Hong Kong Applied Science and Technology Research Institute Company, Limited

Edmund Y Lam

Luhong Liang

King Hung Chiu

Embodiments of the present invention include apparatuses, systems and methods for multi-patch based super-resolution from a single video frame. Such embodiments include a scale-invariant self-similarity (SiSS) based super-resolution method. Instead of searching HR examples in a database or in LR image, the present embodiments may select the patches according to the SiSS characteristics of the patch itself, so that the computational complexity of the method may be reduced because there is not any search involved. To solve the problem of lack of relevant examples in natural images, the present embodiments may employ multi-shaped and multi-sized patches in HR image reconstruction. Additionally, embodiments may include steps for a hybrid weighing method for suppressing artifacts. Advantageously, certain embodiments of the method may be 10&#x2dc;1,000 times faster than the example based SR approaches using patch searching and can achieve comparable HR image quality.

Growing community of inventors

Hong Kong, China

Edmund Y Lam