This paper provides a comprehensive analysis of recent advances in 3D shape generation using implicit representations. It categorizes the studies based on the type of representation (signed distance fields, radiance fields, and triplanes) and the generation architecture. The paper discusses the attributes of each representation in detail and highlights potential future research directions. The key contributions include: 1. **Introduction to Implicit Representations**: The paper introduces signed distance fields (SDFs), radiance fields (RFs), and triplanes, explaining their properties and applications. 2. **Generation Architectures**: It covers various architectures used to generate 3D shapes from these representations, including generative adversarial networks (GANs), variational autoencoders (VAEs), diffusion models (DMs), and 2D-to-3D models. 3. **Recent Studies**: The paper reviews recent works on 3D shape generation using SDFs, RFs, and triplanes, categorizing them by generation architecture and results. 4. **Discussion and Future Directions**: It discusses open problems such as improving geometric quality, generating at higher speeds, handling large-scale scenes, and combining implicit and explicit representations. The paper aims to provide insights for researchers and inspire future work in this area, emphasizing the need for advancements in 3D shape generation to meet the growing demand for advanced applications like virtual reality and augmented reality.This paper provides a comprehensive analysis of recent advances in 3D shape generation using implicit representations. It categorizes the studies based on the type of representation (signed distance fields, radiance fields, and triplanes) and the generation architecture. The paper discusses the attributes of each representation in detail and highlights potential future research directions. The key contributions include: 1. **Introduction to Implicit Representations**: The paper introduces signed distance fields (SDFs), radiance fields (RFs), and triplanes, explaining their properties and applications. 2. **Generation Architectures**: It covers various architectures used to generate 3D shapes from these representations, including generative adversarial networks (GANs), variational autoencoders (VAEs), diffusion models (DMs), and 2D-to-3D models. 3. **Recent Studies**: The paper reviews recent works on 3D shape generation using SDFs, RFs, and triplanes, categorizing them by generation architecture and results. 4. **Discussion and Future Directions**: It discusses open problems such as improving geometric quality, generating at higher speeds, handling large-scale scenes, and combining implicit and explicit representations. The paper aims to provide insights for researchers and inspire future work in this area, emphasizing the need for advancements in 3D shape generation to meet the growing demand for advanced applications like virtual reality and augmented reality.