TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation

• URL: http://arxiv.org/abs/2404.16752v1
• Date: Thu, 25 Apr 2024 17:09:14 GMT
• Title: TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation
• Authors: Sai Kumar Dwivedi, Yu Sun, Priyanka Patel, Yao Feng, Michael J. Black,
• Abstract summary: Current methods leverage 3D pseudo-ground-truth (p-GT) and 2D keypoints, leading to robust performance. With such methods, we observe a paradoxical decline in 3D pose accuracy with increasing 2D accuracy. We quantify the error induced by current camera models and show that fitting 2D keypoints and p-GT accurately causes incorrect 3D poses.
• Score: 48.08156777874614
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We address the problem of regressing 3D human pose and shape from a single image, with a focus on 3D accuracy. The current best methods leverage large datasets of 3D pseudo-ground-truth (p-GT) and 2D keypoints, leading to robust performance. With such methods, we observe a paradoxical decline in 3D pose accuracy with increasing 2D accuracy. This is caused by biases in the p-GT and the use of an approximate camera projection model. We quantify the error induced by current camera models and show that fitting 2D keypoints and p-GT accurately causes incorrect 3D poses. Our analysis defines the invalid distances within which minimizing 2D and p-GT losses is detrimental. We use this to formulate a new loss Threshold-Adaptive Loss Scaling (TALS) that penalizes gross 2D and p-GT losses but not smaller ones. With such a loss, there are many 3D poses that could equally explain the 2D evidence. To reduce this ambiguity we need a prior over valid human poses but such priors can introduce unwanted bias. To address this, we exploit a tokenized representation of human pose and reformulate the problem as token prediction. This restricts the estimated poses to the space of valid poses, effectively providing a uniform prior. Extensive experiments on the EMDB and 3DPW datasets show that our reformulated keypoint loss and tokenization allows us to train on in-the-wild data while improving 3D accuracy over the state-of-the-art. Our models and code are available for research at https://tokenhmr.is.tue.mpg.de.

Related papers

• LInKs "Lifting Independent Keypoints" -- Partial Pose Lifting for Occlusion Handling with Improved Accuracy in 2D-3D Human Pose Estimation [4.648549457266638]
  We present LInKs, a novel unsupervised learning method to recover 3D human poses from 2D kinematic skeletons. Our approach follows a unique two-step process, which involves first lifting the occluded 2D pose to the 3D domain. This lift-then-fill approach leads to significantly more accurate results compared to models that complete the pose in 2D space alone.
  arXiv  Detail & Related papers  (2023-09-13T18:28:04Z)
• Optimising 2D Pose Representation: Improve Accuracy, Stability and Generalisability Within Unsupervised 2D-3D Human Pose Estimation [7.294965109944706]
  We show that the most optimal representation of a 2D pose is that of two independent segments, the torso and legs, with no shared features between each lifting network. Our results show that the most optimal representation of a 2D pose is that of two independent segments, the torso and legs, with no shared features between each lifting network.
  arXiv  Detail & Related papers  (2022-09-01T17:32:52Z)
• PONet: Robust 3D Human Pose Estimation via Learning Orientations Only [116.1502793612437]
  We propose a novel Pose Orientation Net (PONet) that is able to robustly estimate 3D pose by learning orientations only. PONet estimates the 3D orientation of these limbs by taking advantage of the local image evidence to recover the 3D pose. We evaluate our method on multiple datasets, including Human3.6M, MPII, MPI-INF-3DHP, and 3DPW.
  arXiv  Detail & Related papers  (2021-12-21T12:48:48Z)
• Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows [24.0966076588569]
  We propose a normalizing flow based method that exploits the deterministic 3D-to-2D mapping to solve the ambiguous inverse 2D-to-3D problem. We evaluate our approach on the two benchmark datasets Human3.6M and MPI-INF-3DHP, outperforming all comparable methods in most metrics.
  arXiv  Detail & Related papers  (2021-07-29T07:33:14Z)
• Uncertainty-Aware Camera Pose Estimation from Points and Lines [101.03675842534415]
  Perspective-n-Point-and-Line (Pn$PL) aims at fast, accurate and robust camera localizations with respect to a 3D model from 2D-3D feature coordinates.
  arXiv  Detail & Related papers  (2021-07-08T15:19:36Z)
• 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)
• Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose [70.23652933572647]
  We propose a novel graph convolutional neural network (GraphCNN)-based system that estimates the 3D coordinates of human mesh vertices directly from the 2D human pose. We show that our Pose2Mesh outperforms the previous 3D human pose and mesh estimation methods on various benchmark datasets.
  arXiv  Detail & Related papers  (2020-08-20T16:01:56Z)
• Cascaded deep monocular 3D human pose estimation with evolutionary training data [76.3478675752847]
  Deep representation learning has achieved remarkable accuracy for monocular 3D human pose estimation. This paper proposes a novel data augmentation method that is scalable for massive amount of training data. Our method synthesizes unseen 3D human skeletons based on a hierarchical human representation and synthesizings inspired by prior knowledge.
  arXiv  Detail & Related papers  (2020-06-14T03:09:52Z)

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.