Single-Image Noise Level Estimation for Blind Denoising
By Xinhao Liu, Masayuki Tanaka, Masatoshi Okutomi. IEEE Transactions on Image Processing, 2013
427 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Media Technology
View Paper: https://www.semanticscholar.org/paper/3edfacb70e2bc70b498a25ca5f6e95ce63e74e85
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Lei Zhang
- Wangmeng Zuo
- Luc Van Gool
- Kai Zhang
- Ming-Hsuan Yang
- Chen Change Loy
- Radu Timofte
- Ling Shao
In Media Technology
- Lei Zhang
- Wangmeng Zuo
- Kai Zhang
- Shutao Li
- Xudong Kang
- Stamatios Lefkimmiatis
- Jun Yu Li
- Jon Atli Benediktsson
Citations in the corpus
- Quality Resilient Deep Neural Networks (2017, methodology): “Further improvements could be made by explicitly incorporating techniques to predict distortion type or level such as [17, 15].”
- Toward Convolutional Blind Denoising of Real Photographs (2018, methodology): “For AWGN, several PCAbased [48, 34, 9] methods have been developed for estimating noise standard deviation (SD.”
- Hyperspectral Anomaly Detection With Attribute and Edge-Preserving Filters (2017, methodology): “1 Furthermore, noisy bands in the original images have been removed using a recently published noisy level estimation method [36].”
- Deep learning for denoising (2018, background): “Noise estimation is used for reducing labor and uncertainty (Liu et al., 2013), which is still an approximate procedure.”
- Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising (2017, methodology): “In the case of real noisy images, the noise levels can be estimated via some noise estimation methods [31, 32].”
- Universal Denoising Networks : A Novel CNN Architecture for Image Denoising (2017, methodology): “Given that there are several methods available for estimating the standard deviation of the noise from the noisy input [13,29], we now have a good indication about the range of values that the parameter ε should lie in, as opposed to λ in the previous formulation.”
- Sparse Gradient Regularized Deep Retinex Network for Robust Low-Light Image Enhancement (2021, methodology): “Besides RRM [10], JED [11] and RetinexNet, other methods are pre-processed by BM3D [23] with the noise level estimated by [58].”