Super Resolution of Quality Images through Sparse Representation

Sparse Representation Based Image Super‐resolution Using Large Patches

“…For brevity, we summarize some main notations in Table 1. Sparse representation based methods are widely used in the field of learningbased super-resolution [12,15,17] . An over-complete dictionary pair is important for these methods [18,19] .…”

“…A common assumption of these methods is sparse representation invariance [13] . Recent sparse representation based super-resolution methods [14,15] focus on learning an efficient dictionary pair. However, the patch size used in the above methods is relatively small, which leads to poor SR results when the magnification factor is large.…”