3D reconstruction from a single view image is a long-standing prob-lem in computer vision. Various methods based on different shape representations(such as point cloud or volumetric representations) have been proposed. However,the 3D shape reconstruction with fine details and complex structures are still chal-lenging and have not yet be solved. Thanks to the recent advance of the deepshape representations, it becomes promising to learn the structure and detail rep-resentation using deep neural networks. In this paper, we propose a novel methodcalled STD-Net to reconstruct the 3D models utilizing the mesh representationthat is well suitable for characterizing complex structure and geometry details.To reconstruct complex 3D mesh models with fine details, our method consists of(1) an auto-encoder network for recovering the structure of an object with bound-ing box representation from a single image, (2) a topology-adaptive graph CNNfor updating vertex position for meshes of complex topology, and (3) an unifiedmesh deformation block that deforms the structural boxes into structure-awaremeshed models. Experimental results on the images from ShapeNet show that ourproposed STD-Net has better performance than other state-of-the-art methods onreconstructing 3D objects with complex structures and fine geometric details.

中文翻译：

---

STD-Net：用于从单个图像进行 3D 重建的结构保留和拓扑自适应变形网络

从单视图图像进行 3D 重建是计算机视觉中长期存在的问题。已经提出了基于不同形状表示（例如点云或体积表示）的各种方法。然而，细节精细、结构复杂的3D形状重建仍然具有挑战性，尚未解决。由于 deepshape 表示的最新进展，使用深度神经网络学习结构和细节表示变得很有希望。在本文中，我们提出了一种称为 STD-Net 的新方法来利用网格表示重建 3D 模型，该方法非常适合表征复杂的结构和几何细节。为了重建具有精细细节的复杂 3D 网格模型，我们的方法包括（1）一个自动编码器网络，用于从单个图像中恢复具有边界框表示的对象的结构，（2）一个拓扑自适应图 CNN，用于更新复杂拓扑网格的顶点位置，以及（ 3）统一网格变形块，将结构盒变形为结构感知模型。ShapeNet 图像的实验结果表明，我们提出的 STD-Net 在重建具有复杂结构和精细几何细节的 3D 对象方面比其他最先进的方法具有更好的性能。