Super-resolving a noisy image is a challenging problem, and needs special care as compared to the conventional super resolution approaches, when the power of noise is unknown. In this scenario, we propose an approach to super-resolve single noisy image by minimizing nuclear norm in a virtual sparse domain that tunes with the power of noise via parameter learning. The approach minimizes nuclear norm to explore the inherent low-rank structure of visual data, and is further augmented with coarse-to-fine information by adaptively re-aligning the data along the principal components of a dictionary in virtual sparse domain. The experimental results demonstrate the robustness of our approach across different powers of noise.
CITATION STYLE
Mandal, S., & Rajagopalan, A. N. (2018). Single noisy image super resolution by minimizing nuclear norm in virtual sparse domain. In Communications in Computer and Information Science (Vol. 841, pp. 163–176). Springer Verlag. https://doi.org/10.1007/978-981-13-0020-2_15
Mendeley helps you to discover research relevant for your work.