Efficient Conditional Diffusion Model with Probability Flow Sampling for Image Super-resolution
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (7) · 6862-6870
DOI: 10.1609/aaai.v38i7.28511 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Yutao Yuan und 1 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref).
Abstract (Originalsprache)
Image super-resolution is a fundamentally ill-posed problem because multiple valid high-resolution images exist for one low-resolution image. Super-resolution methods based on diffusion probabilistic models can deal with the ill-posed nature by learning the distribution of high-resolution images conditioned on low-resolution images, avoiding the problem of blurry images in PSNR-oriented methods. However, existing diffusion-based super-resolution methods have high time consumption with the use of iterative sampling, while the quality and consistency of generated images are less than ideal due to problems like color shifting. In this paper, we propose Efficient Conditional Diffusion Model with Probability Flow Sampling (ECDP) for image super-resolution. To reduce the time consumption, we design a continuous-time conditional diffusion model for image super-resolution, which enables the use of probability flow sampling for efficient generation. Additionally, to improve the consistency of generated images, we propose a hybrid parametrization for the denoiser network, which interpolates between the data-predicting parametrization and the noise-predicting parametrization for different noise scales. Moreover, we design an image quality loss as a complement to the score matching loss of diffusion models, further improving the consistency and quality of super-resolution. Extensive experiments on DIV2K, ImageNet, and CelebA demonstrate that our method achieves higher super-resolution quality than existing diffusion-based image super-resolution methods while having lower time consumption. Our code is available at https://github.com/Yuan-Yutao/ECDP.
Zitieren
APA
Yuan, Y., & Yuan, C. (2024). Efficient Conditional Diffusion Model with Probability Flow Sampling for Image Super-resolution. Proceedings of the AAAI Conference on Artificial Intelligence, 38(7), 6862-6870. https://doi.org/10.1609/aaai.v38i7.28511
Vancouver
Yuan Y, Yuan C. Efficient Conditional Diffusion Model with Probability Flow Sampling for Image Super-resolution. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(7):6862-6870. doi:10.1609/aaai.v38i7.28511
BibTeX
@article{Yuan2024,
author = {Yuan, Yutao and Yuan, Chun},
title = {Efficient Conditional Diffusion Model with Probability Flow Sampling for Image Super-resolution},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {7},
pages = {6862--6870},
doi = {10.1609/aaai.v38i7.28511}
}
EUVIMED