3-D Clothed Human Model Reconstruction Based on Single-View In-the-Wild Image Data

Three-dimensional clothed human reconstruction has gained great development recently. However, many methods complete reconstruction based on model trained on the synthetic data with artificial appearance or the 3-D scan data with high costs. The difference between synthetic data, 3-D scan data and in-the-wild data severely restricts application of these methods in real world. Moreover, due to complex background and pose in the image, some researches on the 3-D clothed human reconstruction from single-view in-the-wild images are facing challenges. In this article, a modular model is designed to perform the 3-D clothed human reconstruction with high quality based on one single-view in-the-wild image. In detail, the model consists of Cloth Encoder which extracts the feature of clothes, Body Encoder which obtains the parameters of human body, and cloth generation module which generates the clothes on the human model. Specifically, an adaptive integration of convolution neural network and self-attention is proposed to extract features of the input image. Moreover, to eliminate the distraction of the background, the segmentation of the input image is utilized to supervise our training process. The proposed method is compared with the mainstream methods on the two datasets, MSCOCO and 3-D poses in the wild (3DPW). The quantitative and qualitative results demonstrate that our method is more accurate in reconstructing clothed human model than the previous methods. Based on the experiment results, our work provides a more convenient and accurate 3-D clothed human reconstruction technique in the real world.