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:this https URL
View on arXiv@article{xia2025_2503.21751,
title={ Reconstructing Humans with a Biomechanically Accurate Skeleton },
author={ Yan Xia and Xiaowei Zhou and Etienne Vouga and Qixing Huang and Georgios Pavlakos },
journal={arXiv preprint arXiv:2503.21751},
year={ 2025 }
}