Reconstructing Humans with a Biomechanically Accurate Skeleton

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xia, Yan, Zhou, Xiaowei, Vouga, Etienne, Huang, Qixing, Pavlakos, Georgios
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910896771563520
author Xia, Yan
Zhou, Xiaowei
Vouga, Etienne
Huang, Qixing
Pavlakos, Georgios
author_facet Xia, Yan
Zhou, Xiaowei
Vouga, Etienne
Huang, Qixing
Pavlakos, Georgios
contents 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/
format Preprint
id arxiv_https___arxiv_org_abs_2503_21751
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reconstructing Humans with a Biomechanically Accurate Skeleton
Xia, Yan
Zhou, Xiaowei
Vouga, Etienne
Huang, Qixing
Pavlakos, Georgios
Computer Vision and Pattern Recognition
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/
title Reconstructing Humans with a Biomechanically Accurate Skeleton
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.21751