity.com/paper/2303.02454/) (2023)
- [SSFlowNet: Semi-supervised Scene Flow Estimation On Point Clouds With Pseudo Label](https://mlsanity.com/paper/2312.15271/) (2023)
- [CMU-Flownet: Exploring Point Cloud Scene Flow Estimation in Occluded Scenario](https://mlsanity.com/paper/2404.10571/) (2024)
- [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)
- [EgoFlowNet: Non-Rigid Scene Flow from Point Clouds with Ego-Motion Support](https://mlsanity.com/paper/2407.02920/) (2024)
- [SSRFlow: Semantic-aware Fusion with Spatial Temporal Re-embedding for Real-world Scene Flow](https://mlsanity.com/paper/2408.07825/) (2024)

## Abstract (arXiv)

3D scene flow estimation from point clouds is a low-level 3D motion perception task in computer vision. Flow embedding is a commonly used technique in scene flow estimation, and it encodes the point motion between two consecutive frames. Thus, it is critical for the flow embeddings to capture the correct overall direction of the motion. However, previous works only search locally to determine a soft correspondence, ignoring the distant points that turn out to be the actual matching ones. In addition, the estimated correspondence is usually from the forward direction of the adjacent point clouds, and may not be consistent with the estimated correspondence acquired from the backward direction. To tackle these problems, we propose a novel all-to-all flow embedding layer with backward reliability validation during the initial scene flow estimation. Besides, we investigate and compare several design choices in key components of the 3D scene flow network, including the point similarity calculation, input elements of predictor, and predictor & refinement level design. After carefully choosing the most effective designs, we are able to present a model that achieves the state-of-the-art performance on FlyingThings3D and KITTI Scene Flow datasets. Our proposed model surpasses all existing methods by at least 38.2% on FlyingThings3D dataset and 24.7% on KITTI Scene Flow dataset for EPE3D metric. We release our codes at https://github.com/IRMVLab/3DFlow.