Guest Editor(s)
Dr. Duo Peng
Email: duo_peng@mymail.sutd.edu.sg
Affiliation: Institute for Digital Molecular Analytics and Science (IDMxS), Nanyang Technological University, 639798, Singapore
Homepage:
Research Interests: generative AI, domain adaptation, computer vision
Summary
Recent breakthroughs in generative modelling, particularly diffusion models, generative adversarial networks (GANs), and large-scale vision–language models, have significantly advanced the field of image generation. These developments have unlocked unprecedented capabilities in synthesizing high-fidelity, diverse, and controllable images, enabling transformative applications in computer vision, digital media, medical imaging, and scientific visualization.
This Special Issue aims to provide a forum for researchers and practitioners to share the latest theoretical insights, algorithmic innovations, and application-driven studies in image generation. We particularly welcome works that bridge foundational models with domain-specific challenges, explore multimodal conditioning mechanisms, and address issues such as controllability, fairness, interpretability, and robustness in generative systems.
Suggested Themes include:
· Diffusion models, GANs, and transformer-based generative architectures
· Multimodal and cross-domain image synthesis (e.g., text-to-image, sketch-to-image)
· Controllable and editable image generation methods
· Generative models for medical and scientific imaging
· Robustness, fairness, and interpretability in generative systems
· Efficient training and deployment of large-scale generative models
Keywords
Image generation; Diffusion models; Robustness; Generative adversarial networks; Multimodal synthesis; Controllable generation; Medical imaging
Published Papers
Login
Register
Submit a Paper
Propose a Special lssue