3D models of objects and scenes are critical to many academic disciplines and industrial applications. Of particular interest is the emerging opportunity for 3D graphics to serve artificial intelligence: computer vision systems can benefit from synthetically‐generated training data rendered from virtual 3D scenes, and robots can be trained to navigate in and interact with real‐world environments by first acquiring skills in simulated ones. One of the most promising ways to achieve this is by learning and applying generative models of 3D content: computer programs that can synthesize new 3D shapes and scenes. To allow users to edit and manipulate the synthesized 3D content to achieve their goals, the generative model should also be structure‐aware: it should express 3D shapes and scenes using abstractions that allow manipulation of their high‐level structure. This state‐of‐the‐art report surveys historical work and recent progress on learning structure‐aware generative models of 3D shapes and scenes. We present fundamental representations of 3D shape and scene geometry and structures, describe prominent methodologies including probabilistic models, deep generative models, program synthesis, and neural networks for structured data, and cover many recent methods for structure‐aware synthesis of 3D shapes and indoor scenes.

中文翻译：

---

学习 3D 结构的生成模型

对象和场景的 3D 模型对于许多学科和工业应用至关重要。特别令人感兴趣的是 3D 图形服务于人工智能的新兴机会：计算机视觉系统可以从虚拟 3D 场景渲染的合成训练数据中受益，并且可以训练机器人通过首先获取在现实世界环境中导航和交互模拟技能。实现这一目标的最有希望的方法之一是学习和应用 3D 内容的生成模型：可以合成新的 3D 形状和场景的计算机程序。为了允许用户编辑和操作合成的 3D 内容以实现他们的目标，生成模型还应该具有结构意识：它应该使用允许操纵其高级结构的抽象来表达 3D 形状和场景。这份最先进的报告调查了在学习 3D 形状和场景的结构感知生成模型方面的历史工作和最新进展。我们展示了 3D 形状和场景几何和结构的基本表示，描述了包括概率模型、深度生成模型、程序合成和用于结构化数据的神经网络在内的主要方法，并涵盖了许多用于 3D 形状和室内场景的结构感知合成的最新方法.