Estimating human pose and shape from monocular images is a long-standing
problem in computer vision. Since the release of statistical body models, 3D
human mesh recovery has been drawing broader attention. With the same goal of
obtaining well-aligned and physically plausible mesh resul
本文提出了一种端到端可训练模型，以单个 RGB 图像感知 3D 场景，估计相机姿态和室内布局，并重建人体和物体网格。通过对所有估计方面施加全面而复杂的损失，我们证明了我们的模型优于现有的人体网格方法和室内场景重建方法。据我们所知，这是第一个在网格级别输出对象和人体预测，并对场景和人体姿态进行联合优化的模型。