论文标题
SPGNET：在低维空间中的空间投影引导3D人姿势估计
SPGNet: Spatial Projection Guided 3D Human Pose Estimation in Low Dimensional Space
论文作者
论文摘要
我们提出了一种用于3D人姿势估计的方法SPGNET，该方法将多维重新投影混合到监督学习中。在这种方法中，2到3D峰值网络预测了3D人姿势的全局位置和坐标。然后，我们将估计的3D姿势与空间调整一起重新投影回到2D密钥点。损失功能将估计的3D姿势与3D姿势地面真理进行了比较，并以输入2D姿势重新投影了2D姿势。此外，我们提出了一个运动学约束，以限制人骨长度恒定的预测靶标。基于数据集人物36M的估计结果，我们的方法在定性和定量上都优于许多最新方法。
We propose a method SPGNet for 3D human pose estimation that mixes multi-dimensional re-projection into supervised learning. In this method, the 2D-to-3D-lifting network predicts the global position and coordinates of the 3D human pose. Then, we re-project the estimated 3D pose back to the 2D key points along with spatial adjustments. The loss functions compare the estimated 3D pose with the 3D pose ground truth, and re-projected 2D pose with the input 2D pose. In addition, we propose a kinematic constraint to restrict the predicted target with constant human bone length. Based on the estimation results for the dataset Human3.6M, our approach outperforms many state-of-the-art methods both qualitatively and quantitatively.
