mlsanityData to 7 Oct 2026

milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing

arXiv 2306.17010 ↗First posted 29 Jun 2023cs.CV cs.AI cs.LGcited by 20

Not on the map. Why?

Abstract (arXiv)

Human motion sensing plays a crucial role in smart systems for decision-making, user interaction, and personalized services. Extensive research that has been conducted is predominantly based on cameras, whose intrusive nature limits their use in smart home applications. To address this, mmWave radars have gained popularity due to their privacy-friendly features. In this work, we propose milliFlow, a novel deep learning approach to estimate scene flow as complementary motion information for mmWave point cloud, serving as an intermediate level of features and directly benefiting downstream human motion sensing tasks. Experimental results demonstrate the superior performance of our method when compared with the competing approaches. Furthermore, by incorporating scene flow information, we achieve remarkable improvements in human activity recognition and human parsing and support human body part tracking. Code and dataset are available at https://github.com/Toytiny/milliFlow.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 25 of its 96 references that are in the map. First posted on arXiv 29 Jun 2023.

Builds on

25 of 96 references.

References · 25

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  4. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  5. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
  6. 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 241
  7. 2020FLOT: Scene Flow on Point Clouds Guided by Optimal Transportcited by 129
  8. 2019Just Go with the Flow: Self-Supervised Scene Flow Estimationcited by 98
  9. 2021Neural Scene Flow Priorcited by 91
  10. 2020PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Cloudscited by 74
  11. 2020FlowStep3D: Model Unrolling for Self-Supervised Scene Flow Estimationcited by 71
  12. 2021Weakly Supervised Learning of Rigid 3D Scene Flowcited by 60
13 more
  1. 2019FlowNet3D++: Geometric Losses For Deep Scene Flow Estimationcited by 55
  2. 2021Scalable Scene Flow from Point Clouds in the Real Worldcited by 49
  3. 2022Dynamic 3D Scene Analysis by Point Cloud Accumulationcited by 47
  4. 2020Scene Flow from Point Clouds with or without Learningcited by 44
  5. 2022Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimationcited by 38
  6. 2023Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervisioncited by 36
  7. 2021FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Cloudscited by 30
  8. 2022Self-Supervised Scene Flow Estimation with 4-D Automotive Radarcited by 29
  9. 2017Scene Flow to Action Map: A New Representation for RGB-D based Action Recognition with Convolutional Neural Networkscited by 20
  10. 2021CubeLearn: End-to-end Learning for Human Motion Recognition from Raw mmWave Radar Signalscited by 17
  11. 2023Re-Evaluating LiDAR Scene Flow for Autonomous Drivingcited by 17
  12. 2022Cross Vision-RF Gait Re-identification with Low-cost RGB-D Cameras and mmWave Radarscited by 8
  13. 2020An Intelligent Non-Invasive Real Time Human Activity Recognition System for Next-Generation Healthcarecited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 11; 2026: 5.

20 papers.

Sort:

By area:

  1. 2024RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radarcited by 32
  2. 2023Exploring Radar Data Representations in Autonomous Driving: A Comprehensive Reviewcited by 22
  3. 2025RadarLLM: Empowering Large Language Models to Understand Human Motion from Millimeter-Wave Point Cloud Sequencecited by 7
  4. 2025M4Human: A Large-Scale Multimodal mmWave Radar Benchmark for Human Mesh Reconstructioncited by 6
  5. 2025TARS: Traffic-Aware Radar Scene Flow Estimationcited by 3
  6. 2025mmPred: Radar-based Human Motion Prediction in the Darkcited by 3
  7. 2025RaLiFlow: Scene Flow Estimation with 4D Radar and LiDAR Point Cloudscited by 3
  8. 2025Wideband RF Radiance Field Modeling Using Frequency-embedded 3D Gaussian Splattingcited by 2
  9. 2025RAPTR: Radar-based 3D Pose Estimation using Transformercited by 2
  10. 2025RISE: Single Static Radar-based Indoor Scene Understandingcited by 2
  11. 2025DNOI-4DRO: Deep 4D Radar Odometry with Differentiable Neural-Optimization Iterationscited by 1
  12. 2026A Two-Stage Motion-Aware Framework for mmWave-based Human Mesh Recoverycited by 1
8 more
  1. 2024STARFlow: Spatial Temporal Feature Re-embedding with Attentive Learning for Real-world Scene Flowcited by 0
  2. 2024SSRFlow: Semantic-aware Fusion with Spatial Temporal Re-embedding for Real-world Scene Flowcited by 0
  3. 2025mmFlux: Crowd Flow Analytics with Commodity mmWave MIMO Radarcited by 0
  4. 2025MSDNet: Efficient 4D Radar Super-Resolution via Multi-Stage Distillationcited by 0
  5. 2026Purify-then-Align: Towards Robust Human Sensing under Modality Missing with Knowledge Distillation from Noisy Multimodal Teachercited by 0
  6. 2026DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognitioncited by 0
  7. 2026mmHRI: Towards Privacy-Preserving Human-Robot Interaction with Millimeter-Wave Radarcited by 0
  8. 2026DiFF: Doppler-informed Flow Matching for Human Motion Flowcited by 0