Image Upsampling using L3

Introduction

Image resolution enhancement is an important problem with many practical applications. It enables efficient image compression for storage and transfer over a network. It also offers the possibility of enhancing an image captured using a lower resolution camera before displaying it on a bigger or higher resolution screen. With the ubiquitous cellphone cameras and high resolution displays nowadays, having a fast and accurate technique to upsample a low resolution image has become quite important.

Background

L3 stands for Linear, Local and Learned. In a real world image there is usually a strong correlation between the neighboring pixels. L3 uses this correlation to generate a higher resolution image from the lower resolution image pixels. It uses machine learning to efficiently learn this dependence present in the data. L3 consists of two steps: Rendering and Learning. The rendering step adaptively selects from a stored table of linear transforms to convert the low resolution pixel data into higher resolution image pixels. The training step learns and stores these linear transforms used in the rendering step. Rendering In the rendering step, a N*N patch, n(x,y,p) is selected, centered around the pixel (x,y) in the low resolution sensor data. Then we classify the pixel into one of the predefined classes, c, based on the mean intensity level, pixel color and contrast. Finally, we apply the appropriate linear transform, T(c, r), for the class c and output channel r. The computation is repeated independently for each pixel in the low resolution sensor image. Training

We use the following two approaches based on L3 to enhance the spatial resolution of an input image.

Appendix

You can write math equations as follows: $y=x+5$

You can include images as follows (you will need to upload the image first using the toolbox on the left bar, using the "Upload file" link).