no code implementations • 19 Nov 2023 • Zhenghao Pan, Haijin Zeng, JieZhang Cao, Kai Zhang, Yongyong Chen
Specifically, firstly, we employ a pre-trained diffusion model, which has been trained on a substantial corpus of RGB images, as the generative denoiser within the Plug-and-Play framework for the first time.
no code implementations • 5 Jul 2023 • Kai Feng, Yongqiang Zhao, Seong G. Kong, Haijin Zeng
This paper presents a deep learning-based spectral demosaicing technique trained in an unsupervised manner.
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, 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 • 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 • 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).
no code implementations • 3 Dec 2020 • Haijin Zeng
Low-rank tensor completion has been widely used in computer vision and machine learning.
no code implementations • 30 May 2020 • Haijin Zeng, Xiaozhen Xie, Jifeng Ning
Instead of traditional bandwise total variation, we use the SSTV regularization to simultaneously consider global spatial structure and spectral correlation of neighboring bands.
no code implementations • 28 May 2020 • Haijin Zeng, Xiaozhen Xie, Jifeng Ning
Higher-order low-rank tensor arises in many data processing applications and has attracted great interests.
no code implementations • 8 May 2020 • Haijin Zeng, Xiaozhen Xie, Jifeng Ning
From one aspect, local LR of HSIs is formulated using a non-convex $L_{\gamma}$-norm, which provides a closer approximation to the matrix rank than the traditional NN.
no code implementations • 19 Apr 2020 • Haijin Zeng, Xiaozhen Xie, Jifeng Ning
In this paper, we propose a novel model to recover a low-rank tensor by simultaneously performing double nuclear norm regularized low-rank matrix factorizations to the all-mode matricizations of the underlying tensor.