Research on 3D Human Body Reconstruction Algorithm of Monocular Image
Zijian Liang, Huan Liang, Wenlong Fu · 2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) · 2021
The three-dimensional human body feature parameters extracted by the neural network method are coupled in the high-dimensional feature space. The fully connected network processes the three-dimensional human pose and shape feature information synchronously, which cannot handle multifactor features well, which makes the model perform poorly. To solve this problem, on the basis of the benchmark network, a decoupling model is added, which processes the three-dimensional human pose and shape information separately, and finally integrates the features through the bi-linear transformation method. Through experimental verification, the algorithm effectively reduces the reconstruction error, and the improved algorithm performs better.