Empirical filter designs generalize relationships inferred from training data to effect realistic solutions that conform well to the human visual system. Complex algorithms invol...
We study the low-level problem of predicting pixel intensities after subpixel image translations. This is a basic subroutine for image warping and super-resolution, and it has a c...
Interpolated images have data redundancy, and special correlation exists among neighboring pixels, which is a crucial clue in digital forensics. We design a neural network based f...
— The DCT-based JPEG standard is certainly one of the most successful applications of transform coding methods for still digital images. A commonly recognized disadvantage of the...
Ill-posed linear equations are pervasive in computer vision. A popular way to solve an ill-posed problem is regularization. In this paper, we propose a new criterion for designing ...