2 code implementations • 10 Apr 2024 • Xianlu Li, Nicolas Nadisic, Shaoguang Huang, Aleksandra Pižurica
By unfolding iterative optimization methods into neural networks, this approach offers enhanced interpretability and reliability compared to data-driven deep learning methods, and greater adaptability and generalization than model-based approaches.
no code implementations • 6 May 2023 • Haijin Zeng, JieZhang Cao, Kai Feng, Shaoguang Huang, Hongyan zhang, Hiep Luong, Wilfried Philips
However, model-based approaches rely on hand-crafted priors and hyperparameters, while learning-based methods are incapable of estimating the inherent degradation patterns and noise distributions in the imaging procedure, which could inform supervised learning.
no code implementations • 23 Mar 2023 • Haijin Zeng, Kai Feng, Shaoguang Huang, JieZhang Cao, Yongyong Chen, Hongyan zhang, Hiep Luong, Wilfried Philips
The advantage of Maformer is that it can leverage the MSFA information and non-local dependencies present in the data.
no code implementations • 23 Mar 2023 • Haijin Zeng, Kai Feng, JieZhang Cao, Shaoguang Huang, Yongqiang Zhao, Hiep Luong, Jan Aelterman, Wilfried Philips
DJRD includes a newly designed Quad Bayer remosaicing (QB-Re) block, integrated denoising modules based on Swin-transformer and multi-scale wavelet transform.
no code implementations • 27 Apr 2022 • Haijin Zeng, Shaoguang Huang, Yongyong Chen, Hiep Luong, Wilfried Philips
Based on this fact, we propose a novel TV regularization to simultaneously characterize the sparsity and low-rank priors of the gradient map (LRSTV).