Advances in 3D Generation: A Survey
IEEE Publication Technology This paper was produced by the IEEE Publication Technology Group. They are in Piscataway, NJ.Manuscript received April 19, 2021; revised August 16, 2021.
Abstract
Generating 3D models lies at the core of computer graphics and has been the focus of decades of research. With the emergence of generative artificial intelligence (AI) and advanced generative models, the field of 3D content generation is rapidly advancing, unlocking unprecedented capabilities for creating high-quality and diverse 3D models. The rapid growth of this field makes it challenging to keep up with all recent developments. This survey aims to introduce the fundamental methodologies of 3D generation methods and establish a structured roadmap, encompassing 3D representation, generation methods, datasets, and corresponding applications. Specifically, we introduce the 3D representations that serve as the backbone for 3D generation. Furthermore, we provide a comprehensive overview of the rapidly growing literature on generation methods, categorized by the type of algorithmic paradigms, including feedforward generation, optimization-based generation, procedural generation, and generative novel view synthesis. Lastly, we discuss available datasets, applications, and open challenges. This survey offers an intuitive starting point for researchers, artists, and practitioners alike t
中文速览
如今想用算法自动生成逼真多样的三维模型，面临表示方式繁多、数据稀缺、多视角一致性难以保证等重重挑战，研究进展又日新月异、难以全面跟踪。这篇综述系统梳理了三维内容生成（3D content generation）领域的核心方法，将三维表示分为显式、隐式和混合三大类，并把生成方法归纳为前馈生成、基于优化的生成、程序化生成和生成式新视角合成四条技术路线，同时整理了主流训练数据集和下游应用场景。研究发现，以神经辐射场（NeRF）为代表的神经表示与以扩散模型为代表的生成式AI相结合，正在推动三维生成质量和多样性实现跨越式提升。这项综述为计算机视觉、图形学研究者及内容创作者提供了一张清晰的技术路线图，有助于加速三维内容生成走向游戏、影视、元宇宙等实际应用。
原文 arXiv:2401.17807;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2401.17807v1