mlsanityData to 14 Oct 2026

ReMP: Reusable Motion Prior for Multi-domain 3D Human Pose Estimation and Motion Inbetweening

arXiv 2411.09435 ↗First posted 13 Nov 2024cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

We present Reusable Motion prior (ReMP), an effective motion prior that can accurately track the temporal evolution of motion in various downstream tasks. Inspired by the success of foundation models, we argue that a robust spatio-temporal motion prior can encapsulate underlying 3D dynamics applicable to various sensor modalities. We learn the rich motion prior from a sequence of complete parametric models of posed human body shape. Our prior can easily estimate poses in missing frames or noisy measurements despite significant occlusion by employing a temporal attention mechanism. More interestingly, our prior can guide the system with incomplete and challenging input measurements to quickly extract critical information to estimate the sequence of poses, significantly improving the training efficiency for mesh sequence recovery. ReMP consistently outperforms the baseline method on diverse and practical 3D motion data, including depth point clouds, LiDAR scans, and IMU sensor data. Project page is available in https://hojunjang17.github.io/ReMP.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 37 of its 45 references that are in the map. First posted on arXiv 13 Nov 2024.

Builds on

37 of 45 references.

References · 37

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020Language Models are Few-Shot Learnerscited by 32,419
  5. 2022Training language models to follow instructions with human feedbackcited by 15,971
  6. 2023Segment Anythingcited by 8,234
  7. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  8. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  9. 2017Neural Discrete Representation Learningcited by 4,712
  10. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  11. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  12. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
25 more
  1. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  2. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  3. 2018Open3D: A Modern Library for 3D Data Processingcited by 721
  4. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 501
  5. 2023MoMask: Generative Masked Modeling of 3D Human Motionscited by 400
  6. 2017Learning from Synthetic Humanscited by 359
  7. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 324
  8. 2021Character Controllers Using Motion VAEscited by 184
  9. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
  10. 20183D-CODED : 3D Correspondences by Deep Deformationcited by 160
  11. 2022Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensorscited by 146
  12. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  13. 2017Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUscited by 109
  14. 2019The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimationcited by 79
  15. 2022PoseGPT: Quantization-based 3D Human Motion Generation and Forecastingcited by 78
  16. 2022Transformer Inertial Poser: Real-time Human Motion Reconstruction from Sparse IMUs with Simultaneous Terrain Generationcited by 76
  17. 2020Rethinking the Heatmap Regression for Bottom-up Human Pose Estimationcited by 69
  18. 20226D Rotation Representation For Unconstrained Head Pose Estimationcited by 64
  19. 2018Deep Inertial Poser: Learning to Reconstruct Human Pose from Sparse Inertial Measurements in Real Timecited by 47
  20. 2023SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environmentscited by 47
  21. 2022LiDARCap: Long-range Marker-less 3D Human Motion Capture with LiDAR Point Cloudscited by 33
  22. 2021VoteHMR: Occlusion-Aware Voting Network for Robust 3D Human Mesh Recovery from Partial Point Cloudscited by 18
  23. 2023Human-M3: A Multi-view Multi-modal Dataset for 3D Human Pose Estimation in Outdoor Scenescited by 11
  24. 2021Self-supervised 3D Human Mesh Recovery from Noisy Point Cloudscited by 8
  25. 2022Neural Marionette: Unsupervised Learning of Motion Skeleton and Latent Dynamics from Volumetric Videocited by 2

Built on by

Cited by year (2026 to 14 Oct)

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

2 papers.

  1. 20253D Human Pose and Shape Estimation from LiDAR Point Clouds: A Reviewcited by 0
  2. 2026EgoPoseVR: Spatiotemporal Multi-Modal Reasoning for Egocentric Full-Body Pose in Virtual Realitycited by 0