Deep Image Synthesis from Intuitive User Input: A Review and Perspectives
It provides a comprehensive overview for researchers and practitioners in computer graphics and AI, but is incremental as it synthesizes existing work without introducing new methods.
This paper reviews recent advances in deep generative models like GANs and VAEs for synthesizing photo-realistic images from intuitive user inputs such as text or sketches, covering input versatility, methodologies, datasets, and evaluation metrics.
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 that adhere to the input content. While classic 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 tasks. 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 pollination between major image generation paradigms, and evaluation and comparison of generation methods.