STD-Net: Structure-Preserving and Topology-Adaptive Deformation Network for Single-View 3D Reconstruction

3D reconstruction from single-view images is a long-standing research problem. There have been various methods based on point clouds and volumetric representations. In spite of success in 3D models generation, it is quite challenging for these approaches to deal with models with complex topology and fine geometric details. Thanks to the recent advance of deep shape representations, learning the structure and detail representation using deep neural networks is a promising direction. In this article, we propose a novel approach named STD-Net to reconstruct 3D models utilizing mesh representation that is well suited for characterizing complex structures and geometry details. Our method consists of (1) an auto-encoder network for recovering the structure of an object with bounding box representation from a single-view image; (2) a topology-adaptive GCN for updating vertex position for meshes of complex topology; and (3) a unified mesh deformation block that deforms the structural boxes into structure-aware meshes. Evaluation on ShapeNet and PartNet shows that STD-Net has better performance than state-of-the-art methods in reconstructing complex structures and fine geometric details.

Automated summary

In this article, a novel approach named STD-Net is proposed for 3D reconstruction using mesh representation suitable for characterizing complex structures and geometry details. The method includes an auto-encoder network for recovering the object structure from a single-view image, a topology-adaptive GCN for updating vertex position for meshes of complex topology, and a unified mesh deformation block for deforming the structural boxes into structure-aware meshes. Evaluation on ShapeNet and PartNet demonstrates that STD-Net outperforms state-of-the-art methods in reconstructing complex structures and fine geometric details.