期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 29, 期 -, 页码 3927-3940出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2020.2965294
关键词
Image prior; real-world noisy image denoising; pyramid network; two-pathway unscented Kalman filter
资金
- National Natural Science Foundation of China [61673402, 61273270, 60802069, 61702117]
- Natural Science Foundation of Guangdong Province [2017A030311029, 2016B010123005, 2017B090909005]
- National Key R&D Program of China [2018YFB1601101, 2018YFB1601100]
- Science and Technology Program of Guangzhou of China [201704020180, 201604020024]
- Fundamental Research Funds for the Central Universities of China [17lgzd08]
Recently, image prior learning has emerged as an effective tool for image denoising, which exploits prior knowledge to obtain sparse coding models and utilize them to reconstruct the clean image from the noisy one. Albeit promising, these prior-learning based methods suffer from some limitations such as lack of adaptivity and failed attempts to improve performance and efficiency simultaneously. With the purpose of addressing these problems, in this paper, we propose a Pyramid Guided Filter Network (PGF-Net) integrated with pyramid-based neural network and Two-Pathway Unscented Kalman Filter (TP-UKF). The combination of pyramid network and TP-UKF is based on the consideration that the former enables our model to better exploit hierarchical and multi-scale features, while the latter can guide the network to produce an improved (a posteriori) estimation of the denoising results with fine-scale image details. Through synthesizing the respective advantages of pyramid network and TP-UKF, our proposed architecture, in stark contrast to prior learning methods, is able to decompose the image denoising task into a series of more manageable stages and adaptively eliminate the noise on real images in an efficient manner. We conduct extensive experiments and show that our PGF-Net achieves notable improvement on visual perceptual quality and higher computational efficiency compared to state-of-the-art methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据