A comprehensive survey on diffusion models and their applications
Md Manjurul Ahsan, Shivakumar Raman, Yingtao Liu, Zahed Siddique
Abstract
Diffusion Models (DMs) are probabilistic models that create realistic samples by simulating the diffusion process, gradually adding and removing noise from data. These models have gained popularity in domains such as image processing, speech synthesis, and natural language processing due to their ability to produce high-quality samples. As DMs are being adopted in various domains, existing literature reviews that often focus on specific areas like computer vision or medical imaging may not serve a broader audience across multiple fields. Therefore, this review presents a comprehensive overview of DMs, covering their theoretical foundations and algorithmic innovations. We highlight their applications in diverse areas such as media quality, authenticity, synthesis, image transformation, healthcare, and more. Unlike prior surveys that are often domain-specific, this review integrates developments across multiple fields and proposes a unified taxonomy of diffusion models, categorizing them by architecture, conditioning strategy, and application. This cross-domain synthesis not only reveals underexplored areas but also identifies emerging interdisciplinary opportunities, offering actionable insights for future research. By consolidating current knowledge and identifying emerging trends, this review aims to facilitate a deeper understanding and broader adoption of DMs and provide guidelines for future researchers and practitioners across diverse disciplines.