Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation


一个和Learning to estimate 3D human pose and shape from a single color image. In: CVPR (2018) 类似的工作。

论文不是从RGB图片获得SMPL模型的参数,而是考虑中间监督,使用了human part segmentation,来回归参数。
(3D-HPE)Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation


对模型参数(3D-HPE)Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation使用了L1损失。

(3D-HPE)Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation

3D 关节损失:

(3D-HPE)Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation

2D关节点损失:

(3D-HPE)Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation

相关文章: