We address the problem of regressing 3D human pose and shape from a single
image, with a focus on 3D accuracy. The current best methods leverage large
datasets of 3D pseudo-ground-truth (p-GT) and 2D keypoints, leading to robust
performance. With such methods, we observe a paradoxical decline in 3D pose
accuracy with increasing 2D accuracy. This is caused by biases in the p-GT and
the use of an approximate camera projection model. We quantify the error
induced by current camera models and show that fitting 2D keypoints and p-GT
accurately causes incorrect 3D poses. Our analysis defines the invalid
distances within which minimizing 2D and p-GT losses is detrimental. We use
this to formulate a new loss Threshold-Adaptive Loss Scaling (TALS) that
penalizes gross 2D and p-GT losses but not smaller ones. With such a loss,
there are many 3D poses that could equally explain the 2D evidence. To reduce
this ambiguity we need a prior over valid human poses but such priors can
introduce unwanted bias. To address this, we exploit a tokenized representation
of human pose and reformulate the problem as token prediction. This restricts
the estimated poses to the space of valid poses, effectively providing a
uniform prior. Extensive experiments on the EMDB and 3DPW datasets show that
our reformulated keypoint loss and tokenization allows us to train on
in-the-wild data while improving 3D accuracy over the state-of-the-art. Our
models and code are available for research at this https URL

从单个图像中推断 3D 人体姿态和形状的问题，重点关注 3D 准确性。目前最好的方法利用大量的 3D 伪地面真值 (p-GT) 和 2D 关键点数据集，以实现稳健性能。我们观察到，随着 2D 准确性的提高，3D 姿势准确性出现矛盾下降。错误的 3D 姿势是由于当前相机模型的偏差和 2D 关键点与 p-GT 的准确匹配引起的。我们定量化了当前相机模型引入的误差，并证明精确拟合 2D 关键点和 p-GT 会导致错误的 3D 姿势。我们提出了新的阈值自适应损失缩放 (TALS) 来惩罚较大的 2D 和 p-GT 损失，但不惩罚较小的损失。此方法可以解释 2D 数据的多个 3D 姿势，为了减少模糊性，我们需要一个先验来限制人体姿势的有效空间，我们利用人体姿势的 Token 编码重新定义了问题，这有效地引入了一个统一的先验。基于 EMDB 和 3DPW 数据集的大量实验证明，我们改进的关键点损失和 Token 编码使我们能够在野外数据上进行训练，并提高了 3D 准确性，我们的模型和代码可供研究使用。