HybrIK relies on a combination of analytical inverse kinematics and deep learning to produce more accurate 3D pose estimation from 2D monocular images. HybrIK has three major components: (1) pretrained convolution backbone, (2) deconvolution to lift 3D pose from 2D convolution features, (3) analytical inverse kinematics pass correcting deep learning prediction using learned distribution of plausible twist and swing angles. In this paper we propose an enhancement of the 2D to 3D lifting module, replacing deconvolution with Transformer, resulting in accuracy and computational efficiency improvement relative to the original HybrIK method. We demonstrate our results on commonly used H36M, PW3D, COCO and HP3D datasets. Our code is publicly available https://github.com/boreshkinai/hybrik-transformer.

翻译：HybrIK方法结合了解析逆运动学与深度学习，可从二维单目图像生成更精确的三维姿态估计。该方法包含三个主要模块：(1)预训练卷积骨干网络，(2)通过反卷积从二维卷积特征中提升三维姿态，(3)利用可信扭角与摆角分布修正深度学习预测结果的解析逆运动学通路。本文提出对二维到三维提升模块的改进，采用Transformer替代反卷积模块，在保持原HybrIK方法精度的同时提升了计算效率。我们在H36M、PW3D、COCO及HP3D等通用数据集上验证了该方法的效果。代码已开源至https://github.com/boreshkinai/hybrik-transformer。