mlsanityData to 7 Oct 2026

MGF: Mixed Gaussian Flow for Diverse Trajectory Prediction

arXiv 2402.12238 ↗First posted 19 Feb 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

To predict future trajectories, the normalizing flow with a standard Gaussian prior suffers from weak diversity. The ineffectiveness comes from the conflict between the fact of asymmetric and multi-modal distribution of likely outcomes and symmetric and single-modal original distribution and supervision losses. Instead, we propose constructing a mixed Gaussian prior for a normalizing flow model for trajectory prediction. The prior is constructed by analyzing the trajectory patterns in the training samples without requiring extra annotations while showing better expressiveness and being multi-modal and asymmetric. Besides diversity, it also provides better controllability for probabilistic trajectory generation. We name our method Mixed Gaussian Flow (MGF). It achieves state-of-the-art performance in the evaluation of both trajectory alignment and diversity on the popular UCY/ETH and SDD datasets. Code is available at https://github.com/mulplue/MGF.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 42 of its 65 references that are in the map. First posted on arXiv 19 Feb 2024.

Builds on

42 of 65 references.

References · 42

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2016Density estimation using Real NVPcited by 2,029
  3. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  4. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  5. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 327
  6. 2020Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Predictioncited by 324
  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. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 251
  10. 2020It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Predictioncited by 235
  11. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 220
  12. 2016Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoderscited by 219
30 more
  1. 2020Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Predictioncited by 218
  2. 2017Social Attention: Modeling Attention in Human Crowdscited by 185
  3. 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 184
  4. 2022Stochastic Trajectory Prediction via Motion Indeterminacy Diffusioncited by 184
  5. 2019PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settingscited by 178
  6. 2020From Goals, Waypoints & Paths To Long Term Human Trajectory Forecastingcited by 166
  7. 2023Leapfrog Diffusion Model for Stochastic Trajectory Predictioncited by 129
  8. 2022GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoningcited by 128
  9. 2019Peeking into the Future: Predicting Future Person Activities and Locations in Videoscited by 112
  10. 2019SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Predictioncited by 111
  11. 2023EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoningcited by 97
  12. 2022Remember Intentions: Retrospective-Memory-based Trajectory Predictioncited by 86
  13. 2019Semi-Supervised Learning with Normalizing Flowscited by 76
  14. 2020Diverse and Admissible Trajectory Forecasting through Multimodal Context Understandingcited by 68
  15. 2021MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Predictioncited by 61
  16. 2021Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesiscited by 46
  17. 2022Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimationcited by 40
  18. 2021RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecastingcited by 36
  19. 2020DAG-Net: Double Attentive Graph Neural Network for Trajectory Forecastingcited by 30
  20. 2023Fast Inference and Update of Probabilistic Density Estimation on Trajectory Predictioncited by 27
  21. 2023SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Predictioncited by 27
  22. 2020Representational aspects of depth and conditioning in normalizing flowscited by 25
  23. 2019Noise Regularization for Conditional Density Estimationcited by 23
  24. 2021Online Multi-Agent Forecasting with Interpretable Collaborative Graph Neural Networkcited by 20
  25. 2019Generative Hybrid Representations for Activity Forecasting with No-Regret Learningcited by 18
  26. 2019Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmaxcited by 18
  27. 2018Gaussian Mixture Generative Adversarial Networks for Diverse Datasets, and the Unsupervised Clustering of Imagescited by 15
  28. 2023Another Vertical View: A Hierarchical Network for Heterogeneous Trajectory Prediction via Spectrumscited by 14
  29. 2021Instance-Aware Predictive Navigation in Multi-Agent Environmentscited by 5
  30. 2021PluGeN: Multi-Label Conditional Generation From Pre-Trained Modelscited by 5

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 3.

6 papers.

  1. 2024FollowGen: A Scaled Noise Conditional Diffusion Model for Car-Following Trajectory Predictioncited by 3
  2. 2024Crossfusor: A Cross-Attention Transformer Enhanced Conditional Diffusion Model for Car-Following Trajectory Predictioncited by 2
  3. 2024RealTraj: Towards Real-World Pedestrian Trajectory Forecastingcited by 2
  4. 2025Towards Efficient Real-Time Video Motion Transfer via Generative Time Series Modelingcited by 2
  5. 2025Recent Advances in Multi-Agent Human Trajectory Prediction: A Comprehensive Reviewcited by 2
  6. 2025PatchTraj: Unified Time-Frequency Representation Learning via Dynamic Patches for Trajectory Predictioncited by 0