The paper provides a comprehensive overview of the rapidly evolving field of 3D content generation. It begins by emphasizing the significance of 3D model generation in computer graphics and highlights the recent advancements enabled by advanced neural representations and generative models. The survey aims to introduce fundamental methodologies of 3D generation methods and establish a structured roadmap encompassing 3D representation, generation methods, datasets, and applications.

The survey delves into the foundational aspects of 3D generation by introducing the various 3D representations that serve as the backbone for 3D generation. It provides a detailed overview of the rapidly growing literature on generation methods, categorized by the type of algorithmic paradigms. These paradigms include feedforward generation, optimization-based generation, procedural generation, and generative novel view synthesis. Each category is thoroughly explored, shedding light on the diverse approaches and techniques employed in 3D model generation.

Furthermore, the paper discusses the available datasets, applications, and open challenges in the field of 3D content generation. It highlights the importance of datasets in training and evaluating 3D generation models and provides insights into the current and potential applications of 3D generation techniques. Additionally, it addresses the open challenges and future directions in the field, emphasizing the need for continued research and development to overcome existing limitations and drive further advancements in 3D content generation.