tag:blogger.com,1999:blog-19092890.post2503828658455242667..comments2024-03-28T15:26:27.432+02:00Comments on Image Sensors World: Kogakuin University Video Super-Resolution Said to Exceed Nyquist LimitVladimir Koifmanhttp://www.blogger.com/profile/01800020176563544699noreply@blogger.comBlogger4125tag:blogger.com,1999:blog-19092890.post-34657711935767624652015-11-23T16:03:12.918+02:002015-11-23T16:03:12.918+02:00That's what I was getting at with my previous ...That's what I was getting at with my previous comment, and the buzz in the title makes it sound like they've devised some magic to pull information that is lost out of thin air. Huge red herring.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-19092890.post-84406851279651045402015-11-22T20:43:11.727+02:002015-11-22T20:43:11.727+02:00Their papers talk about creating above-Nyquist fre...Their papers talk about creating above-Nyquist frequencies by making the edges steeper, and proceed by calling it "super-resolution", based on a naive idea that additional spatial frequencies equal higher image resolution. Sharpening is something that has been used in all cameras and TV sets for 60+ years. A sharpened "vertical" edge has almost infinite frequency spectrum, for sure, but image resolution is not improved, only acutance. Acutance can be changed post-capture, resolution is a much different story related to sampling in the image sensor. In contrast, there are methods of computational super-resolution that require heavy-duty image processing to extract additional image detail based on a variety of image priors, such as sparsity in certain mathematical domains, non-local self-similarity, simlarity across different image scales, and other image priors. The very fact that their publications never provide any objective measure of their "super-resolution" enhancement, such as PSNR relative to a ground truth high-resolution image, is peculiar. This kind of enhancement counts on subjective perception of increased sharpness while never increasing the actual image resolution. At best this is a misuse of the established terminology, or a plain misrepresentation.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-19092890.post-16335265139558858682015-11-22T11:42:22.791+02:002015-11-22T11:42:22.791+02:00That's great, but is it right? I can produce ...That's great, but is it right? I can produce results higher than Nyquist limit, too, simply by injecting in random data above the Nyquist limit. I would probably want to see a ground truth vs reconstructed and corresponding error at the high frequencies.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-19092890.post-54395128869348532812015-11-22T01:36:57.659+02:002015-11-22T01:36:57.659+02:00How is this different from the endless adaptive sh...How is this different from the endless adaptive sharpening algorithms already in use? What makes it unique?Anonymousnoreply@blogger.com