# GMSF: Global Matching Scene Flow

arXiv: https://arxiv.org/abs/2305.17432 · HTML: https://mlsanity.com/paper/2305.17432/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 66 references that are in the map.
- First posted on arXiv 27 May 2023.

## Builds on (most cited first, 30 of 55)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [FlowNet3D: Learning Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/1806.01411/) (2018)
- [PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling](https://mlsanity.com/paper/2003.00492/) (2020)
- [Geometric Transformer for Fast and Robust Point Cloud Registration](https://mlsanity.com/paper/2202.06688/) (2022)
- [3D Object Detection with Pointformer](https://mlsanity.com/paper/2012.11409/) (2020)
- [TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech](https://mlsanity.com/paper/2007.06028/) (2020)
- [PPFNet: Global Context Aware Local Features for Robust 3D Point Matching](https://mlsanity.com/paper/1802.02669/) (2018)
- [DKM: Dense Kernelized Feature Matching for Geometry Estimation](https://mlsanity.com/paper/2202.00667/) (2022)
- [The Perfect Match: 3D Point Cloud Matching with Smoothed Densities](https://mlsanity.com/paper/1811.06879/) (2018)
- [CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration](https://mlsanity.com/paper/2110.14076/) (2021)
- [PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors](https://mlsanity.com/paper/1808.10322/) (2018)
- [FLOT: Scene Flow on Point Clouds Guided by Optimal Transport](https://mlsanity.com/paper/2007.11142/) (2020)

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

- [Zero-Shot Monocular Scene Flow Estimation in the Wild](https://mlsanity.com/paper/2501.10357/) (2025)
- [3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling](https://mlsanity.com/paper/2402.18146/) (2024)
- [HiMo: High-Speed Objects Motion Compensation in Point Clouds](https://mlsanity.com/paper/2503.00803/) (2025)
- [DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method](https://mlsanity.com/paper/2508.17054/) (2025)
- [DiffSF: Diffusion Models for Scene Flow Estimation](https://mlsanity.com/paper/2403.05327/) (2024)
- [TeFlow: Enabling Multi-frame Supervision for Self-Supervised Feed-forward Scene Flow Estimation](https://mlsanity.com/paper/2602.19053/) (2026)
- [Self-Supervised Multi-Frame Neural Scene Flow](https://mlsanity.com/paper/2403.16116/) (2024)
- [NeuroGauss4D-PCI: 4D Neural Fields and Gaussian Deformation Fields for Point Cloud Interpolation](https://mlsanity.com/paper/2405.14241/) (2024)
- [sim2art: Accurate Articulated Object Modeling from a Single Video using Synthetic Training Data Only](https://mlsanity.com/paper/2512.07698/) (2025)
- [SynFlow: Scaling Up LiDAR Scene Flow Estimation with Synthetic Data](https://mlsanity.com/paper/2604.09411/) (2026)
- [Articulation in Prime: Primitive-Based Articulated Object Understanding from a Single Casual Video](https://mlsanity.com/paper/2605.18645/) (2026)
- [SSRFlow: Semantic-aware Fusion with Spatial Temporal Re-embedding for Real-world Scene Flow](https://mlsanity.com/paper/2408.07825/) (2024)
- [Self-Supervised Scene Flow Estimation with Point-Voxel Fusion and Surface Representation](https://mlsanity.com/paper/2410.13355/) (2024)
- [UniFlow: Zero-Shot LiDAR Scene Flow for Autonomous Vehicles](https://mlsanity.com/paper/2511.18254/) (2025)

## Abstract (arXiv)

We tackle the task of scene flow estimation from point clouds. Given a source and a target point cloud, the objective is to estimate a translation from each point in the source point cloud to the target, resulting in a 3D motion vector field. Previous dominant scene flow estimation methods require complicated coarse-to-fine or recurrent architectures as a multi-stage refinement. In contrast, we propose a significantly simpler single-scale one-shot global matching to address the problem. Our key finding is that reliable feature similarity between point pairs is essential and sufficient to estimate accurate scene flow. We thus propose to decompose the feature extraction step via a hybrid local-global-cross transformer architecture which is crucial to accurate and robust feature representations. Extensive experiments show that the proposed Global Matching Scene Flow (GMSF) sets a new state-of-the-art on multiple scene flow estimation benchmarks. On FlyingThings3D, with the presence of occlusion points, GMSF reduces the outlier percentage from the previous best performance of 27.4% to 5.6%. On KITTI Scene Flow, without any fine-tuning, our proposed method shows state-of-the-art performance. On the Waymo-Open dataset, the proposed method outperforms previous methods by a large margin. The code is available at https://github.com/ZhangYushan3/GMSF.