With the progress of 3D human pose and shape estimation, state-of-the-art methods can either be robust to occlusions or obtain pixel-aligned accuracy in non-occlusion cases. However, they cannot obtain robustness and mesh-image alignment at the same time. In this work, we present NIKI (Neural Inverse Kinematics with Invertible Neural Network), which models bi-directional errors to improve the robustness to occlusions and obtain pixel-aligned accuracy. NIKI can learn from both the forward and inverse processes with invertible networks. In the inverse process, the model separates the error from the plausible 3D pose manifold for a robust 3D human pose estimation. In the forward process, we enforce the zero-error boundary conditions to improve the sensitivity to reliable joint positions for better mesh-image alignment. Furthermore, NIKI emulates the analytical inverse kinematics algorithms with the twist-and-swing decomposition for better interpretability. Experiments on standard and occlusion-specific benchmarks demonstrate the effectiveness of NIKI, where we exhibit robust and well-aligned results simultaneously. Code is available at https://github.com/Jeff-sjtu/NIKI

翻译：随着三维人体姿态与形状估计的进展，现有最先进方法要么对遮挡具有鲁棒性，要么在无遮挡情况下获得像素级对齐精度。然而，它们无法同时兼顾鲁棒性与网格-图像对齐。本文提出NIKI（基于可逆神经网络的神经逆向运动学），通过建模双向误差来提升对遮挡的鲁棒性并实现像素级对齐精度。NIKI能够利用可逆网络从正向与逆向过程中学习。在逆向过程中，模型从合理的3D姿态流形中分离误差，以实现鲁棒的三维人体姿态估计。在正向过程中，我们强制施加零误差边界条件，以提高对可靠关节位置的敏感性，从而优化网格-图像对齐。此外，NIKI通过扭转-摆动分解模拟解析逆向运动学算法，以增强可解释性。在标准与特定遮挡基准上的实验证明了NIKI的有效性，我们同时展现了鲁棒且良好对齐的结果。代码开源地址：https://github.com/Jeff-sjtu/NIKI