Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Normalizing Flows on the Product Space of SO(3) Manifolds for Probabilistic Human Pose Modeling (2404.05675v1)

Published 8 Apr 2024 in cs.CV

Abstract: Normalizing flows have proven their efficacy for density estimation in Euclidean space, but their application to rotational representations, crucial in various domains such as robotics or human pose modeling, remains underexplored. Probabilistic models of the human pose can benefit from approaches that rigorously consider the rotational nature of human joints. For this purpose, we introduce HuProSO3, a normalizing flow model that operates on a high-dimensional product space of SO(3) manifolds, modeling the joint distribution for human joints with three degrees of freedom. HuProSO3's advantage over state-of-the-art approaches is demonstrated through its superior modeling accuracy in three different applications and its capability to evaluate the exact likelihood. This work not only addresses the technical challenge of learning densities on SO(3) manifolds, but it also has broader implications for domains where the probabilistic regression of correlated 3D rotations is of importance.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (38)
  1. Pose-conditioned joint angle limits for 3D human pose reconstruction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
  2. Keep it smpl: Automatic estimation of 3d human pose and shape from a single image. In Proceedings of the European Conference on Computer Vision (ECCV), 2016.
  3. GFPose: Learning 3d human pose prior with gradient fields. arXiv preprint arXiv:2212.08641, 2022.
  4. Adversarial parametric pose prior. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
  5. Nice: Non-linear independent components estimation. In International Conference on Learning Representations (ICLR), 2015.
  6. Density estimation using real NVP. In International Conference on Learning Representations (ICLR), 2017.
  7. Neural spline flows. In Advances in neural information processing systems (NeurIPS), 2019.
  8. Reparameterizing distributions on lie groups. In Proceedings of the twenty-second international conference on artificial intelligence and statistics, 2019.
  9. Correlation Coefficients for Random Variables on a Unit Sphere or Hypersphere. Biometrika, 73, 1986.
  10. MADE: Masked autoencoder for distribution estimation. In Proceedings of the 32nd international conference on machine learning (ICML), 2015.
  11. Thorsten Glüsenkamp. Unifying supervised learning and VAEs – coverage, systematics and goodness-of-fit in normalizing-flow based neural network models for astro-particle reconstructions. arXiv preprint arXiv:2008.05825, 2023.
  12. Glow: Generative flow with invertible 1x1 convolutions. In Advances in neural information processing systems (NeurIPS), 2018.
  13. Normalizing flows: An introduction and review of current methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021.
  14. Probabilistic Modeling for Human Mesh Recovery. In 2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021.
  15. Determination of 3D human body postures from a single view. Computer Vision, Graphics, and Image Processing, 1985.
  16. A Non-parametric Bayesian Network Prior of Human Pose. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2013.
  17. On the limited memory BFGS method for large scale optimization. Mathematical Programming, 1989.
  18. Delving into Discrete Normalizing Flows on SO(3) Manifold for Probabilistic Rotation Modeling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
  19. AMASS: Archive of Motion Capture As Surface Shapes. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019.
  20. Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifold. In Proceedings of the International Conference on Machine Learning (ICML), 2021.
  21. Risk-sensitive sequential action control with multi-modal human trajectory forecasting for safe crowd-robot interaction. CoRR, abs/2009.05702, 2020.
  22. ProtoRes: Proto-residual network for pose authoring via learned inverse kinematics. In International Conference on Learning Representations (ICLR), 2022.
  23. Masked autoregressive flow for density estimation. In Advances in neural information processing systems (NeurIPS), 2017.
  24. Normalizing Flows for Probabilistic Modeling and Inference. Journal of Machine Learning Research, 2019.
  25. Expressive Body Capture: 3D Hands, Face, and Body From a Single Image. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
  26. HuMoR: 3D Human Motion Model for Robust Pose Estimation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021.
  27. Normalizing flows on tori and spheres. In Proceedings of the International Conference on Machine Learning (ICML), 2020.
  28. The Earth Mover’s Distance as a Metric for Image Retrieval. International Journal of Computer Vision, 2000.
  29. Motron: Multimodal Probabilistic Human Motion Forecasting. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
  30. Hierarchical kinematic probability distributions for 3D human shape and pose estimation from images in the wild. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021a.
  31. Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021b.
  32. HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
  33. normflows: A PyTorch Package for Normalizing Flows. Journal of Open Source Software, 2023.
  34. Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields. In Proceedings of the European Conference on Computer Vision (ECCV), 2022.
  35. SMPL-IK: Learned Morphology-Aware Inverse Kinematics for AI Driven Artistic Workflows. arXiv preprint arXiv:2208.08274, 2022.
  36. GHUM & GHUML: Generative 3D Human Shape and Articulated Pose Models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
  37. Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows. In Proceedings of the European Conference on Computer Vision (ECCV), 2020.
  38. On the Continuity of Rotation Representations in Neural Networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now