Denoising Diffusion Probabilistic Models, Jonathan Ho, Ajay Jain, Pieter Abbeel, 2020Advances in Neural Information Processing Systems (NeurIPS), Vol. 33DOI: 10.48550/arXiv.2006.11239 - This foundational paper introduced Denoising Diffusion Probabilistic Models (DDPMs) and established the use of the U-Net architecture for noise prediction, the core task discussed in the section.
Deep Learning, Ian Goodfellow, Yoshua Bengio, Aaron Courville, 2016 (MIT Press) - A standard textbook providing comprehensive explanations of convolutional neural networks, encoder-decoder designs, and concepts like skip connections, offering a broad understanding of the underlying principles.