mlsanityData to 7 Oct 2026

MGTR: Multi-Granular Transformer for Motion Prediction with LiDAR

arXiv 2312.02409 ↗First posted 5 Dec 2023cs.CV cs.ROcited by 9

Not on the map. Why?

Abstract (arXiv)

Motion prediction has been an essential component of autonomous driving systems since it handles highly uncertain and complex scenarios involving moving agents of different types. In this paper, we propose a Multi-Granular TRansformer (MGTR) framework, an encoder-decoder network that exploits context features in different granularities for different kinds of traffic agents. To further enhance MGTR's capabilities, we leverage LiDAR point cloud data by incorporating LiDAR semantic features from an off-the-shelf LiDAR feature extractor. We evaluate MGTR on Waymo Open Dataset motion prediction benchmark and show that the proposed method achieved state-of-the-art performance, ranking 1st on its leaderboard (https://waymo.com/open/challenges/2023/motion-prediction/).

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 35 of its 39 references that are in the map. First posted on arXiv 5 Dec 2023.

Builds on

35 of 39 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020End-to-End Object Detection with Transformerscited by 7,384
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2014Going Deeper with Convolutionscited by 4,231
  6. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  7. 2021Multiscale Vision Transformerscited by 896
  8. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 701
  9. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
  10. 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 532
  11. 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 528
  12. 2019MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Predictioncited by 417
23 more
  1. 2020TNT: Target-driveN Trajectory Predictioncited by 345
  2. 2021DenseTNT: End-to-end Trajectory Prediction from Dense Goal Setscited by 292
  3. 2018Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networkscited by 289
  4. 2022Wayformer: Motion Forecasting via Simple & Efficient Attention Networkscited by 279
  5. 2022Motion Transformer with Global Intention Localization and Local Movement Refinementcited by 267
  6. 2021MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Predictioncited by 246
  7. 2021MP3: A Unified Model to Map, Perceive, Predict and Plancited by 211
  8. 2021Scene Transformer: A unified architecture for predicting multiple agent trajectoriescited by 165
  9. 2021IntentNet: Learning to Predict Intention from Raw Sensor Datacited by 158
  10. 2023MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Queryingcited by 139
  11. 2019Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Datacited by 104
  12. 2020MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Mapscited by 100
  13. 2018Uncertainty-aware Short-term Motion Prediction of Traffic Actors for Autonomous Drivingcited by 90
  14. 2020TPNet: Trajectory Proposal Network for Motion Predictioncited by 80
  15. 2022LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perceptioncited by 74
  16. 2020MANTRA: Memory Augmented Networks for Multiple Trajectory Predictioncited by 69
  17. 2020Diverse and Admissible Trajectory Forecasting through Multimodal Context Understandingcited by 68
  18. 2020MultiXNet: Multiclass Multistage Multimodal Motion Predictioncited by 31
  19. 2023WOMD-LiDAR: Raw Sensor Dataset Benchmark for Motion Forecastingcited by 28
  20. 2021MVFuseNet: Improving End-to-End Object Detection and Motion Forecasting through Multi-View Fusion of LiDAR Datacited by 18
  21. 2023Pedestrian Crossing Action Recognition and Trajectory Prediction with 3D Human Keypointscited by 12
  22. 2022ReCoAt: A Deep Learning-based Framework for Multi-Modal Motion Prediction in Autonomous Driving Applicationcited by 9
  23. 2019Group Re-Identification with Multi-grained Matching and Integrationcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 0; 2026: 2.

9 papers.

  1. 2024DriveGPT: Scaling Autoregressive Behavior Models for Drivingcited by 29
  2. 2024Large Language Models Powered Context-aware Motion Prediction in Autonomous Drivingcited by 13
  3. 2024Transfer Learning Study of Motion Transformer-based Trajectory Predictionscited by 5
  4. 2024AMEND: A Mixture of Experts Framework for Long-tailed Trajectory Predictioncited by 4
  5. 2024DuoSpaceNet: Leveraging Both Bird's-Eye-View and Perspective View Representations for 3D Object Detectioncited by 2
  6. 2026Streaming Real-Time Trajectory Prediction Using Endpoint-Aware Modelingcited by 1
  7. 2024The Research of Group Re-identification from Multiple Camerascited by 0
  8. 2024LiMTR: Time Series Motion Prediction for Diverse Road Users through Multimodal Feature Integrationcited by 0
  9. 2026FlowS: One-Step Motion Prediction via Local Transport Conditioningcited by 0