Artificial Intelligence Generated Content (AIGC) is revolutionizing the fields of multimedia signal processing and computer vision with the explosive development of large language models (LLMs) and vision and multimodal LLMs. AI-driven visual content generation, which includes images, videos, and 3D and 4D dynamic visual contents, shows remarkable potential in areas such as image synthesis, video editing, virtual reality, and art creation. Advances in conditional generation and multimodal representation research are helping improve the quality of visual content generation. In this context, controllable AI visual content generation is receiving increasing attention. With the aim of maintaining user interaction and controllability, ensuring content diversity and consistency in the generation process, and generating high quality visual contents that meet users’ expectations, there is an urgent need to explore generation-oriented representation theories and methods, and to elucidate theories, methods, models, and evaluation metrics related to controllable generation. This special issue aims to explore the basic methods and main applications of controllable AI visual content generation, while promoting progress in the development of controllable and reliable AI-driven visual content generation techniques.

The scope of this special issue includes, but is not limited to, the following topics:

• Representation Theory and Methods for AI Visual Content Generation
• Methods and Models for Controllable AI Visual Content Generation
• 3D Reconstruction and Novel View Synthesis
• 4D Dynamic Reconstruction and Generation
• Visual Content Creation and Editing
• Controllable AIGC for Video Enhancement & Restoration
• Quality Evaluation and Forgery Detection for AIGC
• Efficiency and Scalability of AIGC Models

Please find more information in the following link:

https://link.springer.com/collections/gbibajbjfb