A nonconvex nonsmooth regularization method with structure tensor total variation.
Zhuo-Xu CuiQibin FanYichuan DongTong LiuPublished in: J. Vis. Commun. Image Represent. (2017)
Keyphrases
- structure tensor
- regularization method
- total variation
- image restoration
- convex optimization
- regularization term
- regularization methods
- inverse problems
- nonlinear diffusion
- anisotropic diffusion
- image denoising
- optical flow
- regularization parameter
- denoising
- edge preserving
- partial differential equations
- corner detection
- super resolution
- markov random field
- edge information
- positive definite
- augmented lagrangian
- objective function
- low rank
- human vision
- spatial structure
- blurred images
- global optimization
- image processing
- optimization problems
- diffusion process
- noisy images
- computer vision
- scale spaces
- image reconstruction
- diffusion tensor
- gaussian noise
- high quality