# DeFlow: Decoder of Scene Flow Network in Autonomous Driving

arXiv: https://arxiv.org/abs/2401.16122 · HTML: https://mlsanity.com/paper/2401.16122/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 36 references that are in the map.
- First posted on arXiv 29 Jan 2024.

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

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [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)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [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)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds](https://mlsanity.com/paper/1910.06528/) (2019)
- [Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation](https://mlsanity.com/paper/1904.05290/) (2019)
- [Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2206.02099/) (2022)
- [Neural Scene Flow Prior](https://mlsanity.com/paper/2111.01253/) (2021)
- [CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow](https://mlsanity.com/paper/2203.16896/) (2022)
- [PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds](https://mlsanity.com/paper/2012.00987/) (2020)
- [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)
- [Patchwork++: Fast and Robust Ground Segmentation Solving Partial Under-Segmentation Using 3D Point Cloud](https://mlsanity.com/paper/2207.11919/) (2022)
- [Self-Supervised Pillar Motion Learning for Autonomous Driving](https://mlsanity.com/paper/2104.08683/) (2021)
- [Fast Neural Scene Flow](https://mlsanity.com/paper/2304.09121/) (2023)
- [Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation](https://mlsanity.com/paper/2207.07522/) (2022)
- [Open-world Semantic Segmentation for LIDAR Point Clouds](https://mlsanity.com/paper/2207.01452/) (2022)
- [SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flow](https://mlsanity.com/paper/2211.14020/) (2022)
- [Dynablox: Real-time Detection of Diverse Dynamic Objects in Complex Environments](https://mlsanity.com/paper/2304.10049/) (2023)
- [A Dynamic Points Removal Benchmark in Point Cloud Maps](https://mlsanity.com/paper/2307.07260/) (2023)
- [GMA3D: Local-Global Attention Learning to Estimate Occluded Motions of Scene Flow](https://mlsanity.com/paper/2210.03296/) (2022)

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

- [SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving](https://mlsanity.com/paper/2407.01702/) (2024)
- [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)
- [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)
- [HiMo: High-Speed Objects Motion Compensation in Point Clouds](https://mlsanity.com/paper/2503.00803/) (2025)
- [DUFOMap: Efficient Dynamic Awareness Mapping](https://mlsanity.com/paper/2403.01449/) (2024)
- [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)
- [AGO: Adaptive Grounding for Open World 3D Occupancy Prediction](https://mlsanity.com/paper/2504.10117/) (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)
- [BeautyMap: Binary-Encoded Adaptable Ground Matrix for Dynamic Points Removal in Global Maps](https://mlsanity.com/paper/2405.07283/) (2024)
- [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)
- [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)
- [RegFormer++: An Efficient Large-Scale 3D LiDAR Point Registration Network with Projection-Aware 2D Transformer](https://mlsanity.com/paper/2603.14290/) (2026)
- [SSF-PAN: Semantic Scene Flow-Based Perception for Autonomous Navigation in Traffic Scenarios](https://mlsanity.com/paper/2501.16754/) (2025)
- [AsyncBEV: Cross-modal Flow Alignment in Asynchronous 3D Object Detection](https://mlsanity.com/paper/2601.12994/) (2026)
- [SynFlow: Scaling Up LiDAR Scene Flow Estimation with Synthetic Data](https://mlsanity.com/paper/2604.09411/) (2026)
- [Temporal Overlapping Prediction: A Self-supervised Pre-training Method for LiDAR Moving Object Segmentation](https://mlsanity.com/paper/2503.07167/) (2025)
- [UniFlow: Zero-Shot LiDAR Scene Flow for Autonomous Vehicles](https://mlsanity.com/paper/2511.18254/) (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)
- [CorrelationFlow: A Training-Free Geometric Approach for LiDAR Scene Flow Estimation](https://mlsanity.com/paper/2607.29237/) (2026)
- [RVLoss: Runoff Vote Loss for Self-Supervised LiDAR Scene Flow Estimation](https://mlsanity.com/paper/2608.18864/) (2026)
- [AevaScenes: An FMCW LiDAR Dataset and Benchmark for Long-Range Perception](https://mlsanity.com/paper/2609.33230/) (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 determines a scene's 3D motion field, by predicting the motion of points in the scene, especially for aiding tasks in autonomous driving. Many networks with large-scale point clouds as input use voxelization to create a pseudo-image for real-time running. However, the voxelization process often results in the loss of point-specific features. This gives rise to a challenge in recovering those features for scene flow tasks. Our paper introduces DeFlow which enables a transition from voxel-based features to point features using Gated Recurrent Unit (GRU) refinement. To further enhance scene flow estimation performance, we formulate a novel loss function that accounts for the data imbalance between static and dynamic points. Evaluations on the Argoverse 2 scene flow task reveal that DeFlow achieves state-of-the-art results on large-scale point cloud data, demonstrating that our network has better performance and efficiency compared to others. The code is open-sourced at https://github.com/KTH-RPL/deflow.