DSG-Net：学习三维形状生成的非纠缠结构和几何
DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generation
摘要：
三维图形生成是计算机图形学中的一个基本操作。虽然已经取得了重大进展，特别是最近的深度生成模型，但以可控的方式合成具有丰富几何细节和复杂结构的高质量形状仍然是一个挑战。为了解决这个问题，我们引入了DSG-Net，这是一种深度神经网络，它可以学习3D形状的解纠缠结构化和几何网格表示，其中形状，几何形状和结构的两个关键方面以协同方式编码，以确保生成的形状的可扩展性，同时也尽可能地解纠缠。这支持了一系列新颖的形状生成应用与解纠缠控制，如插值的结构（几何），同时保持几何（结构）不变。为了实现这一点，我们同时学习结构和几何结构，通过变分自编码器（VAE）在一个层次的方式为两者，在每个级别的双射映射。通过这种方式，我们在单独的潜在空间中有效地编码几何和结构，同时确保它们的兼容性：结构用于引导几何，反之亦然。在叶级，使用条件部分VAE表示部分几何形状，以编码高质量的几何细节，由结构上下文作为条件引导。我们的方法不仅支持可控生成应用，而且还生成高质量的合成形状，优于最先进的方法。该代码已在https://github.com/IGLICT/DSG-Net上发布。
英文摘要：
D shape generation is a fundamental operation in computer graphics. While significant progress has been made, especially with recent deep generative models, it remains a challenge to synthesize high-quality shapes with rich geometric details and complex structure, in a controllable manner. To tackle this, we introduce DSG-Net, a deep neural network that learns a disentangled structured and geometric mesh representation for 3D shapes, where two key aspects of shapes, geometry, and structure, are encoded in a synergistic manner to ensure plausibility of the generated shapes, while also being disentangled as much as possible. This supports a range of novel shape generation applications with disentangled control, such as interpolation of structure (geometry) while keeping geometry (structure) unchanged. To achieve this, we simultaneously learn structure and geometry through variational autoencoders (VAEs) in a hierarchical manner for both, with bijective mappings at each level. In this manner, we effectively encode geometry and structure in separate latent spaces, while ensuring their compatibility: the structure is used to guide the geometry and vice versa. At the leaf level, the part geometry is represented using a conditional part VAE, to encode high-quality geometric details, guided by the structure context as the condition. Our method not only supports controllable generation applications but also produces high-quality synthesized shapes, outperforming state-of-the-art methods. The code has been released at https://github.com/IGLICT/DSG-Net.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
