mlsanityData to 14 Oct 2026

Uncertainty-aware Probabilistic 3D Human Motion Forecasting via Invertible Networks

arXiv 2507.14694 ↗First posted 19 Jul 2025cs.RO cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

3D human motion forecasting aims to enable autonomous applications. Estimating uncertainty for each prediction (i.e., confidence based on probability density or quantile) is essential for safety-critical contexts like human-robot collaboration to minimize risks. However, existing diverse motion forecasting approaches struggle with uncertainty quantification due to implicit probabilistic representations hindering uncertainty modeling. We propose ProbHMI, which introduces invertible networks to parameterize poses in a disentangled latent space, enabling probabilistic dynamics modeling. A forecasting module then explicitly predicts future latent distributions, allowing effective uncertainty quantification. Evaluated on benchmarks, ProbHMI achieves strong performance for both deterministic and diverse prediction while validating uncertainty calibration, critical for risk-aware decision making.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 34 of its 51 references that are in the map. First posted on arXiv 19 Jul 2025.

Builds on

34 of 51 references.

References · 34

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  2. 2016Density estimation using Real NVPcited by 2,042
  3. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  4. 2014NICE: Non-linear Independent Components Estimationcited by 1,058
  5. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
  6. 2020Learning Lane Graph Representations for Motion Forecastingcited by 382
  7. 2018Invertible Residual Networkscited by 365
  8. 2017On human motion prediction using recurrent neural networkscited by 338
  9. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecastingcited by 337
  10. 2023Robots That Ask For Help: Uncertainty Alignment for Large Language Model Plannerscited by 308
  11. 2019Residual Flows for Invertible Generative Modelingcited by 257
  12. 2017A Multi-Horizon Quantile Recurrent Forecastercited by 211
22 more
  1. 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 185
  2. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  3. 2020History Repeats Itself: Human Motion Prediction via Motion Attentioncited by 165
  4. 2020Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Predictioncited by 132
  5. 2020We are More than Our Joints: Predicting how 3D Bodies Movecited by 115
  6. 2023HumanMAC: Masked Motion Completion for Human Motion Predictioncited by 81
  7. 2017DeLiGAN : Generative Adversarial Networks for Diverse and Limited Datacited by 77
  8. 2017Learning Human Motion Models for Long-term Predictionscited by 67
  9. 2021Generating Smooth Pose Sequences for Diverse Human Motion Predictioncited by 66
  10. 2018Accurate and Diverse Sampling of Sequences based on a "Best of Many" Sample Objectivecited by 56
  11. 2022Spatio-Temporal Gating-Adjacency GCN for Human Motion Predictioncited by 48
  12. 2019Modeling Human Motion with Quaternion-based Neural Networkscited by 45
  13. 2022Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimationcited by 40
  14. 2021Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Predictioncited by 37
  15. 2022Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Spacecited by 32
  16. 2022Motron: Multimodal Probabilistic Human Motion Forecastingcited by 30
  17. 2022Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Predictioncited by 28
  18. 2022Pose Forecasting in Industrial Human-Robot Collaborationcited by 25
  19. 2021Fast User Adaptation for Human Motion Prediction in Physical Human-Robot Interactioncited by 6
  20. 2023SPOTR: Spatio-temporal Pose Transformers for Human Motion Predictioncited by 4
  21. 2024Towards more realistic human motion prediction with attention to motion coordinationcited by 4
  22. 2022Vision-Based Uncertainty-Aware Motion Planning based on Probabilistic Semantic Segmentationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025CaFlow: Enhancing Long-Term Action Quality Assessment with Causal Counterfactual Flowcited by 0
  2. 2026Gaussian-Mixture Latent Flow for Stochastic 3D Human Motion Predictioncited by 0