Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?

Chaoning Zhang, Chenshuang Zhang, Sheng Zheng, Yu Qiao, Chenghao Li, Mengchun Zhang, Sumit Kumar Dam, Chu Myaet Thwal, Ye Lin Tun, Le Luang Huy, Donguk kim, Sung-Ho Bae, Lik-Hang Lee, Yang Yang, Heng Tao Shen, In So Kweon, Choong Seon Hong

TL;DR

This paper surveys generative AI (AIGC) across techniques, tasks, applications, and challenges, clarifying terminology and the landscape as it shifts from analysis to content creation. It distinguishes two foundational technical strands—backbone architectures with self-supervised pretraining and deep generative models (GANs and diffusion models)—and then organizes AIGC tasks by output type (text, image, video, 3D, and beyond). It catalogs text and image generation methods, multimodal extensions, and emerging content modalities, highlighting key systems (e.g., GPT/ChatGPT, diffusion-based image generation, and NeRF-based 3D methods) and major industry deployments. It also discusses ethical, legal, and societal implications, providing an outlook on future control, scalability, and the startup/industry ecosystem.

Abstract

As ChatGPT goes viral, generative AI (AIGC, a.k.a AI-generated content) has made headlines everywhere because of its ability to analyze and create text, images, and beyond. With such overwhelming media coverage, it is almost impossible for us to miss the opportunity to glimpse AIGC from a certain angle. In the era of AI transitioning from pure analysis to creation, it is worth noting that ChatGPT, with its most recent language model GPT-4, is just a tool out of numerous AIGC tasks. Impressed by the capability of the ChatGPT, many people are wondering about its limits: can GPT-5 (or other future GPT variants) help ChatGPT unify all AIGC tasks for diversified content creation? Toward answering this question, a comprehensive review of existing AIGC tasks is needed. As such, our work comes to fill this gap promptly by offering a first look at AIGC, ranging from its techniques to applications. Modern generative AI relies on various technical foundations, ranging from model architecture and self-supervised pretraining to generative modeling methods (like GAN and diffusion models). After introducing the fundamental techniques, this work focuses on the technological development of various AIGC tasks based on their output type, including text, images, videos, 3D content, etc., which depicts the full potential of ChatGPT's future. Moreover, we summarize their significant applications in some mainstream industries, such as education and creativity content. Finally, we discuss the challenges currently faced and present an outlook on how generative AI might evolve in the near future.

A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?

TL;DR

This paper surveys generative AI (AIGC) across techniques, tasks, applications, and challenges, clarifying terminology and the landscape as it shifts from analysis to content creation. It distinguishes two foundational technical strands—backbone architectures with self-supervised pretraining and deep generative models (GANs and diffusion models)—and then organizes AIGC tasks by output type (text, image, video, 3D, and beyond). It catalogs text and image generation methods, multimodal extensions, and emerging content modalities, highlighting key systems (e.g., GPT/ChatGPT, diffusion-based image generation, and NeRF-based 3D methods) and major industry deployments. It also discusses ethical, legal, and societal implications, providing an outlook on future control, scalability, and the startup/industry ecosystem.

Abstract

As ChatGPT goes viral, generative AI (AIGC, a.k.a AI-generated content) has made headlines everywhere because of its ability to analyze and create text, images, and beyond. With such overwhelming media coverage, it is almost impossible for us to miss the opportunity to glimpse AIGC from a certain angle. In the era of AI transitioning from pure analysis to creation, it is worth noting that ChatGPT, with its most recent language model GPT-4, is just a tool out of numerous AIGC tasks. Impressed by the capability of the ChatGPT, many people are wondering about its limits: can GPT-5 (or other future GPT variants) help ChatGPT unify all AIGC tasks for diversified content creation? Toward answering this question, a comprehensive review of existing AIGC tasks is needed. As such, our work comes to fill this gap promptly by offering a first look at AIGC, ranging from its techniques to applications. Modern generative AI relies on various technical foundations, ranging from model architecture and self-supervised pretraining to generative modeling methods (like GAN and diffusion models). After introducing the fundamental techniques, this work focuses on the technological development of various AIGC tasks based on their output type, including text, images, videos, 3D content, etc., which depicts the full potential of ChatGPT's future. Moreover, we summarize their significant applications in some mainstream industries, such as education and creativity content. Finally, we discuss the challenges currently faced and present an outlook on how generative AI might evolve in the near future.
Paper Structure (48 sections, 9 equations, 21 figures)

This paper contains 48 sections, 9 equations, 21 figures.

Table of Contents

  1. Introduction
  2. Overview
  3. Popularity indicated by search interest
  4. Why does it get popular?
  5. Content need
  6. Technology conditions
  7. Fundamental techniques behind AIGC
  8. General techniques in AI
  9. Backbone architecture
  10. Self-supervised pretraining
  11. Creation techniques in AI
  12. Likelihood-based models
  13. Energy-based models
  14. Two star-models: from GAN to diffusion model
  15. AIGC task: text generation
  16. ...and 33 more sections

Figures (21)

  • Figure 1: Search interest of generative AI: Timeline trend (left) and region-wise interest (right). The color darkness on the right part indicates the rank interest level.
  • Figure 2: Search interest of AIGC: Timeline trend (left) and region-wise interest (right). The color darkness on the right part indicates the rank interest level.
  • Figure 3: Search interest comparison between generative AI and AIGC: Timeline trend (left) and region-wise interest (right).
  • Figure 4: An overview of generative AI (AIGC): fundamental techniques, core AIGC tasks, and industrial applications.
  • Figure 5: Transformer structure (figure obtained from vaswani2017attention).
  • ...and 16 more figures