DensePose provides a pixel-accurate association of images with 3D mesh coordinates, but does not provide a 3D mesh, while Human Mesh Reconstruction (HMR) systems have high 2D reprojection error, as measured by DensePose localization metrics. In this work we introduce MeshPose to jointly tackle DensePose and HMR. For this we first introduce new losses that allow us to use weak DensePose supervision to accurately localize in 2D a subset of the mesh vertices ('VertexPose'). We then lift these vertices to 3D, yielding a low-poly body mesh ('MeshPose'). Our system is trained in an end-to-end manner and is the first HMR method to attain competitive DensePose accuracy, while also being lightweight and amenable to efficient inference, making it suitable for real-time AR applications.

翻译：DensePose 提供了图像与三维网格坐标的像素级精确关联，但未生成三维网格；而人体网格重建（HMR）系统在 DensePose 定位指标衡量下存在较高的二维重投影误差。本研究提出 MeshPose 以协同解决 DensePose 与 HMR 问题。为此，我们首先引入新型损失函数，使得能够利用弱监督的 DensePose 数据精确地定位网格顶点子集在二维空间中的位置（"VertexPose"）。随后将这些顶点提升至三维空间，生成低面数人体网格（"MeshPose"）。本系统采用端到端训练方式，是首个达到与 DensePose 相媲美精度水平的 HMR 方法，同时兼具轻量化与高效推理特性，适用于实时增强现实应用场景。