mlsanityData to 14 Oct 2026

Motion-DVAE: Unsupervised learning for fast human motion denoising

arXiv 2306.05846 ↗First posted 9 Jun 2023cs.CV cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Pose and motion priors are crucial for recovering realistic and accurate human motion from noisy observations. Substantial progress has been made on pose and shape estimation from images, and recent works showed impressive results using priors to refine frame-wise predictions. However, a lot of motion priors only model transitions between consecutive poses and are used in time-consuming optimization procedures, which is problematic for many applications requiring real-time motion capture. We introduce Motion-DVAE, a motion prior to capture the short-term dependencies of human motion. As part of the dynamical variational autoencoder (DVAE) models family, Motion-DVAE combines the generative capability of VAE models and the temporal modeling of recurrent architectures. Together with Motion-DVAE, we introduce an unsupervised learned denoising method unifying regression- and optimization-based approaches in a single framework for real-time 3D human pose estimation. Experiments show that the proposed approach reaches competitive performance with state-of-the-art methods while being much faster.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 55 of its 91 references that are in the map. First posted on arXiv 9 Jun 2023.

Builds on

55 of 91 references.

References · 55

  1. 2017Neural Discrete Representation Learningcited by 4,712
  2. 2013Auto-Encoding Variational Bayescited by 4,053
  3. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  4. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  5. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  6. 2017End-to-end Recovery of Human Shape and Posecited by 885
  7. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  8. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  9. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  10. 2015Generating Sentences from a Continuous Spacecited by 612
  11. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 501
  12. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 441
38 more
  1. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  2. 2017Learning from Synthetic Humanscited by 359
  3. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 337
  4. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 324
  5. 2018Learning 3D Human Dynamics from Videocited by 316
  6. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  7. 2020STAR: Sparse Trained Articulated Human Body Regressorcited by 194
  8. 2019Diagnosing and Enhancing VAE Modelscited by 193
  9. 2021Character Controllers Using Motion VAEscited by 184
  10. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  11. 2019Learning to Reconstruct People in Clothing from a Single RGB Cameracited by 168
  12. 2020Monocular Expressive Body Regression through Body-Driven Attentioncited by 155
  13. 2021Probabilistic Modeling for Human Mesh Recoverycited by 153
  14. 2021GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Camerascited by 153
  15. 2023Decoupling Human and Camera Motion from Videos in the Wildcited by 142
  16. 2020Dynamical Variational Autoencoders: A Comprehensive Reviewcited by 128
  17. 2019Generating 3D People in Scenes without Peoplecited by 127
  18. 2019Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapsecited by 121
  19. 2021SimPoE: Simulated Character Control for 3D Human Pose Estimationcited by 114
  20. 2020Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimationcited by 113
  21. 2019Exploiting temporal context for 3D human pose estimation in the wildcited by 110
  22. 20203D Human Motion Estimation via Motion Compression and Refinementcited by 98
  23. 2019RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimationcited by 85
  24. 2022Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fieldscited by 85
  25. 2020Human Body Model Fitting by Learned Gradient Descentcited by 81
  26. 2019Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsensecited by 71
  27. 2021All One Needs to Know about Metaverse: A Complete Survey on Technological Singularity, Virtual Ecosystem, and Research Agendacited by 67
  28. 2021Playing for 3D Human Recoverycited by 64
  29. 2015Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Videocited by 54
  30. 2019The Usual Suspects? Reassessing Blame for VAE Posterior Collapsecited by 52
  31. 2021Conditional Directed Graph Convolution for 3D Human Pose Estimationcited by 52
  32. 2021Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wildcited by 48
  33. 2022Learned Vertex Descent: A New Direction for 3D Human Model Fittingcited by 37
  34. 2021Task-Generic Hierarchical Human Motion Prior using VAEscited by 33
  35. 2022Neural MoCon: Neural Motion Control for Physically Plausible Human Motion Capturecited by 31
  36. 2022SUPR: A Sparse Unified Part-Based Human Representationcited by 21
  37. 2021Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulationcited by 19
  38. 2021Metaverse for Social Good: A University Campus Prototypecited by 17

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generationcited by 10