A novel solo dictionary learning method for single image super-resolution

Single image super-resolution (SR) reconstruction has become a hot branch of SR. In this paper, we propose a new method for single image SR using non-negative matrix factorization (NMF) and novel solo dictionary learning. Compared to the existing method, the introduction of NMF can generate global image more similar to ground truth image and the proposed solo dictionary learning can reconstruct image without retraining the dictionary when the zooming factor changes. Moreover, experimental results show that the proposed method has better effect in both subjective and objective image quality evaluation.