Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 8240-8257
DOI: 10.1109/tpami.2024.3432812 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von Tong Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 39-mal zitiert (Crossref) und nennt 93 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Image denoising is a fundamental problem in computational photography, where achieving high perception with low distortion is highly demanding. Current methods either struggle with perceptual quality or suffer from significant distortion. Recently, the emerging diffusion model has achieved state-of-the-art performance in various tasks and demonstrates great potential for image denoising. However, stimulating diffusion models for image denoising is not straightforward and requires solving several critical problems. For one thing, the input inconsistency hinders the connection between diffusion models and image denoising. For another, the content inconsistency between the generated image and the desired denoised image introduces distortion. To tackle these problems, we present a novel strategy called the Diffusion Model for Image Denoising (DMID) by understanding and rethinking the diffusion model from a denoising perspective. Our DMID strategy includes an adaptive embedding method that embeds the noisy image into a pre-trained unconditional diffusion model and an adaptive ensembling method that reduces distortion in the denoised image. Our DMID strategy achieves state-of-the-art performance on both distortion-based and perception-based metrics, for both Gaussian and real-world image denoising.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Li, T., Feng, H., Wang, L., Zhu, L., Xiong, Z., & Huang, H. (2024). Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 8240-8257. https://doi.org/10.1109/tpami.2024.3432812
Vancouver
Li T, Feng H, Wang L, Zhu L, Xiong Z, Huang H. Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):8240-8257. doi:10.1109/tpami.2024.3432812
BibTeX
@article{Li2024,
author = {Li, Tong and Feng, Hansen and Wang, Lizhi and Zhu, Lin and Xiong, Zhiwei and Huang, Hua},
title = {Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {12},
pages = {8240--8257},
doi = {10.1109/tpami.2024.3432812}
}
EUVIMED