Enhancing Score-Based Generative Diffusion Models with Time-Correlated Noise
Introducing time-correlated "active" noise sources into the forward diffusion process of score-based generative models can improve their ability to learn complex data distributions and generate higher-quality samples.
Generative Fractional Diffusion Models: Enhancing Image Generation with Fractional Brownian Motion
This paper introduces Generative Fractional Diffusion Models (GFDM), a novel approach to image generation that leverages the correlated increments and long-term memory of fractional Brownian motion (fBM) to enhance image quality, diversity, and distribution coverage compared to traditional diffusion models reliant on Brownian motion.
Theoretical Research on Generative Diffusion Models: Advancements and Insights
Generative diffusion models have shown high success in various fields with a powerful theoretical foundation. This study provides an overview of the theoretical developments in this domain, categorizing the research into training-based and sampling-based approaches.
Understanding Generative Diffusion Models in Statistical Thermodynamics
Generative diffusion models exhibit phase transitions and critical instability, revealing a deep connection to equilibrium statistical mechanics.
© 2024 by Linnk AI