PROJECT TITLE :

Low-Rank Matrix Decomposition Help Internal and External Learnings for Super-Resolution - 2018

ABSTRACT:

Wisely utilizing the internal and external learning methods is a new challenge in super-resolution problem. To address this issue, we tend to analyze the attributes of two methodologies and realize 2 observations of their recovered details: one) they're complementary in each feature house and image plane and a pair of) they distribute sparsely within the spatial house. These inspire us to propose a coffee-rank resolution which effectively integrates two learning methods and then achieves a superior result. To fit this solution, the interior learning methodology and the external learning method are tailored to supply multiple preliminary results. Our theoretical analysis and experiment prove that the proposed low-rank solution does not require massive inputs to ensure the performance, and thereby simplifying the planning of two learning strategies for the solution. Intensive experiments show the proposed solution improves the one learning method in both qualitative and quantitative assessments. Surprisingly, it shows additional superior capability on noisy images and outperforms state-of-the-art methods.