Reconstructing Humans with a Biomechanically Accurate Skeleton

• URL: http://arxiv.org/abs/2503.21751v1
• Date: Thu, 27 Mar 2025 17:56:24 GMT
• Title: Reconstructing Humans with a Biomechanically Accurate Skeleton
• Authors: Yan Xia, Xiaowei Zhou, Etienne Vouga, Qixing Huang, Georgios Pavlakos,
• Abstract summary: We introduce a method for reconstructing 3D humans from a single image using a biomechanically accurate skeleton model.<n>Compared to state-of-the-art methods for 3D human mesh recovery, our model achieves competitive performance on standard benchmarks.
• Score: 55.06027148976482
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In this paper, we introduce a method for reconstructing 3D humans from a single image using a biomechanically accurate skeleton model. To achieve this, we train a transformer that takes an image as input and estimates the parameters of the model. Due to the lack of training data for this task, we build a pipeline to produce pseudo ground truth model parameters for single images and implement a training procedure that iteratively refines these pseudo labels. Compared to state-of-the-art methods for 3D human mesh recovery, our model achieves competitive performance on standard benchmarks, while it significantly outperforms them in settings with extreme 3D poses and viewpoints. Additionally, we show that previous reconstruction methods frequently violate joint angle limits, leading to unnatural rotations. In contrast, our approach leverages the biomechanically plausible degrees of freedom making more realistic joint rotation estimates. We validate our approach across multiple human pose estimation benchmarks. We make the code, models and data available at: https://isshikihugh.github.io/HSMR/

Related papers

• ARTS: Semi-Analytical Regressor using Disentangled Skeletal Representations for Human Mesh Recovery from Videos [18.685856290041283]
  ARTS surpasses existing state-of-the-art video-based methods in both per-frame accuracy and temporal consistency on popular benchmarks. A skeleton estimation and disentanglement module is proposed to estimate the 3D skeletons from a video. The regressor consists of three modules: Temporal Inverse Kinematics (TIK), Bone-guided Shape Fitting (BSF), and Motion-Centric Refinement (MCR)
  arXiv  Detail & Related papers  (2024-10-21T02:06:43Z)
• Score-Guided Diffusion for 3D Human Recovery [10.562998991986102]
  We present Score-Guided Human Mesh Recovery (ScoreHMR), an approach for solving inverse problems for 3D human pose and shape reconstruction. ScoreHMR mimics model fitting approaches, but alignment with the image observation is achieved through score guidance in the latent space of a diffusion model. We evaluate our approach on three settings/applications: (i) single-frame model fitting; (ii) reconstruction from multiple uncalibrated views; (iii) reconstructing humans in video sequences.
  arXiv  Detail & Related papers  (2024-03-14T17:56:14Z)
• Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image [85.91935485902708]
  We show that the key to a zero-shot single-view metric depth model lies in the combination of large-scale data training and resolving the metric ambiguity from various camera models. We propose a canonical camera space transformation module, which explicitly addresses the ambiguity problems and can be effortlessly plugged into existing monocular models. Our method enables the accurate recovery of metric 3D structures on randomly collected internet images.
  arXiv  Detail & Related papers  (2023-07-20T16:14:23Z)
• Adversarial Parametric Pose Prior [106.12437086990853]
  We learn a prior that restricts the SMPL parameters to values that produce realistic poses via adversarial training. We show that our learned prior covers the diversity of the real-data distribution, facilitates optimization for 3D reconstruction from 2D keypoints, and yields better pose estimates when used for regression from images.
  arXiv  Detail & Related papers  (2021-12-08T10:05:32Z)
• Creating and Reenacting Controllable 3D Humans with Differentiable Rendering [3.079885946230076]
  This paper proposes a new end-to-end neural rendering architecture to transfer appearance and reenact human actors. Our method leverages a carefully designed graph convolutional network (GCN) to model the human body manifold structure. By taking advantages of both different synthesisiable rendering and the 3D parametric model, our method is fully controllable.
  arXiv  Detail & Related papers  (2021-10-22T12:40:09Z)
• Probabilistic Modeling for Human Mesh Recovery [73.11532990173441]
  This paper focuses on the problem of 3D human reconstruction from 2D evidence. We recast the problem as learning a mapping from the input to a distribution of plausible 3D poses.
  arXiv  Detail & Related papers  (2021-08-26T17:55:11Z)
• HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation [39.67289969828706]
  We propose a novel hybrid inverse kinematics solution (HybrIK) to bridge the gap between body mesh estimation and 3D keypoint estimation. HybrIK directly transforms accurate 3D joints to relative body-part rotations for 3D body mesh reconstruction. We show that HybrIK preserves both the accuracy of 3D pose and the realistic body structure of the parametric human model.
  arXiv  Detail & Related papers  (2020-11-30T10:32:30Z)
• 3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data [77.57798334776353]
  We consider the problem of obtaining dense 3D reconstructions of humans from single and partially occluded views. We suggest that ambiguities can be modelled more effectively by parametrizing the possible body shapes and poses. We show that our method outperforms alternative approaches in ambiguous pose recovery on standard benchmarks for 3D humans.
  arXiv  Detail & Related papers  (2020-11-02T13:55:31Z)
• Neural Descent for Visual 3D Human Pose and Shape [67.01050349629053]
  We present deep neural network methodology to reconstruct the 3d pose and shape of people, given an input RGB image. We rely on a recently introduced, expressivefull body statistical 3d human model, GHUM, trained end-to-end. Central to our methodology, is a learning to learn and optimize approach, referred to as HUmanNeural Descent (HUND), which avoids both second-order differentiation.
  arXiv  Detail & Related papers  (2020-08-16T13:38:41Z)

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.