This survey provides a comprehensive overview of 3D generation methods, focusing on the fundamental methodologies, datasets, and applications. It highlights the rapid advancements in 3D content generation, driven by the success of generative AI in images and videos. The survey is structured into several sections, covering 3D representations, generation methods, datasets, and applications. 1. **Neural Scene Representations**: This section discusses explicit, implicit, and hybrid scene representations. Explicit representations include point clouds, meshes, and multi-layer representations. Implicit representations focus on Neural Radiance Fields (NeRFs) and Neural Signed Distance Fields (SDFs). Hybrid representations combine elements of both explicit and implicit forms. 2. **Generation Methods**: The survey categorizes 3D generation methods into four types: feedforward generation, optimization-based generation, procedural generation, and generative novel view synthesis. Each category is explored in detail, with examples of popular methods such as GANs, diffusion models, autoregressive models, VAEs, and normalizing flows. 3. **Datasets**: The availability of datasets is crucial for training and evaluating 3D generation models. The survey discusses various datasets used in 3D content generation, emphasizing their role in advancing the field. 4. **Applications**: The survey covers applications of 3D generation, including 3D human and face generation, 3D editing, and other immersive experiences. It highlights the potential of 3D content in video games, movies, and virtual characters. 5. **Open Challenges**: The survey concludes with a discussion on open challenges in 3D content generation, emphasizing the need for further research to address the complexities of 3D space and improve the quality and diversity of generated models. The survey aims to provide a structured roadmap for researchers and practitioners in the field of 3D content generation, helping them stay updated with the latest advancements and fostering further innovation.This survey provides a comprehensive overview of 3D generation methods, focusing on the fundamental methodologies, datasets, and applications. It highlights the rapid advancements in 3D content generation, driven by the success of generative AI in images and videos. The survey is structured into several sections, covering 3D representations, generation methods, datasets, and applications. 1. **Neural Scene Representations**: This section discusses explicit, implicit, and hybrid scene representations. Explicit representations include point clouds, meshes, and multi-layer representations. Implicit representations focus on Neural Radiance Fields (NeRFs) and Neural Signed Distance Fields (SDFs). Hybrid representations combine elements of both explicit and implicit forms. 2. **Generation Methods**: The survey categorizes 3D generation methods into four types: feedforward generation, optimization-based generation, procedural generation, and generative novel view synthesis. Each category is explored in detail, with examples of popular methods such as GANs, diffusion models, autoregressive models, VAEs, and normalizing flows. 3. **Datasets**: The availability of datasets is crucial for training and evaluating 3D generation models. The survey discusses various datasets used in 3D content generation, emphasizing their role in advancing the field. 4. **Applications**: The survey covers applications of 3D generation, including 3D human and face generation, 3D editing, and other immersive experiences. It highlights the potential of 3D content in video games, movies, and virtual characters. 5. **Open Challenges**: The survey concludes with a discussion on open challenges in 3D content generation, emphasizing the need for further research to address the complexities of 3D space and improve the quality and diversity of generated models. The survey aims to provide a structured roadmap for researchers and practitioners in the field of 3D content generation, helping them stay updated with the latest advancements and fostering further innovation.