Curvature preserving image super-resolution with gradient-consistency-anisotropic-regularization prior

作者:

Highlights:

• Curvature preserving image super-resolution.

• Gradient-consistency-anisotropic-regularization prior.

• Adaptive de-convolution and curvature refinement.

• Preserving image details and recovering high frequency information.

• Natural-looking and artifact-free reconstruction.

摘要

•Curvature preserving image super-resolution.•Gradient-consistency-anisotropic-regularization prior.•Adaptive de-convolution and curvature refinement.•Preserving image details and recovering high frequency information.•Natural-looking and artifact-free reconstruction.

论文关键词:Adaptive de-convolution,Anisotropic regularization,Curvature preserving,Gradient consistency,Image super-resolution,Image up-sampling

论文评审过程:Received 23 December 2013, Revised 13 August 2014, Accepted 14 August 2014, Available online 23 August 2014.

论文官网地址:https://doi.org/10.1016/j.image.2014.08.002