In this report, we focus on reconstructing clothed humans in the canonical space given multiple views and poses of a human as the input. To achieve this, we utilize the geometric prior of the SMPLX model in the canonical space to learn the implicit representation for geometry reconstruction. Based on the observation that the topology between the posed mesh and the mesh in the canonical space are consistent, we propose to learn latent codes on the posed mesh by leveraging multiple input images and then assign the latent codes to the mesh in the canonical space. Specifically, we first leverage normal and geometry networks to extract the feature vector for each vertex on the SMPLX mesh. Normal maps are adopted for better generalization to unseen images compared to 2D images. Then, features for each vertex on the posed mesh from multiple images are integrated by MLPs. The integrated features acting as the latent code are anchored to the SMPLX mesh in the canonical space. Finally, latent code for each 3D point is extracted and utilized to calculate the SDF. Our work for reconstructing the human shape on canonical pose achieves 3rd performance on WCPA MVP-Human Body Challenge.

本研究关注于使用多视图和多姿势的人体输入，重建位于规范空间中的衣着人体。我们利用SMPLX模型在规范空间中的几何先验，学习了几何重建的隐式表示，并在姿势网格和规范空间网格之间学习潜在编码。最终，我们的工作在WCPA MVP-Human Body Challenge中实现了第三的表现。

基于多视角和多姿态图像的人体模型的Pixel2ISDF: 隐式符号距离场