The following paper has been published in ITE Transactions on Media Technology and Applications.
- Jikai Li, Shogo Muramatsu, [Paper] Structured Deep Image Prior for Image Denoising with Interscale SURE-LET, ITE Transactions on Media Technology and Applications, 2025, Volume 13, Issue 1, Pages 187-199, Released on J-STAGE January 01, 2025, Online ISSN 2186-7364, https://doi.org/10.3169/mta.13.187, https://www.jstage.jst.go.jp/article/mta/13/1/13_187/_article/-char/en,
- Abstract:
This study develops a self-supervised image denoising technique that incorporates a structured deep image prior (DIP) approach with Stein’s unbiased risk estimator and linear expansion of thresholding (SURE-LET). Leveraging interscale and interchannel dependencies of images to develop a multichannel denoising approach. The original DIP, introduced by Ulyanov et al. in 2018, requires a random image as the input for restoration, offering an advantage of not requesting training data. However, the interpretability of the role of the network is limited, and challenges exist in customizing its architecture to incorporate domain knowledge. This work integrates SURE-LET with Monte Carlo computation into the DIP framework, providing the reason of the random image supply and shifting the focus from generator to restorer design, thus enabling the network structure of DIP to more easily reflect domain knowledge. The significance of the developed method is confirmed through denoising simulations using the Kodak image dataset.