Qian Wang

TL;DR: The results show that the proposed ℓ 0TDL method outperforms other competing methods, such as total variation (TV) minimization, TV with low rank (TV+LR), and TDL methods.

TL;DR: Zhang et al. as mentioned in this paper proposed a non-local low-rank cube-based tensor factorization (NLCTF) method to enhance the capability of image feature extraction and spatial edge preservation.

TL;DR: A spectral CT reconstruction method, namely spatial-spectral cube matching frame (SSCMF), inspired by the following three facts, which shows that the SSCMF method outperforms the state-of-the-art algorithms, including the simultaneous algebraic reconstruction technique, total variation minimization,total variation plus low rank, and tensor dictionary learning.

TL;DR: This work establishes a locally linear relationship between the decomposed results ofDSCT and SSCT and proposes an optimization model for DSCT and develops an iterative method with image guided filtering based on the relative total variation regularization.

TL;DR: The numerical mouse, physical phantom and preclinical experiments are performed to evaluate the performance of the proposed DLIMD in material decomposition accuracy, material image edge preservation and feature recovery.