Having spent some time reading over the two approaches to performing super-resolution i have decided that i am going to focus on multi-frame rather than single-frame enhancement. I selected the multi frame approach because i believe it will produce more robust results over a wider range of input images. One of the main limitations of the single-frame approach is that the process will only be effective if the database contains a high resolution image which is similar to the image which is trying to be enhanced.
The multi-frame approach on the other and uses the additional data which is contained in the extra input frames to interpolate the pixel values in the high resolution image, this allows the multi-frame approach to be applied to any input image, even if a similar image was not used during the design of the algorithm.
No comments:
Post a Comment