Connective Viewpoints of Signal-to-Noise Diffusion Models
This work provides a unified framework for understanding noise schedulers in diffusion models, which is incremental for researchers in generative AI.
The paper tackles the need for a comprehensive study of Signal-to-Noise diffusion models by connecting different viewpoints and exploring new perspectives, resulting in the development of a generalized backward equation to enhance inference performance.
Diffusion models (DM) have become fundamental components of generative models, excelling across various domains such as image creation, audio generation, and complex data interpolation. Signal-to-Noise diffusion models constitute a diverse family covering most state-of-the-art diffusion models. While there have been several attempts to study Signal-to-Noise (S2N) diffusion models from various perspectives, there remains a need for a comprehensive study connecting different viewpoints and exploring new perspectives. In this study, we offer a comprehensive perspective on noise schedulers, examining their role through the lens of the signal-to-noise ratio (SNR) and its connections to information theory. Building upon this framework, we have developed a generalized backward equation to enhance the performance of the inference process.