Existing methods for 3D human mesh recovery always directly estimate SMPL
parameters, which involve both joint rotations and shape parameters. However,
these methods present rotation semantic ambiguity, rotation error accumulation,
and shape estimation overfitting, which also leads to errors in the estimated
pose. Additionally, these methods have not efficiently leveraged the
advancements in another hot topic, human pose estimation. To address these
issues, we propose a novel approach, Decomposition of 3D Rotation and Lift from
2D Joint to 3D mesh (D3L). We disentangle 3D joint rotation into bone direction
and bone twist direction so that the human mesh recovery task is broken down
into estimation of pose, twist, and shape, which can be handled independently.
Then we design a 2D-to-3D lifting network for estimating twist direction and 3D
joint position from 2D joint position sequences and introduce a nonlinear
optimization method for fitting shape parameters and bone directions. Our
approach can leverage human pose estimation methods, and avoid pose errors
introduced by shape estimation overfitting. We conduct experiments on the
Human3.6M dataset and demonstrate improved performance compared to existing
methods by a large margin.

本文提出了一种新方法，即将 3D 关节旋转分解为骨向量和骨扭矢量，然后使用非线性优化方法来拟合形状参数和骨向量，设计了一种 2D-to-3D lifting 网络来估计骨扭矢量和 3D 关节位置，从而提高了 3D 人体网格恢复的性能。