Learning Generative Models of 3D Structures
Learning Generative Models of 3D Structures
复制标题
DOI：
10.1111/cgf.14020
复制
发表时间：
2020-05-01
影响因子：
2.5
通讯作者：
Zhang, Hao
中科院分区：
文献类型：
--
作者：
Chaudhuri, Siddhartha;Ritchie, Daniel;Zhang, Hao
对象和场景的3D模型对于许多学科和工业应用至关重要。特别感兴趣的是3D图形为人工智能服务的新兴机会：计算机视觉系统可以从虚拟3D场景中呈现的合成生成的培训数据中受益，并且可以通过首次通过获得现实环境进行培训，可以培训机器人来导航并与现实环境进行交互。模拟的技能。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纵合成的3D内容以实现其目标，生成模型也应具有结构意识：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。该最先进的报告调查了历史工作以及3D形状和场景的学习结构感知生成模型的最新进展。我们介绍了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，深层生成模型，程序合成以及用于结构化数据的神经网络在内的突出方法，并涵盖了许多最新的结构综合方法3D形状和室内场景的方法。
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.