Denoising diffusion models (DDMs) have led to staggering performance leaps in image generation, editing and restoration. However, existing DDMs use very large datasets for training. Here, we introduce a framework for training a DDM on a single image. Our method, which we coin SinDDM, learns the internal statistics of the training image by using a multi-scale diffusion process. To drive the reverse diffusion process, we use a fully-convolutional light-weight denoiser, which is conditioned on both the noise level and the scale. This architecture allows generating samples of arbitrary dimensions, in a coarse-to-fine manner. As we illustrate, SinDDM generates diverse high-quality samples, and is applicable in a wide array of tasks, including style transfer and harmonization. Furthermore, it can be easily guided by external supervision. Particularly, we demonstrate text-guided generation from a single image using a pre-trained CLIP model.
@article{arxiv.2211.16582,
title = {SinDDM: A Single Image Denoising Diffusion Model},
author = {Vladimir Kulikov and Shahar Yadin and Matan Kleiner and Tomer Michaeli},
journal= {arXiv preprint arXiv:2211.16582},
year = {2023}
}
Comments
Updated for ICML 2023 and added the Appendix. Note that the images are lightly compressed. Visit our project page for uncompressed results: https://matankleiner.github.io/sinddm/