We present a supervised learning-based approach for subpixel motion estimation which is then used to perform video super-resolution. The novelty of this work is the formulation of the problem of subpixel motion estimation in a ranking framework. The ranking formulation is a variant of classification and regression formulation, in which the ordering present in class labels namely, the shift between patches is explicitly taken into account. Finally, we demonstrate the applicability of our approach on superresolving synthetically generated images with global subpixel shifts and enhancing real video frames by accounting for both local integer and subpixel shifts.

+More

classification and regression shift supervised learningbased approach ranking formulation subpixel motion estimation superresolving synthetically generated images local integer and subpixel shifts video superresolution patches

Nemanja Petrovic,Thomas S. Huang,Shyamsundar Rajaram,Mithun Das Gupta,.Ordinal Regression Based Subpixel Shift Estimation for Video Super-Resolution. 2007 (),.

Nemanja Petrovic,Thomas S. Huang,Shyamsundar Rajaram,Mithun Das Gupta,"Ordinal Regression Based Subpixel Shift Estimation for Video Super-Resolution" 2007

Nemanja Petrovic,Thomas S. Huang,Shyamsundar Rajaram,Mithun Das Gupta,"Ordinal Regression Based Subpixel Shift Estimation for Video Super-Resolution"