WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion

• URL: http://arxiv.org/abs/2312.07531v2
• Date: Thu, 18 Apr 2024 19:43:25 GMT
• Title: WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion
• Authors: Soyong Shin, Juyong Kim, Eni Halilaj, Michael J. Black,
• Abstract summary: WHAM (World-grounded Humans with Accurate Motion) reconstructs 3D human motion in a global coordinate system from video. Uses camera angular velocity estimated from a SLAM method together with human motion to estimate the body's global trajectory. outperforms all existing 3D human motion recovery methods across multiple in-the-wild benchmarks.
• Score: 43.95997922499137
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The estimation of 3D human motion from video has progressed rapidly but current methods still have several key limitations. First, most methods estimate the human in camera coordinates. Second, prior work on estimating humans in global coordinates often assumes a flat ground plane and produces foot sliding. Third, the most accurate methods rely on computationally expensive optimization pipelines, limiting their use to offline applications. Finally, existing video-based methods are surprisingly less accurate than single-frame methods. We address these limitations with WHAM (World-grounded Humans with Accurate Motion), which accurately and efficiently reconstructs 3D human motion in a global coordinate system from video. WHAM learns to lift 2D keypoint sequences to 3D using motion capture data and fuses this with video features, integrating motion context and visual information. WHAM exploits camera angular velocity estimated from a SLAM method together with human motion to estimate the body's global trajectory. We combine this with a contact-aware trajectory refinement method that lets WHAM capture human motion in diverse conditions, such as climbing stairs. WHAM outperforms all existing 3D human motion recovery methods across multiple in-the-wild benchmarks. Code will be available for research purposes at http://wham.is.tue.mpg.de/

Related papers

• World-Grounded Human Motion Recovery via Gravity-View Coordinates [60.618543026949226]
  We propose estimating human poses in a novel Gravity-View coordinate system. The proposed GV system is naturally gravity-aligned and uniquely defined for each video frame. Our method recovers more realistic motion in both the camera space and world-grounded settings, outperforming state-of-the-art methods in both accuracy and speed.
  arXiv  Detail & Related papers  (2024-09-10T17:25:47Z)
• TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments [106.80978555346958]
  Current methods can't reliably estimate moving humans in global coordinates. TRACE is the first one-stage method to jointly recover and track 3D humans in global coordinates from dynamic cameras. It achieves state-of-the-art performance on tracking and HPS benchmarks.
  arXiv  Detail & Related papers  (2023-06-05T13:00:44Z)
• Markerless 3D human pose tracking through multiple cameras and AI: Enabling high accuracy, robustness, and real-time performance [0.0]
  Tracking 3D human motion in real-time is crucial for numerous applications across many fields. Recent advances in Artificial Intelligence have allowed for markerless solutions. We propose a markerless framework that combines multi-camera views and 2D AI-based pose estimation methods to track 3D human motion.
  arXiv  Detail & Related papers  (2023-03-31T15:06:50Z)
• Decoupling Human and Camera Motion from Videos in the Wild [67.39432972193929]
  We propose a method to reconstruct global human trajectories from videos in the wild. Our method decouples the camera and human motion, which allows us to place people in the same world coordinate frame.
  arXiv  Detail & Related papers  (2023-02-24T18:59:15Z)
• Scene-Aware 3D Multi-Human Motion Capture from a Single Camera [83.06768487435818]
  We consider the problem of estimating the 3D position of multiple humans in a scene as well as their body shape and articulation from a single RGB video recorded with a static camera. We leverage recent advances in computer vision using large-scale pre-trained models for a variety of modalities, including 2D body joints, joint angles, normalized disparity maps, and human segmentation masks. In particular, we estimate the scene depth and unique person scale from normalized disparity predictions using the 2D body joints and joint angles.
  arXiv  Detail & Related papers  (2023-01-12T18:01:28Z)
• MotionBERT: A Unified Perspective on Learning Human Motion Representations [46.67364057245364]
  We present a unified perspective on tackling various human-centric video tasks by learning human motion representations from large-scale and heterogeneous data resources. We propose a pretraining stage in which a motion encoder is trained to recover the underlying 3D motion from noisy partial 2D observations. We implement motion encoder with a Dual-stream Spatio-temporal Transformer (DSTformer) neural network.
  arXiv  Detail & Related papers  (2022-10-12T19:46:25Z)
• Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors [71.29186299435423]
  We introduce (HPS) Human POSEitioning System, a method to recover the full 3D pose of a human registered with a 3D scan of the surrounding environment. We show that our optimization-based integration exploits the benefits of the two, resulting in pose accuracy free of drift. HPS could be used for VR/AR applications where humans interact with the scene without requiring direct line of sight with an external camera.
  arXiv  Detail & Related papers  (2021-03-31T17:58:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.