mlsanityData to 7 Oct 2026

Generating Smooth Pose Sequences for Diverse Human Motion Prediction

arXiv 2108.08422 ↗First posted 19 Aug 2021cs.CVcited by 66

Not on the map. Why?

Abstract (arXiv)

Recent progress in stochastic motion prediction, i.e., predicting multiple possible future human motions given a single past pose sequence, has led to producing truly diverse future motions and even providing control over the motion of some body parts. However, to achieve this, the state-of-the-art method requires learning several mappings for diversity and a dedicated model for controllable motion prediction. In this paper, we introduce a unified deep generative network for both diverse and controllable motion prediction. To this end, we leverage the intuition that realistic human motions consist of smooth sequences of valid poses, and that, given limited data, learning a pose prior is much more tractable than a motion one. We therefore design a generator that predicts the motion of different body parts sequentially, and introduce a normalizing flow based pose prior, together with a joint angle loss, to achieve motion realism.Our experiments on two standard benchmark datasets, Human3.6M and HumanEva-I, demonstrate that our approach outperforms the state-of-the-art baselines in terms of both sample diversity and accuracy. The code is available at https://github.com/wei-mao-2019/gsps

Key facts. Cited by 66 papers in the map (data through 7 Oct 2026). Builds on 37 of its 61 references that are in the map. First posted on arXiv 19 Aug 2021.

Builds on

37 of 61 references.

References · 37

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2015Variational Inference with Normalizing Flowscited by 2,161
  5. 2016Density estimation using Real NVPcited by 2,029
  6. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  7. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  8. 2017Masked Autoregressive Flow for Density Estimationcited by 680
  9. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  10. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  11. 2017On human motion prediction using recurrent neural networkscited by 336
  12. 2015Skip-Thought Vectorscited by 321
25 more
  1. 2016A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehiclescited by 251
  2. 2019Learning Trajectory Dependencies for Human Motion Predictioncited by 245
  3. 2015Structural-RNN: Deep Learning on Spatio-Temporal Graphscited by 234
  4. 2016Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoderscited by 219
  5. 2018Neural Autoregressive Flowscited by 207
  6. 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 184
  7. 2021Character Controllers Using Motion VAEscited by 182
  8. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  9. 2020History Repeats Itself: Human Motion Prediction via Motion Attentioncited by 164
  10. 2018Human Motion Prediction via Spatio-Temporal Inpaintingcited by 114
  11. 2018QuaterNet: A Quaternion-based Recurrent Model for Human Motioncited by 108
  12. 2017Deep representation learning for human motion prediction and classificationcited by 97
  13. 2019Structured Prediction Helps 3D Human Motion Modellingcited by 96
  14. 2020Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flowscited by 94
  15. 2017The Pose Knows: Video Forecasting by Generating Pose Futurescited by 88
  16. 2018A Neural Temporal Model for Human Motion Predictioncited by 87
  17. 2018MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamicscited by 86
  18. 2019Diverse Trajectory Forecasting with Determinantal Point Processescited by 80
  19. 2017DeLiGAN : Generative Adversarial Networks for Diverse and Limited Datacited by 77
  20. 2018Accurate and Diverse Sampling of Sequences based on a "Best of Many" Sample Objectivecited by 56
  21. 2018BiHMP-GAN: Bidirectional 3D Human Motion Prediction GANcited by 55
  22. 2018Human Motion Modeling using DVGANscited by 45
  23. 2019Imitation Learning for Human Pose Predictioncited by 44
  24. 2021Multi-level Motion Attention for Human Motion Predictioncited by 35
  25. 2018Structure from Recurrent Motion: From Rigidity to Recurrencycited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 12; 2023: 17; 2024: 13; 2025: 13; 2026: 9.

66 papers.

Sort:

By area:

  1. 2022TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Textscited by 357
  2. 2023MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusioncited by 210
  3. 2023InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusioncited by 181
  4. 2023CG-HOI: Contact-Guided 3D Human-Object Interaction Generationcited by 137
  5. 2022BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Predictioncited by 82
  6. 2023HumanMAC: Masked Motion Completion for Human Motion Predictioncited by 81
  7. 2024Seamless Human Motion Composition with Blended Positional Encodingscited by 77
  8. 2024InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interactioncited by 63
  9. 2021The Wanderings of Odysseus in 3D Scenescited by 59
  10. 2022MultiAct: Long-Term 3D Human Motion Generation from Multiple Action Labelscited by 45
  11. 2023Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchorscited by 34
  12. 2022A generic diffusion-based approach for 3D human pose prediction in the wildcited by 33
38 more
  1. 2022Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Spacecited by 32
  2. 2022Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learningcited by 30
  3. 2024Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioningcited by 29
  4. 2022Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Predictioncited by 28
  5. 2023Stochastic Multi-Person 3D Motion Forecastingcited by 28
  6. 2023CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusioncited by 21
  7. 2024Stratified Avatar Generation from Sparse Observationscited by 19
  8. 2022HiT-DVAE: Human Motion Generation via Hierarchical Transformer Dynamical VAEcited by 16
  9. 2023TransFusion: A Practical and Effective Transformer-based Diffusion Model for 3D Human Motion Predictioncited by 16
  10. 2025The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimationcited by 16
  11. 2023Can We Use Diffusion Probabilistic Models for 3D Motion Prediction?cited by 14
  12. 2024Learning Semantic Latent Directions for Accurate and Controllable Human Motion Predictioncited by 14
  13. 2025Simulating the Real World: A Unified Survey of Multimodal Generative Modelscited by 14
  14. 2022Didn't see that coming: a survey on non-verbal social human behavior forecastingcited by 12
  15. 2025Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Predictioncited by 12
  16. 2023Toward Reliable Human Pose Forecasting with Uncertaintycited by 11
  17. 2021Dyadic Human Motion Predictioncited by 9
  18. 2023GazeMoDiff: Gaze-guided Diffusion Model for Stochastic Human Motion Predictioncited by 9
  19. 2024MotionWavelet: Human Motion Prediction via Wavelet Manifold Learningcited by 8
  20. 2024MotionMap: Representing Multimodality in Human Pose Forecastingcited by 7
  21. 2024Multi-Condition Latent Diffusion Network for Scene-Aware Neural Human Motion Predictioncited by 6
  22. 2024DivDiff: A Conditional Diffusion Model for Diverse Human Motion Predictioncited by 6
  23. 2022Learning Disentangled Representations for Controllable Human Motion Predictioncited by 5
  24. 2022FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observationscited by 5
  25. 2022Overlooked Poses Actually Make Sense: Distilling Privileged Knowledge for Human Motion Predictioncited by 4
  26. 2023DeFeeNet: Consecutive 3D Human Motion Prediction with Deviation Feedbackcited by 4
  27. 2023Orientation-Aware Leg Movement Learning for Action-Driven Human Motion Predictioncited by 4
  28. 2025CacheFlow: Fast Human Motion Prediction by Cached Normalizing Flowcited by 4
  29. 2023Data-Driven Stochastic Motion Evaluation and Optimization with Image by Spatially-Aligned Temporal Encodingcited by 3
  30. 2023Meta-Auxiliary Learning for Adaptive Human Pose Predictioncited by 2
  31. 2024Frequency-Guided Multi-Level Human Action Anomaly Detection with Normalizing Flowscited by 2
  32. 2024Diverse Code Query Learning for Speech-Driven Facial Animationcited by 2
  33. 2024COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Modelscited by 2
  34. 2025Uncertainty-aware Probabilistic 3D Human Motion Forecasting via Invertible Networkscited by 2
  35. 2025A Spatio-temporal Continuous Network for Stochastic 3D Human Motion Predictioncited by 2
  36. 2024Off-the-shelf ChatGPT is a Good Few-shot Human Motion Predictorcited by 1
  37. 2025Human Motion Prediction, Reconstruction, and Generationcited by 1
  38. 2025Quality assessment of 3D human animation: Subjective and objective evaluationcited by 1

50 most cited of 66 All 66 (JSON)