English

Connective Viewpoints of Signal-to-Noise Diffusion Models

Computer Vision and Pattern Recognition 2024-08-09 v1 Artificial Intelligence Machine Learning Neural and Evolutionary Computing

Abstract

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.

Keywords

Cite

@article{arxiv.2408.04221,
  title  = {Connective Viewpoints of Signal-to-Noise Diffusion Models},
  author = {Khanh Doan and Long Tung Vuong and Tuan Nguyen and Anh Tuan Bui and Quyen Tran and Thanh-Toan Do and Dinh Phung and Trung Le},
  journal= {arXiv preprint arXiv:2408.04221},
  year   = {2024}
}
R2 v1 2026-06-28T18:07:19.134Z