基于生物力学精确骨骼的人体重建

Reconstructing Humans with a Biomechanically Accurate Skeleton

March 27, 2025

作者: Yan Xia, Xiaowei Zhou, Etienne Vouga, Qixing Huang, Georgios Pavlakos

cs.AI

摘要

本文提出了一种基于生物力学精确骨骼模型从单张图像重建三维人体的方法。为实现这一目标，我们训练了一个以图像为输入并估计模型参数的Transformer网络。鉴于该任务缺乏训练数据，我们构建了一个管道来为单张图像生成伪真实模型参数，并实施了一种迭代优化这些伪标签的训练流程。与当前最先进的三维人体网格恢复方法相比，我们的模型在标准基准测试中表现出竞争力，同时在极端三维姿态和视角设置下显著优于现有方法。此外，我们指出以往的重建方法常违反关节角度限制，导致不自然的旋转。相比之下，我们的方法利用生物力学上合理的自由度，从而做出更为真实的关节旋转估计。我们在多个人体姿态估计基准上验证了该方法的有效性。代码、模型及数据已公开于：https://isshikihugh.github.io/HSMR/。

English

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/