Denoising Diffusion Probabilistic Models

This paper introduces a new type of generative model called Denoising Diffusion Probabilistic Models (DDPMs). These models learn to generate images by gradually reversing a process that adds noise to the image until it becomes pure noise. Then, the model learns to remove the noise step by step, effectively reconstructing the original image. This approach has shown impressive results in generating high-quality images and offers a novel way to approach generative modeling.