We present an approach that can reconstruct hands in 3D from monocular input. Our approach for Hand Mesh Recovery, HaMeR, follows a fully transformer-based architecture and can analyze hands with significantly increased accuracy and robustness compared to previous work. The key to HaMeR's success lies in scaling up both the data used for training and the capacity of the deep network for hand reconstruction. For training data, we combine multiple datasets that contain 2D or 3D hand annotations. For the deep model, we use a large scale Vision Transformer architecture. Our final model consistently outperforms the previous baselines on popular 3D hand pose benchmarks. To further evaluate the effect of our design in non-controlled settings, we annotate existing in-the-wild datasets with 2D hand keypoint annotations. On this newly collected dataset of annotations, HInt, we demonstrate significant improvements over existing baselines. We make our code, data and models available on the project website: https://geopavlakos.github.io/hamer/.

翻译：我们提出了一种从单目输入进行三维手部重建的方法。我们的手部网格重建方法HaMeR采用完全基于Transformer的架构，与先前工作相比，能够以显著提升的精度和鲁棒性分析手部。HaMeR成功的关键在于同时扩大训练数据规模和手部重建深度网络的容量。在训练数据方面，我们整合了多个包含二维或三维手部标注的数据集；在深度模型方面，我们采用大规模视觉Transformer架构。最终模型在主流三维手部姿态基准测试中持续优于先前基线方法。为进一步评估我们在非受控环境下的设计效果，我们对现有野外数据集进行了二维手部关键点标注。在这套新收集的标注数据集HInt上，我们展示出相较于现有基线方法的显著改进。我们已在项目网站https://geopavlakos.github.io/hamer/上公开代码、数据和模型。