ResDiff: Combining CNN and Diffusion Model for Image Super-resolution
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (8) · 8975-8983
DOI: 10.1609/aaai.v38i8.28746 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Shuyao Shang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 133-mal zitiert (Crossref).
Abstract (Originalsprache)
Adapting the Diffusion Probabilistic Model (DPM) for direct image super-resolution is wasteful, given that a simple Convolutional Neural Network (CNN) can recover the main low-frequency content. Therefore, we present ResDiff, a novel Diffusion Probabilistic Model based on Residual structure for Single Image Super-Resolution (SISR). ResDiff utilizes a combination of a CNN, which restores primary low-frequency components, and a DPM, which predicts the residual between the ground-truth image and the CNN predicted image. In contrast to the common diffusion-based methods that directly use LR space to guide the noise towards HR space, ResDiff utilizes the CNN’s initial prediction to direct the noise towards the residual space between HR space and CNN-predicted space, which not only accelerates the generation process but also acquires superior sample quality. Additionally, a frequency-domain-based loss function for CNN is introduced to facilitate its restoration, and a frequency-domain guided diffusion is designed for DPM on behalf of predicting high-frequency details. The extensive experiments on multiple benchmark datasets demonstrate that ResDiff outperforms previous diffusion based methods in terms of shorter model convergence time, superior generation quality, and more diverse samples.
Zitieren
APA
Shang, S., Shan, Z., Liu, G., Wang, L., Wang, X., Zhang, Z., & Zhang, J. (2024). ResDiff: Combining CNN and Diffusion Model for Image Super-resolution. Proceedings of the AAAI Conference on Artificial Intelligence, 38(8), 8975-8983. https://doi.org/10.1609/aaai.v38i8.28746
Vancouver
Shang S, Shan Z, Liu G, Wang L, Wang X, Zhang Z, et al. ResDiff: Combining CNN and Diffusion Model for Image Super-resolution. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(8):8975-8983. doi:10.1609/aaai.v38i8.28746
BibTeX
@article{Shang2024,
author = {Shang, Shuyao and Shan, Zhengyang and Liu, Guangxing and Wang, LunQian and Wang, XingHua and Zhang, Zekai and Zhang, Jinglin},
title = {ResDiff: Combining CNN and Diffusion Model for Image Super-resolution},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {8},
pages = {8975--8983},
doi = {10.1609/aaai.v38i8.28746}
}
EUVIMED