mlsanityData to 7 Oct 2026

MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction

arXiv 2108.09274 ↗First posted 20 Aug 2021cs.CVcited by 61

Not on the map. Why?

Abstract (arXiv)

Pedestrian trajectory prediction is challenging due to its uncertain and multimodal nature. While generative adversarial networks can learn a distribution over future trajectories, they tend to predict out-of-distribution samples when the distribution of future trajectories is a mixture of multiple, possibly disconnected modes. To address this issue, we propose a multi-generator model for pedestrian trajectory prediction. Each generator specializes in learning a distribution over trajectories routing towards one of the primary modes in the scene, while a second network learns a categorical distribution over these generators, conditioned on the dynamics and scene input. This architecture allows us to effectively sample from specialized generators and to significantly reduce the out-of-distribution samples compared to single generator methods.

Key facts. Cited by 61 papers in the map (data through 7 Oct 2026). Builds on 29 of its 45 references that are in the map. First posted on arXiv 20 Aug 2021.

Builds on

29 of 45 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  3. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  4. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  5. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  6. 2018Assessing Generative Models via Precision and Recallcited by 401
  7. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  8. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 296
  9. 2017Toward Multimodal Image-to-Image Translationcited by 295
  10. 2020It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Predictioncited by 235
  11. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 228
  12. 2016Unrolled Generative Adversarial Networkscited by 208
17 more
  1. 2017Generalization and Equilibrium in Generative Adversarial Nets (GANs)cited by 165
  2. 2016Discrete Variational Autoencoderscited by 124
  3. 2017Neural Expectation Maximizationcited by 123
  4. 2019Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANscited by 78
  5. 2019Conditional Generative Neural System for Probabilistic Trajectory Predictioncited by 76
  6. 2019The Garden of Forking Paths: Towards Multi-Future Trajectory Predictioncited by 72
  7. 2020Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Planscited by 72
  8. 2017Multi-Agent Diverse Generative Adversarial Networkscited by 59
  9. 2020Goal-GAN: Multimodal Trajectory Prediction Based on Goal Position Estimationcited by 57
  10. 2018Accurate and Diverse Sampling of Sequences based on a "Best of Many" Sample Objectivecited by 56
  11. 2019Conditional Flow Variational Autoencoders for Structured Sequence Predictioncited by 36
  12. 2017AdaGAN: Boosting Generative Modelscited by 34
  13. 2017CAR-Net: Clairvoyant Attentive Recurrent Networkcited by 34
  14. 2018Disconnected Manifold Learning for Generative Adversarial Networkscited by 27
  15. 2020Learning disconnected manifolds: a no GANs landcited by 25
  16. 2018GD-GAN: Generative Adversarial Networks for Trajectory Prediction and Group Detection in Crowdscited by 15
  17. 2016Ensembles of Generative Adversarial Networkscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 11; 2023: 18; 2024: 16; 2025: 13; 2026: 3.

61 papers.

Sort:

By area:

  1. 2022Stochastic Trajectory Prediction via Motion Indeterminacy Diffusioncited by 184
  2. 2023Leapfrog Diffusion Model for Stochastic Trajectory Predictioncited by 129
  3. 2022Adaptive Trajectory Prediction via Transferable GNNcited by 51
  4. 2022Non-Probability Sampling Network for Stochastic Human Trajectory Predictioncited by 46
  5. 2022Learning Pedestrian Group Representations for Multi-modal Trajectory Predictioncited by 44
  6. 2023EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecastingcited by 41
  7. 2024SingularTrajectory: Universal Trajectory Predictor Using Diffusion Modelcited by 35
  8. 2024Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Predictioncited by 31
  9. 2025MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation based Distillationcited by 31
  10. 2023The Integration of Prediction and Planning in Deep Learning Automated Driving Systems: A Reviewcited by 29
  11. 2022Forecasting from LiDAR via Future Object Detectioncited by 28
  12. 2022Goal-driven Self-Attentive Recurrent Networks for Trajectory Predictioncited by 28
38 more
  1. 2022Dynamic-Group-Aware Networks for Multi-Agent Trajectory Prediction with Relational Reasoningcited by 28
  2. 2022Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking?cited by 28
  3. 2023Fast Inference and Update of Probabilistic Density Estimation on Trajectory Predictioncited by 27
  4. 2024LG-Traj: LLM Guided Pedestrian Trajectory Predictioncited by 24
  5. 2022PedFormer: Pedestrian Behavior Prediction via Cross-Modal Attention Modulation and Gated Multitask Learningcited by 23
  6. 2024MART: MultiscAle Relational Transformer Networks for Multi-agent Trajectory Predictioncited by 21
  7. 2022LatentFormer: Multi-Agent Transformer-Based Interaction Modeling and Trajectory Predictioncited by 19
  8. 2023DICE: Diverse Diffusion Model with Scoring for Trajectory Predictioncited by 18
  9. 2023Unsupervised Sampling Promoting for Stochastic Human Trajectory Predictioncited by 17
  10. 2025Unified Uncertainty-Aware Diffusion for Multi-Agent Trajectory Modelingcited by 15
  11. 2025Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directionscited by 14
  12. 2022Collaborative Uncertainty Benefits Multi-Agent Multi-Modal Trajectory Forecastingcited by 13
  13. 2023Uncertainty-Aware Pedestrian Trajectory Prediction via Distributional Diffusioncited by 13
  14. 2023A Novel Benchmarking Paradigm and a Scale- and Motion-Aware Model for Egocentric Pedestrian Trajectory Predictioncited by 12
  15. 2024Social Physics Informed Diffusion Model for Crowd Simulationcited by 11
  16. 2024Intention-aware Denoising Diffusion Model for Trajectory Predictioncited by 11
  17. 2023Vision-based Multi-future Trajectory Prediction: A Surveycited by 8
  18. 2023TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Modelscited by 8
  19. 2023Conditional Unscented Autoencoders for Trajectory Predictioncited by 7
  20. 2023PGODE: Towards High-quality System Dynamics Modelingcited by 7
  21. 2025Continuous Locomotive Crowd Behavior Generationcited by 7
  22. 2025TrajFlow: Multi-modal Motion Prediction via Flow Matchingcited by 7
  23. 2024MGF: Mixed Gaussian Flow for Diverse Trajectory Predictioncited by 6
  24. 2023Distilling Knowledge for Short-to-Long Term Trajectory Predictioncited by 5
  25. 2024Towards Generalizable and Interpretable Motion Prediction: A Deep Variational Bayes Approachcited by 5
  26. 2025TrajEvo: Designing Trajectory Prediction Heuristics via LLM-driven Evolutioncited by 5
  27. 2025Social-Pose: Enhancing Trajectory Prediction with Human Body Posecited by 5
  28. 2025TrajEvo: Trajectory Prediction Heuristics Design via LLM-driven Evolutioncited by 5
  29. 2023Scene Style Text Editingcited by 4
  30. 2023XVTP3D: Cross-view Trajectory Prediction Using Shared 3D Queries for Autonomous Drivingcited by 4
  31. 2024AMEND: A Mixture of Experts Framework for Long-tailed Trajectory Predictioncited by 4
  32. 2024Motion Forecasting via Model-Based Risk Minimizationcited by 4
  33. 2023GDTS: Goal-Guided Diffusion Model with Tree Sampling for Multi-Modal Pedestrian Trajectory Predictioncited by 3
  34. 2023Sparse Pedestrian Character Learning for Trajectory Predictioncited by 3
  35. 2024Evaluating Human Trajectory Prediction with Metamorphic Testingcited by 3
  36. 2024Building Real-time Awareness of Out-of-distribution in Trajectory Prediction for Autonomous Vehiclescited by 3
  37. 2025Stochastic Trajectory Prediction under Unstructured Constraintscited by 3
  38. 2026Heteroscedastic Diffusion for Multi-Agent Trajectory Modelingcited by 3

50 most cited of 61 All 61 (JSON)