IDEA-Net: Adaptive Dual Self-Attention Network for Single Image Denoising

Zheming Zuo, Xinyu Chen, Han Xu, Jie Li, wenjuan liao, zhixin yang, Shizheng Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

36 Downloads (Pure)

Abstract

Image denoising is a challenging task due to possible data bias and prediction variance. Existing approaches usually suffer from high computational cost. In this work, we propose an unsupervised image denoiser, dubbed as adaptIve Dual sElf-Attention Network (IDEA-Net), to handle these challenges. IDEA-Net benefits from a generatively learned image-wise dual self-attention region where the denoising process is enforced. Besides, IDEA-Net is not only robust to possible data bias but also helpful to reduce the prediction variance by applying a simplified encoder-decoder with Poisson dropout operations on a single noisy image merely. The proposed IDEA-Net demonstrated the outperformance on four benchmark datasets compared with other single-image-based learning and non-learning image denoisers. IDEA-Net also shows an appropriate choice to remove real-world noise in low-light and noisy scenes, which in turn, contribute to more accurate dark face detection. The source code is available at https://github. com/zhemingzuo/IDEA-Net.
Original languageEnglish
Title of host publicationProceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision
PublisherIEEE
Pages739-748
ISBN (Electronic)9781665458245
DOIs
Publication statusPublished - 15 Feb 2022
EventIEEE/CVF 2022 Winter Conference on Applications of Computer Vision - Waikoloa, United States
Duration: 4 Jan 20228 Feb 2022
https://wacv2022.thecvf.com/home

Publication series

NameIEEE Winter Applications and Computer Vision Workshops
PublisherIEEE
ISSN (Electronic)2690-621X

Conference

ConferenceIEEE/CVF 2022 Winter Conference on Applications of Computer Vision
Abbreviated titleWACV 2022
Country/TerritoryUnited States
CityWaikoloa
Period4/01/228/02/22
Internet address

Fingerprint

Dive into the research topics of 'IDEA-Net: Adaptive Dual Self-Attention Network for Single Image Denoising'. Together they form a unique fingerprint.

Cite this