Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers

• URL: http://arxiv.org/abs/2210.06110v2
• Date: Fri, 14 Oct 2022 09:23:56 GMT
• Title: Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers
• Authors: Moritz Einfalt, Katja Ludwig, Rainer Lienhart
• Abstract summary: We present a Transformer-based pose uplifting scheme that can operate on temporally sparse 2D pose sequences. We show how masked token modeling can be utilized for temporal upsampling within Transformer blocks. We evaluate our method on two popular benchmark datasets: Human3.6M and MPI-INF-3DHP.
• Score: 28.586258731448687
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The state-of-the-art for monocular 3D human pose estimation in videos is dominated by the paradigm of 2D-to-3D pose uplifting. While the uplifting methods themselves are rather efficient, the true computational complexity depends on the per-frame 2D pose estimation. In this paper, we present a Transformer-based pose uplifting scheme that can operate on temporally sparse 2D pose sequences but still produce temporally dense 3D pose estimates. We show how masked token modeling can be utilized for temporal upsampling within Transformer blocks. This allows to decouple the sampling rate of input 2D poses and the target frame rate of the video and drastically decreases the total computational complexity. Additionally, we explore the option of pre-training on large motion capture archives, which has been largely neglected so far. We evaluate our method on two popular benchmark datasets: Human3.6M and MPI-INF-3DHP. With an MPJPE of 45.0 mm and 46.9 mm, respectively, our proposed method can compete with the state-of-the-art while reducing inference time by a factor of 12. This enables real-time throughput with variable consumer hardware in stationary and mobile applications. We release our code and models at https://github.com/goldbricklemon/uplift-upsample-3dhpe

Related papers

• MPL: Lifting 3D Human Pose from Multi-view 2D Poses [75.26416079541723]
  We propose combining 2D pose estimation, for which large and rich training datasets exist, and 2D-to-3D pose lifting, using a transformer-based network. Our experiments demonstrate decreases up to 45% in MPJPE errors compared to the 3D pose obtained by triangulating the 2D poses.
  arXiv  Detail & Related papers  (2024-08-20T12:55:14Z)
• UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues [55.69339788566899]
  UPose3D is a novel approach for multi-view 3D human pose estimation. It improves robustness and flexibility without requiring direct 3D annotations.
  arXiv  Detail & Related papers  (2024-04-23T00:18:00Z)
• A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation [18.72362803593654]
  The dominant paradigm in 3D human pose estimation that lifts a 2D pose sequence to 3D heavily relies on long-term temporal clues. This can be attributed to their inherent inability to perceive spatial context as plain 2D joint coordinates carry no visual cues. We propose a straightforward yet powerful solution: leveraging the readily available intermediate visual representations produced by off-the-shelf (pre-trained) 2D pose detectors.
  arXiv  Detail & Related papers  (2023-11-06T18:04:13Z)
• Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video [23.93644678238666]
  We propose a Pose and Mesh Co-Evolution network (PMCE) to recover 3D human motion from a video. The proposed PMCE outperforms previous state-of-the-art methods in terms of both per-frame accuracy and temporal consistency.
  arXiv  Detail & Related papers  (2023-08-20T16:03:21Z)
• P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation [78.83305967085413]
  This paper introduces a novel Pre-trained Spatial Temporal Many-to-One (P-STMO) model for 2D-to-3D human pose estimation task. Our method outperforms state-of-the-art methods with fewer parameters and less computational overhead.
  arXiv  Detail & Related papers  (2022-03-15T04:00:59Z)
• Shape-aware Multi-Person Pose Estimation from Multi-View Images [47.13919147134315]
  Our proposed coarse-to-fine pipeline first aggregates noisy 2D observations from multiple camera views into 3D space. The final pose estimates are attained from a novel optimization scheme which links high-confidence multi-view 2D observations and 3D joint candidates.
  arXiv  Detail & Related papers  (2021-10-05T20:04:21Z)
• 3D Human Pose Estimation with Spatial and Temporal Transformers [59.433208652418976]
  We present PoseFormer, a purely transformer-based approach for 3D human pose estimation in videos. Inspired by recent developments in vision transformers, we design a spatial-temporal transformer structure. We quantitatively and qualitatively evaluate our method on two popular and standard benchmark datasets.
  arXiv  Detail & Related papers  (2021-03-18T18:14:37Z)
• Synthetic Training for Monocular Human Mesh Recovery [100.38109761268639]
  This paper aims to estimate 3D mesh of multiple body parts with large-scale differences from a single RGB image. The main challenge is lacking training data that have complete 3D annotations of all body parts in 2D images. We propose a depth-to-scale (D2S) projection to incorporate the depth difference into the projection function to derive per-joint scale variants.
  arXiv  Detail & Related papers  (2020-10-27T03:31:35Z)
• Light3DPose: Real-time Multi-Person 3D PoseEstimation from Multiple Views [5.510992382274774]
  We present an approach to perform 3D pose estimation of multiple people from a few calibrated camera views. Our architecture aggregates feature-maps from a 2D pose estimator backbone into a comprehensive representation of the 3D scene. The proposed method is inherently efficient: as a pure bottom-up approach, it is computationally independent of the number of people in the scene.
  arXiv  Detail & Related papers  (2020-04-06T14:12:19Z)
• Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation [57.11299763566534]
  We present a solution to recover 3D pose from multi-view images captured with spatially calibrated cameras. We exploit 3D geometry to fuse input images into a unified latent representation of pose, which is disentangled from camera view-points. Our architecture then conditions the learned representation on camera projection operators to produce accurate per-view 2d detections.
  arXiv  Detail & Related papers  (2020-04-05T12:52:29Z)

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.