Deep image synthesis from intuitive user input: A review and perspectives

• Published in: Computational visual media (Beijing) Vol. 8; no. 1; pp. 3 - 31
• Main Authors: Xue, Yuan, Guo, Yuan-Chen, Zhang, Han, Xu, Tao, Zhang, Song-Hai, Huang, Xiaolei
• Format: Journal Article
• Language: English
• Published: Beijing Tsinghua University Press 01.03.2022; Springer Nature B.V; SpringerOpen
• Subjects: Artificial Intelligence; Computer Graphics; Computer Science; deep generative models; Generative adversarial networks; Image management; Image processing; Image Processing and Computer Vision; Image retrieval; image synthesis; intuitive user input; Review Article; Synthesis; synthesized image quality evaluation; User Interfaces and Human Computer Interaction; intuitive user input; synthesized image quality evaluation; image synthesis; deep generative models
• ISSN: 2096-0433; 2096-0662
• DOI: 10.1007/s41095-021-0234-8

In many applications of computer graphics, art, and design, it is desirable for a user to provide intuitive non-image input, such as text, sketch, stroke, graph, or layout, and have a computer system automatically generate photo-realistic images according to that input. While classically, works that allow such automatic image content generation have followed a framework of image retrieval and composition, recent advances in deep generative models such as generative adversarial networks (GANs), variational autoencoders (VAEs), and flow-based methods have enabled more powerful and versatile image generation approaches. This paper reviews recent works for image synthesis given intuitive user input, covering advances in input versatility, image generation methodology, benchmark datasets, and evaluation metrics. This motivates new perspectives on input representation and interactivity, cross fertilization between major image generation paradigms, and evaluation and comparison of generation methods.