Topology-Aware Single-Image 3D Shape Reconstruction
Topology-Aware Single-Image 3D Shape Reconstruction
复制标题
DOI：
10.1109/cvprw50498.2020.00143
复制
发表时间：
2020-06
期刊：
影响因子：
--
通讯作者：
Qimin Chen;Vincent Nguyen;Feng Han;Raimondas Kiveris;Z. Tu
中科院分区：
文献类型：
--
作者：
Qimin Chen;Vincent Nguyen;Feng Han;Raimondas Kiveris;Z. Tu
我们尝试解决 3D 形状重建的拓扑感知问题。这里正在研究两种类型的高级形状类型，即属（切割/孔的数量）和连通性（连接组件的数量），它们在 3D 对象重建/理解中非常重要，但迄今为止与现有的密集体素预测文献脱节。我们提出了一种拓扑感知形状自动编码器组件（TPWCoder），通过从潜在变量近似拓扑属性函数，例如几何和与神经网络的连接。 TPWCoder可以直接与现有的3D形状重建管道相结合，进行端到端的训练和预测。在具有挑战性的大型 CAD 模型数据集 (ABC) 上，TPWCoder 表现出了比竞争方法明显的定量和定性改进，并且还在 ShapeNet 数据集上显示了改进的定量结果。
We make an attempt to address topology-awareness for 3D shape reconstruction. Two types of high-level shape typologies are being studied here, namely genus (number of cuttings/holes) and connectivity (number of connected components), which are of great importance in 3D object reconstruction/understanding but have been thus far disjoint from the existing dense voxel-wise prediction literature. We propose a topology-aware shape autoencoder component (TPWCoder) by approximating topology property functions such as genus and connectivity with neural networks from the latent variables. TPWCoder can be directly combined with the existing 3D shape reconstruction pipelines for end-to-end training and prediction. On the challenging A Big CAD Model Dataset (ABC), TPWCoder demonstrates a noticeable quantitative and qualitative improvement over the competing methods, and it also shows improved quantitative result on the ShapeNet dataset.