Learning to Generate 3D Shapes from a Single Example
Learning to Generate 3D Shapes from a Single Example
复制标题
DOI：
10.1145/3550454.3555480
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
Rundi Wu;Changxi Zheng
中科院分区：
文献类型：
--
作者：
Rundi Wu;Changxi Zheng
现有的 3D 形状生成模型通常在大型 3D 数据集（通常是特定对象类别）上进行训练。在本文中，我们研究了仅从单个参考 3D 形状学习的深度生成模型。具体来说，我们提出了一种基于 GAN 的多尺度模型，旨在捕获输入形状在一系列空间尺度上的几何特征。为了避免在 3D 体积上操作而产生大量内存和计算成本，我们在三平面混合表示之上构建了生成器，这仅需要 2D 卷积。我们在参考形状的体素金字塔上训练我们的生成模型，不需要任何外部监督或手动注释。经过训练后，我们的模型可以生成可能具有不同尺寸和纵横比的多样化且高质量的 3D 形状。生成的形状呈现出不同尺度的变化，同时保留了参考形状的全局结构。通过广泛的定性和定量评估，我们证明我们的模型可以生成各种类型的 3D 形状。1
Existing generative models for 3D shapes are typically trained on a large 3D dataset, often of a specific object category. In this paper, we investigate the deep generative model that learns from only a single reference 3D shape. Specifically, we present a multi-scale GAN-based model designed to capture the input shape's geometric features across a range of spatial scales. To avoid large memory and computational cost induced by operating on the 3D volume, we build our generator atop the tri-plane hybrid representation, which requires only 2D convolutions. We train our generative model on a voxel pyramid of the reference shape, without the need of any external supervision or manual annotation. Once trained, our model can generate diverse and high-quality 3D shapes possibly of different sizes and aspect ratios. The resulting shapes present variations across different scales, and at the same time retain the global structure of the reference shape. Through extensive evaluation, both qualitative and quantitative, we demonstrate that our model can generate 3D shapes of various types.1