The full form of VDSR is Very Deep Super Resolution
Very Deep Super Resolution (VDSR) is a deep learning approach for enlarging an image. It has 20 weight layers which is much deeper compared with SRCNN which only got 3 layers.
Sometimes, we only got a poor image and we want to have digital enlargement (zoom in), but the image gets blurred when zoomed in. This is because the conventional interpolation or enlargement of a small image to become a large image, will get a poor image quality. With VDSR, we can obtain a high-resolution (HR) image with high quality from a low resolution (LR) image.
VDSR
means
Very Deep Super ResolutionVery Deep Super Resolution" title="how to pronounce Very Deep Super Resolution"/>
Leave a Reply
You must be logged in to post a comment.