mlsanityData to 13 Oct 2026

Stochastic Multi-Person 3D Motion Forecasting

arXiv 2306.05421 ↗First posted 8 Jun 2023cs.CVcited by 28

Not on the map. Why?

Abstract (arXiv)

This paper aims to deal with the ignored real-world complexities in prior work on human motion forecasting, emphasizing the social properties of multi-person motion, the diversity of motion and social interactions, and the complexity of articulated motion. To this end, we introduce a novel task of stochastic multi-person 3D motion forecasting. We propose a dual-level generative modeling framework that separately models independent individual motion at the local level and social interactions at the global level. Notably, this dual-level modeling mechanism can be achieved within a shared generative model, through introducing learnable latent codes that represent intents of future motion and switching the codes' modes of operation at different levels. Our framework is general; we instantiate it with different generative models, including generative adversarial networks and diffusion models, and various multi-person forecasting models. Extensive experiments on CMU-Mocap, MuPoTS-3D, and SoMoF benchmarks show that our approach produces diverse and accurate multi-person predictions, significantly outperforming the state of the art.

Key facts. Cited by 28 papers in the map (data through 13 Oct 2026). Builds on 50 of its 76 references that are in the map. First posted on arXiv 8 Jun 2023.

Builds on

50 of 76 references.

References · 50

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,952
  3. 2020Denoising Diffusion Implicit Modelscited by 9,718
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,023
  5. 2013Auto-Encoding Variational Bayescited by 4,024
  6. 2015Variational Inference with Normalizing Flowscited by 2,163
  7. 2014Conditional Generative Adversarial Netscited by 2,157
  8. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,603
  9. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,213
  10. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 688
  11. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 616
  12. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 489
38 more
  1. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  2. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 297
  3. 2016A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehiclescited by 253
  4. 2020It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Predictioncited by 236
  5. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 228
  6. 2016Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoderscited by 219
  7. 2020Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Predictioncited by 218
  8. 2021Stochastic Scene-Aware Motion Predictioncited by 203
  9. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  10. 2020Long-term Human Motion Prediction with Scene Contextcited by 191
  11. 2017Social Attention: Modeling Attention in Human Crowdscited by 185
  12. 2022Stochastic Trajectory Prediction via Motion Indeterminacy Diffusioncited by 185
  13. 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 184
  14. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  15. 2020Human Trajectory Forecasting in Crowds: A Deep Learning Perspectivecited by 129
  16. 2022GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoningcited by 128
  17. 2020We are More than Our Joints: Predicting how 3D Bodies Movecited by 115
  18. 2019SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Predictioncited by 111
  19. 2016Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypothesescited by 96
  20. 2017The Pose Knows: Video Forecasting by Generating Pose Futurescited by 88
  21. 2018MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamicscited by 86
  22. 2019Diverse Trajectory Forecasting with Determinantal Point Processescited by 80
  23. 2019Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANscited by 78
  24. 2017DeLiGAN : Generative Adversarial Networks for Diverse and Limited Datacited by 77
  25. 2021Multi-Person Extreme Motion Predictioncited by 74
  26. 2020Recursive Social Behavior Graph for Trajectory Predictioncited by 66
  27. 2021Generating Smooth Pose Sequences for Diverse Human Motion Predictioncited by 66
  28. 2021Multi-Person 3D Motion Prediction with Multi-Range Transformerscited by 63
  29. 2021The Wanderings of Odysseus in 3D Scenescited by 59
  30. 2018Accurate and Diverse Sampling of Sequences based on a "Best of Many" Sample Objectivecited by 56
  31. 2021TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wildcited by 52
  32. 2020Socially and Contextually Aware Human Motion and Pose Forecastingcited by 51
  33. 2022Adaptive Trajectory Prediction via Transferable GNNcited by 51
  34. 2021Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesiscited by 46
  35. 2021Interpretable Social Anchors for Human Trajectory Forecasting in Crowdscited by 44
  36. 2023Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchorscited by 34
  37. 2021Simple Baseline for Single Human Motion Forecastingcited by 18
  38. 2022Didn't see that coming: a survey on non-verbal social human behavior forecastingcited by 12

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2023: 8; 2024: 11; 2025: 5; 2026: 4.

28 papers.

Sort:

By area:

  1. 2023InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusioncited by 182
  2. 2023CG-HOI: Contact-Guided 3D Human-Object Interaction Generationcited by 138
  3. 2023HumanTOMATO: Text-aligned Whole-body Motion Generationcited by 103
  4. 2024Seamless Human Motion Composition with Blended Positional Encodingscited by 79
  5. 2025InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactionscited by 68
  6. 2024InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interactioncited by 64
  7. 2024Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioningcited by 29
  8. 2023InterControl: Zero-shot Human Interaction Generation by Controlling Every Jointcited by 23
  9. 2024Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaptioncited by 19
  10. 2024Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editingcited by 17
  11. 2023Joint-Relation Transformer for Multi-Person Motion Predictioncited by 16
  12. 2023Formulating Discrete Probability Flow Through Optimal Transportcited by 12
16 more
  1. 2025Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Predictioncited by 12
  2. 2023Social Motion Prediction with Cognitive Hierarchiescited by 8
  3. 2025Multi-Person Interaction Generation from Two-Person Motion Priorscited by 8
  4. 2025Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animationcited by 7
  5. 2024Multi-Condition Latent Diffusion Network for Scene-Aware Neural Human Motion Predictioncited by 6
  6. 2024Gated Temporal Diffusion for Stochastic Long-Term Dense Anticipationcited by 6
  7. 2024Human Motion Prediction under Unexpected Perturbationcited by 5
  8. 2024Two-Person Interaction Augmentation with Skeleton Priorscited by 5
  9. 2026Unleashing Guidance Without Classifiers for Human-Object Interaction Animationcited by 5
  10. 2023The MI-Motion Dataset and Benchmark for 3D Multi-Person Motion Predictioncited by 3
  11. 2024COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Modelscited by 2
  12. 2025MoReact: Generating Reactive Motion from Textual Descriptionscited by 2
  13. 2026HandX: Scaling Bimanual Motion and Interaction Generationcited by 2
  14. 2024Social-MAE: Social Masked Autoencoder for Multi-person Motion Representation Learningcited by 0
  15. 2026Residual Flow Matching with Dynamic Cross-Interaction for 3D Multi-Person Motion Predictioncited by 0
  16. 2026Multi-Person Human Motion Forecasting in Complex Scenescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Massively Multi-Person 3D Human Motion Forecasting with Scene Context
  2. 2022PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting
  3. 2022BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction
  4. 2025Human Motion Prediction, Reconstruction, and Generation
  5. 2025Unconditional Human Motion and Shape Generation via Balanced Score-Based Diffusion
  6. 2024Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction
  7. 2024DivDiff: A Conditional Diffusion Model for Diverse Human Motion Prediction
  8. 2023AMD: Autoregressive Motion Diffusion